From 55f252c9f50e998f6bc3aadc7806f049f7443d21 Mon Sep 17 00:00:00 2001
From: Lukas Czerner <lczerner@redhat.com>
Date: Mon, 27 May 2013 23:32:35 -0400
Subject: ext4: truncate_inode_pages() in orphan cleanup path

Currently we do not tell mm to zero out tail of the page before truncate
in orphan_cleanup(). This is ok, because the page should not be
uptodate, however this may eventually change and I might cause problems.

Call truncate_inode_pages() as precautionary measure. Thanks Jan Kara
for pointing this out.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/super.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'fs/ext4/super.c')

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 94cc84db7c9a..c468560c8765 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2170,6 +2170,7 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 			jbd_debug(2, "truncating inode %lu to %lld bytes\n",
 				  inode->i_ino, inode->i_size);
 			mutex_lock(&inode->i_mutex);
+			truncate_inode_pages(inode->i_mapping, inode->i_size);
 			ext4_truncate(inode);
 			mutex_unlock(&inode->i_mutex);
 			nr_truncates++;
-- 
cgit v1.2.3-59-g8ed1b


From 566370a2e56837be98bc62d012fc2d2d11851db4 Mon Sep 17 00:00:00 2001
From: Paul Taysom <taysom@chromium.org>
Date: Tue, 28 May 2013 07:51:21 -0400
Subject: ext4: suppress ext4 orphan messages on mount

Suppress the messages releating to processing the ext4 orphan list
("truncating inode" and "deleting unreferenced inode") unless the
debug option is on, since otherwise they end up taking up space in the
log that could be used for more useful information.

Tested by opening several files, unlinking them, then
crashing the system, rebooting the system and examining
/var/log/messages.

Addresses the problem described in http://crbug.com/220976

Signed-off-by: Paul Taysom <taysom@chromium.org>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/super.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

(limited to 'fs/ext4/super.c')

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index c468560c8765..a9c143820f7d 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2164,9 +2164,10 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 		list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
 		dquot_initialize(inode);
 		if (inode->i_nlink) {
-			ext4_msg(sb, KERN_DEBUG,
-				"%s: truncating inode %lu to %lld bytes",
-				__func__, inode->i_ino, inode->i_size);
+			if (test_opt(sb, DEBUG))
+				ext4_msg(sb, KERN_DEBUG,
+					"%s: truncating inode %lu to %lld bytes",
+					__func__, inode->i_ino, inode->i_size);
 			jbd_debug(2, "truncating inode %lu to %lld bytes\n",
 				  inode->i_ino, inode->i_size);
 			mutex_lock(&inode->i_mutex);
@@ -2175,9 +2176,10 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 			mutex_unlock(&inode->i_mutex);
 			nr_truncates++;
 		} else {
-			ext4_msg(sb, KERN_DEBUG,
-				"%s: deleting unreferenced inode %lu",
-				__func__, inode->i_ino);
+			if (test_opt(sb, DEBUG))
+				ext4_msg(sb, KERN_DEBUG,
+					"%s: deleting unreferenced inode %lu",
+					__func__, inode->i_ino);
 			jbd_debug(2, "deleting unreferenced inode %lu\n",
 				  inode->i_ino);
 			nr_orphans++;
-- 
cgit v1.2.3-59-g8ed1b


From f2d50a65c93cfe718742bc85dff55bf8f11967b6 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Tue, 4 Jun 2013 12:51:16 -0400
Subject: ext4: deprecate max_writeback_mb_bump sysfs attribute

This attribute is now unused so deprecate it.  We still show the old
default value to keep some compatibility but we don't allow writing to
that attribute anymore.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/ext4.h  |  1 -
 fs/ext4/super.c | 30 ++++++++++++++++++++++++------
 2 files changed, 24 insertions(+), 7 deletions(-)

(limited to 'fs/ext4/super.c')

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 82d2b6000a61..46674058d251 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1241,7 +1241,6 @@ struct ext4_sb_info {
 	unsigned int s_mb_stats;
 	unsigned int s_mb_order2_reqs;
 	unsigned int s_mb_group_prealloc;
-	unsigned int s_max_writeback_mb_bump;
 	unsigned int s_max_dir_size_kb;
 	/* where last allocation was done - for stream allocation */
 	unsigned long s_mb_last_group;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index a9c143820f7d..eac4d3081ba4 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2380,7 +2380,10 @@ struct ext4_attr {
 	ssize_t (*show)(struct ext4_attr *, struct ext4_sb_info *, char *);
 	ssize_t (*store)(struct ext4_attr *, struct ext4_sb_info *,
 			 const char *, size_t);
-	int offset;
+	union {
+		int offset;
+		int deprecated_val;
+	} u;
 };
 
 static int parse_strtoull(const char *buf,
@@ -2449,7 +2452,7 @@ static ssize_t inode_readahead_blks_store(struct ext4_attr *a,
 static ssize_t sbi_ui_show(struct ext4_attr *a,
 			   struct ext4_sb_info *sbi, char *buf)
 {
-	unsigned int *ui = (unsigned int *) (((char *) sbi) + a->offset);
+	unsigned int *ui = (unsigned int *) (((char *) sbi) + a->u.offset);
 
 	return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
 }
@@ -2458,7 +2461,7 @@ static ssize_t sbi_ui_store(struct ext4_attr *a,
 			    struct ext4_sb_info *sbi,
 			    const char *buf, size_t count)
 {
-	unsigned int *ui = (unsigned int *) (((char *) sbi) + a->offset);
+	unsigned int *ui = (unsigned int *) (((char *) sbi) + a->u.offset);
 	unsigned long t;
 	int ret;
 
@@ -2507,12 +2510,20 @@ static ssize_t trigger_test_error(struct ext4_attr *a,
 	return count;
 }
 
+static ssize_t sbi_deprecated_show(struct ext4_attr *a,
+				   struct ext4_sb_info *sbi, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n", a->u.deprecated_val);
+}
+
 #define EXT4_ATTR_OFFSET(_name,_mode,_show,_store,_elname) \
 static struct ext4_attr ext4_attr_##_name = {			\
 	.attr = {.name = __stringify(_name), .mode = _mode },	\
 	.show	= _show,					\
 	.store	= _store,					\
-	.offset = offsetof(struct ext4_sb_info, _elname),	\
+	.u = {							\
+		.offset = offsetof(struct ext4_sb_info, _elname),\
+	},							\
 }
 #define EXT4_ATTR(name, mode, show, store) \
 static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store)
@@ -2523,6 +2534,14 @@ static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store)
 #define EXT4_RW_ATTR_SBI_UI(name, elname)	\
 	EXT4_ATTR_OFFSET(name, 0644, sbi_ui_show, sbi_ui_store, elname)
 #define ATTR_LIST(name) &ext4_attr_##name.attr
+#define EXT4_DEPRECATED_ATTR(_name, _val)	\
+static struct ext4_attr ext4_attr_##_name = {			\
+	.attr = {.name = __stringify(_name), .mode = 0444 },	\
+	.show	= sbi_deprecated_show,				\
+	.u = {							\
+		.deprecated_val = _val,				\
+	},							\
+}
 
 EXT4_RO_ATTR(delayed_allocation_blocks);
 EXT4_RO_ATTR(session_write_kbytes);
@@ -2537,7 +2556,7 @@ EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan);
 EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs);
 EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request);
 EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc);
-EXT4_RW_ATTR_SBI_UI(max_writeback_mb_bump, s_max_writeback_mb_bump);
+EXT4_DEPRECATED_ATTR(max_writeback_mb_bump, 128);
 EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb);
 EXT4_ATTR(trigger_fs_error, 0200, NULL, trigger_test_error);
 
@@ -3790,7 +3809,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	sbi->s_stripe = ext4_get_stripe_size(sbi);
-	sbi->s_max_writeback_mb_bump = 128;
 	sbi->s_extent_max_zeroout_kb = 32;
 
 	/*
-- 
cgit v1.2.3-59-g8ed1b


From 2e8fa54e3b48e4ce8c4e9ca4674ffbc973f58be5 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Tue, 4 Jun 2013 14:21:02 -0400
Subject: ext4: split extent conversion lists to reserved & unreserved parts

Now that we have extent conversions with reserved transaction, we have
to prevent extent conversions without reserved transaction (from DIO
code) to block these (as that would effectively void any transaction
reservation we did).  So split lists, work items, and work queues to
reserved and unreserved parts.

