From: James Smart <james.smart@broadcom.com>
Date: Tue, 1 Dec 2020 17:52:43 -0800
Subject: nvme-fc: avoid calling _nvme_fc_abort_outstanding_ios from interrupt
 context
Patch-mainline: v5.11-rc3
Git-commit: 19fce0470f05031e6af36e49ce222d0f0050d432
References: bsc#1187076

Recent patches changed calling sequences. nvme_fc_abort_outstanding_ios
used to be called from a timeout or work context. Now it is being called
in an io completion context, which can be an interrupt handler.
Unfortunately, the abort outstanding ios routine attempts to stop nvme
queues and nested routines that may try to sleep, which is in conflict
with the interrupt handler.

Correct replacing the direct call with a work element scheduling, and the
abort outstanding ios routine will be called in the work element.

Fixes: 95ced8a2c72d ("nvme-fc: eliminate terminate_io use by nvme_fc_error_recovery")
Signed-off-by: James Smart <james.smart@broadcom.com>
Reported-by: Daniel Wagner <dwagner@suse.de>
Tested-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Daniel Wagner <dwagner@suse.de>
---
 drivers/nvme/host/fc.c |   15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -159,6 +159,7 @@ struct nvme_fc_ctrl {
 	struct blk_mq_tag_set	admin_tag_set;
 	struct blk_mq_tag_set	tag_set;
 
+	struct work_struct	ioerr_work;
 	struct delayed_work	connect_work;
 
 	struct kref		ref;
@@ -1564,6 +1565,15 @@ static inline void
 }
 
 static void
+nvme_fc_ctrl_ioerr_work(struct work_struct *work)
+{
+	struct nvme_fc_ctrl *ctrl =
+			container_of(work, struct nvme_fc_ctrl, ioerr_work);
+
+	nvme_fc_error_recovery(ctrl, "transport detected io error");
+}
+
+static void
 nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 {
 	struct nvme_fc_fcp_op *op = fcp_req_to_fcp_op(req);
@@ -1720,7 +1730,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req
 
 check_error:
 	if (terminate_assoc)
-		nvme_fc_error_recovery(ctrl, "transport detected io error");
+		queue_work(nvme_reset_wq, &ctrl->ioerr_work);
 }
 
 static int
@@ -2892,6 +2902,7 @@ nvme_fc_delete_ctrl(struct nvme_ctrl *nc
 {
 	struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
 
+	cancel_work_sync(&ctrl->ioerr_work);
 	cancel_delayed_work_sync(&ctrl->connect_work);
 	/*
 	 * kill the association on the link side.  this will block
@@ -3092,6 +3103,7 @@ nvme_fc_init_ctrl(struct device *dev, st
 
 	INIT_WORK(&ctrl->ctrl.reset_work, nvme_fc_reset_ctrl_work);
 	INIT_DELAYED_WORK(&ctrl->connect_work, nvme_fc_connect_ctrl_work);
+	INIT_WORK(&ctrl->ioerr_work, nvme_fc_ctrl_ioerr_work);
 	spin_lock_init(&ctrl->lock);
 
 	/* io queue count */
@@ -3183,6 +3195,7 @@ nvme_fc_init_ctrl(struct device *dev, st
 
 fail_ctrl:
 	nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING);
+	cancel_work_sync(&ctrl->ioerr_work);
 	cancel_work_sync(&ctrl->ctrl.reset_work);
 	cancel_delayed_work_sync(&ctrl->connect_work);