summaryrefslogtreecommitdiff
path: root/block
diff options
context:
space:
mode:
Diffstat (limited to 'block')
-rw-r--r--block/bfq-iosched.c12
-rw-r--r--block/bio.c4
-rw-r--r--block/blk-core.c1
-rw-r--r--block/blk-iocost.c5
-rw-r--r--block/blk-mq-sched.h2
-rw-r--r--block/blk-mq.c18
-rw-r--r--block/blk-settings.c46
-rw-r--r--block/blk-stat.c17
-rw-r--r--block/partitions/core.c37
9 files changed, 96 insertions, 46 deletions
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index c34b090178a9..fa98470df3f0 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -5896,18 +5896,6 @@ static void bfq_finish_requeue_request(struct request *rq)
struct bfq_data *bfqd;
/*
- * Requeue and finish hooks are invoked in blk-mq without
- * checking whether the involved request is actually still
- * referenced in the scheduler. To handle this fact, the
- * following two checks make this function exit in case of
- * spurious invocations, for which there is nothing to do.
- *
- * First, check whether rq has nothing to do with an elevator.
- */
- if (unlikely(!(rq->rq_flags & RQF_ELVPRIV)))
- return;
-
- /*
* rq either is not associated with any icq, or is an already
* requeued request that has not (yet) been re-inserted into
* a bfq_queue.
diff --git a/block/bio.c b/block/bio.c
index a9931f23d933..e865ea55b9f9 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -879,8 +879,10 @@ bool __bio_try_merge_page(struct bio *bio, struct page *page,
struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
if (page_is_mergeable(bv, page, len, off, same_page)) {
- if (bio->bi_iter.bi_size > UINT_MAX - len)
+ if (bio->bi_iter.bi_size > UINT_MAX - len) {
+ *same_page = false;
return false;
+ }
bv->bv_len += len;
bio->bi_iter.bi_size += len;
return true;
diff --git a/block/blk-core.c b/block/blk-core.c
index d9d632639bd1..10c08ac50697 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -539,6 +539,7 @@ struct request_queue *blk_alloc_queue(int node_id)
goto fail_stats;
q->backing_dev_info->ra_pages = VM_READAHEAD_PAGES;
+ q->backing_dev_info->io_pages = VM_READAHEAD_PAGES;
q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK;
q->node = node_id;
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 413e0b5c8e6b..d37b55db2409 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -2092,14 +2092,15 @@ static void ioc_pd_free(struct blkg_policy_data *pd)
{
struct ioc_gq *iocg = pd_to_iocg(pd);
struct ioc *ioc = iocg->ioc;
+ unsigned long flags;
if (ioc) {
- spin_lock(&ioc->lock);
+ spin_lock_irqsave(&ioc->lock, flags);
if (!list_empty(&iocg->active_list)) {
propagate_active_weight(iocg, 0, 0);
list_del_init(&iocg->active_list);
}
- spin_unlock(&ioc->lock);
+ spin_unlock_irqrestore(&ioc->lock, flags);
hrtimer_cancel(&iocg->waitq_timer);
hrtimer_cancel(&iocg->delay_timer);
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index 126021fc3a11..e81ca1bf6e10 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -66,7 +66,7 @@ static inline void blk_mq_sched_requeue_request(struct request *rq)
struct request_queue *q = rq->q;
struct elevator_queue *e = q->elevator;
- if (e && e->type->ops.requeue_request)
+ if ((rq->rq_flags & RQF_ELVPRIV) && e && e->type->ops.requeue_request)
e->type->ops.requeue_request(rq);
}
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b3d2785eefe9..cdced4aca2e8 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1412,6 +1412,11 @@ out:
hctx->dispatched[queued_to_index(queued)]++;
+ /* If we didn't flush the entire list, we could have told the driver
+ * there was more coming, but that turned out to be a lie.
+ */
+ if ((!list_empty(list) || errors) && q->mq_ops->commit_rqs && queued)
+ q->mq_ops->commit_rqs(hctx);
/*
* Any items that need requeuing? Stuff them into hctx->dispatch,
* that is where we will continue on next queue run.
