kernel_optimize_test/fs/proc/inode.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

475 lines
10 KiB
C

/*
* linux/fs/proc/inode.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/time.h>
#include <linux/proc_fs.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/stat.h>
#include <linux/completion.h>
#include <linux/poll.h>
#include <linux/file.h>
#include <linux/limits.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/smp_lock.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include "internal.h"
struct proc_dir_entry *de_get(struct proc_dir_entry *de)
{
if (de)
atomic_inc(&de->count);
return de;
}
/*
* Decrements the use count and checks for deferred deletion.
*/
void de_put(struct proc_dir_entry *de)
{
if (de) {
lock_kernel();
if (!atomic_read(&de->count)) {
printk("de_put: entry %s already free!\n", de->name);
unlock_kernel();
return;
}
if (atomic_dec_and_test(&de->count))
free_proc_entry(de);
unlock_kernel();
}
}
/*
* Decrement the use count of the proc_dir_entry.
*/
static void proc_delete_inode(struct inode *inode)
{
struct proc_dir_entry *de;
truncate_inode_pages(&inode->i_data, 0);
/* Stop tracking associated processes */
put_pid(PROC_I(inode)->pid);
/* Let go of any associated proc directory entry */
de = PROC_I(inode)->pde;
if (de) {
if (de->owner)
module_put(de->owner);
de_put(de);
}
clear_inode(inode);
}
struct vfsmount *proc_mnt;
static void proc_read_inode(struct inode * inode)
{
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
}
static struct kmem_cache * proc_inode_cachep;
static struct inode *proc_alloc_inode(struct super_block *sb)
{
struct proc_inode *ei;
struct inode *inode;
ei = (struct proc_inode *)kmem_cache_alloc(proc_inode_cachep, GFP_KERNEL);
if (!ei)
return NULL;
ei->pid = NULL;
ei->fd = 0;
ei->op.proc_get_link = NULL;
ei->pde = NULL;
inode = &ei->vfs_inode;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
return inode;
}
static void proc_destroy_inode(struct inode *inode)
{
kmem_cache_free(proc_inode_cachep, PROC_I(inode));
}
static void init_once(struct kmem_cache * cachep, void *foo)
{
struct proc_inode *ei = (struct proc_inode *) foo;
inode_init_once(&ei->vfs_inode);
}
int __init proc_init_inodecache(void)
{
proc_inode_cachep = kmem_cache_create("proc_inode_cache",
sizeof(struct proc_inode),
0, (SLAB_RECLAIM_ACCOUNT|
SLAB_MEM_SPREAD|SLAB_PANIC),
init_once);
return 0;
}
static int proc_remount(struct super_block *sb, int *flags, char *data)
{
*flags |= MS_NODIRATIME;
return 0;
}
static const struct super_operations proc_sops = {
.alloc_inode = proc_alloc_inode,
.destroy_inode = proc_destroy_inode,
.read_inode = proc_read_inode,
.drop_inode = generic_delete_inode,
.delete_inode = proc_delete_inode,
.statfs = simple_statfs,
.remount_fs = proc_remount,
};
static void pde_users_dec(struct proc_dir_entry *pde)
{
spin_lock(&pde->pde_unload_lock);
pde->pde_users--;
if (pde->pde_unload_completion && pde->pde_users == 0)
complete(pde->pde_unload_completion);
spin_unlock(&pde->pde_unload_lock);
}
static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence)
{
struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
loff_t rv = -EINVAL;
loff_t (*llseek)(struct file *, loff_t, int);
spin_lock(&pde->pde_unload_lock);
/*
* remove_proc_entry() is going to delete PDE (as part of module
* cleanup sequence). No new callers into module allowed.
*/
if (!pde->proc_fops) {
spin_unlock(&pde->pde_unload_lock);
return rv;
}
/*
* Bump refcount so that remove_proc_entry will wail for ->llseek to
* complete.
