linux/drivers/md/dm-delay.c

380 lines
8.0 KiB
C
Raw Normal View History

/*
* Copyright (C) 2005-2007 Red Hat GmbH
*
* A target that delays reads and/or writes and can send
* them to different devices.
*
* This file is released under the GPL.
*/
#include <linux/module.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
#include <linux/slab.h>
#include <linux/device-mapper.h>
#define DM_MSG_PREFIX "delay"
struct delay_c {
struct timer_list delay_timer;
struct mutex timer_lock;
struct workqueue_struct *kdelayd_wq;
struct work_struct flush_expired_bios;
struct list_head delayed_bios;
atomic_t may_delay;
struct dm_dev *dev_read;
sector_t start_read;
unsigned read_delay;
unsigned reads;
struct dm_dev *dev_write;
sector_t start_write;
unsigned write_delay;
unsigned writes;
};
struct dm_delay_info {
struct delay_c *context;
struct list_head list;
unsigned long expires;
};
static DEFINE_MUTEX(delayed_bios_lock);
static void handle_delayed_timer(unsigned long data)
{
struct delay_c *dc = (struct delay_c *)data;
queue_work(dc->kdelayd_wq, &dc->flush_expired_bios);
}
static void queue_timeout(struct delay_c *dc, unsigned long expires)
{
mutex_lock(&dc->timer_lock);
if (!timer_pending(&dc->delay_timer) || expires < dc->delay_timer.expires)
mod_timer(&dc->delay_timer, expires);
mutex_unlock(&dc->timer_lock);
}
static void flush_bios(struct bio *bio)
{
struct bio *n;
while (bio) {
n = bio->bi_next;
bio->bi_next = NULL;
generic_make_request(bio);
bio = n;
}
}
static struct bio *flush_delayed_bios(struct delay_c *dc, int flush_all)
{
struct dm_delay_info *delayed, *next;
unsigned long next_expires = 0;
int start_timer = 0;
struct bio_list flush_bios = { };
mutex_lock(&delayed_bios_lock);
list_for_each_entry_safe(delayed, next, &dc->delayed_bios, list) {
if (flush_all || time_after_eq(jiffies, delayed->expires)) {
struct bio *bio = dm_bio_from_per_bio_data(delayed,
sizeof(struct dm_delay_info));
list_del(&delayed->list);
bio_list_add(&flush_bios, bio);
if ((bio_data_dir(bio) == WRITE))
delayed->context->writes--;
else
delayed->context->reads--;
continue;
}
if (!start_timer) {
start_timer = 1;
next_expires = delayed->expires;
} else
next_expires = min(next_expires, delayed->expires);
}
mutex_unlock(&delayed_bios_lock);
if (start_timer)
queue_timeout(dc, next_expires);
return bio_list_get(&flush_bios);
}
static void flush_expired_bios(struct work_struct *work)
{
struct delay_c *dc;
dc = container_of(work, struct delay_c, flush_expired_bios);
flush_bios(flush_delayed_bios(dc, 0));
}
/*
* Mapping parameters:
* <device> <offset> <delay> [<write_device> <write_offset> <write_delay>]
*
* With separate write parameters, the first set is only used for reads.
* Delays are specified in milliseconds.
*/
static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
{
struct delay_c *dc;
unsigned long long tmpll;
char dummy;
int ret;
if (argc != 3 && argc != 6) {
ti->error = "requires exactly 3 or 6 arguments";
return -EINVAL;
}
dc = kmalloc(sizeof(*dc), GFP_KERNEL);
if (!dc) {
ti->error = "Cannot allocate context";
return -ENOMEM;
}
dc->reads = dc->writes = 0;
ret = -EINVAL;
if (sscanf(argv[1], "%llu%c", &tmpll, &dummy) != 1) {
ti->error = "Invalid device sector";
goto bad;
}
dc->start_read = tmpll;
if (sscanf(argv[2], "%u%c", &dc->read_delay, &dummy) != 1) {
ti->error = "Invalid delay";
goto bad;
}
ret = dm_get_device(ti, argv[0], dm_table_get_mode(ti->table),
&dc->dev_read);
if (ret) {
ti->error = "Device lookup failed";
goto bad;
}
ret = -EINVAL;
dc->dev_write = NULL;
if (argc == 3)
goto out;
if (sscanf(argv[4], "%llu%c", &tmpll, &dummy) != 1) {
ti->error = "Invalid write device sector";
goto bad_dev_read;
}
dc->start_write = tmpll;
if (sscanf(argv[5], "%u%c", &dc->write_delay, &dummy) != 1) {
ti->error = "Invalid write delay";
goto bad_dev_read;
}
ret = dm_get_device(ti, argv[3], dm_table_get_mode(ti->table),
&dc->dev_write);
if (ret) {
ti->error = "Write device lookup failed";
goto bad_dev_read;
}
out:
ret = -EINVAL;
dc->kdelayd_wq = alloc_workqueue("kdelayd", WQ_MEM_RECLAIM, 0);
if (!dc->kdelayd_wq) {
DMERR("Couldn't start kdelayd");
goto bad_queue;
}
setup_timer(&dc->delay_timer, handle_delayed_timer, (unsigned long)dc);
INIT_WORK(&dc->flush_expired_bios, flush_expired_bios);
INIT_LIST_HEAD(&dc->delayed_bios);
mutex_init(&dc->timer_lock);
atomic_set(&dc->may_delay, 1);
ti->num_flush_bios = 1;
ti->num_discard_bios = 1;
ti->per_bio_data_size = sizeof(struct dm_delay_info);
ti->private = dc;
return 0;
bad_queue:
if (dc->dev_write)
dm_put_device(ti, dc->dev_write);
bad_dev_read:
dm_put_device(ti, dc->dev_read);
bad:
kfree(dc);
return ret;
}
static void delay_dtr(struct dm_target *ti)
{
struct delay_c *dc = ti->private;
destroy_workqueue(dc->kdelayd_wq);
dm_put_device(ti, dc->dev_read);
if (dc->dev_write)
dm_put_device(ti, dc->dev_write);
kfree(dc);
}
static int delay_bio(struct delay_c *dc, int delay, struct bio *bio)
{
struct dm_delay_info *delayed;
unsigned long expires = 0;
if (!delay || !atomic_read(&dc->may_delay))
return 1;
delayed = dm_per_bio_data(bio, sizeof(struct dm_delay_info));
delayed->context = dc;
delayed->expires = expires = jiffies + msecs_to_jiffies(delay);
mutex_lock(&delayed_bios_lock);
if (bio_data_dir(bio) == WRITE)
dc->writes++;
else
dc->reads++;
list_add_tail(&delayed->list, &dc->delayed_bios);
mutex_unlock(&delayed_bios_lock);
queue_timeout(dc, expires);
return 0;
}
static void delay_presuspend(struct dm_target *ti)
{
struct delay_c *dc = ti->private;
atomic_set(&dc->may_delay, 0);
del_timer_sync(&dc->delay_timer);
flush_bios(flush_delayed_bios(dc, 1));
}
static void delay_resume(struct dm_target *ti)
{
struct delay_c *dc = ti->private;
atomic_set(&dc->may_delay, 1);
}
static int delay_map(struct dm_target *ti, struct bio *bio)
{
struct delay_c *dc = ti->private;
if ((bio_data_dir(bio) == WRITE) && (dc->dev_write)) {
bio->bi_bdev = dc->dev_write->bdev;
if (bio_sectors(bio))
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-11 22:44:27 +00:00
bio->bi_iter.bi_sector = dc->start_write +
dm_target_offset(ti, bio->bi_iter.bi_sector);
return delay_bio(dc, dc->write_delay, bio);
}
bio->bi_bdev = dc->dev_read->bdev;
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-11 22:44:27 +00:00
bio->bi_iter.bi_sector = dc->start_read +
dm_target_offset(ti, bio->bi_iter.bi_sector);
return delay_bio(dc, dc->read_delay, bio);
}
dm: fix truncated status strings Avoid returning a truncated table or status string instead of setting the DM_BUFFER_FULL_FLAG when the last target of a table fills the buffer. When processing a table or status request, the function retrieve_status calls ti->type->status. If ti->type->status returns non-zero, retrieve_status assumes that the buffer overflowed and sets DM_BUFFER_FULL_FLAG. However, targets don't return non-zero values from their status method on overflow. Most targets returns always zero. If a buffer overflow happens in a target that is not the last in the table, it gets noticed during the next iteration of the loop in retrieve_status; but if a buffer overflow happens in the last target, it goes unnoticed and erroneously truncated data is returned. In the current code, the targets behave in the following way: * dm-crypt returns -ENOMEM if there is not enough space to store the key, but it returns 0 on all other overflows. * dm-thin returns errors from the status method if a disk error happened. This is incorrect because retrieve_status doesn't check the error code, it assumes that all non-zero values mean buffer overflow. * all the other targets always return 0. This patch changes the ti->type->status function to return void (because most targets don't use the return code). Overflow is detected in retrieve_status: if the status method fills up the remaining space completely, it is assumed that buffer overflow happened. Cc: stable@vger.kernel.org Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
2013-03-01 22:45:44 +00:00
static void delay_status(struct dm_target *ti, status_type_t type,
unsigned status_flags, char *result, unsigned maxlen)
{
struct delay_c *dc = ti->private;
int sz = 0;
switch (type) {
case STATUSTYPE_INFO:
DMEMIT("%u %u", dc->reads, dc->writes);
break;
case STATUSTYPE_TABLE:
DMEMIT("%s %llu %u", dc->dev_read->name,
(unsigned long long) dc->start_read,
dc->read_delay);
if (dc->dev_write)
DMEMIT(" %s %llu %u", dc->dev_write->name,
(unsigned long long) dc->start_write,
dc->write_delay);
break;
}
}
static int delay_iterate_devices(struct dm_target *ti,
iterate_devices_callout_fn fn, void *data)
{
struct delay_c *dc = ti->private;
int ret = 0;
ret = fn(ti, dc->dev_read, dc->start_read, ti->len, data);
if (ret)
goto out;
if (dc->dev_write)
ret = fn(ti, dc->dev_write, dc->start_write, ti->len, data);
out:
return ret;
}
static struct target_type delay_target = {
.name = "delay",
dm: fix truncated status strings Avoid returning a truncated table or status string instead of setting the DM_BUFFER_FULL_FLAG when the last target of a table fills the buffer. When processing a table or status request, the function retrieve_status calls ti->type->status. If ti->type->status returns non-zero, retrieve_status assumes that the buffer overflowed and sets DM_BUFFER_FULL_FLAG. However, targets don't return non-zero values from their status method on overflow. Most targets returns always zero. If a buffer overflow happens in a target that is not the last in the table, it gets noticed during the next iteration of the loop in retrieve_status; but if a buffer overflow happens in the last target, it goes unnoticed and erroneously truncated data is returned. In the current code, the targets behave in the following way: * dm-crypt returns -ENOMEM if there is not enough space to store the key, but it returns 0 on all other overflows. * dm-thin returns errors from the status method if a disk error happened. This is incorrect because retrieve_status doesn't check the error code, it assumes that all non-zero values mean buffer overflow. * all the other targets always return 0. This patch changes the ti->type->status function to return void (because most targets don't use the return code). Overflow is detected in retrieve_status: if the status method fills up the remaining space completely, it is assumed that buffer overflow happened. Cc: stable@vger.kernel.org Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
2013-03-01 22:45:44 +00:00
.version = {1, 2, 1},
.module = THIS_MODULE,
.ctr = delay_ctr,
.dtr = delay_dtr,
.map = delay_map,
.presuspend = delay_presuspend,
.resume = delay_resume,
.status = delay_status,
.iterate_devices = delay_iterate_devices,
};
static int __init dm_delay_init(void)
{
int r;
r = dm_register_target(&delay_target);
if (r < 0) {
DMERR("register failed %d", r);
goto bad_register;
}
return 0;
bad_register:
return r;
}
static void __exit dm_delay_exit(void)
{
dm_unregister_target(&delay_target);
}
/* Module hooks */
module_init(dm_delay_init);
module_exit(dm_delay_exit);
MODULE_DESCRIPTION(DM_NAME " delay target");
MODULE_AUTHOR("Heinz Mauelshagen <mauelshagen@redhat.com>");
MODULE_LICENSE("GPL");