blk_sysfs.c
static struct queue_sysfs_entry queue_ra_entry = {
.attr = {.name = "read_ahead_kb", .mode = S_IRUGO | S_IWUSR },
.show = queue_ra_show,
.store = queue_ra_store,
};
static struct queue_sysfs_entry queue_max_sectors_entry = {
.attr = {.name = "max_sectors_kb", .mode = S_IRUGO | S_IWUSR },
.show = queue_max_sectors_show,
.store = queue_max_sectors_store,
};
blk-map.c Functions related to mapping data to requests
static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs)
{
return bio_alloc_bioset(gfp_mask, nr_iovecs, NULL);
}
blk_rq_map_user_iov - map user data to a request, for REQ_TYPE_BLOCK_PC usage
scsi_ioctl.c
static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
struct sg_io_hdr *hdr, fmode_t mode);
scst/sg.c
static int sg_start_req(Sg_request *srp, unsigned char *cmd);
=> scsi_dispatch_cmd
=> scsi_request_fn
=> __blk_run_queue_uncond
=> __blk_run_queue
=> blk_queue_bio
=> generic_make_request
=> submit_bio
=> submit_bh
* generic_make_request - hand a buffer to its device driver for I/O
* @bio: The bio describing the location in memory and on the device.
*
* generic_make_request() is used to make I/O requests of block
* devices. It is passed a &struct bio, which describes the I/O that needs
* to be done.
submit_bio - submit a bio to the block device layer for I/O
void submit_bio(int rw, struct bio *bio);
void generic_make_request(struct bio *bio);
在每个进程的task_struct中，都包含有两个变量----struct bio *bio_list，实际的提交操作会由generic_make_request()调用__generic_make_request()函数完成。
/* stacked block device info */
struct bio_list *bio_list;
/**
* generic_make_request - hand a buffer to its device driver for I/O
* @bio: The bio describing the location in memory and on the device.
*
* generic_make_request() is used to make I/O requests of block
* devices. It is passed a &struct bio, which describes the I/O that needs
* to be done.
*
* generic_make_request() does not return any status. The
* success/failure status of the request, along with notification of
* completion, is delivered asynchronously through the bio->bi_end_io
* function described (one day) else where.
*
* The caller of generic_make_request must make sure that bi_io_vec
* are set to describe the memory buffer, and that bi_dev and bi_sector are
* set to describe the device address, and the
* bi_end_io and optionally bi_private are set to describe how
* completion notification should be signaled.
*
* generic_make_request and the drivers it calls may use bi_next if this
* bio happens to be merged with someone else, and may resubmit the bio to
* a lower device by calling into generic_make_request recursively, which
* means the bio should NOT be touched after the call to ->make_request_fn.
*/
void generic_make_request(struct bio *bio)
{
struct bio_list bio_list_on_stack;
if (!generic_make_request_checks(bio))
return;
/*
* We only want one ->make_request_fn to be active at a time, else
* stack usage with stacked devices could be a problem. So use
* current->bio_list to keep a list of requests submited by a
* make_request_fn function. current->bio_list is also used as a
* flag to say if generic_make_request is currently active in this
* task or not. If it is NULL, then no make_request is active. If
* it is non-NULL, then a make_request is active, and new requests
* should be added at the tail
*/
if (current->bio_list) {
bio_list_add(current->bio_list, bio);
return;
}
/* following loop may be a bit non-obvious, and so deserves some
* explanation.
* Before entering the loop, bio->bi_next is NULL (as all callers
* ensure that) so we have a list with a single bio.
* We pretend that we have just taken it off a longer list, so
* we assign bio_list to a pointer to the bio_list_on_stack,
* thus initialising the bio_list of new bios to be
* added. ->make_request() may indeed add some more bios
* through a recursive call to generic_make_request. If it
* did, we find a non-NULL value in bio_list and re-enter the loop
* from the top. In this case we really did just take the bio
* of the top of the list (no pretending) and so remove it from
* bio_list, and call into ->make_request() again.
