After running IOPS test for 30 second we get
kernel:NMI watchdog: Watchdog detected hard LOCKUP on cpu 0
The driver is speend too much time in it's ISR.
In ISR EQ and CQ processing routines, if we hit the entry_repost
numbers of EQE/CQEs just break out of the routine as opposed to
hitting the doorbell with NOARM and continue processing.
Signed-off-by: Dick Kennedy <dick.kennedy@xxxxxxxxxxxx>
Signed-off-by: James Smart <james.smart@xxxxxxxxxxxx>
---
drivers/scsi/lpfc/lpfc_debugfs.c | 30 +++++++++++++++---------------
drivers/scsi/lpfc/lpfc_sli.c | 8 ++------
2 files changed, 17 insertions(+), 21 deletions(-)
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index a41daedeb967..7284533f4df2 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -3075,11 +3075,11 @@ __lpfc_idiag_print_wq(struct lpfc_queue *qp, char *wqtype,
qp->assoc_qid, qp->q_cnt_1,
(unsigned long long)qp->q_cnt_4);
len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
- "\t\tWQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
- "HOST-IDX[%04d], PORT-IDX[%04d]",
+ "\t\tWQID[%02d], QE-CNT[%04d], QE-SZ[%04d], "
+ "HST-IDX[%04d], PRT-IDX[%04d], PST[%03d]",
qp->queue_id, qp->entry_count,
qp->entry_size, qp->host_index,
- qp->hba_index);
+ qp->hba_index, qp->entry_repost);
len += snprintf(pbuffer + len,
LPFC_QUE_INFO_GET_BUF_SIZE - len, "\n");
return len;
@@ -3126,11 +3126,11 @@ __lpfc_idiag_print_cq(struct lpfc_queue *qp, char *cqtype,
qp->assoc_qid, qp->q_cnt_1, qp->q_cnt_2,
qp->q_cnt_3, (unsigned long long)qp->q_cnt_4);
len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
- "\tCQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
- "HOST-IDX[%04d], PORT-IDX[%04d]",
+ "\tCQID[%02d], QE-CNT[%04d], QE-SZ[%04d], "
+ "HST-IDX[%04d], PRT-IDX[%04d], PST[%03d]",
qp->queue_id, qp->entry_count,
qp->entry_size, qp->host_index,
- qp->hba_index);
+ qp->hba_index, qp->entry_repost);
len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len, "\n");
@@ -3152,16 +3152,16 @@ __lpfc_idiag_print_rqpair(struct lpfc_queue *qp, struct lpfc_queue *datqp,
qp->assoc_qid, qp->q_cnt_1, qp->q_cnt_2,
qp->q_cnt_3, (unsigned long long)qp->q_cnt_4);
len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
- "\t\tHQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
- "HOST-IDX[%04d], PORT-IDX[%04d]\n",
+ "\t\tHQID[%02d], QE-CNT[%04d], QE-SZ[%04d], "
+ "HST-IDX[%04d], PRT-IDX[%04d], PST[%03d]\n",
qp->queue_id, qp->entry_count, qp->entry_size,
- qp->host_index, qp->hba_index);
+ qp->host_index, qp->hba_index, qp->entry_repost);
len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
- "\t\tDQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
- "HOST-IDX[%04d], PORT-IDX[%04d]\n",
+ "\t\tDQID[%02d], QE-CNT[%04d], QE-SZ[%04d], "
+ "HST-IDX[%04d], PRT-IDX[%04d], PST[%03d]\n",
datqp->queue_id, datqp->entry_count,
datqp->entry_size, datqp->host_index,
- datqp->hba_index);
+ datqp->hba_index, datqp->entry_repost);
return len;
}
@@ -3247,10 +3247,10 @@ __lpfc_idiag_print_eq(struct lpfc_queue *qp, char *eqtype,
eqtype, qp->q_cnt_1, qp->q_cnt_2, qp->q_cnt_3,
(unsigned long long)qp->q_cnt_4);
len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
- "EQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
- "HOST-IDX[%04d], PORT-IDX[%04d]",
+ "EQID[%02d], QE-CNT[%04d], QE-SZ[%04d], "
+ "HST-IDX[%04d], PRT-IDX[%04d], PST[%03d]",
qp->queue_id, qp->entry_count, qp->entry_size,
- qp->host_index, qp->hba_index);
+ qp->host_index, qp->hba_index, qp->entry_repost);
len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len, "\n");
return len;
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index cdf02a957690..66bb86656bba 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -13234,10 +13234,6 @@ lpfc_sli4_nvmet_handle_rcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
case FC_STATUS_INSUFF_BUF_NEED_BUF:
hrq->RQ_no_posted_buf++;
/* Post more buffers if possible */
- spin_lock_irqsave(&phba->hbalock, iflags);
- phba->hba_flag |= HBA_POST_RECEIVE_BUFFER;
- spin_unlock_irqrestore(&phba->hbalock, iflags);
- workposted = true;
break;
}
out:
@@ -13391,7 +13387,7 @@ lpfc_sli4_hba_handle_eqe(struct lpfc_hba *phba, struct lpfc_eqe *eqe,
while ((cqe = lpfc_sli4_cq_get(cq))) {
workposted |= lpfc_sli4_fp_handle_cqe(phba, cq, cqe);
if (!(++ecount % cq->entry_repost))
- lpfc_sli4_cq_release(cq, LPFC_QUEUE_NOARM);
+ break;
}
/* Track the max number of CQEs processed in 1 EQ */
@@ -13681,7 +13677,7 @@ lpfc_sli4_hba_intr_handler(int irq, void *dev_id)
lpfc_sli4_hba_handle_eqe(phba, eqe, hba_eqidx);
if (!(++ecount % fpeq->entry_repost))
- lpfc_sli4_eq_release(fpeq, LPFC_QUEUE_NOARM);
+ break;
fpeq->EQ_processed++;
}
--
2.11.0
