kernel_optimize_test/drivers/block/loop.h
Ming Lei f893366795 block: loop: don't hold lo_ctl_mutex in lo_open
The lo_ctl_mutex is held for running all ioctl handlers, and
in some ioctl handlers, ioctl_by_bdev(BLKRRPART) is called for
rereading partitions, which requires bd_mutex.

So it is easy to cause failure because trylock(bd_mutex) may
fail inside blkdev_reread_part(), and follows the lock context:

blkid or other application:
	->open()
		->mutex_lock(bd_mutex)
		->lo_open()
			->mutex_lock(lo_ctl_mutex)

losetup(set fd ioctl):
	->mutex_lock(lo_ctl_mutex)
	->ioctl_by_bdev(BLKRRPART)
		->trylock(bd_mutex)

This patch trys to eliminate the ABBA lock dependency by removing
lo_ctl_mutext in lo_open() with the following approach:

1) make lo_refcnt as atomic_t and avoid acquiring lo_ctl_mutex in lo_open():
	- for open vs. add/del loop, no any problem because of loop_index_mutex
	- freeze request queue during clr_fd, so I/O can't come until
	  clearing fd is completed, like the effect of holding lo_ctl_mutex
	  in lo_open
	- both open() and release() have been serialized by bd_mutex already

2) don't hold lo_ctl_mutex for decreasing/checking lo_refcnt in
lo_release(), then lo_ctl_mutex is only required for the last release.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: Jarod Wilson <jarod@redhat.com>
Acked-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2015-05-20 09:06:09 -06:00

93 lines
2.3 KiB
C

/*
* loop.h
*
* Written by Theodore Ts'o, 3/29/93.
*
* Copyright 1993 by Theodore Ts'o. Redistribution of this file is
* permitted under the GNU General Public License.
*/
#ifndef _LINUX_LOOP_H
#define _LINUX_LOOP_H
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
#include <linux/spinlock.h>
#include <linux/mutex.h>
#include <linux/workqueue.h>
#include <uapi/linux/loop.h>
/* Possible states of device */
enum {
Lo_unbound,
Lo_bound,
Lo_rundown,
};
struct loop_func_table;
struct loop_device {
int lo_number;
atomic_t lo_refcnt;
loff_t lo_offset;
loff_t lo_sizelimit;
int lo_flags;
int (*transfer)(struct loop_device *, int cmd,
struct page *raw_page, unsigned raw_off,
struct page *loop_page, unsigned loop_off,
int size, sector_t real_block);
char lo_file_name[LO_NAME_SIZE];
char lo_crypt_name[LO_NAME_SIZE];
char lo_encrypt_key[LO_KEY_SIZE];
int lo_encrypt_key_size;
struct loop_func_table *lo_encryption;
__u32 lo_init[2];
kuid_t lo_key_owner; /* Who set the key */
int (*ioctl)(struct loop_device *, int cmd,
unsigned long arg);
struct file * lo_backing_file;
struct block_device *lo_device;
unsigned lo_blocksize;
void *key_data;
gfp_t old_gfp_mask;
spinlock_t lo_lock;
struct workqueue_struct *wq;
struct list_head write_cmd_head;
struct work_struct write_work;
bool write_started;
int lo_state;
struct mutex lo_ctl_mutex;
struct request_queue *lo_queue;
struct blk_mq_tag_set tag_set;
struct gendisk *lo_disk;
};
struct loop_cmd {
struct work_struct read_work;
struct request *rq;
struct list_head list;
};
/* Support for loadable transfer modules */
struct loop_func_table {
int number; /* filter type */
int (*transfer)(struct loop_device *lo, int cmd,
struct page *raw_page, unsigned raw_off,
struct page *loop_page, unsigned loop_off,
int size, sector_t real_block);
int (*init)(struct loop_device *, const struct loop_info64 *);
/* release is called from loop_unregister_transfer or clr_fd */
int (*release)(struct loop_device *);
int (*ioctl)(struct loop_device *, int cmd, unsigned long arg);
struct module *owner;
};
int loop_register_transfer(struct loop_func_table *funcs);
int loop_unregister_transfer(int number);
#endif