[PATCH-v5 0/5] add support for a lazytime mount option

@@ -397,7 +397,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
 	 * shot. If still dirty, it will be redirty_tail()'ed below.  Update
 	 * the dirty time to prevent enqueue and sync it again.
 	 */
-	if ((inode->i_state & I_DIRTY) &&
+	if ((inode->i_state & I_DIRTY_WB) &&
 	    (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages))
 		inode->dirtied_when = jiffies;
 

@@ -428,13 +428,15 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
 			 */
 			redirty_tail(inode, wb);
 		}
-	} else if (inode->i_state & I_DIRTY) {
+	} else if (inode->i_state & I_DIRTY_WB) {
 		/*
 		 * Filesystems can dirty the inode during writeback operations,
 		 * such as delayed allocation during submission or metadata
 		 * updates after data IO completion.
 		 */
 		redirty_tail(inode, wb);
+	} else if (inode->i_state & I_DIRTY_TIME) {
+		list_move(&inode->i_wb_list, &wb->b_dirty_time);
 	} else {
 		/* The inode is clean. Remove from writeback lists. */
 		list_del_init(&inode->i_wb_list);

@@ -482,11 +484,15 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	/* Clear I_DIRTY_PAGES if we've written out all dirty pages */
 	if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
 		inode->i_state &= ~I_DIRTY_PAGES;
-	dirty = inode->i_state & I_DIRTY;
-	inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC);
+	dirty = inode->i_state & (I_DIRTY_SYNC | I_DIRTY_DATASYNC);
+	if (dirty && (inode->i_state & I_DIRTY_TIME))
+		dirty |= I_DIRTY_TIME;
+	inode->i_state &= ~dirty;
 	spin_unlock(&inode->i_lock);
+	if (dirty & I_DIRTY_TIME)
+		mark_inode_dirty_sync(inode);
 	/* Don't write the inode if only I_DIRTY_PAGES was set */
-	if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
+	if (dirty) {
 		int err = write_inode(inode, wbc);
 		if (ret == 0)
 			ret = err;

@@ -1162,7 +1168,11 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 
 	spin_lock(&inode->i_lock);
 	if ((inode->i_state & flags) != flags) {
-		const int was_dirty = inode->i_state & I_DIRTY;
+		const int was_dirty = inode->i_state & I_DIRTY_WB;
+
+		if ((flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) &&
+		    (inode->i_state & I_DIRTY_TIME))
+			inode->i_state &= ~I_DIRTY_TIME;
 
 		inode->i_state |= flags;
 

@@ -1224,6 +1234,24 @@ out_unlock_inode:
 }
 EXPORT_SYMBOL(__mark_inode_dirty);
 
+void inode_requeue_dirtytime(struct inode *inode)
+{
+	struct backing_dev_info *bdi = inode_to_bdi(inode);
+
+	spin_lock(&bdi->wb.list_lock);
+	spin_lock(&inode->i_lock);
+	if ((inode->i_state & I_DIRTY_WB) == 0) {
+		if (inode->i_state & I_DIRTY_TIME)
+			list_move(&inode->i_wb_list, &bdi->wb.b_dirty_time);
+		else
+			list_del_init(&inode->i_wb_list);
+	}
+	spin_unlock(&inode->i_lock);
+	spin_unlock(&bdi->wb.list_lock);
+
+}
+EXPORT_SYMBOL(inode_requeue_dirtytime);
+
 static void wait_sb_inodes(struct super_block *sb)
 {
 	struct inode *inode, *old_inode = NULL;

@@ -1277,6 +1305,29 @@ static void wait_sb_inodes(struct super_block *sb)
 	iput(old_inode);
 }
 
