@@ -711,6 +711,9 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
pci_channel_state_t state,
pci_ers_result_t (*reset_subordinates)(struct pci_dev *pdev));
+/* CXL error reporting and handling */
+void cxl_do_recovery(struct pci_dev *dev);
+
bool pcie_wait_for_link(struct pci_dev *pdev, bool active);
int pcie_retrain_link(struct pci_dev *pdev, bool use_lt);
@@ -1025,6 +1025,8 @@ static int cxl_rch_handle_error_iter(struct pci_dev *dev, void *data)
err_handler->error_detected(dev, pci_channel_io_normal);
else if (info->severity == AER_FATAL)
err_handler->error_detected(dev, pci_channel_io_frozen);
+
+ cxl_do_recovery(dev);
}
out:
device_unlock(&dev->dev);
@@ -1049,6 +1051,8 @@ static void cxl_handle_error(struct pci_dev *dev, struct aer_err_info *info)
pdrv->cxl_err_handler->cor_error_detected(dev);
pcie_clear_device_status(dev);
+ } else {
+ cxl_do_recovery(dev);
}
}
@@ -276,3 +276,57 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
return status;
}
+
+static void cxl_walk_bridge(struct pci_dev *bridge,
+ int (*cb)(struct pci_dev *, void *),
+ void *userdata)
+{
+ if (cb(bridge, userdata))
+ return;
+
+ if (bridge->subordinate)
+ pci_walk_bus(bridge->subordinate, cb, userdata);
+}
+
+static int cxl_report_error_detected(struct pci_dev *dev, void *data)
+{
+ const struct cxl_error_handlers *cxl_err_handler;
+ struct pci_driver *pdrv = dev->driver;
+ bool *status = data;
+
+ device_lock(&dev->dev);
+ if (pdrv && pdrv->cxl_err_handler &&
+ pdrv->cxl_err_handler->error_detected) {
+ cxl_err_handler = pdrv->cxl_err_handler;
+ *status = cxl_err_handler->error_detected(dev);
+ }
+ device_unlock(&dev->dev);
+ return *status;
+}
+
+void cxl_do_recovery(struct pci_dev *dev)
+{
+ struct pci_host_bridge *host = pci_find_host_bridge(dev->bus);
+ int type = pci_pcie_type(dev);
+ struct pci_dev *bridge;
+ int status;
+
+ if (type == PCI_EXP_TYPE_ROOT_PORT ||
+ type == PCI_EXP_TYPE_DOWNSTREAM ||
+ type == PCI_EXP_TYPE_UPSTREAM ||
+ type == PCI_EXP_TYPE_ENDPOINT)
+ bridge = dev;
+ else
+ bridge = pci_upstream_bridge(dev);
+
+ cxl_walk_bridge(bridge, cxl_report_error_detected, &status);
+ if (status)
+ panic("CXL cachemem error.");
+
+ if (host->native_aer || pcie_ports_native) {
+ pcie_clear_device_status(dev);
+ pci_aer_clear_nonfatal_status(dev);
+ }
+
+ pci_info(bridge, "CXL uncorrectable error.\n");
+}
Existing recovery procedure for PCIe uncorrectable errors (UCE) does not apply to CXL devices. Recovery can not be used for CXL devices because of potential corruption on what can be system memory. Also, current PCIe UCE recovery, in the case of a Root Port (RP) or Downstream Switch Port (DSP), does not begin at the RP/DSP but begins at the first downstream device. This will miss handling CXL Protocol Errors in a CXL RP or DSP. A separate CXL recovery is needed because of the different handling requirements Add a new function, cxl_do_recovery() using the following. Add cxl_walk_bridge() to iterate the detected error's sub-topology. cxl_walk_bridge() is similar to pci_walk_bridge() but the CXL flavor will begin iteration at the RP or DSP rather than beginning at the first downstream device. Add cxl_report_error_detected() as an analog to report_error_detected(). It will call pci_driver::cxl_err_handlers for each iterated downstream device. The pci_driver::cxl_err_handler's UCE handler returns a boolean indicating if there was a UCE error detected during handling. cxl_do_recovery() uses the status from cxl_report_error_detected() to determine how to proceed. Non-fatal CXL UCE errors will be treated as fatal. If a UCE was present during handling then cxl_do_recovery() will kernel panic. Signed-off-by: Terry Bowman <terry.bowman@amd.com> --- drivers/pci/pci.h | 3 +++ drivers/pci/pcie/aer.c | 4 ++++ drivers/pci/pcie/err.c | 54 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 61 insertions(+)