linux-stable/include/linux/pid.h
Oleg Nesterov 8190773985 kernel/fork.c:copy_process(): don't add the uninitialized child to thread/task/pid lists
copy_process() adds the new child to thread_group/init_task.tasks list and
then does attach_pid(child, PIDTYPE_PID).  This means that the lockless
next_thread() or next_task() can see this thread with the wrong pid.  Say,
"ls /proc/pid/task" can list the same inode twice.

We could move attach_pid(child, PIDTYPE_PID) up, but in this case
find_task_by_vpid() can find the new thread before it was fully
initialized.

And this is already true for PIDTYPE_PGID/PIDTYPE_SID, With this patch
copy_process() initializes child->pids[*].pid first, then calls
attach_pid() to insert the task into the pid->tasks list.

attach_pid() no longer need the "struct pid*" argument, it is always
called after pid_link->pid was already set.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Sergey Dyasly <dserrg@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-03 16:08:03 -07:00

200 lines
5.8 KiB
C

#ifndef _LINUX_PID_H
#define _LINUX_PID_H
#include <linux/rcupdate.h>
enum pid_type
{
PIDTYPE_PID,
PIDTYPE_PGID,
PIDTYPE_SID,
PIDTYPE_MAX
};
/*
* What is struct pid?
*
* A struct pid is the kernel's internal notion of a process identifier.
* It refers to individual tasks, process groups, and sessions. While
* there are processes attached to it the struct pid lives in a hash
* table, so it and then the processes that it refers to can be found
* quickly from the numeric pid value. The attached processes may be
* quickly accessed by following pointers from struct pid.
*
* Storing pid_t values in the kernel and referring to them later has a
* problem. The process originally with that pid may have exited and the
* pid allocator wrapped, and another process could have come along
* and been assigned that pid.
*
* Referring to user space processes by holding a reference to struct
* task_struct has a problem. When the user space process exits
* the now useless task_struct is still kept. A task_struct plus a
* stack consumes around 10K of low kernel memory. More precisely
* this is THREAD_SIZE + sizeof(struct task_struct). By comparison
* a struct pid is about 64 bytes.
*
* Holding a reference to struct pid solves both of these problems.
* It is small so holding a reference does not consume a lot of
* resources, and since a new struct pid is allocated when the numeric pid
* value is reused (when pids wrap around) we don't mistakenly refer to new
* processes.
*/
/*
* struct upid is used to get the id of the struct pid, as it is
* seen in particular namespace. Later the struct pid is found with
* find_pid_ns() using the int nr and struct pid_namespace *ns.
*/
struct upid {
/* Try to keep pid_chain in the same cacheline as nr for find_vpid */
int nr;
struct pid_namespace *ns;
struct hlist_node pid_chain;
};
struct pid
{
atomic_t count;
unsigned int level;
/* lists of tasks that use this pid */
struct hlist_head tasks[PIDTYPE_MAX];
struct rcu_head rcu;
struct upid numbers[1];
};
extern struct pid init_struct_pid;
struct pid_link
{
struct hlist_node node;
struct pid *pid;
};
static inline struct pid *get_pid(struct pid *pid)
{
if (pid)
atomic_inc(&pid->count);
return pid;
}
extern void put_pid(struct pid *pid);
extern struct task_struct *pid_task(struct pid *pid, enum pid_type);
extern struct task_struct *get_pid_task(struct pid *pid, enum pid_type);
extern struct pid *get_task_pid(struct task_struct *task, enum pid_type type);
/*
* these helpers must be called with the tasklist_lock write-held.
*/
extern void attach_pid(struct task_struct *task, enum pid_type);
extern void detach_pid(struct task_struct *task, enum pid_type);
extern void change_pid(struct task_struct *task, enum pid_type,
struct pid *pid);
extern void transfer_pid(struct task_struct *old, struct task_struct *new,
enum pid_type);
struct pid_namespace;
extern struct pid_namespace init_pid_ns;
/*
* look up a PID in the hash table. Must be called with the tasklist_lock
* or rcu_read_lock() held.
*
* find_pid_ns() finds the pid in the namespace specified
* find_vpid() finds the pid by its virtual id, i.e. in the current namespace
*
* see also find_task_by_vpid() set in include/linux/sched.h
*/
extern struct pid *find_pid_ns(int nr, struct pid_namespace *ns);
extern struct pid *find_vpid(int nr);
/*
* Lookup a PID in the hash table, and return with it's count elevated.
*/
extern struct pid *find_get_pid(int nr);
extern struct pid *find_ge_pid(int nr, struct pid_namespace *);
int next_pidmap(struct pid_namespace *pid_ns, unsigned int last);
extern struct pid *alloc_pid(struct pid_namespace *ns);
extern void free_pid(struct pid *pid);
extern void disable_pid_allocation(struct pid_namespace *ns);
/*
* ns_of_pid() returns the pid namespace in which the specified pid was
* allocated.
*
* NOTE:
* ns_of_pid() is expected to be called for a process (task) that has
* an attached 'struct pid' (see attach_pid(), detach_pid()) i.e @pid
* is expected to be non-NULL. If @pid is NULL, caller should handle
* the resulting NULL pid-ns.
*/
static inline struct pid_namespace *ns_of_pid(struct pid *pid)
{
struct pid_namespace *ns = NULL;
if (pid)
ns = pid->numbers[pid->level].ns;
return ns;
}
/*
* is_child_reaper returns true if the pid is the init process
* of the current namespace. As this one could be checked before
* pid_ns->child_reaper is assigned in copy_process, we check
* with the pid number.
*/
static inline bool is_child_reaper(struct pid *pid)
{
return pid->numbers[pid->level].nr == 1;
}
/*
* the helpers to get the pid's id seen from different namespaces
*
* pid_nr() : global id, i.e. the id seen from the init namespace;
* pid_vnr() : virtual id, i.e. the id seen from the pid namespace of
* current.
* pid_nr_ns() : id seen from the ns specified.
*
* see also task_xid_nr() etc in include/linux/sched.h
*/
static inline pid_t pid_nr(struct pid *pid)
{
pid_t nr = 0;
if (pid)
nr = pid->numbers[0].nr;
return nr;
}
pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns);
pid_t pid_vnr(struct pid *pid);
#define do_each_pid_task(pid, type, task) \
do { \
if ((pid) != NULL) \
hlist_for_each_entry_rcu((task), \
&(pid)->tasks[type], pids[type].node) {
/*
* Both old and new leaders may be attached to
* the same pid in the middle of de_thread().
*/
#define while_each_pid_task(pid, type, task) \
if (type == PIDTYPE_PID) \
break; \
} \
} while (0)
#define do_each_pid_thread(pid, type, task) \
do_each_pid_task(pid, type, task) { \
struct task_struct *tg___ = task; \
do {
#define while_each_pid_thread(pid, type, task) \
} while_each_thread(tg___, task); \
task = tg___; \
} while_each_pid_task(pid, type, task)
#endif /* _LINUX_PID_H */