remarkable-linux/fs/proc/root.c

239 lines
5.1 KiB
C
Raw Normal View History

/*
* linux/fs/proc/root.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* proc root directory handling functions
*/
#include <asm/uaccess.h>
#include <linux/errno.h>
#include <linux/time.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/bitops.h>
#include <linux/smp_lock.h>
#include <linux/mount.h>
#include <linux/pid_namespace.h>
#include "internal.h"
struct proc_dir_entry *proc_bus, *proc_root_fs, *proc_root_driver;
static int proc_test_super(struct super_block *sb, void *data)
{
return sb->s_fs_info == data;
}
static int proc_set_super(struct super_block *sb, void *data)
{
struct pid_namespace *ns;
ns = (struct pid_namespace *)data;
sb->s_fs_info = get_pid_ns(ns);
return set_anon_super(sb, NULL);
}
[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 03:02:57 -06:00
static int proc_get_sb(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data, struct vfsmount *mnt)
{
int err;
struct super_block *sb;
struct pid_namespace *ns;
struct proc_inode *ei;
if (proc_mnt) {
/* Seed the root directory with a pid so it doesn't need
* to be special in base.c. I would do this earlier but
* the only task alive when /proc is mounted the first time
* is the init_task and it doesn't have any pids.
*/
ei = PROC_I(proc_mnt->mnt_sb->s_root->d_inode);
if (!ei->pid)
ei->pid = find_get_pid(1);
}
if (flags & MS_KERNMOUNT)
ns = (struct pid_namespace *)data;
else
ns = current->nsproxy->pid_ns;
sb = sget(fs_type, proc_test_super, proc_set_super, ns);
if (IS_ERR(sb))
return PTR_ERR(sb);
if (!sb->s_root) {
sb->s_flags = flags;
err = proc_fill_super(sb);
if (err) {
up_write(&sb->s_umount);
deactivate_super(sb);
return err;
}
ei = PROC_I(sb->s_root->d_inode);
if (!ei->pid) {
rcu_read_lock();
ei->pid = get_pid(find_pid_ns(1, ns));
rcu_read_unlock();
}
sb->s_flags |= MS_ACTIVE;
ns->proc_mnt = mnt;
}
return simple_set_mnt(mnt, sb);
}
static void proc_kill_sb(struct super_block *sb)
{
struct pid_namespace *ns;
ns = (struct pid_namespace *)sb->s_fs_info;
kill_anon_super(sb);
put_pid_ns(ns);
}
proc: fix NULL ->i_fop oops proc_kill_inodes() can clear ->i_fop in the middle of vfs_readdir resulting in NULL dereference during "file->f_op->readdir(file, buf, filler)". The solution is to remove proc_kill_inodes() completely: a) we don't have tricky modules implementing their tricky readdir hooks which could keeping this revoke from hell. b) In a situation when module is gone but PDE still alive, standard readdir will return only "." and "..", because pde->next was cleared by remove_proc_entry(). c) the race proc_kill_inode() destined to prevent is not completely fixed, just race window made smaller, because vfs_readdir() is run without sb_lock held and without file_list_lock held. Effectively, ->i_fop is cleared at random moment, which can't fix properly anything. BUG: unable to handle kernel NULL pointer dereference at virtual address 00000018 printing eip: c1061205 *pdpt = 0000000005b22001 *pde = 0000000000000000 Oops: 0000 [#1] PREEMPT SMP Modules linked in: foo af_packet ipv6 cpufreq_ondemand loop serio_raw sr_mod k8temp cdrom hwmon amd_rng Pid: 2033, comm: find Not tainted (2.6.24-rc1-b1d08ac064268d0ae2281e98bf5e82627e0f0c56 #2) EIP: 0060:[<c1061205>] EFLAGS: 00010246 CPU: 0 EIP is at vfs_readdir+0x47/0x74 EAX: c6b6a780 EBX: 00000000 ECX: c1061040 EDX: c5decf94 ESI: c6b6a780 EDI: fffffffe EBP: c9797c54 ESP: c5decf78 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 Process find (pid: 2033, ti=c5dec000 task=c64bba90 task.ti=c5dec000) Stack: c5decf94 c1061040 fffffff7 0805ffbc 00000000 c6b6a780 c1061295 0805ffbc 00000000 00000400 00000000 00000004 0805ffbc 4588eff4 c5dec000 c10026ba 00000004 0805ffbc 00000400 0805ffbc 4588eff4 bfdc6c70 000000dc 