+/*
+ * Take all of the indoes on the dirty_time list, and mark them as
+ * dirty, so they will be written out.
+ */
+static void flush_sb_dirty_time(struct super_block *sb)
+{
+	struct bdi_writeback *wb = &sb->s_bdi->wb;
+	LIST_HEAD(tmp);
+
+	spin_lock(&wb->list_lock);
+	list_cut_position(&tmp, &wb->b_dirty_time, wb->b_dirty_time.prev);
+	while (!list_empty(&tmp)) {
+		struct inode *inode = wb_inode(tmp.prev);
+
+		list_del_init(&inode->i_wb_list);
+		spin_unlock(&wb->list_lock);
+		if (inode->i_state & I_DIRTY_TIME)
+			mark_inode_dirty_sync(inode);
+		spin_lock(&wb->list_lock);
+	}
+	spin_unlock(&wb->list_lock);
+}
+
 /**
  * writeback_inodes_sb_nr -	writeback dirty inodes from given super_block
  * @sb: the superblock

@@ -1388,6 +1439,7 @@ void sync_inodes_sb(struct super_block *sb)
 		return;
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
 
+	flush_sb_dirty_time(sb);
 	bdi_queue_work(sb->s_bdi, &work);
 	wait_for_completion(&done);
 

@@ -30,7 +30,7 @@
  * inode_sb_list_lock protects:
  *   sb->s_inodes, inode->i_sb_list
  * bdi->wb.list_lock protects:
- *   bdi->wb.b_{dirty,io,more_io}, inode->i_wb_list
+ *   bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_wb_list
  * inode_hash_lock protects:
  *   inode_hashtable, inode->i_hash
  *

@@ -1430,11 +1430,19 @@ static void iput_final(struct inode *inode)
  */
 void iput(struct inode *inode)
 {
-	if (inode) {
-		BUG_ON(inode->i_state & I_CLEAR);
-
-		if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock))
-			iput_final(inode);
+	if (!inode)
+		return;
+	BUG_ON(inode->i_state & I_CLEAR);
+retry:
+	if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock)) {
+		if (inode->i_nlink && (inode->i_state & I_DIRTY_TIME)) {
+			atomic_inc(&inode->i_count);
+			inode->i_state &= ~I_DIRTY_TIME;
+			spin_unlock(&inode->i_lock);
+			mark_inode_dirty_sync(inode);
+			goto retry;
+		}
+		iput_final(inode);
 	}
 }
 EXPORT_SYMBOL(iput);

@@ -1510,6 +1518,27 @@ static int update_time(struct inode *inode, struct timespec *time, int flags)
 		inode->i_ctime = *time;
 	if (flags & S_MTIME)
 		inode->i_mtime = *time;
+
+	if ((inode->i_sb->s_flags & MS_LAZYTIME) &&
+	    !(flags & S_VERSION) &&
+	    !(inode->i_state & I_DIRTY_WB)) {
+		if (inode->i_state & I_DIRTY_TIME)
+			return 0;
+		spin_lock(&inode->i_lock);
+		if (inode->i_state & I_DIRTY_WB) {
+			spin_unlock(&inode->i_lock);
+			goto force_dirty;
+		}
+		if (inode->i_state & I_DIRTY_TIME) {
+			spin_unlock(&inode->i_lock);
+			return 0;
+		}
+		inode->i_state |= I_DIRTY_TIME;
+		spin_unlock(&inode->i_lock);
+		inode_requeue_dirtytime(inode);
+		return 0;
+	}
+force_dirty:
 	mark_inode_dirty_sync(inode);
 	return 0;
 }

@@ -1066,7 +1066,7 @@ struct inode *alloc_anon_inode(struct super_block *s)
 	 * list because mark_inode_dirty() will think
 	 * that it already _is_ on the dirty list.
 	 */
-	inode->i_state = I_DIRTY;
+	inode->i_state = I_DIRTY_WB;
 	inode->i_mode = S_IRUSR | S_IWUSR;
 	inode->i_uid = current_fsuid();
 	inode->i_gid = current_fsgid();

