linux/fs/jffs2/super.c

440 lines
10 KiB
C
Raw Normal View History

/*
* JFFS2 -- Journalling Flash File System, Version 2.
*
* Copyright © 2001-2007 Red Hat, Inc.
*
* Created by David Woodhouse <dwmw2@infradead.org>
*
* For licensing information, see the file 'LICENCE' in this directory.
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/fs.h>
#include <linux/err.h>
#include <linux/mount.h>
#include <linux/parser.h>
#include <linux/jffs2.h>
#include <linux/pagemap.h>
#include <linux/mtd/super.h>
#include <linux/ctype.h>
#include <linux/namei.h>
#include <linux/seq_file.h>
#include <linux/exportfs.h>
#include "compr.h"
#include "nodelist.h"
static void jffs2_put_super(struct super_block *);
static struct kmem_cache *jffs2_inode_cachep;
static struct inode *jffs2_alloc_inode(struct super_block *sb)
{
struct jffs2_inode_info *f;
f = kmem_cache_alloc(jffs2_inode_cachep, GFP_KERNEL);
if (!f)
return NULL;
return &f->vfs_inode;
}
2011-01-07 06:49:49 +00:00
static void jffs2_i_callback(struct rcu_head *head)
{
2011-01-07 06:49:49 +00:00
struct inode *inode = container_of(head, struct inode, i_rcu);
kmem_cache_free(jffs2_inode_cachep, JFFS2_INODE_INFO(inode));
}
2011-01-07 06:49:49 +00:00
static void jffs2_destroy_inode(struct inode *inode)
{
call_rcu(&inode->i_rcu, jffs2_i_callback);
}
static void jffs2_i_init_once(void *foo)
{
struct jffs2_inode_info *f = foo;
mutex_init(&f->sem);
inode_init_once(&f->vfs_inode);
}
static const char *jffs2_compr_name(unsigned int compr)
{
switch (compr) {
case JFFS2_COMPR_MODE_NONE:
return "none";
#ifdef CONFIG_JFFS2_LZO
case JFFS2_COMPR_MODE_FORCELZO:
return "lzo";
#endif
#ifdef CONFIG_JFFS2_ZLIB
case JFFS2_COMPR_MODE_FORCEZLIB:
return "zlib";
#endif
default:
/* should never happen; programmer error */
WARN_ON(1);
return "";
}
}
static int jffs2_show_options(struct seq_file *s, struct dentry *root)
{
struct jffs2_sb_info *c = JFFS2_SB_INFO(root->d_sb);
struct jffs2_mount_opts *opts = &c->mount_opts;
if (opts->override_compr)
seq_printf(s, ",compr=%s", jffs2_compr_name(opts->compr));
if (opts->rp_size)
seq_printf(s, ",rp_size=%u", opts->rp_size / 1024);
return 0;
}
static int jffs2_sync_fs(struct super_block *sb, int wait)
{
struct jffs2_sb_info *c = JFFS2_SB_INFO(sb);
#ifdef CONFIG_JFFS2_FS_WRITEBUFFER
cancel_delayed_work_sync(&c->wbuf_dwork);
#endif
mutex_lock(&c->alloc_sem);
jffs2_flush_wbuf_pad(c);
mutex_unlock(&c->alloc_sem);
return 0;
}
static struct inode *jffs2_nfs_get_inode(struct super_block *sb, uint64_t ino,
uint32_t generation)
{
/* We don't care about i_generation. We'll destroy the flash
before we start re-using inode numbers anyway. And even
if that wasn't true, we'd have other problems...*/
return jffs2_iget(sb, ino);
}
static struct dentry *jffs2_fh_to_dentry(struct super_block *sb, struct fid *fid,
int fh_len, int fh_type)
{
return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
jffs2_nfs_get_inode);
}
static struct dentry *jffs2_fh_to_parent(struct super_block *sb, struct fid *fid,
int fh_len, int fh_type)
{
