Merge patch series "mpi3mr: Support PCI Error Recovery"

Sumit Saxena <sumit.saxena@broadcom.com> says:

This patch series contains the changes done in the driver to support
PCI error recovery. It is rework of older patch series from Ranjan
Kumar, see [1].

[1] https://lore.kernel.org/all/20231214205900.270488-1-ranjan.kumar@broadcom.com/

Link: https://lore.kernel.org/r/20240627101735.18286-1-sumit.saxena@broadcom.comSigned-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/scsi/mpi3mr/mpi3mr.h

@@ -23,6 +23,7 @@
 #include <linux/miscdevice.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/aer.h>
 #include <linux/poll.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
@@ -56,8 +57,8 @@ extern struct list_head mrioc_list;
 extern int prot_mask;
 extern atomic64_t event_counter;
 
-#define MPI3MR_DRIVER_VERSION	"8.9.1.0.50"
-#define MPI3MR_DRIVER_RELDATE	"14-May-2024"
+#define MPI3MR_DRIVER_VERSION	"8.9.1.0.51"
+#define MPI3MR_DRIVER_RELDATE	"29-May-2024"
 
 #define MPI3MR_DRIVER_NAME	"mpi3mr"
 #define MPI3MR_DRIVER_LICENSE	"GPL"
@@ -129,6 +130,7 @@ extern atomic64_t event_counter;
 #define MPI3MR_PREPARE_FOR_RESET_TIMEOUT	180
 #define MPI3MR_RESET_ACK_TIMEOUT		30
 #define MPI3MR_MUR_TIMEOUT			120
+#define MPI3MR_RESET_TIMEOUT			510
 
 #define MPI3MR_WATCHDOG_INTERVAL		1000 /* in milli seconds */
 
@@ -517,6 +519,7 @@ struct mpi3mr_throttle_group_info {
 
 /* HBA port flags */
 #define MPI3MR_HBA_PORT_FLAG_DIRTY	0x01
+#define MPI3MR_HBA_PORT_FLAG_NEW       0x02
 
 /* IOCTL data transfer sge*/
 #define MPI3MR_NUM_IOCTL_SGE		256
@@ -1153,6 +1156,8 @@ struct scmd_priv {
  * @trace_release_trigger_active: Trace trigger active flag
  * @fw_release_trigger_active: Fw release trigger active flag
  * @snapdump_trigger_active: Snapdump trigger active flag
+ * @pci_err_recovery: PCI error recovery in progress
+ * @block_on_pci_err: Block IO during PCI error recovery
  */
 struct mpi3mr_ioc {
 	struct list_head list;
@@ -1353,6 +1358,8 @@ struct mpi3mr_ioc {
 	bool snapdump_trigger_active;
 	bool trace_release_trigger_active;
 	bool fw_release_trigger_active;
+	bool pci_err_recovery;
+	bool block_on_pci_err;
 };
 
 /**

drivers/scsi/mpi3mr/mpi3mr_app.c

@@ -846,7 +846,7 @@ static int mpi3mr_bsg_pel_abort(struct mpi3mr_ioc *mrioc)
 		dprint_bsg_err(mrioc, "%s: reset in progress\n", __func__);
 		return -1;
 	}
-	if (mrioc->stop_bsgs) {
+	if (mrioc->stop_bsgs || mrioc->block_on_pci_err) {
 		dprint_bsg_err(mrioc, "%s: bsgs are blocked\n", __func__);
 		return -1;
 	}
@@ -1492,6 +1492,9 @@ static long mpi3mr_bsg_adp_reset(struct mpi3mr_ioc *mrioc,
 		goto out;
 	}
 
+	if (mrioc->unrecoverable || mrioc->block_on_pci_err)
+		return -EINVAL;
+
 	sg_copy_to_buffer(job->request_payload.sg_list,
 			  job->request_payload.sg_cnt,
 			  &adpreset, sizeof(adpreset));
@@ -2575,7 +2578,7 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job)
 		mutex_unlock(&mrioc->bsg_cmds.mutex);
 		goto out;
 	}
-	if (mrioc->stop_bsgs) {
+	if (mrioc->stop_bsgs || mrioc->block_on_pci_err) {
 		dprint_bsg_err(mrioc, "%s: bsgs are blocked\n", __func__);
 		rval = -EAGAIN;
 		mutex_unlock(&mrioc->bsg_cmds.mutex);
@@ -3108,7 +3111,8 @@ adp_state_show(struct device *dev, struct device_attribute *attr,
 	ioc_state = mpi3mr_get_iocstate(mrioc);
 	if (ioc_state == MRIOC_STATE_UNRECOVERABLE)
 		adp_state = MPI3MR_BSG_ADPSTATE_UNRECOVERABLE;
-	else if ((mrioc->reset_in_progress) || (mrioc->stop_bsgs))
+	else if (mrioc->reset_in_progress || mrioc->stop_bsgs ||
+		 mrioc->block_on_pci_err)
 		adp_state = MPI3MR_BSG_ADPSTATE_IN_RESET;
 	else if (ioc_state == MRIOC_STATE_FAULT)
 		adp_state = MPI3MR_BSG_ADPSTATE_FAULT;

