Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1268553

[PATCH 2/3] mm/page_isolation: add new tracepoint, test_pages_isolated

Show all headers | View raw

cma allocation should be guranteeded to succeed, but, sometimes,
it could be failed in current implementation. To track down
the problem, we need to know which page is problematic and
this new tracepoint will report it.

Acked-by: Michal Nazarewicz <mina86@mina86.com>
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
---
 include/trace/events/page_isolation.h | 38 +++++++++++++++++++++++++++++++++++
 mm/page_isolation.c                   |  5 +++++
 2 files changed, 43 insertions(+)
 create mode 100644 include/trace/events/page_isolation.h

diff --git a/include/trace/events/page_isolation.h b/include/trace/events/page_isolation.h
new file mode 100644
index 0000000..6fb6440
--- /dev/null
+++ b/include/trace/events/page_isolation.h
@@ -0,0 +1,38 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM page_isolation
+
+#if !defined(_TRACE_PAGE_ISOLATION_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_PAGE_ISOLATION_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(test_pages_isolated,
+
+	TP_PROTO(
+		unsigned long start_pfn,
+		unsigned long end_pfn,
+		unsigned long fin_pfn),
+
+	TP_ARGS(start_pfn, end_pfn, fin_pfn),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, start_pfn)
+		__field(unsigned long, end_pfn)
+		__field(unsigned long, fin_pfn)
+	),
+
+	TP_fast_assign(
+		__entry->start_pfn = start_pfn;
+		__entry->end_pfn = end_pfn;
+		__entry->fin_pfn = fin_pfn;
+	),
+
+	TP_printk("start_pfn=0x%lx end_pfn=0x%lx fin_pfn=0x%lx ret=%s",
+		__entry->start_pfn, __entry->end_pfn, __entry->fin_pfn,
+		__entry->end_pfn == __entry->fin_pfn ? "success" : "fail")
+);
+
+#endif /* _TRACE_PAGE_ISOLATION_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 029a171..f484b93 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -9,6 +9,9 @@
 #include <linux/hugetlb.h>
 #include "internal.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/page_isolation.h>
+
 static int set_migratetype_isolate(struct page *page,
 				bool skip_hwpoisoned_pages)
 {
@@ -268,6 +271,8 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
 						skip_hwpoisoned_pages);
 	spin_unlock_irqrestore(&zone->lock, flags);
 
+	trace_test_pages_isolated(start_pfn, end_pfn, pfn);
+
 	return pfn < end_pfn ? -EBUSY : 0;
 }
 
-- 
1.9.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[PATCH 1/3] mm/page_isolation: return last tested pfn rather than failure indicator Joonsoo Kim <js1304@gmail.com> - 2015-11-13 03:30 +0100
  [PATCH 2/3] mm/page_isolation: add new tracepoint, test_pages_isolated Joonsoo Kim <js1304@gmail.com> - 2015-11-13 03:30 +0100
    Re: [PATCH 2/3] mm/page_isolation: add new tracepoint,  test_pages_isolated David Rientjes <rientjes@google.com> - 2015-11-14 00:00 +0100
  [PATCH 3/3] mm/cma: always check which page cause allocation failure Joonsoo Kim <js1304@gmail.com> - 2015-11-13 03:30 +0100

csiph-web