return generic_fh_to_parent(sb, fid, fh_len, fh_type,
jffs2_nfs_get_inode);
}
static struct dentry *jffs2_get_parent(struct dentry *child)
{
struct jffs2_inode_info *f;
uint32_t pino;
VFS: (Scripted) Convert S_ISLNK/DIR/REG(dentry->d_inode) to d_is_*(dentry) Convert the following where appropriate: (1) S_ISLNK(dentry->d_inode) to d_is_symlink(dentry). (2) S_ISREG(dentry->d_inode) to d_is_reg(dentry). (3) S_ISDIR(dentry->d_inode) to d_is_dir(dentry). This is actually more complicated than it appears as some calls should be converted to d_can_lookup() instead. The difference is whether the directory in question is a real dir with a ->lookup op or whether it's a fake dir with a ->d_automount op. In some circumstances, we can subsume checks for dentry->d_inode not being NULL into this, provided we the code isn't in a filesystem that expects d_inode to be NULL if the dirent really *is* negative (ie. if we're going to use d_inode() rather than d_backing_inode() to get the inode pointer). Note that the dentry type field may be set to something other than DCACHE_MISS_TYPE when d_inode is NULL in the case of unionmount, where the VFS manages the fall-through from a negative dentry to a lower layer. In such a case, the dentry type of the negative union dentry is set to the same as the type of the lower dentry. However, if you know d_inode is not NULL at the call site, then you can use the d_is_xxx() functions even in a filesystem. There is one further complication: a 0,0 chardev dentry may be labelled DCACHE_WHITEOUT_TYPE rather than DCACHE_SPECIAL_TYPE. Strictly, this was intended for special directory entry types that don't have attached inodes. The following perl+coccinelle script was used: use strict; my @callers; open($fd, 'git grep -l \'S_IS[A-Z].*->d_inode\' |') || die "Can't grep for S_ISDIR and co. callers"; @callers = <$fd>; close($fd); unless (@callers) { print "No matches\n"; exit(0); } my @cocci = ( '@@', 'expression E;', '@@', '', '- S_ISLNK(E->d_inode->i_mode)', '+ d_is_symlink(E)', '', '@@', 'expression E;', '@@', '', '- S_ISDIR(E->d_inode->i_mode)', '+ d_is_dir(E)', '', '@@', 'expression E;', '@@', '', '- S_ISREG(E->d_inode->i_mode)', '+ d_is_reg(E)' ); my $coccifile = "tmp.sp.cocci"; open($fd, ">$coccifile") || die $coccifile; print($fd "$_\n") || die $coccifile foreach (@cocci); close($fd); foreach my $file (@callers) { chomp $file; print "Processing ", $file, "\n"; system("spatch", "--sp-file", $coccifile, $file, "--in-place", "--no-show-diff") == 0 || die "spatch failed"; } [AV: overlayfs parts skipped] Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2015-01-29 12:02:35 +00:00
BUG_ON(!d_is_dir(child));
f = JFFS2_INODE_INFO(d_inode(child));
pino = f->inocache->pino_nlink;
JFFS2_DEBUG("Parent of directory ino #%u is #%u\n",
f->inocache->ino, pino);
return d_obtain_alias(jffs2_iget(child->d_sb, pino));
}
static const struct export_operations jffs2_export_ops = {
.get_parent = jffs2_get_parent,
.fh_to_dentry = jffs2_fh_to_dentry,
.fh_to_parent = jffs2_fh_to_parent,
};
/*
* JFFS2 mount options.
*
* Opt_override_compr: override default compressor
* Opt_rp_size: size of reserved pool in KiB
* Opt_err: just end of array marker
*/
enum {
Opt_override_compr,
Opt_rp_size,
Opt_err,
};
static const match_table_t tokens = {
{Opt_override_compr, "compr=%s"},
{Opt_rp_size, "rp_size=%u"},
{Opt_err, NULL},
};
static int jffs2_parse_options(struct jffs2_sb_info *c, char *data)
{
substring_t args[MAX_OPT_ARGS];
char *p, *name;
unsigned int opt;
if (!data)
return 0;
while ((p = strsep(&data, ","))) {
int token;
if (!*p)
continue;
token = match_token(p, tokens, args);
switch (token) {
case Opt_override_compr:
name = match_strdup(&args[0]);
if (!name)
return -ENOMEM;
if (!strcmp(name, "none"))
c->mount_opts.compr = JFFS2_COMPR_MODE_NONE;
#ifdef CONFIG_JFFS2_LZO
else if (!strcmp(name, "lzo"))
c->mount_opts.compr = JFFS2_COMPR_MODE_FORCELZO;
#endif
#ifdef CONFIG_JFFS2_ZLIB
else if (!strcmp(name, "zlib"))
c->mount_opts.compr =
JFFS2_COMPR_MODE_FORCEZLIB;
#endif
else {
pr_err("Error: unknown compressor \"%s\"\n",
name);
kfree(name);
return -EINVAL;
}
kfree(name);
c->mount_opts.override_compr = true;
break;
case Opt_rp_size:
if (match_int(&args[0], &opt))
return -EINVAL;
opt *= 1024;
if (opt > c->mtd->size) {
pr_warn("Too large reserve pool specified, max "
"is %llu KB\n", c->mtd->size / 1024);
return -EINVAL;
}
c->mount_opts.rp_size = opt;
break;
default:
pr_err("Error: unrecognized mount option '%s' or missing value\n",
p);
return -EINVAL;
}
}
return 0;
}
static int jffs2_remount_fs(struct super_block *sb, int *flags, char *data)
{
struct jffs2_sb_info *c = JFFS2_SB_INFO(sb);
int err;
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 14:14:33 +00:00
sync_filesystem(sb);
err = jffs2_parse_options(c, data);
if (err)
return -EINVAL;
return jffs2_do_remount_fs(sb, flags, data);
}
static const struct super_operations jffs2_super_operations =
{
.alloc_inode = jffs2_alloc_inode,
.destroy_inode =jffs2_destroy_inode,
.put_super = jffs2_put_super,
.statfs = jffs2_statfs,
.remount_fs = jffs2_remount_fs,
.evict_inode = jffs2_evict_inode,
.dirty_inode = jffs2_dirty_inode,
.show_options = jffs2_show_options,
.sync_fs = jffs2_sync_fs,
};
/*
* fill in the superblock
*/
static int jffs2_fill_super(struct super_block *sb, void *data, int silent)
{
struct jffs2_sb_info *c;
int ret;
jffs2_dbg(1, "jffs2_get_sb_mtd():"
" New superblock for device %d (\"%s\")\n",
sb->s_mtd->index, sb->s_mtd->name);
c = kzalloc(sizeof(*c), GFP_KERNEL);
if (!c)
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 09:02:57 +00:00
return -ENOMEM;
c->mtd = sb->s_mtd;
c->os_priv = sb;
sb->s_fs_info = c;
ret = jffs2_parse_options(c, data);
if (ret) {
kfree(c);
return -EINVAL;
}
/* Initialize JFFS2 superblock locks, the further initialization will
* be done later */
mutex_init(&c->alloc_sem);
mutex_init(&c->erase_free_sem);
init_waitqueue_head(&c->erase_wait);
init_waitqueue_head(&c->inocache_wq);
spin_lock_init(&c->erase_completion_lock);
spin_lock_init(&c->inocache_lock);
sb->s_op = &jffs2_super_operations;
sb->s_export_op = &jffs2_export_ops;
sb->s_flags = sb->s_flags | MS_NOATIME;
sb->s_xattr = jffs2_xattr_handlers;
#ifdef CONFIG_JFFS2_FS_POSIX_ACL
sb->s_flags |= MS_POSIXACL;
#endif
ret = jffs2_do_fill_super(sb, data, silent);
return ret;
}
