summaryrefslogtreecommitdiffstats
path: root/block
diff options
context:
space:
mode:
Diffstat (limited to 'block')
-rw-r--r--block/bfq-cgroup.c4
-rw-r--r--block/bio.c5
-rw-r--r--block/blk-cgroup.c109
-rw-r--r--block/blk-core.c9
-rw-r--r--block/blk-mq-tag.c13
-rw-r--r--block/blk-mq.c4
-rw-r--r--block/blk-throttle.c5
-rw-r--r--block/elevator.c2
-rw-r--r--block/genhd.c6
-rw-r--r--block/partition-generic.c6
10 files changed, 77 insertions, 86 deletions
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 58c6efa9f9a9..9fe5952d117d 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -275,9 +275,9 @@ static void bfqg_and_blkg_get(struct bfq_group *bfqg)
void bfqg_and_blkg_put(struct bfq_group *bfqg)
{
- bfqg_put(bfqg);
-
blkg_put(bfqg_to_blkg(bfqg));
+
+ bfqg_put(bfqg);
}
/* @stats = 0 */
diff --git a/block/bio.c b/block/bio.c
index b12966e415d3..0093bed81c0e 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1684,7 +1684,7 @@ void generic_end_io_acct(struct request_queue *q, int req_op,
const int sgrp = op_stat_group(req_op);
int cpu = part_stat_lock();
- part_stat_add(cpu, part, ticks[sgrp], duration);
+ part_stat_add(cpu, part, nsecs[sgrp], jiffies_to_nsecs(duration));
part_round_stats(q, cpu, part);
part_dec_in_flight(q, part, op_is_write(req_op));
@@ -2015,7 +2015,8 @@ int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg)
{
if (unlikely(bio->bi_blkg))
return -EBUSY;
- blkg_get(blkg);
+ if (!blkg_try_get(blkg))
+ return -ENODEV;
bio->bi_blkg = blkg;
return 0;
}
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 694595b29b8f..c630e02836a8 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -310,28 +310,11 @@ struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
}
}
-static void blkg_pd_offline(struct blkcg_gq *blkg)
-{
- int i;
-
- lockdep_assert_held(blkg->q->queue_lock);
- lockdep_assert_held(&blkg->blkcg->lock);
-
- for (i = 0; i < BLKCG_MAX_POLS; i++) {
- struct blkcg_policy *pol = blkcg_policy[i];
-
- if (blkg->pd[i] && !blkg->pd[i]->offline &&
- pol->pd_offline_fn) {
- pol->pd_offline_fn(blkg->pd[i]);
- blkg->pd[i]->offline = true;
- }
- }
-}
-
static void blkg_destroy(struct blkcg_gq *blkg)
{
struct blkcg *blkcg = blkg->blkcg;
struct blkcg_gq *parent = blkg->parent;
+ int i;
lockdep_assert_held(blkg->q->queue_lock);
lockdep_assert_held(&blkcg->lock);
@@ -340,6 +323,13 @@ static void blkg_destroy(struct blkcg_gq *blkg)
WARN_ON_ONCE(list_empty(&blkg->q_node));
WARN_ON_ONCE(hlist_unhashed(&blkg->blkcg_node));
+ for (i = 0; i < BLKCG_MAX_POLS; i++) {
+ struct blkcg_policy *pol = blkcg_policy[i];
+
+ if (blkg->pd[i] && pol->pd_offline_fn)
+ pol->pd_offline_fn(blkg->pd[i]);
+ }
+
if (parent) {
blkg_rwstat_add_aux(&parent->stat_bytes, &blkg->stat_bytes);
blkg_rwstat_add_aux(&parent->stat_ios, &blkg->stat_ios);
@@ -382,7 +372,6 @@ static void blkg_destroy_all(struct request_queue *q)
struct blkcg *blkcg = blkg->blkcg;
spin_lock(&blkcg->lock);
- blkg_pd_offline(blkg);
blkg_destroy(blkg);
spin_unlock(&blkcg->lock);
}
@@ -1053,59 +1042,64 @@ static struct cftype blkcg_legacy_files[] = {
{ } /* terminate */
};
+/*
+ * blkcg destruction is a three-stage process.
+ *
+ * 1. Destruction starts. The blkcg_css_offline() callback is invoked
+ * which offlines writeback. Here we tie the next stage of blkg destruction
+ * to the completion of writeback associated with the blkcg. This lets us
+ * avoid punting potentially large amounts of outstanding writeback to root
+ * while maintaining any ongoing policies. The next stage is triggered when
+ * the nr_cgwbs count goes to zero.
+ *
+ * 2. When the nr_cgwbs count goes to zero, blkcg_destroy_blkgs() is called
+ * and handles the destruction of blkgs. Here the css reference held by
+ * the blkg is put back eventually allowing blkcg_css_free() to be called.
+ * This work may occur in cgwb_release_workfn() on the cgwb_release
+ * workqueue. Any submitted ios that fail to get the blkg ref will be
+ * punted to the root_blkg.
+ *
+ * 3. Once the blkcg ref count goes to zero, blkcg_css_free() is called.
+ * This finally frees the blkcg.
+ */
+
/**
* blkcg_css_offline - cgroup css_offline callback
* @css: css of interest
*
- * This function is called when @css is about to go away and responsible
- * for offlining all blkgs pd and killing all wbs associated with @css.
- * blkgs pd offline should be done while holding both q and blkcg locks.
- * As blkcg lock is nested inside q lock, this function performs reverse
- * double lock dancing.
- *
- * This is the blkcg counterpart of ioc_release_fn().
+ * This function is called when @css is about to go away. Here the cgwbs are
+ * offlined first and only once writeback associated with the blkcg has
+ * finished do we start step 2 (see above).
*/
static void blkcg_css_offline(struct cgroup_subsys_state *css)
{
struct blkcg *blkcg = css_to_blkcg(css);
- struct blkcg_gq *blkg;
-
- spin_lock_irq(&blkcg->lock);
-
- hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
- struct request_queue *q = blkg->q;
-
- if (spin_trylock(q->queue_lock)) {
- blkg_pd_offline(blkg);
- spin_unlock(q->queue_lock);
- } else {
- spin_unlock_irq(&blkcg->lock);
- cpu_relax();
- spin_lock_irq(&blkcg->lock);
- }
- }
-
- spin_unlock_irq(&blkcg->lock);
+ /* this prevents anyone from attaching or migrating to this blkcg */
wb_blkcg_offline(blkcg);
+
+ /* put the base cgwb reference allowing step 2 to be triggered */
+ blkcg_cgwb_put(blkcg);
}
/**
- * blkcg_destroy_all_blkgs - destroy all blkgs associated with a blkcg
+ * blkcg_destroy_blkgs - responsible for shooting down blkgs
* @blkcg: blkcg of interest
*
- * This function is called when blkcg css is about to free and responsible for
- * destroying all blkgs associated with @blkcg.
- * blkgs should be removed while holding both q and blkcg locks. As blkcg lock
+ * blkgs should be removed while holding both q and blkcg locks. As blkcg lock
* is nested inside q lock, this function performs reverse double lock dancing.
+ * Destroying the blkgs releases the reference held on the blkcg's css allowing
+ * blkcg_css_free to eventually be called.
+ *
+ * This is the blkcg counterpart of ioc_release_fn().
