int dm_resume(struct mapped_device *md)
{
struct bio *def;
struct dm_table *map = dm_get_table(md);
down_write(&md->lock);
if (!map ||
!test_bit(DMF_SUSPENDED, &md->flags) ||
!dm_table_get_size(map)) {
up_write(&md->lock);
dm_table_put(map);
return -EINVAL;
}
dm_table_resume_targets(map);
clear_bit(DMF_SUSPENDED, &md->flags);
clear_bit(DMF_BLOCK_IO, &md->flags);
def = bio_list_get(&md->deferred);
__flush_deferred_io(md, def);
up_write(&md->lock);
__unlock_fs(md);
dm_table_unplug_all(map);
dm_table_put(map);
return 0;
}
/*
* Split the bio into several clones.
*/
static void __split_bio(struct mapped_device *md, struct bio *bio)
{
struct clone_info ci;
ci.map = dm_get_table(md);
if (!ci.map) {
bio_io_error(bio, bio->bi_size);
return;
}
ci.md = md;
ci.bio = bio;
ci.io = alloc_io(md);
ci.io->error = 0;
atomic_set(&ci.io->io_count, 1);
ci.io->bio = bio;
ci.io->md = md;
ci.sector = bio->bi_sector;
ci.sector_count = bio_sectors(bio);
ci.idx = bio->bi_idx;
atomic_inc(&md->pending);
while (ci.sector_count)
__clone_and_map(&ci);
/* drop the extra reference count */
dec_pending(ci.io, 0);
dm_table_put(ci.map);
}
/**ltl
* 功能: 分割bio请求
* 参数:
* 返回值:
* 说明:
*/
static void __split_bio(struct mapped_device *md, struct bio *bio)
{
struct clone_info ci;
ci.map = dm_get_table(md);
if (!ci.map) {
bio_io_error(bio, bio->bi_size);
return;
}
ci.md = md;
ci.bio = bio;
ci.io = alloc_io(md);
ci.io->error = 0;
atomic_set(&ci.io->io_count, 1);
ci.io->bio = bio;
ci.io->md = md;
ci.sector = bio->bi_sector; /* 请求起始扇区 */
/* 从这里可以看出数据长度必定是512的整数倍 */
ci.sector_count = bio_sectors(bio); /* 数据长度(扇区数) */
ci.idx = bio->bi_idx; /* 当前bi_vec数组下标 */
start_io_acct(ci.io);
while (ci.sector_count) /* 分发各个请求 */
__clone_and_map(&ci);
/* drop the extra reference count */
dec_pending(ci.io, 0);
dm_table_put(ci.map);
}
/**ltl
* 功能: 映射设备的泄流处理函数
* 参数:
* 返回值:
* 说明:
*/
static void dm_unplug_all(request_queue_t *q)
{
struct mapped_device *md = q->queuedata;
struct dm_table *map = dm_get_table(md); /* 映射设备的映射表 */
if (map) {
dm_table_unplug_all(map); /* 将映射表中的所有物理设备泄流 */
dm_table_put(map);
}
}
static void dm_unplug_all(request_queue_t *q)
{
struct mapped_device *md = q->queuedata;
struct dm_table *map = dm_get_table(md);
if (map) {
dm_table_unplug_all(map);
dm_table_put(map);
}
}
static void __unbind(struct mapped_device *md)
{
struct dm_table *map = md->map;
if (!map)
return;
dm_table_event_callback(map, NULL, NULL);
write_lock(&md->map_lock);
md->map = NULL;
write_unlock(&md->map_lock);
dm_table_put(map);
}
void dm_put(struct mapped_device *md)
{
struct dm_table *map = dm_get_table(md);
if (atomic_dec_and_test(&md->holders)) {
if (!test_bit(DMF_SUSPENDED, &md->flags) && map)
dm_table_suspend_targets(map);
__unbind(md);
free_dev(md);
}
dm_table_put(map);
}
static int dm_flush_all(request_queue_t *q, struct gendisk *disk,
sector_t *error_sector)
{
struct mapped_device *md = q->queuedata;
struct dm_table *map = dm_get_table(md);
int ret = -ENXIO;
if (map) {
ret = dm_table_flush_all(map);
dm_table_put(map);
}
return ret;
}
static int dm_any_congested(void *congested_data, int bdi_bits)
{
int r;
struct mapped_device *md = (struct mapped_device *) congested_data;
struct dm_table *map = dm_get_table(md);
if (!map || test_bit(DMF_BLOCK_IO, &md->flags))
r = bdi_bits;
else
r = dm_table_any_congested(map, bdi_bits);
dm_table_put(map);
return r;
}
int dm_create_error_table(struct dm_table **result, struct mapped_device *md)
{
struct dm_table *t;
sector_t dev_size = 1;
int r;
/*
* Find current size of device.
