/*
* q->request_fn for old request-based dm.
* Called with the queue lock held.
*/
static void dm_old_request_fn(struct request_queue *q)
{
struct mapped_device *md = q->queuedata;
struct dm_target *ti = md->immutable_target;
struct request *rq;
struct dm_rq_target_io *tio;
sector_t pos = 0;
if (unlikely(!ti)) {
int srcu_idx;
struct dm_table *map = dm_get_live_table(md, &srcu_idx);
if (unlikely(!map)) {
dm_put_live_table(md, srcu_idx);
return;
}
ti = dm_table_find_target(map, pos);
dm_put_live_table(md, srcu_idx);
}
/*
* For suspend, check blk_queue_stopped() and increment
* ->pending within a single queue_lock not to increment the
* number of in-flight I/Os after the queue is stopped in
* dm_suspend().
*/
while (!blk_queue_stopped(q)) {
rq = blk_peek_request(q);
if (!rq)
return;
/* always use block 0 to find the target for flushes for now */
pos = 0;
if (req_op(rq) != REQ_OP_FLUSH)
pos = blk_rq_pos(rq);
if ((dm_old_request_peeked_before_merge_deadline(md) &&
md_in_flight(md) && rq->bio && !bio_multiple_segments(rq->bio) &&
md->last_rq_pos == pos && md->last_rq_rw == rq_data_dir(rq)) ||
(ti->type->busy && ti->type->busy(ti))) {
blk_delay_queue(q, 10);
return;
}
dm_start_request(md, rq);
tio = tio_from_request(rq);
init_tio(tio, rq, md);
/* Establish tio->ti before queuing work (map_tio_request) */
tio->ti = ti;
kthread_queue_work(&md->kworker, &tio->work);
BUG_ON(!irqs_disabled());
}
}
static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
struct request *rq = bd->rq;
struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
struct mapped_device *md = tio->md;
struct dm_target *ti = md->immutable_target;
if (unlikely(!ti)) {
int srcu_idx;
struct dm_table *map = dm_get_live_table(md, &srcu_idx);
ti = dm_table_find_target(map, 0);
dm_put_live_table(md, srcu_idx);
}
/*
* On suspend dm_stop_queue() handles stopping the blk-mq
* request_queue BUT: even though the hw_queues are marked
* BLK_MQ_S_STOPPED at that point there is still a race that
* is allowing block/blk-mq.c to call ->queue_rq against a
* hctx that it really shouldn't. The following check guards
* against this rarity (albeit _not_ race-free).
*/
if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
return BLK_MQ_RQ_QUEUE_BUSY;
if (ti->type->busy && ti->type->busy(ti))
return BLK_MQ_RQ_QUEUE_BUSY;
dm_start_request(md, rq);
/* Init tio using md established in .init_request */
init_tio(tio, rq, md);
/*
* Establish tio->ti before calling map_request().
*/
tio->ti = ti;
/* Direct call is fine since .queue_rq allows allocations */
if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE) {
/* Undo dm_start_request() before requeuing */
rq_end_stats(md, rq);
rq_completed(md, rq_data_dir(rq), false);
return BLK_MQ_RQ_QUEUE_BUSY;
}
return BLK_MQ_RQ_QUEUE_OK;
}
static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
struct request *rq = bd->rq;
struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
struct mapped_device *md = tio->md;
struct dm_target *ti = md->immutable_target;
if (unlikely(!ti)) {
int srcu_idx;
struct dm_table *map = dm_get_live_table(md, &srcu_idx);
ti = dm_table_find_target(map, 0);
dm_put_live_table(md, srcu_idx);
}
if (ti->type->busy && ti->type->busy(ti))
return BLK_MQ_RQ_QUEUE_BUSY;
dm_start_request(md, rq);
/* Init tio using md established in .init_request */
init_tio(tio, rq, md);
/*
* Establish tio->ti before calling map_request().
*/
tio->ti = ti;
/* Direct call is fine since .queue_rq allows allocations */
if (map_request(tio) == DM_MAPIO_REQUEUE) {
/* Undo dm_start_request() before requeuing */
rq_end_stats(md, rq);
rq_completed(md, rq_data_dir(rq), false);
blk_mq_delay_run_hw_queue(hctx, 100/*ms*/);
return BLK_MQ_RQ_QUEUE_BUSY;
}
return BLK_MQ_RQ_QUEUE_OK;
}
static void __clone_and_map(struct clone_info *ci)
{
struct bio *clone, *bio = ci->bio;
struct dm_target *ti = dm_table_find_target(ci->map, ci->sector);
sector_t len = 0, max = max_io_len(ci->md, ci->sector, ti);
struct target_io *tio;
/*
* Allocate a target io object.
