linux_dsm_epyc7002/include/linux/pid.h
Eric W. Biederman 63f818f46a proc: Use a dedicated lock in struct pid
syzbot wrote:
> ========================================================
> WARNING: possible irq lock inversion dependency detected
> 5.6.0-syzkaller #0 Not tainted
> --------------------------------------------------------
> swapper/1/0 just changed the state of lock:
> ffffffff898090d8 (tasklist_lock){.+.?}-{2:2}, at: send_sigurg+0x9f/0x320 fs/fcntl.c:840
> but this lock took another, SOFTIRQ-unsafe lock in the past:
>  (&pid->wait_pidfd){+.+.}-{2:2}
>
>
> and interrupts could create inverse lock ordering between them.
>
>
> other info that might help us debug this:
>  Possible interrupt unsafe locking scenario:
>
>        CPU0                    CPU1
>        ----                    ----
>   lock(&pid->wait_pidfd);
>                                local_irq_disable();
>                                lock(tasklist_lock);
>                                lock(&pid->wait_pidfd);
>   <Interrupt>
>     lock(tasklist_lock);
>
>  *** DEADLOCK ***
>
> 4 locks held by swapper/1/0:

The problem is that because wait_pidfd.lock is taken under the tasklist
lock.  It must always be taken with irqs disabled as tasklist_lock can be
taken from interrupt context and if wait_pidfd.lock was already taken this
would create a lock order inversion.

Oleg suggested just disabling irqs where I have added extra calls to
wait_pidfd.lock.  That should be safe and I think the code will eventually
do that.  It was rightly pointed out by Christian that sharing the
wait_pidfd.lock was a premature optimization.

It is also true that my pre-merge window testing was insufficient.  So
remove the premature optimization and give struct pid a dedicated lock of
it's own for struct pid things.  I have verified that lockdep sees all 3
paths where we take the new pid->lock and lockdep does not complain.

It is my current day dream that one day pid->lock can be used to guard the
task lists as well and then the tasklist_lock won't need to be held to
deliver signals.  That will require taking pid->lock with irqs disabled.

Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/lkml/00000000000011d66805a25cd73f@google.com/
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Reported-by: syzbot+343f75cdeea091340956@syzkaller.appspotmail.com
Reported-by: syzbot+832aabf700bc3ec920b9@syzkaller.appspotmail.com
Reported-by: syzbot+f675f964019f884dbd0f@syzkaller.appspotmail.com
Reported-by: syzbot+a9fb1457d720a55d6dc5@syzkaller.appspotmail.com
Fixes: 7bc3e6e55a ("proc: Use a list of inodes to flush from proc")
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2020-04-09 12:15:35 -05:00

211 lines
6.0 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_PID_H
#define _LINUX_PID_H
#include <linux/rculist.h>
#include <linux/wait.h>
#include <linux/refcount.h>
enum pid_type
{
PIDTYPE_PID,
PIDTYPE_TGID,
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 {
int nr;
struct pid_namespace *ns;
};
struct pid
{
refcount_t count;
unsigned int level;
spinlock_t lock;
/* lists of tasks that use this pid */
struct hlist_head tasks[PIDTYPE_MAX];
struct hlist_head inodes;
/* wait queue for pidfd notifications */
wait_queue_head_t wait_pidfd;
struct rcu_head rcu;
struct upid numbers[1];
};
extern struct pid init_struct_pid;
extern const struct file_operations pidfd_fops;
struct file;
extern struct pid *pidfd_pid(const struct file *file);
static inline struct pid *get_pid(struct pid *pid)
{
if (pid)
refcount_inc(&pid->count);
return pid;
}
extern void put_pid(struct pid *pid);
extern struct task_struct *pid_task(struct pid *pid, enum pid_type);
static inline bool pid_has_task(struct pid *pid, enum pid_type type)
{
return !hlist_empty(&pid->tasks[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 *);
extern struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
size_t set_tid_size);
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], pid_links[type]) {
/*
* 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; \
for_each_thread(tg___, task) {
#define while_each_pid_thread(pid, type, task) \
} \
task = tg___; \
} while_each_pid_task(pid, type, task)
#endif /* _LINUX_PID_H */