From eee2fa6ab3225192d6d894c54a6fb02ac9efdff6 Mon Sep 17 00:00:00 2001 From: Ka-Cheong Poon Date: Mon, 23 Jul 2018 20:51:21 -0700 Subject: [PATCH] rds: Changing IP address internal representation to struct in6_addr This patch changes the internal representation of an IP address to use struct in6_addr. IPv4 address is stored as an IPv4 mapped address. All the functions which take an IP address as argument are also changed to use struct in6_addr. But RDS socket layer is not modified such that it still does not accept IPv6 address from an application. And RDS layer does not accept nor initiate IPv6 connections. v2: Fixed sparse warnings. Signed-off-by: Ka-Cheong Poon Acked-by: Santosh Shilimkar Signed-off-by: David S. Miller --- net/rds/af_rds.c | 140 ++++++++++++------ net/rds/bind.c | 91 ++++++++---- net/rds/cong.c | 23 +-- net/rds/connection.c | 132 ++++++++++------- net/rds/ib.c | 17 +-- net/rds/ib.h | 51 +++++-- net/rds/ib_cm.c | 299 +++++++++++++++++++++++++++++---------- net/rds/ib_rdma.c | 15 +- net/rds/ib_recv.c | 18 +-- net/rds/ib_send.c | 10 +- net/rds/loop.c | 7 +- net/rds/rdma.c | 6 +- net/rds/rdma_transport.c | 56 +++++--- net/rds/rds.h | 70 ++++++--- net/rds/recv.c | 51 ++++--- net/rds/send.c | 67 +++++++-- net/rds/tcp.c | 32 ++++- net/rds/tcp_connect.c | 34 +++-- net/rds/tcp_listen.c | 18 +-- net/rds/tcp_recv.c | 9 +- net/rds/tcp_send.c | 4 +- net/rds/threads.c | 69 +++++++-- net/rds/transport.c | 15 +- 23 files changed, 864 insertions(+), 370 deletions(-) diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index ab751a150f70..fc1a5c63b783 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2006 Oracle. All rights reserved. + * Copyright (c) 2006, 2018 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 @@ -35,6 +35,7 @@ #include #include #include +#include #include #include @@ -113,26 +114,63 @@ void rds_wake_sk_sleep(struct rds_sock *rs) static int rds_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { - struct sockaddr_in *sin = (struct sockaddr_in *)uaddr; struct rds_sock *rs = rds_sk_to_rs(sock->sk); - - memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); + struct sockaddr_in6 *sin6; + struct sockaddr_in *sin; + int uaddr_len; /* racey, don't care */ if (peer) { - if (!rs->rs_conn_addr) + if (ipv6_addr_any(&rs->rs_conn_addr)) return -ENOTCONN; - sin->sin_port = rs->rs_conn_port; - sin->sin_addr.s_addr = rs->rs_conn_addr; + if (ipv6_addr_v4mapped(&rs->rs_conn_addr)) { + sin = (struct sockaddr_in *)uaddr; + memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); + sin->sin_family = AF_INET; + sin->sin_port = rs->rs_conn_port; + sin->sin_addr.s_addr = rs->rs_conn_addr_v4; + uaddr_len = sizeof(*sin); + } else { + sin6 = (struct sockaddr_in6 *)uaddr; + sin6->sin6_family = AF_INET6; + sin6->sin6_port = rs->rs_conn_port; + sin6->sin6_addr = rs->rs_conn_addr; + sin6->sin6_flowinfo = 0; + /* scope_id is the same as in the bound address. */ + sin6->sin6_scope_id = rs->rs_bound_scope_id; + uaddr_len = sizeof(*sin6); + } } else { - sin->sin_port = rs->rs_bound_port; - sin->sin_addr.s_addr = rs->rs_bound_addr; + /* If socket is not yet bound, set the return address family + * to be AF_UNSPEC (value 0) and the address size to be that + * of an IPv4 address. + */ + if (ipv6_addr_any(&rs->rs_bound_addr)) { + sin = (struct sockaddr_in *)uaddr; + memset(sin, 0, sizeof(*sin)); + sin->sin_family = AF_UNSPEC; + return sizeof(*sin); + } + if (ipv6_addr_v4mapped(&rs->rs_bound_addr)) { + sin = (struct sockaddr_in *)uaddr; + memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); + sin->sin_family = AF_INET; + sin->sin_port = rs->rs_bound_port; + sin->sin_addr.s_addr = rs->rs_bound_addr_v4; + uaddr_len = sizeof(*sin); + } else { + sin6 = (struct sockaddr_in6 *)uaddr; + sin6->sin6_family = AF_INET6; + sin6->sin6_port = rs->rs_bound_port; + sin6->sin6_addr = rs->rs_bound_addr; + sin6->sin6_flowinfo = 0; + sin6->sin6_scope_id = rs->rs_bound_scope_id; + uaddr_len = sizeof(*sin6); + } } - sin->sin_family = AF_INET; - - return sizeof(*sin); + return uaddr_len; } /* @@ -203,11 +241,12 @@ static int rds_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) static int rds_cancel_sent_to(struct rds_sock *rs, char __user *optval, int len) { + struct sockaddr_in6 sin6; struct sockaddr_in sin; int ret = 0; /* racing with another thread binding seems ok here */ - if (rs->rs_bound_addr == 0) { + if (ipv6_addr_any(&rs->rs_bound_addr)) { ret = -ENOTCONN; /* XXX not a great errno */ goto out; } @@ -215,14 +254,23 @@ static int rds_cancel_sent_to(struct rds_sock *rs, char __user *optval, if (len < sizeof(struct sockaddr_in)) { ret = -EINVAL; goto out; + } else if (len < sizeof(struct sockaddr_in6)) { + /* Assume IPv4 */ + if (copy_from_user(&sin, optval, sizeof(struct sockaddr_in))) { + ret = -EFAULT; + goto out; + } + ipv6_addr_set_v4mapped(sin.sin_addr.s_addr, &sin6.sin6_addr); + sin6.sin6_port = sin.sin_port; + } else { + if (copy_from_user(&sin6, optval, + sizeof(struct sockaddr_in6))) { + ret = -EFAULT; + goto out; + } } - if (copy_from_user(&sin, optval, sizeof(sin))) { - ret = -EFAULT; - goto out; - } - - rds_send_drop_to(rs, &sin); + rds_send_drop_to(rs, &sin6); out: return ret; } @@ -435,31 +483,41 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) { struct sock *sk = sock->sk; - struct sockaddr_in *sin = (struct sockaddr_in *)uaddr; + struct sockaddr_in *sin; struct rds_sock *rs = rds_sk_to_rs(sk); int ret = 0; lock_sock(sk); - if (addr_len != sizeof(struct sockaddr_in)) { + switch (addr_len) { + case sizeof(struct sockaddr_in): + sin = (struct sockaddr_in *)uaddr; + if (sin->sin_family != AF_INET) { + ret = -EAFNOSUPPORT; + break; + } + if (sin->sin_addr.s_addr == htonl(INADDR_ANY)) { + ret = -EDESTADDRREQ; + break; + } + if (IN_MULTICAST(ntohl(sin->sin_addr.s_addr)) || + sin->sin_addr.s_addr == htonl(INADDR_BROADCAST)) { + ret = -EINVAL; + break; + } + ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &rs->rs_conn_addr); + rs->rs_conn_port = sin->sin_port; + break; + + case sizeof(struct sockaddr_in6): + ret = -EPROTONOSUPPORT; + break; + + default: ret = -EINVAL; - goto out; + break; } - if (sin->sin_family != AF_INET) { - ret = -EAFNOSUPPORT; - goto out; - } - - if (sin->sin_addr.s_addr == htonl(INADDR_ANY)) { - ret = -EDESTADDRREQ; - goto out; - } - - rs->rs_conn_addr = sin->sin_addr.s_addr; - rs->rs_conn_port = sin->sin_port; - -out: release_sock(sk); return ret; } @@ -578,8 +636,10 @@ static void rds_sock_inc_info(struct socket *sock, unsigned int len, list_for_each_entry(inc, &rs->rs_recv_queue, i_item) { total++; if (total <= len) - rds_inc_info_copy(inc, iter, inc->i_saddr, - rs->rs_bound_addr, 1); + rds_inc_info_copy(inc, iter, + inc->i_saddr.s6_addr32[3], + rs->rs_bound_addr_v4, + 1); } read_unlock(&rs->rs_recv_lock); @@ -608,8 +668,8 @@ static void rds_sock_info(struct socket *sock, unsigned int len, list_for_each_entry(rs, &rds_sock_list, rs_item) { sinfo.sndbuf = rds_sk_sndbuf(rs); sinfo.rcvbuf = rds_sk_rcvbuf(rs); - sinfo.bound_addr = rs->rs_bound_addr; - sinfo.connected_addr = rs->rs_conn_addr; + sinfo.bound_addr = rs->rs_bound_addr_v4; + sinfo.connected_addr = rs->rs_conn_addr_v4; sinfo.bound_port = rs->rs_bound_port; sinfo.connected_port = rs->rs_conn_port; sinfo.inum = sock_i_ino(rds_rs_to_sk(rs)); diff --git a/net/rds/bind.c b/net/rds/bind.c index 5aa3a64aa4f0..c401776ad938 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2006 Oracle. All rights reserved. + * Copyright (c) 2006, 2018 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 @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include @@ -42,42 +43,58 @@ static struct rhashtable bind_hash_table; static const struct rhashtable_params ht_parms = { .nelem_hint = 768, - .key_len = sizeof(u64), + .key_len = RDS_BOUND_KEY_LEN, .key_offset = offsetof(struct rds_sock, rs_bound_key), .head_offset = offsetof(struct rds_sock, rs_bound_node), .max_size = 16384, .min_size = 1024, }; +/* Create a key for the bind hash table manipulation. Port is in network byte + * order. + */ +static inline void __rds_create_bind_key(u8 *key, const struct in6_addr *addr, + __be16 port, __u32 scope_id) +{ + memcpy(key, addr, sizeof(*addr)); + key += sizeof(*addr); + memcpy(key, &port, sizeof(port)); + key += sizeof(port); + memcpy(key, &scope_id, sizeof(scope_id)); +} + /* * Return the rds_sock bound at the given local address. * * The rx path can race with rds_release. We notice if rds_release() has * marked this socket and don't return a rs ref to the rx path. */ -struct rds_sock *rds_find_bound(__be32 addr, __be16 port) +struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port, + __u32 scope_id) { - u64 key = ((u64)addr << 32) | port; + u8 key[RDS_BOUND_KEY_LEN]; struct rds_sock *rs; - rs = rhashtable_lookup_fast(&bind_hash_table, &key, ht_parms); + __rds_create_bind_key(key, addr, port, scope_id); + rs = rhashtable_lookup_fast(&bind_hash_table, key, ht_parms); if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD)) rds_sock_addref(rs); else rs = NULL; - rdsdebug("returning rs %p for %pI4:%u\n", rs, &addr, - ntohs(port)); + rdsdebug("returning