*/
BUG_ON(bio->bi_next);
bio_list_init(&bio_list_on_stack);
current->bio_list = &bio_list_on_stack;
do {
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
将bio发送给disk，调用blk_queue_bio
q->make_request_fn(q, bio);
bio = bio_list_pop(current->bio_list);
} while (bio);
current->bio_list = NULL; /* deactivate */
}
void blk_queue_bio(struct request_queue *q, struct bio *bio)
{
const bool sync = !!(bio->bi_rw & REQ_SYNC);
struct blk_plug *plug;
int el_ret, rw_flags, where = ELEVATOR_INSERT_SORT;
struct request *req;
unsigned int request_count = 0;
/*
* low level driver can indicate that it wants pages above a
* certain limit bounced to low memory (ie for highmem, or even
* ISA dma in theory)
*/
blk_queue_bounce(q, &bio);
if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
bio_endio(bio, -EIO);
return;
}
if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
spin_lock_irq(q->queue_lock);
where = ELEVATOR_INSERT_FLUSH;
goto get_rq;
}
/*
* Check if we can merge with the plugged list before grabbing
* any locks.
*/
if (blk_attempt_plug_merge(q, bio, &request_count))
return;
spin_lock_irq(q->queue_lock);
el_ret = elv_merge(q, &req, bio);
if (el_ret == ELEVATOR_BACK_MERGE) {
if (bio_attempt_back_merge(q, req, bio)) {
elv_bio_merged(q, req, bio);
if (!attempt_back_merge(q, req))
elv_merged_request(q, req, el_ret);
goto out_unlock;
}
} else if (el_ret == ELEVATOR_FRONT_MERGE) {
if (bio_attempt_front_merge(q, req, bio)) {
elv_bio_merged(q, req, bio);
if (!attempt_front_merge(q, req))
elv_merged_request(q, req, el_ret);
goto out_unlock;
}
}
get_rq:
/*
* This sync check and mask will be re-done in init_request_from_bio(),
* but we need to set it earlier to expose the sync flag to the
* rq allocator and io schedulers.
*/
rw_flags = bio_data_dir(bio);
if (sync)
rw_flags |= REQ_SYNC;
/*
* Grab a free request. This is might sleep but can not fail.
* Returns with the queue unlocked.
*/
req = get_request(q, rw_flags, bio, GFP_NOIO);
if (unlikely(!req)) {
bio_endio(bio, -ENODEV); /* @q is dead */
goto out_unlock;
}
/*
* After dropping the lock and possibly sleeping here, our request
* may now be mergeable after it had proven unmergeable (above).
* We don't worry about that case for efficiency. It won't happen
* often, and the elevators are able to handle it.
*/
init_request_from_bio(req, bio);
if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags))
req->cpu = raw_smp_processor_id();
plug = current->plug;
if (plug) {
/*
* If this is the first request added after a plug, fire
* of a plug trace. If others have been added before, check
* if we have multiple devices in this plug. If so, make a
* note to sort the list before dispatch.
*/
if (list_empty(&plug->list))
trace_block_plug(q);
else {
if (request_count >= BLK_MAX_REQUEST_COUNT) {
blk_flush_plug_list(plug, false);
trace_block_plug(q);
}
}
list_add_tail(&req->queuelist, &plug->list);
blk_account_io_start(req, true);
} else {
spin_lock_irq(q->queue_lock);
add_acct_request(q, req, where);
__blk_run_queue(q);
out_unlock:
spin_unlock_irq(q->queue_lock);
}
}
/**
* __blk_run_queue - run a single device queue
* @q: The queue to run
*
* Description:
* See @blk_run_queue. This variant must be called with the queue lock
* held and interrupts disabled.
*/
void __blk_run_queue(struct request_queue *q)
{
if (unlikely(blk_queue_stopped(q)))
return;
__blk_run_queue_uncond(q);
}
/**
* __blk_run_queue_uncond - run a queue whether or not it has been stopped
* @q:The queue to run
*
* Description:
* Invoke request handling on a queue if there are any pending requests.
* May be used to restart request handling after a request has completed.
* This variant runs the queue whether or not the queue has been
* stopped. Must be called with the queue lock held and interrupts
* disabled. See also @blk_run_queue.
*/
inline void __blk_run_queue_uncond(struct request_queue *q)
{
if (unlikely(blk_queue_dead(q)))
return;
/*
* Some request_fn implementations, e.g. scsi_request_fn(), unlock
* the queue lock internally. As a result multiple threads may be
* running such a request function concurrently. Keep track of the
* number of active request_fn invocations such that blk_drain_queue()
* can wait until all these request_fn calls have finished.
*/
q->request_fn_active++;
调用请求处理函数
q->request_fn(q);
q->request_fn_active--;
}