kernel_optimize_test/fs/proc/root.c
Alexey Dobriyan 5a622f2d0f proc: fix proc_dir_entry refcounting
Creating PDEs with refcount 0 and "deleted" flag has problems (see below).
Switch to usual scheme:
* PDE is created with refcount 1
* every de_get does +1
* every de_put() and remove_proc_entry() do -1
* once refcount reaches 0, PDE is freed.

This elegantly fixes at least two following races (both observed) without
introducing new locks, without abusing old locks, without spreading
lock_kernel():

1) PDE leak

remove_proc_entry			de_put
-----------------			------
			[refcnt = 1]
if (atomic_read(&de->count) == 0)
					if (atomic_dec_and_test(&de->count))
						if (de->deleted)
							/* also not taken! */
							free_proc_entry(de);
else
	de->deleted = 1;
		[refcount=0, deleted=1]

2) use after free

remove_proc_entry			de_put
-----------------			------
			[refcnt = 1]

					if (atomic_dec_and_test(&de->count))
if (atomic_read(&de->count) == 0)
	free_proc_entry(de);
						/* boom! */
						if (de->deleted)
							free_proc_entry(de);

BUG: unable to handle kernel paging request at virtual address 6b6b6b6b
printing eip: c10acdda *pdpt = 00000000338f8001 *pde = 0000000000000000
Oops: 0000 [#1] PREEMPT SMP
Modules linked in: af_packet ipv6 cpufreq_ondemand loop serio_raw psmouse k8temp hwmon sr_mod cdrom
Pid: 23161, comm: cat Not tainted (2.6.24-rc2-8c0863403f109a43d7000b4646da4818220d501f #4)
EIP: 0060:[<c10acdda>] EFLAGS: 00210097 CPU: 1
EIP is at strnlen+0x6/0x18
EAX: 6b6b6b6b EBX: 6b6b6b6b ECX: 6b6b6b6b EDX: fffffffe
ESI: c128fa3b EDI: f380bf34 EBP: ffffffff ESP: f380be44
 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068
Process cat (pid: 23161, ti=f380b000 task=f38f2570 task.ti=f380b000)
Stack: c10ac4f0 00000278 c12ce000 f43cd2a8 00000163 00000000 7da86067 00000400
       c128fa20 00896b18 f38325a8 c128fe20 ffffffff 00000000 c11f291e 00000400
       f75be300 c128fa20 f769c9a0 c10ac779 f380bf34 f7bfee70 c1018e6b f380bf34
Call Trace:
 [<c10ac4f0>] vsnprintf+0x2ad/0x49b
 [<c10ac779>] vscnprintf+0x14/0x1f
 [<c1018e6b>] vprintk+0xc5/0x2f9
 [<c10379f1>] handle_fasteoi_irq+0x0/0xab
 [<c1004f44>] do_IRQ+0x9f/0xb7
 [<c117db3b>] preempt_schedule_irq+0x3f/0x5b
 [<c100264e>] need_resched+0x1f/0x21
 [<c10190ba>] printk+0x1b/0x1f
 [<c107c8ad>] de_put+0x3d/0x50
 [<c107c8f8>] proc_delete_inode+0x38/0x41
 [<c107c8c0>] proc_delete_inode+0x0/0x41
 [<c1066298>] generic_delete_inode+0x5e/0xc6
 [<c1065aa9>] iput+0x60/0x62
 [<c1063c8e>] d_kill+0x2d/0x46
 [<c1063fa9>] dput+0xdc/0xe4
 [<c10571a1>] __fput+0xb0/0xcd
 [<c1054e49>] filp_close+0x48/0x4f
 [<c1055ee9>] sys_close+0x67/0xa5
 [<c10026b6>] sysenter_past_esp+0x5f/0x85
=======================
Code: c9 74 0c f2 ae 74 05 bf 01 00 00 00 4f 89 fa 5f 89 d0 c3 85 c9 57 89 c7 89 d0 74 05 f2 ae 75 01 4f 89 f8 5f c3 89 c1 89 c8 eb 06 <80> 38 00 74 07 40 4a 83 fa ff 75 f4 29 c8 c3 90 90 90 57 83 c9
EIP: [<c10acdda>] strnlen+0x6/0x18 SS:ESP 0068:f380be44

Also, remove broken usage of ->deleted from reiserfs: if sget() succeeds,
module is already pinned and remove_proc_entry() can't happen => nobody
can mark PDE deleted.

Dummy proc root in netns code is not marked with refcount 1. AFAICS, we
never get it, it's just for proper /proc/net removal. I double checked
CLONE_NETNS continues to work.

Patch survives many hours of modprobe/rmmod/cat loops without new bugs
which can be attributed to refcounting.

Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru>
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>
2007-12-05 09:21:20 -08:00

240 lines
5.1 KiB
C

/*
* 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);
}
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);
}
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,
.count = ATOMIC_INIT(1),
.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);