hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

s390/scm_blk: fix request number accounting 

If a block device driver cannot fetch all requests from the blocklayer
it's in his responsibility to call the request function at a later time.
Normally this would be done after the next irq for the underlying device
is handled. However in situations where we have no outstanding request
we have to schedule the request function for a later time.

This is determined using an internal counter of requests issued to the
hardware.

In some cases where we give a request back to the block layer unhandled
the number of queued requests was not adjusted. Fix this class of
failures by adjusting queued_requests in all functions used to give
a request back to the block layer.

Reviewed-by: Peter Oberparleiter <peter.oberparleiter@de.ibm.com>
Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: Peter Oberparleiter <peter.oberparleiter@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
This commit is contained in:
Sebastian Ott 2013-02-28 12:07:27 +01:00 committed by Martin Schwidefsky
parent f6a70a0707
commit 8360cb5f38
1 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
drivers/s390/block/scm_blk.c
View File

@ -195,14 +195,18 @@ void scm_request_requeue(struct scm_request *scmrq)
scm_release_cluster(scmrq);
blk_requeue_request(bdev->rq, scmrq->request);
atomic_dec(&bdev->queued_reqs);
scm_request_done(scmrq);
scm_ensure_queue_restart(bdev);
}
void scm_request_finish(struct scm_request *scmrq)
{
struct scm_blk_dev *bdev = scmrq->bdev;
scm_release_cluster(scmrq);
blk_end_request_all(scmrq->request, scmrq->error);
atomic_dec(&bdev->queued_reqs);
scm_request_done(scmrq);
}
@ -231,11 +235,13 @@ static void scm_blk_request(struct request_queue *rq)
return;
}
if (scm_need_cluster_request(scmrq)) {
atomic_inc(&bdev->queued_reqs);
blk_start_request(req);
scm_initiate_cluster_request(scmrq);
return;
}
scm_request_prepare(scmrq);
atomic_inc(&bdev->queued_reqs);
blk_start_request(req);
ret = scm_start_aob(scmrq->aob);
@ -244,7 +250,6 @@ static void scm_blk_request(struct request_queue *rq)
scm_request_requeue(scmrq);
return;
}
atomic_inc(&bdev->queued_reqs);
}
}
@ -310,7 +315,6 @@ static void scm_blk_tasklet(struct scm_blk_dev *bdev)
}
scm_request_finish(scmrq);
atomic_dec(&bdev->queued_reqs);
spin_lock_irqsave(&bdev->lock, flags);
}
spin_unlock_irqrestore(&bdev->lock, flags);