drivers/scsi/mpi3mr/mpi3mr_fw.c

@@ -608,7 +608,7 @@ int mpi3mr_blk_mq_poll(struct Scsi_Host *shost, unsigned int queue_num)
 	mrioc = (struct mpi3mr_ioc *)shost->hostdata;
 
 	if ((mrioc->reset_in_progress || mrioc->prepare_for_reset ||
-	    mrioc->unrecoverable))
+	    mrioc->unrecoverable || mrioc->pci_err_recovery))
 		return 0;
 
 	num_entries = mpi3mr_process_op_reply_q(mrioc,
@@ -1693,6 +1693,12 @@ int mpi3mr_admin_request_post(struct mpi3mr_ioc *mrioc, void *admin_req,
 		retval = -EAGAIN;
 		goto out;
 	}
+	if (mrioc->pci_err_recovery) {
+		ioc_err(mrioc, "admin request queue submission failed due to pci error recovery in progress\n");
+		retval = -EAGAIN;
+		goto out;
+	}
+
 	areq_entry = (u8 *)mrioc->admin_req_base +
 	    (areq_pi * MPI3MR_ADMIN_REQ_FRAME_SZ);
 	memset(areq_entry, 0, MPI3MR_ADMIN_REQ_FRAME_SZ);
@@ -2363,6 +2369,11 @@ int mpi3mr_op_request_post(struct mpi3mr_ioc *mrioc,
 		retval = -EAGAIN;
 		goto out;
 	}
+	if (mrioc->pci_err_recovery) {
+		ioc_err(mrioc, "operational request queue submission failed due to pci error recovery in progress\n");
+		retval = -EAGAIN;
+		goto out;
+	}
 
 	segment_base_addr = segments[pi / op_req_q->segment_qd].segment;
 	req_entry = (u8 *)segment_base_addr +
@@ -2627,7 +2638,7 @@ static void mpi3mr_watchdog_work(struct work_struct *work)
 	union mpi3mr_trigger_data trigger_data;
 	u16 reset_reason = MPI3MR_RESET_FROM_FAULT_WATCH;
 
-	if (mrioc->reset_in_progress)
+	if (mrioc->reset_in_progress || mrioc->pci_err_recovery)
 		return;
 
 	if (!mrioc->unrecoverable && !pci_device_is_present(mrioc->pdev)) {
@@ -4268,7 +4279,7 @@ int mpi3mr_reinit_ioc(struct mpi3mr_ioc *mrioc, u8 is_resume)
 		goto out_failed_noretry;
 	}
 
-	if (is_resume) {
+	if (is_resume || mrioc->block_on_pci_err) {
 		dprint_reset(mrioc, "setting up single ISR\n");
 		retval = mpi3mr_setup_isr(mrioc, 1);
 		if (retval) {
@@ -4319,7 +4330,7 @@ int mpi3mr_reinit_ioc(struct mpi3mr_ioc *mrioc, u8 is_resume)
 		goto out_failed;
 	}
 
-	if (is_resume) {
+	if (is_resume || mrioc->block_on_pci_err) {
 		dprint_reset(mrioc, "setting up multiple ISR\n");
 		retval = mpi3mr_setup_isr(mrioc, 0);
 		if (retval) {
@@ -4807,7 +4818,8 @@ void mpi3mr_cleanup_ioc(struct mpi3mr_ioc *mrioc)
 
 	ioc_state = mpi3mr_get_iocstate(mrioc);
 
-	if ((!mrioc->unrecoverable) && (!mrioc->reset_in_progress) &&
+	if (!mrioc->unrecoverable && !mrioc->reset_in_progress &&
+	    !mrioc->pci_err_recovery &&
 	    (ioc_state == MRIOC_STATE_READY)) {
 		if (mpi3mr_issue_and_process_mur(mrioc,
 		    MPI3MR_RESET_FROM_CTLR_CLEANUP))

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);
 	}
@@ -5546,6 +5585,197 @@ mpi3mr_resume(struct device *dev)
 	return 0;
 }
 
