Ocfs2 devel - Dec 2014 - [patch 03/15] ocfs2: call ocfs2_journal_access_di() before ocfs2_journal_dirty() in ocfs2_write_end_nolock()

From: yangwenfang <vicky.yangwenfang at huawei.com>
Subject: ocfs2: call ocfs2_journal_access_di() before ocfs2_journal_dirty() in
ocfs2_write_end_nolock()

After we call ocfs2_journal_access_di() in ocfs2_write_begin(),
jbd2_journal_restart() may also be called, in this function transaction
A's t_updates-- and obtains a new transaction B.  If
jbd2_journal_commit_transaction() is happened to commit transaction A,
when t_updates==0, it will continue to complete commit and unfile buffer.

So when jbd2_journal_dirty_metadata(), the handle is pointed a new
transaction B, and the buffer head's journal head is already freed,
jh->b_transaction == NULL, jh->b_next_transaction == NULL, it returns
EINVAL, So it triggers the BUG_ON(status).

thread 1:                             jbd2:
ocfs2_write_begin                     jbd2_journal_commit_transaction
ocfs2_write_begin_nolock
  ocfs2_start_trans
    jbd2__journal_start(t_updates+1,
                       transaction A)
    ocfs2_journal_access_di
    ocfs2_write_cluster_by_desc
      ocfs2_mark_extent_written
        ocfs2_change_extent_flag
          ocfs2_split_extent
            ocfs2_extend_rotate_transaction
              jbd2_journal_restart
              (t_updates-1,transaction B) t_updates==0
                                        __jbd2_journal_refile_buffer

ocfs2_write_end
ocfs2_write_end_nolock
    ocfs2_journal_dirty
        jbd2_journal_dirty_metadata(bug)
   ocfs2_commit_trans

In ext4, I found that: jbd2_journal_get_write_access() called by

ext4_write_end.
ext4_write_begin
    ext4_journal_start
        __ext4_journal_start_sb
            ext4_journal_check_start
            jbd2__journal_start

ext4_write_end
    ext4_mark_inode_dirty
        ext4_reserve_inode_write
            ext4_journal_get_write_access
                jbd2_journal_get_write_access
        ext4_mark_iloc_dirty
            ext4_do_update_inode
                ext4_handle_dirty_metadata
                    jbd2_journal_dirty_metadata


So I think we should put ocfs2_journal_access_di before
  ocfs2_journal_dirty in the ocfs2_write_end.  and it works well after my
  modification.

Signed-off-by: vicky <vicky.yangwenfang at huawei.com>
Cc: Mark Fasheh <mfasheh at suse.com>
Cc: Joel Becker <jlbec at evilplan.org>
Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
---

 fs/ocfs2/aops.c |   21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff -puN
fs/ocfs2/aops.c~ocfs2-call-ocfs2_journal_access_di-before-ocfs2_journal_dirty-in-ocfs2_write_end_nolock
fs/ocfs2/aops.c
---
a/fs/ocfs2/aops.c~ocfs2-call-ocfs2_journal_access_di-before-ocfs2_journal_dirty-in-ocfs2_write_end_nolock
+++ a/fs/ocfs2/aops.c
@@ -1818,16 +1818,6 @@ try_again:
 		if (ret)
 			goto out_commit;
 	}
-	/*
-	 * We don't want this to fail in ocfs2_write_end(), so do it
-	 * here.
-	 */
-	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
-				      OCFS2_JOURNAL_ACCESS_WRITE);
-	if (ret) {
-		mlog_errno(ret);
-		goto out_quota;
-	}
 
 	/*
 	 * Fill our page array first. That way we've grabbed enough so
@@ -1978,7 +1968,7 @@ int ocfs2_write_end_nolock(struct addres
 			   loff_t pos, unsigned len, unsigned copied,
 			   struct page *page, void *fsdata)
 {
-	int i;
+	int i, ret;
 	unsigned from, to, start = pos & (PAGE_CACHE_SIZE - 1);
 	struct inode *inode = mapping->host;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
@@ -2028,6 +2018,14 @@ int ocfs2_write_end_nolock(struct addres
 		}
 	}
 
