Merge tag 'v4.20-rc5' into for-4.21/block

Pull in v4.20-rc5, solving a conflict we'll otherwise get in aio.c and
also getting the merge fix that went into mainline that users are
hitting testing for-4.21/block and/or for-next.

* tag 'v4.20-rc5': (664 commits)
  Linux 4.20-rc5
  PCI: Fix incorrect value returned from pcie_get_speed_cap()
  MAINTAINERS: Update linux-mips mailing list address
  ocfs2: fix potential use after free
  mm/khugepaged: fix the xas_create_range() error path
  mm/khugepaged: collapse_shmem() do not crash on Compound
  mm/khugepaged: collapse_shmem() without freezing new_page
  mm/khugepaged: minor reorderings in collapse_shmem()
  mm/khugepaged: collapse_shmem() remember to clear holes
  mm/khugepaged: fix crashes due to misaccounted holes
  mm/khugepaged: collapse_shmem() stop if punched or truncated
  mm/huge_memory: fix lockdep complaint on 32-bit i_size_read()
  mm/huge_memory: splitting set mapping+index before unfreeze
  mm/huge_memory: rename freeze_page() to unmap_page()
  initramfs: clean old path before creating a hardlink
  kernel/kcov.c: mark funcs in __sanitizer_cov_trace_pc() as notrace
  psi: make disabling/enabling easier for vendor kernels
  proc: fixup map_files test on arm
  debugobjects: avoid recursive calls with kmemleak
  userfaultfd: shmem: UFFDIO_COPY: set the page dirty if VM_WRITE is not set
  ...

1 files changed, 64 insertions, 11 deletions

diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index de797c641265..e6994e4ce17e 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -152,6 +152,7 @@ struct nvme_fc_ctrl {
 
 	bool			ioq_live;
 	bool			assoc_active;
+	atomic_t		err_work_active;
 	u64			association_id;
 
 	struct list_head	ctrl_list;	/* rport->ctrl_list */
@@ -160,6 +161,7 @@ struct nvme_fc_ctrl {
 	struct blk_mq_tag_set	tag_set;
 
 	struct delayed_work	connect_work;
+	struct work_struct	err_work;
 
 	struct kref		ref;
 	u32			flags;
@@ -1531,6 +1533,10 @@ nvme_fc_abort_aen_ops(struct nvme_fc_ctrl *ctrl)
 	struct nvme_fc_fcp_op *aen_op = ctrl->aen_ops;
 	int i;
 
+	/* ensure we've initialized the ops once */
+	if (!(aen_op->flags & FCOP_FLAGS_AEN))
+		return;
+
 	for (i = 0; i < NVME_NR_AEN_COMMANDS; i++, aen_op++)
 		__nvme_fc_abort_op(ctrl, aen_op);
 }
@@ -1746,12 +1752,12 @@ nvme_fc_init_request(struct blk_mq_tag_set *set, struct request *rq,
 	struct nvme_fc_queue *queue = &ctrl->queues[queue_idx];
 	int res;
 
-	nvme_req(rq)->ctrl = &ctrl->ctrl;
 	res = __nvme_fc_init_request(ctrl, queue, &op->op, rq, queue->rqcnt++);
 	if (res)
 		return res;
 	op->op.fcp_req.first_sgl = &op->sgl[0];
 	op->op.fcp_req.private = &op->priv[0];
+	nvme_req(rq)->ctrl = &ctrl->ctrl;
 	return res;
 }
 
@@ -2049,7 +2055,25 @@ nvme_fc_nvme_ctrl_freed(struct nvme_ctrl *nctrl)
 static void
 nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
 {
-	/* only proceed if in LIVE state - e.g. on first error */
+	int active;
+
+	/*
+	 * if an error (io timeout, etc) while (re)connecting,
+	 * it's an error on creating the new association.
+	 * Start the error recovery thread if it hasn't already
+	 * been started. It is expected there could be multiple
+	 * ios hitting this path before things are cleaned up.
+	 */
+	if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) {
+		active = atomic_xchg(&ctrl->err_work_active, 1);
+		if (!active && !schedule_work(&ctrl->err_work)) {
+			atomic_set(&ctrl->err_work_active, 0);
+			WARN_ON(1);
+		}
+		return;
+	}
+
+	/* Otherwise, only proceed if in LIVE state - e.g. on first error */
 	if (ctrl->ctrl.state != NVME_CTRL_LIVE)
 		return;
 
