Commit b45e05aa authored by Xiang Chen's avatar Xiang Chen Committed by Martin K. Petersen

scsi: hisi_sas: Retry 3 times TMF IO for SAS disks when init device

When init device for SAS disks, it will send TMF IO to clear disks. At that
time TMF IO is broken by some operations such as injecting controller reset
from HW RAs event, the TMF IO will be timeout, and at last device will be
gone. Print is as followed:

hisi_sas_v3_hw 0000:74:02.0: dev[240:1] found
...
hisi_sas_v3_hw 0000:74:02.0: controller resetting...
hisi_sas_v3_hw 0000:74:02.0: phyup: phy7 link_rate=10(sata)
hisi_sas_v3_hw 0000:74:02.0: phyup: phy0 link_rate=9(sata)
hisi_sas_v3_hw 0000:74:02.0: phyup: phy1 link_rate=9(sata)
hisi_sas_v3_hw 0000:74:02.0: phyup: phy2 link_rate=9(sata)
hisi_sas_v3_hw 0000:74:02.0: phyup: phy3 link_rate=9(sata)
hisi_sas_v3_hw 0000:74:02.0: phyup: phy6 link_rate=10(sata)
hisi_sas_v3_hw 0000:74:02.0: phyup: phy5 link_rate=11
hisi_sas_v3_hw 0000:74:02.0: phyup: phy4 link_rate=11
hisi_sas_v3_hw 0000:74:02.0: controller reset complete
hisi_sas_v3_hw 0000:74:02.0: abort tmf: TMF task timeout and not done
hisi_sas_v3_hw 0000:74:02.0: dev[240:1] is gone
sas: driver on host 0000:74:02.0 cannot handle device 5000c500a75a860d,
error:5

To improve the reliability, retry TMF IO max of 3 times for SAS disks which
is the same as softreset does.

Link: https://lore.kernel.org/r/1567774537-20003-6-git-send-email-john.garry@huawei.comSigned-off-by: default avatarXiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: default avatarJohn Garry <john.garry@huawei.com>
Signed-off-by: default avatarMartin K. Petersen <martin.petersen@oracle.com>
parent 76dd768b
...@@ -698,13 +698,13 @@ static struct hisi_sas_device *hisi_sas_alloc_dev(struct domain_device *device) ...@@ -698,13 +698,13 @@ static struct hisi_sas_device *hisi_sas_alloc_dev(struct domain_device *device)
return sas_dev; return sas_dev;
} }
#define HISI_SAS_SRST_ATA_DISK_CNT 3 #define HISI_SAS_DISK_RECOVER_CNT 3
static int hisi_sas_init_device(struct domain_device *device) static int hisi_sas_init_device(struct domain_device *device)
{ {
int rc = TMF_RESP_FUNC_COMPLETE; int rc = TMF_RESP_FUNC_COMPLETE;
struct scsi_lun lun; struct scsi_lun lun;
struct hisi_sas_tmf_task tmf_task; struct hisi_sas_tmf_task tmf_task;
int retry = HISI_SAS_SRST_ATA_DISK_CNT; int retry = HISI_SAS_DISK_RECOVER_CNT;
struct hisi_hba *hisi_hba = dev_to_hisi_hba(device); struct hisi_hba *hisi_hba = dev_to_hisi_hba(device);
struct device *dev = hisi_hba->dev; struct device *dev = hisi_hba->dev;
struct sas_phy *local_phy; struct sas_phy *local_phy;
...@@ -714,10 +714,14 @@ static int hisi_sas_init_device(struct domain_device *device) ...@@ -714,10 +714,14 @@ static int hisi_sas_init_device(struct domain_device *device)
int_to_scsilun(0, &lun); int_to_scsilun(0, &lun);
tmf_task.tmf = TMF_CLEAR_TASK_SET; tmf_task.tmf = TMF_CLEAR_TASK_SET;
rc = hisi_sas_debug_issue_ssp_tmf(device, lun.scsi_lun, while (retry-- > 0) {
&tmf_task); rc = hisi_sas_debug_issue_ssp_tmf(device, lun.scsi_lun,
if (rc == TMF_RESP_FUNC_COMPLETE) &tmf_task);
hisi_sas_release_task(hisi_hba, device); if (rc == TMF_RESP_FUNC_COMPLETE) {
hisi_sas_release_task(hisi_hba, device);
break;
}
}
break; break;
case SAS_SATA_DEV: case SAS_SATA_DEV:
case SAS_SATA_PM: case SAS_SATA_PM:
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment