scsi: mpi3mr: Support PCI Error Recovery callback handlers

PCI Error recovery support is required to recover the controller upon
detection of PCI errors. Add support for the PCI error recovery callback
handlers in mpi3mr driver.
Co-developed-by: Sathya Prakash <sathya.prakash@broadcom.com>
Signed-off-by: Sathya Prakash <sathya.prakash@broadcom.com>
Co-developed-by: Ranjan Kumar <ranjan.kumar@broadcom.com>
Signed-off-by: Ranjan Kumar <ranjan.kumar@broadcom.com>
Signed-off-by: Sumit Saxena <sumit.saxena@broadcom.com>
Link: https://lore.kernel.org/r/20240627101735.18286-2-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>
@@ -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 */
 
@@ -1153,6 +1155,8 @@ 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 +1357,8 @@ 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_os.c

@@ -5546,6 +5546,197 @@ 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 +5754,13 @@ 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 +5769,7 @@ 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,
 };