summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorTrond Myklebust <trond.myklebust@primarydata.com>2016-09-04 12:46:35 -0400
committerTrond Myklebust <trond.myklebust@primarydata.com>2016-09-04 12:59:00 -0400
commit334a8f37115bf35e38617315a360a91ac4f2b2c6 (patch)
treeb07b98d2a766ca6faa34d80e0e2ba778a74bcc77 /fs
parent52ec7be2e27392201adf77892ba883f68df88c99 (diff)
pNFS: Don't forget the layout stateid if there are outstanding LAYOUTGETs
If there are outstanding LAYOUTGET rpc calls, then we want to ensure that we keep the layout stateid around so we that don't inadvertently pick up an old/misordered sequence id. The race is as follows: Client Server ====== ====== LAYOUTGET(seqid) LAYOUTGET(seqid) return LAYOUTGET(seqid+1) return LAYOUTGET(seqid+2) process LAYOUTGET(seqid+2) forget layout process LAYOUTGET(seqid+1) If it forgets the layout stateid before processing seqid+1, then the client will not check the layout->plh_barrier, and so will set the stateid with seqid+1. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Diffstat (limited to 'fs')
-rw-r--r--fs/nfs/pnfs.c3
1 files changed, 2 insertions, 1 deletions
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index cd8b5fca33f6..2c93a85eda51 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -365,7 +365,8 @@ pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo,
/* Matched by pnfs_get_layout_hdr in pnfs_layout_insert_lseg */
atomic_dec(&lo->plh_refcount);
if (list_empty(&lo->plh_segs)) {
- set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
+ if (atomic_read(&lo->plh_outstanding) == 0)
+ set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
clear_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
}
rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq);