[PATCH AUTOSEL 5.4 24/42] nvme: introduce nvme_sync_io_queues

[PATCH AUTOSEL 5.4 24/42] nvme: introduce nvme_sync_io_queues

[Sasha Levin]

From: Chao Leng <lengchao@huawei.com>

[ Upstream commit 04800fbff4764ab7b32c49d19628605a5d4cb85c ]

Introduce sync io queues for some scenarios which just only need sync
io queues not sync all queues.

Signed-off-by: Chao Leng <lengchao@huawei.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/nvme/host/core.c | 8 ++++++--
 drivers/nvme/host/nvme.h | 1 +
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index ce69aaea581a5..7a964271959d8 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4226,8 +4226,7 @@ void nvme_start_queues(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_start_queues);
 
-
-void nvme_sync_queues(struct nvme_ctrl *ctrl)
+void nvme_sync_io_queues(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
 
@@ -4235,7 +4234,12 @@ void nvme_sync_queues(struct nvme_ctrl *ctrl)
 	list_for_each_entry(ns, &ctrl->namespaces, list)
 		blk_sync_queue(ns->queue);
 	up_read(&ctrl->namespaces_rwsem);
+}
+EXPORT_SYMBOL_GPL(nvme_sync_io_queues);
 
+void nvme_sync_queues(struct nvme_ctrl *ctrl)
+{
+	nvme_sync_io_queues(ctrl);
 	if (ctrl->admin_q)
 		blk_sync_queue(ctrl->admin_q);
 }
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index d7132d8cb7c5d..e392d6cd92ced 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -494,6 +494,7 @@ 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_sync_queues(struct nvme_ctrl *ctrl);
+void nvme_sync_io_queues(struct nvme_ctrl *ctrl);
 void nvme_unfreeze(struct nvme_ctrl *ctrl);
 void nvme_wait_freeze(struct nvme_ctrl *ctrl);
 int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout);
-- 
2.27.0


_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

[PATCH AUTOSEL 5.4 25/42] nvme-rdma: avoid race between time out and tear down

[Sasha Levin]

From: Chao Leng <lengchao@huawei.com>

[ Upstream commit 3017013dcc82a4862bd1e140f8b762cfc594008d ]

Now use teardown_lock to serialize for time out and tear down. This may
cause abnormal: first cancel all request in tear down, then time out may
complete the request again, but the request may already be freed or
restarted.

To avoid race between time out and tear down, in tear down process,
first we quiesce the queue, and then delete the timer and cancel
the time out work for the queue. At the same time we need to delete
teardown_lock.

Signed-off-by: Chao Leng <lengchao@huawei.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/nvme/host/rdma.c | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index a41ee9feab8e7..5199618510a2a 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -110,7 +110,6 @@ struct nvme_rdma_ctrl {
 	struct sockaddr_storage src_addr;
 
 	struct nvme_ctrl	ctrl;
-	struct mutex		teardown_lock;
 	bool			use_inline_data;
 	u32			io_queues[HCTX_MAX_TYPES];
 };
@@ -933,8 +932,8 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
-	mutex_lock(&ctrl->teardown_lock);
 	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+	blk_sync_queue(ctrl->ctrl.admin_q);
 	nvme_rdma_stop_queue(&ctrl->queues[0]);
 	if (ctrl->ctrl.admin_tagset) {
 		blk_mq_tagset_busy_iter(ctrl->ctrl.admin_tagset,
@@ -944,16 +943,15 @@ static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
 	if (remove)
 		blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
 	nvme_rdma_destroy_admin_queue(ctrl, remove);
-	mutex_unlock(&ctrl->teardown_lock);
 }
 
 static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
-	mutex_lock(&ctrl->teardown_lock);
 	if (ctrl->ctrl.queue_count > 1) {
 		nvme_start_freeze(&ctrl->ctrl);
 		nvme_stop_queues(&ctrl->ctrl);
+		nvme_sync_io_queues(&ctrl->ctrl);
 		nvme_rdma_stop_io_queues(ctrl);
 		if (ctrl->ctrl.tagset) {
 			blk_mq_tagset_busy_iter(ctrl->ctrl.tagset,
@@ -964,7 +962,6 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
 			nvme_start_queues(&ctrl->ctrl);
 		nvme_rdma_destroy_io_queues(ctrl, remove);
 	}
-	mutex_unlock(&ctrl->teardown_lock);
 }
 
 static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl)
@@ -1720,16 +1717,12 @@ static void nvme_rdma_complete_timed_out(struct request *rq)
 {
 	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
 	struct nvme_rdma_queue *queue = req->queue;
-	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
 
-	/* fence other contexts that may complete the command */
-	mutex_lock(&ctrl->teardown_lock);
 	nvme_rdma_stop_queue(queue);
 	if (!blk_mq_request_completed(rq)) {
 		nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
 		blk_mq_complete_request(rq);
 	}
-	mutex_unlock(&ctrl->teardown_lock);
 }
 
 static enum blk_eh_timer_return
@@ -2021,7 +2014,6 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 		return ERR_PTR(-ENOMEM);
 	ctrl->ctrl.opts = opts;
 	INIT_LIST_HEAD(&ctrl->list);
-	mutex_init(&ctrl->teardown_lock);
 
 	if (!(opts->mask & NVMF_OPT_TRSVCID)) {
 		opts->trsvcid =
-- 
2.27.0


_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

[PATCH AUTOSEL 5.4 26/42] nvme-tcp: avoid race between time out and tear down

[Sasha Levin]

From: Chao Leng <lengchao@huawei.com>

[ Upstream commit d6f66210f4b1aa2f5944f0e34e0f8db44f499f92 ]

Now use teardown_lock to serialize for time out and tear down. This may
cause abnormal: first cancel all request in tear down, then time out may
complete the request again, but the request may already be freed or
restarted.

