kpriv/linux-hardened
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
linux-hardened/include/linux/elevator.h
Yasuaki Ishimatsu 7681bfeecc block: fix accounting bug on cross partition merges 
/proc/diskstats would display a strange output as follows.

$ cat /proc/diskstats |grep sda
   8       0 sda 90524 7579 102154 20464 0 0 0 0 0 14096 20089
   8       1 sda1 19085 1352 21841 4209 0 0 0 0 4294967064 15689 4293424691
                                                ~~~~~~~~~~
   8       2 sda2 71252 3624 74891 15950 0 0 0 0 232 23995 1562390
   8       3 sda3 54 487 2188 92 0 0 0 0 0 88 92
   8       4 sda4 4 0 8 0 0 0 0 0 0 0 0
   8       5 sda5 81 2027 2130 138 0 0 0 0 0 87 137

Its reason is the wrong way of accounting hd_struct->in_flight. When a bio is
merged into a request belongs to different partition by ELEVATOR_FRONT_MERGE.

The detailed root cause is as follows.

Assuming that there are two partition, sda1 and sda2.

1. A request for sda2 is in request_queue. Hence sda1's hd_struct->in_flight
   is 0 and sda2's one is 1.

        | hd_struct->in_flight
   ---------------------------
   sda1 |          0
   sda2 |          1
   ---------------------------

2. A bio belongs to sda1 is issued and is merged into the request mentioned on
   step1 by ELEVATOR_BACK_MERGE. The first sector of the request is changed
   from sda2 region to sda1 region. However the two partition's
   hd_struct->in_flight are not changed.

        | hd_struct->in_flight
   ---------------------------
   sda1 |          0
   sda2 |          1
   ---------------------------

3. The request is finished and blk_account_io_done() is called. In this case,
   sda2's hd_struct->in_flight, not a sda1's one, is decremented.

        | hd_struct->in_flight
   ---------------------------
   sda1 |         -1
   sda2 |          1
   ---------------------------

The patch fixes the problem by caching the partition lookup
inside the request structure, hence making sure that the increment
and decrement will always happen on the same partition struct. This
also speeds up IO with accounting enabled, since it cuts down on
the number of lookups we have to do.

When reloading partition tables, quiesce IO to ensure that no
request references to the partition struct exists. When it is safe
to free the partition table, the IO for that device is restarted
again.

Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: stable@kernel.org
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2010-10-19 09:07:02 +02:00

