kernel_optimize_test/fs/proc/internal.h
Alexey Dobriyan c2319540cd 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>
2007-11-29 09:24:52 -08:00

81 lines
2.2 KiB
C

/* internal.h: internal procfs definitions
*
* Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/proc_fs.h>
#ifdef CONFIG_PROC_SYSCTL
extern int proc_sys_init(void);
#else
static inline void proc_sys_init(void) { }
#endif
#ifdef CONFIG_NET
extern int proc_net_init(void);
#else
static inline int proc_net_init(void) { return 0; }
#endif
struct vmalloc_info {
unsigned long used;
unsigned long largest_chunk;
};
#ifdef CONFIG_MMU
#define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START)
extern void get_vmalloc_info(struct vmalloc_info *vmi);
#else
#define VMALLOC_TOTAL 0UL
#define get_vmalloc_info(vmi) \
do { \
(vmi)->used = 0; \
(vmi)->largest_chunk = 0; \
} while(0)
extern int nommu_vma_show(struct seq_file *, struct vm_area_struct *);
#endif
extern int maps_protect;
extern void create_seq_entry(char *name, mode_t mode, const struct file_operations *f);
extern int proc_exe_link(struct inode *, struct dentry **, struct vfsmount **);
extern int proc_tid_stat(struct task_struct *, char *);
extern int proc_tgid_stat(struct task_struct *, char *);
extern int proc_pid_status(struct task_struct *, char *);
extern int proc_pid_statm(struct task_struct *, char *);
extern const struct file_operations proc_maps_operations;
extern const struct file_operations proc_numa_maps_operations;
extern const struct file_operations proc_smaps_operations;
extern const struct file_operations proc_maps_operations;
extern const struct file_operations proc_numa_maps_operations;
extern const struct file_operations proc_smaps_operations;
void free_proc_entry(struct proc_dir_entry *de);
int proc_init_inodecache(void);
static inline struct pid *proc_pid(struct inode *inode)
{
return PROC_I(inode)->pid;
}
static inline struct task_struct *get_proc_task(struct inode *inode)
{
return get_pid_task(proc_pid(inode), PIDTYPE_PID);
}
static inline int proc_fd(struct inode *inode)
{
return PROC_I(inode)->fd;
}