@@ -1425,14 +1430,6 @@ out:
blk_mq_release_budgets(q, nr_budgets);
- /*
- * If we didn't flush the entire list, we could have told
- * the driver there was more coming, but that turned out to
- * be a lie.
- */
- if (q->mq_ops->commit_rqs && queued)
- q->mq_ops->commit_rqs(hctx);
-
spin_lock(&hctx->lock);
list_splice_tail_init(list, &hctx->dispatch);
spin_unlock(&hctx->lock);
@@ -2079,6 +2076,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
struct list_head *list)
{
int queued = 0;
+ int errors = 0;
while (!list_empty(list)) {
blk_status_t ret;
@@ -2095,6 +2093,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
break;
}
blk_mq_end_request(rq, ret);
+ errors++;
} else
queued++;
}
@@ -2104,7 +2103,8 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
* the driver there was more coming, but that turned out to
* be a lie.
*/
- if (!list_empty(list) && hctx->queue->mq_ops->commit_rqs && queued)
+ if ((!list_empty(list) || errors) &&
+ hctx->queue->mq_ops->commit_rqs && queued)
hctx->queue->mq_ops->commit_rqs(hctx);
}
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 76a7e03bcd6c..34b721a2743a 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -801,6 +801,52 @@ bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
}
EXPORT_SYMBOL_GPL(blk_queue_can_use_dma_map_merging);
+/**
+ * blk_queue_set_zoned - configure a disk queue zoned model.
+ * @disk: the gendisk of the queue to configure
+ * @model: the zoned model to set
+ *
+ * Set the zoned model of the request queue of @disk according to @model.
+ * When @model is BLK_ZONED_HM (host managed), this should be called only
+ * if zoned block device support is enabled (CONFIG_BLK_DEV_ZONED option).
+ * If @model specifies BLK_ZONED_HA (host aware), the effective model used
+ * depends on CONFIG_BLK_DEV_ZONED settings and on the existence of partitions
+ * on the disk.
+ */
+void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model)
+{
+ switch (model) {
+ case BLK_ZONED_HM:
+ /*
+ * Host managed devices are supported only if
+ * CONFIG_BLK_DEV_ZONED is enabled.
+ */
+ WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED));
+ break;
+ case BLK_ZONED_HA:
+ /*
+ * Host aware devices can be treated either as regular block
+ * devices (similar to drive managed devices) or as zoned block
+ * devices to take advantage of the zone command set, similarly
+ * to host managed devices. We try the latter if there are no
+ * partitions and zoned block device support is enabled, else
+ * we do nothing special as far as the block layer is concerned.
+ */
+ if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) ||
+ disk_has_partitions(disk))
+ model = BLK_ZONED_NONE;
+ break;
+ case BLK_ZONED_NONE:
+ default:
+ if (WARN_ON_ONCE(model != BLK_ZONED_NONE))
+ model = BLK_ZONED_NONE;
+ break;
+ }
+
+ disk->queue->limits.zoned = model;
+}
+EXPORT_SYMBOL_GPL(blk_queue_set_zoned);
+
static int __init blk_settings_init(void)
{
blk_max_low_pfn = max_low_pfn - 1;
diff --git a/block/blk-stat.c b/block/blk-stat.c
index 7da302ff88d0..ae3dd1fb8e61 100644
--- a/block/blk-stat.c
+++ b/block/blk-stat.c
@@ -137,6 +137,7 @@ void blk_stat_add_callback(struct request_queue *q,
struct blk_stat_callback *cb)
{
unsigned int bucket;
+ unsigned long flags;
int cpu;
for_each_possible_cpu(cpu) {
@@ -147,20 +148,22 @@ void blk_stat_add_callback(struct request_queue *q,
