Merge branch 'lazytime' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull lazytime mount option support from Al Viro:
 "Lazytime stuff from tytso"

* 'lazytime' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  ext4: add optimization for the lazytime mount option
  vfs: add find_inode_nowait() function
  vfs: add support for a lazytime mount option

fs/ext4/inode.c

@@ -4174,6 +4174,65 @@ 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 | I_DIRTY_TIME_EXPIRED);
+		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
@@ -4283,10 +4342,11 @@ static int ext4_do_update_inode(handle_t *handle,
 				cpu_to_le16(ei->i_extra_isize);
 		}
 	}
-
 	ext4_inode_csum_set(inode, raw_inode, ei);
-
 	spin_unlock(&ei->i_raw_lock);
+	if (inode->i_sb->s_flags & MS_LAZYTIME)
+		ext4_update_other_inodes_time(inode->i_sb, inode->i_ino,
+					      bh->b_data);
 
 	BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
 	rc = ext4_handle_dirty_metadata(handle, NULL, bh);
@@ -4875,11 +4935,17 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
  * If the inode is marked synchronous, we don't honour that here - doing
  * so would cause a commit on atime updates, which we don't bother doing.
  * We handle synchronous inodes at the highest possible level.
+ *
+ * If only the I_DIRTY_TIME flag is set, we can skip everything.  If
+ * I_DIRTY_TIME and I_DIRTY_SYNC is set, the only inode fields we need
+ * to copy into the on-disk inode structure are the timestamp files.
  */
 void ext4_dirty_inode(struct inode *inode, int flags)
 {
 	handle_t *handle;
 
+	if (flags == I_DIRTY_TIME)
+		return;
 	handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
 	if (IS_ERR(handle))
 		goto out;

fs/ext4/super.c

@@ -1126,6 +1126,7 @@ enum {
 	Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
 	Opt_usrquota, Opt_grpquota, Opt_i_version, Opt_dax,
 	Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
+	Opt_lazytime, Opt_nolazytime,
 	Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
 	Opt_inode_readahead_blks, Opt_journal_ioprio,
 	Opt_dioread_nolock, Opt_dioread_lock,
@@ -1190,6 +1191,8 @@ static const match_table_t tokens = {
 	{Opt_dax, "dax"},
 	{Opt_stripe, "stripe=%u"},
 	{Opt_delalloc, "delalloc"},
+	{Opt_lazytime, "lazytime"},
+	{Opt_nolazytime, "nolazytime"},
 	{Opt_nodelalloc, "nodelalloc"},
 	{Opt_removed, "mblk_io_submit"},
 	{Opt_removed, "nomblk_io_submit"},
@@ -1448,6 +1451,12 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 	case Opt_i_version:
 		sb->s_flags |= MS_I_VERSION;
 		return 1;
+	case Opt_lazytime:
+		sb->s_flags |= MS_LAZYTIME;
+		return 1;
+	case Opt_nolazytime:
+		sb->s_flags &= ~MS_LAZYTIME;
+		return 1;
 	}
 
 	for (m = ext4_mount_opts; m->token != Opt_err; m++)
@@ -5044,6 +5053,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	}
 #endif
 
+	*flags = (*flags & ~MS_LAZYTIME) | (sb->s_flags & MS_LAZYTIME);
 	ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data);
 	kfree(orig_data);
 	return 0;

fs/fs-writeback.c

@@ -253,14 +253,19 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t)
 	return ret;
 }
 
+#define EXPIRE_DIRTY_ATIME 0x0001
+
 /*
  * Move expired (dirtied before work->older_than_this) dirty inodes from
  * @delaying_queue to @dispatch_queue.
  */
 static int move_expired_inodes(struct list_head *delaying_queue,
 			       struct list_head *dispatch_queue,
+			       int flags,
 			       struct wb_writeback_work *work)
 {
+	unsigned long *older_than_this = NULL;
+	unsigned long expire_time;
 	LIST_HEAD(tmp);
 	struct list_head *pos, *node;
 	struct super_block *sb = NULL;
@@ -268,13 +273,21 @@ static int move_expired_inodes(struct list_head *delaying_queue,
 	int do_sb_sort = 0;
 	int moved = 0;
 
+	if ((flags & EXPIRE_DIRTY_ATIME) == 0)
+		older_than_this = work->older_than_this;
+	else if ((work->reason == WB_REASON_SYNC) == 0) {
+		expire_time = jiffies - (HZ * 86400);
+		older_than_this = &expire_time;
+	}
 	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++;
+		if (flags & EXPIRE_DIRTY_ATIME)
+			set_bit(__I_DIRTY_TIME_EXPIRED, &inode->i_state);
 		if (sb_is_blkdev_sb(inode->i_sb))
 			continue;
 		if (sb && sb != inode->i_sb)
@@ -315,9 +328,12 @@ static int move_expired_inodes(struct list_head *delaying_queue,
 static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work)
 {
 	int moved;
+
 	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, 0, work);
+	moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io,
+				     EXPIRE_DIRTY_ATIME, work);
 	trace_writeback_queue_io(wb, work, moved);
 }
 
@@ -441,6 +457,8 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
 		 * 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);
@@ -487,7 +505,13 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	spin_lock(&inode->i_lock);
 
 	dirty = inode->i_state & I_DIRTY;
-	inode->i_state &= ~I_DIRTY;
+	if (((dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) &&
+	     (inode->i_state & I_DIRTY_TIME)) ||
+	    (inode->i_state & I_DIRTY_TIME_EXPIRED)) {
+		dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED;
+		trace_writeback_lazytime(inode);
+	}
+	inode->i_state &= ~dirty;
 
 	/*
 	 * Paired with smp_mb() in __mark_inode_dirty().  This allows
@@ -507,8 +531,10 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 
 	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 & ~I_DIRTY_PAGES) {
 		int err = write_inode(inode, wbc);
 		if (ret == 0)
 			ret = err;
@@ -556,7 +582,7 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 	 * make sure inode is on some writeback list and leave it there unless
 	 * we have completely cleaned the inode.
 	 */
-	if (!(inode->i_state & I_DIRTY) &&
+	if (!(inode->i_state & I_DIRTY_ALL) &&
 	    (wbc->sync_mode != WB_SYNC_ALL ||
 	     !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK)))
 		goto out;
@@ -571,7 +597,7 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 	 * If inode is clean, remove it from writeback lists. Otherwise don't
 	 * touch it. See comment above for explanation.
 	 */
-	if (!(inode->i_state & I_DIRTY))
+	if (!(inode->i_state & I_DIRTY_ALL))
 		list_del_init(&inode->i_wb_list);
 	spin_unlock(&wb->list_lock);
 	inode_sync_complete(inode);
@@ -713,7 +739,7 @@ static long writeback_sb_inodes(struct super_block *sb,
 		wrote += write_chunk - wbc.nr_to_write;
 		spin_lock(&wb->list_lock);
 		spin_lock(&inode->i_lock);
-		if (!(inode->i_state & I_DIRTY))
+		if (!(inode->i_state & I_DIRTY_ALL))
 			wrote++;
 		requeue_inode(inode, wb, &wbc);
 		inode_sync_complete(inode);
@@ -1151,16 +1177,20 @@ static noinline void block_dump___mark_inode_dirty(struct inode *inode)
  * page->mapping->host, so the page-dirtying time is recorded in the internal
  * blockdev inode.
  */
+#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
 void __mark_inode_dirty(struct inode *inode, int flags)
 {
 	struct super_block *sb = inode->i_sb;
 	struct backing_dev_info *bdi = NULL;
+	int dirtytime;
+
+	trace_writeback_mark_inode_dirty(inode, flags);
 
 	/*
 	 * Don't do this for I_DIRTY_PAGES - that doesn't actually
 	 * dirty the inode itself
 	 */
-	if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
+	if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_TIME)) {
 		trace_writeback_dirty_inode_start(inode, flags);
 
 		if (sb->s_op->dirty_inode)
@@ -1168,6 +1198,9 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 
 		trace_writeback_dirty_inode(inode, flags);
 	}
+	if (flags & I_DIRTY_INODE)
+		flags &= ~I_DIRTY_TIME;
+	dirtytime = flags & I_DIRTY_TIME;
 
