30a91cb4ef
Rework I/O completions to work more like the old code path. blk_mq_end_io now stays out of the business of deferring completions to others CPUs and calling blk_mark_rq_complete. The latter is very important to allow completing requests that have timed out and thus are already marked completed, the former allows using the IPI callout even for driver specific completions instead of having to reimplement them. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
220 lines
5.1 KiB
C
220 lines
5.1 KiB
C
/*
|
|
* Functions related to generic timeout handling of requests.
|
|
*/
|
|
#include <linux/kernel.h>
|
|
#include <linux/module.h>
|
|
#include <linux/blkdev.h>
|
|
#include <linux/fault-inject.h>
|
|
|
|
#include "blk.h"
|
|
#include "blk-mq.h"
|
|
|
|
#ifdef CONFIG_FAIL_IO_TIMEOUT
|
|
|
|
static DECLARE_FAULT_ATTR(fail_io_timeout);
|
|
|
|
static int __init setup_fail_io_timeout(char *str)
|
|
{
|
|
return setup_fault_attr(&fail_io_timeout, str);
|
|
}
|
|
__setup("fail_io_timeout=", setup_fail_io_timeout);
|
|
|
|
int blk_should_fake_timeout(struct request_queue *q)
|
|
{
|
|
if (!test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags))
|
|
return 0;
|
|
|
|
return should_fail(&fail_io_timeout, 1);
|
|
}
|
|
|
|
static int __init fail_io_timeout_debugfs(void)
|
|
{
|
|
struct dentry *dir = fault_create_debugfs_attr("fail_io_timeout",
|
|
NULL, &fail_io_timeout);
|
|
|
|
return PTR_ERR_OR_ZERO(dir);
|
|
}
|
|
|
|
late_initcall(fail_io_timeout_debugfs);
|
|
|
|
ssize_t part_timeout_show(struct device *dev, struct device_attribute *attr,
|
|
char *buf)
|
|
{
|
|
struct gendisk *disk = dev_to_disk(dev);
|
|
int set = test_bit(QUEUE_FLAG_FAIL_IO, &disk->queue->queue_flags);
|
|
|
|
return sprintf(buf, "%d\n", set != 0);
|
|
}
|
|
|
|
ssize_t part_timeout_store(struct device *dev, struct device_attribute *attr,
|
|
const char *buf, size_t count)
|
|
{
|
|
struct gendisk *disk = dev_to_disk(dev);
|
|
int val;
|
|
|
|
if (count) {
|
|
struct request_queue *q = disk->queue;
|
|
char *p = (char *) buf;
|
|
|
|
val = simple_strtoul(p, &p, 10);
|
|
spin_lock_irq(q->queue_lock);
|
|
if (val)
|
|
queue_flag_set(QUEUE_FLAG_FAIL_IO, q);
|
|
else
|
|
queue_flag_clear(QUEUE_FLAG_FAIL_IO, q);
|
|
spin_unlock_irq(q->queue_lock);
|
|
}
|
|
|
|
return count;
|
|
}
|
|
|
|
#endif /* CONFIG_FAIL_IO_TIMEOUT */
|
|
|
|
/*
|
|
* blk_delete_timer - Delete/cancel timer for a given function.
|
|
* @req: request that we are canceling timer for
|
|
*
|
|
*/
|
|
void blk_delete_timer(struct request *req)
|
|
{
|
|
list_del_init(&req->timeout_list);
|
|
}
|
|
|
|
static void blk_rq_timed_out(struct request *req)
|
|
{
|
|
struct request_queue *q = req->q;
|
|
enum blk_eh_timer_return ret = BLK_EH_RESET_TIMER;
|
|
|
|
if (q->rq_timed_out_fn)
|
|
ret = q->rq_timed_out_fn(req);
|
|
switch (ret) {
|
|
case BLK_EH_HANDLED:
|
|
/* Can we use req->errors here? */
|
|
if (q->mq_ops)
|
|
__blk_mq_complete_request(req);
|
|
else
|
|
__blk_complete_request(req);
|
|
break;
|
|
case BLK_EH_RESET_TIMER:
|
|
if (q->mq_ops)
|
|
blk_mq_add_timer(req);
|
|
else
|
|
blk_add_timer(req);
|
|
|
|
blk_clear_rq_complete(req);
|
|
break;
|
|
case BLK_EH_NOT_HANDLED:
|
|
/*
|
|
* LLD handles this for now but in the future
|
|
* we can send a request msg to abort the command
|
|
* and we can move more of the generic scsi eh code to
|
|
* the blk layer.