@@ -2187,7 +2187,7 @@ void logfs_evict_inode(struct inode *inode)
 	 * aliases, which are moved back.  No write to the medium happens.
 	 */
 	/* Only deleted files may be dirty at this point */
-	BUG_ON(inode->i_state & I_DIRTY && inode->i_nlink);
+	BUG_ON(inode->i_state & I_DIRTY_WB && inode->i_nlink);
 	if (!block)
 		return;
 	if ((logfs_super(sb)->s_flags & LOGFS_SB_FLAG_SHUTDOWN)) {

@@ -915,7 +915,7 @@ static int wait_for_concurrent_writes(struct file *file)
 		dprintk("nfsd: write resume %d\n", task_pid_nr(current));
 	}
 
-	if (inode->i_state & I_DIRTY) {
+	if (inode->i_state & I_DIRTY_WB) {
 		dprintk("nfsd: write sync %d\n", task_pid_nr(current));
 		err = vfs_fsync(file, 0);
 	}

@@ -660,7 +660,7 @@ static struct inode * get_pipe_inode(void)
 	 * list because "mark_inode_dirty()" will think
 	 * that it already _is_ on the dirty list.
 	 */
-	inode->i_state = I_DIRTY;
+	inode->i_state = I_DIRTY_WB;
 	inode->i_mode = S_IFIFO | S_IRUSR | S_IWUSR;
 	inode->i_uid = current_fsuid();
 	inode->i_gid = current_fsgid();

@@ -44,6 +44,7 @@ static int show_sb_opts(struct seq_file *m, struct super_block *sb)
 		{ MS_SYNCHRONOUS, ",sync" },
 		{ MS_DIRSYNC, ",dirsync" },
 		{ MS_MANDLOCK, ",mand" },
+		{ MS_LAZYTIME, ",lazytime" },
 		{ 0, NULL }
 	};
 	const struct proc_fs_info *fs_infop;

@@ -177,8 +177,16 @@ SYSCALL_DEFINE1(syncfs, int, fd)
  */
 int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync)
 {
+	struct inode *inode = file->f_mapping->host;
+
 	if (!file->f_op->fsync)
 		return -EINVAL;
+	if (!datasync && (inode->i_state & I_DIRTY_TIME)) {
+		spin_lock(&inode->i_lock);
+		inode->i_state &= ~I_DIRTY_TIME;
+		spin_unlock(&inode->i_lock);
+		mark_inode_dirty_sync(inode);
+	}
 	return file->f_op->fsync(file, start, end, datasync);
 }
 EXPORT_SYMBOL(vfs_fsync_range);

@@ -477,7 +477,7 @@ int ufs_truncate(struct inode *inode, loff_t old_i_size)
 		retry |= ufs_trunc_tindirect (inode);
 		if (!retry)
 			break;
-		if (IS_SYNC(inode) && (inode->i_state & I_DIRTY))
+		if (IS_SYNC(inode) && (inode->i_state & I_DIRTY_WB))
 			ufs_sync_inode (inode);
 		yield();
 	}

@@ -55,6 +55,7 @@ struct bdi_writeback {
 	struct list_head b_dirty;	/* dirty inodes */
 	struct list_head b_io;		/* parked for writeback */
 	struct list_head b_more_io;	/* parked for more writeback */
+	struct list_head b_dirty_time;	/* time stamps are dirty */
 	spinlock_t list_lock;		/* protects the b_* lists */
 };
 

@@ -1720,19 +1720,26 @@ struct super_operations {
 #define __I_DIO_WAKEUP		9
 #define I_DIO_WAKEUP		(1 << I_DIO_WAKEUP)
 #define I_LINKABLE		(1 << 10)
+#define I_DIRTY_TIME		(1 << 11)
 
-#define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
+/* Inode should be on the b_dirty/b_io/b_more_io lists */
+#define I_DIRTY_WB (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
+/* Inode should be on the b_dirty/b_io/b_more_io/b_dirty_time lists */
+#define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES | I_DIRTY_TIME)
+/* The inode itself is dirty  */
+#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_TIME)
 
 extern void __mark_inode_dirty(struct inode *, int);
 static inline void mark_inode_dirty(struct inode *inode)
 {
-	__mark_inode_dirty(inode, I_DIRTY);
+	__mark_inode_dirty(inode, I_DIRTY_WB);
 }
 
 static inline void mark_inode_dirty_sync(struct inode *inode)
 {
 	__mark_inode_dirty(inode, I_DIRTY_SYNC);
 }
+extern void inode_requeue_dirtytime(struct inode *);
 
 extern void inc_nlink(struct inode *inode);
 extern void drop_nlink(struct inode *inode);