To avoid race between time out and tear down, in tear down process,
first we quiesce the queue, and then delete the timer and cancel
the time out work for the queue. At the same time we need to delete
teardown_lock.

Signed-off-by: Chao Leng <lengchao@huawei.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/nvme/host/tcp.c | 14 +++-----------
 1 file changed, 3 insertions(+), 11 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index e159b78b5f3b4..76440f26c1453 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -110,7 +110,6 @@ struct nvme_tcp_ctrl {
 	struct sockaddr_storage src_addr;
 	struct nvme_ctrl	ctrl;
 
-	struct mutex		teardown_lock;
 	struct work_struct	err_work;
 	struct delayed_work	connect_work;
 	struct nvme_tcp_request async_req;
@@ -1797,8 +1796,8 @@ static int nvme_tcp_configure_admin_queue(struct nvme_ctrl *ctrl, bool new)
 static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
 		bool remove)
 {
-	mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
 	blk_mq_quiesce_queue(ctrl->admin_q);
+	blk_sync_queue(ctrl->admin_q);
 	nvme_tcp_stop_queue(ctrl, 0);
 	if (ctrl->admin_tagset) {
 		blk_mq_tagset_busy_iter(ctrl->admin_tagset,
@@ -1808,18 +1807,17 @@ static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
 	if (remove)
 		blk_mq_unquiesce_queue(ctrl->admin_q);
 	nvme_tcp_destroy_admin_queue(ctrl, remove);
-	mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
 }
 
 static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 		bool remove)
 {
-	mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
 	if (ctrl->queue_count <= 1)
-		goto out;
+		return;
 	blk_mq_quiesce_queue(ctrl->admin_q);
 	nvme_start_freeze(ctrl);
 	nvme_stop_queues(ctrl);
+	nvme_sync_io_queues(ctrl);
 	nvme_tcp_stop_io_queues(ctrl);
 	if (ctrl->tagset) {
 		blk_mq_tagset_busy_iter(ctrl->tagset,
@@ -1829,8 +1827,6 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 	if (remove)
 		nvme_start_queues(ctrl);
 	nvme_tcp_destroy_io_queues(ctrl, remove);
-out:
-	mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
 }
 
 static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl)
@@ -2074,14 +2070,11 @@ static void nvme_tcp_complete_timed_out(struct request *rq)
 	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
 	struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl;
 
-	/* fence other contexts that may complete the command */
-	mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
 	nvme_tcp_stop_queue(ctrl, nvme_tcp_queue_id(req->queue));
 	if (!blk_mq_request_completed(rq)) {
 		nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
 		blk_mq_complete_request(rq);
 	}
-	mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
 }
 
 static enum blk_eh_timer_return
@@ -2344,7 +2337,6 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
 			nvme_tcp_reconnect_ctrl_work);
 	INIT_WORK(&ctrl->err_work, nvme_tcp_error_recovery_work);
 	INIT_WORK(&ctrl->ctrl.reset_work, nvme_reset_ctrl_work);
-	mutex_init(&ctrl->teardown_lock);
 
 	if (!(opts->mask & NVMF_OPT_TRSVCID)) {
 		opts->trsvcid =
-- 
2.27.0


_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

[PATCH AUTOSEL 5.4 27/42] nvme-rdma: avoid repeated request completion

[Sasha Levin]

From: Sagi Grimberg <sagi@grimberg.me>

[ Upstream commit fdf58e02adecbef4c7cbb2073d8ea225e6fd5f26 ]

The request may be executed asynchronously, and rq->state may be
changed to IDLE. To avoid repeated request completion, only
MQ_RQ_COMPLETE of rq->state is checked in nvme_rdma_complete_timed_out.
It is not safe, so need adding check IDLE for rq->state.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Chao Leng <lengchao@huawei.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/nvme/host/rdma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 5199618510a2a..9948e2dfe55f2 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1719,7 +1719,7 @@ static void nvme_rdma_complete_timed_out(struct request *rq)
 	struct nvme_rdma_queue *queue = req->queue;
 
 	nvme_rdma_stop_queue(queue);
-	if (!blk_mq_request_completed(rq)) {
+	if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) {
 		nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
 		blk_mq_complete_request(rq);
 	}
-- 
2.27.0


_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

[PATCH AUTOSEL 5.4 28/42] nvme-tcp: avoid repeated request completion

[Sasha Levin]

From: Sagi Grimberg <sagi@grimberg.me>

[ Upstream commit 0a8a2c85b83589a5c10bc5564b796836bf4b4984 ]

The request may be executed asynchronously, and rq->state may be
changed to IDLE. To avoid repeated request completion, only
MQ_RQ_COMPLETE of rq->state is checked in nvme_tcp_complete_timed_out.
It is not safe, so need adding check IDLE for rq->state.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Chao Leng <lengchao@huawei.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/nvme/host/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 76440f26c1453..a31c6e1f6063a 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -2071,7 +2071,7 @@ static void nvme_tcp_complete_timed_out(struct request *rq)
 	struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl;
 
 	nvme_tcp_stop_queue(ctrl, nvme_tcp_queue_id(req->queue));
-	if (!blk_mq_request_completed(rq)) {
+	if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) {
 		nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
 		blk_mq_complete_request(rq);
 	}
-- 
2.27.0


_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme