Merge branch 'pci/trace'

- Add generic RAS tracepoint for hotplug events (Shuai Xue)

- Add RAS tracepoint for link speed changes (Shuai Xue)

* pci/trace:
  Documentation: tracing: Add PCI tracepoint documentation
  PCI: trace: Add RAS tracepoint to monitor link speed changes
  PCI: trace: Add generic RAS tracepoint for hotplug event

12 files changed, 280 insertions, 15 deletions

diff --git a/Documentation/trace/events-pci.rst b/Documentation/trace/events-pci.rst
new file mode 100644
index 000000000000..03ff4ad30ddf
--- /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:%d, max_bus_speed:%d, 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 notification enable
+  - ``3`` - Bandwidth notification IRQ
+  - ``4`` - Hotplug event
+
+
+**Example Usage**::
+
+    # Enable the tracepoint
+    echo 1 > /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:20, max_bus_speed:23, width:1, flit_mode:0, status:DLLLA
diff --git a/Documentation/trace/index.rst b/Documentation/trace/index.rst
index b4a429dc4f7a..0a40bfabcf19 100644
--- a/Documentation/trace/index.rst
+++ b/Documentation/trace/index.rst
@@ -54,6 +54,7 @@ applications.
    events-power
    events-nmi
    events-msr
+   events-pci
    boottime-trace
    histogram
    histogram-design
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index 8922f90afecb..41ebc3b9a518 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -48,3 +48,6 @@ 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/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 de7c8f6def12..30545e756f6b 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -4553,7 +4553,7 @@ 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 7930d9d3182e..18e6c053bbd8 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -5,6 +5,7 @@
 #include <linux/align.h>
 #include <linux/bitfield.h>
 #include <linux/pci.h>
+#include <trace/events/pci.h>
 
 struct pcie_tlp_log;
 
@@ -601,12 +602,28 @@ 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 4ae92c9f912a..c4c8d260bf96 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 9494e7f6e36f..1d4e7e1b0ba1 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -23,6 +23,7 @@
 #include <linux/irqdomain.h>
 #include <linux/pm_runtime.h>
 #include <linux/bitfield.h>
+#include <trace/events/pci.h>
 #include "pci.h"
 
 static struct resource busn_resource = {
@@ -820,14 +821,16 @@ 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);
 
@@ -914,7 +917,7 @@ 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/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..9a9122f62fd3
--- /dev/null
+++ b/include/trace/events/pci.h
@@ -0,0 +1,129 @@
+/* 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 <uapi/linux/pci_regs.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}
+
+/*
+ * Note: For generic PCI hotplug events, we pass already-resolved strings
+ * (port_name, slot) instead of driver-specific structures like 'struct
+ * controller'.  This is because different PCI hotplug drivers (pciehp, cpqphp,
+ * ibmphp, shpchp) define their own versions of 'struct controller' with
+ * different fields and helper functions. Using driver-specific structures would
+ * make the tracepoint interface non-generic and cause compatibility issues
+ * across different drivers.
+ */
+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)
+	)
+);
+
+#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:%d, max_bus_speed:%d, width:%u, flit_mode:%u, status:%s\n",
+		__get_str(port_name),
+		__entry->type,
+		__entry->reason,
+		__entry->cur_bus_speed,
+		__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 */
+#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 */