@@ -90,6 +90,7 @@ struct inodes_stat_t {
 #define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
 #define MS_I_VERSION	(1<<23) /* Update inode I_version field */
 #define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
+#define MS_LAZYTIME	(1<<25) /* Update the on-disk [acm]times lazily */
 
 /* These sb flags are internal to the kernel */
 #define MS_NOSEC	(1<<28)

@@ -69,10 +69,10 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 	unsigned long background_thresh;
 	unsigned long dirty_thresh;
 	unsigned long bdi_thresh;
-	unsigned long nr_dirty, nr_io, nr_more_io;
+	unsigned long nr_dirty, nr_io, nr_more_io, nr_dirty_time;
 	struct inode *inode;
 
-	nr_dirty = nr_io = nr_more_io = 0;
+	nr_dirty = nr_io = nr_more_io = nr_dirty_time = 0;
 	spin_lock(&wb->list_lock);
 	list_for_each_entry(inode, &wb->b_dirty, i_wb_list)
 		nr_dirty++;

@@ -80,6 +80,9 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 		nr_io++;
 	list_for_each_entry(inode, &wb->b_more_io, i_wb_list)
 		nr_more_io++;
+	list_for_each_entry(inode, &wb->b_dirty_time, i_wb_list)
+		if (inode->i_state & I_DIRTY_TIME)
+			nr_dirty_time++;
 	spin_unlock(&wb->list_lock);
 
 	global_dirty_limits(&background_thresh, &dirty_thresh);

@@ -98,6 +101,7 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 		   "b_dirty:            %10lu\n"
 		   "b_io:               %10lu\n"
 		   "b_more_io:          %10lu\n"
+		   "b_dirty_time:       %10lu\n"
 		   "bdi_list:           %10u\n"
 		   "state:              %10lx\n",
 		   (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)),

@@ -111,6 +115,7 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 		   nr_dirty,
 		   nr_io,
 		   nr_more_io,
+		   nr_dirty_time,
 		   !list_empty(&bdi->bdi_list), bdi->state);
 #undef K
 

@@ -418,6 +423,7 @@ static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
 	INIT_LIST_HEAD(&wb->b_dirty);
 	INIT_LIST_HEAD(&wb->b_io);
 	INIT_LIST_HEAD(&wb->b_more_io);
+	INIT_LIST_HEAD(&wb->b_dirty_time);
 	spin_lock_init(&wb->list_lock);
 	INIT_DELAYED_WORK(&wb->dwork, bdi_writeback_workfn);
 }

@@ -1147,6 +1147,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 	if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
 		trace_writeback_dirty_inode_start(inode, flags);
 
+		inode->i_ts_dirty_day = 0;
 		if (sb->s_op->dirty_inode)
 			sb->s_op->dirty_inode(inode, flags);
 

@@ -1507,6 +1507,9 @@ static int relatime_need_update(struct vfsmount *mnt, struct inode *inode,
  */
 static int update_time(struct inode *inode, struct timespec *time, int flags)
 {
+	struct timespec uptime;
+	unsigned short days_since_boot;
+
 	if (inode->i_op->update_time)
 		return inode->i_op->update_time(inode, time, flags);
 

