pds_core: add attempts to fix broken PCI

If we see a 0xff value from a PCI register read, we know that
the PCI connection is broken, possibly by a low level reset that
didn't go through the nice pci_error_handlers path.

Make use of the PCI cleanup code that we already have from the
reset handlers and add some detection and attempted recovery
from a broken PCI connection.

Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Brett Creeley <brett.creeley@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Author: emusln

drivers/net/ethernet/amd/pds_core/core.c

@@ -578,6 +578,18 @@ void pdsc_fw_up(struct pdsc *pdsc)
 	pdsc_teardown(pdsc, PDSC_TEARDOWN_RECOVERY);
 }
 
+static void pdsc_check_pci_health(struct pdsc *pdsc)
+{
+	u8 fw_status = ioread8(&pdsc->info_regs->fw_status);
+
+	/* is PCI broken? */
+	if (fw_status != PDS_RC_BAD_PCI)
+		return;
+
+	pdsc_reset_prepare(pdsc->pdev);
+	pdsc_reset_done(pdsc->pdev);
+}
+
 void pdsc_health_thread(struct work_struct *work)
 {
 	struct pdsc *pdsc = container_of(work, struct pdsc, health_work);
@@ -604,6 +616,8 @@ void pdsc_health_thread(struct work_struct *work)
 			pdsc_fw_down(pdsc);
 	}
 
+	pdsc_check_pci_health(pdsc);
+
 	pdsc->fw_generation = pdsc->fw_status & PDS_CORE_FW_STS_F_GENERATION;
 
 out_unlock:

drivers/net/ethernet/amd/pds_core/core.h

@@ -283,6 +283,9 @@ int pdsc_devcmd_reset(struct pdsc *pdsc);
 int pdsc_dev_reinit(struct pdsc *pdsc);
 int pdsc_dev_init(struct pdsc *pdsc);
 
+void pdsc_reset_prepare(struct pci_dev *pdev);
+void pdsc_reset_done(struct pci_dev *pdev);
+
 int pdsc_intr_alloc(struct pdsc *pdsc, char *name,
 		    irq_handler_t handler, void *data);
 void pdsc_intr_free(struct pdsc *pdsc, int index);

drivers/net/ethernet/amd/pds_core/main.c

@@ -445,7 +445,7 @@ static void pdsc_remove(struct pci_dev *pdev)
 	devlink_free(dl);
 }
 
-static void pdsc_reset_prepare(struct pci_dev *pdev)
+void pdsc_reset_prepare(struct pci_dev *pdev)
 {
 	struct pdsc *pdsc = pci_get_drvdata(pdev);
 
@@ -457,7 +457,7 @@ static void pdsc_reset_prepare(struct pci_dev *pdev)
 	pci_disable_device(pdev);
 }
 
-static void pdsc_reset_done(struct pci_dev *pdev)
+void pdsc_reset_done(struct pci_dev *pdev)
 {
 	struct pdsc *pdsc = pci_get_drvdata(pdev);
 	struct device *dev = pdsc->dev;