Hotplug events are critical indicators for analyzing hardware health,
particularly in AI supercomputers where surprise link downs can
significantly impact system performance and reliability. The failure
characterization analysis illustrates the significance of failures
caused by the Infiniband link errors. Meta observes that 2% in a machine
learning cluster and 6% in a vision application cluster of Infiniband
failures co-occur with GPU failures, such as falling off the bus, which
may indicate a correlation with PCIe.[1]

Add a generic RAS tracepoint for hotplug event to help healthy check.

[1]https://arxiv.org/abs/2410.21680

Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
---
 drivers/pci/hotplug/trace.h | 68 +++++++++++++++++++++++++++++++++++++
 include/uapi/linux/pci.h    |  7 ++++
 2 files changed, 75 insertions(+)
 create mode 100644 drivers/pci/hotplug/trace.h

diff --git a/drivers/pci/hotplug/trace.h b/drivers/pci/hotplug/trace.h
new file mode 100644
index 000000000000..a56e22534bc0
--- /dev/null
+++ b/drivers/pci/hotplug/trace.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#if !defined(_TRACE_HW_EVENT_PCI_HP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_HW_EVENT_PCI_HP_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM hotplug
+
+#define PCI_HP_TRANS_STATE					\
+	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_NO_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_HP_TRANS_STATE
+
+/*
+ * 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 trans_state),
+
+	TP_ARGS(port_name, slot, trans_state),
+
+	TP_STRUCT__entry(
+		__string(	port_name,	port_name	)
+		__string(	slot,		slot		)
+		__field(	int,		trans_state	)
+	),
+
+	TP_fast_assign(
+		__assign_str(port_name);
+		__assign_str(slot);
+		__entry->trans_state = trans_state;
+	),
+
+	TP_printk("%s slot:%s, trans_state:%s\n",
+		__get_str(port_name),
+		__get_str(slot),
+		__print_symbolic(__entry->trans_state, PCI_HP_TRANS_STATE)
+	)
+);
+
+#endif /* _TRACE_HW_EVENT_PCI_HP_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH  ../../drivers/pci/hotplug
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace
+
+/* 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..1f751785a43d 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_trans_type {
+	PCI_HOTPLUG_LINK_UP,
+	PCI_HOTPLUG_LINK_DOWN,
+	PCI_HOTPLUG_CARD_PRESENT,
+	PCI_HOTPLUG_CARD_NO_PRESENT,
+};
+
 #endif /* _UAPILINUX_PCI_H */
-- 
2.39.3