#include <linux/sched/loadavg.h>
#include <linux/sched/signal.h>
#include <trace/events/block.h>
+#include <linux/blk-mq.h>
#include "blk-rq-qos.h"
#include "blk-stat.h"
stat->rqs.mean);
}
-static inline bool iolatency_may_queue(struct iolatency_grp *iolat,
- wait_queue_entry_t *wait,
- bool first_block)
+static void iolat_cleanup_cb(struct rq_wait *rqw, void *private_data)
{
- struct rq_wait *rqw = &iolat->rq_wait;
+ atomic_dec(&rqw->inflight);
+ wake_up(&rqw->wait);
+}
- if (first_block && waitqueue_active(&rqw->wait) &&
- rqw->wait.head.next != &wait->entry)
- return false;
+static bool iolat_acquire_inflight(struct rq_wait *rqw, void *private_data)
+{
+ struct iolatency_grp *iolat = private_data;
return rq_wait_inc_below(rqw, iolat->rq_depth.max_depth);
}
static void __blkcg_iolatency_throttle(struct rq_qos *rqos,
struct iolatency_grp *iolat,
- spinlock_t *lock, bool issue_as_root,
+ bool issue_as_root,
bool use_memdelay)
- __releases(lock)
- __acquires(lock)
{
struct rq_wait *rqw = &iolat->rq_wait;
unsigned use_delay = atomic_read(&lat_to_blkg(iolat)->use_delay);
- DEFINE_WAIT(wait);
- bool first_block = true;
if (use_delay)
blkcg_schedule_throttle(rqos->q, use_memdelay);
return;
}
- if (iolatency_may_queue(iolat, &wait, first_block))
- return;
-
- do {
- prepare_to_wait_exclusive(&rqw->wait, &wait,
- TASK_UNINTERRUPTIBLE);
-
- if (iolatency_may_queue(iolat, &wait, first_block))
- break;
- first_block = false;
-
- if (lock) {
- spin_unlock_irq(lock);
- io_schedule();
- spin_lock_irq(lock);
- } else {
- io_schedule();
- }
- } while (1);
-
- finish_wait(&rqw->wait, &wait);
+ rq_qos_wait(rqw, iolat, iolat_acquire_inflight, iolat_cleanup_cb);
}
#define SCALE_DOWN_FACTOR 2
scale_change(iolat, direction > 0);
}
-static void blkcg_iolatency_throttle(struct rq_qos *rqos, struct bio *bio,
- spinlock_t *lock)
+static void blkcg_iolatency_throttle(struct rq_qos *rqos, struct bio *bio)
{
struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
- struct blkcg *blkcg;
- struct blkcg_gq *blkg;
- struct request_queue *q = rqos->q;
+ struct blkcg_gq *blkg = bio->bi_blkg;
bool issue_as_root = bio_issue_as_root_blkg(bio);
if (!blk_iolatency_enabled(blkiolat))
return;
- rcu_read_lock();
- blkcg = bio_blkcg(bio);
- bio_associate_blkcg(bio, &blkcg->css);
- blkg = blkg_lookup(blkcg, q);
- if (unlikely(!blkg)) {
- if (!lock)
- spin_lock_irq(q->queue_lock);
- blkg = blkg_lookup_create(blkcg, q);
- if (IS_ERR(blkg))
- blkg = NULL;
- if (!lock)
- spin_unlock_irq(q->queue_lock);
- }
- if (!blkg)
- goto out;
-
- bio_issue_init(&bio->bi_issue, bio_sectors(bio));
- bio_associate_blkg(bio, blkg);
-out:
- rcu_read_unlock();
while (blkg && blkg->parent) {
struct iolatency_grp *iolat = blkg_to_lat(blkg);
if (!iolat) {
}
check_scale_change(iolat);
- __blkcg_iolatency_throttle(rqos, iolat, lock, issue_as_root,
+ __blkcg_iolatency_throttle(rqos, iolat, issue_as_root,
(bio->bi_opf & REQ_SWAP) == REQ_SWAP);
blkg = blkg->parent;
}
u64 now = ktime_to_ns(ktime_get());
bool issue_as_root = bio_issue_as_root_blkg(bio);
bool enabled = false;
+ int inflight = 0;
blkg = bio->bi_blkg;
- if (!blkg)
+ if (!blkg || !bio_flagged(bio, BIO_TRACKED))
return;
iolat = blkg_to_lat(bio->bi_blkg);
return;
enabled = blk_iolatency_enabled(iolat->blkiolat);
+ if (!enabled)
+ return;
+
while (blkg && blkg->parent) {
iolat = blkg_to_lat(blkg);
if (!iolat) {
}
rqw = &iolat->rq_wait;
- atomic_dec(&rqw->inflight);
- if (!enabled || iolat->min_lat_nsec == 0)
+ inflight = atomic_dec_return(&rqw->inflight);
+ WARN_ON_ONCE(inflight < 0);
+ if (iolat->min_lat_nsec == 0)
goto next;
iolatency_record_time(iolat, &bio->bi_issue, now,
issue_as_root);
* We could be exiting, don't access the pd unless we have a
* ref on the blkg.
