[PATCH 0/1] nilfs2: fix device cache flush in nilfs_sync_fs()

[Ryusuke Konishi]

Hi Andrew,

Please add the following patch to the queue for the next merge window.

It ensures that nilfs_sync_fs() function sends a cache flush request
to the underlying device when required. The current nilfs_sync_fs()
has a defect that it can skip the flush if only a small amount of data
is written. The original cover letter can be seen at:

[1] http://marc.info/?l=linux-nilfs&m=141061909728506
"[PATCH v6 0/1] nilfs2: add missing blkdev_issue_flush() to
nilfs_sync_fs()"

Thanks,
Ryusuke Konishi
--
Andreas Rohner (1):
nilfs2: add missing blkdev_issue_flush() to nilfs_sync_fs()

fs/nilfs2/file.c | 8 +++-----
fs/nilfs2/ioctl.c | 8 +++-----
fs/nilfs2/segment.c | 3 +++
fs/nilfs2/super.c | 6 ++++++
fs/nilfs2/the_nilfs.h | 22 ++++++++++++++++++++++
5 files changed, 37 insertions(+), 10 deletions(-)

--
To unsubscribe from this list: send the line "unsubscribe linux-nilfs" in
the body of a message to majordomo-***@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html

[Ryusuke Konishi]

From: Andreas Rohner <***@gmx.net>

Under normal circumstances nilfs_sync_fs() writes out the super block,
which causes a flush of the underlying block device. But this depends on
the THE_NILFS_SB_DIRTY flag, which is only set if the pointer to the
last segment crosses a segment boundary. So if only a small amount of
data is written before the call to nilfs_sync_fs(), no flush of the
block device occurs.

In the above case an additional call to blkdev_issue_flush() is needed.
To prevent unnecessary overhead, the new flag nilfs->ns_flushed_device
is introduced, which is cleared whenever new logs are written and set
whenever the block device is flushed. For convenience the function
nilfs_flush_device() is added, which contains the above logic.

Signed-off-by: Andreas Rohner <***@gmx.net>
Signed-off-by: Ryusuke Konishi <***@lab.ntt.co.jp>
---
fs/nilfs2/file.c | 8 +++-----
fs/nilfs2/ioctl.c | 8 +++-----
fs/nilfs2/segment.c | 3 +++
fs/nilfs2/super.c | 6 ++++++
fs/nilfs2/the_nilfs.h | 22 ++++++++++++++++++++++
5 files changed, 37 insertions(+), 10 deletions(-)

diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index 2497815..e9e3325 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -56,11 +56,9 @@ int nilfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
mutex_unlock(&inode->i_mutex);

nilfs = inode->i_sb->s_fs_info;
- if (!err && nilfs_test_opt(nilfs, BARRIER)) {
- err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
- if (err != -EIO)
- err = 0;
- }
+ if (!err)
+ err = nilfs_flush_device(nilfs);
+
return err;
}

diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 422fb54..9a20e51 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -1022,11 +1022,9 @@ static int nilfs_ioctl_sync(struct inode *inode, struct file *filp,
return ret;

nilfs = inode->i_sb->s_fs_info;
- if (nilfs_test_opt(nilfs, BARRIER)) {
- ret = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
- if (ret == -EIO)
- return ret;
- }
+ ret = nilfs_flush_device(nilfs);
+ if (ret < 0)
+ return ret;

if (argp != NULL) {
down_read(&nilfs->ns_segctor_sem);
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index a1a1916..0b7d2ca 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -1833,6 +1833,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
nilfs_set_next_segment(nilfs, segbuf);

if (update_sr) {
+ nilfs->ns_flushed_device = 0;
nilfs_set_last_segment(nilfs, segbuf->sb_pseg_start,
segbuf->sb_sum.seg_seq, nilfs->ns_cno++);

@@ -2216,6 +2217,8 @@ int nilfs_construct_dsync_segment(struct super_block *sb, struct inode *inode,
sci->sc_dsync_end = end;

err = nilfs_segctor_do_construct(sci, SC_LSEG_DSYNC);
+ if (!err)
+ nilfs->ns_flushed_device = 0;

nilfs_transaction_unlock(sb);
return err;
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 228f5bd..2e5b3ec 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -310,6 +310,9 @@ int nilfs_commit_super(struct super_block *sb, int flag)
nilfs->ns_sbsize));
}
clear_nilfs_sb_dirty(nilfs);
+ nilfs->ns_flushed_device = 1;
+ /* make sure store to ns_flushed_device cannot be reordered */
+ smp_wmb();
return nilfs_sync_super(sb, flag);
}

@@ -514,6 +517,9 @@ static int nilfs_sync_fs(struct super_block *sb, int wait)
}
up_write(&nilfs->ns_sem);

+ if (!err)
+ err = nilfs_flush_device(nilfs);
+
return err;
}

diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index d01ead1..23778d3 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -46,6 +46,7 @@ enum {
/**
* struct the_nilfs - struct to supervise multiple nilfs mount points
* @ns_flags: flags
+ * @ns_flushed_device: flag indicating if all volatile data was flushed
* @ns_bdev: block device
* @ns_sem: semaphore for shared states
* @ns_snapshot_mount_mutex: mutex to protect snapshot mounts
@@ -103,6 +104,7 @@ enum {
*/
struct the_nilfs {
unsigned long ns_flags;
+ int ns_flushed_device;

struct block_device *ns_bdev;
struct rw_semaphore ns_sem;
@@ -371,4 +373,24 @@ static inline int nilfs_segment_is_active(struct the_nilfs *nilfs, __u64 n)
return n == nilfs->ns_segnum || n == nilfs->ns_nextnum;
}

+static inline int nilfs_flush_device(struct the_nilfs *nilfs)
+{
+ int err;
+
+ if (!nilfs_test_opt(nilfs, BARRIER) || nilfs->ns_flushed_device)
+ return 0;
+
+ nilfs->ns_flushed_device = 1;
+ /*
+ * the store to ns_flushed_device must not be reordered after
+ * blkdev_issue_flush().
+ */
+ smp_wmb();
+
+ err = blkdev_issue_flush(nilfs->ns_bdev, GFP_KERNEL, NULL);
+ if (err != -EIO)
+ err = 0;
+ return err;
+}
+
#endif /* _THE_NILFS_H */