Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 436ad941 authored by Cathy Avery's avatar Cathy Avery Committed by Martin K. Petersen
Browse files

scsi: storvsc: Allow only one remove lun work item to be issued per lun



When running multipath on a VM if all available paths go down the driver
can schedule large amounts of storvsc_remove_lun work items to the same
lun. In response to the failing paths typically storvsc responds by
taking host->scan_mutex and issuing a TUR per lun. If there has been
heavy IO to the failed device all the failed IOs are returned from the
host. A remove lun work item is issued per failed IO. If the outstanding
TURs have not been completed in a timely manner the scan_mutex is never
released or released too late. Consequently the many remove lun work
items are not completed as scsi_remove_device also tries to take
host->scan_mutex.  This results in dragging the VM down and sometimes
completely.

This patch only allows one remove lun to be issued to a particular lun
while it is an instantiated member of the scsi stack.

Signed-off-by: default avatarCathy Avery <cavery@redhat.com>
Reviewed-by: default avatarChristoph Hellwig <hch@lst.de>
Reviewed-by: default avatarLong Li <longli@microsoft.com>
Signed-off-by: default avatarMartin K. Petersen <martin.petersen@oracle.com>
parent ca6958b4
Loading
Loading
Loading
Loading
+21 −5
Original line number Diff line number Diff line
@@ -486,6 +486,7 @@ struct hv_host_device {
	unsigned int port;
	unsigned char path;
	unsigned char target;
	struct workqueue_struct *handle_error_wq;
};

struct storvsc_scan_work {
@@ -922,6 +923,7 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb,
{
	struct storvsc_scan_work *wrk;
	void (*process_err_fn)(struct work_struct *work);
	struct hv_host_device *host_dev = shost_priv(host);
	bool do_work = false;

	switch (SRB_STATUS(vm_srb->srb_status)) {
@@ -988,7 +990,7 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb,
	wrk->lun = vm_srb->lun;
	wrk->tgt_id = vm_srb->target_id;
	INIT_WORK(&wrk->work, process_err_fn);
	schedule_work(&wrk->work);
	queue_work(host_dev->handle_error_wq, &wrk->work);
}


@@ -1803,10 +1805,19 @@ static int storvsc_probe(struct hv_device *device,
	if (stor_device->num_sc != 0)
		host->nr_hw_queues = stor_device->num_sc + 1;

	/*
	 * Set the error handler work queue.
	 */
	host_dev->handle_error_wq =
			alloc_ordered_workqueue("storvsc_error_wq_%d",
						WQ_MEM_RECLAIM,
						host->host_no);
	if (!host_dev->handle_error_wq)
		goto err_out2;
	/* Register the HBA and start the scsi bus scan */
	ret = scsi_add_host(host, &device->device);
	if (ret != 0)
		goto err_out2;
		goto err_out3;

	if (!dev_is_ide) {
		scsi_scan_host(host);
@@ -1815,7 +1826,7 @@ static int storvsc_probe(struct hv_device *device,
			 device->dev_instance.b[4]);
		ret = scsi_add_device(host, 0, target, 0);
		if (ret)
			goto err_out3;
			goto err_out4;
	}
#if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
	if (host->transportt == fc_transport_template) {
@@ -1827,14 +1838,17 @@ static int storvsc_probe(struct hv_device *device,
		fc_host_port_name(host) = stor_device->port_name;
		stor_device->rport = fc_remote_port_add(host, 0, &ids);
		if (!stor_device->rport)
			goto err_out3;
			goto err_out4;
	}
#endif
	return 0;

err_out3:
err_out4:
	scsi_remove_host(host);

err_out3:
	destroy_workqueue(host_dev->handle_error_wq);

err_out2:
	/*
	 * Once we have connected with the host, we would need to
@@ -1858,6 +1872,7 @@ static int storvsc_remove(struct hv_device *dev)
{
	struct storvsc_device *stor_device = hv_get_drvdata(dev);
	struct Scsi_Host *host = stor_device->host;
	struct hv_host_device *host_dev = shost_priv(host);

#if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
	if (host->transportt == fc_transport_template) {
@@ -1865,6 +1880,7 @@ static int storvsc_remove(struct hv_device *dev)
		fc_remove_host(host);
	}
#endif
	destroy_workqueue(host_dev->handle_error_wq);
	scsi_remove_host(host);
	storvsc_dev_remove(dev);
	scsi_host_put(host);