linux-kernel - [PATCH v3 13/15] cxl/pci: Add trace logging for CXL PCIe port RAS errors

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20241113215429.3177981-14-terry.bowman@amd.com>
Date: Wed, 13 Nov 2024 15:54:27 -0600
From: Terry Bowman <terry.bowman@....com>
To: <linux-cxl@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
	<linux-pci@...r.kernel.org>, <nifan.cxl@...il.com>, <ming4.li@...el.com>,
	<dave@...olabs.net>, <jonathan.cameron@...wei.com>, <dave.jiang@...el.com>,
	<alison.schofield@...el.com>, <vishal.l.verma@...el.com>,
	<dan.j.williams@...el.com>, <bhelgaas@...gle.com>, <mahesh@...ux.ibm.com>,
	<ira.weiny@...el.com>, <oohall@...il.com>, <Benjamin.Cheatham@....com>,
	<rrichter@....com>, <nathan.fontenot@....com>, <terry.bowman@....com>,
	<Smita.KoralahalliChannabasappa@....com>, <lukas@...ner.de>
Subject: [PATCH v3 13/15] cxl/pci: Add trace logging for CXL PCIe port RAS errors

The CXL drivers use kernel trace functions for logging endpoint and
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. Additionally, update
the PCIe port error handlers to invoke these new trace functions.

Signed-off-by: Terry Bowman <terry.bowman@....com>
---
 drivers/cxl/core/pci.c   | 16 ++++++++++----
 drivers/cxl/core/trace.h | 47 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 59 insertions(+), 4 deletions(-)

diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index 2c5cfc506f74..794a601fdbf9 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -661,10 +661,14 @@ static void __cxl_handle_cor_ras(struct device *dev,
 
 	addr = ras_base + CXL_RAS_CORRECTABLE_STATUS_OFFSET;
 	status = readl(addr);
-	if (status & CXL_RAS_CORRECTABLE_STATUS_MASK) {
-		writel(status & CXL_RAS_CORRECTABLE_STATUS_MASK, addr);
+	if (!(status & CXL_RAS_CORRECTABLE_STATUS_MASK))
+		return;
+	writel(status & CXL_RAS_CORRECTABLE_STATUS_MASK, addr);
+
+	if (is_cxl_memdev(dev))
 		trace_cxl_aer_correctable_error(to_cxl_memdev(dev), status);
-	}
+	else
+		trace_cxl_port_aer_correctable_error(dev, status);
 }
 
 static void cxl_handle_endpoint_cor_ras(struct cxl_dev_state *cxlds)
@@ -720,7 +724,11 @@ static bool __cxl_handle_ras(struct device *dev, void __iomem *ras_base)
 	}
 
 	header_log_copy(ras_base, hl);
-	trace_cxl_aer_uncorrectable_error(to_cxl_memdev(dev), status, fe, hl);
+	if (is_cxl_memdev(dev))
+		trace_cxl_aer_uncorrectable_error(to_cxl_memdev(dev), status, fe, hl);
+	else
+		trace_cxl_port_aer_uncorrectable_error(dev, status, fe, hl);
+
 	writel(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK, addr);
 
 	return true;
diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index 8389a94adb1a..681e415ac8f5 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(devname, 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(devname);
+		__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(devname), __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(devname, dev_name(dev))
+		__string(host, dev_name(dev->parent))
+		__field(u32, status)
+	),
+	TP_fast_assign(
+		__assign_str(devname);
+		__assign_str(host);
+		__entry->status = status;
+	),
+	TP_printk("device=%s host=%s status='%s'",
+		  __get_str(devname), __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),
-- 
2.34.1