+/**
+ * mpi3mr_pcierr_error_detected - PCI error detected callback
+ * @pdev: PCI device instance
+ * @state: channel state
+ *
+ * This function is called by the PCI error recovery driver and
+ * based on the state passed the driver decides what actions to
+ * be recommended back to PCI driver.
+ *
+ * For all of the states if there is no valid mrioc or scsi host
+ * references in the PCI device then this function will return
+ * the result as disconnect.
+ *
+ * For normal state, this function will return the result as can
+ * recover.
+ *
+ * For frozen state, this function will block for any pending
+ * controller initialization or re-initialization to complete,
+ * stop any new interactions with the controller and return
+ * status as reset required.
+ *
+ * For permanent failure state, this function will mark the
+ * controller as unrecoverable and return status as disconnect.
+ *
+ * Returns: PCI_ERS_RESULT_NEED_RESET or CAN_RECOVER or
+ * DISCONNECT based on the controller state.
+ */
+static pci_ers_result_t
+mpi3mr_pcierr_error_detected(struct pci_dev *pdev, pci_channel_state_t state)
+{
+	struct Scsi_Host *shost;
+	struct mpi3mr_ioc *mrioc;
+	unsigned int timeout = MPI3MR_RESET_TIMEOUT;
+
+	dev_info(&pdev->dev, "%s: callback invoked state(%d)\n", __func__,
+	    state);
+
+	shost = pci_get_drvdata(pdev);
+	mrioc = shost_priv(shost);
+
+	switch (state) {
+	case pci_channel_io_normal:
+		return PCI_ERS_RESULT_CAN_RECOVER;
+	case pci_channel_io_frozen:
+		mrioc->pci_err_recovery = true;
+		mrioc->block_on_pci_err = true;
+		do {
+			if (mrioc->reset_in_progress || mrioc->is_driver_loading)
+				ssleep(1);
+			else
+				break;
+		} while (--timeout);
+
+		if (!timeout) {
+			mrioc->pci_err_recovery = true;
+			mrioc->block_on_pci_err = true;
+			mrioc->unrecoverable = 1;
+			mpi3mr_stop_watchdog(mrioc);
+			mpi3mr_flush_cmds_for_unrecovered_controller(mrioc);
+			return PCI_ERS_RESULT_DISCONNECT;
+		}
+
+		scsi_block_requests(mrioc->shost);
+		mpi3mr_stop_watchdog(mrioc);
+		mpi3mr_cleanup_resources(mrioc);
+		return PCI_ERS_RESULT_NEED_RESET;
+	case pci_channel_io_perm_failure:
+		mrioc->pci_err_recovery = true;
+		mrioc->block_on_pci_err = true;
+		mrioc->unrecoverable = 1;
+		mpi3mr_stop_watchdog(mrioc);
+		mpi3mr_flush_cmds_for_unrecovered_controller(mrioc);
+		return PCI_ERS_RESULT_DISCONNECT;
+	default:
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+}
+
+/**
+ * mpi3mr_pcierr_slot_reset - Post slot reset callback
+ * @pdev: PCI device instance
+ *
+ * This function is called by the PCI error recovery driver
+ * after a slot or link reset issued by it for the recovery, the
+ * driver is expected to bring back the controller and
+ * initialize it.
+ *
+ * This function restores PCI state and reinitializes controller
+ * resources and the controller, this blocks for any pending
+ * reset to complete.
+ *
+ * Returns: PCI_ERS_RESULT_DISCONNECT on failure or
+ * PCI_ERS_RESULT_RECOVERED
+ */
+static pci_ers_result_t mpi3mr_pcierr_slot_reset(struct pci_dev *pdev)
+{
+	struct Scsi_Host *shost;
+	struct mpi3mr_ioc *mrioc;
+	unsigned int timeout = MPI3MR_RESET_TIMEOUT;
+
+	dev_info(&pdev->dev, "%s: callback invoked\n", __func__);
+
+	shost = pci_get_drvdata(pdev);
+	mrioc = shost_priv(shost);
+
+	do {
+		if (mrioc->reset_in_progress)
+			ssleep(1);
+		else
+			break;
+	} while (--timeout);
+
+	if (!timeout)
+		goto out_failed;
+
+	pci_restore_state(pdev);
+
+	if (mpi3mr_setup_resources(mrioc)) {
+		ioc_err(mrioc, "setup resources failed\n");
+		goto out_failed;
+	}
+	mrioc->unrecoverable = 0;
+	mrioc->pci_err_recovery = false;
+
+	if (mpi3mr_soft_reset_handler(mrioc, MPI3MR_RESET_FROM_FIRMWARE, 0))
+		goto out_failed;
+
+	return PCI_ERS_RESULT_RECOVERED;
+
+out_failed:
+	mrioc->unrecoverable = 1;
+	mrioc->block_on_pci_err = false;
+	scsi_unblock_requests(shost);
+	mpi3mr_start_watchdog(mrioc);
+	return PCI_ERS_RESULT_DISCONNECT;
+}
+
+/**
+ * mpi3mr_pcierr_resume - PCI error recovery resume
+ * callback
+ * @pdev: PCI device instance
+ *
+ * This function enables all I/O and IOCTLs post reset issued as
+ * part of the PCI error recovery
+ *
+ * Return: Nothing.
+ */
+static void mpi3mr_pcierr_resume(struct pci_dev *pdev)
+{
+	struct Scsi_Host *shost;
+	struct mpi3mr_ioc *mrioc;
+
+	dev_info(&pdev->dev, "%s: callback invoked\n", __func__);
+
+	shost = pci_get_drvdata(pdev);
+	mrioc = shost_priv(shost);
+
+	if (mrioc->block_on_pci_err) {
+		mrioc->block_on_pci_err = false;
+		scsi_unblock_requests(shost);
+		mpi3mr_start_watchdog(mrioc);
+	}
+}
+
+/**
+ * mpi3mr_pcierr_mmio_enabled - PCI error recovery callback
+ * @pdev: PCI device instance
+ *
+ * This is called only if mpi3mr_pcierr_error_detected returns
+ * PCI_ERS_RESULT_CAN_RECOVER.
+ *
+ * Return: PCI_ERS_RESULT_DISCONNECT when the controller is
+ * unrecoverable or when the shost/mrioc reference cannot be
+ * found, else return PCI_ERS_RESULT_RECOVERED
+ */
+static pci_ers_result_t mpi3mr_pcierr_mmio_enabled(struct pci_dev *pdev)
+{
+	struct Scsi_Host *shost;
+	struct mpi3mr_ioc *mrioc;
+
+	dev_info(&pdev->dev, "%s: callback invoked\n", __func__);
+
+	shost = pci_get_drvdata(pdev);
+	mrioc = shost_priv(shost);
+
+	if (mrioc->unrecoverable)
+		return PCI_ERS_RESULT_DISCONNECT;
+
+	return PCI_ERS_RESULT_RECOVERED;
+}
+
 static const struct pci_device_id mpi3mr_pci_id_table[] = {
 	{
 		PCI_DEVICE_SUB(MPI3_MFGPAGE_VENDORID_BROADCOM,
@@ -5563,6 +5793,13 @@ static const struct pci_device_id mpi3mr_pci_id_table[] = {
 };
 MODULE_DEVICE_TABLE(pci, mpi3mr_pci_id_table);
 
+static struct pci_error_handlers mpi3mr_err_handler = {
+	.error_detected = mpi3mr_pcierr_error_detected,
+	.mmio_enabled = mpi3mr_pcierr_mmio_enabled,
+	.slot_reset = mpi3mr_pcierr_slot_reset,
+	.resume = mpi3mr_pcierr_resume,
+};
+
 static SIMPLE_DEV_PM_OPS(mpi3mr_pm_ops, mpi3mr_suspend, mpi3mr_resume);
 
 static struct pci_driver mpi3mr_pci_driver = {
@@ -5571,6 +5808,7 @@ static struct pci_driver mpi3mr_pci_driver = {
 	.probe = mpi3mr_probe,
 	.remove = mpi3mr_remove,
 	.shutdown = mpi3mr_shutdown,
+	.err_handler = &mpi3mr_err_handler,
 	.driver.pm = &mpi3mr_pm_ops,
 };
 

drivers/scsi/mpi3mr/mpi3mr_transport.c

@@ -151,6 +151,11 @@ static int mpi3mr_report_manufacture(struct mpi3mr_ioc *mrioc,
 		return -EFAULT;
 	}
 
+	if (mrioc->pci_err_recovery) {
+		ioc_err(mrioc, "%s: pci error recovery in progress!\n", __func__);
+		return -EFAULT;
+	}
+
 	data_out_sz = sizeof(struct rep_manu_request);
 	data_in_sz = sizeof(struct rep_manu_reply);
 	data_out = dma_alloc_coherent(&mrioc->pdev->dev,
@@ -790,6 +795,12 @@ static int mpi3mr_set_identify(struct mpi3mr_ioc *mrioc, u16 handle,
 		return -EFAULT;
 	}
 