Reviewed-by: Zheng Liu <wenqing.lz@taobao.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/ext4.h    | 25 ++++++++++++++++-----
 fs/ext4/page-io.c | 65 +++++++++++++++++++++++++++++++++++--------------------
 fs/ext4/super.c   | 38 ++++++++++++++++++++++----------
 3 files changed, 88 insertions(+), 40 deletions(-)

(limited to 'fs/ext4/super.c')

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 8de219b758fb..b69a733b5b42 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -887,12 +887,22 @@ struct ext4_inode_info {
 	qsize_t i_reserved_quota;
 #endif
 
-	/* completed IOs that might need unwritten extents handling */
-	struct list_head i_completed_io_list;
+	/* Lock protecting lists below */
 	spinlock_t i_completed_io_lock;
+	/*
+	 * Completed IOs that need unwritten extents handling and have
+	 * transaction reserved
+	 */
+	struct list_head i_rsv_conversion_list;
+	/*
+	 * Completed IOs that need unwritten extents handling and don't have
+	 * transaction reserved
+	 */
+	struct list_head i_unrsv_conversion_list;
 	atomic_t i_ioend_count;	/* Number of outstanding io_end structs */
 	atomic_t i_unwritten; /* Nr. of inflight conversions pending */
-	struct work_struct i_unwritten_work;	/* deferred extent conversion */
+	struct work_struct i_rsv_conversion_work;
+	struct work_struct i_unrsv_conversion_work;
 
 	spinlock_t i_block_reservation_lock;
 
@@ -1264,8 +1274,10 @@ struct ext4_sb_info {
 	struct flex_groups *s_flex_groups;
 	ext4_group_t s_flex_groups_allocated;
 
-	/* workqueue for dio unwritten */
-	struct workqueue_struct *dio_unwritten_wq;
+	/* workqueue for unreserved extent convertions (dio) */
+	struct workqueue_struct *unrsv_conversion_wq;
+	/* workqueue for reserved extent conversions (buffered io) */
+	struct workqueue_struct *rsv_conversion_wq;
 
 	/* timer for periodic error stats printing */
 	struct timer_list s_err_report;
@@ -2646,7 +2658,8 @@ extern int ext4_put_io_end(ext4_io_end_t *io_end);
 extern void ext4_put_io_end_defer(ext4_io_end_t *io_end);
 extern void ext4_io_submit_init(struct ext4_io_submit *io,
 				struct writeback_control *wbc);
-extern void ext4_end_io_work(struct work_struct *work);
+extern void ext4_end_io_rsv_work(struct work_struct *work);
+extern void ext4_end_io_unrsv_work(struct work_struct *work);
 extern void ext4_io_submit(struct ext4_io_submit *io);
 extern int ext4_bio_write_page(struct ext4_io_submit *io,
 			       struct page *page,
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 5f20bc481041..bcdfd6bdde06 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -58,8 +58,10 @@ void ext4_ioend_shutdown(struct inode *inode)
 	 * We need to make sure the work structure is finished being
 	 * used before we let the inode get destroyed.
 	 */
-	if (work_pending(&EXT4_I(inode)->i_unwritten_work))
-		cancel_work_sync(&EXT4_I(inode)->i_unwritten_work);
+	if (work_pending(&EXT4_I(inode)->i_rsv_conversion_work))
+		cancel_work_sync(&EXT4_I(inode)->i_rsv_conversion_work);
+	if (work_pending(&EXT4_I(inode)->i_unrsv_conversion_work))
+		cancel_work_sync(&EXT4_I(inode)->i_unrsv_conversion_work);
 }
 
 static void ext4_release_io_end(ext4_io_end_t *io_end)
@@ -114,20 +116,17 @@ static int ext4_end_io(ext4_io_end_t *io)
 	return ret;
 }
 
-static void dump_completed_IO(struct inode *inode)
+static void dump_completed_IO(struct inode *inode, struct list_head *head)
 {
 #ifdef	EXT4FS_DEBUG
 	struct list_head *cur, *before, *after;
 	ext4_io_end_t *io, *io0, *io1;
 
-	if (list_empty(&EXT4_I(inode)->i_completed_io_list)) {
-		ext4_debug("inode %lu completed_io list is empty\n",
-			   inode->i_ino);
+	if (list_empty(head))
 		return;
-	}
 
-	ext4_debug("Dump inode %lu completed_io list\n", inode->i_ino);
-	list_for_each_entry(io, &EXT4_I(inode)->i_completed_io_list, list) {
+	ext4_debug("Dump inode %lu completed io list\n", inode->i_ino);
+	list_for_each_entry(io, head, list) {
 		cur = &io->list;
 		before = cur->prev;
 		io0 = container_of(before, ext4_io_end_t, list);
@@ -148,16 +147,23 @@ static void ext4_add_complete_io(ext4_io_end_t *io_end)
 	unsigned long flags;
 
 	BUG_ON(!(io_end->flag & EXT4_IO_END_UNWRITTEN));
-	wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq;
-
 	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
-	if (list_empty(&ei->i_completed_io_list))
-		queue_work(wq, &ei->i_unwritten_work);
-	list_add_tail(&io_end->list, &ei->i_completed_io_list);
+	if (io_end->handle) {
+		wq = EXT4_SB(io_end->inode->i_sb)->rsv_conversion_wq;
+		if (list_empty(&ei->i_rsv_conversion_list))
+			queue_work(wq, &ei->i_rsv_conversion_work);
+		list_add_tail(&io_end->list, &ei->i_rsv_conversion_list);
+	} else {
+		wq = EXT4_SB(io_end->inode->i_sb)->unrsv_conversion_wq;
+		if (list_empty(&ei->i_unrsv_conversion_list))
+			queue_work(wq, &ei->i_unrsv_conversion_work);
+		list_add_tail(&io_end->list, &ei->i_unrsv_conversion_list);
+	}
 	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
 }
 
-static int ext4_do_flush_completed_IO(struct inode *inode)
+static int ext4_do_flush_completed_IO(struct inode *inode,
+				      struct list_head *head)
 {
 	ext4_io_end_t *io;
 	struct list_head unwritten;
@@ -166,8 +172,8 @@ static int ext4_do_flush_completed_IO(struct inode *inode)
 	int err, ret = 0;
 
 	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
-	dump_completed_IO(inode);
-	list_replace_init(&ei->i_completed_io_list, &unwritten);
+	dump_completed_IO(inode, head);
+	list_replace_init(head, &unwritten);
 	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
 
 	while (!list_empty(&unwritten)) {
@@ -183,21 +189,34 @@ static int ext4_do_flush_completed_IO(struct inode *inode)
 }
 
 /*
- * work on completed aio dio IO, to convert unwritten extents to extents
+ * work on completed IO, to convert unwritten extents to extents
  */
-void ext4_end_io_work(struct work_struct *work)
+void ext4_end_io_rsv_work(struct work_struct *work)
 {
 	struct ext4_inode_info *ei = container_of(work, struct ext4_inode_info,
-						  i_unwritten_work);
-	ext4_do_flush_completed_IO(&ei->vfs_inode);
+						  i_rsv_conversion_work);
+	ext4_do_flush_completed_IO(&ei->vfs_inode, &ei->i_rsv_conversion_list);
+}
+
+void ext4_end_io_unrsv_work(struct work_struct *work)
+{
+	struct ext4_inode_info *ei = container_of(work, struct ext4_inode_info,
+						  i_unrsv_conversion_work);
+	ext4_do_flush_completed_IO(&ei->vfs_inode, &ei->i_unrsv_conversion_list);
 }
 
 int ext4_flush_unwritten_io(struct inode *inode)
 {
-	int ret;
+	int ret, err;
+
 	WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex) &&
 		     !(inode->i_state & I_FREEING));
-	ret = ext4_do_flush_completed_IO(inode);
+	ret = ext4_do_flush_completed_IO(inode,
+					 &EXT4_I(inode)->i_rsv_conversion_list);
+	err = ext4_do_flush_completed_IO(inode,
+					 &EXT4_I(inode)->i_unrsv_conversion_list);
+	if (!ret)
+		ret = err;
 	ext4_unwritten_wait(inode);
 	return ret;
 }
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index eac4d3081ba4..7c8e1713e203 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -750,8 +750,10 @@ static void ext4_put_super(struct super_block *sb)
 	ext4_unregister_li_request(sb);
 	dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
 
-	flush_workqueue(sbi->dio_unwritten_wq);
-	destroy_workqueue(sbi->dio_unwritten_wq);
+	flush_workqueue(sbi->unrsv_conversion_wq);
+	flush_workqueue(sbi->rsv_conversion_wq);
+	destroy_workqueue(sbi->unrsv_conversion_wq);
+	destroy_workqueue(sbi->rsv_conversion_wq);
 
 	if (sbi->s_journal) {
 		err = jbd2_journal_destroy(sbi->s_journal);
@@ -859,13 +861,15 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	ei->i_reserved_quota = 0;
 #endif
 	ei->jinode = NULL;
-	INIT_LIST_HEAD(&ei->i_completed_io_list);
+	INIT_LIST_HEAD(&ei->i_rsv_conversion_list);
+	INIT_LIST_HEAD(&ei->i_unrsv_conversion_list);
 	spin_lock_init(&ei->i_completed_io_lock);
 	ei->i_sync_tid = 0;
 	ei->i_datasync_tid = 0;
 	atomic_set(&ei->i_ioend_count, 0);
 	atomic_set(&ei->i_unwritten, 0);
-	INIT_WORK(&ei->i_unwritten_work, ext4_end_io_work);
+	INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work);
+	INIT_WORK(&ei->i_unrsv_conversion_work, ext4_end_io_unrsv_work);
 
 	return &ei->vfs_inode;
 }
@@ -3936,12 +3940,20 @@ no_journal:
 	 * The maximum number of concurrent works can be high and
 	 * concurrency isn't really necessary.  Limit it to 1.
 	 */
-	EXT4_SB(sb)->dio_unwritten_wq =
-		alloc_workqueue("ext4-dio-unwritten", WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
-	if (!EXT4_SB(sb)->dio_unwritten_wq) {
-		printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n");
+	EXT4_SB(sb)->rsv_conversion_wq =
+		alloc_workqueue("ext4-rsv-conversion", WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
+	if (!EXT4_SB(sb)->rsv_conversion_wq) {
+		printk(KERN_ERR "EXT4-fs: failed to create workqueue\n");
 		ret = -ENOMEM;
-		goto failed_mount_wq;
+		goto failed_mount4;
+	}
+
+	EXT4_SB(sb)->unrsv_conversion_wq =
+		alloc_workqueue("ext4-unrsv-conversion", WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
+	if (!EXT4_SB(sb)->unrsv_conversion_wq) {
+		printk(KERN_ERR "EXT4-fs: failed to create workqueue\n");
+		ret = -ENOMEM;
+		goto failed_mount4;
 	}
 
 	/*
@@ -4095,7 +4107,10 @@ failed_mount4a:
 	sb->s_root = NULL;
 failed_mount4:
 	ext4_msg(sb, KERN_ERR, "mount failed");
-	destroy_workqueue(EXT4_SB(sb)->dio_unwritten_wq);
+	if (EXT4_SB(sb)->rsv_conversion_wq)
+		destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq);
+	if (EXT4_SB(sb)->unrsv_conversion_wq)
+		destroy_workqueue(EXT4_SB(sb)->unrsv_conversion_wq);
 failed_mount_wq:
 	if (sbi->s_journal) {
 		jbd2_journal_destroy(sbi->s_journal);
@@ -4541,7 +4556,8 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	trace_ext4_sync_fs(sb, wait);
-	flush_workqueue(sbi->dio_unwritten_wq);
+	flush_workqueue(sbi->rsv_conversion_wq);
+	flush_workqueue(sbi->unrsv_conversion_wq);
 	/*
 	 * Writeback quota in non-journalled quota case - journalled quota has
 	 * no dirty dquots
-- 
cgit v1.2.3-59-g8ed1b


From 06a407f13daf9e48f0ef7189c7e54082b53940c7 Mon Sep 17 00:00:00 2001
From: Dmitry Monakhov <dmonakhov@openvz.org>
Date: Wed, 12 Jun 2013 22:25:07 -0400
Subject: ext4: fix data integrity for ext4_sync_fs

Inode's data or non journaled quota may be written w/o jounral so we
_must_ send a barrier at the end of ext4_sync_fs. But it can be
skipped if journal commit will do it for us.

Also fix data integrity for nojournal mode.

Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/super.c      | 36 +++++++++++++++++++++++++++++++++++-
 include/linux/jbd2.h | 13 +++++++++++++
 2 files changed, 48 insertions(+), 1 deletion(-)

(limited to 'fs/ext4/super.c')

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 7c8e1713e203..0f77c2e4b888 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -69,6 +69,7 @@ static void ext4_mark_recovery_complete(struct super_block *sb,
 static void ext4_clear_journal_err(struct super_block *sb,
 				   struct ext4_super_block *es);
 static int ext4_sync_fs(struct super_block *sb, int wait);
+static int ext4_sync_fs_nojournal(struct super_block *sb, int wait);
 static int ext4_remount(struct super_block *sb, int *flags, char *data);
 static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf);
 static int ext4_unfreeze(struct super_block *sb);
@@ -1097,6 +1098,7 @@ static const struct super_operations ext4_nojournal_sops = {
 	.dirty_inode	= ext4_dirty_inode,
 	.drop_inode	= ext4_drop_inode,
 	.evict_inode	= ext4_evict_inode,
+	.sync_fs	= ext4_sync_fs_nojournal,
 	.put_super	= ext4_put_super,
 	.statfs		= ext4_statfs,
 	.remount_fs	= ext4_remount,
@@ -4553,6 +4555,7 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
 {
 	int ret = 0;
 	tid_t target;
+	bool needs_barrier = false;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	trace_ext4_sync_fs(sb, wait);
@@ -4563,10 +4566,41 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
 	 * no dirty dquots
 	 */
 	dquot_writeback_dquots(sb, -1);
+	/*
+	 * Data writeback is possible w/o journal transaction, so barrier must
+	 * being sent at the end of the function. But we can skip it if
+	 * transaction_commit will do it for us.
+	 */
+	target = jbd2_get_latest_transaction(sbi->s_journal);
+	if (wait && sbi->s_journal->j_flags & JBD2_BARRIER &&
+	    !jbd2_trans_will_send_data_barrier(sbi->s_journal, target))
+		needs_barrier = true;
+
 	if (jbd2_journal_start_commit(sbi->s_journal, &target)) {
 		if (wait)
-			jbd2_log_wait_commit(sbi->s_journal, target);
+			ret = jbd2_log_wait_commit(sbi->s_journal, target);
+	}
+	if (needs_barrier) {
+		int err;
+		err = blkdev_issue_flush(sb->s_bdev, GFP_KERNEL, NULL);
+		if (!ret)
+			ret = err;
 	}
+
+	return ret;
+}
+
+static int ext4_sync_fs_nojournal(struct super_block *sb, int wait)
+{
+	int ret = 0;
+
+	trace_ext4_sync_fs(sb, wait);
+	flush_workqueue(EXT4_SB(sb)->rsv_conversion_wq);
+	flush_workqueue(EXT4_SB(sb)->unrsv_conversion_wq);
+	dquot_writeback_dquots(sb, -1);
+	if (wait && test_opt(sb, BARRIER))
+		ret = blkdev_issue_flush(sb->s_bdev, GFP_KERNEL, NULL);
+
 	return ret;
 }
 
