exynos-linux-stable/include/linux/sysctl.h
Eric W. Biederman a3a7b992b2 proc: Fix proc_sys_prune_dcache to hold a sb reference
commit 2fd1d2c4ceb2248a727696962cf3370dc9f5a0a4 upstream.

Andrei Vagin writes:
FYI: This bug has been reproduced on 4.11.7
> BUG: Dentry ffff895a3dd01240{i=4e7c09a,n=lo}  still in use (1) [unmount of proc proc]
> ------------[ cut here ]------------
> WARNING: CPU: 1 PID: 13588 at fs/dcache.c:1445 umount_check+0x6e/0x80
> CPU: 1 PID: 13588 Comm: kworker/1:1 Not tainted 4.11.7-200.fc25.x86_64 #1
> Hardware name: CompuLab sbc-flt1/fitlet, BIOS SBCFLT_0.08.04 06/27/2015
> Workqueue: events proc_cleanup_work
> Call Trace:
>  dump_stack+0x63/0x86
>  __warn+0xcb/0xf0
>  warn_slowpath_null+0x1d/0x20
>  umount_check+0x6e/0x80
>  d_walk+0xc6/0x270
>  ? dentry_free+0x80/0x80
>  do_one_tree+0x26/0x40
>  shrink_dcache_for_umount+0x2d/0x90
>  generic_shutdown_super+0x1f/0xf0
>  kill_anon_super+0x12/0x20
>  proc_kill_sb+0x40/0x50
>  deactivate_locked_super+0x43/0x70
>  deactivate_super+0x5a/0x60
>  cleanup_mnt+0x3f/0x90
>  mntput_no_expire+0x13b/0x190
>  kern_unmount+0x3e/0x50
>  pid_ns_release_proc+0x15/0x20
>  proc_cleanup_work+0x15/0x20
>  process_one_work+0x197/0x450
>  worker_thread+0x4e/0x4a0
>  kthread+0x109/0x140
>  ? process_one_work+0x450/0x450
>  ? kthread_park+0x90/0x90
>  ret_from_fork+0x2c/0x40
> ---[ end trace e1c109611e5d0b41 ]---
> VFS: Busy inodes after unmount of proc. Self-destruct in 5 seconds.  Have a nice day...
> BUG: unable to handle kernel NULL pointer dereference at           (null)
> IP: _raw_spin_lock+0xc/0x30
> PGD 0

Fix this by taking a reference to the super block in proc_sys_prune_dcache.

The superblock reference is the core of the fix however the sysctl_inodes
list is converted to a hlist so that hlist_del_init_rcu may be used.  This
allows proc_sys_prune_dache to remove inodes the sysctl_inodes list, while
not causing problems for proc_sys_evict_inode when if it later choses to
remove the inode from the sysctl_inodes list.  Removing inodes from the
sysctl_inodes list allows proc_sys_prune_dcache to have a progress
guarantee, while still being able to drop all locks.  The fact that
head->unregistering is set in start_unregistering ensures that no more
inodes will be added to the the sysctl_inodes list.

Previously the code did a dance where it delayed calling iput until the
next entry in the list was being considered to ensure the inode remained on
the sysctl_inodes list until the next entry was walked to.  The structure
of the loop in this patch does not need that so is much easier to
understand and maintain.

Cc: stable@vger.kernel.org
Reported-by: Andrei Vagin <avagin@gmail.com>
Tested-by: Andrei Vagin <avagin@openvz.org>
Fixes: ace0c791e6c3 ("proc/sysctl: Don't grab i_lock under sysctl_lock.")
Fixes: d6cffbbe9a7e ("proc/sysctl: prune stale dentries during unregistering")
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-08-15 18:14:43 +02:00

