[SCSI] qla2xxx: Correct rport/fcport visibility-state handling during loop-resync.
There were several issues here, one, during RSCN handling if a
follow-on RSCN occurred (within interrupt context) the DPC thread
could inadvertantly leave the fcport in a stale lost state.
Secondly, scheduled rport removal is handled exclusively by the
'parent' DPC thread, so wake up the proper thread. Finally,
process vport loop-resync's only when the vport has in an
"active" state (ID acquired).
Signed-off-by: Seokmann Ju <seokmann.ju@qlogic.com>
Signed-off-by: Andrew Vasquez <andrew.vasquez@qlogic.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c
index e756576..9a850a2 100644
--- a/drivers/scsi/qla2xxx/qla_mid.c
+++ b/drivers/scsi/qla2xxx/qla_mid.c
@@ -277,7 +277,8 @@
clear_bit(RESET_ACTIVE, &vha->dpc_flags);
}
- if (test_and_clear_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags)) {
+ if (atomic_read(&vha->vp_state) == VP_ACTIVE &&
+ test_and_clear_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags)) {
if (!(test_and_set_bit(LOOP_RESYNC_ACTIVE, &vha->dpc_flags))) {
qla2x00_loop_resync(vha);
clear_bit(LOOP_RESYNC_ACTIVE, &vha->dpc_flags);