}
}
EXPORT_SYMBOL_NS_GPL(read_cdat_data, CXL);
- addr = cxlds->regs.ras + CXL_RAS_CAP_CONTROL_OFFSET;
- fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK, readl(addr)));
+
+ void cxl_cor_error_detected(struct pci_dev *pdev)
+ {
+ struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
+ struct cxl_memdev *cxlmd = cxlds->cxlmd;
+ struct device *dev = &cxlmd->dev;
+ void __iomem *addr;
+ u32 status;
+
+ if (!cxlds->regs.ras)
+ return;
+
+ addr = cxlds->regs.ras + CXL_RAS_CORRECTABLE_STATUS_OFFSET;
+ status = readl(addr);
+ if (status & CXL_RAS_CORRECTABLE_STATUS_MASK) {
+ writel(status & CXL_RAS_CORRECTABLE_STATUS_MASK, addr);
+ trace_cxl_aer_correctable_error(dev, status);
+ }
+ }
+ EXPORT_SYMBOL_NS_GPL(cxl_cor_error_detected, CXL);
+
+ /* CXL spec rev3.0 8.2.4.16.1 */
+ static void header_log_copy(struct cxl_dev_state *cxlds, u32 *log)
+ {
+ void __iomem *addr;
+ u32 *log_addr;
+ int i, log_u32_size = CXL_HEADERLOG_SIZE / sizeof(u32);
+
+ addr = cxlds->regs.ras + CXL_RAS_HEADER_LOG_OFFSET;
+ log_addr = log;
+
+ for (i = 0; i < log_u32_size; i++) {
+ *log_addr = readl(addr);
+ log_addr++;
+ addr += sizeof(u32);
+ }
+ }
+
+ /*
+ * Log the state of the RAS status registers and prepare them to log the
+ * next error status. Return 1 if reset needed.
+ */
+ static bool cxl_report_and_clear(struct cxl_dev_state *cxlds)
+ {
+ struct cxl_memdev *cxlmd = cxlds->cxlmd;
+ struct device *dev = &cxlmd->dev;
+ u32 hl[CXL_HEADERLOG_SIZE_U32];
+ void __iomem *addr;
+ u32 status;
+ u32 fe;
+
+ if (!cxlds->regs.ras)
+ return false;
+
+ addr = cxlds->regs.ras + CXL_RAS_UNCORRECTABLE_STATUS_OFFSET;
+ status = readl(addr);
+ if (!(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK))
+ return false;
+
+ /* If multiple errors, log header points to first error from ctrl reg */
+ if (hweight32(status) > 1) {
++ void __iomem *rcc_addr =
++ cxlds->regs.ras + CXL_RAS_CAP_CONTROL_OFFSET;
++
++ fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK,
++ readl(rcc_addr)));
+ } else {
+ fe = status;
+ }
+
+ header_log_copy(cxlds, hl);
+ trace_cxl_aer_uncorrectable_error(dev, status, fe, hl);
+ writel(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK, addr);
+
+ return true;
+ }
+
+ pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
+ pci_channel_state_t state)
+ {
+ struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
+ struct cxl_memdev *cxlmd = cxlds->cxlmd;
+ struct device *dev = &cxlmd->dev;
+ bool ue;
+
+ /*
+ * A frozen channel indicates an impending reset which is fatal to
+ * CXL.mem operation, and will likely crash the system. On the off
+ * chance the situation is recoverable dump the status of the RAS
+ * capability registers and bounce the active state of the memdev.
+ */
+ ue = cxl_report_and_clear(cxlds);
+
+ switch (state) {
+ case pci_channel_io_normal:
+ if (ue) {
+ device_release_driver(dev);
+ return PCI_ERS_RESULT_NEED_RESET;
+ }
+ return PCI_ERS_RESULT_CAN_RECOVER;
+ case pci_channel_io_frozen:
+ dev_warn(&pdev->dev,
+ "%s: frozen state error detected, disable CXL.mem\n",
+ dev_name(dev));
+ device_release_driver(dev);
+ return PCI_ERS_RESULT_NEED_RESET;
+ case pci_channel_io_perm_failure:
+ dev_warn(&pdev->dev,
+ "failure state error detected, request disconnect\n");
+ return PCI_ERS_RESULT_DISCONNECT;
+ }
+ return PCI_ERS_RESULT_NEED_RESET;
+ }
+ EXPORT_SYMBOL_NS_GPL(cxl_error_detected, CXL);