228 lines
7 KiB
C

/*
* sysctl.h: General linux system control interface
*
* Begun 24 March 1995, Stephen Tweedie
*
****************************************************************
****************************************************************
**
** WARNING:
** The values in this file are exported to user space via
** the sysctl() binary interface. Do *NOT* change the
** numbering of any existing values here, and do not change
** any numbers within any one set of values. If you have to
** redefine an existing interface, use a new number for it.
** The kernel will then return -ENOTDIR to any application using
** the old binary interface.
**
****************************************************************
****************************************************************
*/
#ifndef _LINUX_SYSCTL_H
#define _LINUX_SYSCTL_H
#include <linux/list.h>
#include <linux/rcupdate.h>
#include <linux/wait.h>
#include <linux/rbtree.h>
#include <linux/uidgid.h>
#include <uapi/linux/sysctl.h>
/* For the /proc/sys support */
struct completion;
struct ctl_table;
struct nsproxy;
struct ctl_table_root;
struct ctl_table_header;
struct ctl_dir;
typedef int proc_handler (struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
extern int proc_dostring(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int proc_dointvec(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int proc_douintvec(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int proc_dointvec_minmax(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int proc_dointvec_jiffies(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int proc_dointvec_ms_jiffies(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int proc_doulongvec_minmax(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int,
void __user *, size_t *, loff_t *);
extern int proc_do_large_bitmap(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
/*
* Register a set of sysctl names by calling register_sysctl_table
* with an initialised array of struct ctl_table's. An entry with
* NULL procname terminates the table. table->de will be
* set up by the registration and need not be initialised in advance.
*
* sysctl names can be mirrored automatically under /proc/sys. The
* procname supplied controls /proc naming.
*
* The table's mode will be honoured both for sys_sysctl(2) and
* proc-fs access.
*
* Leaf nodes in the sysctl tree will be represented by a single file
* under /proc; non-leaf nodes will be represented by directories. A
* null procname disables /proc mirroring at this node.
*
* sysctl(2) can automatically manage read and write requests through
* the sysctl table. The data and maxlen fields of the ctl_table
* struct enable minimal validation of the values being written to be
* performed, and the mode field allows minimal authentication.
*
* There must be a proc_handler routine for any terminal nodes
* mirrored under /proc/sys (non-terminals are handled by a built-in
* directory handler). Several default handlers are available to
* cover common cases.
*/
/* Support for userspace poll() to watch for changes */
struct ctl_table_poll {
atomic_t event;
wait_queue_head_t wait;
};
static inline void *proc_sys_poll_event(struct ctl_table_poll *poll)
{
return (void *)(unsigned long)atomic_read(&poll->event);
}
#define __CTL_TABLE_POLL_INITIALIZER(name) { \
.event = ATOMIC_INIT(0), \
.wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.wait) }
#define DEFINE_CTL_TABLE_POLL(name) \
struct ctl_table_poll name = __CTL_TABLE_POLL_INITIALIZER(name)
/* A sysctl table is an array of struct ctl_table: */
struct ctl_table
{
const char *procname; /* Text ID for /proc/sys, or zero */
void *data;
int maxlen;
umode_t mode;
struct ctl_table *child; /* Deprecated */
proc_handler *proc_handler; /* Callback for text formatting */
struct ctl_table_poll *poll;
void *extra1;
void *extra2;
};
struct ctl_node {
struct rb_node node;
struct ctl_table_header *header;
};
/* struct ctl_table_header is used to maintain dynamic lists of
struct ctl_table trees. */
struct ctl_table_header
{
union {
struct {
struct ctl_table *ctl_table;
int used;
int count;
int nreg;
};
struct rcu_head rcu;
};
struct completion *unregistering;
struct ctl_table *ctl_table_arg;
struct ctl_table_root *root;
struct ctl_table_set *set;
struct ctl_dir *parent;
struct ctl_node *node;
struct hlist_head inodes; /* head for proc_inode->sysctl_inodes */
};
struct ctl_dir {
/* Header must be at the start of ctl_dir */
struct ctl_table_header header;
struct rb_root root;
};
struct ctl_table_set {
int (*is_seen)(struct ctl_table_set *);
struct ctl_dir dir;
};
struct ctl_table_root {
struct ctl_table_set default_set;
struct ctl_table_set *(*lookup)(struct ctl_table_root *root);
void (*set_ownership)(struct ctl_table_header *head,
struct ctl_table *table,
kuid_t *uid, kgid_t *gid);
int (*permissions)(struct ctl_table_header *head, struct ctl_table *table);
};
/* struct ctl_path describes where in the hierarchy a table is added */
struct ctl_path {
const char *procname;
};
#ifdef CONFIG_SYSCTL
void proc_sys_poll_notify(struct ctl_table_poll *poll);
extern void setup_sysctl_set(struct ctl_table_set *p,
struct ctl_table_root *root,
int (*is_seen)(struct ctl_table_set *));
extern void retire_sysctl_set(struct ctl_table_set *set);
void register_sysctl_root(struct ctl_table_root *root);
struct ctl_table_header *__register_sysctl_table(
struct ctl_table_set *set,
const char *path, struct ctl_table *table);
struct ctl_table_header *__register_sysctl_paths(
struct ctl_table_set *set,
const struct ctl_path *path, struct ctl_table *table);
struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *table);
struct ctl_table_header *register_sysctl_table(struct ctl_table * table);
struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path,
struct ctl_table *table);
void unregister_sysctl_table(struct ctl_table_header * table);
extern int sysctl_init(void);
extern struct ctl_table sysctl_mount_point[];
#else /* CONFIG_SYSCTL */
static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * table)
{
return NULL;
}
static inline struct ctl_table_header *register_sysctl_paths(
const struct ctl_path *path, struct ctl_table *table)
{
return NULL;
}
static inline void unregister_sysctl_table(struct ctl_table_header * table)
{
}
static inline void setup_sysctl_set(struct ctl_table_set *p,
struct ctl_table_root *root,
int (*is_seen)(struct ctl_table_set *))
{
}
#endif /* CONFIG_SYSCTL */
int sysctl_max_threads(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
#endif /* _LINUX_SYSCTL_H */