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index c3645b9475f1..a79783faecad 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1374,6 +1374,19 @@ static inline u32 jbd2_chksum(journal_t *journal, u32 crc,
 	return *(u32 *)desc.ctx;
 }
 
+/* Return most recent uncommitted transaction */
+static inline tid_t  jbd2_get_latest_transaction(journal_t *journal)
+{
+	tid_t tid;
+
+	read_lock(&journal->j_state_lock);
+	tid = journal->j_commit_request;
+	if (journal->j_running_transaction)
+		tid = journal->j_running_transaction->t_tid;
+	read_unlock(&journal->j_state_lock);
+	return tid;
+}
+
 #ifdef __KERNEL__
 
 #define buffer_trace_init(bh)	do {} while (0)
-- 
cgit v1.2.3-59-g8ed1b


From 4418e14112e3ca85e8492a4489a3552b0cc526a8 Mon Sep 17 00:00:00 2001
From: Dmitry Monakhov <dmonakhov@openvz.org>
Date: Wed, 12 Jun 2013 22:38:04 -0400
Subject: ext4: Fix fsync error handling after filesystem abort

If filesystem was aborted after inode's write back is complete
but before its metadata was updated we may return success
results in data loss.
In order to handle fs abort correctly we have to check
fs state once we discover that it is in MS_RDONLY state

Test case: http://patchwork.ozlabs.org/patch/244297

Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/fsync.c |  7 ++++++-
 fs/ext4/super.c | 12 +++++++++++-
 2 files changed, 17 insertions(+), 2 deletions(-)

(limited to 'fs/ext4/super.c')

diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index fc938ebbddec..a8bc47f75fa0 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -98,8 +98,13 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 
 	trace_ext4_sync_file_enter(file, datasync);
 
-	if (inode->i_sb->s_flags & MS_RDONLY)
+	if (inode->i_sb->s_flags & MS_RDONLY) {
+		/* Make sure that we read updated s_mount_flags value */
+		smp_rmb();
+		if (EXT4_SB(inode->i_sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+			ret = -EROFS;
 		goto out;
+	}
 
 	if (!journal) {
 		ret = generic_file_fsync(file, start, end, datasync);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 0f77c2e4b888..eb52a7be1fc1 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -399,6 +399,11 @@ static void ext4_handle_error(struct super_block *sb)
 	}
 	if (test_opt(sb, ERRORS_RO)) {
 		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
+		/*
+		 * Make sure updated value of ->s_mount_flags will be visible
+		 * before ->s_flags update
+		 */
+		smp_wmb();
 		sb->s_flags |= MS_RDONLY;
 	}
 	if (test_opt(sb, ERRORS_PANIC))
@@ -571,8 +576,13 @@ void __ext4_abort(struct super_block *sb, const char *function,
 
 	if ((sb->s_flags & MS_RDONLY) == 0) {
 		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
-		sb->s_flags |= MS_RDONLY;
 		EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+		/*
+		 * Make sure updated value of ->s_mount_flags will be visible
+		 * before ->s_flags update
+		 */
+		smp_wmb();
+		sb->s_flags |= MS_RDONLY;
 		if (EXT4_SB(sb)->s_journal)
 			jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
 		save_error_info(sb, function, line);
-- 
cgit v1.2.3-59-g8ed1b


From 03b40e349695dc700582568e5b410a89058f707e Mon Sep 17 00:00:00 2001
From: Jon Ernst <jonernst07@gmx.com>
Date: Mon, 17 Jun 2013 08:56:26 -0400
Subject: ext4: delete unused variables

This patch removed several unused variables.

Signed-off-by: Jon Ernst <jonernst07@gmx.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/move_extent.c | 3 ---
 fs/ext4/resize.c      | 3 +--
 fs/ext4/super.c       | 2 --
 3 files changed, 1 insertion(+), 7 deletions(-)

(limited to 'fs/ext4/super.c')

diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 3dcbf364022f..e86dddbd8296 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -912,7 +912,6 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
 	struct page *pagep[2] = {NULL, NULL};
 	handle_t *handle;
 	ext4_lblk_t orig_blk_offset;
-	long long offs = orig_page_offset << PAGE_CACHE_SHIFT;
 	unsigned long blocksize = orig_inode->i_sb->s_blocksize;
 	unsigned int w_flags = 0;
 	unsigned int tmp_data_size, data_size, replaced_size;
@@ -940,8 +939,6 @@ again:
 	orig_blk_offset = orig_page_offset * blocks_per_page +
 		data_offset_in_page;
 
-	offs = (long long)orig_blk_offset << orig_inode->i_blkbits;
-
 	/* Calculate data_size */
 	if ((orig_blk_offset + block_len_in_page - 1) ==
 	    ((orig_inode->i_size - 1) >> orig_inode->i_blkbits)) {
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 6ed4df27da8d..707095b924d9 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1556,11 +1556,10 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 	int reserved_gdb = ext4_bg_has_super(sb, input->group) ?
 		le16_to_cpu(es->s_reserved_gdt_blocks) : 0;
 	struct inode *inode = NULL;
-	int gdb_off, gdb_num;
+	int gdb_off;
 	int err;
 	__u16 bg_flags = 0;
 
-	gdb_num = input->group / EXT4_DESC_PER_BLOCK(sb);
 	gdb_off = input->group % EXT4_DESC_PER_BLOCK(sb);
 
 	if (gdb_off == 0 && !EXT4_HAS_RO_COMPAT_FEATURE(sb,
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index eb52a7be1fc1..54701fca4515 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1924,7 +1924,6 @@ static int ext4_fill_flex_info(struct super_block *sb)
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_group_desc *gdp = NULL;
 	ext4_group_t flex_group;
-	unsigned int groups_per_flex = 0;
 	int i, err;
 
 	sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
@@ -1932,7 +1931,6 @@ static int ext4_fill_flex_info(struct super_block *sb)
 		sbi->s_log_groups_per_flex = 0;
 		return 1;
 	}
-	groups_per_flex = 1U << sbi->s_log_groups_per_flex;
 
 	err = ext4_alloc_flex_bg_array(sb, sbi->s_groups_count);
 	if (err)
-- 
cgit v1.2.3-59-g8ed1b


From d3922a777f9b4c4df898d326fa940f239af4f9b6 Mon Sep 17 00:00:00 2001
From: Zheng Liu <wenqing.lz@taobao.com>
Date: Mon, 1 Jul 2013 08:12:37 -0400
Subject: ext4: improve extent cache shrink mechanism to avoid to burn CPU time

Now we maintain an proper in-order LRU list in ext4 to reclaim entries
from extent status tree when we are under heavy memory pressure.  For
keeping this order, a spin lock is used to protect this list.  But this
lock burns a lot of CPU time.  We can use the following steps to trigger
it.

  % cd /dev/shm
  % dd if=/dev/zero of=ext4-img bs=1M count=2k
  % mkfs.ext4 ext4-img
  % mount -t ext4 -o loop ext4-img /mnt
  % cd /mnt
  % for ((i=0;i<160;i++)); do truncate -s 64g $i; done
  % for ((i=0;i<160;i++)); do cp $i /dev/null &; done
  % perf record -a -g
  % perf report

This commit tries to fix this problem.  Now a new member called
i_touch_when is added into ext4_inode_info to record the last access
time for an inode.  Meanwhile we never need to keep a proper in-order
LRU list.  So this can avoid to burns some CPU time.  When we try to
reclaim some entries from extent status tree, we use list_sort() to get
a proper in-order list.  Then we traverse this list to discard some
entries.  In ext4_sb_info, we use s_es_last_sorted to record the last
time of sorting this list.  When we traverse the list, we skip the inode
that is newer than this time, and move this inode to the tail of LRU
list.  When the head of the list is newer than s_es_last_sorted, we will
sort the LRU list again.

