blk-mq: introduce blk_mq_tagset_wait_completed_request()

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: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index da19f0bc8876d21d9f0263ed79f8f15720935739..008388e82b5c55f2e06b224998a46bf5b46a9d39 100644 (file)
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -10,6 +10,7 @@
 #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"
@@ -354,6 +355,37 @@ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 }
 EXPORT_SYMBOL(blk_mq_tagset_busy_iter);
 
+static bool blk_mq_tagset_count_completed_rqs(struct request *rq,
+               void *data, bool reserved)
+{
+       unsigned *count = data;
+
+       if (blk_mq_request_completed(rq))
+               (*count)++;
+       return true;
+}
+
+/**
+ * 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);
+
 /**
  * blk_mq_queue_tag_busy_iter - iterate over all requests with a driver tag
  * @q:         Request queue to examine.

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index baac2926e54a4a8f049edcc67bec20c9897bf172..ee0719b649b6c56767f0378a8b1d483418cfab7f 100644 (file)
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -322,6 +322,7 @@ bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
 void blk_mq_run_hw_queues(struct request_queue *q, bool async);
 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);