linux-toradex.git/fs/nfs/blocklayout, branch v3.7.2

pnfsblock: cleanup nfs4_blkdev_get

2012-10-08T23:32:40+00:00

It is not needed at all and it is messing with return values...

Reported-by: Wei Yongjun 
Signed-off-by: Peng Tao 
Signed-off-by: Trond Myklebust

NFS41: send real write size in layoutget

2012-10-08T23:32:22+00:00

For buffer write, block layout client scan inode mapping to find
next hole and use offset-to-hole as layoutget length. Object
layout client uses offset-to-isize as layoutget length.

For direct write, both block layout and object layout use dreq->bytes_left.

Signed-off-by: Peng Tao 
Signed-off-by: Trond Myklebust

NFSv4.1: bl_pg_init_write should be static

2012-10-02T15:34:29+00:00

Reported-by: Fengguang Wu 
Signed-off-by: Trond Myklebust

pnfsblock: use list_move_tail instead of list_del/list_add_tail

2012-10-01T22:39:05+00:00

Using list_move_tail() instead of list_del() + list_add_tail().

spatch with a semantic match is used to found this problem.
(http://coccinelle.lip6.fr/)

Signed-off-by: Wei Yongjun 
Signed-off-by: Trond Myklebust

pnfsblock: fix non-aligned DIO write

2012-10-01T22:38:35+00:00

For DIO writes, if it is not blocksize aligned, we need to do
internal serialization. It may slow down writers anyway. So we
just bail them out and resend to MDS.

Cc: stable  [since v3.4]
Signed-off-by: Peng Tao 
Signed-off-by: Trond Myklebust

pnfsblock: fix non-aligned DIO read

2012-10-01T22:38:29+00:00

For DIO read, if it is not sector aligned, we should reject it
and resend via MDS. Otherwise there might be data corruption.
Also teach bl_read_pagelist to handle partial page reads for DIO.

Cc: stable  [since v3.4]
Signed-off-by: Peng Tao 
Signed-off-by: Trond Myklebust

pnfsblock: fix partial page buffer wirte

2012-10-01T22:38:24+00:00

If applications use flock to protect its write range, generic NFS
will not do read-modify-write cycle at page cache level. Therefore
LD should know how to handle non-sector aligned writes. Otherwise
there will be data corruption.

Cc: stable 
Signed-off-by: Peng Tao 
Signed-off-by: Trond Myklebust

Revert "pnfsblock: bail out partial page IO"

2012-10-01T22:38:16+00:00

This reverts commit 159e0561e322dd8008fff59e36efff8d2bdd0b0e, in favor
of a more complete fix to the alignment issue.

Signed-off-by: Peng Tao 
Signed-off-by: Trond Myklebust

NFSv4.1: Replace get_device_info() with filelayout_get_device_info()

2012-09-28T20:03:08+00:00

Fix the namespace pollution issue.

Signed-off-by: Trond Myklebust

pnfsblock: bail out partial page IO

2012-07-30T22:52:06+00:00

Current block layout driver read/write code assumes page
aligned IO in many places. Add a checker to validate the assumption.
Otherwise there would be data corruption like when application does
open(O_WRONLY) and page unaliged write.

Signed-off-by: Peng Tao 
Signed-off-by: Trond Myklebust