+	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		copied = ret;
+		mlog_errno(ret);
+		goto out;
+	}
+
 out_write_size:
 	pos += copied;
 	if (pos > i_size_read(inode)) {
@@ -2042,6 +2040,7 @@ out_write_size:
 	ocfs2_update_inode_fsync_trans(handle, inode, 1);
 	ocfs2_journal_dirty(handle, wc->w_di_bh);
 
+out:
 	ocfs2_commit_trans(osb, handle);
 
 	ocfs2_run_deallocs(osb, &wc->w_dealloc);
_

So I now have a mess on my hands due to reordering
ocfs2-fix-journal-commit-deadlock.patch ahead of this patch.

It concerns the label "out:".  Should it be placed before or after the
call to ocfs2_unlock_pages()?

My current copy of ocfs2_write_end_nolock() is below, followed by my
current version of
ocfs2-call-ocfs2_journal_access_di-before-ocfs2_journal_dirty-in-ocfs2_write_end_nolock.patch

Thanks.

int ocfs2_write_end_nolock(struct address_space *mapping,
			   loff_t pos, unsigned len, unsigned copied,
			   struct page *page, void *fsdata)
{
	int i, ret;
	unsigned from, to, start = pos & (PAGE_CACHE_SIZE - 1);
	struct inode *inode = mapping->host;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	struct ocfs2_write_ctxt *wc = fsdata;
	struct ocfs2_dinode *di = (struct ocfs2_dinode *)wc->w_di_bh->b_data;
	handle_t *handle = wc->w_handle;
	struct page *tmppage;

	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
		ocfs2_write_end_inline(inode, pos, len, &copied, di, wc);
		goto out_write_size;
	}

	if (unlikely(copied < len)) {
		if (!PageUptodate(wc->w_target_page))
			copied = 0;

		ocfs2_zero_new_buffers(wc->w_target_page, start+copied,
				       start+len);
	}
	flush_dcache_page(wc->w_target_page);

	for(i = 0; i < wc->w_num_pages; i++) {
		tmppage = wc->w_pages[i];

		if (tmppage == wc->w_target_page) {
			from = wc->w_target_from;
			to = wc->w_target_to;

			BUG_ON(from > PAGE_CACHE_SIZE ||
			       to > PAGE_CACHE_SIZE ||
			       to < from);
		} else {
			/*
			 * Pages adjacent to the target (if any) imply
			 * a hole-filling write in which case we want
			 * to flush their entire range.
			 */
			from = 0;
			to = PAGE_CACHE_SIZE;
		}

		if (page_has_buffers(tmppage)) {
			if (ocfs2_should_order_data(inode))
				ocfs2_jbd2_file_inode(wc->w_handle, inode);
			block_commit_write(tmppage, from, to);
		}
	}

	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
				      OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret) {
		copied = ret;
		mlog_errno(ret);
		goto out;
	}

out_write_size:
	pos += copied;
	if (pos > i_size_read(inode)) {
		i_size_write(inode, pos);
		mark_inode_dirty(inode);
	}
	inode->i_blocks = ocfs2_inode_sector_count(inode);
	di->i_size = cpu_to_le64((u64)i_size_read(inode));
	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
	di->i_mtime_nsec = di->i_ctime_nsec =
cpu_to_le32(inode->i_mtime.tv_nsec);
	ocfs2_update_inode_fsync_trans(handle, inode, 1);
	ocfs2_journal_dirty(handle, wc->w_di_bh);

	/* unlock pages before dealloc since it needs acquiring j_trans_barrier
	 * lock, or it will cause a deadlock since journal commit threads holds
	 * this lock and will ask for the page lock when flushing the data.
	 * put it here to preserve the unlock order.
	 */
	ocfs2_unlock_pages(wc);

out:
	ocfs2_commit_trans(osb, handle);

	ocfs2_run_deallocs(osb, &wc->w_dealloc);

	brelse(wc->w_di_bh);
	kfree(wc);

	return copied;
}


From: yangwenfang <vicky.yangwenfang at huawei.com>
Subject: ocfs2: call ocfs2_journal_access_di() before ocfs2_journal_dirty() in
ocfs2_write_end_nolock()

After we call ocfs2_journal_access_di() in ocfs2_write_begin(),
jbd2_journal_restart() may also be called, in this function transaction
A's t_updates-- and obtains a new transaction B.  If
jbd2_journal_commit_transaction() is happened to commit transaction A,
when t_updates==0, it will continue to complete commit and unfile buffer.

