Merge tag 'nfs-for-4.8-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

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

  Stable bugfixes:
   - nfs: don't create zero-length requests

   - several LAYOUTGET bugfixes

  Features:
   - several performance related features

   - more aggressive caching when we can rely on close-to-open
     cache consistency

   - remove serialisation of O_DIRECT reads and writes

   - optimise several code paths to not flush to disk unnecessarily.

     However allow for the idiosyncracies of pNFS for those layout
     types that need to issue a LAYOUTCOMMIT before the metadata can
     be updated on the server.

   - SUNRPC updates to the client data receive path

   - pNFS/SCSI support RH/Fedora dm-mpath device nodes

   - pNFS files/flexfiles can now use unprivileged ports when
     the generic NFS mount options allow it.

  Bugfixes:
   - Don't use RDMA direct data placement together with data
     integrity or privacy security flavours

   - Remove the RDMA ALLPHYSICAL memory registration mode as
     it has potential security holes.

   - Several layout recall fixes to improve NFSv4.1 protocol
     compliance.

   - Fix an Oops in the pNFS files and flexfiles connection
     setup to the DS

   - Allow retry of operations that used a returned delegation
      stateid

   - Don't mark the inode as revalidated if a LAYOUTCOMMIT is
     outstanding

   - Fix writeback races in nfs4_copy_range() and
     nfs42_proc_deallocate()"

* tag 'nfs-for-4.8-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (104 commits)
  pNFS: Actively set attributes as invalid if LAYOUTCOMMIT is outstanding
  NFSv4: Clean up lookup of SECINFO_NO_NAME
  NFSv4.2: Fix warning "variable ‘stateids’ set but not used"
  NFSv4: Fix warning "no previous prototype for ‘nfs4_listxattr’"
  SUNRPC: Fix a compiler warning in fs/nfs/clnt.c
  pNFS: Remove redundant smp_mb() from pnfs_init_lseg()
  pNFS: Cleanup - do layout segment initialisation in one place
  pNFS: Remove redundant stateid invalidation
  pNFS: Remove redundant pnfs_mark_layout_returned_if_empty()
  pNFS: Clear the layout metadata if the server changed the layout stateid
  pNFS: Cleanup - don't open code pnfs_mark_layout_stateid_invalid()
  NFS: pnfs_mark_matching_lsegs_return() should match the layout sequence id
  pNFS: Do not set plh_return_seq for non-callback related layoutreturns
  pNFS: Ensure layoutreturn acts as a completion for layout callbacks
  pNFS: Fix CB_LAYOUTRECALL stateid verification
  pNFS: Always update the layout barrier seqid on LAYOUTGET
  pNFS: Always update the layout stateid if NFS_LAYOUT_INVALID_STID is set
  pNFS: Clear the layout return tracking on layout reinitialisation
  pNFS: LAYOUTRETURN should only update the stateid if the layout is valid
  nfs: don't create zero-length requests
  ...

1 files changed, 24 insertions, 16 deletions

diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 99d2e5b72726..81f0e879f019 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -558,7 +558,6 @@ out_sendbuf:
 
 out_fail:
 	rpcrdma_buffer_put(req);
-	r_xprt->rx_stats.failed_marshal_count++;
 	return NULL;
 }
 
@@ -590,8 +589,19 @@ xprt_rdma_free(void *buffer)
 	rpcrdma_buffer_put(req);
 }
 
-/*
+/**
+ * xprt_rdma_send_request - marshal and send an RPC request
+ * @task: RPC task with an RPC message in rq_snd_buf
+ *
+ * Return values:
+ *        0:	The request has been sent
+ * ENOTCONN:	Caller needs to invoke connect logic then call again
+ *  ENOBUFS:	Call again later to send the request
+ *      EIO:	A permanent error occurred. The request was not sent,
+ *		and don't try it again
+ *
  * send_request invokes the meat of RPC RDMA. It must do the following:
+ *
  *  1.  Marshal the RPC request into an RPC RDMA request, which means
  *	putting a header in front of data, and creating IOVs for RDMA
  *	from those in the request.
@@ -600,7 +610,6 @@ xprt_rdma_free(void *buffer)
  *	the request (rpcrdma_ep_post).
  *  4.  No partial sends are possible in the RPC-RDMA protocol (as in UDP).
  */
-
 static int
 xprt_rdma_send_request(struct rpc_task *task)
 {
@@ -610,6 +619,9 @@ xprt_rdma_send_request(struct rpc_task *task)
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
 	int rc = 0;
 
+	/* On retransmit, remove any previously registered chunks */
+	r_xprt->rx_ia.ri_ops->ro_unmap_safe(r_xprt, req, false);
+
 	rc = rpcrdma_marshal_req(rqst);
 	if (rc < 0)
 		goto failed_marshal;
@@ -630,11 +642,12 @@ xprt_rdma_send_request(struct rpc_task *task)
 	return 0;
 
 failed_marshal:
-	r_xprt->rx_stats.failed_marshal_count++;
 	dprintk("RPC:       %s: rpcrdma_marshal_req failed, status %i\n",
 		__func__, rc);
 	if (rc == -EIO)
-		return -EIO;
+		r_xprt->rx_stats.failed_marshal_count++;
+	if (rc != -ENOTCONN)
+		return rc;
 drop_connection:
 	xprt_disconnect_done(xprt);
 	return -ENOTCONN;	/* implies disconnect */
@@ -660,7 +673,7 @@ void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
 		   xprt->stat.bad_xids,
 		   xprt->stat.req_u,
 		   xprt->stat.bklog_u);
-	seq_printf(seq, "%lu %lu %lu %llu %llu %llu %llu %lu %lu %lu %lu\n",
+	seq_printf(seq, "%lu %lu %lu %llu %llu %llu %llu %lu %lu %lu %lu ",
 		   r_xprt->rx_stats.read_chunk_count,
 		   r_xprt->rx_stats.write_chunk_count,
 		   r_xprt->rx_stats.reply_chunk_count,
@@ -672,6 +685,10 @@ void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
 		   r_xprt->rx_stats.failed_marshal_count,
 		   r_xprt->rx_stats.bad_reply_count,
 		   r_xprt->rx_stats.nomsg_call_count);
+	seq_printf(seq, "%lu %lu %lu\n",
+		   r_xprt->rx_stats.mrs_recovered,
+		   r_xprt->rx_stats.mrs_orphaned,
+		   r_xprt->rx_stats.mrs_allocated);
 }
 
 static int
@@ -741,7 +758,6 @@ void xprt_rdma_cleanup(void)
 			__func__, rc);
 
 	rpcrdma_destroy_wq();
-	frwr_destroy_recovery_wq();
 
 	rc = xprt_unregister_transport(&xprt_rdma_bc);
 	if (rc)
@@ -753,20 +769,13 @@ int xprt_rdma_init(void)
 {
 	int rc;
 
-	rc = frwr_alloc_recovery_wq();
-	if (rc)
-		return rc;
-
 	rc = rpcrdma_alloc_wq();
-	if (rc) {
-		frwr_destroy_recovery_wq();
+	if (rc)
 		return rc;
-	}
 
 	rc = xprt_register_transport(&xprt_rdma);
 	if (rc) {
 		rpcrdma_destroy_wq();
-		frwr_destroy_recovery_wq();
 		return rc;
 	}
 
@@ -774,7 +783,6 @@ int xprt_rdma_init(void)
 	if (rc) {
 		xprt_unregister_transport(&xprt_rdma);
 		rpcrdma_destroy_wq();
-		frwr_destroy_recovery_wq();
 		return rc;
 	}