[PATCH v1 1/3] pnfs/blocklayout: set PNFS_LAYOUTRETURN_ON_ERROR

[Benjamin Coddington <bcodding@redhat.com>]

If there's an error doing I/O to block device, and the client resends the
I/O to the MDS, the MDS must recall the layout from the client before
processing the I/O.  Let's preempt that exchange by returning the layout
before falling back to the MDS when there's an error.

Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
---
 fs/nfs/blocklayout/blocklayout.c | 2 ++
 fs/nfs/pnfs.h                    | 4 +++-
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index d8863a804b15..f66c9f2816a5 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -887,6 +887,7 @@ static struct pnfs_layoutdriver_type blocklayout_type = {
 	.name				= "LAYOUT_BLOCK_VOLUME",
 	.owner				= THIS_MODULE,
 	.flags				= PNFS_LAYOUTRET_ON_SETATTR |
+					  PNFS_LAYOUTRET_ON_ERROR |
 					  PNFS_READ_WHOLE_PAGE,
 	.read_pagelist			= bl_read_pagelist,
 	.write_pagelist			= bl_write_pagelist,
@@ -910,6 +911,7 @@ static struct pnfs_layoutdriver_type scsilayout_type = {
 	.name				= "LAYOUT_SCSI",
 	.owner				= THIS_MODULE,
 	.flags				= PNFS_LAYOUTRET_ON_SETATTR |
+					  PNFS_LAYOUTRET_ON_ERROR |
 					  PNFS_READ_WHOLE_PAGE,
 	.read_pagelist			= bl_read_pagelist,
 	.write_pagelist			= bl_write_pagelist,
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 99731e3e332f..4b4120b6824a 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -524,8 +524,10 @@ static inline int pnfs_return_layout(struct inode *ino)
 	struct nfs_inode *nfsi = NFS_I(ino);
 	struct nfs_server *nfss = NFS_SERVER(ino);
 
-	if (pnfs_enabled_sb(nfss) && nfsi->layout)
+	if (pnfs_enabled_sb(nfss) && nfsi->layout) {
+		set_bit(NFS_LAYOUT_RETURN_REQUESTED, &nfsi->layout->plh_flags);
 		return _pnfs_return_layout(ino);
+	}
 
 	return 0;
 }
-- 
2.9.3