blk-mq: move the srcu_struct used for quiescing to the tagset
All I/O submissions have fairly similar latencies, and a tagset-wide
quiesce is a fairly common operation.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Chao Leng <lengchao@huawei.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Link: https://lore.kernel.org/r/20221101150050.3510-12-hch@lst.de
[axboe: fix whitespace]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
diff --git a/block/blk-core.c b/block/blk-core.c
index 5d50dd1..e9e2bf1 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -65,7 +65,6 @@ DEFINE_IDA(blk_queue_ida);
* For queue allocation
*/
struct kmem_cache *blk_requestq_cachep;
-struct kmem_cache *blk_requestq_srcu_cachep;
/*
* Controlling structure to kblockd
@@ -373,26 +372,20 @@ static void blk_timeout_work(struct work_struct *work)
{
}
-struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu)
+struct request_queue *blk_alloc_queue(int node_id)
{
struct request_queue *q;
- q = kmem_cache_alloc_node(blk_get_queue_kmem_cache(alloc_srcu),
- GFP_KERNEL | __GFP_ZERO, node_id);
+ q = kmem_cache_alloc_node(blk_requestq_cachep, GFP_KERNEL | __GFP_ZERO,
+ node_id);
if (!q)
return NULL;
- if (alloc_srcu) {
- blk_queue_flag_set(QUEUE_FLAG_HAS_SRCU, q);
- if (init_srcu_struct(q->srcu) != 0)
- goto fail_q;
- }
-
q->last_merge = NULL;
q->id = ida_alloc(&blk_queue_ida, GFP_KERNEL);
if (q->id < 0)
- goto fail_srcu;
+ goto fail_q;
q->stats = blk_alloc_queue_stats();
if (!q->stats)
@@ -435,11 +428,8 @@ struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu)
blk_free_queue_stats(q->stats);
fail_id:
ida_free(&blk_queue_ida, q->id);
-fail_srcu:
- if (alloc_srcu)
- cleanup_srcu_struct(q->srcu);
fail_q:
- kmem_cache_free(blk_get_queue_kmem_cache(alloc_srcu), q);
+ kmem_cache_free(blk_requestq_cachep, q);
return NULL;
}
@@ -1172,9 +1162,6 @@ int __init blk_dev_init(void)
sizeof_field(struct request, cmd_flags));
BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 *
sizeof_field(struct bio, bi_opf));
- BUILD_BUG_ON(ALIGN(offsetof(struct request_queue, srcu),
- __alignof__(struct request_queue)) !=
- sizeof(struct request_queue));
/* used for unplugging and affects IO latency/throughput - HIGHPRI */
kblockd_workqueue = alloc_workqueue("kblockd",
@@ -1185,10 +1172,6 @@ int __init blk_dev_init(void)
blk_requestq_cachep = kmem_cache_create("request_queue",
sizeof(struct request_queue), 0, SLAB_PANIC, NULL);
- blk_requestq_srcu_cachep = kmem_cache_create("request_queue_srcu",
- sizeof(struct request_queue) +
- sizeof(struct srcu_struct), 0, SLAB_PANIC, NULL);
-
blk_debugfs_root = debugfs_create_dir("block", NULL);
return 0;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index a03abad..bee728da 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -261,8 +261,8 @@ EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait);
*/
void blk_mq_wait_quiesce_done(struct request_queue *q)
{
- if (blk_queue_has_srcu(q))
- synchronize_srcu(q->srcu);
+ if (q->tag_set->flags & BLK_MQ_F_BLOCKING)
+ synchronize_srcu(q->tag_set->srcu);
else
synchronize_rcu();
}
@@ -4003,7 +4003,7 @@ static struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set,
struct request_queue *q;
int ret;
- q = blk_alloc_queue(set->numa_node, set->flags & BLK_MQ_F_BLOCKING);
+ q = blk_alloc_queue(set->numa_node);
if (!q)
return ERR_PTR(-ENOMEM);
q->queuedata = queuedata;
@@ -4168,9 +4168,6 @@ static void blk_mq_update_poll_flag(struct request_queue *q)
int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
struct request_queue *q)
{
- WARN_ON_ONCE(blk_queue_has_srcu(q) !=
- !!(set->flags & BLK_MQ_F_BLOCKING));
-
/* mark the queue as mq asap */
q->mq_ops = set->ops;
@@ -4429,8 +4426,18 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
if (set->nr_maps == 1 && set->nr_hw_queues > nr_cpu_ids)