 	/*
 	 * Paired with smp_mb() in __writeback_single_inode() for the
@@ -1175,16 +1208,21 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 	 */
 	smp_mb();
 
-	if ((inode->i_state & flags) == flags)
+	if (((inode->i_state & flags) == flags) ||
+	    (dirtytime && (inode->i_state & I_DIRTY_INODE)))
 		return;
 
 	if (unlikely(block_dump))
 		block_dump___mark_inode_dirty(inode);
 
 	spin_lock(&inode->i_lock);
+	if (dirtytime && (inode->i_state & I_DIRTY_INODE))
+		goto out_unlock_inode;
 	if ((inode->i_state & flags) != flags) {
 		const int was_dirty = inode->i_state & I_DIRTY;
 
+		if (flags & I_DIRTY_INODE)
+			inode->i_state &= ~I_DIRTY_TIME;
 		inode->i_state |= flags;
 
 		/*
@@ -1231,8 +1269,10 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 			}
 
 			inode->dirtied_when = jiffies;
-			list_move(&inode->i_wb_list, &bdi->wb.b_dirty);
+			list_move(&inode->i_wb_list, dirtytime ?
+				  &bdi->wb.b_dirty_time : &bdi->wb.b_dirty);
 			spin_unlock(&bdi->wb.list_lock);
+			trace_writeback_dirty_inode_enqueue(inode);
 
 			if (wakeup_bdi)
 				bdi_wakeup_thread_delayed(bdi);

fs/gfs2/file.c

@@ -654,7 +654,7 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
 {
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = mapping->host;
-	int sync_state = inode->i_state & I_DIRTY;
+	int sync_state = inode->i_state & I_DIRTY_ALL;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	int ret = 0, ret1 = 0;
 
@@ -667,7 +667,7 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
 	if (!gfs2_is_jdata(ip))
 		sync_state &= ~I_DIRTY_PAGES;
 	if (datasync)
-		sync_state &= ~I_DIRTY_SYNC;
+		sync_state &= ~(I_DIRTY_SYNC | I_DIRTY_TIME);
 
 	if (sync_state) {
 		ret = sync_inode_metadata(inode, 1);

fs/inode.c

@@ -18,6 +18,7 @@
 #include <linux/buffer_head.h> /* for inode_has_buffers */
 #include <linux/ratelimit.h>
 #include <linux/list_lru.h>
+#include <trace/events/writeback.h>
 #include "internal.h"
 
 /*
@@ -30,7 +31,7 @@
  * 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
  *
@@ -403,7 +404,8 @@ static void inode_lru_list_add(struct inode *inode)
  */
 void inode_add_lru(struct inode *inode)
 {
-	if (!(inode->i_state & (I_DIRTY | I_SYNC | I_FREEING | I_WILL_FREE)) &&
+	if (!(inode->i_state & (I_DIRTY_ALL | I_SYNC |
+				I_FREEING | I_WILL_FREE)) &&
 	    !atomic_read(&inode->i_count) && inode->i_sb->s_flags & MS_ACTIVE)
 		inode_lru_list_add(inode);
 }
@@ -634,7 +636,7 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
 			spin_unlock(&inode->i_lock);
 			continue;
 		}
-		if (inode->i_state & I_DIRTY && !kill_dirty) {
+		if (inode->i_state & I_DIRTY_ALL && !kill_dirty) {
 			spin_unlock(&inode->i_lock);
 			busy = 1;
 			continue;
@@ -1268,6 +1270,56 @@ 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;
@@ -1418,10 +1470,19 @@ static void iput_final(struct inode *inode)
  */
 void iput(struct inode *inode)
 {
-	if (inode) {
+	if (!inode)
+		return;
 	BUG_ON(inode->i_state & I_CLEAR);
-
-		if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock))
+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);
+			trace_writeback_lazytime_iput(inode);
+			mark_inode_dirty_sync(inode);
+			goto retry;
+		}
 		iput_final(inode);
 	}
 }
@@ -1481,14 +1542,9 @@ static int relatime_need_update(struct vfsmount *mnt, struct inode *inode,
 	return 0;
 }
 
