Existing recovery procedure for PCIe uncorrectable errors (UCE) does not
apply to CXL devices. Recovery can not be used for CXL devices because of
the potential for corruption on what can be system memory. Also, current
PCIe UCE recovery does not begin at the bridge but begins at the bridge's
first downstream device. This will miss handling CXL protocol errors in a
CXL root port. 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 bridge rather than beginning at the
bridge's first downstream child.
Add cxl_report_error_detected() as an analog to report_error_detected().
It will call pci_driver::cxl_err_handlers for each iterated downstream
child. The pci_driver::cxl_err_handlers 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@xxxxxxx>
---
drivers/pci/pci.h | 3 +++
drivers/pci/pcie/aer.c | 5 +++-
drivers/pci/pcie/err.c | 54 ++++++++++++++++++++++++++++++++++++++++++
3 files changed, 61 insertions(+), 1 deletion(-)
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 14d00ce45bfa..5a67e41919d8 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -658,6 +658,9 @@ 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);
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index d772f123c6a2..19432ab2cfb6 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -1048,7 +1048,10 @@ 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 if (info->severity == AER_NONFATAL)
+ cxl_do_recovery(dev);
+ else if (info->severity == AER_FATAL)
+ cxl_do_recovery(dev);
}
static int handles_cxl_error_iter(struct pci_dev *dev, void *data)
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index 31090770fffc..3785f4ca5103 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -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)
+{
+ bool *status = userdata;
+
+ cb(bridge, status);
+ if (bridge->subordinate && !*status)
+ pci_walk_bus(bridge->subordinate, cb, status);
+}
+
+static int cxl_report_error_detected(struct pci_dev *dev, void *data)
+{
+ 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) {
+ const struct cxl_error_handlers *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. Invoking panic");
+
+ if (host->native_aer || pcie_ports_native) {
+ pcie_clear_device_status(dev);
+ pci_aer_clear_nonfatal_status(dev);
+ }
+
+ pci_info(bridge, "No uncorrectable error found. Continuing.\n");
+}
--
2.34.1
