Merge branch 'xfs-dax-fixes-for-4.5' into for-next

2 files changed, 24 insertions, 12 deletions

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index f5392ab2def1..ebe9b8290a70 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -402,19 +402,26 @@ xfs_file_splice_read(
         if (XFS_FORCED_SHUTDOWN(ip->i_mount))
                 return -EIO;
 
-        xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
-
         trace_xfs_file_splice_read(ip, count, *ppos, ioflags);
 
-        /* for dax, we need to avoid the page cache */
-        if (IS_DAX(VFS_I(ip)))
-                ret = default_file_splice_read(infilp, ppos, pipe, count, flags);
-        else
-                ret = generic_file_splice_read(infilp, ppos, pipe, count, flags);
-        if (ret > 0)
-                XFS_STATS_ADD(ip->i_mount, xs_read_bytes, ret);
+        /*
+         * DAX inodes cannot ues the page cache for splice, so we have to push
+         * them through the VFS IO path. This means it goes through
+         * ->read_iter, which for us takes the XFS_IOLOCK_SHARED. Hence we
+         * cannot lock the splice operation at this level for DAX inodes.
+         */
+        if (IS_DAX(VFS_I(ip))) {
+                ret = default_file_splice_read(infilp, ppos, pipe, count,
+                                               flags);
+                goto out;
+        }
 
+        xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
+        ret = generic_file_splice_read(infilp, ppos, pipe, count, flags);
         xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
+out:
+        if (ret > 0)
+                XFS_STATS_ADD(ip->i_mount, xs_read_bytes, ret);
         return ret;
 }
 
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index f4f5b43cf647..9ed146b96856 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -203,15 +203,20 @@ xfs_iomap_write_direct(
          * this outside the transaction context, but if we commit and then crash
          * we may not have zeroed the blocks and this will be exposed on
          * recovery of the allocation. Hence we must zero before commit.
+         *
          * Further, if we are mapping unwritten extents here, we need to zero
          * and convert them to written so that we don't need an unwritten extent
          * callback for DAX. This also means that we need to be able to dip into
-         * the reserve block pool if there is no space left but we need to do
-         * unwritten extent conversion.
+         * the reserve block pool for bmbt block allocation if there is no space
+         * left but we need to do unwritten extent conversion.
          */
+
         if (IS_DAX(VFS_I(ip))) {
                 bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO;
-                tp->t_flags |= XFS_TRANS_RESERVE;
+                if (ISUNWRITTEN(imap)) {
+                        tp->t_flags |= XFS_TRANS_RESERVE;
+                        resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0) << 1;
+                }
         }
         error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write,
                                   resblks, resrtextents);