*/
- if (!blkg_try_get(blkg))
+ if (!blkg_tryget(blkg))
continue;
iolat = blkg_to_lat(blkg);
return 0;
}
-static void iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val)
+/*
+ * return 1 for enabling iolatency, return -1 for disabling iolatency, otherwise
+ * return 0.
+ */
+static int iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val)
{
struct iolatency_grp *iolat = blkg_to_lat(blkg);
- struct blk_iolatency *blkiolat = iolat->blkiolat;
u64 oldval = iolat->min_lat_nsec;
iolat->min_lat_nsec = val;
BLKIOLATENCY_MAX_WIN_SIZE);
if (!oldval && val)
- atomic_inc(&blkiolat->enabled);
+ return 1;
if (oldval && !val)
- atomic_dec(&blkiolat->enabled);
+ return -1;
+ return 0;
}
static void iolatency_clear_scaling(struct blkcg_gq *blkg)
u64 lat_val = 0;
u64 oldval;
int ret;
+ int enable = 0;
ret = blkg_conf_prep(blkcg, &blkcg_policy_iolatency, buf, &ctx);
if (ret)
blkg = ctx.blkg;
oldval = iolat->min_lat_nsec;
- iolatency_set_min_lat_nsec(blkg, lat_val);
+ enable = iolatency_set_min_lat_nsec(blkg, lat_val);
+ if (enable) {
+ WARN_ON_ONCE(!blk_get_queue(blkg->q));
+ blkg_get(blkg);
+ }
+
if (oldval != iolat->min_lat_nsec) {
iolatency_clear_scaling(blkg);
}
ret = 0;
out:
blkg_conf_finish(&ctx);
+ if (ret == 0 && enable) {
+ struct iolatency_grp *tmp = blkg_to_lat(blkg);
+ struct blk_iolatency *blkiolat = tmp->blkiolat;
+
+ blk_mq_freeze_queue(blkg->q);
+
+ if (enable == 1)
+ atomic_inc(&blkiolat->enabled);
+ else if (enable == -1)
+ atomic_dec(&blkiolat->enabled);
+ else
+ WARN_ON_ONCE(1);
+
+ blk_mq_unfreeze_queue(blkg->q);
+
+ blkg_put(blkg);
+ blk_put_queue(blkg->q);
+ }
return ret ?: nbytes;
}
{
struct iolatency_grp *iolat = pd_to_lat(pd);
struct blkcg_gq *blkg = lat_to_blkg(iolat);
+ struct blk_iolatency *blkiolat = iolat->blkiolat;
+ int ret;
- iolatency_set_min_lat_nsec(blkg, 0);
+ ret = iolatency_set_min_lat_nsec(blkg, 0);
+ if (ret == 1)
+ atomic_inc(&blkiolat->enabled);
+ if (ret == -1)
+ atomic_dec(&blkiolat->enabled);
iolatency_clear_scaling(blkg);
}
OSDN Git Service
