[PATCH v3 6/6] PCI/AER: Unmask RCEC internal errors to enable RCH downstream port error handling

[Terry Bowman]

From: Robert Richter <rrich...@amd.com>

RCEC AER corrected and uncorrectable internal errors (CIE/UIE) are
disabled by default. [1][2] Enable them to receive CXL downstream port
errors of a Restricted CXL Host (RCH).

[1] CXL 3.0 Spec, 12.2.1.1 - RCH Downstream Port Detected Errors
[2] PCIe Base Spec 6.0, 7.8.4.3 Uncorrectable Error Mask Register,
    7.8.4.6 Correctable Error Mask Register

Co-developed-by: Terry Bowman <terry.bow...@amd.com>
Signed-off-by: Robert Richter <rrich...@amd.com>
Signed-off-by: Terry Bowman <terry.bow...@amd.com>
Cc: "Oliver O'Halloran" <ooh...@gmail.com>
Cc: Bjorn Helgaas <bhelg...@google.com>
Cc: Mahesh J Salgaonkar <mah...@linux.ibm.com>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-...@vger.kernel.org
---
 drivers/pci/pcie/aer.c | 73 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 73 insertions(+)

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 171a08fd8ebd..3973c731e11d 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -1000,7 +1000,79 @@ static void cxl_handle_error(struct pci_dev *dev, struct 
aer_err_info *info)
                pcie_walk_rcec(dev, cxl_handle_error_iter, info);
 }
 
+static bool cxl_error_is_native(struct pci_dev *dev)
+{
+       struct pci_host_bridge *host = pci_find_host_bridge(dev->bus);
+
+       if (pcie_ports_native)
+               return true;
+
+       return host->native_aer && host->native_cxl_error;
+}
+
+static int handles_cxl_error_iter(struct pci_dev *dev, void *data)
+{
+       int *handles_cxl = data;
+
+       *handles_cxl = is_cxl_mem_dev(dev) && cxl_error_is_native(dev);
+
+       return *handles_cxl;
+}
+
+static bool handles_cxl_errors(struct pci_dev *rcec)
+{
+       int handles_cxl = 0;
+
+       if (!rcec->aer_cap)
+               return false;
+
+       if (pci_pcie_type(rcec) == PCI_EXP_TYPE_RC_EC)
+               pcie_walk_rcec(rcec, handles_cxl_error_iter, &handles_cxl);
+
+       return !!handles_cxl;
+}
+
+static int __cxl_unmask_internal_errors(struct pci_dev *rcec)
+{
+       int aer, rc;
+       u32 mask;
+
+       /*
+        * Internal errors are masked by default, unmask RCEC's here
+        * PCI6.0 7.8.4.3 Uncorrectable Error Mask Register (Offset 08h)
+        * PCI6.0 7.8.4.6 Correctable Error Mask Register (Offset 14h)
+        */
+       aer = rcec->aer_cap;
+       rc = pci_read_config_dword(rcec, aer + PCI_ERR_UNCOR_MASK, &mask);
+       if (rc)
+               return rc;
+       mask &= ~PCI_ERR_UNC_INTN;
+       rc = pci_write_config_dword(rcec, aer + PCI_ERR_UNCOR_MASK, mask);
+       if (rc)
+               return rc;
+
+       rc = pci_read_config_dword(rcec, aer + PCI_ERR_COR_MASK, &mask);
+       if (rc)
+               return rc;
+       mask &= ~PCI_ERR_COR_INTERNAL;
+       rc = pci_write_config_dword(rcec, aer + PCI_ERR_COR_MASK, mask);
+
+       return rc;
+}
+
+static void cxl_unmask_internal_errors(struct pci_dev *rcec)
+{
+       if (!handles_cxl_errors(rcec))
+               return;
+
+       if (__cxl_unmask_internal_errors(rcec))
+               dev_err(&rcec->dev, "cxl: Failed to unmask internal errors");
+       else
+               dev_dbg(&rcec->dev, "cxl: Internal errors unmasked");
+}
+
 #else
+static inline void cxl_unmask_internal_errors(struct pci_dev *dev) { }
 static inline void cxl_handle_error(struct pci_dev *dev,
                                    struct aer_err_info *info) { }
 #endif
@@ -1397,6 +1469,7 @@ static int aer_probe(struct pcie_device *dev)
                return status;
        }
 
+       cxl_unmask_internal_errors(port);
        aer_enable_rootport(rpc);
        pci_info(port, "enabled with IRQ %d\n", dev->irq);
        return 0;
-- 
2.34.1