mirror of
https://github.com/torvalds/linux.git
synced 2024-11-11 14:42:24 +00:00
c6ce194325
Hi,
If you can manage to submit an async write as the first async I/O from
the context of a process with realtime scheduling priority, then a
cfq_queue is allocated, but filed into the wrong async_cfqq bucket. It
ends up in the best effort array, but actually has realtime I/O
scheduling priority set in cfqq->ioprio.
The reason is that cfq_get_queue assumes the default scheduling class and
priority when there is no information present (i.e. when the async cfqq
is created):
static struct cfq_queue *
cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic,
struct bio *bio, gfp_t gfp_mask)
{
const int ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio);
const int ioprio = IOPRIO_PRIO_DATA(cic->ioprio);
cic->ioprio starts out as 0, which is "invalid". So, class of 0
(IOPRIO_CLASS_NONE) is passed to cfq_async_queue_prio like so:
async_cfqq = cfq_async_queue_prio(cfqd, ioprio_class, ioprio);
static struct cfq_queue **
cfq_async_queue_prio(struct cfq_data *cfqd, int ioprio_class, int ioprio)
{
switch (ioprio_class) {
case IOPRIO_CLASS_RT:
return &cfqd->async_cfqq[0][ioprio];
case IOPRIO_CLASS_NONE:
ioprio = IOPRIO_NORM;
/* fall through */
case IOPRIO_CLASS_BE:
return &cfqd->async_cfqq[1][ioprio];
case IOPRIO_CLASS_IDLE:
return &cfqd->async_idle_cfqq;
default:
BUG();
}
}
Here, instead of returning a class mapped from the process' scheduling
priority, we get back the bucket associated with IOPRIO_CLASS_BE.
Now, there is no queue allocated there yet, so we create it:
cfqq = cfq_find_alloc_queue(cfqd, is_sync, cic, bio, gfp_mask);
That function ends up doing this:
cfq_init_cfqq(cfqd, cfqq, current->pid, is_sync);
cfq_init_prio_data(cfqq, cic);
cfq_init_cfqq marks the priority as having changed. Then, cfq_init_prio
data does this:
ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio);
switch (ioprio_class) {
default:
printk(KERN_ERR "cfq: bad prio %x\n", ioprio_class);
case IOPRIO_CLASS_NONE:
/*
* no prio set, inherit CPU scheduling settings
*/
cfqq->ioprio = task_nice_ioprio(tsk);
cfqq->ioprio_class = task_nice_ioclass(tsk);
break;
So we basically have two code paths that treat IOPRIO_CLASS_NONE
differently, which results in an RT async cfqq filed into a best effort
bucket.
Attached is a patch which fixes the problem. I'm not sure how to make
it cleaner. Suggestions would be welcome.
Signed-off-by: Jeff Moyer <jmoyer@redhat.com>
Tested-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
Cc: stable@kernel.org
Signed-off-by: Jens Axboe <axboe@fb.com>
|
||
|---|---|---|
| .. | ||
| partitions | ||
| bio-integrity.c | ||
| bio.c | ||
| blk-cgroup.c | ||
| blk-cgroup.h | ||
| blk-core.c | ||
| blk-exec.c | ||
| blk-flush.c | ||
| blk-integrity.c | ||
| blk-ioc.c | ||
| blk-iopoll.c | ||
| blk-lib.c | ||
| blk-map.c | ||
| blk-merge.c | ||
| blk-mq-cpu.c | ||
| blk-mq-cpumap.c | ||
| blk-mq-sysfs.c | ||
| blk-mq-tag.c | ||
| blk-mq-tag.h | ||
| blk-mq.c | ||
| blk-mq.h | ||
| blk-settings.c | ||
| blk-softirq.c | ||
| blk-sysfs.c | ||
| blk-tag.c | ||
| blk-throttle.c | ||
| blk-timeout.c | ||
| blk.h | ||
| bounce.c | ||
| bsg-lib.c | ||
| bsg.c | ||
| cfq-iosched.c | ||
| cmdline-parser.c | ||
| compat_ioctl.c | ||
| deadline-iosched.c | ||
| elevator.c | ||
| genhd.c | ||
| ioctl.c | ||
| ioprio.c | ||
| Kconfig | ||
| Kconfig.iosched | ||
| Makefile | ||
| noop-iosched.c | ||
| partition-generic.c | ||
| scsi_ioctl.c | ||
| t10-pi.c | ||