In this commit, we break the loop if s_extent_cache_cnt == 0 because
that means that all extents in extent status tree have been reclaimed.

Meanwhile in this commit, ext4_es_{un}register_shrinker()'s prototype is
changed to save a local variable in these functions.

Reported-by: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Zheng Liu <wenqing.lz@taobao.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/ext4.h           |  2 ++
 fs/ext4/extents_status.c | 75 +++++++++++++++++++++++++++++++++++-------------
 fs/ext4/extents_status.h |  5 ++--
 fs/ext4/inode.c          |  4 +++
 fs/ext4/super.c          |  7 +++--
 5 files changed, 68 insertions(+), 25 deletions(-)

(limited to 'fs/ext4/super.c')

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index f85f1fb49df8..f5f3b6c58240 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -864,6 +864,7 @@ struct ext4_inode_info {
 	rwlock_t i_es_lock;
 	struct list_head i_es_lru;
 	unsigned int i_es_lru_nr;	/* protected by i_es_lock */
+	unsigned long i_touch_when;	/* jiffies of last accessing */
 
 	/* ialloc */
 	ext4_group_t	i_last_alloc_group;
@@ -1303,6 +1304,7 @@ struct ext4_sb_info {
 	/* Reclaim extents from extent status tree */
 	struct shrinker s_es_shrinker;
 	struct list_head s_es_lru;
+	unsigned long s_es_last_sorted;
 	struct percpu_counter s_extent_cache_cnt;
 	spinlock_t s_es_lru_lock ____cacheline_aligned_in_smp;
 };
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index e6941e622d31..ee018d5f397e 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -10,6 +10,7 @@
  * Ext4 extents status tree core functions.
  */
 #include <linux/rbtree.h>
+#include <linux/list_sort.h>
 #include "ext4.h"
 #include "extents_status.h"
 #include "ext4_extents.h"
@@ -291,7 +292,6 @@ out:
 
 	read_unlock(&EXT4_I(inode)->i_es_lock);
 
-	ext4_es_lru_add(inode);
 	trace_ext4_es_find_delayed_extent_range_exit(inode, es);
 }
 
@@ -672,7 +672,6 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
 error:
 	write_unlock(&EXT4_I(inode)->i_es_lock);
 
-	ext4_es_lru_add(inode);
 	ext4_es_print_tree(inode);
 
 	return err;
@@ -734,7 +733,6 @@ out:
 
 	read_unlock(&EXT4_I(inode)->i_es_lock);
 
-	ext4_es_lru_add(inode);
 	trace_ext4_es_lookup_extent_exit(inode, es, found);
 	return found;
 }
@@ -878,12 +876,28 @@ int ext4_es_zeroout(struct inode *inode, struct ext4_extent *ex)
 				     EXTENT_STATUS_WRITTEN);
 }
 
+static int ext4_inode_touch_time_cmp(void *priv, struct list_head *a,
+				     struct list_head *b)
+{
+	struct ext4_inode_info *eia, *eib;
+	eia = list_entry(a, struct ext4_inode_info, i_es_lru);
+	eib = list_entry(b, struct ext4_inode_info, i_es_lru);
+
+	if (eia->i_touch_when == eib->i_touch_when)
+		return 0;
+	if (time_after(eia->i_touch_when, eib->i_touch_when))
+		return 1;
+	else
+		return -1;
+}
+
 static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc)
 {
 	struct ext4_sb_info *sbi = container_of(shrink,
 					struct ext4_sb_info, s_es_shrinker);
 	struct ext4_inode_info *ei;
-	struct list_head *cur, *tmp, scanned;
+	struct list_head *cur, *tmp;
+	LIST_HEAD(skiped);
 	int nr_to_scan = sc->nr_to_scan;
 	int ret, nr_shrunk = 0;
 
@@ -893,23 +907,41 @@ static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc)
 	if (!nr_to_scan)
 		return ret;
 
-	INIT_LIST_HEAD(&scanned);
-
 	spin_lock(&sbi->s_es_lru_lock);
+
+	/*
+	 * If the inode that is at the head of LRU list is newer than
+	 * last_sorted time, that means that we need to sort this list.
+	 */
+	ei = list_first_entry(&sbi->s_es_lru, struct ext4_inode_info, i_es_lru);
+	if (sbi->s_es_last_sorted < ei->i_touch_when) {
+		list_sort(NULL, &sbi->s_es_lru, ext4_inode_touch_time_cmp);
+		sbi->s_es_last_sorted = jiffies;
+	}
+
 	list_for_each_safe(cur, tmp, &sbi->s_es_lru) {
-		list_move_tail(cur, &scanned);
+		/*
+		 * If we have already reclaimed all extents from extent
+		 * status tree, just stop the loop immediately.
+		 */
+		if (percpu_counter_read_positive(&sbi->s_extent_cache_cnt) == 0)
+			break;
 
 		ei = list_entry(cur, struct ext4_inode_info, i_es_lru);
 
-		read_lock(&ei->i_es_lock);
-		if (ei->i_es_lru_nr == 0) {
-			read_unlock(&ei->i_es_lock);
+		/* Skip the inode that is newer than the last_sorted time */
+		if (sbi->s_es_last_sorted < ei->i_touch_when) {
+			list_move_tail(cur, &skiped);
 			continue;
 		}
-		read_unlock(&ei->i_es_lock);
+
+		if (ei->i_es_lru_nr == 0)
+			continue;
 
 		write_lock(&ei->i_es_lock);
 		ret = __es_try_to_reclaim_extents(ei, nr_to_scan);
+		if (ei->i_es_lru_nr == 0)
+			list_del_init(&ei->i_es_lru);
 		write_unlock(&ei->i_es_lock);
 
 		nr_shrunk += ret;
@@ -917,7 +949,9 @@ static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc)
 		if (nr_to_scan == 0)
 			break;
 	}
-	list_splice_tail(&scanned, &sbi->s_es_lru);
+
+	/* Move the newer inodes into the tail of the LRU list. */
+	list_splice_tail(&skiped, &sbi->s_es_lru);
 	spin_unlock(&sbi->s_es_lru_lock);
 
 	ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
@@ -925,21 +959,19 @@ static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc)
 	return ret;
 }
 
-void ext4_es_register_shrinker(struct super_block *sb)
+void ext4_es_register_shrinker(struct ext4_sb_info *sbi)
 {
-	struct ext4_sb_info *sbi;
-
-	sbi = EXT4_SB(sb);
 	INIT_LIST_HEAD(&sbi->s_es_lru);
 	spin_lock_init(&sbi->s_es_lru_lock);
+	sbi->s_es_last_sorted = 0;
 	sbi->s_es_shrinker.shrink = ext4_es_shrink;
 	sbi->s_es_shrinker.seeks = DEFAULT_SEEKS;
 	register_shrinker(&sbi->s_es_shrinker);
 }
 
-void ext4_es_unregister_shrinker(struct super_block *sb)
+void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi)
 {
-	unregister_shrinker(&EXT4_SB(sb)->s_es_shrinker);
+	unregister_shrinker(&sbi->s_es_shrinker);
 }
 
 void ext4_es_lru_add(struct inode *inode)
@@ -947,11 +979,14 @@ void ext4_es_lru_add(struct inode *inode)
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 
+	ei->i_touch_when = jiffies;
+
+	if (!list_empty(&ei->i_es_lru))
+		return;
+
 	spin_lock(&sbi->s_es_lru_lock);
 	if (list_empty(&ei->i_es_lru))
 		list_add_tail(&ei->i_es_lru, &sbi->s_es_lru);
-	else
-		list_move_tail(&ei->i_es_lru, &sbi->s_es_lru);
 	spin_unlock(&sbi->s_es_lru_lock);
 }
 
diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h
index f740eb03b707..e936730cc5b0 100644
--- a/fs/ext4/extents_status.h
+++ b/fs/ext4/extents_status.h
@@ -39,6 +39,7 @@
 				 EXTENT_STATUS_DELAYED | \
 				 EXTENT_STATUS_HOLE)
 
