1 files changed, 81 insertions, 51 deletions

diff --git a/net/rds/connection.c b/net/rds/connection.c
index cfb05953b0e5..3176ead0ab4d 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -34,7 +34,8 @@
 #include <linux/list.h>
 #include <linux/slab.h>
 #include <linux/export.h>
-#include <net/inet_hashtables.h>
+#include <net/ipv6.h>
+#include <net/inet6_hashtables.h>
 
 #include "rds.h"
 #include "loop.h"
@@ -49,18 +50,21 @@ static unsigned long rds_conn_count;
 static struct hlist_head rds_conn_hash[RDS_CONNECTION_HASH_ENTRIES];
 static struct kmem_cache *rds_conn_slab;
 
-static struct hlist_head *rds_conn_bucket(__be32 laddr, __be32 faddr)
+static struct hlist_head *rds_conn_bucket(const struct in6_addr *laddr,
+					  const struct in6_addr *faddr)
 {
+	static u32 rds6_hash_secret __read_mostly;
 	static u32 rds_hash_secret __read_mostly;
 
-	unsigned long hash;
+	u32 lhash, fhash, hash;
 
 	net_get_random_once(&rds_hash_secret, sizeof(rds_hash_secret));
+	net_get_random_once(&rds6_hash_secret, sizeof(rds6_hash_secret));
+
+	lhash = (__force u32)laddr->s6_addr32[3];
+	fhash = __ipv6_addr_jhash(faddr, rds6_hash_secret);
+	hash = __inet6_ehashfn(lhash, 0, fhash, 0, rds_hash_secret);
 
-	/* Pass NULL, don't need struct net for hash */
-	hash = __inet_ehashfn(be32_to_cpu(laddr), 0,
-			      be32_to_cpu(faddr), 0,
-			      rds_hash_secret);
 	return &rds_conn_hash[hash & RDS_CONNECTION_HASH_MASK];
 }
 
@@ -72,20 +76,25 @@ static struct hlist_head *rds_conn_bucket(__be32 laddr, __be32 faddr)
 /* rcu read lock must be held or the connection spinlock */
 static struct rds_connection *rds_conn_lookup(struct net *net,
 					      struct hlist_head *head,
-					      __be32 laddr, __be32 faddr,
-					      struct rds_transport *trans)
+					      const struct in6_addr *laddr,
+					      const struct in6_addr *faddr,
+					      struct rds_transport *trans,
+					      int dev_if)
 {
 	struct rds_connection *conn, *ret = NULL;
 
 	hlist_for_each_entry_rcu(conn, head, c_hash_node) {
-		if (conn->c_faddr == faddr && conn->c_laddr == laddr &&
-		    conn->c_trans == trans && net == rds_conn_net(conn)) {
+		if (ipv6_addr_equal(&conn->c_faddr, faddr) &&
+		    ipv6_addr_equal(&conn->c_laddr, laddr) &&
+		    conn->c_trans == trans &&
+		    net == rds_conn_net(conn) &&
+		    conn->c_dev_if == dev_if) {
 			ret = conn;
 			break;
 		}
 	}
-	rdsdebug("returning conn %p for %pI4 -> %pI4\n", ret,
-		 &laddr, &faddr);
+	rdsdebug("returning conn %p for %pI6c -> %pI6c\n", ret,
+		 laddr, faddr);
 	return ret;
 }
 
@@ -99,8 +108,8 @@ static void rds_conn_path_reset(struct rds_conn_path *cp)
 {
 	struct rds_connection *conn = cp->cp_conn;
 