*/
tio = alloc_tio(ci->md);
tio->io = ci->io;
tio->ti = ti;
memset(&tio->info, 0, sizeof(tio->info));
if (ci->sector_count <= max) {
/*
* Optimise for the simple case where we can do all of
* the remaining io with a single clone.
*/
clone = clone_bio(bio, ci->sector, ci->idx,
bio->bi_vcnt - ci->idx, ci->sector_count);
__map_bio(ti, clone, tio);
ci->sector_count = 0;
} else if (to_sector(bio->bi_io_vec[ci->idx].bv_len) <= max) {
/*
* There are some bvecs that don't span targets.
* Do as many of these as possible.
*/
int i;
sector_t remaining = max;
sector_t bv_len;
for (i = ci->idx; remaining && (i < bio->bi_vcnt); i++) {
bv_len = to_sector(bio->bi_io_vec[i].bv_len);
if (bv_len > remaining)
break;
remaining -= bv_len;
len += bv_len;
}
clone = clone_bio(bio, ci->sector, ci->idx, i - ci->idx, len);
__map_bio(ti, clone, tio);
ci->sector += len;
ci->sector_count -= len;
ci->idx = i;
} else {
/*
* Create two copy bios to deal with io that has
* been split across a target.
*/
struct bio_vec *bv = bio->bi_io_vec + ci->idx;
clone = split_bvec(bio, ci->sector, ci->idx,
bv->bv_offset, max);
__map_bio(ti, clone, tio);
ci->sector += max;
ci->sector_count -= max;
ti = dm_table_find_target(ci->map, ci->sector);
len = to_sector(bv->bv_len) - max;
clone = split_bvec(bio, ci->sector, ci->idx,
bv->bv_offset + to_bytes(max), len);
tio = alloc_tio(ci->md);
tio->io = ci->io;
tio->ti = ti;
memset(&tio->info, 0, sizeof(tio->info));
__map_bio(ti, clone, tio);
ci->sector += len;
ci->sector_count -= len;
ci->idx++;
}
}
static void __clone_and_map(struct clone_info *ci)
{
struct bio *clone, *bio = ci->bio;
struct dm_target *ti = dm_table_find_target(ci->map, ci->sector);
sector_t len = 0, max = max_io_len(ci->md, ci->sector, ti);
struct target_io *tio;
/*
* Allocate a target io object.
*/
tio = alloc_tio(ci->md);
tio->io = ci->io;
tio->ti = ti;
memset(&tio->info, 0, sizeof(tio->info));
if (ci->sector_count <= max) {
/*
* Optimise for the simple case where we can do all of
* the remaining io with a single clone.
*/
clone = clone_bio(bio, ci->sector, ci->idx,
bio->bi_vcnt - ci->idx, ci->sector_count,
ci->md->bs);
__map_bio(ti, clone, tio);
ci->sector_count = 0;
} else if (to_sector(bio->bi_io_vec[ci->idx].bv_len) <= max) {
/*
* There are some bvecs that don't span targets.
* Do as many of these as possible.
*/
int i;
sector_t remaining = max;
sector_t bv_len;
for (i = ci->idx; remaining && (i < bio->bi_vcnt); i++) {
bv_len = to_sector(bio->bi_io_vec[i].bv_len);
if (bv_len > remaining)
break;
remaining -= bv_len;
len += bv_len;
}
clone = clone_bio(bio, ci->sector, ci->idx, i - ci->idx, len,
ci->md->bs);
__map_bio(ti, clone, tio);
ci->sector += len;
ci->sector_count -= len;
ci->idx = i;
} else {
/*
* Handle a bvec that must be split between two or more targets.
