blk-mq: introduce blk_mq_tagset_wait_completed_request()

mainline inclusion
from mainline-v5.4-rc1
commit f9934a80
category: bugfix
bugzilla: NA
CVE: NA
Link: https://gitee.com/openeuler/kernel/issues/I1WGZE

-------------------------------------------------

blk-mq may schedule to call queue's complete function on remote CPU via
IPI, but doesn't provide any way to synchronize the request's complete
fn. The current queue freeze interface can't provide the synchonization
because aborted requests stay at blk-mq queues during EH.

In some driver's EH(such as NVMe), hardware queue's resource may be freed
&re-allocated. If the completed request's complete fn is run finally
after the hardware queue's resource is released, kernel crash will be
triggered.

Prepare for fixing this kind of issue by introducing
blk_mq_tagset_wait_completed_request().

Cc: Max Gurtovoy <maxg@mellanox.com>
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Christoph Hellwig <hch@lst.de>
Reviewed-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
Reviewed-by: NChao Leng <lengchao@huawei.com>
Reviewed-by: NJike Cheng <chengjike.cheng@huawei.com>
Conflicts:
  block/blk-mq-tag.c
  include/linux/blk-mq.h
[lrz: remain return type to void as 4.19]
Signed-off-by: NRuozhu Li <liruozhu@huawei.com>
Signed-off-by: NLijie <lijie34@huawei.com>
Reviewed-by: NTao Hou <houtao1@huawei.com>
Signed-off-by: NYang Yingliang <yangyingliang@huawei.com>

block/blk-mq-tag.c

@@ -9,6 +9,7 @@
 #include <linux/module.h>
 
 #include <linux/blk-mq.h>
+#include <linux/delay.h>
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-tag.h"
@@ -328,6 +329,36 @@ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 }
 EXPORT_SYMBOL(blk_mq_tagset_busy_iter);
 
+static void blk_mq_tagset_count_completed_rqs(struct request *rq,
+		void *data, bool reserved)
+{
+	unsigned *count = data;
+
+	if (blk_mq_request_completed(rq))
+		(*count)++;
+}
+
+/**
+ * blk_mq_tagset_wait_completed_request - wait until all completed req's
+ * complete funtion is run
+ * @tagset:	Tag set to drain completed request
+ *
+ * Note: This function has to be run after all IO queues are shutdown
+ */
+void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset)
+{
+	while (true) {
+		unsigned count = 0;
+
+		blk_mq_tagset_busy_iter(tagset,
+				blk_mq_tagset_count_completed_rqs, &count);
+		if (!count)
+			break;
+		msleep(5);
+	}
+}
+EXPORT_SYMBOL(blk_mq_tagset_wait_completed_request);
+
 static void __blk_mq_queue_tag_busy_iter(struct request_queue *q,
 		busy_iter_fn *fn, void *priv, bool inflight)
 {

include/linux/blk-mq.h

@@ -316,6 +316,7 @@ void blk_mq_run_hw_queues(struct request_queue *q, bool async);
 void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs);
 void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 		busy_tag_iter_fn *fn, void *priv);
+void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset);
 void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_unfreeze_queue(struct request_queue *q);
 void blk_freeze_queue_start(struct request_queue *q);