tracing: Add the ::ppin field to the mce_record tracepoint

Machine Check Error information from 'struct mce' is exposed to userspace
through the mce_record tracepoint.

Currently, however, the PPIN (Protected Processor Inventory Number) field
of 'struct mce' is not exposed.

Add a PPIN field to the tracepoint as it provides a unique identifier for
the system (or socket in case of multi-socket systems) on which the MCE
has been received.

Also, add a comment explaining the kind of information that can be and
should be added to the tracepoint.

Signed-off-by: Avadhut Naik <avadhut.naik@amd.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Sohil Mehta <sohil.mehta@intel.com>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/r/20240401171455.1737976-2-avadhut.naik@amd.com

diff --git a/include/trace/events/mce.h b/include/trace/events/mce.h
index 9c4e1216399695c1735b8dbfa213270bc6bfdf70..294fccc329c16a0868dd87e6fb8b7c802f6b2b8e 100644 (file)
--- a/include/trace/events/mce.h
+++ b/include/trace/events/mce.h
@@ -9,6 +9,14 @@
 #include <linux/tracepoint.h>
 #include <asm/mce.h>
 
+/*
+ * MCE Event Record.
+ *
+ * Only very relevant and transient information which cannot be
+ * gathered from a system by any other means or which can only be
+ * acquired arduously should be added to this record.
+ */
+
 TRACE_EVENT(mce_record,
 
        TP_PROTO(struct mce *m),
@@ -25,6 +33,7 @@ TRACE_EVENT(mce_record,
                __field(        u64,            ipid            )
                __field(        u64,            ip              )
                __field(        u64,            tsc             )
+               __field(        u64,            ppin            )
                __field(        u64,            walltime        )
                __field(        u32,            cpu             )
                __field(        u32,            cpuid           )
@@ -45,6 +54,7 @@ TRACE_EVENT(mce_record,
                __entry->ipid           = m->ipid;
                __entry->ip             = m->ip;
                __entry->tsc            = m->tsc;
+               __entry->ppin           = m->ppin;
                __entry->walltime       = m->time;
                __entry->cpu            = m->extcpu;
                __entry->cpuid          = m->cpuid;
@@ -55,7 +65,7 @@ TRACE_EVENT(mce_record,
                __entry->cpuvendor      = m->cpuvendor;
        ),
 
-       TP_printk("CPU: %d, MCGc/s: %llx/%llx, MC%d: %016Lx, IPID: %016Lx, ADDR: %016Lx, MISC: %016Lx, SYND: %016Lx, RIP: %02x:<%016Lx>, TSC: %llx, vendor: %u, CPUID: %x, time: %llu, socket: %u, APIC: %x",
+       TP_printk("CPU: %d, MCGc/s: %llx/%llx, MC%d: %016Lx, IPID: %016Lx, ADDR: %016Lx, MISC: %016Lx, SYND: %016Lx, RIP: %02x:<%016Lx>, TSC: %llx, PPIN: %llx, vendor: %u, CPUID: %x, time: %llu, socket: %u, APIC: %x",
                __entry->cpu,
                __entry->mcgcap, __entry->mcgstatus,
                __entry->bank, __entry->status,
@@ -65,6 +75,7 @@ TRACE_EVENT(mce_record,
                __entry->synd,
                __entry->cs, __entry->ip,
                __entry->tsc,
+               __entry->ppin,
                __entry->cpuvendor,
                __entry->cpuid,
                __entry->walltime,