Merge tag 'nfs-for-4.14-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Hightlights include:

  Stable bugfixes:
   - Fix mirror allocation in the writeback code to avoid a use after
     free
   - Fix the O_DSYNC writes to use the correct byte range
   - Fix 2 use after free issues in the I/O code

  Features:
   - Writeback fixes to split up the inode->i_lock in order to reduce
     contention
   - RPC client receive fixes to reduce the amount of time the
     xprt->transport_lock is held when receiving data from a socket into
     am XDR buffer.
   - Ditto fixes to reduce contention between call side users of the
     rdma rb_lock, and its use in rpcrdma_reply_handler.
   - Re-arrange rdma stats to reduce false cacheline sharing.
   - Various rdma cleanups and optimisations.
   - Refactor the NFSv4.1 exchange id code and clean up the code.
   - Const-ify all instances of struct rpc_xprt_ops

  Bugfixes:
   - Fix the NFSv2 'sec=' mount option.
   - NFSv4.1: don't use machine credentials for CLOSE when using
     'sec=sys'
   - Fix the NFSv3 GRANT callback when the port changes on the server.
   - Fix livelock issues with COMMIT
   - NFSv4: Use correct inode in _nfs4_opendata_to_nfs4_state() when
     doing and NFSv4.1 open by filehandle"

* tag 'nfs-for-4.14-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (69 commits)
  NFS: Count the bytes of skipped subrequests in nfs_lock_and_join_requests()
  NFS: Don't hold the group lock when calling nfs_release_request()
  NFS: Remove pnfs_generic_transfer_commit_list()
  NFS: nfs_lock_and_join_requests and nfs_scan_commit_list can deadlock
  NFS: Fix 2 use after free issues in the I/O code
  NFS: Sync the correct byte range during synchronous writes
  lockd: Delete an error message for a failed memory allocation in reclaimer()
  NFS: remove jiffies field from access cache
  NFS: flush data when locking a file to ensure cache coherence for mmap.
  SUNRPC: remove some dead code.
  NFS: don't expect errors from mempool_alloc().
  xprtrdma: Use xprt_pin_rqst in rpcrdma_reply_handler
  xprtrdma: Re-arrange struct rx_stats
  NFS: Fix NFSv2 security settings
  NFSv4.1: don't use machine credentials for CLOSE when using 'sec=sys'
  SUNRPC: ECONNREFUSED should cause a rebind.
  NFS: Remove unused parameter gfp_flags from nfs_pageio_init()
  NFSv4: Fix up mirror allocation
  SUNRPC: Add a separate spinlock to protect the RPC request receive list
  SUNRPC: Cleanup xs_tcp_read_common()
  ...

1 files changed, 47 insertions, 43 deletions

diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 4f154d3..9b5de31 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -969,10 +969,12 @@ static void xs_local_data_read_skb(struct rpc_xprt *xprt,
 		return;
 
 	/* Look up and lock the request corresponding to the given XID */
-	spin_lock_bh(&xprt->transport_lock);
+	spin_lock(&xprt->recv_lock);
 	rovr = xprt_lookup_rqst(xprt, *xp);
 	if (!rovr)
 		goto out_unlock;
+	xprt_pin_rqst(rovr);
+	spin_unlock(&xprt->recv_lock);
 	task = rovr->rq_task;
 
 	copied = rovr->rq_private_buf.buflen;
@@ -981,13 +983,16 @@ static void xs_local_data_read_skb(struct rpc_xprt *xprt,
 
 	if (xs_local_copy_to_xdr(&rovr->rq_private_buf, skb)) {
 		dprintk("RPC:       sk_buff copy failed\n");
-		goto out_unlock;
+		spin_lock(&xprt->recv_lock);
+		goto out_unpin;
 	}
 
+	spin_lock(&xprt->recv_lock);
 	xprt_complete_rqst(task, copied);
-
+out_unpin:
+	xprt_unpin_rqst(rovr);
  out_unlock:
-	spin_unlock_bh(&xprt->transport_lock);
+	spin_unlock(&xprt->recv_lock);
 }
 
 static void xs_local_data_receive(struct sock_xprt *transport)
@@ -1050,10 +1055,12 @@ static void xs_udp_data_read_skb(struct rpc_xprt *xprt,
 		return;
 
 	/* Look up and lock the request corresponding to the given XID */
-	spin_lock_bh(&xprt->transport_lock);
+	spin_lock(&xprt->recv_lock);
 	rovr = xprt_lookup_rqst(xprt, *xp);
 	if (!rovr)
 		goto out_unlock;
+	xprt_pin_rqst(rovr);
+	spin_unlock(&xprt->recv_lock);
 	task = rovr->rq_task;
 
 	if ((copied = rovr->rq_private_buf.buflen) > repsize)
@@ -1062,16 +1069,21 @@ static void xs_udp_data_read_skb(struct rpc_xprt *xprt,
 	/* Suck it into the iovec, verify checksum if not done by hw. */
 	if (csum_partial_copy_to_xdr(&rovr->rq_private_buf, skb)) {
 		__UDPX_INC_STATS(sk, UDP_MIB_INERRORS);
-		goto out_unlock;
+		spin_lock(&xprt->recv_lock);
+		goto out_unpin;
 	}
 
 	__UDPX_INC_STATS(sk, UDP_MIB_INDATAGRAMS);
 
+	spin_lock_bh(&xprt->transport_lock);
 	xprt_adjust_cwnd(xprt, task, copied);
+	spin_unlock_bh(&xprt->transport_lock);
+	spin_lock(&xprt->recv_lock);
 	xprt_complete_rqst(task, copied);
-
+out_unpin:
+	xprt_unpin_rqst(rovr);
  out_unlock:
-	spin_unlock_bh(&xprt->transport_lock);
+	spin_unlock(&xprt->recv_lock);
 }
 
 static void xs_udp_data_receive(struct sock_xprt *transport)
@@ -1277,25 +1289,12 @@ static inline void xs_tcp_read_common(struct rpc_xprt *xprt,
 	}
 
 	len = desc->count;
-	if (len > transport->tcp_reclen - transport->tcp_offset) {
-		struct xdr_skb_reader my_desc;
-
-		len = transport->tcp_reclen - transport->tcp_offset;
-		memcpy(&my_desc, desc, sizeof(my_desc));
-		my_desc.count = len;
-		r = xdr_partial_copy_from_skb(rcvbuf, transport->tcp_copied,
-					  &my_desc, xdr_skb_read_bits);
-		desc->count -= r;
-		desc->offset += r;
-	} else
-		r = xdr_partial_copy_from_skb(rcvbuf, transport->tcp_copied,
+	if (len > transport->tcp_reclen - transport->tcp_offset)
+		desc->count = transport->tcp_reclen - transport->tcp_offset;
+	r = xdr_partial_copy_from_skb(rcvbuf, transport->tcp_copied,
 					  desc, xdr_skb_read_bits);
 
-	if (r > 0) {
-		transport->tcp_copied += r;
-		transport->tcp_offset += r;
-	}
-	if (r != len) {
+	if (desc->count) {
 		/* Error when copying to the receive buffer,
 		 * usually because we weren't able to allocate
 		 * additional buffer pages. All we can do now
@@ -1315,6 +1314,10 @@ static inline void xs_tcp_read_common(struct rpc_xprt *xprt,
 		return;
 	}
 
+	transport->tcp_copied += r;
+	transport->tcp_offset += r;
+	desc->count = len - r;
+
 	dprintk("RPC:       XID %08x read %zd bytes\n",
 			ntohl(transport->tcp_xid), r);
 	dprintk("RPC:       xprt = %p, tcp_copied = %lu, tcp_offset = %u, "
@@ -1343,21 +1346,24 @@ static inline int xs_tcp_read_reply(struct rpc_xprt *xprt,
 	dprintk("RPC:       read reply XID %08x\n", ntohl(transport->tcp_xid));
 
 	/* Find and lock the request corresponding to this xid */
-	spin_lock_bh(&xprt->transport_lock);
+	spin_lock(&xprt->recv_lock);
 	req = xprt_lookup_rqst(xprt, transport->tcp_xid);
 	if (!req) {
 		dprintk("RPC:       XID %08x request not found!\n",
 				ntohl(transport->tcp_xid));
-		spin_unlock_bh(&xprt->transport_lock);
+		spin_unlock(&xprt->recv_lock);
 		return -1;
 	}
+	xprt_pin_rqst(req);
+	spin_unlock(&xprt->recv_lock);
 
 	xs_tcp_read_common(xprt, desc, req);
 
+	spin_lock(&xprt->recv_lock);
 	if (!(transport->tcp_flags & TCP_RCV_COPY_DATA))
 		xprt_complete_rqst(req->rq_task, transport->tcp_copied);
-
-	spin_unlock_bh(&xprt->transport_lock);
+	xprt_unpin_rqst(req);
+	spin_unlock(&xprt->recv_lock);
 	return 0;
 }
 
@@ -1376,11 +1382,9 @@ static int xs_tcp_read_callback(struct rpc_xprt *xprt,
 				container_of(xprt, struct sock_xprt, xprt);
 	struct rpc_rqst *req;
 
-	/* Look up and lock the request corresponding to the given XID */
-	spin_lock_bh(&xprt->transport_lock);
+	/* Look up the request corresponding to the given XID */
 	req = xprt_lookup_bc_request(xprt, transport->tcp_xid);
 	if (req == NULL) {
-		spin_unlock_bh(&xprt->transport_lock);
 		printk(KERN_WARNING "Callback slot table overflowed\n");
 		xprt_force_disconnect(xprt);
 		return -1;
@@ -1391,7 +1395,6 @@ static int xs_tcp_read_callback(struct rpc_xprt *xprt,
 
 	if (!(transport->tcp_flags & TCP_RCV_COPY_DATA))
 		xprt_complete_bc_request(req, transport->tcp_copied);
-	spin_unlock_bh(&xprt->transport_lock);
 
 	return 0;
 }
@@ -1516,6 +1519,7 @@ static void xs_tcp_data_receive(struct sock_xprt *transport)
 		.arg.data = xprt,
 	};
 	unsigned long total = 0;
+	int loop;
 	int read = 0;
 
 	mutex_lock(&transport->recv_mutex);
@@ -1524,20 +1528,20 @@ static void xs_tcp_data_receive(struct sock_xprt *transport)
 		goto out;
 
 	/* We use rd_desc to pass struct xprt to xs_tcp_data_recv */
-	for (;;) {
+	for (loop = 0; loop < 64; loop++) {
 		lock_sock(sk);
 		read = tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv);
 		if (read <= 0) {
 			clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state);
 			release_sock(sk);
-			if (!test_bit(XPRT_SOCK_DATA_READY, &transport->sock_state))
-				break;
-		} else {
-			release_sock(sk);
-			total += read;
+			break;
 		}
+		release_sock(sk);
+		total += read;
 		rd_desc.count = 65536;
 	}
+	if (test_bit(XPRT_SOCK_DATA_READY, &transport->sock_state))
+		queue_work(xprtiod_workqueue, &transport->recv_worker);
 out:
 	mutex_unlock(&transport->recv_mutex);
 	trace_xs_tcp_data_ready(xprt, read, total);
@@ -2724,7 +2728,7 @@ static void bc_destroy(struct rpc_xprt *xprt)
 	module_put(THIS_MODULE);
 }
 
-static struct rpc_xprt_ops xs_local_ops = {
+static const struct rpc_xprt_ops xs_local_ops = {
 	.reserve_xprt		= xprt_reserve_xprt,
 	.release_xprt		= xs_tcp_release_xprt,
 	.alloc_slot		= xprt_alloc_slot,
@@ -2742,7 +2746,7 @@ static struct rpc_xprt_ops xs_local_ops = {
 	.disable_swap		= xs_disable_swap,
 };
 
-static struct rpc_xprt_ops xs_udp_ops = {
+static const struct rpc_xprt_ops xs_udp_ops = {
 	.set_buffer_size	= xs_udp_set_buffer_size,
 	.reserve_xprt		= xprt_reserve_xprt_cong,
 	.release_xprt		= xprt_release_xprt_cong,
@@ -2764,7 +2768,7 @@ static struct rpc_xprt_ops xs_udp_ops = {
 	.inject_disconnect	= xs_inject_disconnect,
 };
 
-static struct rpc_xprt_ops xs_tcp_ops = {
+static const struct rpc_xprt_ops xs_tcp_ops = {
 	.reserve_xprt		= xprt_reserve_xprt,
 	.release_xprt		= xs_tcp_release_xprt,
 	.alloc_slot		= xprt_lock_and_alloc_slot,
@@ -2795,7 +2799,7 @@ static struct rpc_xprt_ops xs_tcp_ops = {
  * The rpc_xprt_ops for the server backchannel
  */
 
-static struct rpc_xprt_ops bc_tcp_ops = {
+static const struct rpc_xprt_ops bc_tcp_ops = {
 	.reserve_xprt		= xprt_reserve_xprt,
 	.release_xprt		= xprt_release_xprt,
 	.alloc_slot		= xprt_alloc_slot,