drivers that have shared tagsets may need to quiesce potentially a lot
of request queues that all share a single tagset (e.g. nvme). Add an interface
to quiesce all the queues on a given tagset. This interface is useful because
it can speedup the quiesce by doing it in parallel.
For tagsets that have BLK_MQ_F_BLOCKING set, we use call_srcu to all hctxs
in parallel such that all of them wait for the same rcu elapsed period with
a per-hctx heap allocated rcu_synchronize. for tagsets that don't have
BLK_MQ_F_BLOCKING set, we simply call a single synchronize_rcu as this is
sufficient.
Signed-off-by: Sagi Grimberg <sagi@xxxxxxxxxxx>
---
block/blk-mq.c | 66 ++++++++++++++++++++++++++++++++++++++++++
include/linux/blk-mq.h | 4 +++
2 files changed, 70 insertions(+)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index abcf590f6238..c37e37354330 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -209,6 +209,42 @@ void blk_mq_quiesce_queue_nowait(struct request_queue *q)
}
EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait);
+static void blk_mq_quiesce_blocking_queue_async(struct request_queue *q)
+{
+ struct blk_mq_hw_ctx *hctx;
+ unsigned int i;
+
+ blk_mq_quiesce_queue_nowait(q);
+
+ queue_for_each_hw_ctx(q, hctx, i) {
+ WARN_ON_ONCE(!(hctx->flags & BLK_MQ_F_BLOCKING));
+ hctx->rcu_sync = kmalloc(sizeof(*hctx->rcu_sync), GFP_KERNEL);
+ if (!hctx->rcu_sync)
+ continue;
+
+ init_completion(&hctx->rcu_sync->completion);
+ init_rcu_head(&hctx->rcu_sync->head);
+ call_srcu(hctx->srcu, &hctx->rcu_sync->head,
+ wakeme_after_rcu);
+ }
+}
+
+static void blk_mq_quiesce_blocking_queue_async_wait(struct request_queue *q)
+{
+ struct blk_mq_hw_ctx *hctx;
+ unsigned int i;
+
+ queue_for_each_hw_ctx(q, hctx, i) {
+ WARN_ON_ONCE(!(hctx->flags & BLK_MQ_F_BLOCKING));
+ if (!hctx->rcu_sync) {
+ synchronize_srcu(hctx->srcu);
+ continue;
+ }
+ wait_for_completion(&hctx->rcu_sync->completion);
+ destroy_rcu_head(&hctx->rcu_sync->head);
+ }
+}
+
/**
* blk_mq_quiesce_queue() - wait until all ongoing dispatches have finished
* @q: request queue.
@@ -2884,6 +2920,36 @@ static void queue_set_hctx_shared(struct request_queue *q, bool shared)
}
}
+void blk_mq_quiesce_tagset(struct blk_mq_tag_set *set)
+{
+ struct request_queue *q;
+
+ mutex_lock(&set->tag_list_lock);
+ if (set->flags & BLK_MQ_F_BLOCKING) {
+ list_for_each_entry(q, &set->tag_list, tag_set_list)
+ blk_mq_quiesce_blocking_queue_async(q);
+ list_for_each_entry(q, &set->tag_list, tag_set_list)
+ blk_mq_quiesce_blocking_queue_async_wait(q);
+ } else {
+ list_for_each_entry(q, &set->tag_list, tag_set_list)
+ blk_mq_quiesce_queue_nowait(q);
+ synchronize_rcu();
+ }
+ mutex_unlock(&set->tag_list_lock);
+}
+EXPORT_SYMBOL_GPL(blk_mq_quiesce_tagset);
+
+void blk_mq_unquiesce_tagset(struct blk_mq_tag_set *set)
+{
+ struct request_queue *q;
+
+ mutex_lock(&set->tag_list_lock);
+ list_for_each_entry(q, &set->tag_list, tag_set_list)
+ blk_mq_unquiesce_queue(q);
+ mutex_unlock(&set->tag_list_lock);
+}
+EXPORT_SYMBOL_GPL(blk_mq_unquiesce_tagset);
+
static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set,
bool shared)
{
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 23230c1d031e..a85f2dedc947 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -5,6 +5,7 @@
#include <linux/blkdev.h>
#include <linux/sbitmap.h>
#include <linux/srcu.h>
+#include <linux/rcupdate_wait.h>
struct blk_mq_tags;
struct blk_flush_queue;
@@ -170,6 +171,7 @@ struct blk_mq_hw_ctx {
*/
struct list_head hctx_list;
+ struct rcu_synchronize *rcu_sync;
/**
* @srcu: Sleepable RCU. Use as lock when type of the hardware queue is
* blocking (BLK_MQ_F_BLOCKING). Must be the last member - see also
@@ -532,6 +534,8 @@ int blk_mq_map_queues(struct blk_mq_queue_map *qmap);
void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues);
void blk_mq_quiesce_queue_nowait(struct request_queue *q);
+void blk_mq_quiesce_tagset(struct request_queue *q);
+void blk_mq_unquiesce_tagset(struct request_queue *q);
unsigned int blk_mq_rq_cpu(struct request *rq);
--
2.25.1