rs %p for %pI6c:%u\n", rs, addr, + ntohs(port)); return rs; } /* returns -ve errno or +ve port */ -static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port) +static int rds_add_bound(struct rds_sock *rs, const struct in6_addr *addr, + __be16 *port, __u32 scope_id) { int ret = -EADDRINUSE; u16 rover, last; - u64 key; + u8 key[RDS_BOUND_KEY_LEN]; if (*port != 0) { rover = be16_to_cpu(*port); @@ -95,12 +112,13 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port) if (rover == RDS_FLAG_PROBE_PORT) continue; - key = ((u64)addr << 32) | cpu_to_be16(rover); - if (rhashtable_lookup_fast(&bind_hash_table, &key, ht_parms)) + __rds_create_bind_key(key, addr, cpu_to_be16(rover), + scope_id); + if (rhashtable_lookup_fast(&bind_hash_table, key, ht_parms)) continue; - rs->rs_bound_key = key; - rs->rs_bound_addr = addr; + memcpy(rs->rs_bound_key, key, sizeof(rs->rs_bound_key)); + rs->rs_bound_addr = *addr; net_get_random_once(&rs->rs_hash_initval, sizeof(rs->rs_hash_initval)); rs->rs_bound_port = cpu_to_be16(rover); @@ -114,7 +132,7 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port) rs, &addr, (int)ntohs(*port)); break; } else { - rs->rs_bound_addr = 0; + rs->rs_bound_addr = in6addr_any; rds_sock_put(rs); ret = -ENOMEM; break; @@ -127,44 +145,61 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port) void rds_remove_bound(struct rds_sock *rs) { - if (!rs->rs_bound_addr) + if (ipv6_addr_any(&rs->rs_bound_addr)) return; - rdsdebug("rs %p unbinding from %pI4:%d\n", + rdsdebug("rs %p unbinding from %pI6c:%d\n", rs, &rs->rs_bound_addr, ntohs(rs->rs_bound_port)); rhashtable_remove_fast(&bind_hash_table, &rs->rs_bound_node, ht_parms); rds_sock_put(rs); - rs->rs_bound_addr = 0; + rs->rs_bound_addr = in6addr_any; } int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; - struct sockaddr_in *sin = (struct sockaddr_in *)uaddr; struct rds_sock *rs = rds_sk_to_rs(sk); + struct in6_addr v6addr, *binding_addr; struct rds_transport *trans; + __u32 scope_id = 0; int ret = 0; + __be16 port; + /* We only allow an RDS socket to be bound to an IPv4 address. IPv6 + * address support will be added later. + */ + if (addr_len == sizeof(struct sockaddr_in)) { + struct sockaddr_in *sin = (struct sockaddr_in *)uaddr; + + if (sin->sin_family != AF_INET || + sin->sin_addr.s_addr == htonl(INADDR_ANY)) + return -EINVAL; + ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &v6addr); + binding_addr = &v6addr; + port = sin->sin_port; + } else if (addr_len == sizeof(struct sockaddr_in6)) { + return -EPROTONOSUPPORT; + } else { + return -EINVAL; + } lock_sock(sk); - if (addr_len != sizeof(struct sockaddr_in) || - sin->sin_family != AF_INET || - rs->rs_bound_addr || - sin->sin_addr.s_addr == htonl(INADDR_ANY)) { + /* RDS socket does not allow re-binding. */ + if (!ipv6_addr_any(&rs->rs_bound_addr)) { ret = -EINVAL; goto out; } - ret = rds_add_bound(rs, sin->sin_addr.s_addr, &sin->sin_port); + ret = rds_add_bound(rs, binding_addr, &port, scope_id); if (ret) goto out; if (rs->rs_transport) { /* previously bound */ trans = rs->rs_transport; if (trans->laddr_check(sock_net(sock->sk), - sin->sin_addr.s_addr) != 0) { + binding_addr, scope_id) != 0) { ret = -ENOPROTOOPT; rds_remove_bound(rs); } else { @@ -172,13 +207,13 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) } goto out; } - trans = rds_trans_get_preferred(sock_net(sock->sk), - sin->sin_addr.s_addr); + trans = rds_trans_get_preferred(sock_net(sock->sk), binding_addr, + scope_id); if (!trans) { ret = -EADDRNOTAVAIL; rds_remove_bound(rs); - pr_info_ratelimited("RDS: %s could not find a transport for %pI4, load rds_tcp or rds_rdma?\n", - __func__, &sin->sin_addr.s_addr); + pr_info_ratelimited("RDS: %s could not find a transport for %pI6c, load rds_tcp or rds_rdma?\n", + __func__, binding_addr); goto out; } diff --git a/net/rds/cong.c b/net/rds/cong.c index 63da9d2f142d..ccdff09a79c8 100644 --- a/net/rds/cong.c +++ b/net/rds/cong.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007 Oracle. All rights reserved. + * Copyright (c) 2007, 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 @@ -101,7 +101,7 @@ static DEFINE_RWLOCK(rds_cong_monitor_lock); static DEFINE_SPINLOCK(rds_cong_lock); static struct rb_root rds_cong_tree = RB_ROOT; -static struct rds_cong_map *rds_cong_tree_walk(__be32 addr, +static struct rds_cong_map *rds_cong_tree_walk(const struct in6_addr *addr, struct rds_cong_map *insert) { struct rb_node **p = &rds_cong_tree.rb_node; @@ -109,12 +109,15 @@ static struct rds_cong_map *rds_cong_tree_walk(__be32 addr, struct rds_cong_map *map; while (*p) { + int diff; + parent = *p; map = rb_entry(parent, struct rds_cong_map, m_rb_node); - if (addr < map->m_addr) + diff = rds_addr_cmp(addr, &map->m_addr); + if (diff < 0) p = &(*p)->rb_left; - else if (addr > map->m_addr) + else if (diff > 0) p = &(*p)->rb_right; else return map; @@ -132,7 +135,7 @@ static struct rds_cong_map *rds_cong_tree_walk(__be32 addr, * these bitmaps in the process getting pointers to them. The bitmaps are only * ever freed as the module is removed after all connections have been freed. */ -static struct rds_cong_map *rds_cong_from_addr(__be32 addr) +static struct rds_cong_map *rds_cong_from_addr(const struct in6_addr *addr) { struct rds_cong_map *map; struct rds_cong_map *ret = NULL; @@ -144,7 +147,7 @@ static struct rds_cong_map *rds_cong_from_addr(__be32 addr) if (!map) return NULL; - map->m_addr = addr; + map->m_addr = *addr; init_waitqueue_head(&map->m_waitq); INIT_LIST_HEAD(&map->m_conn_list); @@ -171,7 +174,7 @@ static struct rds_cong_map *rds_cong_from_addr(__be32 addr) kfree(map); } - rdsdebug("map %p for addr %x\n", ret, be32_to_cpu(addr)); + rdsdebug("map %p for addr %pI6c\n", ret, addr); return ret; } @@ -202,8 +205,8 @@ void rds_cong_remove_conn(struct rds_connection *conn) int rds_cong_get_maps(struct rds_connection *conn) { - conn->c_lcong = rds_cong_from_addr(conn->c_laddr); - conn->c_fcong = rds_cong_from_addr(conn->c_faddr); + conn->c_lcong = rds_cong_from_addr(&conn->c_laddr); + conn->c_fcong = rds_cong_from_addr(&conn->c_faddr); if (!(conn->c_lcong && conn->c_fcong)) return -ENOMEM; @@ -353,7 +356,7 @@ void rds_cong_remove_socket(struct rds_sock *rs) /* update congestion map for now-closed port */ spin_lock_irqsave(&rds_cong_lock, flags); - map = rds_cong_tree_walk(rs->rs_bound_addr, NULL); + map = rds_cong_tree_walk(&rs->rs_bound_addr, NULL); spin_unlock_irqrestore(&rds_cong_lock, flags); if (map && rds_cong_test_bit(map, rs->rs_bound_port)) { 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 #include #include -#include +#include +#include #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 @@ static struct rds_connection *__rds_conn_create(struct net *net, } 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; diff --git a/net/rds/ib.c b/net/rds/ib.c index b6ad38e48f62..c712a848957d 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.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 @@ -296,8 +296,8 @@ static int rds_ib_conn_info_visitor(struct rds_connection *conn, if (conn->c_trans != &rds_ib_transport) return 0; - iinfo->src_addr = conn->c_laddr; - iinfo->dst_addr = conn->c_faddr; + iinfo->src_addr = conn->c_laddr.s6_addr32[3]; + iinfo->dst_addr = conn->c_faddr.s6_addr32[3]; memset(&iinfo->src_gid, 0, sizeof(iinfo->src_gid)); memset(&iinfo->dst_gid, 0, sizeof(iinfo->dst_gid)); @@ -341,7 +341,8 @@ static void rds_ib_ic_info(struct socket *sock, unsigned int len, * allowed to influence which paths have priority. We could call userspace * asserting this policy "routing". */ -static int rds_ib_laddr_check(struct net *net, __be32 addr) +static int rds_ib_laddr_check(struct net *net, const struct in6_addr *addr, + __u32 scope_id) { int ret; struct rdma_cm_id *cm_id; @@ -357,7 +358,7 @@ static int rds_ib_laddr_check(struct net *net, __be32 addr) memset(&sin, 0, sizeof(sin)); sin.sin_family = AF_INET; - sin.sin_addr.s_addr = addr; + sin.sin_addr.s_addr = addr->s6_addr32[3]; /* rdma_bind_addr will only succeed for IB & iWARP devices */ ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin); @@ -367,9 +368,9 @@ static int rds_ib_laddr_check(struct net *net, __be32 addr) cm_id->device->node_type != RDMA_NODE_IB_CA) ret = -EADDRNOTAVAIL; - rdsdebug("addr %pI4 ret %d node type %d\n", - &addr, ret, - cm_id->device ? cm_id->device->node_type : -1); + rdsdebug("addr %pI6c ret %d node type %d\n", + addr, ret, + cm_id->device ? cm_id->device->node_type : -1); rdma_destroy_id(cm_id); diff --git a/net/rds/ib.h b/net/rds/ib.h index a6f4d7d68e95..beb95b893f78 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -57,16 +57,44 @@ struct rds_ib_refill_cache { struct list_head *ready; }; +/* This is the common structure for the IB private data exchange in setting up + * an RDS connection. The exchange is different for IPv4 and IPv6 connections. + * The reason is that the address size is different and the addresses + * exchanged are in the beginning of the structure. Hence it is not possible + * for interoperability if same structure is used. + */ +struct