[PATCH v11 0/3] PCI: trace: Add a RAS tracepoint to monitor link speed changes

[PATCH v11 0/3] PCI: trace: Add a RAS tracepoint to monitor link speed changes

[Shuai Xue]

changes since v10:
- explicitly include header file per Ilpo
- add comma on any non-terminator entry  per Ilpo
- compile trace.o under CONFIG_TRACING per Ilpo

changes since v9:
- add a documentation about PCI tracepoints per Bjorn
- create a dedicated drivers/pci/trace.c that always defines the PCI tracepoints per Steve
- move tracepoint callite into __pcie_update_link_speed() per Lukas and Bjorn

changes since v8:
- rewrite commit log from Bjorn
- move pci_hp_event to a common place (include/trace/events/pci.h) per Ilpo
- rename hotplug event strings per Bjorn and Lukas
- add PCIe link tracepoint per Bjorn, Lukas, and Ilpo

Hotplug events are critical indicators for analyzing hardware health, and
surprise link downs can significantly impact system performance and reliability.
In addition, PCIe link speed degradation directly impacts system performance and
often indicates hardware issues such as faulty devices, physical layer problems,
or configuration errors.

This patch set add PCI hotplug and PCIe link tracepoint to help analyze PCI
hotplug events and PCIe link speed degradation.

Shuai Xue (3):
  PCI: trace: Add a generic RAS tracepoint for hotplug event
  PCI: trace: Add a RAS tracepoint to monitor link speed changes
  Documentation: tracing: Add documentation about PCI tracepoints

 Documentation/trace/events-pci.rst |  74 ++++++++++++++++++
 drivers/pci/Makefile               |   3 +
 drivers/pci/hotplug/pciehp_ctrl.c  |  31 ++++++--
 drivers/pci/hotplug/pciehp_hpc.c   |   3 +-
 drivers/pci/pci.c                  |   2 +-
 drivers/pci/pci.h                  |  22 +++++-
 drivers/pci/pcie/bwctrl.c          |   4 +-
 drivers/pci/probe.c                |   9 ++-
 drivers/pci/trace.c                |  11 +++
 include/linux/pci.h                |   1 +
 include/trace/events/pci.h         | 120 +++++++++++++++++++++++++++++
 include/uapi/linux/pci.h           |   7 ++
 12 files changed, 271 insertions(+), 16 deletions(-)
 create mode 100644 Documentation/trace/events-pci.rst
 create mode 100644 drivers/pci/trace.c
 create mode 100644 include/trace/events/pci.h

-- 
2.39.3

[PATCH v11 1/3] PCI: trace: Add a generic RAS tracepoint for hotplug event

[Shuai Xue]

Hotplug events are critical indicators for analyzing hardware health,
and surprise link downs can significantly impact system performance and
reliability.

Define a new TRACING_SYSTEM named "pci", add a generic RAS tracepoint
for hotplug event to help health checks. Add enum pci_hotplug_event in
include/uapi/linux/pci.h so applications like rasdaemon can register
tracepoint event handlers for it.

The following output is generated when a device is hotplugged:

$ echo 1 > /sys/kernel/debug/tracing/events/pci/pci_hp_event/enable
$ cat /sys/kernel/debug/tracing/trace_pipe
   irq/51-pciehp-88      [001] .....  1311.177459: pci_hp_event: 0000:00:02.0 slot:10, event:CARD_PRESENT

   irq/51-pciehp-88      [001] .....  1311.177566: pci_hp_event: 0000:00:02.0 slot:10, event:LINK_UP

Suggested-by: Lukas Wunner <lukas@wunner.de>
Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
Reviewed-by: Lukas Wunner <lukas@wunner.de>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/pci/Makefile              |  3 ++
 drivers/pci/hotplug/pciehp_ctrl.c | 31 ++++++++++++---
 drivers/pci/trace.c               | 11 ++++++
 include/trace/events/pci.h        | 63 +++++++++++++++++++++++++++++++
 include/uapi/linux/pci.h          |  7 ++++
 5 files changed, 109 insertions(+), 6 deletions(-)
 create mode 100644 drivers/pci/trace.c
 create mode 100644 include/trace/events/pci.h

diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index 67647f1880fb..58a4e4ea76b0 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -45,3 +45,6 @@ obj-y				+= controller/
 obj-y				+= switch/
 
 subdir-ccflags-$(CONFIG_PCI_DEBUG) := -DDEBUG
+
+CFLAGS_trace.o := -I$(src)
+obj-$(CONFIG_TRACING)		+= trace.o
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index bcc938d4420f..7805f697a02c 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -19,6 +19,7 @@
 #include <linux/types.h>
 #include <linux/pm_runtime.h>
 #include <linux/pci.h>
+#include <trace/events/pci.h>
 
 #include "../pci.h"
 #include "pciehp.h"
@@ -244,12 +245,20 @@ void pciehp_handle_presence_or_link_change(struct controller *ctrl, u32 events)
 	case ON_STATE:
 		ctrl->state = POWEROFF_STATE;
 		mutex_unlock(&ctrl->state_lock);
-		if (events & PCI_EXP_SLTSTA_DLLSC)
+		if (events & PCI_EXP_SLTSTA_DLLSC) {
 			ctrl_info(ctrl, "Slot(%s): Link Down\n",
 				  slot_name(ctrl));
-		if (events & PCI_EXP_SLTSTA_PDC)
+			trace_pci_hp_event(pci_name(ctrl->pcie->port),
+					   slot_name(ctrl),
+					   PCI_HOTPLUG_LINK_DOWN);
+		}
+		if (events & PCI_EXP_SLTSTA_PDC) {
 			ctrl_info(ctrl, "Slot(%s): Card not present\n",
 				  slot_name(ctrl));
+			trace_pci_hp_event(pci_name(ctrl->pcie->port),
+					   slot_name(ctrl),
+					   PCI_HOTPLUG_CARD_NOT_PRESENT);
+		}
 		pciehp_disable_slot(ctrl, SURPRISE_REMOVAL);
 		break;
 	default:
@@ -269,6 +278,9 @@ void pciehp_handle_presence_or_link_change(struct controller *ctrl, u32 events)
 					      INDICATOR_NOOP);
 			ctrl_info(ctrl, "Slot(%s): Card not present\n",
 				  slot_name(ctrl));
+			trace_pci_hp_event(pci_name(ctrl->pcie->port),
+					   slot_name(ctrl),
+					   PCI_HOTPLUG_CARD_NOT_PRESENT);
 		}
 		mutex_unlock(&ctrl->state_lock);
 		return;
@@ -281,12 +293,19 @@ void pciehp_handle_presence_or_link_change(struct controller *ctrl, u32 events)
 	case OFF_STATE:
 		ctrl->state = POWERON_STATE;
 		mutex_unlock(&ctrl->state_lock);
-		if (present)
+		if (present) {
 			ctrl_info(ctrl, "Slot(%s): Card present\n",
 				  slot_name(ctrl));
-		if (link_active)
-			ctrl_info(ctrl, "Slot(%s): Link Up\n",
-				  slot_name(ctrl));
+			trace_pci_hp_event(pci_name(ctrl->pcie->port),
+					   slot_name(ctrl),
+					   PCI_HOTPLUG_CARD_PRESENT);
+		}
+		if (link_active) {
+			ctrl_info(ctrl, "Slot(%s): Link Up\n", slot_name(ctrl));
+			trace_pci_hp_event(pci_name(ctrl->pcie->port),
+					   slot_name(ctrl),
+					   PCI_HOTPLUG_LINK_UP);
+		}
 		ctrl->request_result = pciehp_enable_slot(ctrl);
 		break;
 	default:
diff --git a/drivers/pci/trace.c b/drivers/pci/trace.c
new file mode 100644
index 000000000000..cf11abca8602
--- /dev/null
+++ b/drivers/pci/trace.c
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Tracepoints for PCI system
+ *
+ * Copyright (C) 2025 Alibaba Corporation
+ */
+
+#include <linux/pci.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/pci.h>
diff --git a/include/trace/events/pci.h b/include/trace/events/pci.h
new file mode 100644
index 000000000000..208609492c06
--- /dev/null
+++ b/include/trace/events/pci.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM pci
+
+#if !defined(_TRACE_HW_EVENT_PCI_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_HW_EVENT_PCI_H
+
+#include <linux/tracepoint.h>
+
+#define PCI_HOTPLUG_EVENT						\
+	EM(PCI_HOTPLUG_LINK_UP,			"LINK_UP")		\
+	EM(PCI_HOTPLUG_LINK_DOWN,		"LINK_DOWN")		\
+	EM(PCI_HOTPLUG_CARD_PRESENT,		"CARD_PRESENT")		\
+	EMe(PCI_HOTPLUG_CARD_NOT_PRESENT,	"CARD_NOT_PRESENT")
+
+/* Enums require being exported to userspace, for user tool parsing */
+#undef EM
+#undef EMe
+#define EM(a, b)	TRACE_DEFINE_ENUM(a);
+#define EMe(a, b)	TRACE_DEFINE_ENUM(a);
+
+PCI_HOTPLUG_EVENT
+
+/*
+ * Now redefine the EM() and EMe() macros to map the enums to the strings
+ * that will be printed in the output.
+ */
+#undef EM
+#undef EMe
+#define EM(a, b)	{a, b},
+#define EMe(a, b)	{a, b}
+
+TRACE_EVENT(pci_hp_event,
+
+	TP_PROTO(const char *port_name,
+		 const char *slot,
+		 const int event),
+
+	TP_ARGS(port_name, slot, event),
+
+	TP_STRUCT__entry(
+		__string(	port_name,	port_name	)
+		__string(	slot,		slot		)
+		__field(	int,		event	)
+	),
+
+	TP_fast_assign(
+		__assign_str(port_name);
+		__assign_str(slot);
+		__entry->event = event;
+	),
+
+	TP_printk("%s slot:%s, event:%s\n",
+		__get_str(port_name),
+		__get_str(slot),
+		__print_symbolic(__entry->event, PCI_HOTPLUG_EVENT)
+	)
+);
+
+#endif /* _TRACE_HW_EVENT_PCI_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/uapi/linux/pci.h b/include/uapi/linux/pci.h
index a769eefc5139..4f150028965d 100644
--- a/include/uapi/linux/pci.h
+++ b/include/uapi/linux/pci.h
@@ -39,4 +39,11 @@
 #define PCIIOC_MMAP_IS_MEM	(PCIIOC_BASE | 0x02)	/* Set mmap state to MEM space. */
 #define PCIIOC_WRITE_COMBINE	(PCIIOC_BASE | 0x03)	/* Enable/disable write-combining. */
 
