diff options
| author | Shuai Xue <xueshuai@linux.alibaba.com> | 2025-12-10 21:29:06 +0800 |
|---|---|---|
| committer | Bjorn Helgaas <bhelgaas@google.com> | 2025-12-23 16:06:00 -0600 |
| commit | d4318c1a79ac49f0726dd23a01d1961757b5f98d (patch) | |
| tree | 8be85a74ca40ee63b5c7d7ef0093587d5cb691ee /include/trace | |
| parent | 9e541b3cee70a3bbe86b176c903c23b29fe033cd (diff) | |
PCI: trace: Add RAS tracepoint to monitor link speed changes
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:20, max_bus_speed:23, 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>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://patch.msgid.link/20251210132907.58799-3-xueshuai@linux.alibaba.com
Diffstat (limited to 'include/trace')
| -rw-r--r-- | include/trace/events/pci.h | 57 |
1 files changed, 57 insertions, 0 deletions
diff --git a/include/trace/events/pci.h b/include/trace/events/pci.h index 39e512a167ee..9a9122f62fd3 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 \ @@ -66,6 +67,62 @@ 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:%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 */ |