[PATCH-v2 5/5] ext4: add support for a lazytime mount option

[Theodore Ts'o <tytso@mit.edu>]

Add an optimization for the MS_LAZYTIME mount option so that we will
opportunistically write out any inodes with the I_DIRTY_TIME flag set
in a particular inode table block when we need to update some inode in
that inode table block anyway.

Also add some temporary code so that we can set the lazytime mount
option without needing a modified /sbin/mount program which can set
MS_LAZYTIME.  We can eventually make this go away once util-linux has
added support.

Google-Bug-Id: 18297052

Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/inode.c             | 48 ++++++++++++++++++++++++++++++++++++++++++---
 fs/ext4/super.c             |  9 +++++++++
 fs/inode.c                  | 36 ++++++++++++++++++++++++++++++++++
 include/linux/fs.h          |  2 ++
 include/trace/events/ext4.h | 29 +++++++++++++++++++++++++++
 5 files changed, 121 insertions(+), 3 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 3356ab5..03149b4 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4163,6 +4163,50 @@ static int ext4_inode_blocks_set(handle_t *handle,
 }
 
 /*
+ * 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 ext4_inode_info	*ei;
+	struct ext4_inode	*raw_inode;
+	unsigned long		ino;
+	struct inode		*inode;
+	int		i, inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
+	int		inode_size = EXT4_INODE_SIZE(sb);
+
+	ino = orig_ino & ~(inodes_per_block - 1);
+	for (i = 0; i < inodes_per_block; i++, ino++, buf += inode_size) {
+		if (ino == orig_ino)
+			continue;
+		inode = find_active_inode_nowait(sb, ino);
+		if (!inode ||
+		    (inode->i_state & I_DIRTY_TIME) == 0 ||
+		    !spin_trylock(&inode->i_lock)) {
+			iput(inode);
+			continue;
+		}
+		inode->i_state &= ~I_DIRTY_TIME;
+		inode->i_ts_dirty_day = 0;
+		spin_unlock(&inode->i_lock);
+
+		ei = EXT4_I(inode);
+		raw_inode = (struct ext4_inode *) buf;
+
+		spin_lock(&ei->i_raw_lock);
+		EXT4_INODE_SET_XTIME(i_ctime, inode, raw_inode);
+		EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode);
+		EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode);
+		ext4_inode_csum_set(inode, raw_inode, ei);
+		spin_unlock(&ei->i_raw_lock);
+		trace_ext4_other_inode_update_time(inode, orig_ino);
+		iput(inode);
+	}
+}
+
+
+/*
  * Post the struct inode info into an on-disk inode location in the
  * buffer-cache.  This gobbles the caller's reference to the
  * buffer_head in the inode location struct.
@@ -4260,7 +4304,6 @@ static int ext4_do_update_inode(handle_t *handle,
 		for (block = 0; block < EXT4_N_BLOCKS; block++)
 			raw_inode->i_block[block] = ei->i_data[block];
 	}
-
 	if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) {
 		raw_inode->i_disk_version = cpu_to_le32(inode->i_version);
 		if (ei->i_extra_isize) {
@@ -4271,10 +4314,9 @@ 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);
+	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);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 4b79f39..1ac1914 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1133,6 +1133,7 @@ enum {
 	Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
 	Opt_usrquota, Opt_grpquota, Opt_i_version,
 	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,
@@ -1195,6 +1196,8 @@ static const match_table_t tokens = {
 	{Opt_i_version, "i_version"},
 	{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"},
@@ -1450,6 +1453,12 @@ 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++)
diff --git a/fs/inode.c b/fs/inode.c
index 5a9a7b0..17eb1c0 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1296,6 +1296,42 @@ struct inode *ilookup(struct super_block *sb, unsigned long ino)
 }
 EXPORT_SYMBOL(ilookup);
 
+/**
+ * find_active_inode_nowait - find an active inode in the inode cache
+ * @sb:		super block of file system to search
+ * @ino:	inode number to search for
+ *
+ * Search for an active inode @ino in the inode cache, and if the
+ * inode is in the cache, the inode is returned with an incremented
+ * reference count.  If the inode is being freed or is newly
+ * initialized, return nothing instead of trying to wait for the inode
+ * initialization or destruction to be complete.
+ */
+struct inode *find_active_inode_nowait(struct super_block *sb,
+				       unsigned long ino)
+{
+	struct hlist_head *head = inode_hashtable + hash(sb, ino);
+	struct inode *inode, *ret_inode = NULL;
+
+	spin_lock(&inode_hash_lock);
+	hlist_for_each_entry(inode, head, i_hash) {
+		if ((inode->i_ino != ino) ||
+		    (inode->i_sb != sb))
+			continue;
+		spin_lock(&inode->i_lock);
+		if ((inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW)) == 0) {
+			__iget(inode);
+			ret_inode = inode;
+		}
+		spin_unlock(&inode->i_lock);
+		goto out;
+	}
+out:
+	spin_unlock(&inode_hash_lock);
+	return ret_inode;
+}
+EXPORT_SYMBOL(find_active_inode_nowait);
+
 int insert_inode_locked(struct inode *inode)
 {
 	struct super_block *sb = inode->i_sb;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e3574cd..dbbd642 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2413,6 +2413,8 @@ 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_active_inode_nowait(struct super_block *,
+					      unsigned long);
 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
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index ff4bd1b..aca53c0 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -75,6 +75,35 @@ 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, __entry->ino,
+		  __entry->mode, __entry->uid, __entry->gid)
+);
+
 TRACE_EVENT(ext4_free_inode,
 	TP_PROTO(struct inode *inode),
 
-- 
2.1.0