@@ -1524,6 +1527,22 @@ static int update_time(struct inode *inode, struct timespec *time, int flags)
 	    !(inode->i_state & I_DIRTY_WB)) {
 		if (inode->i_state & I_DIRTY_TIME)
 			return 0;
+		get_monotonic_boottime(&uptime);
+		days_since_boot = div_u64(uptime.tv_sec, 86400);
+		/*
+		 * If i_ts_dirty_day is zero, then either we have not
+		 * deferred timestamp updates, or the system has been
+		 * up for less than a day (so days_since_boot is
+		 * zero), so we can defer timestamp updates in that
+		 * case.  If a day or more has passed, then
+		 * i_ts_dirty_day will be different from
+		 * days_since_boot, and then we should update the
+		 * on-disk inode and then we can clear i_ts_dirty_day.
+		 */
+		if (inode->i_ts_dirty_day &&
+		    (inode->i_ts_dirty_day != days_since_boot))
+			goto force_dirty;
+
 		spin_lock(&inode->i_lock);
 		if (inode->i_state & I_DIRTY_WB) {
 			spin_unlock(&inode->i_lock);

@@ -1534,6 +1553,7 @@ static int update_time(struct inode *inode, struct timespec *time, int flags)
 			return 0;
 		}
 		inode->i_state |= I_DIRTY_TIME;
+		inode->i_ts_dirty_day = days_since_boot;
 		spin_unlock(&inode->i_lock);
 		inode_requeue_dirtytime(inode);
 		return 0;

@@ -575,6 +575,7 @@ struct inode {
 	struct timespec		i_ctime;
 	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
 	unsigned short          i_bytes;
+	unsigned short		i_ts_dirty_day;
 	unsigned int		i_blkbits;
 	blkcnt_t		i_blocks;
 

@@ -253,7 +253,7 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t)
  */
 static int move_expired_inodes(struct list_head *delaying_queue,
 			       struct list_head *dispatch_queue,
-			       struct wb_writeback_work *work)
+			       unsigned long *older_than_this)
 {
 	LIST_HEAD(tmp);
 	struct list_head *pos, *node;

@@ -264,8 +264,8 @@ static int move_expired_inodes(struct list_head *delaying_queue,
 
 	while (!list_empty(delaying_queue)) {
 		inode = wb_inode(delaying_queue->prev);
-		if (work->older_than_this &&
-		    inode_dirtied_after(inode, *work->older_than_this))
+		if (older_than_this &&
+		    inode_dirtied_after(inode, *older_than_this))
 			break;
 		list_move(&inode->i_wb_list, &tmp);
 		moved++;

@@ -309,9 +309,14 @@ out:
 static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work)
 {
 	int moved;
+	unsigned long one_day_later = jiffies + (HZ * 86400);
+
 	assert_spin_locked(&wb->list_lock);
 	list_splice_init(&wb->b_more_io, &wb->b_io);
-	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, work);
+	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io,
+				    work->older_than_this);
+	moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io,
+				     &one_day_later);
 	trace_writeback_queue_io(wb, work, moved);
 }
 

@@ -679,6 +684,17 @@ static long writeback_sb_inodes(struct super_block *sb,
 		inode->i_state |= I_SYNC;
 		spin_unlock(&inode->i_lock);
 
+		/*
+		 * If the inode is marked dirty time but is not dirty,
+		 * then at last for ext3 and ext4 we need to call
+		 * mark_inode_dirty_sync in order to get the inode
+		 * timestamp transferred to the on disk inode, since
+		 * write_inode is a no-op for those file systems.
+		 */
+		if ((inode->i_state & I_DIRTY_TIME) &&
+		    ((inode->i_state & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) == 0))
+			mark_inode_dirty_sync(inode);
+
 		write_chunk = writeback_chunk_size(wb->bdi, work);
 		wbc.nr_to_write = write_chunk;
 		wbc.pages_skipped = 0;

@@ -1237,9 +1253,10 @@ void inode_requeue_dirtytime(struct inode *inode)
 	spin_lock(&bdi->wb.list_lock);
 	spin_lock(&inode->i_lock);
 	if ((inode->i_state & I_DIRTY_WB) == 0) {
-		if (inode->i_state & I_DIRTY_TIME)
+		if (inode->i_state & I_DIRTY_TIME) {
+			inode->dirtied_when = jiffies;
 			list_move(&inode->i_wb_list, &bdi->wb.b_dirty_time);
-		else
+		} else
 			list_del_init(&inode->i_wb_list);
 	}
 	spin_unlock(&inode->i_lock);