219 lines
7.1 KiB
C
Raw Blame History

#ifndef _LINUX_ELEVATOR_H
#define _LINUX_ELEVATOR_H
#include <linux/percpu.h>
#ifdef CONFIG_BLOCK
typedef int (elevator_merge_fn) (struct request_queue *, struct request **,
struct bio *);
typedef void (elevator_merge_req_fn) (struct request_queue *, struct request *, struct request *);
typedef void (elevator_merged_fn) (struct request_queue *, struct request *, int);
typedef int (elevator_allow_merge_fn) (struct request_queue *, struct request *, struct bio *);
typedef void (elevator_bio_merged_fn) (struct request_queue *,
struct request *, struct bio *);
typedef int (elevator_dispatch_fn) (struct request_queue *, int);
typedef void (elevator_add_req_fn) (struct request_queue *, struct request *);
typedef int (elevator_queue_empty_fn) (struct request_queue *);
typedef struct request *(elevator_request_list_fn) (struct request_queue *, struct request *);
typedef void (elevator_completed_req_fn) (struct request_queue *, struct request *);
typedef int (elevator_may_queue_fn) (struct request_queue *, int);
typedef int (elevator_set_req_fn) (struct request_queue *, struct request *, gfp_t);
typedef void (elevator_put_req_fn) (struct request *);
typedef void (elevator_activate_req_fn) (struct request_queue *, struct request *);
typedef void (elevator_deactivate_req_fn) (struct request_queue *, struct request *);
typedef void *(elevator_init_fn) (struct request_queue *);
typedef void (elevator_exit_fn) (struct elevator_queue *);
struct elevator_ops
{
elevator_merge_fn *elevator_merge_fn;
elevator_merged_fn *elevator_merged_fn;
elevator_merge_req_fn *elevator_merge_req_fn;
elevator_allow_merge_fn *elevator_allow_merge_fn;
elevator_bio_merged_fn *elevator_bio_merged_fn;
elevator_dispatch_fn *elevator_dispatch_fn;
elevator_add_req_fn *elevator_add_req_fn;
elevator_activate_req_fn *elevator_activate_req_fn;
elevator_deactivate_req_fn *elevator_deactivate_req_fn;
elevator_queue_empty_fn *elevator_queue_empty_fn;
elevator_completed_req_fn *elevator_completed_req_fn;
elevator_request_list_fn *elevator_former_req_fn;
elevator_request_list_fn *elevator_latter_req_fn;
elevator_set_req_fn *elevator_set_req_fn;
elevator_put_req_fn *elevator_put_req_fn;
elevator_may_queue_fn *elevator_may_queue_fn;
elevator_init_fn *elevator_init_fn;
elevator_exit_fn *elevator_exit_fn;
void (*trim)(struct io_context *);
};
#define ELV_NAME_MAX (16)
struct elv_fs_entry {
struct attribute attr;
ssize_t (*show)(struct elevator_queue *, char *);
ssize_t (*store)(struct elevator_queue *, const char *, size_t);
};
/*
* identifies an elevator type, such as AS or deadline
*/
struct elevator_type
{
struct list_head list;
struct elevator_ops ops;
struct elv_fs_entry *elevator_attrs;
char elevator_name[ELV_NAME_MAX];
struct module *elevator_owner;
};
/*
* each queue has an elevator_queue associated with it
*/
struct elevator_queue
{
struct elevator_ops *ops;
void *elevator_data;
struct kobject kobj;
struct elevator_type *elevator_type;
struct mutex sysfs_lock;
struct hlist_head *hash;
};
/*
* block elevator interface
*/
extern void elv_dispatch_sort(struct request_queue *, struct request *);
extern void elv_dispatch_add_tail(struct request_queue *, struct request *);
extern void elv_add_request(struct request_queue *, struct request *, int, int);
extern void __elv_add_request(struct request_queue *, struct request *, int, int);
extern void elv_insert(struct request_queue *, struct request *, int);
extern int elv_merge(struct request_queue *, struct request **, struct bio *);
extern void elv_merge_requests(struct request_queue *, struct request *,
struct request *);
extern void elv_merged_request(struct request_queue *, struct request *, int);
extern void elv_bio_merged(struct request_queue *q, struct request *,
struct bio *);
extern void elv_requeue_request(struct request_queue *, struct request *);
extern int elv_queue_empty(struct request_queue *);
extern struct request *elv_former_request(struct request_queue *, struct request *);
extern struct request *elv_latter_request(struct request_queue *, struct request *);
extern int elv_register_queue(struct request_queue *q);
extern void elv_unregister_queue(struct request_queue *q);
extern int elv_may_queue(struct request_queue *, int);
extern void elv_abort_queue(struct request_queue *);
extern void elv_completed_request(struct request_queue *, struct request *);
extern int elv_set_request(struct request_queue *, struct request *, gfp_t);
extern void elv_put_request(struct request_queue *, struct request *);
extern void elv_drain_elevator(struct request_queue *);
extern void elv_quiesce_start(struct request_queue *);
extern void elv_quiesce_end(struct request_queue *);
/*
* io scheduler registration
*/
extern void elv_register(struct elevator_type *);
extern void elv_unregister(struct elevator_type *);
/*
* io scheduler sysfs switching
*/
extern ssize_t elv_iosched_show(struct request_queue *, char *);
extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t);
extern int elevator_init(struct request_queue *, char *);
extern void elevator_exit(struct elevator_queue *);
extern int elv_rq_merge_ok(struct request *, struct bio *);
/*
* Helper functions.
*/
extern struct request *elv_rb_former_request(struct request_queue *, struct request *);
extern struct request *elv_rb_latter_request(struct request_queue *, struct request *);
/*
* rb support functions.
*/
extern struct request *elv_rb_add(struct rb_root *, struct request *);
extern void elv_rb_del(struct rb_root *, struct request *);
extern struct request *elv_rb_find(struct rb_root *, sector_t);
/*
* Return values from elevator merger
*/
#define ELEVATOR_NO_MERGE 0
#define ELEVATOR_FRONT_MERGE 1
#define ELEVATOR_BACK_MERGE 2
/*
* Insertion selection
*/
#define ELEVATOR_INSERT_FRONT 1
#define ELEVATOR_INSERT_BACK 2
#define ELEVATOR_INSERT_SORT 3
#define ELEVATOR_INSERT_REQUEUE 4
/*
* return values from elevator_may_queue_fn
*/
enum {
ELV_MQUEUE_MAY,
ELV_MQUEUE_NO,
ELV_MQUEUE_MUST,
};
#define rq_end_sector(rq) (blk_rq_pos(rq) + blk_rq_sectors(rq))
#define rb_entry_rq(node) rb_entry((node), struct request, rb_node)
/*
* Hack to reuse the csd.list list_head as the fifo time holder while
* the request is in the io scheduler. Saves an unsigned long in rq.
*/
#define rq_fifo_time(rq) ((unsigned long) (rq)->csd.list.next)
#define rq_set_fifo_time(rq,exp) ((rq)->csd.list.next = (void *) (exp))
#define rq_entry_fifo(ptr) list_entry((ptr), struct request, queuelist)
#define rq_fifo_clear(rq) do { \
list_del_init(&(rq)->queuelist); \
INIT_LIST_HEAD(&(rq)->csd.list); \
} while (0)
/*
* io context count accounting
*/
#define elv_ioc_count_mod(name, __val) \
do { \
preempt_disable(); \
__get_cpu_var(name) += (__val); \
preempt_enable(); \
} while (0)
#define elv_ioc_count_inc(name) elv_ioc_count_mod(name, 1)
#define elv_ioc_count_dec(name) elv_ioc_count_mod(name, -1)
#define elv_ioc_count_read(name) \
({ \
unsigned long __val = 0; \
int __cpu; \
smp_wmb(); \
for_each_possible_cpu(__cpu) \
__val += per_cpu(name, __cpu); \
__val; \
})
#endif /* CONFIG_BLOCK */
#endif
Reference in a new issue View git blame Copy permalink