rds_ib_conn_priv_cmn { + u8 ricpc_protocol_major; + u8 ricpc_protocol_minor; + __be16 ricpc_protocol_minor_mask; /* bitmask */ + __be32 ricpc_reserved1; + __be64 ricpc_ack_seq; + __be32 ricpc_credit; /* non-zero enables flow ctl */ +}; + struct rds_ib_connect_private { /* Add new fields at the end, and don't permute existing fields. */ - __be32 dp_saddr; - __be32 dp_daddr; - u8 dp_protocol_major; - u8 dp_protocol_minor; - __be16 dp_protocol_minor_mask; /* bitmask */ - __be32 dp_reserved1; - __be64 dp_ack_seq; - __be32 dp_credit; /* non-zero enables flow ctl */ + __be32 dp_saddr; + __be32 dp_daddr; + struct rds_ib_conn_priv_cmn dp_cmn; +}; + +struct rds6_ib_connect_private { + /* Add new fields at the end, and don't permute existing fields. */ + struct in6_addr dp_saddr; + struct in6_addr dp_daddr; + struct rds_ib_conn_priv_cmn dp_cmn; +}; + +#define dp_protocol_major dp_cmn.ricpc_protocol_major +#define dp_protocol_minor dp_cmn.ricpc_protocol_minor +#define dp_protocol_minor_mask dp_cmn.ricpc_protocol_minor_mask +#define dp_ack_seq dp_cmn.ricpc_ack_seq +#define dp_credit dp_cmn.ricpc_credit + +union rds_ib_conn_priv { + struct rds_ib_connect_private ricp_v4; + struct rds6_ib_connect_private ricp_v6; }; struct rds_ib_send_work { @@ -351,8 +379,8 @@ void rds_ib_listen_stop(void); __printf(2, 3) void __rds_ib_conn_error(struct rds_connection *conn, const char *, ...); int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, - struct rdma_cm_event *event); -int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id); + struct rdma_cm_event *event, bool isv6); +int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id, bool isv6); void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_event *event); @@ -361,7 +389,8 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, __rds_ib_conn_error(conn, KERN_WARNING "RDS/IB: " fmt) /* ib_rdma.c */ -int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr); +int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev, + struct in6_addr *ipaddr); void rds_ib_add_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn); void rds_ib_remove_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn); void rds_ib_destroy_nodev_conns(void); diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index f1684ae6abfd..dd8a867e5a9c 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2006 Oracle. All rights reserved. + * Copyright (c) 2006, 2018 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 @@ -35,6 +35,7 @@ #include #include #include +#include #include "rds_single_path.h" #include "rds.h" @@ -95,25 +96,45 @@ rds_ib_tune_rnr(struct rds_ib_connection *ic, struct ib_qp_attr *attr) */ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_event *event) { - const struct rds_ib_connect_private *dp = NULL; struct rds_ib_connection *ic = conn->c_transport_data; + const union rds_ib_conn_priv *dp = NULL; struct ib_qp_attr qp_attr; + __be64 ack_seq = 0; + __be32 credit = 0; + u8 major = 0; + u8 minor = 0; int err; - if (event->param.conn.private_data_len >= sizeof(*dp)) { - dp = event->param.conn.private_data; - - /* make sure it isn't empty data */ - if (dp->dp_protocol_major) { - rds_ib_set_protocol(conn, - RDS_PROTOCOL(dp->dp_protocol_major, - dp->dp_protocol_minor)); - rds_ib_set_flow_control(conn, be32_to_cpu(dp->dp_credit)); + dp = event->param.conn.private_data; + if (conn->c_isv6) { + if (event->param.conn.private_data_len >= + sizeof(struct rds6_ib_connect_private)) { + major = dp->ricp_v6.dp_protocol_major; + minor = dp->ricp_v6.dp_protocol_minor; + credit = dp->ricp_v6.dp_credit; + /* dp structure start is not guaranteed to be 8 bytes + * aligned. Since dp_ack_seq is 64-bit extended load + * operations can be used so go through get_unaligned + * to avoid unaligned errors. + */ + ack_seq = get_unaligned(&dp->ricp_v6.dp_ack_seq); } + } else if (event->param.conn.private_data_len >= + sizeof(struct rds_ib_connect_private)) { + major = dp->ricp_v4.dp_protocol_major; + minor = dp->ricp_v4.dp_protocol_minor; + credit = dp->ricp_v4.dp_credit; + ack_seq = get_unaligned(&dp->ricp_v4.dp_ack_seq); + } + + /* make sure it isn't empty data */ + if (major) { + rds_ib_set_protocol(conn, RDS_PROTOCOL(major, minor)); + rds_ib_set_flow_control(conn, be32_to_cpu(credit)); } if (conn->c_version < RDS_PROTOCOL(3, 1)) { - pr_notice("RDS/IB: Connection <%pI4,%pI4> version %u.%u no longer supported\n", + pr_notice("RDS/IB: Connection <%pI6c,%pI6c> version %u.%u no longer supported\n", &conn->c_laddr, &conn->c_faddr, RDS_PROTOCOL_MAJOR(conn->c_version), RDS_PROTOCOL_MINOR(conn->c_version)); @@ -121,7 +142,7 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even rds_conn_destroy(conn); return; } else { - pr_notice("RDS/IB: %s conn connected <%pI4,%pI4> version %u.%u%s\n", + pr_notice("RDS/IB: %s conn connected <%pI6c,%pI6c> version %u.%u%s\n", ic->i_active_side ? "Active" : "Passive", &conn->c_laddr, &conn->c_faddr, RDS_PROTOCOL_MAJOR(conn->c_version), @@ -150,7 +171,7 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even printk(KERN_NOTICE "ib_modify_qp(IB_QP_STATE, RTS): err=%d\n", err); /* update ib_device with this local ipaddr */ - err = rds_ib_update_ipaddr(ic->rds_ibdev, conn->c_laddr); + err = rds_ib_update_ipaddr(ic->rds_ibdev, &conn->c_laddr); if (err) printk(KERN_ERR "rds_ib_update_ipaddr failed (%d)\n", err); @@ -158,14 +179,8 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even /* If the peer gave us the last packet it saw, process this as if * we had received a regular ACK. */ if (dp) { - /* dp structure start is not guaranteed to be 8 bytes aligned. - * Since dp_ack_seq is 64-bit extended load operations can be - * used so go through get_unaligned to avoid unaligned errors. - */ - __be64 dp_ack_seq = get_unaligned(&dp->dp_ack_seq); - - if (dp_ack_seq) - rds_send_drop_acked(conn, be64_to_cpu(dp_ack_seq), + if (ack_seq) + rds_send_drop_acked(conn, be64_to_cpu(ack_seq), NULL); } @@ -173,11 +188,12 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even } static void rds_ib_cm_fill_conn_param(struct rds_connection *conn, - struct rdma_conn_param *conn_param, - struct rds_ib_connect_private *dp, - u32 protocol_version, - u32 max_responder_resources, - u32 max_initiator_depth) + struct rdma_conn_param *conn_param, + union rds_ib_conn_priv *dp, + u32 protocol_version, + u32 max_responder_resources, + u32 max_initiator_depth, + bool isv6) { struct rds_ib_connection *ic = conn->c_transport_data; struct rds_ib_device *rds_ibdev = ic->rds_ibdev; @@ -193,24 +209,49 @@ static void rds_ib_cm_fill_conn_param(struct rds_connection *conn, if (dp) { memset(dp, 0, sizeof(*dp)); - dp->dp_saddr = conn->c_laddr; - dp->dp_daddr = conn->c_faddr; - dp->dp_protocol_major = RDS_PROTOCOL_MAJOR(protocol_version); - dp->dp_protocol_minor = RDS_PROTOCOL_MINOR(protocol_version); - dp->dp_protocol_minor_mask = cpu_to_be16(RDS_IB_SUPPORTED_PROTOCOLS); - dp->dp_ack_seq = cpu_to_be64(rds_ib_piggyb_ack(ic)); + if (isv6) { + dp->ricp_v6.dp_saddr = conn->c_laddr; + dp->ricp_v6.dp_daddr = conn->c_faddr; + dp->ricp_v6.dp_protocol_major = + RDS_PROTOCOL_MAJOR(protocol_version); + dp->ricp_v6.dp_protocol_minor = + RDS_PROTOCOL_MINOR(protocol_version); + dp->ricp_v6.dp_protocol_minor_mask = + cpu_to_be16(RDS_IB_SUPPORTED_PROTOCOLS); + dp->ricp_v6.dp_ack_seq = + cpu_to_be64(rds_ib_piggyb_ack(ic)); + + conn_param->private_data = &dp->ricp_v6; + conn_param->private_data_len = sizeof(dp->ricp_v6); + } else { + dp->ricp_v4.dp_saddr = conn->c_laddr.s6_addr32[3]; + dp->ricp_v4.dp_daddr = conn->c_faddr.s6_addr32[3]; + dp->ricp_v4.dp_protocol_major = + RDS_PROTOCOL_MAJOR(protocol_version); + dp->ricp_v4.dp_protocol_minor = + RDS_PROTOCOL_MINOR(protocol_version); + dp->ricp_v4.dp_protocol_minor_mask = + cpu_to_be16(RDS_IB_SUPPORTED_PROTOCOLS); + dp->ricp_v4.dp_ack_seq = + cpu_to_be64(rds_ib_piggyb_ack(ic)); + + conn_param->private_data = &dp->ricp_v4; + conn_param->private_data_len = sizeof(dp->ricp_v4); + } /* Advertise flow control */ if (ic->i_flowctl) { unsigned int credits; - credits = IB_GET_POST_CREDITS(atomic_read(&ic->i_credits)); - dp->dp_credit = cpu_to_be32(credits); - atomic_sub(IB_SET_POST_CREDITS(credits), &ic->i_credits); + credits = IB_GET_POST_CREDITS + (atomic_read(&ic->i_credits)); + if (isv6) + dp->ricp_v6.dp_credit = cpu_to_be32(credits); + else + dp->ricp_v4.dp_credit = cpu_to_be32(credits); + atomic_sub(IB_SET_POST_CREDITS(credits), + &ic->i_credits); } - - conn_param->private_data = dp; - conn_param->private_data_len = sizeof(*dp); } } @@ -349,7 +390,7 @@ static void rds_ib_qp_event_handler(struct ib_event *event, void *data) break; default: rdsdebug("Fatal QP Event %u (%s) " - "- connection %pI4->%pI4, reconnecting\n", + "- connection %pI6c->%pI6c, reconnecting\n", event->event, ib_event_msg(event->event), &conn->c_laddr, &conn->c_faddr); rds_conn_drop(conn); @@ -580,11 +621,13 @@ static int rds_ib_setup_qp(struct rds_connection *conn) return ret; } -static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event) +static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event, bool