+enum pci_hotplug_event {
+	PCI_HOTPLUG_LINK_UP,
+	PCI_HOTPLUG_LINK_DOWN,
+	PCI_HOTPLUG_CARD_PRESENT,
+	PCI_HOTPLUG_CARD_NOT_PRESENT,
+};
+
 #endif /* _UAPILINUX_PCI_H */
-- 
2.39.3

[PATCH v11 2/3] PCI: trace: Add a RAS tracepoint to monitor link speed changes

[Shuai Xue]

PCIe link speed degradation directly impacts system performance and
often indicates hardware issues such as faulty devices, physical layer
problems, or configuration errors.

To this end, add a RAS tracepoint to monitor link speed changes,
enabling proactive health checks and diagnostic analysis.

The following output is generated when a device is hotplugged:

$ echo 1 > /sys/kernel/debug/tracing/events/pci/pcie_link_event/enable
$ cat /sys/kernel/debug/tracing/trace_pipe
   irq/51-pciehp-88      [001] .....   381.545386: pcie_link_event: 0000:00:02.0 type:4, reason:4, cur_bus_speed:2.5 GT/s PCIe, max_bus_speed:16.0 GT/s PCIe, width:1, flit_mode:0, status:DLLLA

Suggested-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Suggested-by: Matthew W Carlis <mattc@purestorage.com>
Suggested-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
---
 drivers/pci/hotplug/pciehp_hpc.c |  3 +-
 drivers/pci/pci.c                |  2 +-
 drivers/pci/pci.h                | 22 ++++++++++--
 drivers/pci/pcie/bwctrl.c        |  4 +--
 drivers/pci/probe.c              |  9 +++--
 include/linux/pci.h              |  1 +
 include/trace/events/pci.h       | 57 ++++++++++++++++++++++++++++++++
 7 files changed, 88 insertions(+), 10 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index bcc51b26d03d..ad5f28f6a8b1 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -320,7 +320,8 @@ int pciehp_check_link_status(struct controller *ctrl)
 	}
 
 	pcie_capability_read_word(pdev, PCI_EXP_LNKSTA2, &linksta2);
-	__pcie_update_link_speed(ctrl->pcie->port->subordinate, lnk_status, linksta2);
+	__pcie_update_link_speed(ctrl->pcie->port->subordinate, PCIE_HOTPLUG,
+				 lnk_status, linksta2);
 
 	if (!found) {
 		ctrl_info(ctrl, "Slot(%s): No device found\n",
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index b0f4d98036cd..96755ffd3841 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -4749,7 +4749,7 @@ int pcie_retrain_link(struct pci_dev *pdev, bool use_lt)
 	 * Link Speed.
 	 */
 	if (pdev->subordinate)
-		pcie_update_link_speed(pdev->subordinate);
+		pcie_update_link_speed(pdev->subordinate, PCIE_LINK_RETRAIN);
 
 	return rc;
 }
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index b8d364545e7d..0ccd629e0ccb 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -3,6 +3,7 @@
 #define DRIVERS_PCI_H
 