@@ -27,6 +27,7 @@
 #include <linux/backing-dev.h>
 #include <linux/tracepoint.h>
 #include <linux/device.h>
+#include <trace/events/fs.h>
 #include "internal.h"
 
 /*

@@ -20,6 +20,9 @@
 #include <linux/list_lru.h>
 #include "internal.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/fs.h>
+
 /*
  * Inode locking rules:
  *

@@ -1440,6 +1443,7 @@ retry:
 			inode->i_state &= ~I_DIRTY_TIME;
 			spin_unlock(&inode->i_lock);
 			mark_inode_dirty_sync(inode);
+			trace_fs_lazytime_iput(inode);
 			goto retry;
 		}
 		iput_final(inode);

@@ -1556,6 +1560,7 @@ static int update_time(struct inode *inode, struct timespec *time, int flags)
 		inode->i_ts_dirty_day = days_since_boot;
 		spin_unlock(&inode->i_lock);
 		inode_requeue_dirtytime(inode);
+		trace_fs_lazytime_defer(inode);
 		return 0;
 	}
 force_dirty:

@@ -0,0 +1,56 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM fs
+
+#if !defined(_TRACE_FS_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_FS_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(fs__inode,
+	TP_PROTO(struct inode *inode),
+
+	TP_ARGS(inode),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	uid_t,	uid			)
+		__field(	gid_t,	gid			)
+		__field(	__u16, mode			)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->uid	= i_uid_read(inode);
+		__entry->gid	= i_gid_read(inode);
+		__entry->mode	= inode->i_mode;
+	),
+
+	TP_printk("dev %d,%d ino %lu mode 0%o uid %u gid %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino, __entry->mode,
+		  __entry->uid, __entry->gid)
+);
+
+DEFINE_EVENT(fs__inode, fs_lazytime_defer,
+	TP_PROTO(struct inode *inode),
+
+	TP_ARGS(inode)
+);
+
+DEFINE_EVENT(fs__inode, fs_lazytime_iput,
+	TP_PROTO(struct inode *inode),
+
+	TP_ARGS(inode)
+);
+
+DEFINE_EVENT(fs__inode, fs_lazytime_flush,
+	TP_PROTO(struct inode *inode),
+
+	TP_ARGS(inode)
+);
+#endif /* _TRACE_FS_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

@@ -1283,6 +1283,56 @@ struct inode *ilookup(struct super_block *sb, unsigned long ino)
 }
 EXPORT_SYMBOL(ilookup);
 
+/**
+ * find_inode_nowait - find an inode in the inode cache
+ * @sb:		super block of file system to search
+ * @hashval:	hash value (usually inode number) to search for
+ * @match:	callback used for comparisons between inodes
+ * @data:	opaque data pointer to pass to @match
+ *
+ * Search for the inode specified by @hashval and @data in the inode
+ * cache, where the helper function @match will return 0 if the inode
+ * does not match, 1 if the inode does match, and -1 if the search
+ * should be stopped.  The @match function must be responsible for
+ * taking the i_lock spin_lock and checking i_state for an inode being
+ * freed or being initialized, and incrementing the reference count
+ * before returning 1.  It also must not sleep, since it is called with
+ * the inode_hash_lock spinlock held.
+ *
+ * This is a even more generalized version of ilookup5() when the
+ * function must never block --- find_inode() can block in
+ * __wait_on_freeing_inode() --- or when the caller can not increment
+ * the reference count because the resulting iput() might cause an
+ * inode eviction().  The tradeoff is that the @match funtion must be
+ * very carefully implemented.
+ */
+struct inode *find_inode_nowait(struct super_block *sb,
+				unsigned long hashval,
+				int (*match)(struct inode *, unsigned long,
+					     void *),
+				void *data)
+{
+	struct hlist_head *head = inode_hashtable + hash(sb, hashval);
+	struct inode *inode, *ret_inode = NULL;
+	int mval;
+
+	spin_lock(&inode_hash_lock);
+	hlist_for_each_entry(inode, head, i_hash) {
+		if (inode->i_sb != sb)
+			continue;
+		mval = match(inode, hashval, data);
+		if (mval == 0)
+			continue;
+		if (mval == 1)
+			ret_inode = inode;
+		goto out;
+	}
+out:
+	spin_unlock(&inode_hash_lock);
+	return ret_inode;
+}
+EXPORT_SYMBOL(find_inode_nowait);
+
 int insert_inode_locked(struct inode *inode)
 {
 	struct super_block *sb = inode->i_sb;