static struct dentry *jffs2_mount(struct file_system_type *fs_type,
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 09:02:57 +00:00
int flags, const char *dev_name,
void *data)
{
return mount_mtd(fs_type, flags, dev_name, data, jffs2_fill_super);
}
static void jffs2_put_super (struct super_block *sb)
{
struct jffs2_sb_info *c = JFFS2_SB_INFO(sb);
jffs2_dbg(2, "%s()\n", __func__);
mutex_lock(&c->alloc_sem);
jffs2_flush_wbuf_pad(c);
mutex_unlock(&c->alloc_sem);
jffs2_sum_exit(c);
jffs2_free_ino_caches(c);
jffs2_free_raw_node_refs(c);
kvfree(c->blocks);
jffs2_flash_cleanup(c);
kfree(c->inocache_list);
jffs2_clear_xattr_subsystem(c);
mtd_sync(c->mtd);
jffs2_dbg(1, "%s(): returning\n", __func__);
}
static void jffs2_kill_sb(struct super_block *sb)
{
struct jffs2_sb_info *c = JFFS2_SB_INFO(sb);
if (!(sb->s_flags & MS_RDONLY))
jffs2_stop_garbage_collect_thread(c);
kill_mtd_super(sb);
kfree(c);
}
static struct file_system_type jffs2_fs_type = {
.owner = THIS_MODULE,
.name = "jffs2",
.mount = jffs2_mount,
.kill_sb = jffs2_kill_sb,
};
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 03:39:14 +00:00
MODULE_ALIAS_FS("jffs2");
static int __init init_jffs2_fs(void)
{
int ret;
/* Paranoia checks for on-medium structures. If we ask GCC
to pack them with __attribute__((packed)) then it _also_
assumes that they're not aligned -- so it emits crappy
code on some architectures. Ideally we want an attribute
which means just 'no padding', without the alignment
thing. But GCC doesn't have that -- we have to just
hope the structs are the right sizes, instead. */
BUILD_BUG_ON(sizeof(struct jffs2_unknown_node) != 12);
BUILD_BUG_ON(sizeof(struct jffs2_raw_dirent) != 40);
BUILD_BUG_ON(sizeof(struct jffs2_raw_inode) != 68);
BUILD_BUG_ON(sizeof(struct jffs2_raw_summary) != 32);
pr_info("version 2.2."
#ifdef CONFIG_JFFS2_FS_WRITEBUFFER
" (NAND)"
#endif
#ifdef CONFIG_JFFS2_SUMMARY
" (SUMMARY) "
#endif
" © 2001-2006 Red Hat, Inc.\n");
jffs2_inode_cachep = kmem_cache_create("jffs2_i",
sizeof(struct jffs2_inode_info),
0, (SLAB_RECLAIM_ACCOUNT|
2016-01-14 23:18:21 +00:00
SLAB_MEM_SPREAD|SLAB_ACCOUNT),
jffs2_i_init_once);
if (!jffs2_inode_cachep) {
pr_err("error: Failed to initialise inode cache\n");
return -ENOMEM;
}
ret = jffs2_compressors_init();
if (ret) {
pr_err("error: Failed to initialise compressors\n");
goto out;
}
ret = jffs2_create_slab_caches();
if (ret) {
pr_err("error: Failed to initialise slab caches\n");
goto out_compressors;
}
ret = register_filesystem(&jffs2_fs_type);
if (ret) {
pr_err("error: Failed to register filesystem\n");
goto out_slab;
}
return 0;
out_slab:
jffs2_destroy_slab_caches();
out_compressors:
jffs2_compressors_exit();
out:
kmem_cache_destroy(jffs2_inode_cachep);
return ret;
}
static void __exit exit_jffs2_fs(void)
{
unregister_filesystem(&jffs2_fs_type);
jffs2_destroy_slab_caches();
jffs2_compressors_exit();
/*
* Make sure all delayed rcu free inodes are flushed before we
* destroy cache.
*/
rcu_barrier();
kmem_cache_destroy(jffs2_inode_cachep);
}
module_init(init_jffs2_fs);
module_exit(exit_jffs2_fs);
MODULE_DESCRIPTION("The Journalling Flash File System, v2");
MODULE_AUTHOR("Red Hat, Inc.");
MODULE_LICENSE("GPL"); // Actually dual-licensed, but it doesn't matter for
// the sake of this tag. It's Free Software.