scsi: mpi3mr: Fix controller init failure on fault during queue creation

Firmware can enter a transient fault while creating operational queues.
The driver fails the load immediately.

Add a retry loop that checks controller status and history bit after
queue creation. If either indicates a fault, retry init up to a set
limit before failing.

Signed-off-by: Chandrakanth Patil <chandrakanth.patil@broadcom.com>
Link: https://lore.kernel.org/r/20250820084138.228471-3-chandrakanth.patil@broadcom.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c
index 0152d31d430abd17ab6b71f248435d9c7c417269..124a0aa0ed9ed6ee018056f81d65fcdc8e4af124 100644 (file)
--- a/drivers/scsi/mpi3mr/mpi3mr_fw.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c
@@ -2353,6 +2353,8 @@ static int mpi3mr_create_op_queues(struct mpi3mr_ioc *mrioc)
 {
        int retval = 0;
        u16 num_queues = 0, i = 0, msix_count_op_q = 1;
+       u32 ioc_status;
+       enum mpi3mr_iocstate ioc_state;
 
        num_queues = min_t(int, mrioc->facts.max_op_reply_q,
            mrioc->facts.max_op_req_q);
@@ -2408,6 +2410,14 @@ static int mpi3mr_create_op_queues(struct mpi3mr_ioc *mrioc)
                retval = -1;
                goto out_failed;
        }
+       ioc_status = readl(&mrioc->sysif_regs->ioc_status);
+       ioc_state = mpi3mr_get_iocstate(mrioc);
+       if ((ioc_status & MPI3_SYSIF_IOC_STATUS_RESET_HISTORY) ||
+           ioc_state != MRIOC_STATE_READY) {
+               mpi3mr_print_fault_info(mrioc);
+               retval = -1;
+               goto out_failed;
+       }
        mrioc->num_op_reply_q = mrioc->num_op_req_q = i;
        ioc_info(mrioc,
            "successfully created %d operational queue pairs(default/polled) queue = (%d/%d)\n",