* Default to 1 sector if inactive.
*/
t = dm_get_table(md);
if (t) {
dev_size = dm_table_get_size(t);
dm_table_put(t);
}
r = dm_table_create(&t, FMODE_READ, 1, md);
if (r)
return r;
r = dm_table_add_target(t, "error", 0, dev_size, NULL);
if (r)
goto out;
r = dm_table_complete(t);
if (r)
goto out;
*result = t;
out:
if (r)
dm_table_put(t);
return r;
}
void dm_put(struct mapped_device *md)
{
struct dm_table *map = dm_get_table(md);
if (atomic_dec_and_test(&md->holders)) {
if (!dm_suspended(md)) {
dm_table_presuspend_targets(map);
dm_table_postsuspend_targets(map);
}
__unbind(md);
free_dev(md);
}
dm_table_put(map);
}
int dm_resume(struct mapped_device *md)
{
int r = -EINVAL;
struct bio *def;
struct dm_table *map = NULL;
down(&md->suspend_lock);
if (!dm_suspended(md))
goto out;
map = dm_get_table(md);
if (!map || !dm_table_get_size(map))
goto out;
r = dm_table_resume_targets(map);
if (r)
goto out;
down_write(&md->io_lock);
clear_bit(DMF_BLOCK_IO, &md->flags);
def = bio_list_get(&md->deferred);
__flush_deferred_io(md, def);
up_write(&md->io_lock);
unlock_fs(md);
if (md->suspended_bdev) {
bdput(md->suspended_bdev);
md->suspended_bdev = NULL;
}
clear_bit(DMF_SUSPENDED, &md->flags);
dm_table_unplug_all(map);
kobject_uevent(&md->disk->kobj, KOBJ_CHANGE);
r = 0;
out:
dm_table_put(map);
up(&md->suspend_lock);
return r;
}
void dm_put(struct mapped_device *md)
{
struct dm_table *map;
BUG_ON(test_bit(DMF_FREEING, &md->flags));
if (atomic_dec_and_lock(&md->holders, &_minor_lock)) {
map = dm_get_table(md);
idr_replace(&_minor_idr, MINOR_ALLOCED, dm_disk(md)->first_minor);
set_bit(DMF_FREEING, &md->flags);
spin_unlock(&_minor_lock);
if (!dm_suspended(md)) {
dm_table_presuspend_targets(map);
dm_table_postsuspend_targets(map);
}
__unbind(md);
dm_table_put(map);
free_dev(md);
}
}
static int dm_blk_ioctl(struct inode *inode, struct file *file,
unsigned int cmd, unsigned long arg)
{
struct mapped_device *md;
struct dm_table *map;
struct dm_target *tgt;
int r = -ENOTTY;
/* We don't really need this lock, but we do need 'inode'. */
unlock_kernel();
md = inode->i_bdev->bd_disk->private_data;
map = dm_get_table(md);
if (!map || !dm_table_get_size(map))
goto out;
/* We only support devices that have a single target */
if (dm_table_get_num_targets(map) != 1)
goto out;
tgt = dm_table_get_target(map, 0);
if (dm_suspended(md)) {
r = -EAGAIN;
goto out;
}
if (tgt->type->ioctl)
r = tgt->type->ioctl(tgt, inode, file, cmd, arg);
out:
dm_table_put(map);
lock_kernel();
return r;
}
/*
* We need to be able to change a mapping table under a mounted
* filesystem. For example we might want to move some data in
* the background. Before the table can be swapped with
* dm_bind_table, dm_suspend must be called to flush any in
* flight bios and ensure that any further io gets deferred.
*/
int dm_suspend(struct mapped_device *md)
{
struct dm_table *map;
DECLARE_WAITQUEUE(wait, current);
/* Flush I/O to the device. */
down_read(&md->lock);
if (test_bit(DMF_BLOCK_IO, &md->flags)) {
up_read(&md->lock);
return -EINVAL;
}
__lock_fs(md);
up_read(&md->lock);
/*
* First we set the BLOCK_IO flag so no more ios will be
* mapped.
*/
down_write(&md->lock);
if (test_bit(DMF_BLOCK_IO, &md->flags)) {
/*
* If we get here we know another thread is
* trying to suspend as well, so we leave the fs
* locked for this thread.
*/
up_write(&md->lock);
return -EINVAL;
}
set_bit(DMF_BLOCK_IO, &md->flags);
add_wait_queue(&md->wait, &wait);
up_write(&md->lock);
/* unplug */
map = dm_get_table(md);
if (map) {
dm_table_unplug_all(map);
dm_table_put(map);
}
/*
* Then we wait for the already mapped ios to
* complete.