blk_rq_stat_init(&cpu_stat[bucket]);
}
- spin_lock(&q->stats->lock);
+ spin_lock_irqsave(&q->stats->lock, flags);
list_add_tail_rcu(&cb->list, &q->stats->callbacks);
blk_queue_flag_set(QUEUE_FLAG_STATS, q);
- spin_unlock(&q->stats->lock);
+ spin_unlock_irqrestore(&q->stats->lock, flags);
}
void blk_stat_remove_callback(struct request_queue *q,
struct blk_stat_callback *cb)
{
- spin_lock(&q->stats->lock);
+ unsigned long flags;
+
+ spin_lock_irqsave(&q->stats->lock, flags);
list_del_rcu(&cb->list);
if (list_empty(&q->stats->callbacks) && !q->stats->enable_accounting)
blk_queue_flag_clear(QUEUE_FLAG_STATS, q);
- spin_unlock(&q->stats->lock);
+ spin_unlock_irqrestore(&q->stats->lock, flags);
del_timer_sync(&cb->timer);
}
@@ -183,10 +186,12 @@ void blk_stat_free_callback(struct blk_stat_callback *cb)
void blk_stat_enable_accounting(struct request_queue *q)
{
- spin_lock(&q->stats->lock);
+ unsigned long flags;
+
+ spin_lock_irqsave(&q->stats->lock, flags);
q->stats->enable_accounting = true;
blk_queue_flag_set(QUEUE_FLAG_STATS, q);
- spin_unlock(&q->stats->lock);
+ spin_unlock_irqrestore(&q->stats->lock, flags);
}
EXPORT_SYMBOL_GPL(blk_stat_enable_accounting);
diff --git a/block/partitions/core.c b/block/partitions/core.c
index e62a98a8eeb7..722406b841df 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -278,6 +278,15 @@ static void hd_struct_free_work(struct work_struct *work)
{
struct hd_struct *part =
container_of(to_rcu_work(work), struct hd_struct, rcu_work);
+ struct gendisk *disk = part_to_disk(part);
+
+ /*
+ * Release the disk reference acquired in delete_partition here.
+ * We can't release it in hd_struct_free because the final put_device
+ * needs process context and thus can't be run directly from a
+ * percpu_ref ->release handler.
+ */
+ put_device(disk_to_dev(disk));
part->start_sect = 0;
part->nr_sects = 0;
@@ -293,7 +302,6 @@ static void hd_struct_free(struct percpu_ref *ref)
rcu_dereference_protected(disk->part_tbl, 1);
rcu_assign_pointer(ptbl->last_lookup, NULL);
- put_device(disk_to_dev(disk));
INIT_RCU_WORK(&part->rcu_work, hd_struct_free_work);
queue_rcu_work(system_wq, &part->rcu_work);
@@ -524,19 +532,20 @@ int bdev_add_partition(struct block_device *bdev, int partno,
int bdev_del_partition(struct block_device *bdev, int partno)
{
struct block_device *bdevp;
- struct hd_struct *part;
- int ret = 0;
+ struct hd_struct *part = NULL;
+ int ret;
- part = disk_get_part(bdev->bd_disk, partno);
- if (!part)
- return -ENXIO;
-
- ret = -ENOMEM;
- bdevp = bdget(part_devt(part));
+ bdevp = bdget_disk(bdev->bd_disk, partno);
if (!bdevp)
- goto out_put_part;
+ return -ENXIO;
mutex_lock(&bdevp->bd_mutex);
+ mutex_lock_nested(&bdev->bd_mutex, 1);
+
+ ret = -ENXIO;
+ part = disk_get_part(bdev->bd_disk, partno);
+ if (!part)
+ goto out_unlock;
ret = -EBUSY;
if (bdevp->bd_openers)
@@ -545,16 +554,14 @@ int bdev_del_partition(struct block_device *bdev, int partno)
sync_blockdev(bdevp);
invalidate_bdev(bdevp);
- mutex_lock_nested(&bdev->bd_mutex, 1);
delete_partition(bdev->bd_disk, part);
- mutex_unlock(&bdev->bd_mutex);
-
ret = 0;
out_unlock:
+ mutex_unlock(&bdev->bd_mutex);
mutex_unlock(&bdevp->bd_mutex);
bdput(bdevp);
-out_put_part:
- disk_put_part(part);
+ if (part)
+ disk_put_part(part);
return ret;
}
generated by cgit v1.2.3 (git 2.39.0) at 2024-09-19 11:59:41 +0300