From 9f7c5d04fdee46dbe715f2758152bb1664d4259c Mon Sep 17 00:00:00 2001
From: Arjan van de Ven <arjan at linux.intel.com>
Date: Fri, 26 Nov 2010 12:18:03 -0800
Subject: [PATCH 1/2] vfs: Add a trace point in the mark_inode_dirty function

PowerTOP would like to be able to show who is keeping the disk
busy by dirtying data. The most logical spot for this is in the vfs
in the mark_inode_dirty() function, doing this on the block level
is not possible because by the time the IO hits the block layer the
guilty party can no longer be found ("kjournald" and "pdflush" are not
useful answers to "who caused this file to be dirty).

The trace point follows the same logic/style as the block_dump code
and pretty much dumps the same data, just not to dmesg (and thus to
/var/log/messages) but via the trace events streams.

Eventually we should be able to phase out the block dump code, but that's
for later on after a transition time.
---
 fs/fs-writeback.c                |    3 +++
 include/linux/fs.h               |   11 +++++++++++
 include/trace/events/writeback.h |   28 ++++++++++++++++++++++++++++
 3 files changed, 42 insertions(+), 0 deletions(-)

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 5b4a936..5ef5bb0 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1081,6 +1081,9 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 	if ((inode->i_state & flags) == flags)
 		return;
 
+	if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES))
+		trace_writeback_inode_dirty(inode, flags);
+
 	if (unlikely(block_dump))
 		block_dump___mark_inode_dirty(inode);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 69cd5bb..e0ac37c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1768,6 +1768,18 @@ struct super_operations {
 
 #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
 
+#define INODE_DIRTY_FLAGS \
+	{ I_DIRTY_SYNC,		"DIRTY-SYNC" }, \
+	{ I_DIRTY_DATASYNC,	"DIRTY-DATASYNC" }, \
+	{ I_DIRTY_PAGES,	"DIRTY-PAGES" }, \
+	{ I_NEW,		"NEW" }, \
+	{ I_WILL_FREE,		"WILL-FREE" }, \
+	{ I_FREEING,		"FREEING" }, \
+	{ I_CLEAR,		"CLEAR" }, \
+	{ I_SYNC,		"SYNC" }, \
+	{ I_REFERENCED,		"REFERENCED" }
+
+
 extern void __mark_inode_dirty(struct inode *, int);
 static inline void mark_inode_dirty(struct inode *inode)
 {
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 5973410..5f1e2a3 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -408,6 +408,34 @@ DEFINE_EVENT(writeback_congest_waited_template, writeback_wait_iff_congested,
 	TP_ARGS(usec_timeout, usec_delayed)
 );
 
+/*
+ * Tracepoint for dirtying an inode; used by PowerTOP
+ */
+TRACE_EVENT(writeback_inode_dirty,
+
+	TP_PROTO(struct inode *inode, int flags),
+
+	TP_ARGS(inode, flags),
+
+	TP_STRUCT__entry(
+		__field(	__kernel_dev_t,	dev		)
+		__field(	ino_t,		ino		)
+		__field(	u32,		flags		)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->flags  = flags;
+	),
+
+	TP_printk("dev %d:%d ino %lu flags %d %s", MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino,
+		  __entry->flags,
+		  __print_flags(__entry->flags, "|", INODE_DIRTY_FLAGS)
+	)
+);
+
 DECLARE_EVENT_CLASS(writeback_single_inode_template,
 
 	TP_PROTO(struct inode *inode,
-- 
1.7.8.5