*/
while (1) {
set_current_state(TASK_INTERRUPTIBLE);
if (!atomic_read(&md->pending) || signal_pending(current))
break;
io_schedule();
}
set_current_state(TASK_RUNNING);
down_write(&md->lock);
remove_wait_queue(&md->wait, &wait);
/* were we interrupted ? */
if (atomic_read(&md->pending)) {
__unlock_fs(md);
clear_bit(DMF_BLOCK_IO, &md->flags);
up_write(&md->lock);
return -EINTR;
}
set_bit(DMF_SUSPENDED, &md->flags);
map = dm_get_table(md);
if (map)
dm_table_suspend_targets(map);
dm_table_put(map);
up_write(&md->lock);
return 0;
}
static void __init dm_setup_drive(void)
{
struct mapped_device *md = NULL;
struct dm_table *table = NULL;
struct dm_setup_target *target;
char *uuid = dm_setup_args.uuid;
fmode_t fmode = FMODE_READ;
/* Finish parsing the targets. */
if (dm_setup_parse_targets(dm_setup_args.targets))
goto parse_fail;
if (dm_create(dm_setup_args.minor, &md)) {
DMDEBUG("failed to create the device");
goto dm_create_fail;
}
DMDEBUG("created device '%s'", dm_device_name(md));
/* In addition to flagging the table below, the disk must be
* set explicitly ro/rw. */
set_disk_ro(dm_disk(md), dm_setup_args.ro);
if (!dm_setup_args.ro)
fmode |= FMODE_WRITE;
if (dm_table_create(&table, fmode, dm_setup_args.target_count, md)) {
DMDEBUG("failed to create the table");
goto dm_table_create_fail;
}
target = dm_setup_args.target;
while (target) {
DMINFO("adding target '%llu %llu %s %s'",
(unsigned long long) target->begin,
(unsigned long long) target->length, target->type,
target->params);
if (dm_table_add_target(table, target->type, target->begin,
target->length, target->params)) {
DMDEBUG("failed to add the target to the table");
goto add_target_fail;
}
target = target->next;
}
if (dm_table_complete(table)) {
DMDEBUG("failed to complete the table");
goto table_complete_fail;
}
/* Suspend the device so that we can bind it to the table. */
if (dm_suspend(md, 0)) {
DMDEBUG("failed to suspend the device pre-bind");
goto suspend_fail;
}
/* Bind the table to the device. This is the only way to associate
* md->map with the table and set the disk capacity directly. */
if (dm_swap_table(md, table)) { /* should return NULL. */
DMDEBUG("failed to bind the device to the table");
goto table_bind_fail;
}
/* Finally, resume and the device should be ready. */
if (dm_resume(md)) {
DMDEBUG("failed to resume the device");
goto resume_fail;
}
/* Export the dm device via the ioctl interface */
if (!strcmp(DM_NO_UUID, dm_setup_args.uuid))
uuid = NULL;
if (dm_ioctl_export(md, dm_setup_args.name, uuid)) {
DMDEBUG("failed to export device with given name and uuid");
goto export_fail;
}
printk(KERN_INFO "dm: dm-%d is ready\n", dm_setup_args.minor);
dm_setup_cleanup();
return;
export_fail:
resume_fail:
table_bind_fail:
suspend_fail:
table_complete_fail:
add_target_fail:
dm_table_put(table);
dm_table_create_fail:
dm_put(md);
dm_create_fail:
dm_setup_cleanup();
parse_fail:
printk(KERN_WARNING "dm: starting dm-%d (%s) failed\n",
dm_setup_args.minor, dm_setup_args.name);
}
/*
* We need to be able to change a mapping table under a mounted
* filesystem. For example we might want to move some data in
* the background. Before the table can be swapped with
* dm_bind_table, dm_suspend must be called to flush any in
* flight bios and ensure that any further io gets deferred.
*/
int dm_suspend(struct mapped_device *md, int do_lockfs)
{
struct dm_table *map = NULL;
DECLARE_WAITQUEUE(wait, current);
struct bio *def;
int r = -EINVAL;
down(&md->suspend_lock);
if (dm_suspended(md))
goto out;
map = dm_get_table(md);
/* This does not get reverted if there's an error later. */
dm_table_presuspend_targets(map);
md->suspended_bdev = bdget_disk(md->disk, 0);
if (!md->suspended_bdev) {
DMWARN("bdget failed in dm_suspend");
r = -ENOMEM;
goto out;
}
/* Flush I/O to the device. */
if (do_lockfs) {
r = lock_fs(md);
if (r)
goto out;
}
/*
* First we set the BLOCK_IO flag so no more ios will be mapped.
*/
down_write(&md->io_lock);
set_bit(DMF_BLOCK_IO, &md->flags);
add_wait_queue(&md->wait, &wait);
up_write(&md->io_lock);
/* unplug */
if (map)
dm_table_unplug_all(map);
/*
* Then we wait for the already mapped ios to
* complete.
