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.
Changes since v1:
Use single threaded workqueue to serialize work in
storvsc_handle_error [Christoph Hellwig]
Signed-off-by: Cathy Avery <cav...@redhat.com>
---
drivers/scsi/storvsc_drv.c | 27 ++++++++++++++++++++++-----
1 file changed, 22 insertions(+), 5 deletions(-)
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 5e7200f..6febcdb 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -486,6 +486,8 @@ struct hv_host_device {
unsigned int port;
unsigned char path;
unsigned char target;
+ struct workqueue_struct *handle_error_wq;
+ char work_q_name[20];
};
struct storvsc_scan_work {
@@ -922,6 +924,7 @@ 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 +991,7 @@ 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 +1806,19 @@ 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.
+ */
+ snprintf(host_dev->work_q_name, sizeof(host_dev->work_q_name),
+ "storvsc_error_wq_%d", host->host_no);
+ host_dev->handle_error_wq =
+ create_singlethread_workqueue(host_dev->work_q_name);
+ 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 +1827,7 @@ 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 +1839,17 @@ 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 +1873,7 @@ 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 +1881,7 @@ 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);
--
2.5.0