set->nr_hw_queues = nr_cpu_ids;
- if (blk_mq_alloc_tag_set_tags(set, set->nr_hw_queues) < 0)
- return -ENOMEM;
+ if (set->flags & BLK_MQ_F_BLOCKING) {
+ set->srcu = kmalloc(sizeof(*set->srcu), GFP_KERNEL);
+ if (!set->srcu)
+ return -ENOMEM;
+ ret = init_srcu_struct(set->srcu);
+ if (ret)
+ goto out_free_srcu;
+ }
+
+ ret = blk_mq_alloc_tag_set_tags(set, set->nr_hw_queues);
+ if (ret)
+ goto out_cleanup_srcu;
ret = -ENOMEM;
for (i = 0; i < set->nr_maps; i++) {
@@ -4460,6 +4467,12 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
}
kfree(set->tags);
set->tags = NULL;
+out_cleanup_srcu:
+ if (set->flags & BLK_MQ_F_BLOCKING)
+ cleanup_srcu_struct(set->srcu);
+out_free_srcu:
+ if (set->flags & BLK_MQ_F_BLOCKING)
+ kfree(set->srcu);
return ret;
}
EXPORT_SYMBOL(blk_mq_alloc_tag_set);
@@ -4499,6 +4512,10 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
kfree(set->tags);
set->tags = NULL;
+ if (set->flags & BLK_MQ_F_BLOCKING) {
+ cleanup_srcu_struct(set->srcu);
+ kfree(set->srcu);
+ }
}
EXPORT_SYMBOL(blk_mq_free_tag_set);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 0b28708..ef59fee 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -377,17 +377,17 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
/* run the code block in @dispatch_ops with rcu/srcu read lock held */
#define __blk_mq_run_dispatch_ops(q, check_sleep, dispatch_ops) \
do { \
- if (!blk_queue_has_srcu(q)) { \
- rcu_read_lock(); \
- (dispatch_ops); \
- rcu_read_unlock(); \
- } else { \
+ if ((q)->tag_set->flags & BLK_MQ_F_BLOCKING) { \
int srcu_idx; \
\
might_sleep_if(check_sleep); \
- srcu_idx = srcu_read_lock((q)->srcu); \
+ srcu_idx = srcu_read_lock((q)->tag_set->srcu); \
(dispatch_ops); \
- srcu_read_unlock((q)->srcu, srcu_idx); \
+ srcu_read_unlock((q)->tag_set->srcu, srcu_idx); \
+ } else { \
+ rcu_read_lock(); \
+ (dispatch_ops); \
+ rcu_read_unlock(); \
} \
} while (0)
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 7b98c70..02e94c4 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -742,10 +742,8 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr,
static void blk_free_queue_rcu(struct rcu_head *rcu_head)
{
- struct request_queue *q = container_of(rcu_head, struct request_queue,
- rcu_head);
-
- kmem_cache_free(blk_get_queue_kmem_cache(blk_queue_has_srcu(q)), q);
+ kmem_cache_free(blk_requestq_cachep,
+ container_of(rcu_head, struct request_queue, rcu_head));
}
/**
@@ -782,9 +780,6 @@ static void blk_release_queue(struct kobject *kobj)
if (queue_is_mq(q))
blk_mq_release(q);
- if (blk_queue_has_srcu(q))
- cleanup_srcu_struct(q->srcu);
-
ida_free(&blk_queue_ida, q->id);
call_rcu(&q->rcu_head, blk_free_queue_rcu);
}
diff --git a/block/blk.h b/block/blk.h
index f1398fb..e85703a 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -27,7 +27,6 @@ struct blk_flush_queue {
};
extern struct kmem_cache *blk_requestq_cachep;
-extern struct kmem_cache *blk_requestq_srcu_cachep;
extern struct kobj_type blk_queue_ktype;
extern struct ida blk_queue_ida;
@@ -429,13 +428,7 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio,
struct page *page, unsigned int len, unsigned int offset,
unsigned int max_sectors, bool *same_page);
-static inline struct kmem_cache *blk_get_queue_kmem_cache(bool srcu)
-{
- if (srcu)
- return blk_requestq_srcu_cachep;
- return blk_requestq_cachep;
-}
-struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu);
+struct request_queue *blk_alloc_queue(int node_id);
int disk_scan_partitions(struct gendisk *disk, fmode_t mode);
diff --git a/block/genhd.c b/block/genhd.c
index e7bd036..09cde91 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1414,7 +1414,7 @@ struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass)
struct request_queue *q;
struct gendisk *disk;
- q = blk_alloc_queue(node, false);
+ q = blk_alloc_queue(node);
if (!q)
return NULL;
