Merge branch 'for-6.15/fw-first-error-logging' into cxl-for-next2

Add logging support for CXL CPER endpoint and port protocol errors.
Including the 2 patches that was completed later.

Link: https://lore.kernel.org/linux-cxl/20250123084421.127697-1-Smita.KoralahalliChannabasappa@amd.com/
Link: https://lore.kernel.org/linux-cxl/20250310223839.31342-1-Smita.KoralahalliChannabasappa@amd.com/

5 files changed, 177 insertions, 0 deletions

diff --git a/drivers/cxl/core/Makefile b/drivers/cxl/core/Makefile
index 9259bcc6773c..ba5f0916d379 100644
--- a/drivers/cxl/core/Makefile
+++ b/drivers/cxl/core/Makefile
@@ -14,5 +14,6 @@ cxl_core-y += pci.o
 cxl_core-y += hdm.o
 cxl_core-y += pmu.o
 cxl_core-y += cdat.o
+cxl_core-y += ras.o
 cxl_core-$(CONFIG_TRACING) += trace.o
 cxl_core-$(CONFIG_CXL_REGION) += region.o
diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 22dac79c5192..83c690ca6fad 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -115,4 +115,7 @@ bool cxl_need_node_perf_attrs_update(int nid);
 int cxl_port_get_switch_dport_bandwidth(struct cxl_port *port,
 					struct access_coordinate *c);
 
+int cxl_ras_init(void);
+void cxl_ras_exit(void);
+
 #endif /* __CXL_CORE_H__ */
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index fc24c5bc9f2a..194892bb1396 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -2350,8 +2350,14 @@ static __init int cxl_core_init(void)
 	if (rc)
 		goto err_region;
 
+	rc = cxl_ras_init();
+	if (rc)
+		goto err_ras;
+
 	return 0;
 
+err_ras:
+	cxl_region_exit();
 err_region:
 	bus_unregister(&cxl_bus_type);
 err_bus:
@@ -2363,6 +2369,7 @@ err_wq:
 
 static void cxl_core_exit(void)
 {
+	cxl_ras_exit();
 	cxl_region_exit();
 	bus_unregister(&cxl_bus_type);
 	destroy_workqueue(cxl_bus_wq);
diff --git a/drivers/cxl/core/ras.c b/drivers/cxl/core/ras.c
new file mode 100644
index 000000000000..485a831695c7
--- /dev/null
+++ b/drivers/cxl/core/ras.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2025 AMD Corporation. All rights reserved. */
+
+#include <linux/pci.h>
+#include <linux/aer.h>
+#include <cxl/event.h>
+#include <cxlmem.h>
+#include "trace.h"
+
+static void cxl_cper_trace_corr_port_prot_err(struct pci_dev *pdev,
+					      struct cxl_ras_capability_regs ras_cap)
+{
+	u32 status = ras_cap.cor_status & ~ras_cap.cor_mask;
+
+	trace_cxl_port_aer_correctable_error(&pdev->dev, status);
+}
+
+static void cxl_cper_trace_uncorr_port_prot_err(struct pci_dev *pdev,
+						struct cxl_ras_capability_regs ras_cap)
+{
+	u32 status = ras_cap.uncor_status & ~ras_cap.uncor_mask;
+	u32 fe;
+
+	if (hweight32(status) > 1)
+		fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK,
+				   ras_cap.cap_control));
+	else
+		fe = status;
+
+	trace_cxl_port_aer_uncorrectable_error(&pdev->dev, status, fe,
+					       ras_cap.header_log);
+}
+
+static void cxl_cper_trace_corr_prot_err(struct pci_dev *pdev,
+				  struct cxl_ras_capability_regs ras_cap)
+{
+	u32 status = ras_cap.cor_status & ~ras_cap.cor_mask;
+	struct cxl_dev_state *cxlds;
+
+	cxlds = pci_get_drvdata(pdev);
+	if (!cxlds)
+		return;
+
+	trace_cxl_aer_correctable_error(cxlds->cxlmd, status);
+}
+
+static void cxl_cper_trace_uncorr_prot_err(struct pci_dev *pdev,
+				    struct cxl_ras_capability_regs ras_cap)
+{
+	u32 status = ras_cap.uncor_status & ~ras_cap.uncor_mask;
+	struct cxl_dev_state *cxlds;
+	u32 fe;
+
+	cxlds = pci_get_drvdata(pdev);
+	if (!cxlds)
+		return;
+
+	if (hweight32(status) > 1)
+		fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK,
+				   ras_cap.cap_control));
+	else
+		fe = status;
+
+	trace_cxl_aer_uncorrectable_error(cxlds->cxlmd, status, fe,
+					  ras_cap.header_log);
+}
+
+static void cxl_cper_handle_prot_err(struct cxl_cper_prot_err_work_data *data)
+{
+	unsigned int devfn = PCI_DEVFN(data->prot_err.agent_addr.device,
+				       data->prot_err.agent_addr.function);
+	struct pci_dev *pdev __free(pci_dev_put) =
+		pci_get_domain_bus_and_slot(data->prot_err.agent_addr.segment,
+					    data->prot_err.agent_addr.bus,
+					    devfn);
+	int port_type;
+
+	if (!pdev)
+		return;
+
+	guard(device)(&pdev->dev);
+
+	port_type = pci_pcie_type(pdev);
+	if (port_type == PCI_EXP_TYPE_ROOT_PORT ||
+	    port_type == PCI_EXP_TYPE_DOWNSTREAM ||
+	    port_type == PCI_EXP_TYPE_UPSTREAM) {
+		if (data->severity == AER_CORRECTABLE)
+			cxl_cper_trace_corr_port_prot_err(pdev, data->ras_cap);
+		else
+			cxl_cper_trace_uncorr_port_prot_err(pdev, data->ras_cap);
+
+		return;
+	}
+
+	if (data->severity == AER_CORRECTABLE)
+		cxl_cper_trace_corr_prot_err(pdev, data->ras_cap);
+	else
+		cxl_cper_trace_uncorr_prot_err(pdev, data->ras_cap);
+}
+
+static void cxl_cper_prot_err_work_fn(struct work_struct *work)
+{
+	struct cxl_cper_prot_err_work_data wd;
+
+	while (cxl_cper_prot_err_kfifo_get(&wd))
+		cxl_cper_handle_prot_err(&wd);
+}
+static DECLARE_WORK(cxl_cper_prot_err_work, cxl_cper_prot_err_work_fn);
+
+int cxl_ras_init(void)
+{
+	return cxl_cper_register_prot_err_work(&cxl_cper_prot_err_work);
+}
+
+void cxl_ras_exit(void)
+{
+	cxl_cper_unregister_prot_err_work(&cxl_cper_prot_err_work);
+	cancel_work_sync(&cxl_cper_prot_err_work);
+}
diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index cea706b683b5..342ae8d50f32 100644
--- a/drivers/cxl/core/trace.h
+++ b/drivers/cxl/core/trace.h
@@ -48,6 +48,34 @@
 	{ CXL_RAS_UC_IDE_RX_ERR, "IDE Rx Error" }			  \
 )
 
+TRACE_EVENT(cxl_port_aer_uncorrectable_error,
+	TP_PROTO(struct device *dev, u32 status, u32 fe, u32 *hl),
+	TP_ARGS(dev, status, fe, hl),
+	TP_STRUCT__entry(
+		__string(device, dev_name(dev))
+		__string(host, dev_name(dev->parent))
+		__field(u32, status)
+		__field(u32, first_error)
+		__array(u32, header_log, CXL_HEADERLOG_SIZE_U32)
+	),
+	TP_fast_assign(
+		__assign_str(device);
+		__assign_str(host);
+		__entry->status = status;
+		__entry->first_error = fe;
+		/*
+		 * Embed the 512B headerlog data for user app retrieval and
+		 * parsing, but no need to print this in the trace buffer.
+		 */
+		memcpy(__entry->header_log, hl, CXL_HEADERLOG_SIZE);
+	),
+	TP_printk("device=%s host=%s status: '%s' first_error: '%s'",
+		  __get_str(device), __get_str(host),
+		  show_uc_errs(__entry->status),
+		  show_uc_errs(__entry->first_error)
+	)
+);
+
 TRACE_EVENT(cxl_aer_uncorrectable_error,
 	TP_PROTO(const struct cxl_memdev *cxlmd, u32 status, u32 fe, u32 *hl),
 	TP_ARGS(cxlmd, status, fe, hl),
@@ -96,6 +124,25 @@ TRACE_EVENT(cxl_aer_uncorrectable_error,
 	{ CXL_RAS_CE_PHYS_LAYER_ERR, "Received Error From Physical Layer" }	\
 )
 
+TRACE_EVENT(cxl_port_aer_correctable_error,
+	TP_PROTO(struct device *dev, u32 status),
+	TP_ARGS(dev, status),
+	TP_STRUCT__entry(
+		__string(device, dev_name(dev))
+		__string(host, dev_name(dev->parent))
+		__field(u32, status)
+	),
+	TP_fast_assign(
+		__assign_str(device);
+		__assign_str(host);
+		__entry->status = status;
+	),
+	TP_printk("device=%s host=%s status='%s'",
+		  __get_str(device), __get_str(host),
+		  show_ce_errs(__entry->status)
+	)
+);
+
 TRACE_EVENT(cxl_aer_correctable_error,
 	TP_PROTO(const struct cxl_memdev *cxlmd, u32 status),
 	TP_ARGS(cxlmd, status),