Memory-failure as the high level machine check handler, it's necessary
to report memory page recovery action result to user space by ftrace.
This patch add a event at ras group for memory-failure.
The output like below:
# tracer: nop
#
# entries-in-buffer/entries-written: 2/2 #P:24
#
# _-----=> irqs-off
# / _----=> need-resched
# | / _---=> hardirq/softirq
# || / _--=> preempt-depth
# ||| / delay
# TASK-PID CPU# |||| TIMESTAMP FUNCTION
# | | | |||| | |
mce-inject-13150 [001] .... 277.019359: memory_failure_event: pfn
0x19869: free buddy page recovery: Delayed
---
v1->v2:
- Comment update
- Just passing 'result' instead of 'action_name[result]',
suggested by Steve. And hard coded there because trace-cmd
and perf do not have a way to process enums.
Cc: Tony Luck <tony.l...@intel.com>
Cc: Steven Rostedt <rost...@goodmis.org>
Signed-off-by: Xie XiuQi <xiexi...@huawei.com>
---
include/ras/ras_event.h | 38 ++++++++++++++++++++++++++++++++++++++
mm/memory-failure.c | 3 +++
2 files changed, 41 insertions(+)
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index 79abb9c..ebb05f3 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -232,6 +232,44 @@ TRACE_EVENT(aer_event,
__print_flags(__entry->status, "|", aer_uncorrectable_errors))
);
+/*
+ * memory-failure recovery action result event
+ *
+ * unsigned long pfn - Page Number of the corrupted page
+ * char * action - Recovery action for various type of pages
+ * int result - Action result
+ *
+ * NOTE: 'action' and 'result' are defined at mm/memory-failure.c
+ */
+TRACE_EVENT(memory_failure_event,
+ TP_PROTO(const unsigned long pfn,
+ const char *action,
+ const int result),
+
+ TP_ARGS(pfn, action, result),
+
+ TP_STRUCT__entry(
+ __field(unsigned long, pfn)
+ __string(action, action)
+ __field(int, result)
+ ),
+
+ TP_fast_assign(
+ __entry->pfn = pfn;
+ __assign_str(action, action);
+ __entry->result = result;
+ ),
+
+ TP_printk("pfn %#lx: %s page recovery: %s",
+ __entry->pfn,
+ __get_str(action),
+ __print_symbolic(__entry->result,
+ {0, "Ignored"},
+ {1, "Failed"},
+ {2, "Delayed"},
+ {3, "Recovered"})
+ )
+);
#endif /* _TRACE_HW_EVENT_MC_H */
/* This part must be outside protection */
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index feb803b..3a71668 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -56,6 +56,7 @@
#include <linux/mm_inline.h>
#include <linux/kfifo.h>
#include "internal.h"
+#include <ras/ras_event.h>
int sysctl_memory_failure_early_kill __read_mostly = 0;
@@ -844,6 +845,8 @@ static struct page_state {
*/
static void action_result(unsigned long pfn, char *msg, int result)
{
+ trace_memory_failure_event(pfn, msg, result);
+
pr_err("MCE %#lx: %s page recovery: %s\n",
pfn, msg, action_name[result]);
}
--
1.8.3.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
