summaryrefslogtreecommitdiffstats
path: root/block
diff options
context:
space:
mode:
Diffstat (limited to 'block')
-rw-r--r--block/badblocks.c2
-rw-r--r--block/bfq-cgroup.c2
-rw-r--r--block/bfq-iosched.c16
-rw-r--r--block/bfq-iosched.h1
-rw-r--r--block/bfq-wf2q.c12
-rw-r--r--block/bio.c14
-rw-r--r--block/blk-cgroup.c8
-rw-r--r--block/blk-core.c1
-rw-r--r--block/blk-iocost.c5
-rw-r--r--block/blk-merge.c13
-rw-r--r--block/blk-mq-sched.c9
-rw-r--r--block/blk-mq-sched.h2
-rw-r--r--block/blk-mq.c13
-rw-r--r--block/blk-stat.c17
-rw-r--r--block/blk-wbt.c2
-rw-r--r--block/bsg-lib.c2
-rw-r--r--block/ioprio.c2
-rw-r--r--block/partitions/core.c37
18 files changed, 91 insertions, 67 deletions
diff --git a/block/badblocks.c b/block/badblocks.c
index 2e5f5697db35..d39056630d9c 100644
--- a/block/badblocks.c
+++ b/block/badblocks.c
@@ -525,7 +525,7 @@ ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len,
case 3:
if (newline != '\n')
return -EINVAL;
- /* fall through */
+ fallthrough;
case 2:
if (length <= 0)
return -EINVAL;
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 68882b9b8f11..b791e2041e49 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -332,7 +332,7 @@ static void bfqg_put(struct bfq_group *bfqg)
kfree(bfqg);
}
-void bfqg_and_blkg_get(struct bfq_group *bfqg)
+static void bfqg_and_blkg_get(struct bfq_group *bfqg)
{
/* see comments in bfq_bic_update_cgroup for why refcounting bfqg */
bfqg_get(bfqg);
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index a4c0bec920cb..fa98470df3f0 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -4980,7 +4980,7 @@ bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
pr_err("bdi %s: bfq: bad prio class %d\n",
bdi_dev_name(bfqq->bfqd->queue->backing_dev_info),
ioprio_class);
- /* fall through */
+ fallthrough;
case IOPRIO_CLASS_NONE:
/*
* No prio set, inherit CPU scheduling settings.
@@ -5112,7 +5112,7 @@ static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd,
return &bfqg->async_bfqq[0][ioprio];
case IOPRIO_CLASS_NONE:
ioprio = IOPRIO_NORM;
- /* fall through */
+ fallthrough;
case IOPRIO_CLASS_BE:
return &bfqg->async_bfqq[1][ioprio];
case IOPRIO_CLASS_IDLE:
@@ -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/bfq-iosched.h b/block/bfq-iosched.h
index cd224aaf9f52..703895224562 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -986,7 +986,6 @@ struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node);
-void bfqg_and_blkg_get(struct bfq_group *bfqg);
void bfqg_and_blkg_put(struct bfq_group *bfqg);
#ifdef CONFIG_BFQ_GROUP_IOSCHED
diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index eb0e2a6daabe..26776bdbdf36 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -533,9 +533,7 @@ static void bfq_get_entity(struct bfq_entity *entity)
bfqq->ref++;
bfq_log_bfqq(bfqq->bfqd, bfqq, "get_entity: %p %d",
bfqq, bfqq->ref);
- } else
- bfqg_and_blkg_get(container_of(entity, struct bfq_group,
- entity));
+ }
}
/**
@@ -649,14 +647,8 @@ static void bfq_forget_entity(struct bfq_service_tree *st,
entity->on_st_or_in_serv = false;
st->wsum -= entity->weight;
- if (is_in_service)
- return;
-
- if (bfqq)
+ if (bfqq && !is_in_service)
bfq_put_queue(bfqq);
- else
- bfqg_and_blkg_put(container_of(entity, struct bfq_group,
- entity));
}
/**
diff --git a/block/bio.c b/block/bio.c
index c63ba04bd629..e865ea55b9f9 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -740,8 +740,8 @@ static inline bool page_is_mergeable(const struct bio_vec *bv,
struct page *page, unsigned int len, unsigned int off,
bool *same_page)
{
- phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) +
- bv->bv_offset + bv->bv_len - 1;
+ size_t bv_end = bv->bv_offset + bv->bv_len;
+ phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) + bv_end - 1;
phys_addr_t page_addr = page_to_phys(page);
if (vec_end_addr + 1 != page_addr + off)
@@ -750,9 +750,9 @@ static inline bool page_is_mergeable(const struct bio_vec *bv,
return false;
*same_page = ((vec_end_addr & PAGE_MASK) == page_addr);
- if (!*same_page && pfn_to_page(PFN_DOWN(vec_end_addr)) + 1 != page)
- return false;
- return true;
+ if (*same_page)
+ return true;
+ return (bv->bv_page + bv_end / PAGE_SIZE) == (page + off / PAGE_SIZE);
}
/*
@@ -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-cgroup.c b/block/blk-cgroup.c
index 619a79b51068..c195365c9817 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1152,13 +1152,15 @@ int blkcg_init_queue(struct request_queue *q)
if (preloaded)
radix_tree_preload_end();
- ret = blk_iolatency_init(q);
+ ret = blk_throtl_init(q);
if (ret)
goto err_destroy_all;
- ret = blk_throtl_init(q);
- if (ret)
+ ret = blk_iolatency_init(q);