*/
struct bio_vec *bv = bio->bi_io_vec + ci->idx;
sector_t remaining = to_sector(bv->bv_len);
unsigned int offset = 0;
do {
if (offset) {
ti = dm_table_find_target(ci->map, ci->sector);
max = max_io_len(ci->md, ci->sector, ti);
tio = alloc_tio(ci->md);
tio->io = ci->io;
tio->ti = ti;
memset(&tio->info, 0, sizeof(tio->info));
}
len = min(remaining, max);
clone = split_bvec(bio, ci->sector, ci->idx,
bv->bv_offset + offset, len,
ci->md->bs);
__map_bio(ti, clone, tio);
ci->sector += len;
ci->sector_count -= len;
offset += to_bytes(len);
} while (remaining -= len);
ci->idx++;
}
}
/**ltl
* 功能: 将bio请求分割成多个bio，并分发到多个目标设备中
* 参数:
* 返回值:
* 说明: 此
*/
static void __clone_and_map(struct clone_info *ci)
{
struct bio *clone, *bio = ci->bio;
/* 根据请求的起始扇区获取目标设备 */
struct dm_target *ti = dm_table_find_target(ci->map, ci->sector);
sector_t len = 0, max = max_io_len(ci->md, ci->sector, ti); /* 可以请求的最大数据长度 */
struct target_io *tio;
/*
* Allocate a target io object.
*/
tio = alloc_tio(ci->md);
tio->io = ci->io;
tio->ti = ti;
memset(&tio->info, 0, sizeof(tio->info));
/* [step1]请求的数据长度没有超出目标设备的剩下的数据长度，则一次操作就可以完成 */
if (ci->sector_count <= max) {
/*
* Optimise for the simple case where we can do all of
* the remaining io with a single clone.
*/
/* 拷贝bio对象 */
clone = clone_bio(bio, ci->sector, ci->idx,
bio->bi_vcnt - ci->idx, ci->sector_count);
/* 将新的bio请求映射为目标设备的请求 */
__map_bio(ti, clone, tio);
ci->sector_count = 0;
}/*[step2]请求的数据长度已经超过目标设备空间，但是idx下标所指的数组项在目标设备空间范围之内 */
else if (to_sector(bio->bi_io_vec[ci->idx].bv_len) <= max) {
/*
* There are some bvecs that don't span targets.
* Do as many of these as possible.
*/
int i;
sector_t remaining = max;
sector_t bv_len;
/* 求出在此目标设备可以传输的最大数据长度 */
for (i = ci->idx; remaining && (i < bio->bi_vcnt); i++) {
bv_len = to_sector(bio->bi_io_vec[i].bv_len);
/* 此bio_vec的数据长度已经超出目标设备的空间
* 表明bio->bi_io_vec[i]中的数据跨越两个目标设备，因此剩余数据要走[step3]中的流程
*/
if (bv_len > remaining)
break;
remaining -= bv_len;
len += bv_len;
}
/* 克隆bio对象 */
clone = clone_bio(bio, ci->sector, ci->idx, i - ci->idx, len);
/* 将bio对象映射到目标设备 */
__map_bio(ti, clone, tio);
/* 剩下请求的起始扇区 */
ci->sector += len;
/* 剩下的扇区数，若此字段不为0，则会转到[step3]执行 */
ci->sector_count -= len;
/* 数据下标 */
ci->idx = i;
}
else
{/* [step3]表示bio->bi_io_vec[i]请求数据跨越了两个目标设备，因此要对其分割 */
/*
* Handle a bvec that must be split between two or more targets.
*/
/* 跨越两个目标设备的bio_vec对象 */
struct bio_vec *bv = bio->bi_io_vec + ci->idx;
/* 数据长度 */
sector_t remaining = to_sector(bv->bv_len);
unsigned int offset = 0;
/* 将bio_vec分割成多份，分发到目标设备中 */
do {
if (offset) {
ti = dm_table_find_target(ci->map, ci->sector); /* 在btree中查找 */
max = max_io_len(ci->md, ci->sector, ti);
tio = alloc_tio(ci->md);
tio->io = ci->io;
tio->ti = ti;
memset(&tio->info, 0, sizeof(tio->info));
}
len = min(remaining, max); /* 数据长度 */
/* 分割bio_vec请求 */
clone = split_bvec(bio, ci->sector, ci->idx,
bv->bv_offset + offset, len);
/* 将请求映射到目标设备 */
__map_bio(ti, clone, tio);
ci->sector += len; /* dm的起始扇区号 */
ci->sector_count -= len; /* 剩下的扇区数 */
offset += to_bytes(len); /* bio_vec的数据偏移量 */
} while (remaining -= len);
/* 将下标指向下了个bio_vec数组项 */
ci->idx++;
}
}