drm/xe/xe_ras: Initialize Uncorrectable AER Registers

Uncorrectable errors from different endpoints in the device are steered to
the USP(Upstream Switch Port) which is a PCI Advanced Error Reporting (AER)
Compliant device. Downgrade all the errors to non-fatal to prevent PCIe
bus driver from triggering a Secondary Bus Reset (SBR). This allows error
detection, containment and recovery in the driver.

The Uncorrectable Error Severity Register has the 'Uncorrectable
Internal Error Severity' set to fatal by default. Set this to
non-fatal and unmask the error.

Reviewed-by: Mallesh Koujalagi <mallesh.koujalagi@intel.com>
Link: https://patch.msgid.link/20260629082802.3690896-10-riana.tauro@intel.com
Signed-off-by: Riana Tauro <riana.tauro@intel.com>

diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
index 44f4e1a3455b7c77c96411268db2c9100dc21ff7..74d5016d9ffe7967b25e8d4b03aa6c5dee47c440 100644 (file)
--- a/drivers/gpu/drm/xe/xe_ras.c
+++ b/drivers/gpu/drm/xe/xe_ras.c
@@ -131,6 +131,68 @@ static inline const char *comp_to_str(u8 component)
        return xe_ras_components[component];
 }
 
+static struct pci_dev *find_usp_dev(struct pci_dev *pdev)
+{
+       struct pci_dev *vsp;
+
+       /*
+        * Device Hierarchy:
+        *
+        * Upstream Switch Port (USP) --> Virtual Switch Port (VSP) --> SGunit (GPU endpoint)
+        */
+       vsp = pci_upstream_bridge(pdev);
+       if (!vsp)
+               return NULL;
+
+       return pci_upstream_bridge(vsp);
+}
+
+static void ras_usp_aer_init(struct xe_device *xe)
+{
+       struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
+       struct pci_dev *usp;
+       u16 aer_cap;
+       u32 status;
+
+       usp = find_usp_dev(pdev);
+       if (!usp)
+               return;
+
+       aer_cap = pci_find_ext_capability(usp, PCI_EXT_CAP_ID_ERR);
+       if (!aer_cap) {
+               dev_warn(&usp->dev, "AER capability unavailable\n");
+               return;
+       }
+
+       /*
+        * Clear any stale Uncorrectable Internal Error Status event in Uncorrectable Error
+        * Status Register.
+        */
+       pci_read_config_dword(usp, aer_cap + PCI_ERR_UNCOR_STATUS, &status);
+       if (status & PCI_ERR_UNC_INTN)
+               pci_write_config_dword(usp, aer_cap + PCI_ERR_UNCOR_STATUS, PCI_ERR_UNC_INTN);
+
+       /*
+        * All errors are steered to USP which is a PCIe AER Compliant device.
+        * Downgrade all the errors to non-fatal to prevent PCIe bus driver
+        * from triggering a Secondary Bus Reset (SBR). This allows error
+        * detection, containment and recovery in the driver.
+        *
+        * The Uncorrectable Error Severity Register has the 'Uncorrectable
+        * Internal Error Severity' set to fatal by default. Set this to
+        * non-fatal and unmask the error.
+        */
+
+       /* Downgrade Uncorrectable Internal Error to non-fatal */
+       pci_clear_and_set_config_dword(usp, aer_cap + PCI_ERR_UNCOR_SEVER, PCI_ERR_UNC_INTN, 0);
+
+       /* Unmask Uncorrectable Internal Error */
+       pci_clear_and_set_config_dword(usp, aer_cap + PCI_ERR_UNCOR_MASK, PCI_ERR_UNC_INTN, 0);
+
+       pci_save_state(usp);
+       dev_dbg(&usp->dev, "Uncorrectable Internal Errors downgraded and unmasked\n");
+}
+
 void xe_ras_counter_threshold_crossed(struct xe_device *xe,
                                      struct xe_sysctrl_event_response *response)
 {
@@ -274,7 +336,7 @@ int xe_ras_clear_counter(struct xe_device *xe, u8 severity, u8 component)
  * xe_ras_init - Initialize Xe RAS
  * @xe: xe device instance
  *
- * Register drm_ras nodes
+ * Initialize Xe RAS
  */
 void xe_ras_init(struct xe_device *xe)
 {
@@ -282,4 +344,10 @@ void xe_ras_init(struct xe_device *xe)
                return;
 
        xe_drm_ras_init(xe);
+
+       if (!xe->info.has_sysctrl)
+               return;
+
+       if (IS_ENABLED(CONFIG_PCIEAER))
+               ras_usp_aer_init(xe);
 }