+struct ext4_sb_info;
 struct ext4_extent;
 
 struct extent_status {
@@ -119,8 +120,8 @@ static inline void ext4_es_store_status(struct extent_status *es,
 	es->es_pblk = block;
 }
 
-extern void ext4_es_register_shrinker(struct super_block *sb);
-extern void ext4_es_unregister_shrinker(struct super_block *sb);
+extern void ext4_es_register_shrinker(struct ext4_sb_info *sbi);
+extern void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi);
 extern void ext4_es_lru_add(struct inode *inode);
 extern void ext4_es_lru_del(struct inode *inode);
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 0db830d541ec..f9ba51f68777 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -514,6 +514,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 		  "logical block %lu\n", inode->i_ino, flags, map->m_len,
 		  (unsigned long) map->m_lblk);
 
+	ext4_es_lru_add(inode);
+
 	/* Lookup extent status tree firstly */
 	if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
 		if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) {
@@ -1526,6 +1528,8 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 		  "logical block %lu\n", inode->i_ino, map->m_len,
 		  (unsigned long) map->m_lblk);
 
+	ext4_es_lru_add(inode);
+
 	/* Lookup extent status tree firstly */
 	if (ext4_es_lookup_extent(inode, iblock, &es)) {
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 54701fca4515..cc8201180b30 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -773,7 +773,7 @@ static void ext4_put_super(struct super_block *sb)
 			ext4_abort(sb, "Couldn't clean up the journal");
 	}
 
-	ext4_es_unregister_shrinker(sb);
+	ext4_es_unregister_shrinker(sbi);
 	del_timer(&sbi->s_err_report);
 	ext4_release_system_zone(sb);
 	ext4_mb_release(sb);
@@ -862,6 +862,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	rwlock_init(&ei->i_es_lock);
 	INIT_LIST_HEAD(&ei->i_es_lru);
 	ei->i_es_lru_nr = 0;
+	ei->i_touch_when = 0;
 	ei->i_reserved_data_blocks = 0;
 	ei->i_reserved_meta_blocks = 0;
 	ei->i_allocated_meta_blocks = 0;
@@ -3799,7 +3800,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_err_report.data = (unsigned long) sb;
 
 	/* Register extent status tree shrinker */
-	ext4_es_register_shrinker(sb);
+	ext4_es_register_shrinker(sbi);
 
 	err = percpu_counter_init(&sbi->s_freeclusters_counter,
 			ext4_count_free_clusters(sb));
@@ -4127,7 +4128,7 @@ failed_mount_wq:
 		sbi->s_journal = NULL;
 	}
 failed_mount3:
-	ext4_es_unregister_shrinker(sb);
+	ext4_es_unregister_shrinker(sbi);
 	del_timer(&sbi->s_err_report);
 	if (sbi->s_flex_groups)
 		ext4_kvfree(sbi->s_flex_groups);
-- 
cgit v1.2.3-59-g8ed1b


From e7c96e8e47baf263d93a8dbbebca7216a912ca05 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 1 Jul 2013 08:12:37 -0400
Subject: ext4: reduce object size when !CONFIG_PRINTK

Reduce the object size ~10% could be useful for embedded systems.

Add #ifdef CONFIG_PRINTK #else #endif blocks to hold formats and
arguments, passing " " to functions when !CONFIG_PRINTK and still
verifying format and arguments with no_printk.

$ size fs/ext4/built-in.o*
   text	   data	    bss	    dec	    hex	filename
 239375	    610	    888	 240873	  3ace9	fs/ext4/built-in.o.new
 264167	    738	    888	 265793	  40e41	fs/ext4/built-in.o.old

    $ grep -E "CONFIG_EXT4|CONFIG_PRINTK" .config
    # CONFIG_PRINTK is not set
    CONFIG_EXT4_FS=y
    CONFIG_EXT4_USE_FOR_EXT23=y
    CONFIG_EXT4_FS_POSIX_ACL=y
    # CONFIG_EXT4_FS_SECURITY is not set
    # CONFIG_EXT4_DEBUG is not set

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/ext4.h  | 80 +++++++++++++++++++++++++++++++++++++++++++++++----------
 fs/ext4/super.c | 15 ++++++-----
 2 files changed, 75 insertions(+), 20 deletions(-)

(limited to 'fs/ext4/super.c')

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index f5f3b6c58240..7cc6b18230ec 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2169,42 +2169,96 @@ extern int ext4_alloc_flex_bg_array(struct super_block *sb,
 				    ext4_group_t ngroup);
 extern const char *ext4_decode_error(struct super_block *sb, int errno,
 				     char nbuf[16]);
+
 extern __printf(4, 5)
 void __ext4_error(struct super_block *, const char *, unsigned int,
 		  const char *, ...);
-#define ext4_error(sb, message...)	__ext4_error(sb, __func__,	\
-						     __LINE__, ## message)
 extern __printf(5, 6)
-void ext4_error_inode(struct inode *, const char *, unsigned int, ext4_fsblk_t,
+void __ext4_error_inode(struct inode *, const char *, unsigned int, ext4_fsblk_t,
 		      const char *, ...);
 extern __printf(5, 6)
-void ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t,
+void __ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t,
 		     const char *, ...);
 extern void __ext4_std_error(struct super_block *, const char *,
 			     unsigned int, int);
 extern __printf(4, 5)
 void __ext4_abort(struct super_block *, const char *, unsigned int,
 		  const char *, ...);
-#define ext4_abort(sb, message...)	__ext4_abort(sb, __func__, \
-						       __LINE__, ## message)
 extern __printf(4, 5)
 void __ext4_warning(struct super_block *, const char *, unsigned int,
 		    const char *, ...);
-#define ext4_warning(sb, message...)	__ext4_warning(sb, __func__, \
-						       __LINE__, ## message)
 extern __printf(3, 4)
-void ext4_msg(struct super_block *, const char *, const char *, ...);
+void __ext4_msg(struct super_block *, const char *, const char *, ...);
 extern void __dump_mmp_msg(struct super_block *, struct mmp_struct *mmp,
 			   const char *, unsigned int, const char *);
-#define dump_mmp_msg(sb, mmp, msg)	__dump_mmp_msg(sb, mmp, __func__, \
-						       __LINE__, msg)
 extern __printf(7, 8)
 void __ext4_grp_locked_error(const char *, unsigned int,
 			     struct super_block *, ext4_group_t,
 			     unsigned long, ext4_fsblk_t,
 			     const char *, ...);
-#define ext4_grp_locked_error(sb, grp, message...) \
-	__ext4_grp_locked_error(__func__, __LINE__, (sb), (grp), ## message)
+
+#ifdef CONFIG_PRINTK
+
+#define ext4_error_inode(inode, func, line, block, fmt, ...)		\
+	__ext4_error_inode(inode, func, line, block, fmt, ##__VA_ARGS__)
+#define ext4_error_file(file, func, line, block, fmt, ...)		\
+	__ext4_error_file(file, func, line, block, fmt, ##__VA_ARGS__)
+#define ext4_error(sb, fmt, ...)					\
+	__ext4_error(sb, __func__, __LINE__, fmt, ##__VA_ARGS__)
+#define ext4_abort(sb, fmt, ...)					\
+	__ext4_abort(sb, __func__, __LINE__, fmt, ##__VA_ARGS__)
+#define ext4_warning(sb, fmt, ...)					\
+	__ext4_warning(sb, __func__, __LINE__, fmt, ##__VA_ARGS__)
+#define ext4_msg(sb, level, fmt, ...)				\
+	__ext4_msg(sb, level, fmt, ##__VA_ARGS__)
+#define dump_mmp_msg(sb, mmp, msg)					\
+	__dump_mmp_msg(sb, mmp, __func__, __LINE__, msg)
+#define ext4_grp_locked_error(sb, grp, ino, block, fmt, ...)		\
+	__ext4_grp_locked_error(__func__, __LINE__, sb, grp, ino, block, \
+				fmt, ##__VA_ARGS__)
+
+#else
+
+#define ext4_error_inode(inode, func, line, block, fmt, ...)		\
+do {									\
+	no_printk(fmt, ##__VA_ARGS__);					\
+	__ext4_error_inode(inode, "", 0, block, " ");			\
+} while (0)
+#define ext4_error_file(file, func, line, block, fmt, ...)		\
+do {									\
+	no_printk(fmt, ##__VA_ARGS__);					\
+	__ext4_error_file(file, "", 0, block, " ");			\
+} while (0)
+#define ext4_error(sb, fmt, ...)					\
+do {									\
+	no_printk(fmt, ##__VA_ARGS__);					\
+	__ext4_error(sb, "", 0, " ");					\
+} while (0)
+#define ext4_abort(sb, fmt, ...)					\
+do {									\
+	no_printk(fmt, ##__VA_ARGS__);					\
+	__ext4_abort(sb, "", 0, " ");					\
+} while (0)
+#define ext4_warning(sb, fmt, ...)					\
+do {									\
+	no_printk(fmt, ##__VA_ARGS__);					\
+	__ext4_warning(sb, "", 0, " ");					\
+} while (0)
+#define ext4_msg(sb, level, fmt, ...)					\
+do {									\
+	no_printk(fmt, ##__VA_ARGS__);					\
+	__ext4_msg(sb, "", " ");					\
+} while (0)
+#define dump_mmp_msg(sb, mmp, msg)					\
+	__dump_mmp_msg(sb, mmp, "", 0, "")
+#define ext4_grp_locked_error(sb, grp, ino, block, fmt, ...)		\
+do {									\
+	no_printk(fmt, ##__VA_ARGS__);				\
+	__ext4_grp_locked_error("", 0, sb, grp, ino, block, " ");	\
+} while (0)
+
+#endif
+
 extern void ext4_update_dynamic_rev(struct super_block *sb);
 extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb,
 					__u32 compat);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index cc8201180b30..85b3dd60169b 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -428,9 +428,9 @@ void __ext4_error(struct super_block *sb, const char *function,
 	ext4_handle_error(sb);
 }
 
-void ext4_error_inode(struct inode *inode, const char *function,
-		      unsigned int line, ext4_fsblk_t block,
-		      const char *fmt, ...)
+void __ext4_error_inode(struct inode *inode, const char *function,
+			unsigned int line, ext4_fsblk_t block,
+			const char *fmt, ...)
 {
 	va_list args;
 	struct va_format vaf;
@@ -457,9 +457,9 @@ void ext4_error_inode(struct inode *inode, const char *function,
 	ext4_handle_error(inode->i_sb);
 }
 
-void ext4_error_file(struct file *file, const char *function,
-		     unsigned int line, ext4_fsblk_t block,
-		     const char *fmt, ...)
+void __ext4_error_file(struct file *file, const char *function,
+		       unsigned int line, ext4_fsblk_t block,
+		       const char *fmt, ...)
 {
 	va_list args;
 	struct va_format vaf;
@@ -591,7 +591,8 @@ void __ext4_abort(struct super_block *sb, const char *function,
 		panic("EXT4-fs panic from previous error\n");
 }
 
-void ext4_msg(struct super_block *sb, const char *prefix, const char *fmt, ...)
+void __ext4_msg(struct super_block *sb,
+		const char *prefix, const char *fmt, ...)
 {
 	struct va_format vaf;
 	va_list args;
-- 
cgit v1.2.3-59-g8ed1b


From 960fd856fdc3b08b3638f3f9b6b4bfceb77660c7 Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Fri, 5 Jul 2013 23:11:16 -0400
Subject: ext4: fix ext4_get_group_number()

The function ext4_get_group_number() was introduced as an optimization
in commit bd86298e60b8.  Unfortunately, this commit incorrectly
calculate the group number for file systems with a 1k block size (when
s_first_data_block is 1 instead of zero).  This could cause the
following kernel BUG:

[  568.877799] ------------[ cut here ]------------
[  568.877833] kernel BUG at fs/ext4/mballoc.c:3728!
[  568.877840] Oops: Exception in kernel mode, sig: 5 [#1]
[  568.877845] SMP NR_CPUS=32 NUMA pSeries
[  568.877852] Modules linked in: binfmt_misc
[  568.877861] CPU: 1 PID: 3516 Comm: fs_mark Not tainted 3.10.0-03216-g7c6809f-dirty #1
[  568.877867] task: c0000001fb0b8000 ti: c0000001fa954000 task.ti: c0000001fa954000
[  568.877873] NIP: c0000000002f42a4 LR: c0000000002f4274 CTR: c000000000317ef8
[  568.877879] REGS: c0000001fa956ed0 TRAP: 0700   Not tainted  (3.10.0-03216-g7c6809f-dirty)
[  568.877884] MSR: 8000000000029032 <SF,EE,ME,IR,DR,RI>  CR: 24000428  XER: 00000000
[  568.877902] SOFTE: 1
[  568.877905] CFAR: c0000000002b5464
[  568.877908]
GPR00: 0000000000000001 c0000001fa957150 c000000000c6a408 c0000001fb588000
GPR04: 0000000000003fff c0000001fa9571c0 c0000001fa9571c4 000138098c50625f
GPR08: 1301200000000000 0000000000000002 0000000000000001 0000000000000000
GPR12: 0000000024000422 c00000000f33a300 0000000000008000 c0000001fa9577f0
GPR16: c0000001fb7d0100 c000000000c29190 c0000000007f46e8 c000000000a14672
GPR20: 0000000000000001 0000000000000008 ffffffffffffffff 0000000000000000
GPR24: 0000000000000100 c0000001fa957278 c0000001fdb2bc78 c0000001fa957288
GPR28: 0000000000100100 c0000001fa957288 c0000001fb588000 c0000001fdb2bd10
[  568.877993] NIP [c0000000002f42a4] .ext4_mb_release_group_pa+0xec/0x1c0
[  568.877999] LR [c0000000002f4274] .ext4_mb_release_group_pa+0xbc/0x1c0
[  568.878004] Call Trace:
[  568.878008] [c0000001fa957150] [c0000000002f4274] .ext4_mb_release_group_pa+0xbc/0x1c0 (unreliable)
[  568.878017] [c0000001fa957200] [c0000000002fb070] .ext4_mb_discard_lg_preallocations+0x394/0x444
[  568.878025] [c0000001fa957340] [c0000000002fb45c] .ext4_mb_release_context+0x33c/0x734
[  568.878032] [c0000001fa957440] [c0000000002fbcf8] .ext4_mb_new_blocks+0x4a4/0x5f4
[  568.878039] [c0000001fa957510] [c0000000002ef56c] .ext4_ext_map_blocks+0xc28/0x1178
[  568.878047] [c0000001fa957640] [c0000000002c1a94] .ext4_map_blocks+0x2c8/0x490
[  568.878054] [c0000001fa957730] [c0000000002c536c] .ext4_writepages+0x738/0xc60
[  568.878062] [c0000001fa957950] [c000000000168a78] .do_writepages+0x5c/0x80
[  568.878069] [c0000001fa9579d0] [c00000000015d1c4] .__filemap_fdatawrite_range+0x88/0xb0
[  568.878078] [c0000001fa957aa0] [c00000000015d23c] .filemap_write_and_wait_range+0x50/0xfc
[  568.878085] [c0000001fa957b30] [c0000000002b8edc] .ext4_sync_file+0x220/0x3c4
[  568.878092] [c0000001fa957be0] [c0000000001f849c] .vfs_fsync_range+0x64/0x80
[  568.878098] [c0000001fa957c70] [c0000000001f84f0] .vfs_fsync+0x38/0x4c
[  568.878105] [c0000001fa957d00] [c0000000001f87f4] .do_fsync+0x54/0x90
[  568.878111] [c0000001fa957db0] [c0000000001f8894] .SyS_fsync+0x28/0x3c
[  568.878120] [c0000001fa957e30] [c000000000009c88] syscall_exit+0x0/0x7c
[  568.878125] Instruction dump:
[  568.878130] 60000000 813d0034 81610070 38000000 7f8b4800 419e001c 813f007c 7d2bfe70
[  568.878144] 7d604a78 7c005850 54000ffe 7c0007b4 <0b000000> e8a10076 e87f0090 7fa4eb78
[  568.878160] ---[ end trace 594d911d9654770b ]---

In addition fix the STD_GROUP optimization so that it works for
bigalloc file systems as well.