So when jbd2_journal_dirty_metadata(), the handle is pointed a new
transaction B, and the buffer head's journal head is already freed,
jh->b_transaction == NULL, jh->b_next_transaction == NULL, it returns
EINVAL, So it triggers the BUG_ON(status).

thread 1:                             jbd2:
ocfs2_write_begin                     jbd2_journal_commit_transaction
ocfs2_write_begin_nolock
  ocfs2_start_trans
    jbd2__journal_start(t_updates+1,
                       transaction A)
    ocfs2_journal_access_di
    ocfs2_write_cluster_by_desc
      ocfs2_mark_extent_written
        ocfs2_change_extent_flag
          ocfs2_split_extent
            ocfs2_extend_rotate_transaction
              jbd2_journal_restart
              (t_updates-1,transaction B) t_updates==0
                                        __jbd2_journal_refile_buffer

ocfs2_write_end
ocfs2_write_end_nolock
    ocfs2_journal_dirty
        jbd2_journal_dirty_metadata(bug)
   ocfs2_commit_trans

In ext4, I found that: jbd2_journal_get_write_access() called by

ext4_write_end.
ext4_write_begin
    ext4_journal_start
        __ext4_journal_start_sb
            ext4_journal_check_start
            jbd2__journal_start

ext4_write_end
    ext4_mark_inode_dirty
        ext4_reserve_inode_write
            ext4_journal_get_write_access
                jbd2_journal_get_write_access
        ext4_mark_iloc_dirty
            ext4_do_update_inode
                ext4_handle_dirty_metadata
                    jbd2_journal_dirty_metadata


So I think we should put ocfs2_journal_access_di before
  ocfs2_journal_dirty in the ocfs2_write_end.  and it works well after my
  modification.

Signed-off-by: vicky <vicky.yangwenfang at huawei.com>
Cc: Mark Fasheh <mfasheh at suse.com>
Cc: Joel Becker <jlbec at evilplan.org>
Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
---

 fs/ocfs2/aops.c |   21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff -puN
fs/ocfs2/aops.c~ocfs2-call-ocfs2_journal_access_di-before-ocfs2_journal_dirty-in-ocfs2_write_end_nolock
fs/ocfs2/aops.c
---
a/fs/ocfs2/aops.c~ocfs2-call-ocfs2_journal_access_di-before-ocfs2_journal_dirty-in-ocfs2_write_end_nolock
+++ a/fs/ocfs2/aops.c
@@ -1822,16 +1822,6 @@ try_again:
 		if (ret)
 			goto out_commit;
 	}
-	/*
-	 * We don't want this to fail in ocfs2_write_end(), so do it
-	 * here.
-	 */
-	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
-				      OCFS2_JOURNAL_ACCESS_WRITE);
-	if (ret) {
-		mlog_errno(ret);
-		goto out_quota;
-	}
 
 	/*
 	 * Fill our page array first. That way we've grabbed enough so
@@ -1982,7 +1972,7 @@ int ocfs2_write_end_nolock(struct addres
 			   loff_t pos, unsigned len, unsigned copied,
 			   struct page *page, void *fsdata)
 {
-	int i;
+	int i, ret;
 	unsigned from, to, start = pos & (PAGE_CACHE_SIZE - 1);
 	struct inode *inode = mapping->host;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
@@ -2032,6 +2022,14 @@ int ocfs2_write_end_nolock(struct addres
 		}
 	}
 
+	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		copied = ret;
+		mlog_errno(ret);
+		goto out;
+	}
+
 out_write_size:
 	pos += copied;
 	if (pos > i_size_read(inode)) {
@@ -2053,6 +2051,7 @@ out_write_size:
 	 */
 	ocfs2_unlock_pages(wc);
 
+out:
 	ocfs2_commit_trans(osb, handle);
 
 	ocfs2_run_deallocs(osb, &wc->w_dealloc);
_