mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-15 16:24:13 +08:00
964fb15acf
The current implementation of worker threads in Btrfs has races in
worker stopping code, which cause all kinds of panics and lockups when
running btrfs/011 xfstest in a loop. The problem is that
btrfs_stop_workers is unsynchronized with respect to check_idle_worker,
check_busy_worker and __btrfs_start_workers.
E.g., check_idle_worker race flow:
btrfs_stop_workers(): check_idle_worker(aworker):
- grabs the lock
- splices the idle list into the
working list
- removes the first worker from the
working list
- releases the lock to wait for
its kthread's completion
- grabs the lock
- if aworker is on the working list,
moves aworker from the working list
to the idle list
- releases the lock
- grabs the lock
- puts the worker
- removes the second worker from the
working list
......
btrfs_stop_workers returns, aworker is on the idle list
FS is umounted, memory is freed
......
aworker is waken up, fireworks ensue
With this applied, I wasn't able to trigger the problem in 48 hours,
whereas previously I could reliably reproduce at least one of these
races within an hour.
Reported-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
122 lines
3.8 KiB
C
122 lines
3.8 KiB
C
/*
|
|
* Copyright (C) 2007 Oracle. All rights reserved.
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public
|
|
* License v2 as published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
* General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public
|
|
* License along with this program; if not, write to the
|
|
* Free Software Foundation, Inc., 59 Temple Place - Suite 330,
|
|
* Boston, MA 021110-1307, USA.
|
|
*/
|
|
|
|
#ifndef __BTRFS_ASYNC_THREAD_
|
|
#define __BTRFS_ASYNC_THREAD_
|
|
|
|
struct btrfs_worker_thread;
|
|
|
|
/*
|
|
* This is similar to a workqueue, but it is meant to spread the operations
|
|
* across all available cpus instead of just the CPU that was used to
|
|
* queue the work. There is also some batching introduced to try and
|
|
* cut down on context switches.
|
|
*
|
|
* By default threads are added on demand up to 2 * the number of cpus.
|
|
* Changing struct btrfs_workers->max_workers is one way to prevent
|
|
* demand creation of kthreads.
|
|
*
|
|
* the basic model of these worker threads is to embed a btrfs_work
|
|
* structure in your own data struct, and use container_of in a
|
|
* work function to get back to your data struct.
|
|
*/
|
|
struct btrfs_work {
|
|
/*
|
|
* func should be set to the function you want called
|
|
* your work struct is passed as the only arg
|
|
*
|
|
* ordered_func must be set for work sent to an ordered work queue,
|
|
* and it is called to complete a given work item in the same
|
|
* order they were sent to the queue.
|
|
*/
|
|
void (*func)(struct btrfs_work *work);
|
|
void (*ordered_func)(struct btrfs_work *work);
|
|
void (*ordered_free)(struct btrfs_work *work);
|
|
|
|
/*
|
|
* flags should be set to zero. It is used to make sure the
|
|
* struct is only inserted once into the list.
|
|
*/
|
|
unsigned long flags;
|
|
|
|
/* don't touch these */
|
|
struct btrfs_worker_thread *worker;
|
|
struct list_head list;
|
|
struct list_head order_list;
|
|
};
|
|
|
|
struct btrfs_workers {
|
|
/* current number of running workers */
|
|
int num_workers;
|
|
|
|
int num_workers_starting;
|
|
|
|
/* max number of workers allowed. changed by btrfs_start_workers */
|
|
int max_workers;
|
|
|
|
/* once a worker has this many requests or fewer, it is idle */
|
|
int idle_thresh;
|
|
|
|
/* force completions in the order they were queued */
|
|
int ordered;
|
|
|
|
/* more workers required, but in an interrupt handler */
|
|
int atomic_start_pending;
|
|
|
|
/*
|
|
* are we allowed to sleep while starting workers or are we required
|
|
* to start them at a later time? If we can't sleep, this indicates
|
|
* which queue we need to use to schedule thread creation.
|
|
*/
|
|
struct btrfs_workers *atomic_worker_start;
|
|
|
|
/* list with all the work threads. The workers on the idle thread
|
|
* may be actively servicing jobs, but they haven't yet hit the
|
|
* idle thresh limit above.
|
|
*/
|
|
struct list_head worker_list;
|
|
struct list_head idle_list;
|
|
|
|
/*
|
|
* when operating in ordered mode, this maintains the list
|
|
* of work items waiting for completion
|
|
*/
|
|
struct list_head order_list;
|
|
struct list_head prio_order_list;
|
|
|
|
/* lock for finding the next worker thread to queue on */
|
|
spinlock_t lock;
|
|
|
|
/* lock for the ordered lists */
|
|
spinlock_t order_lock;
|
|
|
|
/* extra name for this worker, used for current->name */
|
|
char *name;
|
|
|
|
int stopping;
|
|
};
|
|
|
|
void btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work);
|
|
int btrfs_start_workers(struct btrfs_workers *workers);
|
|
void btrfs_stop_workers(struct btrfs_workers *workers);
|
|
void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max,
|
|
struct btrfs_workers *async_starter);
|
|
void btrfs_requeue_work(struct btrfs_work *work);
|
|
void btrfs_set_work_high_prio(struct btrfs_work *work);
|
|
#endif
|