-	rdsdebug("connection %pI4 to %pI4 reset\n",
-	  &conn->c_laddr, &conn->c_faddr);
+	rdsdebug("connection %pI6c to %pI6c reset\n",
+		 &conn->c_laddr, &conn->c_faddr);
 
 	rds_stats_inc(s_conn_reset);
 	rds_send_path_reset(cp);
@@ -142,9 +151,12 @@ static void __rds_conn_path_init(struct rds_connection *conn,
  * are torn down as the module is removed, if ever.
  */
 static struct rds_connection *__rds_conn_create(struct net *net,
-						__be32 laddr, __be32 faddr,
-				       struct rds_transport *trans, gfp_t gfp,
-				       int is_outgoing)
+						const struct in6_addr *laddr,
+						const struct in6_addr *faddr,
+						struct rds_transport *trans,
+						gfp_t gfp,
+						int is_outgoing,
+						int dev_if)
 {
 	struct rds_connection *conn, *parent = NULL;
 	struct hlist_head *head = rds_conn_bucket(laddr, faddr);
@@ -154,9 +166,12 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 	int npaths = (trans->t_mp_capable ? RDS_MPATH_WORKERS : 1);
 
 	rcu_read_lock();
-	conn = rds_conn_lookup(net, head, laddr, faddr, trans);
-	if (conn && conn->c_loopback && conn->c_trans != &rds_loop_transport &&
-	    laddr == faddr && !is_outgoing) {
+	conn = rds_conn_lookup(net, head, laddr, faddr, trans, dev_if);
+	if (conn &&
+	    conn->c_loopback &&
+	    conn->c_trans != &rds_loop_transport &&
+	    ipv6_addr_equal(laddr, faddr) &&
+	    !is_outgoing) {
 		/* This is a looped back IB connection, and we're
 		 * called by the code handling the incoming connect.
 		 * We need a second connection object into which we
@@ -181,8 +196,10 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 	}
 
 	INIT_HLIST_NODE(&conn->c_hash_node);
-	conn->c_laddr = laddr;
-	conn->c_faddr = faddr;
+	conn->c_laddr = *laddr;
+	conn->c_isv6 = !ipv6_addr_v4mapped(laddr);
+	conn->c_faddr = *faddr;
+	conn->c_dev_if = dev_if;
 
 	rds_conn_net_set(conn, net);
 
@@ -199,7 +216,7 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 	 * can bind to the destination address then we'd rather the messages
 	 * flow through loopback rather than either transport.
 	 */
-	loop_trans = rds_trans_get_preferred(net, faddr);
+	loop_trans = rds_trans_get_preferred(net, faddr, conn->c_dev_if);
 	if (loop_trans) {
 		rds_trans_put(loop_trans);
 		conn->c_loopback = 1;
@@ -233,10 +250,10 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 		goto out;
 	}
 
-	rdsdebug("allocated conn %p for %pI4 -> %pI4 over %s %s\n",
-	  conn, &laddr, &faddr,
-	  strnlen(trans->t_name, sizeof(trans->t_name)) ? trans->t_name :
-	  "[unknown]", is_outgoing ? "(outgoing)" : "");
+	rdsdebug("allocated conn %p for %pI6c -> %pI6c over %s %s\n",
+		 conn, laddr, faddr,
+		 strnlen(trans->t_name, sizeof(trans->t_name)) ?
+		 trans->t_name : "[unknown]", is_outgoing ? "(outgoing)" : "");
 
 	/*
 	 * Since we ran without holding the conn lock, someone could
@@ -262,7 +279,8 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 		/* Creating normal conn */
 		struct rds_connection *found;
 
-		found = rds_conn_lookup(net, head, laddr, faddr, trans);
+		found = rds_conn_lookup(net, head, laddr, faddr, trans,
+					dev_if);
 		if (found) {
 			struct rds_conn_path *cp;
 			int i;
@@ -295,18 +313,22 @@ out:
 }
 
 struct rds_connection *rds_conn_create(struct net *net,
-				       __be32 laddr, __be32 faddr,
-				       struct rds_transport *trans, gfp_t gfp)
+				       const struct in6_addr *laddr,
+				       const struct in6_addr *faddr,
+				       struct rds_transport *trans, gfp_t gfp,
+				       int dev_if)
 {
-	return __rds_conn_create(net, laddr, faddr, trans, gfp, 0);
+	return __rds_conn_create(net, laddr, faddr, trans, gfp, 0, dev_if);
 }
 EXPORT_SYMBOL_GPL(rds_conn_create);
 
