[v8,2/2] cxl/pci: Add trace logging for CXL PCIe Port RAS errors

Commit Message

Smita Koralahalli March 10, 2025, 10:38 p.m. UTC

The CXL drivers use kernel trace functions for logging endpoint and
Restricted CXL host (RCH) Downstream Port RAS errors. Similar functionality
is required for CXL Root Ports, CXL Downstream Switch Ports, and CXL
Upstream Switch Ports.

Introduce trace logging functions for both RAS correctable and
uncorrectable errors specific to CXL PCIe Ports. Use them to trace
FW-First Protocol errors.

Co-developed-by: Terry Bowman <[e-mail]>
Signed-off-by: Terry Bowman <[e-mail]>
Signed-off-by: Smita Koralahalli <[e-mail]>
Reviewed-by: Ira Weiny <[e-mail]>
---
 drivers/cxl/core/ras.c   | 37 +++++++++++++++++++++++++++++++
 drivers/cxl/core/trace.h | 47 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 84 insertions(+)

Comments

Alison Schofield March 12, 2025, 6:59 p.m. UTC | #1

On Mon, Mar 10, 2025 at 10:38:39PM +0000, Smita Koralahalli wrote:
> The CXL drivers use kernel trace functions for logging endpoint and
> Restricted CXL host (RCH) Downstream Port RAS errors. Similar functionality
> is required for CXL Root Ports, CXL Downstream Switch Ports, and CXL
> Upstream Switch Ports.
> 
> Introduce trace logging functions for both RAS correctable and
> uncorrectable errors specific to CXL PCIe Ports. Use them to trace
> FW-First Protocol errors.
> 
> Co-developed-by: Terry Bowman <[e-mail]>
> Signed-off-by: Terry Bowman <[e-mail]>
> Signed-off-by: Smita Koralahalli <[e-mail]>
> Reviewed-by: Ira Weiny <[e-mail]>

Reviewed-by: Alison Schofield <[e-mail]>

Li Ming March 13, 2025, 1:03 a.m. UTC | #2

On 3/11/2025 6:38 AM, Smita Koralahalli wrote:
> The CXL drivers use kernel trace functions for logging endpoint and
> Restricted CXL host (RCH) Downstream Port RAS errors. Similar functionality
> is required for CXL Root Ports, CXL Downstream Switch Ports, and CXL
> Upstream Switch Ports.
>
> Introduce trace logging functions for both RAS correctable and
> uncorrectable errors specific to CXL PCIe Ports. Use them to trace
> FW-First Protocol errors.
>
> Co-developed-by: Terry Bowman <[e-mail]>
> Signed-off-by: Terry Bowman <[e-mail]>
> Signed-off-by: Smita Koralahalli <[e-mail]>
> Reviewed-by: Ira Weiny <[e-mail]>

Reviewed-by: Li Ming <[e-mail]>

Patch

diff --git a/drivers/cxl/core/ras.c b/drivers/cxl/core/ras.c
index 9b1773273e23..7617c186891d 100644
--- a/drivers/cxl/core/ras.c
+++ b/drivers/cxl/core/ras.c
@@ -7,6 +7,30 @@ 
 #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)
 {
@@ -49,12 +73,25 @@  static void cxl_cper_handle_prot_err(struct cxl_cper_prot_err_work_data *data)
 		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
diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index e3f842dcdf1d..25ebfbc1616c 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),