-/*
- * This does the actual work of updating an inodes time or version.  Must have
- * had called mnt_want_write() before calling this.
- */
-static int update_time(struct inode *inode, struct timespec *time, int flags)
+int generic_update_time(struct inode *inode, struct timespec *time, int flags)
 {
-	if (inode->i_op->update_time)
-		return inode->i_op->update_time(inode, time, flags);
+	int iflags = I_DIRTY_TIME;
 
 	if (flags & S_ATIME)
 		inode->i_atime = *time;
@@ -1498,9 +1554,27 @@ static int update_time(struct inode *inode, struct timespec *time, int flags)
 		inode->i_ctime = *time;
 	if (flags & S_MTIME)
 		inode->i_mtime = *time;
-	mark_inode_dirty_sync(inode);
+
+	if (!(inode->i_sb->s_flags & MS_LAZYTIME) || (flags & S_VERSION))
+		iflags |= I_DIRTY_SYNC;
+	__mark_inode_dirty(inode, iflags);
 	return 0;
 }
+EXPORT_SYMBOL(generic_update_time);
+
+/*
+ * This does the actual work of updating an inodes time or version.  Must have
+ * had called mnt_want_write() before calling this.
+ */
+static int update_time(struct inode *inode, struct timespec *time, int flags)
+{
+	int (*update_time)(struct inode *, struct timespec *, int);
+
+	update_time = inode->i_op->update_time ? inode->i_op->update_time :
+		generic_update_time;
+
+	return update_time(inode, time, flags);
+}
 
 /**
  *	touch_atime	-	update the access time

fs/jfs/file.c

@@ -39,7 +39,7 @@ int jfs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 		return rc;
 
 	mutex_lock(&inode->i_mutex);
-	if (!(inode->i_state & I_DIRTY) ||
+	if (!(inode->i_state & I_DIRTY_ALL) ||
 	    (datasync && !(inode->i_state & I_DIRTY_DATASYNC))) {
 		/* Make sure committed changes hit the disk */
 		jfs_flush_journal(JFS_SBI(inode->i_sb)->log, 1);

fs/libfs.c

@@ -948,7 +948,7 @@ int __generic_file_fsync(struct file *file, loff_t start, loff_t end,
 
 	mutex_lock(&inode->i_mutex);
 	ret = sync_mapping_buffers(inode->i_mapping);
-	if (!(inode->i_state & I_DIRTY))
+	if (!(inode->i_state & I_DIRTY_ALL))
 		goto out;
 	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
 		goto out;

fs/proc_namespace.c

@@ -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;

fs/sync.c

@@ -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);

include/linux/backing-dev.h

@@ -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 */
 };
 

include/linux/fs.h

@@ -1790,8 +1790,12 @@ 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_TIME_EXPIRED	12
+#define I_DIRTY_TIME_EXPIRED	(1 << __I_DIRTY_TIME_EXPIRED)
 
 #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
+#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME)
 
 extern void __mark_inode_dirty(struct inode *, int);
 static inline void mark_inode_dirty(struct inode *inode)
@@ -1954,6 +1958,7 @@ extern int current_umask(void);
 
 extern void ihold(struct inode * inode);
 extern void iput(struct inode *);
+extern int generic_update_time(struct inode *, struct timespec *, int);
 
 static inline struct inode *file_inode(const struct file *f)
 {
@@ -2492,6 +2497,11 @@ 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

include/trace/events/ext4.h

@@ -73,6 +73,36 @@ struct extent_status;
 	{ FALLOC_FL_ZERO_RANGE,		"ZERO_RANGE"})
 
