NFSv4 fix CLOSE not waiting for direct IO compeletion

Figuring out the root case for the REMOVE/CLOSE race and
suggesting the solution was done by Neil Brown.

Currently what happens is that direct IO calls hold a reference
on the open context which is decremented as an asynchronous task
in the nfs_direct_complete(). Before reference is decremented,
control is returned to the application which is free to close the
file. When close is being processed, it decrements its reference
on the open_context but since directIO still holds one, it doesn't
sent a close on the wire. It returns control to the application
which is free to do other operations. For instance, it can delete a
file. Direct IO is finally releasing its reference and triggering
an asynchronous close. Which races with the REMOVE. On the server,
REMOVE can be processed before the CLOSE, failing the REMOVE with
EACCES as the file is still opened.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
Suggested-by: Neil Brown <neilb@suse.com>
CC: stable@vger.kernel.org
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 1b79dd5cf66160c4de72c5dcc50c456950a6a6fd..3d113cf8908ac93b63276197d09f4330132aca6d 100644 (file)
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -267,8 +267,6 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq)
 {
        struct inode *inode = dreq->inode;
 
-       inode_dio_end(inode);
-
        if (dreq->iocb) {
                long res = (long) dreq->error;
                if (dreq->count != 0) {
@@ -280,7 +278,10 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq)
 
        complete(&dreq->completion);
 
+       igrab(inode);
        nfs_direct_req_release(dreq);
+       inode_dio_end(inode);
+       iput(inode);
 }
 
 static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
@@ -410,8 +411,10 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
         * generic layer handle the completion.
         */
        if (requested_bytes == 0) {
-               inode_dio_end(inode);
+               igrab(inode);
                nfs_direct_req_release(dreq);
+               inode_dio_end(inode);
+               iput(inode);
                return result < 0 ? result : -EIO;
        }
 
@@ -864,8 +867,10 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
         * generic layer handle the completion.
         */
        if (requested_bytes == 0) {
-               inode_dio_end(inode);
+               igrab(inode);
                nfs_direct_req_release(dreq);
+               inode_dio_end(inode);
+               iput(inode);
                return result < 0 ? result : -EIO;
        }
 

diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index f96367a2463e37a355d777fdfe4314eeb561191e..ccd6c1637b270b213c44e1d73775c37ae3ef05ae 100644 (file)
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -83,6 +83,7 @@ nfs_file_release(struct inode *inode, struct file *filp)
        dprintk("NFS: release(%pD2)\n", filp);
 
        nfs_inc_stats(inode, NFSIOS_VFSRELEASE);
+       inode_dio_wait(inode);
        nfs_file_clear_open_context(filp);
        return 0;
 }