[PATCH v7 2/6] cxl/trace: Add TRACE support for CXL media-error records

From: alison . schofield
Date: Fri Feb 17 2023 - 21:19:10 EST


From: Alison Schofield <alison.schofield@xxxxxxxxx>

CXL devices may support the retrieval of a device poison list.
Add a new trace event that the CXL subsystem may use to log
the media-error records returned in the poison list.

Log each media-error record as a trace event of type 'cxl_poison'.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@xxxxxxxxxx>
Signed-off-by: Alison Schofield <alison.schofield@xxxxxxxxx>
---
drivers/cxl/core/mbox.c | 4 +-
drivers/cxl/core/trace.h | 84 ++++++++++++++++++++++++++++++++++++++++
2 files changed, 87 insertions(+), 1 deletion(-)

diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index faa61e5f541f..a3da8b4e92a4 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -1147,7 +1147,9 @@ int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len,
if (rc)
break;

- /* TODO TRACE the media error records */
+ for (int i = 0; i < le16_to_cpu(po->count); i++)
+ trace_cxl_poison(cxlmd, cxlr, &po->record[i],
+ po->flags, po->overflow_t);

/* Protect against an uncleared _FLAG_MORE */
nr_records = nr_records + le16_to_cpu(po->count);
diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index c72ef9321cfe..289fab1a686d 100644
--- a/drivers/cxl/core/trace.h
+++ b/drivers/cxl/core/trace.h
@@ -7,6 +7,7 @@
#define _CXL_EVENTS_H

#include <linux/tracepoint.h>
+#include <linux/pci.h>
#include <asm-generic/unaligned.h>

#include <cxl.h>
@@ -581,6 +582,89 @@ TRACE_EVENT(cxl_memory_module,
)
);

+#define __show_poison_source(source) \
+ __print_symbolic(source, \
+ { CXL_POISON_SOURCE_UNKNOWN, "Unknown" }, \
+ { CXL_POISON_SOURCE_EXTERNAL, "External" }, \
+ { CXL_POISON_SOURCE_INTERNAL, "Internal" }, \
+ { CXL_POISON_SOURCE_INJECTED, "Injected" }, \
+ { CXL_POISON_SOURCE_VENDOR, "Vendor" })
+
+#define show_poison_source(source) \
+ (((source > CXL_POISON_SOURCE_INJECTED) && \
+ (source != CXL_POISON_SOURCE_VENDOR)) ? "Reserved" \
+ : __show_poison_source(source))
+
+#define show_poison_flags(flags) \
+ __print_flags(flags, "|", \
+ { CXL_POISON_FLAG_MORE, "More" }, \
+ { CXL_POISON_FLAG_OVERFLOW, "Overflow" }, \
+ { CXL_POISON_FLAG_SCANNING, "Scanning" })
+
+#define __cxl_poison_addr(record) \
+ (le64_to_cpu(record->address))
+#define cxl_poison_record_dpa(record) \
+ (__cxl_poison_addr(record) & CXL_POISON_START_MASK)
+#define cxl_poison_record_source(record) \
+ (__cxl_poison_addr(record) & CXL_POISON_SOURCE_MASK)
+#define cxl_poison_record_length(record) \
+ (le32_to_cpu(record->length) * CXL_POISON_LEN_MULT)
+#define cxl_poison_overflow(flags, time) \
+ (flags & CXL_POISON_FLAG_OVERFLOW ? le64_to_cpu(time) : 0)
+
+TRACE_EVENT(cxl_poison,
+
+ TP_PROTO(struct cxl_memdev *cxlmd, struct cxl_region *region,
+ const struct cxl_poison_record *record,
+ u8 flags, __le64 overflow_t),
+
+ TP_ARGS(cxlmd, region, record, flags, overflow_t),
+
+ TP_STRUCT__entry(
+ __string(memdev, dev_name(&cxlmd->dev))
+ __string(host, dev_name(cxlmd->dev.parent))
+ __field(u64, serial)
+ __string(region, region)
+ __field(u64, overflow_t)
+ __field(u64, dpa)
+ __field(u32, length)
+ __array(char, uuid, 16)
+ __field(u8, source)
+ __field(u8, flags)
+ ),
+
+ TP_fast_assign(
+ __assign_str(memdev, dev_name(&cxlmd->dev));
+ __assign_str(host, dev_name(cxlmd->dev.parent));
+ __entry->serial = cxlmd->cxlds->serial;
+ __entry->overflow_t = cxl_poison_overflow(flags, overflow_t);
+ __entry->dpa = cxl_poison_record_dpa(record);
+ __entry->length = cxl_poison_record_length(record);
+ __entry->source = cxl_poison_record_source(record);
+ __entry->flags = flags;
+ if (region) {
+ __assign_str(region, dev_name(&region->dev));
+ memcpy(__entry->uuid, &region->params.uuid, 16);
+ } else {
+ __assign_str(region, "");
+ memset(__entry->uuid, 0, 16);
+ }
+ ),
+
+ TP_printk("memdev=%s host=%s serial=%lld region=%s region_uuid=%pU dpa=0x%llx length=0x%x source=%s flags=%s overflow_time=%llu",
+ __get_str(memdev),
+ __get_str(host),
+ __entry->serial,
+ __get_str(region),
+ __entry->uuid,
+ __entry->dpa,
+ __entry->length,
+ show_poison_source(__entry->source),
+ show_poison_flags(__entry->flags),
+ __entry->overflow_t
+ )
+);
+
#endif /* _CXL_EVENTS_H */

#define TRACE_INCLUDE_FILE trace
--
2.37.3