Merge tag 'block-5.9-2020-09-04' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A bit larger than usual this week, mostly due to the NVMe fixes
  arriving late for -rc3 and hence didn't make last weeks pull request.

   - NVMe:
        - instance leak and io boundary fixes from Keith
        - fc locking fix from Christophe
        - various tcp/rdma reset during traffic fixes from Sagi
        - pci use-after-free fix from Tong
        - tcp target null deref fix from Ziye

   - Locking fix for partition removal (Christoph)

   - Ensure bdi->io_pages is always set (me)

   - Fixup for hd struct reference (Ming)

   - Fix for zero length bvecs (Ming)

   - Two small blk-iocost fixes (Tejun)"

* tag 'block-5.9-2020-09-04' of git://git.kernel.dk/linux-block:
  block: allow for_each_bvec to support zero len bvec
  blk-stat: make q->stats->lock irqsafe
  blk-iocost: ioc_pd_free() shouldn't assume irq disabled
  block: fix locking in bdev_del_partition
  block: release disk reference in hd_struct_free_work
  block: ensure bdi->io_pages is always initialized
  nvme-pci: cancel nvme device request before disabling
  nvme: only use power of two io boundaries
  nvme: fix controller instance leak
  nvmet-fc: Fix a missed _irqsave version of spin_lock in 'nvmet_fc_fod_op_done()'
  nvme: Fix NULL dereference for pci nvme controllers
  nvme-rdma: fix reset hang if controller died in the middle of a reset
  nvme-rdma: fix timeout handler
  nvme-rdma: serialize controller teardown sequences
  nvme-tcp: fix reset hang if controller died in the middle of a reset
  nvme-tcp: fix timeout handler
  nvme-tcp: serialize controller teardown sequences
  nvme: have nvme_wait_freeze_timeout return if it timed out
  nvme-fabrics: don't check state NVME_CTRL_NEW for request acceptance
  nvmet-tcp: Fix NULL dereference when a connect data comes in h2cdata pdu

1 files changed, 57 insertions, 23 deletions

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index a44d8ace3a81..16851ae3bddf 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -124,6 +124,7 @@ 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;
@@ -464,6 +465,7 @@ static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl)
 	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
 		return;
 
+	dev_warn(ctrl->device, "starting error recovery\n");
 	queue_work(nvme_reset_wq, &to_tcp_ctrl(ctrl)->err_work);
 }
 
@@ -1526,7 +1528,6 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
 
 	if (!test_and_clear_bit(NVME_TCP_Q_LIVE, &queue->flags))
 		return;
-
 	__nvme_tcp_stop_queue(queue);
 }
 
@@ -1781,7 +1782,15 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 
 	if (!new) {
 		nvme_start_queues(ctrl);
-		nvme_wait_freeze(ctrl);
+		if (!nvme_wait_freeze_timeout(ctrl, NVME_IO_TIMEOUT)) {
+			/*
+			 * If we timed out waiting for freeze we are likely to
+			 * be stuck.  Fail the controller initialization just
+			 * to be safe.
+			 */
+			ret = -ENODEV;
+			goto out_wait_freeze_timed_out;
+		}
 		blk_mq_update_nr_hw_queues(ctrl->tagset,
 			ctrl->queue_count - 1);
 		nvme_unfreeze(ctrl);
@@ -1789,6 +1798,9 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 
 	return 0;
 
+out_wait_freeze_timed_out:
+	nvme_stop_queues(ctrl);
+	nvme_tcp_stop_io_queues(ctrl);
 out_cleanup_connect_q:
 	if (new)
 		blk_cleanup_queue(ctrl->connect_q);
@@ -1874,6 +1886,7 @@ out_free_queue:
 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);
 	nvme_tcp_stop_queue(ctrl, 0);
 	if (ctrl->admin_tagset) {
@@ -1884,13 +1897,16 @@ 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)
-		return;
+		goto out;
+	blk_mq_quiesce_queue(ctrl->admin_q);
 	nvme_start_freeze(ctrl);
 	nvme_stop_queues(ctrl);
 	nvme_tcp_stop_io_queues(ctrl);
@@ -1902,6 +1918,8 @@ 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)
@@ -2148,40 +2166,55 @@ static void nvme_tcp_submit_async_event(struct nvme_ctrl *arg)
 	nvme_tcp_queue_request(&ctrl->async_req, true, true);
 }
 
+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
 nvme_tcp_timeout(struct request *rq, bool reserved)
 {
 	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
-	struct nvme_tcp_ctrl *ctrl = req->queue->ctrl;
+	struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl;
 	struct nvme_tcp_cmd_pdu *pdu = req->pdu;
 
-	/*
-	 * Restart the timer if a controller reset is already scheduled. Any
-	 * timed out commands would be handled before entering the connecting
-	 * state.
-	 */
-	if (ctrl->ctrl.state == NVME_CTRL_RESETTING)
-		return BLK_EH_RESET_TIMER;
-
-	dev_warn(ctrl->ctrl.device,
+	dev_warn(ctrl->device,
 		"queue %d: timeout request %#x type %d\n",
 		nvme_tcp_queue_id(req->queue), rq->tag, pdu->hdr.type);
 
-	if (ctrl->ctrl.state != NVME_CTRL_LIVE) {
+	if (ctrl->state != NVME_CTRL_LIVE) {
 		/*
-		 * Teardown immediately if controller times out while starting
-		 * or we are already started error recovery. all outstanding
-		 * requests are completed on shutdown, so we return BLK_EH_DONE.
+		 * If we are resetting, connecting or deleting we should
+		 * complete immediately because we may block controller
+		 * teardown or setup sequence
+		 * - ctrl disable/shutdown fabrics requests
+		 * - connect requests
+		 * - initialization admin requests
+		 * - I/O requests that entered after unquiescing and
+		 *   the controller stopped responding
+		 *
+		 * All other requests should be cancelled by the error
+		 * recovery work, so it's fine that we fail it here.
 		 */
-		flush_work(&ctrl->err_work);
-		nvme_tcp_teardown_io_queues(&ctrl->ctrl, false);
-		nvme_tcp_teardown_admin_queue(&ctrl->ctrl, false);
+		nvme_tcp_complete_timed_out(rq);
 		return BLK_EH_DONE;
 	}
 
-	dev_warn(ctrl->ctrl.device, "starting error recovery\n");
-	nvme_tcp_error_recovery(&ctrl->ctrl);
-
+	/*
+	 * LIVE state should trigger the normal error recovery which will
+	 * handle completing this request.
+	 */
+	nvme_tcp_error_recovery(ctrl);
 	return BLK_EH_RESET_TIMER;
 }
 
@@ -2422,6 +2455,7 @@ 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 =