 
+TRACE_EVENT(ext4_other_inode_update_time,
+	TP_PROTO(struct inode *inode, ino_t orig_ino),
+
+	TP_ARGS(inode, orig_ino),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	ino_t,	orig_ino		)
+		__field(	uid_t,	uid			)
+		__field(	gid_t,	gid			)
+		__field(	__u16, mode			)
+	),
+
+	TP_fast_assign(
+		__entry->orig_ino = orig_ino;
+		__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 orig_ino %lu ino %lu mode 0%o uid %u gid %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->orig_ino,
+		  (unsigned long) __entry->ino, __entry->mode,
+		  __entry->uid, __entry->gid)
+);
+
 TRACE_EVENT(ext4_free_inode,
 	TP_PROTO(struct inode *inode),
 

include/trace/events/writeback.h

@@ -18,6 +18,8 @@
 		{I_FREEING,		"I_FREEING"},		\
 		{I_CLEAR,		"I_CLEAR"},		\
 		{I_SYNC,		"I_SYNC"},		\
+		{I_DIRTY_TIME,		"I_DIRTY_TIME"},	\
+		{I_DIRTY_TIME_EXPIRED,	"I_DIRTY_TIME_EXPIRED"}, \
 		{I_REFERENCED,		"I_REFERENCED"}		\
 	)
 
@@ -68,6 +70,7 @@ DECLARE_EVENT_CLASS(writeback_dirty_inode_template,
 	TP_STRUCT__entry (
 		__array(char, name, 32)
 		__field(unsigned long, ino)
+		__field(unsigned long, state)
 		__field(unsigned long, flags)
 	),
 
@@ -78,16 +81,25 @@ DECLARE_EVENT_CLASS(writeback_dirty_inode_template,
 		strncpy(__entry->name,
 			bdi->dev ? dev_name(bdi->dev) : "(unknown)", 32);
 		__entry->ino		= inode->i_ino;
+		__entry->state		= inode->i_state;
 		__entry->flags		= flags;
 	),
 
-	TP_printk("bdi %s: ino=%lu flags=%s",
+	TP_printk("bdi %s: ino=%lu state=%s flags=%s",
 		__entry->name,
 		__entry->ino,
+		show_inode_state(__entry->state),
 		show_inode_state(__entry->flags)
 	)
 );
 
+DEFINE_EVENT(writeback_dirty_inode_template, writeback_mark_inode_dirty,
+
+	TP_PROTO(struct inode *inode, int flags),
+
+	TP_ARGS(inode, flags)
+);
+
 DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode_start,
 
 	TP_PROTO(struct inode *inode, int flags),
@@ -596,6 +608,52 @@ DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode,
 	TP_ARGS(inode, wbc, nr_to_write)
 );
 
+DECLARE_EVENT_CLASS(writeback_lazytime_template,
+	TP_PROTO(struct inode *inode),
+
+	TP_ARGS(inode),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(unsigned long,	ino			)
+		__field(unsigned long,	state			)
+		__field(	__u16, mode			)
+		__field(unsigned long, dirtied_when		)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->state	= inode->i_state;
+		__entry->mode	= inode->i_mode;
+		__entry->dirtied_when = inode->dirtied_when;
+	),
+
+	TP_printk("dev %d,%d ino %lu dirtied %lu state %s mode 0%o",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino, __entry->dirtied_when,
+		  show_inode_state(__entry->state), __entry->mode)
+);
+
+DEFINE_EVENT(writeback_lazytime_template, writeback_lazytime,
+	TP_PROTO(struct inode *inode),
+
+	TP_ARGS(inode)
+);
+
+DEFINE_EVENT(writeback_lazytime_template, writeback_lazytime_iput,
+	TP_PROTO(struct inode *inode),
+
+	TP_ARGS(inode)
+);
+
+DEFINE_EVENT(writeback_lazytime_template, writeback_dirty_inode_enqueue,
+
+	TP_PROTO(struct inode *inode),
+
+	TP_ARGS(inode)
+);
+
 #endif /* _TRACE_WRITEBACK_H */
 
 /* This part must be outside protection */

include/uapi/linux/fs.h

@@ -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)
@@ -100,7 +101,8 @@ struct inodes_stat_t {
 /*
  * Superblock flags that can be altered by MS_REMOUNT
  */
-#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION)
+#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\
+			 MS_LAZYTIME)
 
 /*
  * Old magic mount flag and mask

mm/backing-dev.c

@@ -49,10 +49,10 @@ 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++;
@@ -60,6 +60,9 @@ 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);
@@ -78,6 +81,7 @@ 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)),
@@ -91,6 +95,7 @@ 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
 
@@ -380,6 +385,7 @@ 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);
 }