Merge branch 'multipath_tcp'

4 files changed, 135 insertions, 32 deletions

diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index b03bfa055c08..d599fab8adcb 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 +978,65 @@ out:
 }
 EXPORT_SYMBOL_GPL(rpc_bind_new_program);
 
+static struct rpc_xprt *
+rpc_task_get_xprt(struct rpc_clnt *clnt)
+{
+	struct rpc_xprt_switch *xps;
+	struct rpc_xprt *xprt= xprt_iter_get_next(&clnt->cl_xpi);
+
+	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 struct rpc_xprt *
+rpc_task_get_first_xprt(struct rpc_clnt *clnt)
+{
+	struct rpc_xprt_switch *xps;
+	struct rpc_xprt *xprt;
+
+	rcu_read_lock();
+	xprt = xprt_get(rcu_dereference(clnt->cl_xprt));
+	if (xprt) {
+		atomic_long_inc(&xprt->queuelen);
+		xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch);
+		atomic_long_inc(&xps->xps_queuelen);
+	}
+	rcu_read_unlock();
+
+	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 +1045,7 @@ 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 +1055,17 @@ void rpc_task_release_client(struct rpc_task *task)
 
 		rpc_release_client(clnt);
 	}
-	rpc_task_release_transport(task);
 }
 
 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_xprt(clnt);
 }
 
 static
@@ -2696,6 +2762,10 @@ 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 +2773,7 @@ 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);
diff --git a/net/sunrpc/debugfs.c b/net/sunrpc/debugfs.c
index 95ebd76b132d..105bea190a45 100644
--- a/net/sunrpc/debugfs.c
+++ b/net/sunrpc/debugfs.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/**
+/*
  * debugfs interface for sunrpc
  *
  * (c) 2014 Jeff Layton <jlayton@primarydata.com>
@@ -118,12 +118,38 @@ static const struct file_operations tasks_fops = {
 	.release	= tasks_release,
 };
 
+static int do_xprt_debugfs(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *numv)
+{
+	int len;
+	char name[24]; /* enough for "../../rpc_xprt/ + 8 hex digits + NULL */
+	char link[9]; /* enough for 8 hex digits + NULL */
+	int *nump = numv;
+
+	if (IS_ERR_OR_NULL(xprt->debugfs))
+		return 0;
+	len = snprintf(name, sizeof(name), "../../rpc_xprt/%s",
+		       xprt->debugfs->d_name.name);
+	if (len > sizeof(name))
+		return -1;
+	if (*nump == 0)
+		strcpy(link, "xprt");
+	else {
+		len = snprintf(link, sizeof(link), "xprt%d", *nump);
+		if (len > sizeof(link))
+			return -1;
+	}
+	if (!debugfs_create_symlink(link, clnt->cl_debugfs, name))
+		return -1;
+	(*nump)++;
+	return 0;
+}
+
 void
 rpc_clnt_debugfs_register(struct rpc_clnt *clnt)
 {
 	int len;
-	char name[24]; /* enough for "../../rpc_xprt/ + 8 hex digits + NULL */
-	struct rpc_xprt *xprt;
+	char name[9]; /* enough for 8 hex digits + NULL */
+	int xprtnum = 0;
 
 	/* Already registered? */
 	if (clnt->cl_debugfs || !rpc_clnt_dir)
@@ -143,21 +169,7 @@ rpc_clnt_debugfs_register(struct rpc_clnt *clnt)
 				 clnt, &tasks_fops))
 		goto out_err;
 
-	rcu_read_lock();
-	xprt = rcu_dereference(clnt->cl_xprt);
-	/* no "debugfs" dentry? Don't bother with the symlink. */
-	if (IS_ERR_OR_NULL(xprt->debugfs)) {
-		rcu_read_unlock();
-		return;
-	}
-	len = snprintf(name, sizeof(name), "../../rpc_xprt/%s",
-			xprt->debugfs->d_name.name);
-	rcu_read_unlock();
-
-	if (len >= sizeof(name))
-		goto out_err;
-
-	if (!debugfs_create_symlink("xprt", clnt->cl_debugfs, name))
+	if (rpc_clnt_iterate_for_each_xprt(clnt, do_xprt_debugfs, &xprtnum) < 0)
 		goto out_err;
 
 	return;
diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c
index 48ea776364f8..7c74197c2ecf 100644
--- a/net/sunrpc/stats.c
+++ b/net/sunrpc/stats.c
@@ -240,9 +240,16 @@ static void _print_rpc_iostats(struct seq_file *seq, struct rpc_iostats *stats,
 		   stats->om_error_status);
 }
 