@@ -2782,6 +2806,7 @@ nvme_fc_delete_ctrl(struct nvme_ctrl *nctrl)
 {
 	struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
 
+	cancel_work_sync(&ctrl->err_work);
 	cancel_delayed_work_sync(&ctrl->connect_work);
 	/*
 	 * kill the association on the link side.  this will block
@@ -2834,23 +2859,30 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status)
 }
 
 static void
-nvme_fc_reset_ctrl_work(struct work_struct *work)
+__nvme_fc_terminate_io(struct nvme_fc_ctrl *ctrl)
 {
-	struct nvme_fc_ctrl *ctrl =
-		container_of(work, struct nvme_fc_ctrl, ctrl.reset_work);
-	int ret;
-
-	nvme_stop_ctrl(&ctrl->ctrl);
+	nvme_stop_keep_alive(&ctrl->ctrl);
 
 	/* will block will waiting for io to terminate */
 	nvme_fc_delete_association(ctrl);
 
-	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
+	if (ctrl->ctrl.state != NVME_CTRL_CONNECTING &&
+	    !nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING))
 		dev_err(ctrl->ctrl.device,
 			"NVME-FC{%d}: error_recovery: Couldn't change state "
 			"to CONNECTING\n", ctrl->cnum);
-		return;
-	}
+}
+
+static void
+nvme_fc_reset_ctrl_work(struct work_struct *work)
+{
+	struct nvme_fc_ctrl *ctrl =
+		container_of(work, struct nvme_fc_ctrl, ctrl.reset_work);
+	int ret;
+
+	__nvme_fc_terminate_io(ctrl);
+
+	nvme_stop_ctrl(&ctrl->ctrl);
 
 	if (ctrl->rport->remoteport.port_state == FC_OBJSTATE_ONLINE)
 		ret = nvme_fc_create_association(ctrl);
@@ -2865,6 +2897,24 @@ nvme_fc_reset_ctrl_work(struct work_struct *work)
 			ctrl->cnum);
 }
 
+static void
+nvme_fc_connect_err_work(struct work_struct *work)
+{
+	struct nvme_fc_ctrl *ctrl =
+			container_of(work, struct nvme_fc_ctrl, err_work);
+
+	__nvme_fc_terminate_io(ctrl);
+
+	atomic_set(&ctrl->err_work_active, 0);
+
+	/*
+	 * Rescheduling the connection after recovering
+	 * from the io error is left to the reconnect work
+	 * item, which is what should have stalled waiting on
+	 * the io that had the error that scheduled this work.
+	 */
+}
+
 static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = {
 	.name			= "fc",
 	.module			= THIS_MODULE,
@@ -2975,6 +3025,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	ctrl->cnum = idx;
 	ctrl->ioq_live = false;
 	ctrl->assoc_active = false;
+	atomic_set(&ctrl->err_work_active, 0);
 	init_waitqueue_head(&ctrl->ioabort_wait);
 
 	get_device(ctrl->dev);
@@ -2982,6 +3033,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 
 	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->err_work, nvme_fc_connect_err_work);
 	spin_lock_init(&ctrl->lock);
 
 	/* io queue count */
@@ -3071,6 +3123,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 fail_ctrl:
 	nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING);
 	cancel_work_sync(&ctrl->ctrl.reset_work);
+	cancel_work_sync(&ctrl->err_work);
 	cancel_delayed_work_sync(&ctrl->connect_work);
 
 	ctrl->ctrl.opts = NULL;