 struct rds_connection *rds_conn_create_outgoing(struct net *net,
-						__be32 laddr, __be32 faddr,
-				       struct rds_transport *trans, gfp_t gfp)
+						const struct in6_addr *laddr,
+						const struct in6_addr *faddr,
+						struct rds_transport *trans,
+						gfp_t gfp, int dev_if)
 {
-	return __rds_conn_create(net, laddr, faddr, trans, gfp, 1);
+	return __rds_conn_create(net, laddr, faddr, trans, gfp, 1, dev_if);
 }
 EXPORT_SYMBOL_GPL(rds_conn_create_outgoing);
 
@@ -502,12 +524,17 @@ static void rds_conn_message_info(struct socket *sock, unsigned int len,
 
 				/* XXX too lazy to maintain counts.. */
 				list_for_each_entry(rm, list, m_conn_item) {
+					__be32 laddr;
+					__be32 faddr;
+
 					total++;
+					laddr = conn->c_laddr.s6_addr32[3];
+					faddr = conn->c_faddr.s6_addr32[3];
 					if (total <= len)
 						rds_inc_info_copy(&rm->m_inc,
 								  iter,
-								  conn->c_laddr,
-								  conn->c_faddr,
+								  laddr,
+								  faddr,
 								  0);
 				}
 
@@ -584,7 +611,6 @@ static void rds_walk_conn_path_info(struct socket *sock, unsigned int len,
 	struct hlist_head *head;
 	struct rds_connection *conn;
 	size_t i;
-	int j;
 
 	rcu_read_lock();
 
@@ -595,17 +621,20 @@ static void rds_walk_conn_path_info(struct socket *sock, unsigned int len,
 	     i++, head++) {
 		hlist_for_each_entry_rcu(conn, head, c_hash_node) {
 			struct rds_conn_path *cp;
-			int npaths;
 
-			npaths = (conn->c_trans->t_mp_capable ?
-				 RDS_MPATH_WORKERS : 1);
-			for (j = 0; j < npaths; j++) {
-				cp = &conn->c_path[j];
+			/* XXX We only copy the information from the first
+			 * path for now.  The problem is that if there are
+			 * more than one underlying paths, we cannot report
+			 * information of all of them using the existing
+			 * API.  For example, there is only one next_tx_seq,
+			 * which path's next_tx_seq should we report?  It is
+			 * a bug in the design of MPRDS.
+			 */
+			cp = conn->c_path;
 
-				/* XXX no cp_lock usage.. */
-				if (!visitor(cp, buffer))
-					continue;
-			}
+			/* XXX no cp_lock usage.. */
+			if (!visitor(cp, buffer))
+				continue;
 
 			/* We copy as much as we can fit in the buffer,
 			 * but we count all items so that the caller
@@ -624,12 +653,13 @@ static void rds_walk_conn_path_info(struct socket *sock, unsigned int len,
 static int rds_conn_info_visitor(struct rds_conn_path *cp, void *buffer)
 {
 	struct rds_info_connection *cinfo = buffer;
+	struct rds_connection *conn = cp->cp_conn;
 
 	cinfo->next_tx_seq = cp->cp_next_tx_seq;
 	cinfo->next_rx_seq = cp->cp_next_rx_seq;
-	cinfo->laddr = cp->cp_conn->c_laddr;
-	cinfo->faddr = cp->cp_conn->c_faddr;
-	strncpy(cinfo->transport, cp->cp_conn->c_trans->t_name,
+	cinfo->laddr = conn->c_laddr.s6_addr32[3];
+	cinfo->faddr = conn->c_faddr.s6_addr32[3];
+	strncpy(cinfo->transport, conn->c_trans->t_name,
 		sizeof(cinfo->transport));
 	cinfo->flags = 0;