diff options
| author | Shuai Xue <xueshuai@linux.alibaba.com> | 2025-12-10 21:29:05 +0800 |
|---|---|---|
| committer | Bjorn Helgaas <bhelgaas@google.com> | 2025-12-23 16:05:56 -0600 |
| commit | 9e541b3cee70a3bbe86b176c903c23b29fe033cd (patch) | |
| tree | c985d3ab98983e41faff86d88e8a8565c2d803e1 /drivers/pci/hotplug | |
| parent | 8f0b4cce4481fb22653697cced8d0d04027cb1e8 (diff) | |
PCI: trace: Add generic RAS tracepoint for hotplug event
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>
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>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org> # for trace event
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://patch.msgid.link/20251210132907.58799-2-xueshuai@linux.alibaba.com
Diffstat (limited to 'drivers/pci/hotplug')
| -rw-r--r-- | drivers/pci/hotplug/pciehp_ctrl.c | 31 |
1 files changed, 25 insertions, 6 deletions
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: |