|
|
*/
|
|
break;
|
|
default:
|
|
printk(KERN_ERR "block: bad eh return: %d\n", ret);
|
|
break;
|
|
}
|
|
}
|
|
|
|
void blk_rq_check_expired(struct request *rq, unsigned long *next_timeout,
|
|
unsigned int *next_set)
|
|
{
|
|
if (time_after_eq(jiffies, rq->deadline)) {
|
|
list_del_init(&rq->timeout_list);
|
|
|
|
/*
|
|
* Check if we raced with end io completion
|
|
*/
|
|
if (!blk_mark_rq_complete(rq))
|
|
blk_rq_timed_out(rq);
|
|
} else if (!*next_set || time_after(*next_timeout, rq->deadline)) {
|
|
*next_timeout = rq->deadline;
|
|
*next_set = 1;
|
|
}
|
|
}
|
|
|
|
void blk_rq_timed_out_timer(unsigned long data)
|
|
{
|
|
struct request_queue *q = (struct request_queue *) data;
|
|
unsigned long flags, next = 0;
|
|
struct request *rq, *tmp;
|
|
int next_set = 0;
|
|
|
|
spin_lock_irqsave(q->queue_lock, flags);
|
|
|
|
list_for_each_entry_safe(rq, tmp, &q->timeout_list, timeout_list)
|
|
blk_rq_check_expired(rq, &next, &next_set);
|
|
|
|
if (next_set)
|
|
mod_timer(&q->timeout, round_jiffies_up(next));
|
|
|
|
spin_unlock_irqrestore(q->queue_lock, flags);
|
|
}
|
|
|
|
/**
|
|
* blk_abort_request -- Request request recovery for the specified command
|
|
* @req: pointer to the request of interest
|
|
*
|
|
* This function requests that the block layer start recovery for the
|
|
* request by deleting the timer and calling the q's timeout function.
|
|
* LLDDs who implement their own error recovery MAY ignore the timeout
|
|
* event if they generated blk_abort_req. Must hold queue lock.
|
|
*/
|
|
void blk_abort_request(struct request *req)
|
|
{
|
|
if (blk_mark_rq_complete(req))
|
|
return;
|
|
blk_delete_timer(req);
|
|
blk_rq_timed_out(req);
|
|
}
|
|
EXPORT_SYMBOL_GPL(blk_abort_request);
|
|
|
|
void __blk_add_timer(struct request *req, struct list_head *timeout_list)
|
|
{
|
|
struct request_queue *q = req->q;
|
|
unsigned long expiry;
|
|
|
|
if (!q->rq_timed_out_fn)
|
|
return;
|
|
|
|
BUG_ON(!list_empty(&req->timeout_list));
|
|
|
|
/*
|
|
* Some LLDs, like scsi, peek at the timeout to prevent a
|
|
* command from being retried forever.
|
|
*/
|
|
if (!req->timeout)
|
|
req->timeout = q->rq_timeout;
|
|
|
|
req->deadline = jiffies + req->timeout;
|
|
if (timeout_list)
|
|
list_add_tail(&req->timeout_list, timeout_list);
|
|
|
|
/*
|
|
* If the timer isn't already pending or this timeout is earlier
|
|
* than an existing one, modify the timer. Round up to next nearest
|
|
* second.
|
|
*/
|
|
expiry = round_jiffies_up(req->deadline);
|
|
|
|
if (!timer_pending(&q->timeout) ||
|
|
time_before(expiry, q->timeout.expires))
|
|
mod_timer(&q->timeout, expiry);
|
|
|
|
}
|
|
|
|
/**
|
|
* blk_add_timer - Start timeout timer for a single request
|
|
* @req: request that is about to start running.
|
|
*
|
|
* Notes:
|
|
* Each request has its own timer, and as it is added to the queue, we
|
|
* set up the timer. When the request completes, we cancel the timer.
|
|
*/
|
|
void blk_add_timer(struct request *req)
|
|
{
|
|
__blk_add_timer(req, &req->q->timeout_list);
|
|
}
|
|
|