gfs2: Fix iomap write page reclaim deadlock

Since commit 64bc06bb32ee ("gfs2: iomap buffered write support"), gfs2 is doing
buffered writes by starting a transaction in iomap_begin, writing a range of
pages, and ending that transaction in iomap_end.  This approach suffers from
two problems:

  (1) Any allocations necessary for the write are done in iomap_begin, so when
  the data aren't journaled, there is no need for keeping the transaction open
  until iomap_end.

  (2) Transactions keep the gfs2 log flush lock held.  When
  iomap_file_buffered_write calls balance_dirty_pages, this can end up calling
  gfs2_write_inode, which will try to flush the log.  This requires taking the
  log flush lock which is already held, resulting in a deadlock.

Fix both of these issues by not keeping transactions open from iomap_begin to
iomap_end.  Instead, start a small transaction in page_prepare and end it in
page_done when necessary.

Reported-by: Edwin Török <edvin.torok@citrix.com>
Fixes: 64bc06bb32ee ("gfs2: iomap buffered write support")
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Bob Peterson <rpeterso@redhat.com>

1 files changed, 48 insertions, 40 deletions

diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 6f1f0d30fe29..f42718dd292f 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -991,17 +991,28 @@ static void gfs2_write_unlock(struct inode *inode)
 	gfs2_glock_dq_uninit(&ip->i_gh);
 }
 
+static int gfs2_iomap_page_prepare(struct inode *inode, loff_t pos,
+				   unsigned len, struct iomap *iomap)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+
+	return gfs2_trans_begin(sdp, RES_DINODE + (len >> inode->i_blkbits), 0);
+}
+
 static void gfs2_iomap_page_done(struct inode *inode, loff_t pos,
 				 unsigned copied, struct page *page,
 				 struct iomap *iomap)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
 
-	if (page)
+	if (page && !gfs2_is_stuffed(ip))
 		gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied);
+	gfs2_trans_end(sdp);
 }
 
 static const struct iomap_page_ops gfs2_iomap_page_ops = {
+	.page_prepare = gfs2_iomap_page_prepare,
 	.page_done = gfs2_iomap_page_done,
 };
 
@@ -1057,31 +1068,45 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
 	if (alloc_required)
 		rblocks += gfs2_rg_blocks(ip, data_blocks + ind_blocks);
 
-	ret = gfs2_trans_begin(sdp, rblocks, iomap->length >> inode->i_blkbits);
-	if (ret)
-		goto out_trans_fail;
+	if (unstuff || iomap->type == IOMAP_HOLE) {
+		struct gfs2_trans *tr;
 
-	if (unstuff) {
-		ret = gfs2_unstuff_dinode(ip, NULL);
+		ret = gfs2_trans_begin(sdp, rblocks,
+				       iomap->length >> inode->i_blkbits);
 		if (ret)
-			goto out_trans_end;
-		release_metapath(mp);
-		ret = gfs2_iomap_get(inode, iomap->offset, iomap->length,
-				     flags, iomap, mp);
-		if (ret)
-			goto out_trans_end;
-	}
+			goto out_trans_fail;
 
-	if (iomap->type == IOMAP_HOLE) {
-		ret = gfs2_iomap_alloc(inode, iomap, flags, mp);
-		if (ret) {
-			gfs2_trans_end(sdp);
-			gfs2_inplace_release(ip);
-			punch_hole(ip, iomap->offset, iomap->length);
-			goto out_qunlock;
+		if (unstuff) {
+			ret = gfs2_unstuff_dinode(ip, NULL);
+			if (ret)
+				goto out_trans_end;
+			release_metapath(mp);
+			ret = gfs2_iomap_get(inode, iomap->offset,
+					     iomap->length, flags, iomap, mp);
+			if (ret)
+				goto out_trans_end;
+		}
+
+		if (iomap->type == IOMAP_HOLE) {
+			ret = gfs2_iomap_alloc(inode, iomap, flags, mp);
+			if (ret) {
+				gfs2_trans_end(sdp);
+				gfs2_inplace_release(ip);
+				punch_hole(ip, iomap->offset, iomap->length);
+				goto out_qunlock;
+			}
 		}
+
+		tr = current->journal_info;
+		if (tr->tr_num_buf_new)
+			__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+		else
+			gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[0]);
+
+		gfs2_trans_end(sdp);
 	}
-	if (!gfs2_is_stuffed(ip) && gfs2_is_jdata(ip))
+
+	if (gfs2_is_stuffed(ip) || gfs2_is_jdata(ip))
 		iomap->page_ops = &gfs2_iomap_page_ops;
 	return 0;
 
@@ -1121,10 +1146,6 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
 		    iomap->type != IOMAP_MAPPED)
 			ret = -ENOTBLK;
 	}
-	if (!ret) {
-		get_bh(mp.mp_bh[0]);
-		iomap->private = mp.mp_bh[0];
-	}
 	release_metapath(&mp);
 	trace_gfs2_iomap_end(ip, iomap, ret);
 	return ret;
@@ -1135,27 +1156,16 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length,
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	struct gfs2_trans *tr = current->journal_info;
-	struct buffer_head *dibh = iomap->private;
 
 	if ((flags & (IOMAP_WRITE | IOMAP_DIRECT)) != IOMAP_WRITE)
 		goto out;
 
-	if (iomap->type != IOMAP_INLINE) {
+	if (!gfs2_is_stuffed(ip))
 		gfs2_ordered_add_inode(ip);
 
-		if (tr->tr_num_buf_new)
-			__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
-		else
-			gfs2_trans_add_meta(ip->i_gl, dibh);
-	}
-
-	if (inode == sdp->sd_rindex) {
+	if (inode == sdp->sd_rindex)
 		adjust_fs_space(inode);
-		sdp->sd_rindex_uptodate = 0;
-	}
 
-	gfs2_trans_end(sdp);
 	gfs2_inplace_release(ip);
 
 	if (length != written && (iomap->flags & IOMAP_F_NEW)) {
@@ -1175,8 +1185,6 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length,
 	gfs2_write_unlock(inode);
 
 out:
-	if (dibh)
-		brelse(dibh);
 	return 0;
 }