 #include <linux/pci.h>
+#include <trace/events/pci.h>
 
 struct pcie_tlp_log;
 
@@ -455,16 +456,31 @@ static inline int pcie_dev_speed_mbps(enum pci_bus_speed speed)
 }
 
 u8 pcie_get_supported_speeds(struct pci_dev *dev);
-const char *pci_speed_string(enum pci_bus_speed speed);
 void __pcie_print_link_status(struct pci_dev *dev, bool verbose);
 void pcie_report_downtraining(struct pci_dev *dev);
 
-static inline void __pcie_update_link_speed(struct pci_bus *bus, u16 linksta, u16 linksta2)
+enum pcie_link_change_reason {
+	PCIE_LINK_RETRAIN,
+	PCIE_ADD_BUS,
+	PCIE_BWCTRL_ENABLE,
+	PCIE_BWCTRL_IRQ,
+	PCIE_HOTPLUG,
+};
+
+static inline void __pcie_update_link_speed(struct pci_bus *bus,
+					    enum pcie_link_change_reason reason,
+					    u16 linksta, u16 linksta2)
 {
 	bus->cur_bus_speed = pcie_link_speed[linksta & PCI_EXP_LNKSTA_CLS];
 	bus->flit_mode = (linksta2 & PCI_EXP_LNKSTA2_FLIT) ? 1 : 0;
+
+	trace_pcie_link_event(bus,
+			     reason,
+			     FIELD_GET(PCI_EXP_LNKSTA_NLW, linksta),
+			     linksta & PCI_EXP_LNKSTA_LINK_STATUS_MASK);
 }
-void pcie_update_link_speed(struct pci_bus *bus);
+
+void pcie_update_link_speed(struct pci_bus *bus, enum pcie_link_change_reason reason);
 
 /* Single Root I/O Virtualization */
 struct pci_sriov {
diff --git a/drivers/pci/pcie/bwctrl.c b/drivers/pci/pcie/bwctrl.c
index 36f939f23d34..32f1b30ecb84 100644
--- a/drivers/pci/pcie/bwctrl.c
+++ b/drivers/pci/pcie/bwctrl.c
@@ -199,7 +199,7 @@ static void pcie_bwnotif_enable(struct pcie_device *srv)
 	 * Update after enabling notifications & clearing status bits ensures
 	 * link speed is up to date.
 	 */
-	pcie_update_link_speed(port->subordinate);
+	pcie_update_link_speed(port->subordinate, PCIE_BWCTRL_ENABLE);
 }
 
 static void pcie_bwnotif_disable(struct pci_dev *port)
@@ -234,7 +234,7 @@ static irqreturn_t pcie_bwnotif_irq(int irq, void *context)
 	 * speed (inside pcie_update_link_speed()) after LBMS has been
 	 * cleared to avoid missing link speed changes.
 	 */
-	pcie_update_link_speed(port->subordinate);
+	pcie_update_link_speed(port->subordinate, PCIE_BWCTRL_IRQ);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index f41128f91ca7..c4cae2664156 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -21,6 +21,7 @@
 #include <linux/irqdomain.h>
 #include <linux/pm_runtime.h>
 #include <linux/bitfield.h>
+#include <trace/events/pci.h>
 #include "pci.h"
 
 #define CARDBUS_LATENCY_TIMER	176	/* secondary latency timer */
@@ -788,14 +789,16 @@ const char *pci_speed_string(enum pci_bus_speed speed)
 }
 EXPORT_SYMBOL_GPL(pci_speed_string);
 
-void pcie_update_link_speed(struct pci_bus *bus)
+void pcie_update_link_speed(struct pci_bus *bus,
+			    enum pcie_link_change_reason reason)
 {
 	struct pci_dev *bridge = bus->self;
 	u16 linksta, linksta2;
 
 	pcie_capability_read_word(bridge, PCI_EXP_LNKSTA, &linksta);
 	pcie_capability_read_word(bridge, PCI_EXP_LNKSTA2, &linksta2);
-	__pcie_update_link_speed(bus, linksta, linksta2);
+
+	__pcie_update_link_speed(bus, reason, linksta, linksta2);
 }
 EXPORT_SYMBOL_GPL(pcie_update_link_speed);
 
