On 10/01/16 15:56, Ming Lei wrote:
If we just call the rcu/srcu read lock(or the mutex) around .queue_rq(), the
above code needn't to be duplicated any more.
Hello Ming,
Can you have a look at the attached patch? That patch uses an srcu read
lock for all queue types, whether or not the BLK_MQ_F_BLOCKING flag has
been set. Additionally, I have dropped the QUEUE_FLAG_QUIESCING flag.
Just like previous versions, this patch has been tested.
Thanks,
Bart.
>From 25f02ed7ab7b2308fd18b89d180c0c613e55d416 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@xxxxxxxxxxx>
Date: Tue, 27 Sep 2016 10:52:36 -0700
Subject: [PATCH] blk-mq: Introduce blk_mq_quiesce_queue()
blk_mq_quiesce_queue() waits until ongoing .queue_rq() invocations
have finished. This function does *not* wait until all outstanding
requests have finished (this means invocation of request.end_io()).
Signed-off-by: Bart Van Assche <bart.vanassche@xxxxxxxxxxx>
Cc: Ming Lei <tom.leiming@xxxxxxxxx>
Cc: Hannes Reinecke <hare@xxxxxxxx>
Cc: Johannes Thumshirn <jthumshirn@xxxxxxx>
---
block/blk-mq.c | 40 ++++++++++++++++++++++++++++++++++------
include/linux/blk-mq.h | 3 +++
include/linux/blkdev.h | 1 +
3 files changed, 38 insertions(+), 6 deletions(-)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index d8c45de..38ae685 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -115,6 +115,23 @@ void blk_mq_unfreeze_queue(struct request_queue *q)
}
EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
+/**
+ * blk_mq_quiesce_queue() - wait until all ongoing queue_rq calls have finished
+ *
+ * Note: this function does not prevent that the struct request end_io()
+ * callback function is invoked. Additionally, it is not prevented that
+ * new queue_rq() calls occur unless the queue has been stopped first.
+ */
+void blk_mq_quiesce_queue(struct request_queue *q)
+{
+ struct blk_mq_hw_ctx *hctx;
+ unsigned int i;
+
+ queue_for_each_hw_ctx(q, hctx, i)
+ synchronize_srcu(&hctx->queue_rq_srcu);
+}
+EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue);
+
void blk_mq_wake_waiters(struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
@@ -789,11 +806,13 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
LIST_HEAD(rq_list);
LIST_HEAD(driver_list);
struct list_head *dptr;
- int queued;
+ int queued, srcu_idx;
if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
return;
+ srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
+
WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) &&
cpu_online(hctx->next_cpu));
@@ -885,6 +904,8 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
**/
blk_mq_run_hw_queue(hctx, true);
}
+
+ srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
}
/*
@@ -1298,7 +1319,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
const int is_flush_fua = bio->bi_opf & (REQ_PREFLUSH | REQ_FUA);
struct blk_map_ctx data;
struct request *rq;
- unsigned int request_count = 0;
+ unsigned int request_count = 0, srcu_idx;
struct blk_plug *plug;
struct request *same_queue_rq = NULL;
blk_qc_t cookie;
@@ -1341,7 +1362,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
blk_mq_bio_to_request(rq, bio);
/*
- * We do limited pluging. If the bio can be merged, do that.
+ * We do limited plugging. If the bio can be merged, do that.
* Otherwise the existing request in the plug list will be
* issued. So the plug list will have one request at most
*/
@@ -1361,9 +1382,12 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
blk_mq_put_ctx(data.ctx);
if (!old_rq)
goto done;
- if (!blk_mq_direct_issue_request(old_rq, &cookie))
- goto done;
- blk_mq_insert_request(old_rq, false, true, true);
+
+ srcu_idx = srcu_read_lock(&data.hctx->queue_rq_srcu);
+ if (blk_mq_direct_issue_request(old_rq, &cookie) != 0)
+ blk_mq_insert_request(old_rq, false, true, true);
+ srcu_read_unlock(&data.hctx->queue_rq_srcu, srcu_idx);
+
goto done;
}
@@ -1659,6 +1683,8 @@ static void blk_mq_exit_hctx(struct request_queue *q,
if (set->ops->exit_hctx)
set->ops->exit_hctx(hctx, hctx_idx);
+ cleanup_srcu_struct(&hctx->queue_rq_srcu);
+
blk_mq_unregister_cpu_notifier(&hctx->cpu_notifier);
blk_free_flush_queue(hctx->fq);
sbitmap_free(&hctx->ctx_map);
@@ -1741,6 +1767,8 @@ static int blk_mq_init_hctx(struct request_queue *q,
flush_start_tag + hctx_idx, node))
goto free_fq;
+ init_srcu_struct(&hctx->queue_rq_srcu);
+
return 0;
free_fq:
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 368c460d..b2ccd3c 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -3,6 +3,7 @@
#include <linux/blkdev.h>
#include <linux/sbitmap.h>
+#include <linux/srcu.h>
struct blk_mq_tags;
struct blk_flush_queue;
@@ -41,6 +42,8 @@ struct blk_mq_hw_ctx {
struct blk_mq_tags *tags;
+ struct srcu_struct queue_rq_srcu;
+
unsigned long queued;
unsigned long run;
#define BLK_MQ_MAX_DISPATCH_ORDER 7
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c47c358..8259d87 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -824,6 +824,7 @@ extern void __blk_run_queue(struct request_queue *q);
extern void __blk_run_queue_uncond(struct request_queue *q);
extern void blk_run_queue(struct request_queue *);
extern void blk_run_queue_async(struct request_queue *q);
+extern void blk_mq_quiesce_queue(struct request_queue *q);
extern int blk_rq_map_user(struct request_queue *, struct request *,
struct rq_map_data *, void __user *, unsigned long,
gfp_t);
--
2.9.3
