Stall error handler if attempting resets/aborts while an rport is blocked.
This avoids device offline scenarios due to errors in the error handler.
Background:
Although the transport is using the scsi_timed_out functionality to
restart the timeout if the rport is blocked, if the timeout has already
fired before the block occurs, the eh handler still runs and can take
the device offline. Ultimately, this window cannot be resolved without
significant work in the error handler thread. Christoph noted the first
level of these issues when he noted the poor error response handling
by the error thread.
We found, under heavy load and error testing, that time window from when
the scsi_times_out() adds the io to the queue to when the scsi_error_handler
gets around to servicing it, can be in the several seconds range. In most
cases, these test conditions are highly unusual, but possible.
As a result, we're stalling the error handler in this race window so that
we can avoid the device_offline transitions.
Signed-off-by: James Smart <James.Smart@xxxxxxxxxx>
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -21,6 +21,7 @@
#include <linux/pci.h>
#include <linux/interrupt.h>
+#include <linux/delay.h>
#include <scsi/scsi.h>
#include <scsi/scsi_device.h>
@@ -841,6 +842,21 @@ lpfc_queuecommand(struct scsi_cmnd *cmnd
return 0;
}
+static void
+lpfc_block_error_handler(struct scsi_cmnd *cmnd)
+{
+ struct Scsi_Host *shost = cmnd->device->host;
+ struct fc_rport *rport = starget_to_rport(scsi_target(cmnd->device));
+
+ spin_lock_irq(shost->host_lock);
+ while (rport->port_state == FC_PORTSTATE_BLOCKED) {
+ spin_unlock_irq(shost->host_lock);
+ msleep(1000);
+ spin_lock_irq(shost->host_lock);
+ }
+ spin_unlock_irq(shost->host_lock);
+ return;
+}
static int
lpfc_abort_handler(struct scsi_cmnd *cmnd)
@@ -855,6 +871,7 @@ lpfc_abort_handler(struct scsi_cmnd *cmn
unsigned int loop_count = 0;
int ret = SUCCESS;
+ lpfc_block_error_handler(cmnd);
spin_lock_irq(shost->host_lock);
lpfc_cmd = (struct lpfc_scsi_buf *)cmnd->host_scribble;
@@ -957,6 +974,7 @@ lpfc_reset_lun_handler(struct scsi_cmnd
int ret = FAILED;
int cnt, loopcnt;
+ lpfc_block_error_handler(cmnd);
spin_lock_irq(shost->host_lock);
/*
* If target is not in a MAPPED state, delay the reset until
@@ -1073,6 +1091,7 @@ lpfc_reset_bus_handler(struct scsi_cmnd
int cnt, loopcnt;
struct lpfc_scsi_buf * lpfc_cmd;
+ lpfc_block_error_handler(cmnd);
spin_lock_irq(shost->host_lock);
lpfc_cmd = lpfc_get_scsi_buf(phba);
-
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