@@ -882,7 +885,7 @@ static void pci_set_bus_speed(struct pci_bus *bus)
 		pcie_capability_read_dword(bridge, PCI_EXP_LNKCAP, &linkcap);
 		bus->max_bus_speed = pcie_link_speed[linkcap & PCI_EXP_LNKCAP_SLS];
 
-		pcie_update_link_speed(bus);
+		pcie_update_link_speed(bus, PCIE_ADD_BUS);
 	}
 }
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 59876de13860..edd8a61ec44e 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -305,6 +305,7 @@ enum pci_bus_speed {
 	PCI_SPEED_UNKNOWN		= 0xff,
 };
 
+const char *pci_speed_string(enum pci_bus_speed speed);
 enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev);
 enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev);
 
diff --git a/include/trace/events/pci.h b/include/trace/events/pci.h
index 208609492c06..4df4daaa2d27 100644
--- a/include/trace/events/pci.h
+++ b/include/trace/events/pci.h
@@ -5,6 +5,7 @@
 #if !defined(_TRACE_HW_EVENT_PCI_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_HW_EVENT_PCI_H
 
+#include <uapi/linux/pci_regs.h>
 #include <linux/tracepoint.h>
 
 #define PCI_HOTPLUG_EVENT						\
@@ -57,6 +58,62 @@ TRACE_EVENT(pci_hp_event,
 	)
 );
 
+#define PCI_EXP_LNKSTA_LINK_STATUS_MASK (PCI_EXP_LNKSTA_LBMS | \
+					 PCI_EXP_LNKSTA_LABS | \
+					 PCI_EXP_LNKSTA_LT | \
+					 PCI_EXP_LNKSTA_DLLLA)
+
+#define LNKSTA_FLAGS					\
+	{ PCI_EXP_LNKSTA_LT,	"LT"},			\
+	{ PCI_EXP_LNKSTA_DLLLA,	"DLLLA"},		\
+	{ PCI_EXP_LNKSTA_LBMS,	"LBMS"},		\
+	{ PCI_EXP_LNKSTA_LABS,	"LABS"}
+
+TRACE_EVENT(pcie_link_event,
+
+	TP_PROTO(struct pci_bus *bus,
+		  unsigned int reason,
+		  unsigned int width,
+		  unsigned int status
+		),
+
+	TP_ARGS(bus, reason, width, status),
+
+	TP_STRUCT__entry(
+		__string(	port_name,	pci_name(bus->self))
+		__field(	unsigned int,	type		)
+		__field(	unsigned int,	reason		)
+		__field(	unsigned int,	cur_bus_speed	)
+		__field(	unsigned int,	max_bus_speed	)
+		__field(	unsigned int,	width		)
+		__field(	unsigned int,	flit_mode	)
+		__field(	unsigned int,	link_status	)
+	),
+
+	TP_fast_assign(
+		__assign_str(port_name);
+		__entry->type			= pci_pcie_type(bus->self);
+		__entry->reason			= reason;
+		__entry->cur_bus_speed		= bus->cur_bus_speed;
+		__entry->max_bus_speed		= bus->max_bus_speed;
+		__entry->width			= width;
+		__entry->flit_mode		= bus->flit_mode;
+		__entry->link_status		= status;
+	),
+
+	TP_printk("%s type:%d, reason:%d, cur_bus_speed:%s, max_bus_speed:%s, width:%u, flit_mode:%u, status:%s\n",
+		__get_str(port_name),
+		__entry->type,
+		__entry->reason,
+		pci_speed_string(__entry->cur_bus_speed),
+		pci_speed_string(__entry->max_bus_speed),
+		__entry->width,
+		__entry->flit_mode,
+		__print_flags((unsigned long)__entry->link_status, "|",
+				LNKSTA_FLAGS)
+	)
+);
+
 #endif /* _TRACE_HW_EVENT_PCI_H */
 
 /* This part must be outside protection */
-- 
2.39.3

Re: [PATCH v11 2/3] PCI: trace: Add a RAS tracepoint to monitor link speed changes

[kernel test robot]

Hi Shuai,

kernel test robot noticed the following build errors:

