mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-25 22:40:51 +07:00
320ae51fee
Linux currently has two models for block devices: - The classic request_fn based approach, where drivers use struct request units for IO. The block layer provides various helper functionalities to let drivers share code, things like tag management, timeout handling, queueing, etc. - The "stacked" approach, where a driver squeezes in between the block layer and IO submitter. Since this bypasses the IO stack, driver generally have to manage everything themselves. With drivers being written for new high IOPS devices, the classic request_fn based driver doesn't work well enough. The design dates back to when both SMP and high IOPS was rare. It has problems with scaling to bigger machines, and runs into scaling issues even on smaller machines when you have IOPS in the hundreds of thousands per device. The stacked approach is then most often selected as the model for the driver. But this means that everybody has to re-invent everything, and along with that we get all the problems again that the shared approach solved. This commit introduces blk-mq, block multi queue support. The design is centered around per-cpu queues for queueing IO, which then funnel down into x number of hardware submission queues. We might have a 1:1 mapping between the two, or it might be an N:M mapping. That all depends on what the hardware supports. blk-mq provides various helper functions, which include: - Scalable support for request tagging. Most devices need to be able to uniquely identify a request both in the driver and to the hardware. The tagging uses per-cpu caches for freed tags, to enable cache hot reuse. - Timeout handling without tracking request on a per-device basis. Basically the driver should be able to get a notification, if a request happens to fail. - Optional support for non 1:1 mappings between issue and submission queues. blk-mq can redirect IO completions to the desired location. - Support for per-request payloads. Drivers almost always need to associate a request structure with some driver private command structure. Drivers can tell blk-mq this at init time, and then any request handed to the driver will have the required size of memory associated with it. - Support for merging of IO, and plugging. The stacked model gets neither of these. Even for high IOPS devices, merging sequential IO reduces per-command overhead and thus increases bandwidth. For now, this is provided as a potential 3rd queueing model, with the hope being that, as it matures, it can replace both the classic and stacked model. That would get us back to having just 1 real model for block devices, leaving the stacked approach to dm/md devices (as it was originally intended). Contributions in this patch from the following people: Shaohua Li <shli@fusionio.com> Alexander Gordeev <agordeev@redhat.com> Christoph Hellwig <hch@infradead.org> Mike Christie <michaelc@cs.wisc.edu> Matias Bjorling <m@bjorling.me> Jeff Moyer <jmoyer@redhat.com> Acked-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
134 lines
3.2 KiB
C
134 lines
3.2 KiB
C
/*
|
|
* Functions related to setting various queue properties from drivers
|
|
*/
|
|
#include <linux/kernel.h>
|
|
#include <linux/module.h>
|
|
#include <linux/bio.h>
|
|
#include <linux/blkdev.h>
|
|
#include <linux/blk-mq.h>
|
|
#include <linux/sched/sysctl.h>
|
|
|
|
#include "blk.h"
|
|
|
|
/*
|
|
* for max sense size
|
|
*/
|
|
#include <scsi/scsi_cmnd.h>
|
|
|
|
/**
|
|
* blk_end_sync_rq - executes a completion event on a request
|
|
* @rq: request to complete
|
|
* @error: end I/O status of the request
|
|
*/
|
|
static void blk_end_sync_rq(struct request *rq, int error)
|
|
{
|
|
struct completion *waiting = rq->end_io_data;
|
|
|
|
rq->end_io_data = NULL;
|
|
|
|
/*
|
|
* complete last, if this is a stack request the process (and thus
|
|
* the rq pointer) could be invalid right after this complete()
|
|
*/
|
|
complete(waiting);
|
|
}
|
|
|
|
/**
|
|
* blk_execute_rq_nowait - insert a request into queue for execution
|
|
* @q: queue to insert the request in
|
|
* @bd_disk: matching gendisk
|
|
* @rq: request to insert
|
|
* @at_head: insert request at head or tail of queue
|
|
* @done: I/O completion handler
|
|
*
|
|
* Description:
|
|
* Insert a fully prepared request at the back of the I/O scheduler queue
|
|
* for execution. Don't wait for completion.
|
|
*
|
|
* Note:
|
|
* This function will invoke @done directly if the queue is dead.
|
|
*/
|
|
void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
|
|
struct request *rq, int at_head,
|
|
rq_end_io_fn *done)
|
|
{
|
|
int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
|
|
bool is_pm_resume;
|
|
|
|
WARN_ON(irqs_disabled());
|
|
|
|
rq->rq_disk = bd_disk;
|
|
rq->end_io = done;
|
|
|
|
if (q->mq_ops) {
|
|
blk_mq_insert_request(q, rq, true);
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* need to check this before __blk_run_queue(), because rq can
|
|
* be freed before that returns.
|
|
*/
|
|
is_pm_resume = rq->cmd_type == REQ_TYPE_PM_RESUME;
|
|
|
|
spin_lock_irq(q->queue_lock);
|
|
|
|
if (unlikely(blk_queue_dying(q))) {
|
|
rq->cmd_flags |= REQ_QUIET;
|
|
rq->errors = -ENXIO;
|
|
__blk_end_request_all(rq, rq->errors);
|
|
spin_unlock_irq(q->queue_lock);
|
|
return;
|
|
}
|
|
|
|
__elv_add_request(q, rq, where);
|
|
__blk_run_queue(q);
|
|
/* the queue is stopped so it won't be run */
|
|
if (is_pm_resume)
|
|
__blk_run_queue_uncond(q);
|
|
spin_unlock_irq(q->queue_lock);
|
|
}
|
|
EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);
|
|
|
|
/**
|
|
* blk_execute_rq - insert a request into queue for execution
|
|
* @q: queue to insert the request in
|
|
* @bd_disk: matching gendisk
|
|
* @rq: request to insert
|
|
* @at_head: insert request at head or tail of queue
|
|
*
|
|
* Description:
|
|
* Insert a fully prepared request at the back of the I/O scheduler queue
|
|
* for execution and wait for completion.
|
|
*/
|
|
int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
|
|
struct request *rq, int at_head)
|
|
{
|
|
DECLARE_COMPLETION_ONSTACK(wait);
|
|
char sense[SCSI_SENSE_BUFFERSIZE];
|
|
int err = 0;
|
|
unsigned long hang_check;
|
|
|
|
if (!rq->sense) {
|
|
memset(sense, 0, sizeof(sense));
|
|
rq->sense = sense;
|
|
rq->sense_len = 0;
|
|
}
|
|
|
|
rq->end_io_data = &wait;
|
|
blk_execute_rq_nowait(q, bd_disk, rq, at_head, blk_end_sync_rq);
|
|
|
|
/* Prevent hang_check timer from firing at us during very long I/O */
|
|
hang_check = sysctl_hung_task_timeout_secs;
|
|
if (hang_check)
|
|
while (!wait_for_completion_io_timeout(&wait, hang_check * (HZ/2)));
|
|
else
|
|
wait_for_completion_io(&wait);
|
|
|
|
if (rq->errors)
|
|
err = -EIO;
|
|
|
|
return err;
|
|
}
|
|
EXPORT_SYMBOL(blk_execute_rq);
|