Merge tag 'nfs-for-5.3-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

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

  Stable fixes:

   - SUNRPC: Ensure bvecs are re-synced when we re-encode the RPC
     request

   - Fix an Oops in ff_layout_track_ds_error due to a PTR_ERR()
     dereference

   - Revert buggy NFS readdirplus optimisation

   - NFSv4: Handle the special Linux file open access mode

   - pnfs: Fix a problem where we gratuitously start doing I/O through
     the MDS

  Features:

   - Allow NFS client to set up multiple TCP connections to the server
     using a new 'nconnect=X' mount option. Queue length is used to
     balance load.

   - Enhance statistics reporting to report on all transports when using
     multiple connections.

   - Speed up SUNRPC by removing bh-safe spinlocks

   - Add a mechanism to allow NFSv4 to request that containers set a
     unique per-host identifier for when the hostname is not set.

   - Ensure NFSv4 updates the lease_time after a clientid update

  Bugfixes and cleanup:

   - Fix use-after-free in rpcrdma_post_recvs

   - Fix a memory leak when nfs_match_client() is interrupted

   - Fix buggy file access checking in NFSv4 open for execute

   - disable unsupported client side deduplication

   - Fix spurious client disconnections

   - Fix occasional RDMA transport deadlock

   - Various RDMA cleanups

   - Various tracepoint fixes

   - Fix the TCP callback channel to guarantee the server can actually
     send the number of callback requests that was negotiated at mount
     time"

* tag 'nfs-for-5.3-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (68 commits)
  pnfs/flexfiles: Add tracepoints for detecting pnfs fallback to MDS
  pnfs: Fix a problem where we gratuitously start doing I/O through the MDS
  SUNRPC: Optimise transport balancing code
  SUNRPC: Ensure the bvecs are reset when we re-encode the RPC request
  pnfs/flexfiles: Fix PTR_ERR() dereferences in ff_layout_track_ds_error
  NFSv4: Don't use the zero stateid with layoutget
  SUNRPC: Fix up backchannel slot table accounting
  SUNRPC: Fix initialisation of struct rpc_xprt_switch
  SUNRPC: Skip zero-refcount transports
  SUNRPC: Replace division by multiplication in calculation of queue length
  NFSv4: Validate the stateid before applying it to state recovery
  nfs4.0: Refetch lease_time after clientid update
  nfs4: Rename nfs41_setup_state_renewal
  nfs4: Make nfs4_proc_get_lease_time available for nfs4.0
  nfs: Fix copy-and-paste error in debug message
  NFS: Replace 16 seq_printf() calls by seq_puts()
  NFS: Use seq_putc() in nfs_show_stats()
  Revert "NFS: readdirplus optimization by cache mechanism" (memleak)
  SUNRPC: Fix transport accounting when caller specifies an rpc_xprt
  NFS: Record task, client ID, and XID in xdr_status trace points
  ...

1 files changed, 88 insertions, 7 deletions

diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index b03bfa055c08..d8679b6027e9 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -528,6 +528,8 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args)
 		.bc_xprt = args->bc_xprt,
 	};
 	char servername[48];
+	struct rpc_clnt *clnt;
+	int i;
 
 	if (args->bc_xprt) {
 		WARN_ON_ONCE(!(args->protocol & XPRT_TRANSPORT_BC));
@@ -590,7 +592,15 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args)
 	if (args->flags & RPC_CLNT_CREATE_NONPRIVPORT)
 		xprt->resvport = 0;
 
-	return rpc_create_xprt(args, xprt);
+	clnt = rpc_create_xprt(args, xprt);
+	if (IS_ERR(clnt) || args->nconnect <= 1)
+		return clnt;
+
+	for (i = 0; i < args->nconnect - 1; i++) {
+		if (rpc_clnt_add_xprt(clnt, &xprtargs, NULL, NULL) < 0)
+			break;
+	}
+	return clnt;
 }
 EXPORT_SYMBOL_GPL(rpc_create);
 
@@ -968,13 +978,46 @@ out:
 }
 EXPORT_SYMBOL_GPL(rpc_bind_new_program);
 
+struct rpc_xprt *
+rpc_task_get_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt)
+{
+	struct rpc_xprt_switch *xps;
+
+	if (!xprt)
+		return NULL;
+	rcu_read_lock();
+	xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch);
+	atomic_long_inc(&xps->xps_queuelen);
+	rcu_read_unlock();
+	atomic_long_inc(&xprt->queuelen);
+
+	return xprt;
+}
+
+static void
+rpc_task_release_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt)
+{
+	struct rpc_xprt_switch *xps;
+
+	atomic_long_dec(&xprt->queuelen);
+	rcu_read_lock();
+	xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch);
+	atomic_long_dec(&xps->xps_queuelen);
+	rcu_read_unlock();
+
+	xprt_put(xprt);
+}
+
 void rpc_task_release_transport(struct rpc_task *task)
 {
 	struct rpc_xprt *xprt = task->tk_xprt;
 
 	if (xprt) {
 		task->tk_xprt = NULL;
-		xprt_put(xprt);
+		if (task->tk_client)
+			rpc_task_release_xprt(task->tk_client, xprt);
+		else
+			xprt_put(xprt);
 	}
 }
 EXPORT_SYMBOL_GPL(rpc_task_release_transport);
@@ -983,6 +1026,7 @@ void rpc_task_release_client(struct rpc_task *task)
 {
 	struct rpc_clnt *clnt = task->tk_client;
 
+	rpc_task_release_transport(task);
 	if (clnt != NULL) {
 		/* Remove from client task list */
 		spin_lock(&clnt->cl_lock);
@@ -992,14 +1036,34 @@ void rpc_task_release_client(struct rpc_task *task)
 
 		rpc_release_client(clnt);
 	}
-	rpc_task_release_transport(task);
+}
+
+static struct rpc_xprt *
+rpc_task_get_first_xprt(struct rpc_clnt *clnt)
+{
+	struct rpc_xprt *xprt;
+
+	rcu_read_lock();
+	xprt = xprt_get(rcu_dereference(clnt->cl_xprt));
+	rcu_read_unlock();
+	return rpc_task_get_xprt(clnt, xprt);
+}
+
+static struct rpc_xprt *
+rpc_task_get_next_xprt(struct rpc_clnt *clnt)
+{
+	return rpc_task_get_xprt(clnt, xprt_iter_get_next(&clnt->cl_xpi));
 }
 
 static
 void rpc_task_set_transport(struct rpc_task *task, struct rpc_clnt *clnt)
 {
-	if (!task->tk_xprt)
-		task->tk_xprt = xprt_iter_get_next(&clnt->cl_xpi);
+	if (task->tk_xprt)
+		return;
+	if (task->tk_flags & RPC_TASK_NO_ROUND_ROBIN)
+		task->tk_xprt = rpc_task_get_first_xprt(clnt);
+	else
+		task->tk_xprt = rpc_task_get_next_xprt(clnt);
 }
 
 static
@@ -1462,6 +1526,19 @@ size_t rpc_max_bc_payload(struct rpc_clnt *clnt)
 }
 EXPORT_SYMBOL_GPL(rpc_max_bc_payload);
 
+unsigned int rpc_num_bc_slots(struct rpc_clnt *clnt)
+{
+	struct rpc_xprt *xprt;
+	unsigned int ret;
+
+	rcu_read_lock();
+	xprt = rcu_dereference(clnt->cl_xprt);
+	ret = xprt->ops->bc_num_slots(xprt);
+	rcu_read_unlock();
+	return ret;
+}
+EXPORT_SYMBOL_GPL(rpc_num_bc_slots);
+
 /**
  * rpc_force_rebind - force transport to check that remote port is unchanged
  * @clnt: client to rebind
@@ -1788,6 +1865,7 @@ rpc_xdr_encode(struct rpc_task *task)
 	req->rq_snd_buf.head[0].iov_len = 0;
 	xdr_init_encode(&xdr, &req->rq_snd_buf,
 			req->rq_snd_buf.head[0].iov_base, req);
+	xdr_free_bvec(&req->rq_snd_buf);
 	if (rpc_encode_header(task, &xdr))
 		return;
 
@@ -1827,8 +1905,6 @@ call_encode(struct rpc_task *task)
 			rpc_call_rpcerror(task, task->tk_status);
 		}
 		return;
-	} else {
-		xprt_request_prepare(task->tk_rqstp);
 	}
 
 	/* Add task to reply queue before transmission to avoid races */
@@ -2696,6 +2772,10 @@ int rpc_clnt_test_and_add_xprt(struct rpc_clnt *clnt,
 		return -ENOMEM;
 	data->xps = xprt_switch_get(xps);
 	data->xprt = xprt_get(xprt);
+	if (rpc_xprt_switch_has_addr(data->xps, (struct sockaddr *)&xprt->addr)) {
+		rpc_cb_add_xprt_release(data);
+		goto success;
+	}
 
 	task = rpc_call_null_helper(clnt, xprt, NULL,
 			RPC_TASK_SOFT|RPC_TASK_SOFTCONN|RPC_TASK_ASYNC|RPC_TASK_NULLCREDS,
@@ -2703,6 +2783,7 @@ int rpc_clnt_test_and_add_xprt(struct rpc_clnt *clnt,
 	if (IS_ERR(task))
 		return PTR_ERR(task);
 	rpc_put_task(task);
+success:
 	return 1;
 }
 EXPORT_SYMBOL_GPL(rpc_clnt_test_and_add_xprt);