0000007b Call Trace: [<c1061040>] filldir64+0x0/0xc5 [<c1061295>] sys_getdents64+0x63/0xa5 [<c10026ba>] sysenter_past_esp+0x5f/0x85 ======================= Code: 49 83 78 18 00 74 43 8d 6b 74 bf fe ff ff ff 89 e8 e8 b8 c0 12 00 f6 83 2c 01 00 00 10 75 22 8b 5e 10 8b 4c 24 04 89 f0 8b 14 24 <ff> 53 18 f6 46 1a 04 89 c7 75 0b 8b 56 0c 8b 46 08 e8 c8 66 00 EIP: [<c1061205>] vfs_readdir+0x47/0x74 SS:ESP 0068:c5decf78 hch: "Nice, getting rid of this is a very good step formwards. Unfortunately we have another copy of this junk in security/selinux/selinuxfs.c:sel_remove_entries() which would need the same treatment." Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru> Acked-by: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: James Morris <jmorris@namei.org> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-11-28 17:21:23 -07:00
static struct file_system_type proc_fs_type = {
.name = "proc",
.get_sb = proc_get_sb,
.kill_sb = proc_kill_sb,
};
void __init proc_root_init(void)
{
int err = proc_init_inodecache();
if (err)
return;
err = register_filesystem(&proc_fs_type);
if (err)
return;
proc_mnt = kern_mount_data(&proc_fs_type, &init_pid_ns);
err = PTR_ERR(proc_mnt);
if (IS_ERR(proc_mnt)) {
unregister_filesystem(&proc_fs_type);
return;
}
proc_misc_init();
proc_net_init();
#ifdef CONFIG_SYSVIPC
proc_mkdir("sysvipc", NULL);
#endif
proc_root_fs = proc_mkdir("fs", NULL);
proc_root_driver = proc_mkdir("driver", NULL);
proc_mkdir("fs/nfsd", NULL); /* somewhere for the nfsd filesystem to be mounted */
#if defined(CONFIG_SUN_OPENPROMFS) || defined(CONFIG_SUN_OPENPROMFS_MODULE)
/* just give it a mountpoint */
proc_mkdir("openprom", NULL);
#endif
proc_tty_init();
#ifdef CONFIG_PROC_DEVICETREE
proc_device_tree_init();
#endif
proc_bus = proc_mkdir("bus", NULL);
proc_sys_init();
}
static int proc_root_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat
)
{
generic_fillattr(dentry->d_inode, stat);
stat->nlink = proc_root.nlink + nr_processes();
return 0;
}
static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, struct nameidata *nd)
{
if (!proc_lookup(dir, dentry, nd)) {
return NULL;
}
return proc_pid_lookup(dir, dentry, nd);
}
static int proc_root_readdir(struct file * filp,
void * dirent, filldir_t filldir)
{
unsigned int nr = filp->f_pos;
int ret;
lock_kernel();
if (nr < FIRST_PROCESS_ENTRY) {
int error = proc_readdir(filp, dirent, filldir);
if (error <= 0) {
unlock_kernel();
return error;
}
filp->f_pos = FIRST_PROCESS_ENTRY;
}
unlock_kernel();
ret = proc_pid_readdir(filp, dirent, filldir);
return ret;
}
/*
* The root /proc directory is special, as it has the
* <pid> directories. Thus we don't use the generic
* directory handling functions for that..
*/
static const struct file_operations proc_root_operations = {
.read = generic_read_dir,
.readdir = proc_root_readdir,
};
/*
* proc root can do almost nothing..
*/
static const struct inode_operations proc_root_inode_operations = {
.lookup = proc_root_lookup,
.getattr = proc_root_getattr,
};
/*
* This is the root "inode" in the /proc tree..
*/
struct proc_dir_entry proc_root = {
.low_ino = PROC_ROOT_INO,
.namelen = 5,
.name = "/proc",
.mode = S_IFDIR | S_IRUGO | S_IXUGO,
.nlink = 2,
.proc_iops = &proc_root_inode_operations,
.proc_fops = &proc_root_operations,
.parent = &proc_root,
};
int pid_ns_prepare_proc(struct pid_namespace *ns)
{
struct vfsmount *mnt;
mnt = kern_mount_data(&proc_fs_type, ns);
if (IS_ERR(mnt))
return PTR_ERR(mnt);
return 0;
}
void pid_ns_release_proc(struct pid_namespace *ns)
{
mntput(ns->proc_mnt);
}
EXPORT_SYMBOL(proc_symlink);
EXPORT_SYMBOL(proc_mkdir);
EXPORT_SYMBOL(create_proc_entry);
EXPORT_SYMBOL(remove_proc_entry);
EXPORT_SYMBOL(proc_root);
EXPORT_SYMBOL(proc_root_fs);
EXPORT_SYMBOL(proc_bus);
EXPORT_SYMBOL(proc_root_driver);