[SCSI] mpt2sas: Add additional check for responding volumes after Host Reset
ISSUE DESCRIPTION:
This test case involves creating two RAID1 volumes, then
simultaneiously issue host reset and pull all the drives associated to
the 1st raid volume. The observed behavour is the physical drives are
removed, however the volume remains. The expected behavour is the
volume as well as physical drives should be removed from OS.
FIX:
Add support in the post host reset device scan logic for raid volumes
where the driver will have an additional check for responding raid
volume where the status should be either online, optimal, or degraded.
So for voluemes that have a status of missing or failed, the driver
will mark them for deletion.
Signed-off-by: Kashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
index b327d60..228961b 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
@@ -5952,6 +5952,7 @@
_scsih_search_responding_raid_devices(struct MPT2SAS_ADAPTER *ioc)
{
Mpi2RaidVolPage1_t volume_pg1;
+ Mpi2RaidVolPage0_t volume_pg0;
Mpi2RaidPhysDiskPage0_t pd_pg0;
Mpi2ConfigReply_t mpi_reply;
u16 ioc_status;
@@ -5971,8 +5972,17 @@
if (ioc_status == MPI2_IOCSTATUS_CONFIG_INVALID_PAGE)
break;
handle = le16_to_cpu(volume_pg1.DevHandle);
- _scsih_mark_responding_raid_device(ioc,
- le64_to_cpu(volume_pg1.WWID), handle);
+
+ if (mpt2sas_config_get_raid_volume_pg0(ioc, &mpi_reply,
+ &volume_pg0, MPI2_RAID_VOLUME_PGAD_FORM_HANDLE, handle,
+ sizeof(Mpi2RaidVolPage0_t)))
+ continue;
+
+ if (volume_pg0.VolumeState == MPI2_RAID_VOL_STATE_OPTIMAL ||
+ volume_pg0.VolumeState == MPI2_RAID_VOL_STATE_ONLINE ||
+ volume_pg0.VolumeState == MPI2_RAID_VOL_STATE_DEGRADED)
+ _scsih_mark_responding_raid_device(ioc,
+ le64_to_cpu(volume_pg1.WWID), handle);
}
/* refresh the pd_handles */