+static int do_print_stats(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *seqv)
+{
+	struct seq_file *seq = seqv;
+
+	xprt->ops->print_stats(xprt, seq);
+	return 0;
+}
+
 void rpc_clnt_show_stats(struct seq_file *seq, struct rpc_clnt *clnt)
 {
-	struct rpc_xprt *xprt;
 	unsigned int op, maxproc = clnt->cl_maxproc;
 
 	if (!clnt->cl_metrics)
@@ -252,11 +259,7 @@ void rpc_clnt_show_stats(struct seq_file *seq, struct rpc_clnt *clnt)
 	seq_printf(seq, "p/v: %u/%u (%s)\n",
 			clnt->cl_prog, clnt->cl_vers, clnt->cl_program->name);
 
-	rcu_read_lock();
-	xprt = rcu_dereference(clnt->cl_xprt);
-	if (xprt)
-		xprt->ops->print_stats(xprt, seq);
-	rcu_read_unlock();
+	rpc_clnt_iterate_for_each_xprt(clnt, do_print_stats, seq);
 
 	seq_printf(seq, "\tper-op statistics\n");
 	for (op = 0; op < maxproc; op++) {
diff --git a/net/sunrpc/xprtmultipath.c b/net/sunrpc/xprtmultipath.c
index 8394124126f8..9d66ce53355d 100644
--- a/net/sunrpc/xprtmultipath.c
+++ b/net/sunrpc/xprtmultipath.c
@@ -36,6 +36,7 @@ static void xprt_switch_add_xprt_locked(struct rpc_xprt_switch *xps,
 	if (xps->xps_nxprts == 0)
 		xps->xps_net = xprt->xprt_net;
 	xps->xps_nxprts++;
+	xps->xps_nactive++;
 }
 
 /**
@@ -51,8 +52,7 @@ void rpc_xprt_switch_add_xprt(struct rpc_xprt_switch *xps,
 	if (xprt == NULL)
 		return;
 	spin_lock(&xps->xps_lock);
-	if ((xps->xps_net == xprt->xprt_net || xps->xps_net == NULL) &&
-	    !rpc_xprt_switch_has_addr(xps, (struct sockaddr *)&xprt->addr))
+	if (xps->xps_net == xprt->xprt_net || xps->xps_net == NULL)
 		xprt_switch_add_xprt_locked(xps, xprt);
 	spin_unlock(&xps->xps_lock);
 }
@@ -62,6 +62,7 @@ static void xprt_switch_remove_xprt_locked(struct rpc_xprt_switch *xps,
 {
 	if (unlikely(xprt == NULL))
 		return;
+	xps->xps_nactive--;
 	xps->xps_nxprts--;
 	if (xps->xps_nxprts == 0)
 		xps->xps_net = NULL;
@@ -317,8 +318,24 @@ struct rpc_xprt *xprt_switch_find_next_entry_roundrobin(struct list_head *head,
 static
 struct rpc_xprt *xprt_iter_next_entry_roundrobin(struct rpc_xprt_iter *xpi)
 {
-	return xprt_iter_next_entry_multiple(xpi,
+	struct rpc_xprt_switch *xps = rcu_dereference(xpi->xpi_xpswitch);
+	struct rpc_xprt *xprt;
+	unsigned long xprt_queuelen;
+	unsigned long xps_queuelen;
+	unsigned long xps_avglen;
+
+	do {
+		xprt = xprt_iter_next_entry_multiple(xpi,
 			xprt_switch_find_next_entry_roundrobin);
+		if (xprt == NULL)
+			break;
+		xprt_queuelen = atomic_long_read(&xprt->queuelen);
+		if (xprt_queuelen <= 2)
+			break;
+		xps_queuelen = atomic_long_read(&xps->xps_queuelen);
+		xps_avglen = DIV_ROUND_UP(xps_queuelen, xps->xps_nactive);
+	} while (xprt_queuelen > xps_avglen);
+	return xprt;
 }
 
 static