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Reported-by: Li Zhong <lizhongfs@gmail.com>
Reviewed-by: Lukas Czerner <lczerner@redhat.com>
Cc: stable@vger.kernel.org  # 3.10
---
 fs/ext4/balloc.c | 4 ++--
 fs/ext4/super.c  | 8 ++++----
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'fs/ext4/super.c')

diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 58339393fa6e..ddd715e42a5c 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -38,8 +38,8 @@ ext4_group_t ext4_get_group_number(struct super_block *sb,
 	ext4_group_t group;
 
 	if (test_opt2(sb, STD_GROUP_SIZE))
-		group = (le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) +
-			 block) >>
+		group = (block -
+			 le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) >>
 			(EXT4_BLOCK_SIZE_BITS(sb) + EXT4_CLUSTER_BITS(sb) + 3);
 	else
 		ext4_get_group_no_and_offset(sb, block, &group, NULL);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 85b3dd60169b..8862d4ddf71f 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3624,10 +3624,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb));
 	sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb));
 
-	/* Do we have standard group size of blocksize * 8 blocks ? */
-	if (sbi->s_blocks_per_group == blocksize << 3)
-		set_opt2(sb, STD_GROUP_SIZE);
-
 	for (i = 0; i < 4; i++)
 		sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
 	sbi->s_def_hash_version = es->s_def_hash_version;
@@ -3697,6 +3693,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount;
 	}
 
+	/* Do we have standard group size of clustersize * 8 blocks ? */
+	if (sbi->s_blocks_per_group == clustersize << 3)
+		set_opt2(sb, STD_GROUP_SIZE);
+
 	/*
 	 * Test whether we have more sectors than will fit in sector_t,
 	 * and whether the max offset is addressable by the page cache.
-- 
cgit v1.2.3-59-g8ed1b


From ad065dd01662ae22138899e6b1c8eeb3a529964f Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Thu, 11 Jul 2013 18:54:37 -0400
Subject: ext4: don't show usrquota/grpquota twice in /proc/mounts

We now print mount options in a generic fashion in
ext4_show_options(), so we shouldn't be explicitly printing the
{usr,grp}quota options in ext4_show_quota_options().

Without this patch, /proc/mounts can look like this:

 /dev/vdb /vdb ext4 rw,relatime,quota,usrquota,data=ordered,usrquota 0 0
                                      ^^^^^^^^              ^^^^^^^^

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Cc: stable@vger.kernel.org
---
 fs/ext4/super.c | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'fs/ext4/super.c')

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 8862d4ddf71f..bca26f34edf4 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1702,12 +1702,6 @@ static inline void ext4_show_quota_options(struct seq_file *seq,
 
 	if (sbi->s_qf_names[GRPQUOTA])
 		seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]);
-
-	if (test_opt(sb, USRQUOTA))
-		seq_puts(seq, ",usrquota");
-
-	if (test_opt(sb, GRPQUOTA))
-		seq_puts(seq, ",grpquota");
 #endif
 }
 
-- 
cgit v1.2.3-59-g8ed1b


From dd12ed144e9797094c04736f97aa27d5fe401476 Mon Sep 17 00:00:00 2001
From: Eric Sandeen <sandeen@redhat.com>
Date: Fri, 26 Jul 2013 15:21:11 -0400
Subject: ext4: destroy ext4_es_cachep on module unload

Without this, module can't be reloaded.

[  500.521980] kmem_cache_sanity_check (ext4_extent_status): Cache name already exists.

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Cc: stable@vger.kernel.org  # v3.8+
---
 fs/ext4/super.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'fs/ext4/super.c')

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index bca26f34edf4..36b141e420b7 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5481,6 +5481,7 @@ static void __exit ext4_exit_fs(void)
 	kset_unregister(ext4_kset);
 	ext4_exit_system_zone();
 	ext4_exit_pageio();
+	ext4_exit_es();
 }
 
 MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
-- 
cgit v1.2.3-59-g8ed1b


From 59d9fa5c2e9086db11aa287bb4030151d0095a17 Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Thu, 8 Aug 2013 23:01:24 -0400
Subject: ext4: allow the mount options nodelalloc and data=journal

Commit 26092bf ("ext4: use a table-driven handler for mount options")
wrongly disallows the specifying the mount options nodelalloc and
data=journal simultaneously.  This is incorrect; it should have only
disallowed the combination of delalloc and data=journal
simultaneously.

Reported-by: Piotr Sarna <p.sarna@partner.samsung.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Cc: stable@vger.kernel.org
---
 fs/ext4/super.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs/ext4/super.c')

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 36b141e420b7..75b3708b778e 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1359,7 +1359,7 @@ static const struct mount_opts {
 	{Opt_delalloc, EXT4_MOUNT_DELALLOC,
 	 MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
 	{Opt_nodelalloc, EXT4_MOUNT_DELALLOC,
-	 MOPT_EXT4_ONLY | MOPT_CLEAR | MOPT_EXPLICIT},
+	 MOPT_EXT4_ONLY | MOPT_CLEAR},
 	{Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
 	 MOPT_EXT4_ONLY | MOPT_SET},
 	{Opt_journal_async_commit, (EXT4_MOUNT_JOURNAL_ASYNC_COMMIT |
-- 
cgit v1.2.3-59-g8ed1b


From 6ae6514b33f941d3386da0dfbe2942766eab1577 Mon Sep 17 00:00:00 2001
From: Piotr Sarna <p.sarna@partner.samsung.com>
Date: Thu, 8 Aug 2013 23:02:24 -0400
Subject: ext4: fix mount/remount error messages for incompatible mount options

Commit 5688978 ("ext4: improve handling of conflicting mount options")
introduced incorrect messages shown while choosing wrong mount options.

First of all, both cases of incorrect mount options,
"data=journal,delalloc" and "data=journal,dioread_nolock" result in
the same error message.

Secondly, the problem above isn't solved for remount option: the
mismatched parameter is simply ignored.  Moreover, ext4_msg states
that remount with options "data=journal,delalloc" succeeded, which is
not true.

To fix it up, I added a simple check after parse_options() call to
ensure that data=journal and delalloc/dioread_nolock parameters are
not present at the same time.

Signed-off-by: Piotr Sarna <p.sarna@partner.samsung.com>
Acked-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Cc: stable@vger.kernel.org
---
 fs/ext4/super.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

(limited to 'fs/ext4/super.c')

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 75b3708b778e..b59373b625e9 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3483,7 +3483,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		}
 		if (test_opt(sb, DIOREAD_NOLOCK)) {
 			ext4_msg(sb, KERN_ERR, "can't mount with "
-				 "both data=journal and delalloc");
+				 "both data=journal and dioread_nolock");
 			goto failed_mount;
 		}
 		if (test_opt(sb, DELALLOC))
@@ -4727,6 +4727,21 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		goto restore_opts;
 	}
 
+	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
+		if (test_opt2(sb, EXPLICIT_DELALLOC)) {
+			ext4_msg(sb, KERN_ERR, "can't mount with "
+				 "both data=journal and delalloc");
+			err = -EINVAL;
+			goto restore_opts;
+		}
+		if (test_opt(sb, DIOREAD_NOLOCK)) {
+			ext4_msg(sb, KERN_ERR, "can't mount with "
+				 "both data=journal and dioread_nolock");
+			err = -EINVAL;
+			goto restore_opts;
+		}
+	}
+
 	if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
 		ext4_abort(sb, "Abort forced by user");
 
-- 
cgit v1.2.3-59-g8ed1b