[PATCH v9 1/2] PCI: trace: Add a generic RAS tracepoint for hotplug event
From: Shuai Xue <xueshuai@linux.alibaba.com>
Date: 2025-07-23 03:31:32
Also in:
linux-edac, linux-pci, lkml
Subsystem:
pci subsystem, the rest, tracing · Maintainers:
Bjorn Helgaas, Linus Torvalds, Steven Rostedt, Masami Hiramatsu
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 output is like below:
$ echo 1 > /sys/kernel/debug/tracing/events/pci/pci_hp_event/enable
$ cat /sys/kernel/debug/tracing/trace_pipe
<...>-206 [001] ..... 40.373870: pci_hp_event: 0000:00:02.0 slot:10, event:LINK_DOWN
<...>-206 [001] ..... 40.374871: pci_hp_event: 0000:00:02.0 slot:10, event:CARD_NOT_PRESENT
Suggested-by: Lukas Wunner <lukas@wunner.de>
Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Lukas Wunner <lukas@wunner.de>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
drivers/pci/hotplug/pciehp_ctrl.c | 33 +++++++++++++---
include/trace/events/pci.h | 63 +++++++++++++++++++++++++++++++
include/uapi/linux/pci.h | 7 ++++
3 files changed, 97 insertions(+), 6 deletions(-)
create mode 100644 include/trace/events/pci.h
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index bcc938d4420f..d241f270c8de 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c@@ -20,6 +20,9 @@ #include <linux/pm_runtime.h> #include <linux/pci.h> +#define CREATE_TRACE_POINTS +#include <trace/events/pci.h> + #include "../pci.h" #include "pciehp.h"
@@ -244,12 +247,20 @@ 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 +280,9 @@ 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 +295,19 @@ 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/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