@@ -2418,6 +2418,11 @@ extern struct inode *ilookup(struct super_block *sb, unsigned long ino);
 
 extern struct inode * iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *);
 extern struct inode * iget_locked(struct super_block *, unsigned long);
+extern struct inode *find_inode_nowait(struct super_block *,
+				       unsigned long,
+				       int (*match)(struct inode *,
+						    unsigned long, void *),
+				       void *data);
 extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *);
 extern int insert_inode_locked(struct inode *);
 #ifdef CONFIG_DEBUG_LOCK_ALLOC

@@ -4139,6 +4139,66 @@ static int ext4_inode_blocks_set(handle_t *handle,
 	return 0;
 }
 
+struct other_inode {
+	unsigned long		orig_ino;
+	struct ext4_inode	*raw_inode;
+};
+
+static int other_inode_match(struct inode * inode, unsigned long ino,
+			     void *data)
+{
+	struct other_inode *oi = (struct other_inode *) data;
+
+	if ((inode->i_ino != ino) ||
+	    (inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW |
+			       I_DIRTY_SYNC | I_DIRTY_DATASYNC)) ||
+	    ((inode->i_state & I_DIRTY_TIME) == 0))
+		return 0;
+	spin_lock(&inode->i_lock);
+	if (((inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW |
+				I_DIRTY_SYNC | I_DIRTY_DATASYNC)) == 0) &&
+	    (inode->i_state & I_DIRTY_TIME)) {
+		struct ext4_inode_info	*ei = EXT4_I(inode);
+
+		inode->i_state &= ~I_DIRTY_TIME;
+		inode->i_ts_dirty_day = 0;
+		spin_unlock(&inode->i_lock);
+
+		spin_lock(&ei->i_raw_lock);
+		EXT4_INODE_SET_XTIME(i_ctime, inode, oi->raw_inode);
+		EXT4_INODE_SET_XTIME(i_mtime, inode, oi->raw_inode);
+		EXT4_INODE_SET_XTIME(i_atime, inode, oi->raw_inode);
+		ext4_inode_csum_set(inode, oi->raw_inode, ei);
+		spin_unlock(&ei->i_raw_lock);
+		trace_ext4_other_inode_update_time(inode, oi->orig_ino);
+		return -1;
+	}
+	spin_unlock(&inode->i_lock);
+	return -1;
+}
+
+/*
+ * Opportunistically update the other time fields for other inodes in
+ * the same inode table block.
+ */
+static void ext4_update_other_inodes_time(struct super_block *sb,
+					  unsigned long orig_ino, char *buf)
+{
+	struct other_inode oi;
+	unsigned long ino;
+	int i, inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
+	int inode_size = EXT4_INODE_SIZE(sb);
+
+	oi.orig_ino = orig_ino;
+	ino = orig_ino & ~(inodes_per_block - 1);
+	for (i = 0; i < inodes_per_block; i++, ino++, buf += inode_size) {
+		if (ino == orig_ino)
+			continue;
+		oi.raw_inode = (struct ext4_inode *) buf;
+		(void) find_inode_nowait(sb, ino, other_inode_match, &oi);
+	}
+}
+
 /*
  * Post the struct inode info into an on-disk inode location in the
  * buffer-cache.  This gobbles the caller's reference to the