Merge tag 'nfs-for-4.2-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client bugfixes from Trond Myklebust:
 "Highlights include:

  Stable patches:
   - Fix a situation where the client uses the wrong (zero) stateid.
   - Fix a memory leak in nfs_do_recoalesce

  Bugfixes:
   - Plug a memory leak when ->prepare_layoutcommit fails
   - Fix an Oops in the NFSv4 open code
   - Fix a backchannel deadlock
   - Fix a livelock in sunrpc when sendmsg fails due to low memory
     availability
   - Don't revalidate the mapping if both size and change attr are up to
     date
   - Ensure we don't miss a file extension when doing pNFS
   - Several fixes to handle NFSv4.1 sequence operation status bits
     correctly
   - Several pNFS layout return bugfixes"

* tag 'nfs-for-4.2-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (28 commits)
  nfs: Fix an oops caused by using other thread's stack space in ASYNC mode
  nfs: plug memory leak when ->prepare_layoutcommit fails
  SUNRPC: Report TCP errors to the caller
  sunrpc: translate -EAGAIN to -ENOBUFS when socket is writable.
  NFSv4.2: handle NFS-specific llseek errors
  NFS: Don't clear desc->pg_moreio in nfs_do_recoalesce()
  NFS: Fix a memory leak in nfs_do_recoalesce
  NFS: nfs_mark_for_revalidate should always set NFS_INO_REVAL_PAGECACHE
  NFS: Remove the "NFS_CAP_CHANGE_ATTR" capability
  NFS: Set NFS_INO_REVAL_PAGECACHE if the change attribute is uninitialised
  NFS: Don't revalidate the mapping if both size and change attr are up to date
  NFSv4/pnfs: Ensure we don't miss a file extension
  NFSv4: We must set NFS_OPEN_STATE flag in nfs_resync_open_stateid_locked
  SUNRPC: xprt_complete_bc_request must also decrement the free slot count
  SUNRPC: Fix a backchannel deadlock
  pNFS: Don't throw out valid layout segments
  pNFS: pnfs_roc_drain() fix a race with open
  pNFS: Fix races between return-on-close and layoutreturn.
  pNFS: pnfs_roc_drain should return 'true' when sleeping
  pNFS: Layoutreturn must invalidate all existing layout segments.
  ...

net/sunrpc/backchannel_rqst.c

@@ -240,8 +240,8 @@ static struct rpc_rqst *xprt_alloc_bc_request(struct rpc_xprt *xprt, __be32 xid)
 		req = xprt_alloc_bc_req(xprt, GFP_ATOMIC);
 		if (!req)
 			goto not_found;
-		/* Note: this 'free' request adds it to xprt->bc_pa_list */
-		xprt_free_bc_request(req);
+		list_add_tail(&req->rq_bc_pa_list, &xprt->bc_pa_list);
+		xprt->bc_alloc_count++;
 	}
 	req = list_first_entry(&xprt->bc_pa_list, struct rpc_rqst,
 				rq_bc_pa_list);
@@ -336,7 +336,7 @@ void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied)
 
 	spin_lock(&xprt->bc_pa_lock);
 	list_del(&req->rq_bc_pa_list);
-	xprt->bc_alloc_count--;
+	xprt_dec_alloc_count(xprt, 1);
 	spin_unlock(&xprt->bc_pa_lock);
 
 	req->rq_private_buf.len = copied;

net/sunrpc/clnt.c

@@ -1902,6 +1902,7 @@ call_transmit_status(struct rpc_task *task)
 
 	switch (task->tk_status) {
 	case -EAGAIN:
+	case -ENOBUFS:
 		break;
 	default:
 		dprint_status(task);
@@ -1928,7 +1929,6 @@ call_transmit_status(struct rpc_task *task)
 	case -ECONNABORTED:
 	case -EADDRINUSE:
 	case -ENOTCONN:
-	case -ENOBUFS:
 	case -EPIPE:
 		rpc_task_force_reencode(task);
 	}
@@ -2057,12 +2057,13 @@ call_status(struct rpc_task *task)
 	case -ECONNABORTED:
 		rpc_force_rebind(clnt);
 	case -EADDRINUSE:
-	case -ENOBUFS:
 		rpc_delay(task, 3*HZ);
 	case -EPIPE:
 	case -ENOTCONN:
 		task->tk_action = call_bind;
 		break;
+	case -ENOBUFS:
+		rpc_delay(task, HZ>>2);
 	case -EAGAIN:
 		task->tk_action = call_transmit;
 		break;

net/sunrpc/xprtsock.c

@@ -527,6 +527,10 @@ static int xs_local_send_request(struct rpc_task *task)
 			      true, &sent);
 	dprintk("RPC:       %s(%u) = %d\n",
 			__func__, xdr->len - req->rq_bytes_sent, status);
+
+	if (status == -EAGAIN && sock_writeable(transport->inet))
+		status = -ENOBUFS;
+
 	if (likely(sent > 0) || status == 0) {
 		req->rq_bytes_sent += sent;
 		req->rq_xmit_bytes_sent += sent;
@@ -539,6 +543,7 @@ static int xs_local_send_request(struct rpc_task *task)
 
 	switch (status) {
 	case -ENOBUFS:
+		break;
 	case -EAGAIN:
 		status = xs_nospace(task);
 		break;
@@ -589,6 +594,9 @@ static int xs_udp_send_request(struct rpc_task *task)
 	if (status == -EPERM)
 		goto process_status;
 
+	if (status == -EAGAIN && sock_writeable(transport->inet))
+		status = -ENOBUFS;
+
 	if (sent > 0 || status == 0) {
 		req->rq_xmit_bytes_sent += sent;
 		if (sent >= req->rq_slen)
@@ -669,9 +677,6 @@ static int xs_tcp_send_request(struct rpc_task *task)
 		dprintk("RPC:       xs_tcp_send_request(%u) = %d\n",
 				xdr->len - req->rq_bytes_sent, status);
 
-		if (unlikely(sent == 0 && status < 0))
-			break;
-
 		/* If we've sent the entire packet, immediately
 		 * reset the count of bytes sent. */
 		req->rq_bytes_sent += sent;
@@ -681,18 +686,21 @@ static int xs_tcp_send_request(struct rpc_task *task)
 			return 0;
 		}
 
-		if (sent != 0)
-			continue;
-		status = -EAGAIN;
-		break;
+		if (status < 0)
+			break;
+		if (sent == 0) {
+			status = -EAGAIN;
+			break;
+		}
 	}
+	if (status == -EAGAIN && sk_stream_is_writeable(transport->inet))
+		status = -ENOBUFS;
 
 	switch (status) {
 	case -ENOTSOCK:
 		status = -ENOTCONN;
 		/* Should we call xs_close() here? */
 		break;
-	case -ENOBUFS:
 	case -EAGAIN:
 		status = xs_nospace(task);
 		break;
@@ -703,6 +711,7 @@ static int xs_tcp_send_request(struct rpc_task *task)
 	case -ECONNREFUSED:
 	case -ENOTCONN:
 	case -EADDRINUSE:
+	case -ENOBUFS:
 	case -EPIPE:
 		clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
 	}