mm: trace filemap add and del

Use the events API to trace filemap loading and unloading of file pieces
into the page cache.

This patch aims at tracing the eviction reload cycle of executable and
shared libraries pages in a memory constrained environment.

The typical usage is to spot a specific device and inode (for example
/lib/libc.so) to see the eviction cycles, and find out if frequently
used code is rather spread across many pages (bad) or coallesced (good).

Signed-off-by: Robert Jarzmik <[email protected]>
Cc: Dave Chinner <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Steven Rostedt <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Cc: Ingo Molnar <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

2 files changed, 63 insertions, 0 deletions

diff --git a/include/trace/events/filemap.h b/include/trace/events/filemap.h
new file mode 100644
index 000000000000..0421f49a20f7
--- /dev/null
+++ b/include/trace/events/filemap.h
@@ -0,0 +1,58 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM filemap
+
+#if !defined(_TRACE_FILEMAP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_FILEMAP_H
+
+#include <linux/types.h>
+#include <linux/tracepoint.h>
+#include <linux/mm.h>
+#include <linux/memcontrol.h>
+#include <linux/device.h>
+#include <linux/kdev_t.h>
+
+DECLARE_EVENT_CLASS(mm_filemap_op_page_cache,
+
+	TP_PROTO(struct page *page),
+
+	TP_ARGS(page),
+
+	TP_STRUCT__entry(
+		__field(struct page *, page)
+		__field(unsigned long, i_ino)
+		__field(unsigned long, index)
+		__field(dev_t, s_dev)
+	),
+
+	TP_fast_assign(
+		__entry->page = page;
+		__entry->i_ino = page->mapping->host->i_ino;
+		__entry->index = page->index;
+		if (page->mapping->host->i_sb)
+			__entry->s_dev = page->mapping->host->i_sb->s_dev;
+		else
+			__entry->s_dev = page->mapping->host->i_rdev;
+	),
+
+	TP_printk("dev %d:%d ino %lx page=%p pfn=%lu ofs=%lu",
+		MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
+		__entry->i_ino,
+		__entry->page,
+		page_to_pfn(__entry->page),
+		__entry->index << PAGE_SHIFT)
+);
+
+DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_delete_from_page_cache,
+	TP_PROTO(struct page *page),
+	TP_ARGS(page)
+	);
+
+DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_add_to_page_cache,
+	TP_PROTO(struct page *page),
+	TP_ARGS(page)
+	);
+
+#endif /* _TRACE_FILEMAP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/mm/filemap.c b/mm/filemap.c
index e1979fdca805..2581826409f2 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -35,6 +35,9 @@
 #include <linux/cleancache.h>
 #include "internal.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/filemap.h>
+
 /*
  * FIXME: remove all knowledge of the buffer layer from the core VM
  */
@@ -113,6 +116,7 @@ void __delete_from_page_cache(struct page *page)
 {
 	struct address_space *mapping = page->mapping;
 
+	trace_mm_filemap_delete_from_page_cache(page);
 	/*
 	 * if we're uptodate, flush out into the cleancache, otherwise
 	 * invalidate any existing cleancache entries.  We can't leave
@@ -464,6 +468,7 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
 			mapping->nrpages++;
 			__inc_zone_page_state(page, NR_FILE_PAGES);
 			spin_unlock_irq(&mapping->tree_lock);
+			trace_mm_filemap_add_to_page_cache(page);
 		} else {
 			page->mapping = NULL;
 			/* Leave page->index set: truncation relies upon it */