[PATCH v2 3/3] ras/events: Trace CXL CPER events without CXL stack

[Ira Weiny]

If CXL is solely managed by firmware (including HDM configuration and
event processing via firmware first) it is possible to run the system
without the CXL software loaded.  In this case no CXL callback will be
loaded and CXL CPER errors will not be processed at all.

In this case memory device and region (HPA) information is missing but
omitting the error completely is not friendly.  Some device information
is available the event.

Trace CXL CPER events if the CXL stack is not loaded.  A balance was
chosen to decode only the CPER header as this configuration is likely
rare.

Cc: Ard Biesheuvel <ardb@xxxxxxxxxx>
Cc: "Rafael J. Wysocki" <rafael@xxxxxxxxxx>
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Suggested-by: Dan Williams <dan.j.williams@xxxxxxxxx>
Signed-off-by: Ira Weiny <ira.weiny@xxxxxxxxx>

---
Changes:
[djbw: remove local work task and call trace directly]
[djbw: strip down the generic trace information]
---
 drivers/acpi/apei/ghes.c |  6 +++++-
 include/ras/ras_event.h  | 51 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 56 insertions(+), 1 deletion(-)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index cdcfdf6ebe81..20a0e622f829 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -739,8 +739,12 @@ static void cxl_cper_post_event(enum cxl_event_type event_type,
 
 	guard(spinlock_irqsave)(&cxl_cper_work_lock);
 
-	if (!cxl_cper_work)
+	if (!cxl_cper_work) {
+		union cxl_event *evt = &rec->event;
+
+		trace_cper_cxl_event(rec, &evt->generic, event_type);
 		return;
+	}
 
 	wd.event_type = event_type;
 	memcpy(&wd.rec, rec, sizeof(wd.rec));
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index c011ea236e9b..c1fac66fb44a 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -422,6 +422,57 @@ TRACE_EVENT(memory_failure_event,
 	)
 );
 #endif /* CONFIG_MEMORY_FAILURE */
+
+#include <linux/cxl-event.h>
+#include <asm-generic/unaligned.h>
+
+TRACE_EVENT(cper_cxl_event,
+
+	TP_PROTO(struct cxl_cper_event_rec *cper_rec,
+		 struct cxl_event_generic *gen_rec,
+		 enum cxl_event_type event_type),
+
+	TP_ARGS(cper_rec, gen_rec, event_type),
+
+	/* packed record */
+	TP_STRUCT__entry(
+		__field(u16, segment)
+		__field(u8, bus)
+		__field(u8, device)
+		__field(u32, hdr_flags)
+		__field(u64, serial)
+		__field(u64, hdr_timestamp)
+		__field(u8, func)
+		__field(u8, hdr_length)
+		__field(u8, hdr_maint_op_class)
+		__field(u8, event_type)
+		__array(u8, data, CXL_EVENT_RECORD_DATA_LENGTH)
+	),
+
+	TP_fast_assign(
+		__entry->event_type = event_type;
+		__entry->segment = cper_rec->hdr.device_id.segment_num;
+		__entry->bus = cper_rec->hdr.device_id.bus_num;
+		__entry->device = cper_rec->hdr.device_id.device_num;
+		__entry->func = cper_rec->hdr.device_id.func_num;
+		__entry->serial = (((u64)cper_rec->hdr.dev_serial_num.upper_dw) << 32) |
+				 cper_rec->hdr.dev_serial_num.lower_dw;
+		__entry->hdr_length = gen_rec->hdr.length;
+		__entry->hdr_flags = get_unaligned_le24(gen_rec->hdr.flags);
+		__entry->hdr_timestamp = le64_to_cpu(gen_rec->hdr.timestamp);
+		__entry->hdr_maint_op_class = gen_rec->hdr.maint_op_class;
+		memcpy(__entry->data, gen_rec->data, CXL_EVENT_RECORD_DATA_LENGTH);
+	),
+
+	TP_printk("device=%04x:%02x:%02x.%02x serial=%lld : event_type=%d time=%llu "
+		  "len=%d flags=%x maint_op_class=%u : %s",
+		__entry->segment, __entry->bus, __entry->device, __entry->func,
+		__entry->serial, __entry->event_type, __entry->hdr_timestamp,
+		__entry->hdr_length, __entry->hdr_flags, __entry->hdr_maint_op_class,
+		__print_hex(__entry->data, CXL_EVENT_RECORD_DATA_LENGTH))
+
+);
+
 #endif /* _TRACE_HW_EVENT_MC_H */
 
 /* This part must be outside protection */

-- 
2.44.0