isv6) { - const struct rds_ib_connect_private *dp = event->param.conn.private_data; - u16 common; + const union rds_ib_conn_priv *dp = event->param.conn.private_data; + u8 data_len, major, minor; u32 version = 0; + __be16 mask; + u16 common; /* * rdma_cm private data is odd - when there is any private data in the @@ -603,51 +646,126 @@ static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event) return 0; } + if (isv6) { + data_len = sizeof(struct rds6_ib_connect_private); + major = dp->ricp_v6.dp_protocol_major; + minor = dp->ricp_v6.dp_protocol_minor; + mask = dp->ricp_v6.dp_protocol_minor_mask; + } else { + data_len = sizeof(struct rds_ib_connect_private); + major = dp->ricp_v4.dp_protocol_major; + minor = dp->ricp_v4.dp_protocol_minor; + mask = dp->ricp_v4.dp_protocol_minor_mask; + } + /* Even if len is crap *now* I still want to check it. -ASG */ - if (event->param.conn.private_data_len < sizeof (*dp) || - dp->dp_protocol_major == 0) + if (event->param.conn.private_data_len < data_len || major == 0) return RDS_PROTOCOL_3_0; - common = be16_to_cpu(dp->dp_protocol_minor_mask) & RDS_IB_SUPPORTED_PROTOCOLS; - if (dp->dp_protocol_major == 3 && common) { + common = be16_to_cpu(mask) & RDS_IB_SUPPORTED_PROTOCOLS; + if (major == 3 && common) { version = RDS_PROTOCOL_3_0; while ((common >>= 1) != 0) version++; - } else - printk_ratelimited(KERN_NOTICE "RDS: Connection from %pI4 using incompatible protocol version %u.%u\n", - &dp->dp_saddr, - dp->dp_protocol_major, - dp->dp_protocol_minor); + } else { + if (isv6) + printk_ratelimited(KERN_NOTICE "RDS: Connection from %pI6c using incompatible protocol version %u.%u\n", + &dp->ricp_v6.dp_saddr, major, minor); + else + printk_ratelimited(KERN_NOTICE "RDS: Connection from %pI4 using incompatible protocol version %u.%u\n", + &dp->ricp_v4.dp_saddr, major, minor); + } return version; } +/* Given an IPv6 address, find the IB net_device which hosts that address and + * return its index. This is used by the rds_ib_cm_handle_connect() code to + * find the interface index of where an incoming request comes from when + * the request is using a link local address. + * + * Note one problem in this search. It is possible that two interfaces have + * the same link local address. Unfortunately, this cannot be solved unless + * the underlying layer gives us the interface which an incoming RDMA connect + * request comes from. + */ +static u32 __rds_find_ifindex(struct net *net, const struct in6_addr *addr) +{ + struct net_device *dev; + int idx = 0; + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + if (dev->type == ARPHRD_INFINIBAND && + ipv6_chk_addr(net, addr, dev, 0)) { + idx = dev->ifindex; + break; + } + } + rcu_read_unlock(); + + return idx; +} + int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, - struct rdma_cm_event *event) + struct rdma_cm_event *event, bool isv6) { __be64 lguid = cm_id->route.path_rec->sgid.global.interface_id; __be64 fguid = cm_id->route.path_rec->dgid.global.interface_id; - const struct rds_ib_connect_private *dp = event->param.conn.private_data; - struct rds_ib_connect_private dp_rep; + const struct rds_ib_conn_priv_cmn *dp_cmn; struct rds_connection *conn = NULL; struct rds_ib_connection *ic = NULL; struct rdma_conn_param conn_param; + const union rds_ib_conn_priv *dp; + union rds_ib_conn_priv dp_rep; + struct in6_addr s_mapped_addr; + struct in6_addr d_mapped_addr; + const struct in6_addr *saddr6; + const struct in6_addr *daddr6; + int destroy = 1; + u32 ifindex = 0; u32 version; - int err = 1, destroy = 1; + int err = 1; /* Check whether the remote protocol version matches ours. */ - version = rds_ib_protocol_compatible(event); + version = rds_ib_protocol_compatible(event, isv6); if (!version) goto out; - rdsdebug("saddr %pI4 daddr %pI4 RDSv%u.%u lguid 0x%llx fguid " - "0x%llx\n", &dp->dp_saddr, &dp->dp_daddr, + dp = event->param.conn.private_data; + if (isv6) { + dp_cmn = &dp->ricp_v6.dp_cmn; + saddr6 = &dp->ricp_v6.dp_saddr; + daddr6 = &dp->ricp_v6.dp_daddr; + /* If the local address is link local, need to find the + * interface index in order to create a proper RDS + * connection. + */ + if (ipv6_addr_type(daddr6) & IPV6_ADDR_LINKLOCAL) { + /* Using init_net for now .. */ + ifindex = __rds_find_ifindex(&init_net, daddr6); + /* No index found... Need to bail out. */ + if (ifindex == 0) { + err = -EOPNOTSUPP; + goto out; + } + } + } else { + dp_cmn = &dp->ricp_v4.dp_cmn; + ipv6_addr_set_v4mapped(dp->ricp_v4.dp_saddr, &s_mapped_addr); + ipv6_addr_set_v4mapped(dp->ricp_v4.dp_daddr, &d_mapped_addr); + saddr6 = &s_mapped_addr; + daddr6 = &d_mapped_addr; + } + + rdsdebug("saddr %pI6c daddr %pI6c RDSv%u.%u lguid 0x%llx fguid " + "0x%llx\n", saddr6, daddr6, RDS_PROTOCOL_MAJOR(version), RDS_PROTOCOL_MINOR(version), (unsigned long long)be64_to_cpu(lguid), (unsigned long long)be64_to_cpu(fguid)); /* RDS/IB is not currently netns aware, thus init_net */ - conn = rds_conn_create(&init_net, dp->dp_daddr, dp->dp_saddr, - &rds_ib_transport, GFP_KERNEL); + conn = rds_conn_create(&init_net, daddr6, saddr6, + &rds_ib_transport, GFP_KERNEL, ifindex); if (IS_ERR(conn)) { rdsdebug("rds_conn_create failed (%ld)\n", PTR_ERR(conn)); conn = NULL; @@ -678,12 +796,13 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, ic = conn->c_transport_data; rds_ib_set_protocol(conn, version); - rds_ib_set_flow_control(conn, be32_to_cpu(dp->dp_credit)); + rds_ib_set_flow_control(conn, be32_to_cpu(dp_cmn->ricpc_credit)); /* If the peer gave us the last packet it saw, process this as if * we had received a regular ACK. */ - if (dp->dp_ack_seq) - rds_send_drop_acked(conn, be64_to_cpu(dp->dp_ack_seq), NULL); + if (dp_cmn->ricpc_ack_seq) + rds_send_drop_acked(conn, be64_to_cpu(dp_cmn->ricpc_ack_seq), + NULL); BUG_ON(cm_id->context); BUG_ON(ic->i_cm_id); @@ -702,8 +821,8 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, } rds_ib_cm_fill_conn_param(conn, &conn_param, &dp_rep, version, - event->param.conn.responder_resources, - event->param.conn.initiator_depth); + event->param.conn.responder_resources, + event->param.conn.initiator_depth, isv6); /* rdma_accept() calls rdma_reject() internally if it fails */ if (rdma_accept(cm_id, &conn_param)) @@ -718,12 +837,12 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, } -int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id) +int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id, bool isv6) { struct rds_connection *conn = cm_id->context; struct rds_ib_connection *ic = conn->c_transport_data; struct rdma_conn_param conn_param; - struct rds_ib_connect_private dp; + union rds_ib_conn_priv dp; int ret; /* If the peer doesn't do protocol negotiation, we must @@ -738,7 +857,7 @@ int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id) } rds_ib_cm_fill_conn_param(conn, &conn_param, &dp, RDS_PROTOCOL_VERSION, - UINT_MAX, UINT_MAX); + UINT_MAX, UINT_MAX, isv6); ret = rdma_connect(cm_id, &conn_param); if (ret) rds_ib_conn_error(conn, "rdma_connect failed (%d)\n", ret); @@ -758,13 +877,17 @@ int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id) int rds_ib_conn_path_connect(struct rds_conn_path *cp) { struct rds_connection *conn = cp->cp_conn; - struct rds_ib_connection *ic = conn->c_transport_data; - struct sockaddr_in src, dest; + struct sockaddr_storage src, dest; + rdma_cm_event_handler handler; + struct rds_ib_connection *ic; int ret; + ic = conn->c_transport_data; + /* XXX I wonder what affect the port space has */ /* delegate cm event handler to rdma_transport */ - ic->i_cm_id = rdma_create_id(&init_net, rds_rdma_cm_event_handler, conn, + handler = rds_rdma_cm_event_handler; + ic->i_cm_id = rdma_create_id(&init_net, handler, conn, RDMA_PS_TCP, IB_QPT_RC); if (IS_ERR(ic->i_cm_id)) { ret = PTR_ERR(ic->i_cm_id); @@ -775,13 +898,33 @@ int rds_ib_conn_path_connect(struct rds_conn_path *cp) rdsdebug("created cm id %p for conn %p\n", ic->i_cm_id, conn); - src.sin_family = AF_INET; - src.sin_addr.s_addr = (__force u32)conn->c_laddr; - src.sin_port = (__force u16)htons(0); + if (ipv6_addr_v4mapped(&conn->c_faddr)) { + struct sockaddr_in *sin; - dest.sin_family = AF_INET; - dest.sin_addr.s_addr = (__force u32)conn->c_faddr; - dest.sin_port = (__force u16)htons(RDS_PORT); + sin = (struct sockaddr_in *)&src; + sin->sin_family = AF_INET; + sin->sin_addr.s_addr = conn->c_laddr.s6_addr32[3]; + sin->sin_port = 0; + + sin = (struct sockaddr_in *)&dest; + sin->sin_family = AF_INET; + sin->sin_addr.s_addr = conn->c_faddr.s6_addr32[3]; + sin->sin_port = htons(RDS_PORT); + } else { + struct sockaddr_in6 *sin6; + + sin6 = (struct sockaddr_in6 *)&src; + sin6->sin6_family = AF_INET6; + sin6->sin6_addr = conn->c_laddr; + sin6->sin6_port = 0; + sin6->sin6_scope_id = conn->c_dev_if; + + sin6 = (struct sockaddr_in6 *)&dest; + sin6->sin6_family = AF_INET6; + sin6->sin6_addr = conn->c_faddr; + sin6->sin6_port = htons(RDS_CM_PORT); + sin6->sin6_scope_id = conn->c_dev_if; + } ret = rdma_resolve_addr(ic->i_cm_id, (struct sockaddr *)&src, (struct sockaddr *)&dest, diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index e678699268a2..0ec9df043dd0 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.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 @@ -100,18 +100,19 @@ static void rds_ib_remove_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr) kfree_rcu(to_free, rcu); } -int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr) +int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev, + struct in6_addr *ipaddr) { struct rds_ib_device *rds_ibdev_old; - rds_ibdev_old = rds_ib_get_device(ipaddr); + rds_ibdev_old = rds_ib_get_device(ipaddr->s6_addr32[3]); if (!rds_ibdev_old) - return rds_ib_add_ipaddr(rds_ibdev, ipaddr); + return rds_ib_add_ipaddr(rds_ibdev, ipaddr->s6_addr32[3]); if (rds_ibdev_old != rds_ibdev) { - rds_ib_remove_ipaddr(rds_ibdev_old, ipaddr); + rds_ib_remove_ipaddr(rds_ibdev_old, ipaddr->s6_addr32[3]); rds_ib_dev_put(rds_ibdev_old); - return rds_ib_add_ipaddr(rds_ibdev, ipaddr); + return rds_ib_add_ipaddr(rds_ibdev, ipaddr->s6_addr32[3]); } rds_ib_dev_put(rds_ibdev_old); @@ -544,7 +545,7 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, struct rds_ib_connection *ic = rs->rs_conn->c_transport_data; int ret; - rds_ibdev = rds_ib_get_device(rs->rs_bound_addr); + rds_ibdev = rds_ib_get_device(rs->rs_bound_addr.s6_addr32[3]); if (!rds_ibdev) { ret = -ENODEV; goto out; diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 1eaf2550a9f8..557ccbb1ce00 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.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 @@ -266,7 +266,7 @@ static struct rds_ib_incoming *rds_ib_refill_one_inc(struct rds_ib_connection *i rds_ib_stats_inc(s_ib_rx_total_incs); } INIT_LIST_HEAD(&ibinc->ii_frags); - rds_inc_init(&ibinc->ii_inc, ic->conn, ic->conn->c_faddr); + rds_inc_init(&ibinc->ii_inc, ic->conn, &ic->conn->c_faddr); return ibinc; } @@ -418,7 +418,7 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp) ret = ib_post_recv(ic->i_cm_id->qp, &recv->r_wr, &failed_wr); if (ret) { rds_ib_conn_error(conn, "recv post on " - "%pI4 returned %d, disconnecting and " + "%pI6c returned %d, disconnecting and " "reconnecting\n", &conn->c_faddr, ret); break; @@ -848,7 +848,7 @@ static void rds_ib_process_recv(struct rds_connection *conn, if (data_len < sizeof(struct rds_header)) { rds_ib_conn_error(conn, "incoming message " - "from %pI4 didn't include a " + "from %pI6c didn't include a " "header, disconnecting and " "reconnecting\n", &conn->c_faddr); @@ -861,7 +861,7 @@ static void rds_ib_process_recv(struct rds_connection *conn, /* Validate the checksum. */ if (!rds_message_verify_checksum(ihdr)) { rds_ib_conn_error(conn, "incoming message " - "from %pI4 has corrupted header - " + "from %pI6c has corrupted header - " "forcing a reconnect\n", &conn->c_faddr); rds_stats_inc(s_recv_drop_bad_checksum); @@ -941,10 +941,10 @@ static void rds_ib_process_recv(struct rds_connection *conn, ic->i_recv_data_rem = 0; ic->i_ibinc = NULL; - if (ibinc->ii_inc.i_hdr.h_flags == RDS_FLAG_CONG_BITMAP) + if (ibinc->ii_inc.i_hdr.h_flags == RDS_FLAG_CONG_BITMAP) { rds_ib_cong_recv(conn, ibinc); - else { - rds_recv_incoming(conn, conn->c_faddr, conn->c_laddr, + } else { + rds_recv_incoming(conn, &conn->c_faddr, &conn->c_laddr, &ibinc->ii_inc, GFP_ATOMIC); state->ack_next = be64_to_cpu(hdr->h_sequence); state->ack_next_valid = 1; @@ -988,7 +988,7 @@ void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic, } else { /* We expect errors as the qp is drained during shutdown */ if (rds_conn_up(conn) || rds_conn_connecting(conn)) - rds_ib_conn_error(conn, "recv completion on <%pI4,%pI4> had status %u (%s), disconnecting and reconnecting\n", + rds_ib_conn_error(conn, "recv completion on <%pI6c,%pI6c> had status %u (%s), disconnecting and reconnecting\n", &conn->c_laddr, &conn->c_faddr, wc->status, ib_wc_status_msg(wc->status)); diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index 8557a1cae041..c4cdfe491d96 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.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 @@ -305,7 +305,7 @@ void rds_ib_send_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc) /* We expect errors as the qp is drained during shutdown */ if (wc->status != IB_WC_SUCCESS && rds_conn_up(conn)) { - rds_ib_conn_error(conn, "send completion on <%pI4,%pI4> had status %u (%s), disconnecting and reconnecting\n", + rds_ib_conn_error(conn, "send completion on <%pI6c,%pI6c> had status %u (%s), disconnecting and reconnecting\n", &conn->c_laddr, &conn->c_faddr, wc->status, ib_wc_status_msg(wc->status)); } @@ -730,7 +730,7 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, first, &first->s_wr, ret, failed_wr); BUG_ON(failed_wr != &first->s_wr); if (ret) { - printk(KERN_WARNING "RDS/IB: ib_post_send to %pI4 " + printk(KERN_WARNING "RDS/IB: ib_post_send to %pI6c " "returned %d\n", &conn->c_faddr, ret); rds_ib_ring_unalloc(&ic->i_send_ring, work_alloc); rds_ib_sub_signaled(ic, nr_sig); @@ -827,7 +827,7 @@ int rds_ib_xmit_atomic(struct rds_connection *conn, struct rm_atomic_op *op) send, &send->s_atomic_wr, ret, failed_wr); BUG_ON(failed_wr != &send->s_atomic_wr.wr); if (ret) { - printk(KERN_WARNING "RDS/IB: atomic ib_post_send to %pI4 " + printk(KERN_WARNING "RDS/IB: atomic ib_post_send to %pI6c " "returned %d\n", &conn->c_faddr, ret); rds_ib_ring_unalloc(&ic->i_send_ring, work_alloc); rds_ib_sub_signaled(ic, nr_sig); @@ -967,7 +967,7 @@ int rds_ib_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op) first, &first->s_rdma_wr.wr, ret, failed_wr); BUG_ON(failed_wr != &first->s_rdma_wr.wr); if (ret) { - printk(KERN_WARNING "RDS/IB: rdma ib_post_send to %pI4 " + printk(KERN_WARNING "RDS/IB: rdma ib_post_send to %pI6c " "returned %d\n", &conn->c_faddr, ret); rds_ib_ring_unalloc(&ic->i_send_ring, work_alloc); rds_ib_sub_signaled(ic, nr_sig); diff --git a/net/rds/loop.c b/net/rds/loop.c index feea1f96ee2a..1d73ad79c847 100644 --- a/net/rds/loop.c +++ b/net/rds/loop.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 @@ -35,6 +35,7 @@ #include #include #include +#include #include "rds_single_path.h" #include "rds.h" @@ -88,11 +89,11 @@ static int rds_loop_xmit(struct rds_connection *conn, struct rds_message *rm, BUG_ON(hdr_off || sg || off); - rds_inc_init(&rm->m_inc, conn, conn->c_laddr); + rds_inc_init(&rm->m_inc, conn, &conn->c_laddr); /* For the embedded inc. Matching put is in loop_inc_free() */ rds_message_addref(rm); - rds_recv_incoming(conn, conn->c_laddr, conn->c_faddr, &rm->m_inc, + rds_recv_incoming(conn, &conn->c_laddr, &conn->c_faddr, &rm->m_inc, GFP_KERNEL); rds_send_drop_acked(conn, be64_to_cpu(rm->m_inc.i_hdr.h_sequence), diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 634cfcb7bba6..7b3998026825 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007 Oracle. All rights reserved. + * Copyright (c) 2007, 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 @@ -183,7 +183,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, long i; int ret; - if (rs->rs_bound_addr == 0 || !rs->rs_transport) { + if (ipv6_addr_any(&rs->rs_bound_addr) || !rs->rs_transport) { ret = -ENOTCONN; /* XXX not a great errno */ goto out; } @@ -574,7 +574,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, args = CMSG_DATA(cmsg); - if (rs->rs_bound_addr == 0) { + if (ipv6_addr_any(&rs->rs_bound_addr)) { ret = -ENOTCONN; /* XXX not a great errno */ goto out_ret; } diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c index fc59821f0a27..f49abef69550 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2009 Oracle. All rights reserved. + * Copyright (c) 2009, 2018 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 @@ -39,8 +39,9 @@ static struct rdma_cm_id *rds_rdma_listen_id; -int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id, - struct rdma_cm_event *event) +static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, + struct rdma_cm_event *event, + bool isv6) { /* this can be null in the listening path */ struct rds_connection *conn = cm_id->context; @@ -72,7 +73,7 @@ int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id, switch (event->event) { case RDMA_CM_EVENT_CONNECT_REQUEST: - ret = trans->cm_handle_connect(cm_id, event); + ret = trans->cm_handle_connect(cm_id, event, isv6); break; case RDMA_CM_EVENT_ADDR_RESOLVED: @@ -90,7 +91,7 @@ int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id, ibic = conn->c_transport_data; if (ibic && ibic->i_cm_id == cm_id) - ret = trans->cm_initiate_connect(cm_id); + ret = trans->cm_initiate_connect(cm_id, isv6); else rds_conn_drop(conn); } @@ -116,14 +117,14 @@ int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id, case RDMA_CM_EVENT_DISCONNECTED: rdsdebug("DISCONNECT event - dropping connection " - "%pI4->%pI4\n", &conn->c_laddr, + "%pI6c->%pI6c\n", &conn->c_laddr, &conn->c_faddr); rds_conn_drop(conn); break; case RDMA_CM_EVENT_TIMEWAIT_EXIT: if (conn) { - pr_info("RDS: RDMA_CM_EVENT_TIMEWAIT_EXIT event: dropping connection %pI4->%pI4\n", + pr_info("RDS: RDMA_CM_EVENT_TIMEWAIT_EXIT event: dropping connection %pI6c->%pI6c\n", &conn->c_laddr, &conn->c_faddr); rds_conn_drop(conn); } @@ -146,13 +147,20 @@ int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id, return ret; } -static int rds_rdma_listen_init(void) +int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id, + struct rdma_cm_event *event) +{ + return rds_rdma_cm_event_handler_cmn(cm_id, event, false); +} + +static int rds_rdma_listen_init_common(rdma_cm_event_handler handler, + struct sockaddr *sa, + struct rdma_cm_id **ret_cm_id) { - struct sockaddr_in sin; struct rdma_cm_id *cm_id; int ret; - cm_id = rdma_create_id(&init_net, rds_rdma_cm_event_handler, NULL, + cm_id = rdma_create_id(&init_net, handler, NULL, RDMA_PS_TCP, IB_QPT_RC); if (IS_ERR(cm_id)) { ret = PTR_ERR(cm_id); @@ -161,15 +169,11 @@ static int rds_rdma_listen_init(void) return ret; } - sin.sin_family = AF_INET; - sin.sin_addr.s_addr = (__force u32)htonl(INADDR_ANY); - sin.sin_port = (__force u16)htons(RDS_PORT); - /* * XXX I bet this binds the cm_id to a device. If we want to support * fail-over we'll have to take this into consideration. */ - ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin); + ret = rdma_bind_addr(cm_id, sa); if (ret) { printk(KERN_ERR "RDS/RDMA: failed to setup listener, " "rdma_bind_addr() returned %d\n", ret); @@ -185,7 +189,7 @@ static int rds_rdma_listen_init(void) rdsdebug("cm %p listening on port %u\n", cm_id, RDS_PORT); - rds_rdma_listen_id = cm_id; + *ret_cm_id = cm_id; cm_id = NULL; out: if (cm_id) @@ -193,6 +197,26 @@ static int rds_rdma_listen_init(void) return ret; } +/* Initialize the RDS RDMA listeners. We create two listeners for + * compatibility reason. The one on RDS_PORT is used for IPv4 + * requests only. The one on RDS_CM_PORT is used for IPv6 requests + * only. So only IPv6 enabled RDS module will communicate using this + * port. + */ +static int rds_rdma_listen_init(void) +{ + int ret; + struct sockaddr_in sin; + + sin.sin_family = PF_INET; + sin.sin_addr.s_addr = htonl(INADDR_ANY); + sin.sin_port = htons(RDS_PORT); + ret = rds_rdma_listen_init_common(rds_rdma_cm_event_handler, + (struct sockaddr *)&sin, + &rds_rdma_listen_id); + return ret; +} + static void rds_rdma_listen_stop(void) { if (rds_rdma_listen_id) { diff --git a/net/rds/rds.h b/net/rds/rds.h index f2272fb8cd45..1bff26988a5e 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -10,6 +10,7 @@ #include #include #include +#include #include "info.h" @@ -30,6 +31,7 @@ * userspace from listening. */ #define RDS_PORT 18634 +#define RDS_CM_PORT 16385 #ifdef ATOMIC64_INIT #define KERNEL_HAS_ATOMIC64 @@ -61,7 +63,7 @@ void rdsdebug(char *fmt, ...) struct rds_cong_map { struct rb_node m_rb_node; - __be32 m_addr; + struct in6_addr m_addr; wait_queue_head_t m_waitq; struct list_head m_conn_list; unsigned long m_page_addrs[RDS_CONG_MAP_PAGES]; @@ -136,11 +138,13 @@ struct rds_conn_path { /* One rds_connection per RDS address pair */ struct rds_connection { struct hlist_node c_hash_node; - __be32 c_laddr; - __be32 c_faddr; + struct in6_addr c_laddr; + struct in6_addr c_faddr; + int c_dev_if; /* c_laddrs's interface index */ unsigned int c_loopback:1, + c_isv6:1, c_ping_triggered:1, - c_pad_to_32:30; + c_pad_to_32:29; int c_npaths; struct rds_connection *c_passive; struct rds_transport *c_trans; @@ -269,7 +273,7 @@ struct rds_incoming { struct rds_conn_path *i_conn_path; struct rds_header i_hdr; unsigned long i_rx_jiffies; - __be32 i_saddr; + struct in6_addr i_saddr; rds_rdma_cookie_t i_rdma_cookie; struct timeval i_rx_tstamp; @@ -386,7 +390,7 @@ struct rds_message { struct list_head m_conn_item; struct rds_incoming m_inc; u64 m_ack_seq; - __be32 m_daddr; + struct in6_addr m_daddr; unsigned long m_flags; /* Never access m_rs without holding m_rs_lock. @@ -519,7 +523,8 @@ struct rds_transport { t_mp_capable:1; unsigned int t_type; - int (*laddr_check)(struct net *net, __be32 addr); + int (*laddr_check)(struct net *net, const struct in6_addr *addr, + __u32 scope_id); int (*conn_alloc)(struct rds_connection *conn, gfp_t gfp); void (*conn_free)(void *data); int (*conn_path_connect)(struct rds_conn_path *cp); @@ -535,8 +540,8 @@ struct rds_transport { void (*inc_free)(struct rds_incoming *inc); int (*cm_handle_connect)(struct rdma_cm_id *cm_id, - struct rdma_cm_event *event); - int (*cm_initiate_connect)(struct rdma_cm_id *cm_id); + struct rdma_cm_event *event, bool isv6); + int (*cm_initiate_connect)(struct rdma_cm_id *cm_id, bool isv6); void (*cm_connect_complete)(struct rds_connection *conn, struct rdma_cm_event *event); @@ -551,6 +556,12 @@ struct rds_transport { bool (*t_unloading)(struct rds_connection *conn); }; +/* Bind hash table key length. It is the sum of the size of a struct + * in6_addr, a scope_id and a port. + */ +#define RDS_BOUND_KEY_LEN \ + (sizeof(struct in6_addr) + sizeof(__u32) + sizeof(__be16)) + struct rds_sock { struct sock rs_sk; @@ -562,10 +573,14 @@ struct rds_sock { * support. */ struct rhash_head rs_bound_node; - u64 rs_bound_key; - __be32 rs_bound_addr; - __be32 rs_conn_addr; - __be16 rs_bound_port; + u8 rs_bound_key[RDS_BOUND_KEY_LEN]; + struct sockaddr_in6 rs_bound_sin6; +#define rs_bound_addr rs_bound_sin6.sin6_addr +#define rs_bound_addr_v4 rs_bound_sin6.sin6_addr.s6_addr32[3] +#define rs_bound_port rs_bound_sin6.sin6_port +#define rs_bound_scope_id rs_bound_sin6.sin6_scope_id + struct in6_addr rs_conn_addr; +#define rs_conn_addr_v4 rs_conn_addr.s6_addr32[3] __be16 rs_conn_port; struct rds_transport *rs_transport; @@ -701,7 +716,8 @@ extern wait_queue_head_t rds_poll_waitq; /* bind.c */ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); void rds_remove_bound(struct rds_sock *rs); -struct rds_sock *rds_find_bound(__be32 addr, __be16 port); +struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port, + __u32 scope_id); int rds_bind_lock_init(void); void rds_bind_lock_destroy(void); @@ -725,11 +741,15 @@ extern u32 rds_gen_num; int rds_conn_init(void); void rds_conn_exit(void); 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); 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); void rds_conn_shutdown(struct rds_conn_path *cpath); void rds_conn_destroy(struct rds_connection *conn); void rds_conn_drop(struct rds_connection *conn); @@ -840,11 +860,12 @@ void rds_page_exit(void); /* recv.c */ void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn, - __be32 saddr); + struct in6_addr *saddr); void rds_inc_path_init(struct rds_incoming *inc, struct rds_conn_path *conn, - __be32 saddr); + struct in6_addr *saddr); void rds_inc_put(struct rds_incoming *inc); -void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr, +void rds_recv_incoming(struct rds_connection *conn, struct in6_addr *saddr, + struct in6_addr *daddr, struct rds_incoming *inc, gfp_t gfp); int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int msg_flags); @@ -859,7 +880,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len); void rds_send_path_reset(struct rds_conn_path *conn); int rds_send_xmit(struct rds_conn_path *cp); struct sockaddr_in; -void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest); +void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in6 *dest); typedef int (*is_acked_func)(struct rds_message *rm, uint64_t ack); void rds_send_drop_acked(struct rds_connection *conn, u64 ack, is_acked_func is_acked); @@ -946,11 +967,14 @@ void rds_send_worker(struct work_struct *); void rds_recv_worker(struct work_struct *); void rds_connect_path_complete(struct rds_conn_path *conn, int curr); void rds_connect_complete(struct rds_connection *conn); +int rds_addr_cmp(const struct in6_addr *a1, const struct in6_addr *a2); /* transport.c */ void rds_trans_register(struct rds_transport *trans); void rds_trans_unregister(struct rds_transport *trans); -struct rds_transport *rds_trans_get_preferred(struct net *net, __be32 addr); +struct rds_transport *rds_trans_get_preferred(struct net *net, + const struct in6_addr *addr, + __u32 scope_id); void rds_trans_put(struct rds_transport *trans); unsigned int rds_trans_stats_info_copy(struct rds_info_iterator *iter, unsigned int avail); diff --git a/net/rds/recv.c b/net/rds/recv.c index 192ac6f78ded..4217961fd130 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2006 Oracle. All rights reserved. + * Copyright (c) 2006, 2018 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 @@ -41,14 +41,14 @@ #include "rds.h" void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn, - __be32 saddr) + struct in6_addr *saddr) { int i; refcount_set(&inc->i_refcount, 1); INIT_LIST_HEAD(&inc->i_item); inc->i_conn = conn; - inc->i_saddr = saddr; + inc->i_saddr = *saddr; inc->i_rdma_cookie = 0; inc->i_rx_tstamp.tv_sec = 0; inc->i_rx_tstamp.tv_usec = 0; @@ -59,13 +59,13 @@ void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn, EXPORT_SYMBOL_GPL(rds_inc_init); void rds_inc_path_init(struct rds_incoming *inc, struct rds_conn_path *cp, - __be32 saddr) + struct in6_addr *saddr) { refcount_set(&inc->i_refcount, 1); INIT_LIST_HEAD(&inc->i_item); inc->i_conn = cp->cp_conn; inc->i_conn_path = cp; - inc->i_saddr = saddr; + inc->i_saddr = *saddr; inc->i_rdma_cookie = 0; inc->i_rx_tstamp.tv_sec = 0; inc->i_rx_tstamp.tv_usec = 0; @@ -110,7 +110,7 @@ static void rds_recv_rcvbuf_delta(struct rds_sock *rs, struct sock *sk, now_congested = rs->rs_rcv_bytes > rds_sk_rcvbuf(rs); - rdsdebug("rs %p (%pI4:%u) recv bytes %d buf %d " + rdsdebug("rs %p (%pI6c:%u) recv bytes %d buf %d " "now_cong %d delta %d\n", rs, &rs->rs_bound_addr, ntohs(rs->rs_bound_port), rs->rs_rcv_bytes, @@ -260,7 +260,7 @@ static void rds_start_mprds(struct rds_connection *conn) struct rds_conn_path *cp; if (conn->c_npaths > 1 && - IS_CANONICAL(conn->c_laddr, conn->c_faddr)) { + rds_addr_cmp(&conn->c_laddr, &conn->c_faddr) < 0) { for (i = 0; i < conn->c_npaths; i++) { cp = &conn->c_path[i]; rds_conn_path_connect_if_down(cp); @@ -284,7 +284,8 @@ static void rds_start_mprds(struct rds_connection *conn) * conn. This lets loopback, who only has one conn for both directions, * tell us which roles the addrs in the conn are playing for this message. */ -void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr, +void rds_recv_incoming(struct rds_connection *conn, struct in6_addr *saddr, + struct in6_addr *daddr, struct rds_incoming *inc, gfp_t gfp) { struct rds_sock *rs = NULL; @@ -339,7 +340,8 @@ void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr, if (rds_sysctl_ping_enable && inc->i_hdr.h_dport == 0) { if (inc->i_hdr.h_sport == 0) { - rdsdebug("ignore ping with 0 sport from 0x%x\n", saddr); + rdsdebug("ignore ping with 0 sport from %pI6c\n", + saddr); goto out; } rds_stats_inc(s_recv_ping); @@ -362,7 +364,7 @@ void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr, goto out; } - rs = rds_find_bound(daddr, inc->i_hdr.h_dport); + rs = rds_find_bound(daddr, inc->i_hdr.h_dport, conn->c_dev_if); if (!rs) { rds_stats_inc(s_recv_drop_no_sock); goto out; @@ -625,6 +627,7 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, struct rds_sock *rs = rds_sk_to_rs(sk); long timeo; int ret = 0, nonblock = msg_flags & MSG_DONTWAIT; + DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct rds_incoming *inc = NULL; @@ -673,7 +676,7 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, break; } - rdsdebug("copying inc %p from %pI4:%u to user\n", inc, + rdsdebug("copying inc %p from %pI6c:%u to user\n", inc, &inc->i_conn->c_faddr, ntohs(inc->i_hdr.h_sport)); ret = inc->i_conn->c_trans->inc_copy_to_user(inc, &msg->msg_iter); @@ -707,12 +710,26 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, rds_stats_inc(s_recv_delivered); - if (sin) { - sin->sin_family = AF_INET; - sin->sin_port = inc->i_hdr.h_sport; - sin->sin_addr.s_addr = inc->i_saddr; - memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); - msg->msg_namelen = sizeof(*sin); + if (msg->msg_name) { + if (ipv6_addr_v4mapped(&inc->i_saddr)) { + sin = (struct sockaddr_in *)msg->msg_name; + + sin->sin_family = AF_INET; + sin->sin_port = inc->i_hdr.h_sport; + sin->sin_addr.s_addr = + inc->i_saddr.s6_addr32[3]; + memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); + msg->msg_namelen = sizeof(*sin); + } else { + sin6 = (struct sockaddr_in6 *)msg->msg_name; + + sin6->sin6_family = AF_INET6; + sin6->sin6_port = inc->i_hdr.h_sport; + sin6->sin6_addr = inc->i_saddr; + sin6->sin6_flowinfo = 0; + sin6->sin6_scope_id = rs->rs_bound_scope_id; + msg->msg_namelen = sizeof(*sin6); + } } break; } diff --git a/net/rds/send.c b/net/rds/send.c index 94c7f74909be..6ed2e925c36a 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -709,7 +709,7 @@ void rds_send_drop_acked(struct rds_connection *conn, u64 ack, } EXPORT_SYMBOL_GPL(rds_send_drop_acked); -void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest) +void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in6 *dest) { struct rds_message *rm, *tmp; struct rds_connection *conn; @@ -721,8 +721,9 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest) spin_lock_irqsave(&rs->rs_lock, flags); list_for_each_entry_safe(rm, tmp, &rs->rs_send_queue, m_sock_item) { - if (dest && (dest->sin_addr.s_addr != rm->m_daddr || - dest->sin_port != rm->m_inc.i_hdr.h_dport)) + if (dest && + (!ipv6_addr_equal(&dest->sin6_addr, &rm->m_daddr) || + dest->sin6_port != rm->m_inc.i_hdr.h_dport)) continue; list_move(&rm->m_sock_item, &list); @@ -1059,8 +1060,8 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) { struct sock *sk = sock->sk; struct rds_sock *rs = rds_sk_to_rs(sk); + DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); - __be32 daddr; __be16 dport; struct rds_message *rm = NULL; struct rds_connection *conn; @@ -1069,10 +1070,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) int nonblock = msg->msg_flags & MSG_DONTWAIT; long timeo = sock_sndtimeo(sk, nonblock); struct rds_conn_path *cpath; + struct in6_addr daddr; + __u32 scope_id = 0; size_t total_payload_len = payload_len, rdma_payload_len = 0; bool zcopy = ((msg->msg_flags & MSG_ZEROCOPY) && sock_flag(rds_rs_to_sk(rs), SOCK_ZEROCOPY)); int num_sgs = ceil(payload_len, PAGE_SIZE); + int namelen; /* Mirror Linux UDP mirror of BSD error message compatibility */ /* XXX: Perhaps MSG_MORE someday */ @@ -1081,27 +1085,59 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) goto out; } - if (msg->msg_namelen) { - /* XXX fail non-unicast destination IPs? */ - if (msg->msg_namelen < sizeof(*usin) || usin->sin_family != AF_INET) { + namelen = msg->msg_namelen; + if (namelen != 0) { + if (namelen < sizeof(*usin)) { + ret = -EINVAL; + goto out; + } + switch (namelen) { + case sizeof(*usin): + if (usin->sin_family != AF_INET || + usin->sin_addr.s_addr == htonl(INADDR_ANY) || + usin->sin_addr.s_addr == htonl(INADDR_BROADCAST) || + IN_MULTICAST(ntohl(usin->sin_addr.s_addr))) { + ret = -EINVAL; + goto out; + } + ipv6_addr_set_v4mapped(usin->sin_addr.s_addr, &daddr); + dport = usin->sin_port; + break; + + case sizeof(*sin6): { + ret = -EPROTONOSUPPORT; + goto out; + } + + default: ret = -EINVAL; goto out; } - daddr = usin->sin_addr.s_addr; - dport = usin->sin_port; } else { /* We only care about consistency with ->connect() */ lock_sock(sk); daddr = rs->rs_conn_addr; dport = rs->rs_conn_port; + scope_id = rs->rs_bound_scope_id; release_sock(sk); } lock_sock(sk); - if (daddr == 0 || rs->rs_bound_addr == 0) { + if (ipv6_addr_any(&rs->rs_bound_addr) || ipv6_addr_any(&daddr)) { release_sock(sk); - ret = -ENOTCONN; /* XXX not a great errno */ + ret = -ENOTCONN; goto out; + } else if (namelen != 0) { + /* Cannot send to an IPv4 address using an IPv6 source + * address and cannot send to an IPv6 address using an + * IPv4 source address. + */ + if (ipv6_addr_v4mapped(&daddr) ^ + ipv6_addr_v4mapped(&rs->rs_bound_addr)) { + release_sock(sk); + ret = -EOPNOTSUPP; + goto out; + } } release_sock(sk); @@ -1155,13 +1191,14 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) /* rds_conn_create has a spinlock that runs with IRQ off. * Caching the conn in the socket helps a lot. */ - if (rs->rs_conn && rs->rs_conn->c_faddr == daddr) + if (rs->rs_conn && ipv6_addr_equal(&rs->rs_conn->c_faddr, &daddr)) conn = rs->rs_conn; else { conn = rds_conn_create_outgoing(sock_net(sock->sk), - rs->rs_bound_addr, daddr, - rs->rs_transport, - sock->sk->sk_allocation); + &rs->rs_bound_addr, &daddr, + rs->rs_transport, + sock->sk->sk_allocation, + scope_id); if (IS_ERR(conn)) { ret = PTR_ERR(conn); goto out; diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 351a28474667..dadb33790333 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.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 @@ -37,6 +37,8 @@ #include #include #include +#include +#include #include "rds.h" #include "tcp.h" @@ -262,9 +264,33 @@ static void rds_tcp_tc_info(struct socket *rds_sock, unsigned int len, spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags); } -static int rds_tcp_laddr_check(struct net *net, __be32 addr) +static int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr, + __u32 scope_id) { - if (inet_addr_type(net, addr) == RTN_LOCAL) + struct net_device *dev = NULL; + int ret; + + if (ipv6_addr_v4mapped(addr)) { + if (inet_addr_type(net, addr->s6_addr32[3]) == RTN_LOCAL) + return 0; + return -EADDRNOTAVAIL; + } + + /* If the scope_id is specified, check only those addresses + * hosted on the specified interface. + */ + if (scope_id != 0) { + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, scope_id); + /* scope_id is not valid... */ + if (!dev) { + rcu_read_unlock(); + return -EADDRNOTAVAIL; + } + rcu_read_unlock(); + } + ret = ipv6_chk_addr(net, addr, dev, 0); + if (ret) return 0; return -EADDRNOTAVAIL; } diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c index d999e7075645..231ae927858e 100644 --- a/net/rds/tcp_connect.c +++ b/net/rds/tcp_connect.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 @@ -66,7 +66,8 @@ void rds_tcp_state_change(struct sock *sk) * RDS connection as RDS_CONN_UP until the reconnect, * to avoid RDS datagram loss. */ - if (!IS_CANONICAL(cp->cp_conn->c_laddr, cp->cp_conn->c_faddr) && + if (rds_addr_cmp(&cp->cp_conn->c_laddr, + &cp->cp_conn->c_faddr) >= 0 && rds_conn_path_transition(cp, RDS_CONN_CONNECTING, RDS_CONN_ERROR)) { rds_conn_path_drop(cp, false); @@ -88,7 +89,9 @@ void rds_tcp_state_change(struct sock *sk) int rds_tcp_conn_path_connect(struct rds_conn_path *cp) { struct socket *sock = NULL; - struct sockaddr_in src, dest; + struct sockaddr_in sin; + struct sockaddr *addr; + int addrlen; int ret; struct rds_connection *conn = cp->cp_conn; struct rds_tcp_connection *tc = cp->cp_transport_data; @@ -112,30 +115,33 @@ int rds_tcp_conn_path_connect(struct rds_conn_path *cp) rds_tcp_tune(sock); - src.sin_family = AF_INET; - src.sin_addr.s_addr = (__force u32)conn->c_laddr; - src.sin_port = (__force u16)htons(0); + sin.sin_family = AF_INET; + sin.sin_addr.s_addr = conn->c_laddr.s6_addr32[3]; + sin.sin_port = 0; + addr = (struct sockaddr *)&sin; + addrlen = sizeof(sin); - ret = sock->ops->bind(sock, (struct sockaddr *)&src, sizeof(src)); + ret = sock->ops->bind(sock, addr, addrlen); if (ret) { - rdsdebug("bind failed with %d at address %pI4\n", + rdsdebug("bind failed with %d at address %pI6c\n", ret, &conn->c_laddr); goto out; } - dest.sin_family = AF_INET; - dest.sin_addr.s_addr = (__force u32)conn->c_faddr; - dest.sin_port = (__force u16)htons(RDS_TCP_PORT); + sin.sin_family = AF_INET; + sin.sin_addr.s_addr = conn->c_faddr.s6_addr32[3]; + sin.sin_port = htons(RDS_TCP_PORT); + addr = (struct sockaddr *)&sin; + addrlen = sizeof(sin); /* * once we call connect() we can start getting callbacks and they * own the socket */ rds_tcp_set_callbacks(sock, cp); - ret = sock->ops->connect(sock, (struct sockaddr *)&dest, sizeof(dest), - O_NONBLOCK); + ret = sock->ops->connect(sock, addr, addrlen, O_NONBLOCK); - rdsdebug("connect to address %pI4 returned %d\n", &conn->c_faddr, ret); + rdsdebug("connect to address %pI6c returned %d\n", &conn->c_faddr, ret); if (ret == -EINPROGRESS) ret = 0; if (ret == 0) { diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 22571189f21e..4fdf5b3a47df 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2006, 2018 Oracle. All rights reserved. + * Copyright (c) 2006, 2018 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 @@ -83,13 +83,12 @@ static struct rds_tcp_connection *rds_tcp_accept_one_path(struct rds_connection *conn) { int i; - bool peer_is_smaller = IS_CANONICAL(conn->c_faddr, conn->c_laddr); int npaths = max_t(int, 1, conn->c_npaths); /* for mprds, all paths MUST be initiated by the peer * with the smaller address. */ - if (!peer_is_smaller) { + if (rds_addr_cmp(&conn->c_faddr, &conn->c_laddr) >= 0) { /* Make sure we initiate at least one path if this * has not already been done; rds_start_mprds() will * take care of additional paths, if necessary. @@ -164,13 +163,16 @@ int rds_tcp_accept_one(struct socket *sock) inet = inet_sk(new_sock->sk); - rdsdebug("accepted tcp %pI4:%u -> %pI4:%u\n", - &inet->inet_saddr, ntohs(inet->inet_sport), - &inet->inet_daddr, ntohs(inet->inet_dport)); + rdsdebug("accepted tcp %pI6c:%u -> %pI6c:%u\n", + &new_sock->sk->sk_v6_rcv_saddr, ntohs(inet->inet_sport), + &new_sock->sk->sk_v6_daddr, ntohs(inet->inet_dport)); conn = rds_conn_create(sock_net(sock->sk), - inet->inet_saddr, inet->inet_daddr, - &rds_tcp_transport, GFP_KERNEL); + &new_sock->sk->sk_v6_rcv_saddr, + &new_sock->sk->sk_v6_daddr, + &rds_tcp_transport, GFP_KERNEL, + new_sock->sk->sk_bound_dev_if); + if (IS_ERR(conn)) { ret = PTR_ERR(conn); goto out; diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c index b9fbd2ee74ef..42c5ff1eda95 100644 --- a/net/rds/tcp_recv.c +++ b/net/rds/tcp_recv.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 @@ -179,7 +179,7 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb, tc->t_tinc = tinc; rdsdebug("alloced tinc %p\n", tinc); rds_inc_path_init(&tinc->ti_inc, cp, - cp->cp_conn->c_faddr); + &cp->cp_conn->c_faddr); tinc->ti_inc.i_rx_lat_trace[RDS_MSG_RX_HDR] = local_clock(); @@ -239,8 +239,9 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb, if (tinc->ti_inc.i_hdr.h_flags == RDS_FLAG_CONG_BITMAP) rds_tcp_cong_recv(conn, tinc); else - rds_recv_incoming(conn, conn->c_faddr, - conn->c_laddr, &tinc->ti_inc, + rds_recv_incoming(conn, &conn->c_faddr, + &conn->c_laddr, + &tinc->ti_inc, arg->gfp); tc->t_tinc_hdr_rem = sizeof(struct rds_header); diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c index 7df869d37afd..78a2554a4497 100644 --- a/net/rds/tcp_send.c +++ b/net/rds/tcp_send.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 @@ -153,7 +153,7 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm, * an incoming RST. */ if (rds_conn_path_up(cp)) { - pr_warn("RDS/tcp: send to %pI4 on cp [%d]" + pr_warn("RDS/tcp: send to %pI6c on cp [%d]" "returned %d, " "disconnecting and reconnecting\n", &conn->c_faddr, cp->cp_index, ret); diff --git a/net/rds/threads.c b/net/rds/threads.c index c52861d77a59..e64f9e4c3cda 100644 --- a/net/rds/threads.c +++ b/net/rds/threads.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2006 Oracle. All rights reserved. + * Copyright (c) 2006, 2018 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 @@ -82,8 +82,8 @@ void rds_connect_path_complete(struct rds_conn_path *cp, int curr) return; } - rdsdebug("conn %p for %pI4 to %pI4 complete\n", - cp->cp_conn, &cp->cp_conn->c_laddr, &cp->cp_conn->c_faddr); + rdsdebug("conn %p for %pI6c to %pI6c complete\n", + cp->cp_conn, &cp->cp_conn->c_laddr, &cp->cp_conn->c_faddr); cp->cp_reconnect_jiffies = 0; set_bit(0, &cp->cp_conn->c_map_queued); @@ -125,13 +125,13 @@ void rds_queue_reconnect(struct rds_conn_path *cp) unsigned long rand; struct rds_connection *conn = cp->cp_conn; - rdsdebug("conn %p for %pI4 to %pI4 reconnect jiffies %lu\n", - conn, &conn->c_laddr, &conn->c_faddr, - cp->cp_reconnect_jiffies); + rdsdebug("conn %p for %pI6c to %pI6c reconnect jiffies %lu\n", + conn, &conn->c_laddr, &conn->c_faddr, + cp->cp_reconnect_jiffies); /* let peer with smaller addr initiate reconnect, to avoid duels */ if (conn->c_trans->t_type == RDS_TRANS_TCP && - !IS_CANONICAL(conn->c_laddr, conn->c_faddr)) + rds_addr_cmp(&conn->c_laddr, &conn->c_faddr) >= 0) return; set_bit(RDS_RECONNECT_PENDING, &cp->cp_flags); @@ -145,7 +145,7 @@ void rds_queue_reconnect(struct rds_conn_path *cp) } get_random_bytes(&rand, sizeof(rand)); - rdsdebug("%lu delay %lu ceil conn %p for %pI4 -> %pI4\n", + rdsdebug("%lu delay %lu ceil conn %p for %pI6c -> %pI6c\n", rand % cp->cp_reconnect_jiffies, cp->cp_reconnect_jiffies, conn, &conn->c_laddr, &conn->c_faddr); rcu_read_lock(); @@ -167,14 +167,14 @@ void rds_connect_worker(struct work_struct *work) int ret; if (cp->cp_index > 0 && - !IS_CANONICAL(cp->cp_conn->c_laddr, cp->cp_conn->c_faddr)) + rds_addr_cmp(&cp->cp_conn->c_laddr, &cp->cp_conn->c_faddr) >= 0) return; clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags); ret = rds_conn_path_transition(cp, RDS_CONN_DOWN, RDS_CONN_CONNECTING); if (ret) { ret = conn->c_trans->conn_path_connect(cp); - rdsdebug("conn %p for %pI4 to %pI4 dispatched, ret %d\n", - conn, &conn->c_laddr, &conn->c_faddr, ret); + rdsdebug("conn %p for %pI6c to %pI6c dispatched, ret %d\n", + conn, &conn->c_laddr, &conn->c_faddr, ret); if (ret) { if (rds_conn_path_transition(cp, @@ -259,3 +259,50 @@ int rds_threads_init(void) return 0; } + +/* Compare two IPv6 addresses. Return 0 if the two addresses are equal. + * Return 1 if the first is greater. Return -1 if the second is greater. + */ +int rds_addr_cmp(const struct in6_addr *addr1, + const struct in6_addr *addr2) +{ +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 + const __be64 *a1, *a2; + u64 x, y; + + a1 = (__be64 *)addr1; + a2 = (__be64 *)addr2; + + if (*a1 != *a2) { + if (be64_to_cpu(*a1) < be64_to_cpu(*a2)) + return -1; + else + return 1; + } else { + x = be64_to_cpu(*++a1); + y = be64_to_cpu(*++a2); + if (x < y) + return -1; + else if (x > y) + return 1; + else + return 0; + } +#else + u32 a, b; + int i; + + for (i = 0; i < 4; i++) { + if (addr1->s6_addr32[i] != addr2->s6_addr32[i]) { + a = ntohl(addr1->s6_addr32[i]); + b = ntohl(addr2->s6_addr32[i]); + if (a < b) + return -1; + else if (a > b) + return 1; + } + } + return 0; +#endif +} +EXPORT_SYMBOL_GPL(rds_addr_cmp); diff --git a/net/rds/transport.c b/net/rds/transport.c index 0b188dd0a344..c9788dbce441 100644 --- a/net/rds/transport.c +++ b/net/rds/transport.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 @@ -33,6 +33,7 @@ #include #include #include +#include #include "rds.h" #include "loop.h" @@ -75,20 +76,26 @@ void rds_trans_put(struct rds_transport *trans) module_put(trans->t_owner); } -struct rds_transport *rds_trans_get_preferred(struct net *net, __be32 addr) +struct rds_transport *rds_trans_get_preferred(struct net *net, + const struct in6_addr *addr, + __u32 scope_id) { struct rds_transport *ret = NULL; struct rds_transport *trans; unsigned int i; - if (IN_LOOPBACK(ntohl(addr))) + if (ipv6_addr_v4mapped(addr)) { + if (*(u_int8_t *)&addr->s6_addr32[3] == IN_LOOPBACKNET) + return &rds_loop_transport; + } else if (ipv6_addr_loopback(addr)) { return &rds_loop_transport; + } down_read(&rds_trans_sem); for (i = 0; i < RDS_TRANS_COUNT; i++) { trans = transports[i]; - if (trans && (trans->laddr_check(net, addr) == 0) && + if (trans && (trans->laddr_check(net, addr, scope_id) == 0) && (!trans->t_owner || try_module_get(trans->t_owner))) { ret = trans; break;