+	if (mrioc->pci_err_recovery) {
+		ioc_err(mrioc, "%s: pci error recovery in progress!\n",
+		    __func__);
+		return -EFAULT;
+	}
+
 	if ((mpi3mr_cfg_get_dev_pg0(mrioc, &ioc_status, &device_pg0,
 	    sizeof(device_pg0), MPI3_DEVICE_PGAD_FORM_HANDLE, handle))) {
 		ioc_err(mrioc, "%s: device page0 read failed\n", __func__);
@@ -1007,6 +1018,9 @@ mpi3mr_alloc_hba_port(struct mpi3mr_ioc *mrioc, u16 port_id)
 	hba_port->port_id = port_id;
 	ioc_info(mrioc, "hba_port entry: %p, port: %d is added to hba_port list\n",
 	    hba_port, hba_port->port_id);
+	if (mrioc->reset_in_progress ||
+		mrioc->pci_err_recovery)
+		hba_port->flags = MPI3MR_HBA_PORT_FLAG_NEW;
 	list_add_tail(&hba_port->list, &mrioc->hba_port_table_list);
 	return hba_port;
 }
@@ -1055,7 +1069,7 @@ void mpi3mr_update_links(struct mpi3mr_ioc *mrioc,
 	struct mpi3mr_sas_node *mr_sas_node;
 	struct mpi3mr_sas_phy *mr_sas_phy;
 
-	if (mrioc->reset_in_progress)
+	if (mrioc->reset_in_progress || mrioc->pci_err_recovery)
 		return;
 
 	spin_lock_irqsave(&mrioc->sas_node_lock, flags);
@@ -1978,7 +1992,7 @@ int mpi3mr_expander_add(struct mpi3mr_ioc *mrioc, u16 handle)
 	if (!handle)
 		return -1;
 
-	if (mrioc->reset_in_progress)
+	if (mrioc->reset_in_progress || mrioc->pci_err_recovery)
 		return -1;
 
 	if ((mpi3mr_cfg_get_sas_exp_pg0(mrioc, &ioc_status, &expander_pg0,
@@ -2184,7 +2198,7 @@ void mpi3mr_expander_node_remove(struct mpi3mr_ioc *mrioc,
 	/* remove sibling ports attached to this expander */
 	list_for_each_entry_safe(mr_sas_port, next,
 	   &sas_expander->sas_port_list, port_list) {
-		if (mrioc->reset_in_progress)
+		if (mrioc->reset_in_progress || mrioc->pci_err_recovery)
 			return;
 		if (mr_sas_port->remote_identify.device_type ==
 		    SAS_END_DEVICE)
@@ -2234,7 +2248,7 @@ void mpi3mr_expander_remove(struct mpi3mr_ioc *mrioc, u64 sas_address,
 	struct mpi3mr_sas_node *sas_expander;
 	unsigned long flags;
 
-	if (mrioc->reset_in_progress)
+	if (mrioc->reset_in_progress || mrioc->pci_err_recovery)
 		return;
 
 	if (!hba_port)
@@ -2545,6 +2559,11 @@ static int mpi3mr_get_expander_phy_error_log(struct mpi3mr_ioc *mrioc,
 		return -EFAULT;
 	}
 
+	if (mrioc->pci_err_recovery) {
+		ioc_err(mrioc, "%s: pci error recovery in progress!\n", __func__);
+		return -EFAULT;
+	}
+
 	data_out_sz = sizeof(struct phy_error_log_request);
 	data_in_sz = sizeof(struct phy_error_log_reply);
 	sz = data_out_sz + data_in_sz;
@@ -2804,6 +2823,12 @@ mpi3mr_expander_phy_control(struct mpi3mr_ioc *mrioc,
 		return -EFAULT;
 	}
 
+	if (mrioc->pci_err_recovery) {
+		ioc_err(mrioc, "%s: pci error recovery in progress!\n",
+		    __func__);
+		return -EFAULT;
+	}
+
 	data_out_sz = sizeof(struct phy_control_request);
 	data_in_sz = sizeof(struct phy_control_reply);
 	sz = data_out_sz + data_in_sz;
@@ -3227,6 +3252,12 @@ mpi3mr_transport_smp_handler(struct bsg_job *job, struct Scsi_Host *shost,
 		goto out;
 	}
 
+	if (mrioc->pci_err_recovery) {
+		ioc_err(mrioc, "%s: pci error recovery in progress!\n", __func__);
+		rc = -EFAULT;
+		goto out;
+	}
+
 	rc = mpi3mr_map_smp_buffer(&mrioc->pdev->dev, &job->request_payload,
 	    &dma_addr_out, &dma_len_out, &addr_out);
 	if (rc)