+ if (ret) {
+ blk_throtl_exit(q);
goto err_destroy_all;
+ }
return 0;
err_destroy_all:
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-merge.c b/block/blk-merge.c
index 6529e3aab001..f685d633bcc9 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -154,7 +154,7 @@ static inline unsigned get_max_io_size(struct request_queue *q,
if (max_sectors > start_offset)
return max_sectors - start_offset;
- return sectors & (lbs - 1);
+ return sectors & ~(lbs - 1);
}
static inline unsigned get_max_segment_size(const struct request_queue *q,
@@ -533,10 +533,17 @@ int __blk_rq_map_sg(struct request_queue *q, struct request *rq,
}
EXPORT_SYMBOL(__blk_rq_map_sg);
+static inline unsigned int blk_rq_get_max_segments(struct request *rq)
+{
+ if (req_op(rq) == REQ_OP_DISCARD)
+ return queue_max_discard_segments(rq->q);
+ return queue_max_segments(rq->q);
+}
+
static inline int ll_new_hw_segment(struct request *req, struct bio *bio,
unsigned int nr_phys_segs)
{
- if (req->nr_phys_segments + nr_phys_segs > queue_max_segments(req->q))
+ if (req->nr_phys_segments + nr_phys_segs > blk_rq_get_max_segments(req))
goto no_merge;
if (blk_integrity_merge_bio(req->q, req, bio) == false)
@@ -624,7 +631,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
return 0;
total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
- if (total_phys_segments > queue_max_segments(q))
+ if (total_phys_segments > blk_rq_get_max_segments(req))
return 0;
if (blk_integrity_merge_rq(q, req, next) == false)
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index a19cdf159b75..d2790e5b06d1 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -78,6 +78,15 @@ void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx)
return;
clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+ /*
+ * Order clearing SCHED_RESTART and list_empty_careful(&hctx->dispatch)
+ * in blk_mq_run_hw_queue(). Its pair is the barrier in
+ * blk_mq_dispatch_rq_list(). So dispatch code won't see SCHED_RESTART,
+ * meantime new request added to hctx->dispatch is missed to check in
+ * blk_mq_run_hw_queue().
+ */
+ smp_mb();
+
blk_mq_run_hw_queue(hctx, true);
}
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 0015a1892153..b3d2785eefe9 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1438,6 +1438,15 @@ out:
spin_unlock(&hctx->lock);
/*
+ * Order adding requests to hctx->dispatch and checking
+ * SCHED_RESTART flag. The pair of this smp_mb() is the one
+ * in blk_mq_sched_restart(). Avoid restart code path to
+ * miss the new added requests to hctx->dispatch, meantime
+ * SCHED_RESTART is observed here.
+ */
+ smp_mb();
+
+ /*
* If SCHED_RESTART was set by the caller of this function and
* it is no longer set that means that it was cleared by another
* thread and hence that a queue rerun is needed.
@@ -1834,6 +1843,7 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
/**
* blk_mq_request_bypass_insert - Insert a request at dispatch list.
* @rq: Pointer to request to be inserted.
+ * @at_head: true if the request should be inserted at the head of the list.
* @run_queue: If we should run the hardware queue after inserting the request.
*
* Should only be used carefully, when the caller knows we want to
@@ -2016,7 +2026,8 @@ insert:
if (bypass_insert)
return BLK_STS_RESOURCE;
- blk_mq_request_bypass_insert(rq, false, run_queue);
+ blk_mq_sched_insert_request(rq, false, run_queue, false);
+
return BLK_STS_OK;
}
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/blk-wbt.c b/block/blk-wbt.c
index 0fa615eefd52..fd410086fe1d 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -528,7 +528,7 @@ static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio)
if ((bio->bi_opf & (REQ_SYNC | REQ_IDLE)) ==
(REQ_SYNC | REQ_IDLE))
return false;
- /* fallthrough */
+ fallthrough;
case REQ_OP_DISCARD:
return true;
default:
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index fb7b347f8010..d185396d88bb 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -378,7 +378,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
bset->timeout_fn = timeout;
set = &bset->tag_set;
- set->ops = &bsg_mq_ops,
+ set->ops = &bsg_mq_ops;
set->nr_hw_queues = 1;
set->queue_depth = 128;
set->numa_node = NUMA_NO_NODE;
diff --git a/block/ioprio.c b/block/ioprio.c
index 77bcab11dce5..04ebd37966f1 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -71,7 +71,7 @@ int ioprio_check_cap(int ioprio)
case IOPRIO_CLASS_RT:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- /* fall through */
+ fallthrough;
/* rt has prio field too */
case IOPRIO_CLASS_BE:
if (data >= IOPRIO_BE_NR || data < 0)
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;
}