[auto build test ERROR on pci/for-linus]
[also build test ERROR on trace/for-next linus/master v6.17-rc7 next-20250925]
[cannot apply to pci/next]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Shuai-Xue/PCI-trace-Add-a-generic-RAS-tracepoint-for-hotplug-event/20250925-142250
base:   https://git.kernel.org/pub/scm/linux/kernel/git/pci/pci.git for-linus
patch link:    https://lore.kernel.org/r/20250925061928.42758-3-xueshuai%40linux.alibaba.com
patch subject: [PATCH v11 2/3] PCI: trace: Add a RAS tracepoint to monitor link speed changes
config: x86_64-buildonly-randconfig-006-20250926 (https://download.01.org/0day-ci/archive/20250926/202509260804.F13FDt4V-lkp@intel.com/config)
compiler: gcc-14 (Debian 14.2.0-19) 14.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250926/202509260804.F13FDt4V-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202509260804.F13FDt4V-lkp@intel.com/

All errors (new ones prefixed by >>):

   ld: vmlinux.o: in function `trace_raw_output_pcie_link_event':
   trace.c:(.text+0x91792a): undefined reference to `pci_speed_string'
>> ld: trace.c:(.text+0x917935): undefined reference to `pci_speed_string'

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

[PATCH v11 3/3] Documentation: tracing: Add documentation about PCI tracepoints

[Shuai Xue]

The PCI tracing system provides tracepoints to monitor critical hardware
events that can impact system performance and reliability. Add
documentation about it.

Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
---
 Documentation/trace/events-pci.rst | 74 ++++++++++++++++++++++++++++++
 1 file changed, 74 insertions(+)
 create mode 100644 Documentation/trace/events-pci.rst

diff --git a/Documentation/trace/events-pci.rst b/Documentation/trace/events-pci.rst
new file mode 100644
index 000000000000..500b27713224
--- /dev/null
+++ b/Documentation/trace/events-pci.rst
@@ -0,0 +1,74 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===========================
+Subsystem Trace Points: PCI
+===========================
+
+Overview
+========
+The PCI tracing system provides tracepoints to monitor critical hardware events
+that can impact system performance and reliability. These events normally show
+up here:
+
+	/sys/kernel/tracing/events/pci
+
+Cf. include/trace/events/pci.h for the events definitions.
+
+Available Tracepoints
+=====================
+
+pci_hp_event
+------------
+
+Monitors PCI hotplug events including card insertion/removal and link
+state changes.
+::
+
+    pci_hp_event  "%s slot:%s, event:%s\n"
+
+**Event Types**:
+
+* ``LINK_UP`` - PCIe link established
+* ``LINK_DOWN`` - PCIe link lost
+* ``CARD_PRESENT`` - Card detected in slot
+* ``CARD_NOT_PRESENT`` - Card removed from slot
+
+**Example Usage**:
+
+    # Enable the tracepoint
+    echo 1> /sys/kernel/debug/tracing/events/pci/pci_hp_event/enable
+
+    # Monitor events (the following output is generated when a device is hotplugged)
+    cat /sys/kernel/debug/tracing/trace_pipe
+       irq/51-pciehp-88      [001] .....  1311.177459: pci_hp_event: 0000:00:02.0 slot:10, event:CARD_PRESENT
+
+       irq/51-pciehp-88      [001] .....  1311.177566: pci_hp_event: 0000:00:02.0 slot:10, event:LINK_UP
+
+pcie_link_event
+---------------
+
+Monitors PCIe link speed changes and provides detailed link status information.
+::
+
+    pcie_link_event  "%s type:%d, reason:%d, cur_bus_speed:%s, max_bus_speed:%s, width:%u, flit_mode:%u, status:%s\n"
+
+**Parameters**:
+
+* ``type`` - PCIe device type (4=Root Port, etc.)
+* ``reason`` - Reason for link change:
+
+  - ``0`` - Link retrain
+  - ``1`` - Bus enumeration
+  - ``2`` - Bandwidth controller enable
+  - ``3`` - Bandwidth controller IRQ
+  - ``4`` - Hotplug event
+
+
+**Example Usage**:
+
+    # Enable the tracepoint
+    echo1 > /sys/kernel/debug/tracing/events/pci/pcie_link_event/enable
+
+    # Monitor events (the following output is generated when a device is hotplugged)
+    cat /sys/kernel/debug/tracing/trace_pipe
+       irq/51-pciehp-88      [001] .....   381.545386: pcie_link_event: 0000:00:02.0 type:4, reason:4, cur_bus_speed:2.5 GT/s PCIe, max_bus_speed:16.0 GT/s PCIe, width:1, flit_mode:0, status:DLLLA
-- 
2.39.3