*/
-static void blkcg_destroy_all_blkgs(struct blkcg *blkcg)
+void blkcg_destroy_blkgs(struct blkcg *blkcg)
{
spin_lock_irq(&blkcg->lock);
+
while (!hlist_empty(&blkcg->blkg_list)) {
struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first,
- struct blkcg_gq,
- blkcg_node);
+ struct blkcg_gq, blkcg_node);
struct request_queue *q = blkg->q;
if (spin_trylock(q->queue_lock)) {
@@ -1117,6 +1111,7 @@ static void blkcg_destroy_all_blkgs(struct blkcg *blkcg)
spin_lock_irq(&blkcg->lock);
}
}
+
spin_unlock_irq(&blkcg->lock);
}
@@ -1125,8 +1120,6 @@ static void blkcg_css_free(struct cgroup_subsys_state *css)
struct blkcg *blkcg = css_to_blkcg(css);
int i;
- blkcg_destroy_all_blkgs(blkcg);
-
mutex_lock(&blkcg_pol_mutex);
list_del(&blkcg->all_blkcgs_node);
@@ -1189,6 +1182,7 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
INIT_HLIST_HEAD(&blkcg->blkg_list);
#ifdef CONFIG_CGROUP_WRITEBACK
INIT_LIST_HEAD(&blkcg->cgwb_list);
+ refcount_set(&blkcg->cgwb_refcnt, 1);
#endif
list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs);
@@ -1480,11 +1474,8 @@ void blkcg_deactivate_policy(struct request_queue *q,
list_for_each_entry(blkg, &q->blkg_list, q_node) {
if (blkg->pd[pol->plid]) {
- if (!blkg->pd[pol->plid]->offline &&
- pol->pd_offline_fn) {
+ if (pol->pd_offline_fn)
pol->pd_offline_fn(blkg->pd[pol->plid]);
- blkg->pd[pol->plid]->offline = true;
- }
pol->pd_free_fn(blkg->pd[pol->plid]);
blkg->pd[pol->plid] = NULL;
}
@@ -1519,8 +1510,10 @@ int blkcg_policy_register(struct blkcg_policy *pol)
for (i = 0; i < BLKCG_MAX_POLS; i++)
if (!blkcg_policy[i])
break;
- if (i >= BLKCG_MAX_POLS)
+ if (i >= BLKCG_MAX_POLS) {
+ pr_warn("blkcg_policy_register: BLKCG_MAX_POLS too small\n");
goto err_unlock;
+ }
/* Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs */
if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) ||
diff --git a/block/blk-core.c b/block/blk-core.c
index dee56c282efb..cff0a60ee200 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2163,9 +2163,12 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)
{
const int op = bio_op(bio);
- if (part->policy && (op_is_write(op) && !op_is_flush(op))) {
+ if (part->policy && op_is_write(op)) {
char b[BDEVNAME_SIZE];
+ if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
+ return false;
+
WARN_ONCE(1,
"generic_make_request: Trying to write "
"to read-only block-device %s (partno %d)\n",
@@ -2730,17 +2733,15 @@ void blk_account_io_done(struct request *req, u64 now)
* containing request is enough.
*/
if (blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) {
- unsigned long duration;
const int sgrp = op_stat_group(req_op(req));
struct hd_struct *part;
int cpu;
- duration = nsecs_to_jiffies(now - req->start_time_ns);
cpu = part_stat_lock();
part = req->part;
part_stat_inc(cpu, part, ios[sgrp]);
- part_stat_add(cpu, part, ticks[sgrp], duration);
+ part_stat_add(cpu, part, nsecs[sgrp], now - req->start_time_ns);
part_round_stats(req->q, cpu, part);
part_dec_in_flight(req->q, part, rq_data_dir(req));
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 94e1ed667b6e..41317c50a446 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -322,16 +322,11 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
/*
* __blk_mq_update_nr_hw_queues will update the nr_hw_queues and
- * queue_hw_ctx after freeze the queue. So we could use q_usage_counter
- * to avoid race with it. __blk_mq_update_nr_hw_queues will users
- * synchronize_rcu to ensure all of the users go out of the critical
- * section below and see zeroed q_usage_counter.
+ * queue_hw_ctx after freeze the queue, so we use q_usage_counter
+ * to avoid race with it.
*/
- rcu_read_lock();
- if (percpu_ref_is_zero(&q->q_usage_counter)) {
- rcu_read_unlock();
+ if (!percpu_ref_tryget(&q->q_usage_counter))
return;
- }
queue_for_each_hw_ctx(q, hctx, i) {
struct blk_mq_tags *tags = hctx->tags;
@@ -347,7 +342,7 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
bt_for_each(hctx, &tags->breserved_tags, fn, priv, true);
bt_for_each(hctx, &tags->bitmap_tags, fn, priv, false);
}
- rcu_read_unlock();
+ blk_queue_exit(q);
}
static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth,
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 85a1c1a59c72..e3c39ea8e17b 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1628,7 +1628,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
BUG_ON(!rq->q);
if (rq->mq_ctx != this_ctx) {
if (this_ctx) {
- trace_block_unplug(this_q, depth, from_schedule);
+ trace_block_unplug(this_q, depth, !from_schedule);
blk_mq_sched_insert_requests(this_q, this_ctx,
&ctx_list,
from_schedule);
@@ -1648,7 +1648,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
* on 'ctx_list'. Do those.
*/
if (this_ctx) {
- trace_block_unplug(this_q, depth, from_schedule);
+ trace_block_unplug(this_q, depth, !from_schedule);
blk_mq_sched_insert_requests(this_q, this_ctx, &ctx_list,
from_schedule);
}
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index a3eede00d302..01d0620a4e4a 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -2129,8 +2129,9 @@ static inline void throtl_update_latency_buckets(struct throtl_data *td)
static void blk_throtl_assoc_bio(struct throtl_grp *tg, struct bio *bio)
{
#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
- if (bio->bi_css)
- bio_associate_blkg(bio, tg_to_blkg(tg));
+ /* fallback to root_blkg if we fail to get a blkg ref */
+ if (bio->bi_css && (bio_associate_blkg(bio, tg_to_blkg(tg)) == -ENODEV))
+ bio_associate_blkg(bio, bio->bi_disk->queue->root_blkg);
bio_issue_init(&bio->bi_issue, bio_sectors(bio));
#endif
}
diff --git a/block/elevator.c b/block/elevator.c
index 6a06b5d040e5..fae58b2f906f 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -609,7 +609,7 @@ void elv_drain_elevator(struct request_queue *q)
while (e->type->ops.sq.elevator_dispatch_fn(q, 1))
;
- if (q->nr_sorted && printed++ < 10) {
+ if (q->nr_sorted && !blk_queue_is_zoned(q) && printed++ < 10 ) {
printk(KERN_ERR "%s: forced dispatching is broken "
"(nr_sorted=%u), please report this\n",
q->elevator->type->elevator_name, q->nr_sorted);
diff --git a/block/genhd.c b/block/genhd.c
index 8cc719a37b32..be5bab20b2ab 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1343,18 +1343,18 @@ static int diskstats_show(struct seq_file *seqf, void *v)
part_stat_read(hd, ios[STAT_READ]),
part_stat_read(hd, merges[STAT_READ]),
part_stat_read(hd, sectors[STAT_READ]),
- jiffies_to_msecs(part_stat_read(hd, ticks[STAT_READ])),
+ (unsigned int)part_stat_read_msecs(hd, STAT_READ),
part_stat_read(hd, ios[STAT_WRITE]),
part_stat_read(hd, merges[STAT_WRITE]),
part_stat_read(hd, sectors[STAT_WRITE]),
- jiffies_to_msecs(part_stat_read(hd, ticks[STAT_WRITE])),
+ (unsigned int)part_stat_read_msecs(hd, STAT_WRITE),
inflight[0],
jiffies_to_msecs(part_stat_read(hd, io_ticks)),
jiffies_to_msecs(part_stat_read(hd, time_in_queue)),
part_stat_read(hd, ios[STAT_DISCARD]),
part_stat_read(hd, merges[STAT_DISCARD]),
part_stat_read(hd, sectors[STAT_DISCARD]),
- jiffies_to_msecs(part_stat_read(hd, ticks[STAT_DISCARD]))
+ (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD)
);
}
disk_part_iter_exit(&piter);
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 5a8975a1201c..d3d14e81fb12 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -136,18 +136,18 @@ ssize_t part_stat_show(struct device *dev,
part_stat_read(p, ios[STAT_READ]),
part_stat_read(p, merges[STAT_READ]),
(unsigned long long)part_stat_read(p, sectors[STAT_READ]),
- jiffies_to_msecs(part_stat_read(p, ticks[STAT_READ])),
+ (unsigned int)part_stat_read_msecs(p, STAT_READ),
part_stat_read(p, ios[STAT_WRITE]),
part_stat_read(p, merges[STAT_WRITE]),
(unsigned long long)part_stat_read(p, sectors[STAT_WRITE]),
- jiffies_to_msecs(part_stat_read(p, ticks[STAT_WRITE])),
+ (unsigned int)part_stat_read_msecs(p, STAT_WRITE),
inflight[0],
jiffies_to_msecs(part_stat_read(p, io_ticks)),
jiffies_to_msecs(part_stat_read(p, time_in_queue)),
part_stat_read(p, ios[STAT_DISCARD]),
part_stat_read(p, merges[STAT_DISCARD]),
(unsigned long long)part_stat_read(p, sectors[STAT_DISCARD]),
- jiffies_to_msecs(part_stat_read(p, ticks[STAT_DISCARD])));
+ (unsigned int)part_stat_read_msecs(p, STAT_DISCARD));
}
ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
generated by cgit v1.2.3 (git 2.25.1) at 2024-08-28 00:51:13 +0000