[PATCH 3/4] blk-mq: introduce blk_mq_unfreeze_queue_no_drain_io

[PATCH 3/4] blk-mq: introduce blk_mq_unfreeze_queue_no_drain_io

[Ming Lei]

This patch introduces blk_mq_unfreeze_queue_no_drain_io() so that
it can be used when no necessary to check if IO is drained, such
as nvme pci resetting(nvme_reset_work).

Cc: Tejun Heo <tj at kernel.org>
Cc: Jianchao Wang <jianchao.w.wang at oracle.com>
Cc: Kent Overstreet <kent.overstreet at gmail.com>
Cc: linux-block at vger.kernel.org
Cc: Christoph Hellwig <hch at lst.de>
Cc: linux-nvme at lists.infradead.org
Cc: Keith Busch <keith.busch at intel.com>
Signed-off-by: Ming Lei <ming.lei at redhat.com>
---
 block/blk-mq.c         | 25 +++++++++++++++++++++++--
 include/linux/blk-mq.h |  1 +
 2 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 85a1c1a59c72..a22f82061b93 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -191,20 +191,41 @@ void blk_mq_freeze_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_mq_freeze_queue);
 
-void blk_mq_unfreeze_queue(struct request_queue *q)
+static void __blk_mq_unfreeze_queue(struct request_queue *q,
+		bool need_drop_zero)
 {
 	int freeze_depth;
 
 	freeze_depth = atomic_dec_return(&q->mq_freeze_depth);
 	WARN_ON_ONCE(freeze_depth < 0);
 	if (!freeze_depth) {
-		percpu_ref_reinit(&q->q_usage_counter);
+		if (need_drop_zero)
+			percpu_ref_reinit(&q->q_usage_counter);
+		else
+			percpu_ref_resurge(&q->q_usage_counter);
 		wake_up_all(&q->mq_freeze_wq);
 	}
 }
+
+void blk_mq_unfreeze_queue(struct request_queue *q)
+{
+	__blk_mq_unfreeze_queue(q, true);
+}
 EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
 
 /*
+ * Compared with blk_mq_unfreeze_queue(), the verion of _no_drain_io
+ * doesn't require the queue is really frozen, and it is useful in
+ * case of timeout handling in which IO can't be drained and has to
+ * be retried after controler is recovered.
+ */
+void blk_mq_unfreeze_queue_no_drain_io(struct request_queue *q)
+{
+	__blk_mq_unfreeze_queue(q, false);
+}
+EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue_no_drain_io);
+
+/*
  * FIXME: replace the scsi_internal_device_*block_nowait() calls in the
  * mpt3sas driver such that this function can be removed.
  */
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 1da59c16f637..5e0740ec407f 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -279,6 +279,7 @@ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 		busy_tag_iter_fn *fn, void *priv);
 void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_unfreeze_queue(struct request_queue *q);
+void blk_mq_unfreeze_queue_no_drain_io(struct request_queue *q);
 void blk_freeze_queue_start(struct request_queue *q);
 void blk_mq_freeze_queue_wait(struct request_queue *q);
 int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
-- 
2.9.5

[PATCH 4/4] nvme: don't drain IO in nvme_reset_work()

[Ming Lei]

After the controller is recovered, it isn't necessary to wait for
completion of all in-flight IO. More importantly, it is easy to trigger
deadlock if there is new IO timeout triggered.

Cc: Tejun Heo <tj at kernel.org>
Cc: Jianchao Wang <jianchao.w.wang at oracle.com>
Cc: Kent Overstreet <kent.overstreet at gmail.com>
Cc: linux-block at vger.kernel.org
Cc: Christoph Hellwig <hch at lst.de>
Cc: linux-nvme at lists.infradead.org
Cc: Keith Busch <keith.busch at intel.com>
Signed-off-by: Ming Lei <ming.lei at redhat.com>
---
 drivers/nvme/host/core.c | 12 ++++++++----
 drivers/nvme/host/nvme.h |  2 +-
 drivers/nvme/host/pci.c  |  3 +--
 3 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index dd8ec1dd9219..cf6a2267d44e 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1203,7 +1203,7 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
 	if (effects & NVME_CMD_EFFECTS_LBCC)
 		nvme_update_formats(ctrl);
 	if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK))
-		nvme_unfreeze(ctrl);
+		nvme_unfreeze(ctrl, true);
 	if (effects & NVME_CMD_EFFECTS_CCC)
 		nvme_init_identify(ctrl);
 	if (effects & (NVME_CMD_EFFECTS_NIC | NVME_CMD_EFFECTS_NCC))
@@ -3602,13 +3602,17 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_kill_queues);
 
-void nvme_unfreeze(struct nvme_ctrl *ctrl)
+void nvme_unfreeze(struct nvme_ctrl *ctrl, bool check_io_drained)
 {
 	struct nvme_ns *ns;
 
 	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list)
-		blk_mq_unfreeze_queue(ns->queue);
+	list_for_each_entry(ns, &ctrl->namespaces, list) {
+		if  (check_io_drained)
+			blk_mq_unfreeze_queue(ns->queue);
+		else
+			blk_mq_unfreeze_queue_no_drain_io(ns->queue);
+	}
 	up_read(&ctrl->namespaces_rwsem);
 }
 EXPORT_SYMBOL_GPL(nvme_unfreeze);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index bb4a2003c097..fd56270637d1 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -432,7 +432,7 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 void nvme_stop_queues(struct nvme_ctrl *ctrl);
 void nvme_start_queues(struct nvme_ctrl *ctrl);
 void nvme_kill_queues(struct nvme_ctrl *ctrl);
-void nvme_unfreeze(struct nvme_ctrl *ctrl);
+void nvme_unfreeze(struct nvme_ctrl *ctrl, bool check_io_drained);
 void nvme_wait_freeze(struct nvme_ctrl *ctrl);
 void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout);
 void nvme_start_freeze(struct nvme_ctrl *ctrl);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index d668682f91df..1c26a2e92063 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2328,11 +2328,10 @@ static void nvme_reset_work(struct work_struct *work)
 		new_state = NVME_CTRL_ADMIN_ONLY;
 	} else {
 		nvme_start_queues(&dev->ctrl);
-		nvme_wait_freeze(&dev->ctrl);
 		/* hit this only when allocate tagset fails */
 		if (nvme_dev_add(dev))
 			new_state = NVME_CTRL_ADMIN_ONLY;
-		nvme_unfreeze(&dev->ctrl);
+		nvme_unfreeze(&dev->ctrl, false);
 	}
 
 	/*
-- 
2.9.5