*/
pde->pde_users++;
/*
* Save function pointer under lock, to protect against ->proc_fops
* NULL'ifying right after ->pde_unload_lock is dropped.
*/
llseek = pde->proc_fops->llseek;
spin_unlock(&pde->pde_unload_lock);
if (!llseek)
llseek = default_llseek;
rv = llseek(file, offset, whence);
pde_users_dec(pde);
return rv;
}
static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
{
struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
ssize_t rv = -EIO;
ssize_t (*read)(struct file *, char __user *, size_t, loff_t *);
spin_lock(&pde->pde_unload_lock);
if (!pde->proc_fops) {
spin_unlock(&pde->pde_unload_lock);
return rv;
}
pde->pde_users++;
read = pde->proc_fops->read;
spin_unlock(&pde->pde_unload_lock);
if (read)
rv = read(file, buf, count, ppos);
pde_users_dec(pde);
return rv;
}
static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
{
struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
ssize_t rv = -EIO;
ssize_t (*write)(struct file *, const char __user *, size_t, loff_t *);
spin_lock(&pde->pde_unload_lock);
if (!pde->proc_fops) {
spin_unlock(&pde->pde_unload_lock);
return rv;
}
pde->pde_users++;
write = pde->proc_fops->write;
spin_unlock(&pde->pde_unload_lock);
if (write)
rv = write(file, buf, count, ppos);
pde_users_dec(pde);
return rv;
}
static unsigned int proc_reg_poll(struct file *file, struct poll_table_struct *pts)
{
struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
unsigned int rv = DEFAULT_POLLMASK;
unsigned int (*poll)(struct file *, struct poll_table_struct *);
spin_lock(&pde->pde_unload_lock);
if (!pde->proc_fops) {
spin_unlock(&pde->pde_unload_lock);
return rv;
}
pde->pde_users++;
poll = pde->proc_fops->poll;
spin_unlock(&pde->pde_unload_lock);
if (poll)
rv = poll(file, pts);
pde_users_dec(pde);
return rv;
}
static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
long rv = -ENOTTY;
long (*unlocked_ioctl)(struct file *, unsigned int, unsigned long);
int (*ioctl)(struct inode *, struct file *, unsigned int, unsigned long);
spin_lock(&pde->pde_unload_lock);
if (!pde->proc_fops) {
spin_unlock(&pde->pde_unload_lock);
return rv;
}
pde->pde_users++;
unlocked_ioctl = pde->proc_fops->unlocked_ioctl;
ioctl = pde->proc_fops->ioctl;
spin_unlock(&pde->pde_unload_lock);
if (unlocked_ioctl) {
rv = unlocked_ioctl(file, cmd, arg);
if (rv == -ENOIOCTLCMD)
rv = -EINVAL;
} else if (ioctl) {
lock_kernel();
rv = ioctl(file->f_path.dentry->d_inode, file, cmd, arg);
unlock_kernel();
}
pde_users_dec(pde);
return rv;
}
#ifdef CONFIG_COMPAT
static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
long rv = -ENOTTY;
long (*compat_ioctl)(struct file *, unsigned int, unsigned long);
spin_lock(&pde->pde_unload_lock);
if (!pde->proc_fops) {
spin_unlock(&pde->pde_unload_lock);
return rv;
}
pde->pde_users++;
compat_ioctl = pde->proc_fops->compat_ioctl;
spin_unlock(&pde->pde_unload_lock);
if (compat_ioctl)
rv = compat_ioctl(file, cmd, arg);
pde_users_dec(pde);
return rv;
}
#endif
static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma)
{
struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
int rv = -EIO;
int (*mmap)(struct file *, struct vm_area_struct *);
spin_lock(&pde->pde_unload_lock);
if (!pde->proc_fops) {
spin_unlock(&pde->pde_unload_lock);
return rv;
}
pde->pde_users++;
mmap = pde->proc_fops->mmap;
spin_unlock(&pde->pde_unload_lock);
if (mmap)
rv = mmap(file, vma);
pde_users_dec(pde);
return rv;
}
static int proc_reg_open(struct inode *inode, struct file *file)
{
struct proc_dir_entry *pde = PDE(inode);
int rv = 0;
int (*open)(struct inode *, struct file *);
spin_lock(&pde->pde_unload_lock);
if (!pde->proc_fops) {
spin_unlock(&pde->pde_unload_lock);
return rv;
}
pde->pde_users++;
open = pde->proc_fops->open;
spin_unlock(&pde->pde_unload_lock);
if (open)
rv = open(inode, file);
pde_users_dec(pde);
return rv;
}
static int proc_reg_release(struct inode *inode, struct file *file)
{
struct proc_dir_entry *pde = PDE(inode);
int rv = 0;
int (*release)(struct inode *, struct file *);
spin_lock(&pde->pde_unload_lock);
if (!pde->proc_fops) {
spin_unlock(&pde->pde_unload_lock);
return rv;
}
pde->pde_users++;
release = pde->proc_fops->release;
spin_unlock(&pde->pde_unload_lock);
if (release)
rv = release(inode, file);
pde_users_dec(pde);
return rv;
}
static const struct file_operations proc_reg_file_ops = {
.llseek = proc_reg_llseek,
.read = proc_reg_read,
.write = proc_reg_write,
.poll = proc_reg_poll,
.unlocked_ioctl = proc_reg_unlocked_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = proc_reg_compat_ioctl,
#endif
.mmap = proc_reg_mmap,
.open = proc_reg_open,
.release = proc_reg_release,
};
#ifdef CONFIG_COMPAT
static const struct file_operations proc_reg_file_ops_no_compat = {
.llseek = proc_reg_llseek,
.read = proc_reg_read,
.write = proc_reg_write,
.poll = proc_reg_poll,
.unlocked_ioctl = proc_reg_unlocked_ioctl,
.mmap = proc_reg_mmap,
.open = proc_reg_open,
.release = proc_reg_release,
};
#endif
struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
struct proc_dir_entry *de)
{
struct inode * inode;
if (de != NULL && !try_module_get(de->owner))
goto out_mod;
inode = iget(sb, ino);
if (!inode)
goto out_ino;
PROC_I(inode)->fd = 0;
PROC_I(inode)->pde = de;
if (de) {
if (de->mode) {
inode->i_mode = de->mode;
inode->i_uid = de->uid;
inode->i_gid = de->gid;
}
if (de->size)
inode->i_size = de->size;
if (de->nlink)
inode->i_nlink = de->nlink;
if (de->proc_iops)
inode->i_op = de->proc_iops;
if (de->proc_fops) {
if (S_ISREG(inode->i_mode)) {
#ifdef CONFIG_COMPAT
if (!de->proc_fops->compat_ioctl)
inode->i_fop =
&proc_reg_file_ops_no_compat;
else
#endif
inode->i_fop = &proc_reg_file_ops;
}
else
inode->i_fop = de->proc_fops;
}
}
return inode;
out_ino:
if (de != NULL)
module_put(de->owner);
out_mod:
return NULL;
}
int proc_fill_super(struct super_block *s)
{
struct inode * root_inode;
s->s_flags |= MS_NODIRATIME | MS_NOSUID | MS_NOEXEC;
s->s_blocksize = 1024;
s->s_blocksize_bits = 10;
s->s_magic = PROC_SUPER_MAGIC;
s->s_op = &proc_sops;
s->s_time_gran = 1;
de_get(&proc_root);
root_inode = proc_get_inode(s, PROC_ROOT_INO, &proc_root);
if (!root_inode)
goto out_no_root;
root_inode->i_uid = 0;
root_inode->i_gid = 0;
s->s_root = d_alloc_root(root_inode);
if (!s->s_root)
goto out_no_root;
return 0;
out_no_root:
printk("proc_read_super: get root inode failed\n");
iput(root_inode);
de_put(&proc_root);
return -ENOMEM;
}
MODULE_LICENSE("GPL");