*/
while (1) {
set_current_state(TASK_INTERRUPTIBLE);
if (!atomic_read(&md->pending) || signal_pending(current))
break;
io_schedule();
}
set_current_state(TASK_RUNNING);
down_write(&md->io_lock);
remove_wait_queue(&md->wait, &wait);
/* were we interrupted ? */
r = -EINTR;
if (atomic_read(&md->pending)) {
clear_bit(DMF_BLOCK_IO, &md->flags);
def = bio_list_get(&md->deferred);
__flush_deferred_io(md, def);
up_write(&md->io_lock);
unlock_fs(md);
goto out;
}
up_write(&md->io_lock);
dm_table_postsuspend_targets(map);
set_bit(DMF_SUSPENDED, &md->flags);
r = 0;
out:
if (r && md->suspended_bdev) {
bdput(md->suspended_bdev);
md->suspended_bdev = NULL;
}
dm_table_put(map);
up(&md->suspend_lock);
return r;
}
/*
* We need to be able to change a mapping table under a mounted
* filesystem. For example we might want to move some data in
* the background. Before the table can be swapped with
* dm_bind_table, dm_suspend must be called to flush any in
* flight bios and ensure that any further io gets deferred.
*/
int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
{
struct dm_table *map = NULL;
unsigned long flags;
DECLARE_WAITQUEUE(wait, current);
struct bio *def;
int r = -EINVAL;
int do_lockfs = suspend_flags & DM_SUSPEND_LOCKFS_FLAG ? 1 : 0;
int noflush = suspend_flags & DM_SUSPEND_NOFLUSH_FLAG ? 1 : 0;
down(&md->suspend_lock);
if (dm_suspended(md))
goto out_unlock;
map = dm_get_table(md);
/*
* DMF_NOFLUSH_SUSPENDING must be set before presuspend.
* This flag is cleared before dm_suspend returns.
*/
if (noflush)
set_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);
/* This does not get reverted if there's an error later. */
dm_table_presuspend_targets(map);
/* bdget() can stall if the pending I/Os are not flushed */
if (!noflush) {
md->suspended_bdev = bdget_disk(md->disk, 0);
if (!md->suspended_bdev) {
DMWARN("bdget failed in dm_suspend");
r = -ENOMEM;
goto flush_and_out;
}
}
/*
* Flush I/O to the device.
* noflush supersedes do_lockfs, because lock_fs() needs to flush I/Os.
*/
if (do_lockfs && !noflush) {
r = lock_fs(md);
if (r)
goto out;
}
/*
* First we set the BLOCK_IO flag so no more ios will be mapped.
*/
down_write(&md->io_lock);
set_bit(DMF_BLOCK_IO, &md->flags);
add_wait_queue(&md->wait, &wait);
up_write(&md->io_lock);
/* unplug */
if (map)
dm_table_unplug_all(map);
/*
* Then we wait for the already mapped ios to
* complete.
*/
while (1) {
set_current_state(TASK_INTERRUPTIBLE);
if (!atomic_read(&md->pending) || signal_pending(current))
break;
io_schedule();
}
set_current_state(TASK_RUNNING);
down_write(&md->io_lock);
remove_wait_queue(&md->wait, &wait);
if (noflush) {
spin_lock_irqsave(&md->pushback_lock, flags);
clear_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);
bio_list_merge_head(&md->deferred, &md->pushback);
bio_list_init(&md->pushback);
spin_unlock_irqrestore(&md->pushback_lock, flags);
}
/* were we interrupted ? */
r = -EINTR;
if (atomic_read(&md->pending)) {
clear_bit(DMF_BLOCK_IO, &md->flags);
def = bio_list_get(&md->deferred);
__flush_deferred_io(md, def);
up_write(&md->io_lock);
unlock_fs(md);
goto out; /* pushback list is already flushed, so skip flush */
}
up_write(&md->io_lock);
dm_table_postsuspend_targets(map);
set_bit(DMF_SUSPENDED, &md->flags);
r = 0;
flush_and_out:
if (r && noflush) {
/*
* Because there may be already I/Os in the pushback list,
* flush them before return.
*/
down_write(&md->io_lock);
spin_lock_irqsave(&md->pushback_lock, flags);
clear_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);
bio_list_merge_head(&md->deferred, &md->pushback);
bio_list_init(&md->pushback);
spin_unlock_irqrestore(&md->pushback_lock, flags);
def = bio_list_get(&md->deferred);
__flush_deferred_io(md, def);
up_write(&md->io_lock);
}
out:
if (r && md->suspended_bdev) {
bdput(md->suspended_bdev);
md->suspended_bdev = NULL;
}
dm_table_put(map);
out_unlock:
up(&md->suspend_lock);
return r;
}