scsi: mpi3mr: Prevent PCI writes from driver during PCI error recovery

Prevent interaction with the hardware while the error recovery in progress.

Co-developed-by: Sathya Prakash <[email protected]>
Signed-off-by: Sathya Prakash <[email protected]>
Co-developed-by: Ranjan Kumar <[email protected]>
Signed-off-by: Ranjan Kumar <[email protected]>
Signed-off-by: Sumit Saxena <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Martin K. Petersen <[email protected]>

1 files changed, 44 insertions, 5 deletions

diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c
index 0986b362e5f0..69b14918de59 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_os.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_os.c
@@ -956,7 +956,7 @@ static int mpi3mr_report_tgtdev_to_host(struct mpi3mr_ioc *mrioc,
 	int retval = 0;
 	struct mpi3mr_tgt_dev *tgtdev;
 
-	if (mrioc->reset_in_progress)
+	if (mrioc->reset_in_progress || mrioc->pci_err_recovery)
 		return -1;
 
 	tgtdev = mpi3mr_get_tgtdev_by_perst_id(mrioc, perst_id);
@@ -2007,6 +2007,7 @@ static void mpi3mr_fwevt_bh(struct mpi3mr_ioc *mrioc,
 	struct mpi3_device_page0 *dev_pg0 = NULL;
 	u16 perst_id, handle, dev_info;
 	struct mpi3_device0_sas_sata_format *sasinf = NULL;
+	unsigned int timeout;
 
 	mpi3mr_fwevt_del_from_list(mrioc, fwevt);
 	mrioc->current_event = fwevt;
@@ -2097,8 +2098,18 @@ static void mpi3mr_fwevt_bh(struct mpi3mr_ioc *mrioc,
 	}
 	case MPI3_EVENT_WAIT_FOR_DEVICES_TO_REFRESH:
 	{
-		while (mrioc->device_refresh_on)
+		timeout = MPI3MR_RESET_TIMEOUT * 2;
+		while ((mrioc->device_refresh_on || mrioc->block_on_pci_err) &&
+		    !mrioc->unrecoverable && !mrioc->pci_err_recovery) {
 			msleep(500);
+			if (!timeout--) {
+				mrioc->unrecoverable = 1;
+				break;
+			}
+		}
+
+		if (mrioc->unrecoverable || mrioc->pci_err_recovery)
+			break;
 
 		dprint_event_bh(mrioc,
 		    "scan for non responding and newly added devices after soft reset started\n");
@@ -3796,6 +3807,13 @@ int mpi3mr_issue_tm(struct mpi3mr_ioc *mrioc, u8 tm_type,
 		mutex_unlock(&drv_cmd->mutex);
 		goto out;
 	}
+	if (mrioc->block_on_pci_err) {
+		retval = -1;
+		dprint_tm(mrioc, "sending task management failed due to\n"
+				"pci error recovery in progress\n");
+		mutex_unlock(&drv_cmd->mutex);
+		goto out;
+	}
 
 	drv_cmd->state = MPI3MR_CMD_PENDING;
 	drv_cmd->is_waiting = 1;
@@ -4181,6 +4199,7 @@ static int mpi3mr_eh_bus_reset(struct scsi_cmnd *scmd)
 	struct mpi3mr_sdev_priv_data *sdev_priv_data;
 	u8 dev_type = MPI3_DEVICE_DEVFORM_VD;
 	int retval = FAILED;
+	unsigned int timeout = MPI3MR_RESET_TIMEOUT;
 
 	sdev_priv_data = scmd->device->hostdata;
 	if (sdev_priv_data && sdev_priv_data->tgt_priv_data) {
@@ -4191,12 +4210,24 @@ static int mpi3mr_eh_bus_reset(struct scsi_cmnd *scmd)
 	if (dev_type == MPI3_DEVICE_DEVFORM_VD) {
 		mpi3mr_wait_for_host_io(mrioc,
 			MPI3MR_RAID_ERRREC_RESET_TIMEOUT);
-		if (!mpi3mr_get_fw_pending_ios(mrioc))
+		if (!mpi3mr_get_fw_pending_ios(mrioc)) {
+			while (mrioc->reset_in_progress ||
+			       mrioc->prepare_for_reset ||
+			       mrioc->block_on_pci_err) {
+				ssleep(1);
+				if (!timeout--) {
+					retval = FAILED;
+					goto out;
+				}
+			}
 			retval = SUCCESS;
+			goto out;
+		}
 	}
 	if (retval == FAILED)
 		mpi3mr_print_pending_host_io(mrioc);
 
+out:
 	sdev_printk(KERN_INFO, scmd->device,
 		"Bus reset is %s for scmd(%p)\n",
 		((retval == SUCCESS) ? "SUCCESS" : "FAILED"), scmd);
@@ -4879,7 +4910,8 @@ static int mpi3mr_qcmd(struct Scsi_Host *shost,
 		goto out;
 	}
 
-	if (mrioc->reset_in_progress) {
+	if (mrioc->reset_in_progress || mrioc->prepare_for_reset
+	    || mrioc->block_on_pci_err) {
 		retval = SCSI_MLQUEUE_HOST_BUSY;
 		goto out;
 	}
@@ -5362,7 +5394,14 @@ static void mpi3mr_remove(struct pci_dev *pdev)
 	while (mrioc->reset_in_progress || mrioc->is_driver_loading)
 		ssleep(1);
 
-	if (!pci_device_is_present(mrioc->pdev)) {
+	if (mrioc->block_on_pci_err) {
+		mrioc->block_on_pci_err = false;
+		scsi_unblock_requests(shost);
+		mrioc->unrecoverable = 1;
+	}
+
+	if (!pci_device_is_present(mrioc->pdev) ||
+	    mrioc->pci_err_recovery) {
 		mrioc->unrecoverable = 1;
 		mpi3mr_flush_cmds_for_unrecovered_controller(mrioc);
 	}