From fc1b6d6de2208774efd2a20bf0daddb02d18b1e0 Mon Sep 17 00:00:00 2001 From: Tuong Lien Date: Fri, 8 Nov 2019 12:05:11 +0700 Subject: tipc: introduce TIPC encryption & authentication This commit offers an option to encrypt and authenticate all messaging, including the neighbor discovery messages. The currently most advanced algorithm supported is the AEAD AES-GCM (like IPSec or TLS). All encryption/decryption is done at the bearer layer, just before leaving or after entering TIPC. Supported features: - Encryption & authentication of all TIPC messages (header + data); - Two symmetric-key modes: Cluster and Per-node; - Automatic key switching; - Key-expired revoking (sequence number wrapped); - Lock-free encryption/decryption (RCU); - Asynchronous crypto, Intel AES-NI supported; - Multiple cipher transforms; - Logs & statistics; Two key modes: - Cluster key mode: One single key is used for both TX & RX in all nodes in the cluster. - Per-node key mode: Each nodes in the cluster has one specific TX key. For RX, a node requires its peers' TX key to be able to decrypt the messages from those peers. Key setting from user-space is performed via netlink by a user program (e.g. the iproute2 'tipc' tool). Internal key state machine: Attach Align(RX) +-+ +-+ | V | V +---------+ Attach +---------+ | IDLE |---------------->| PENDING |(user = 0) +---------+ +---------+ A A Switch| A | | | | | | Free(switch/revoked) | | (Free)| +----------------------+ | |Timeout | (TX) | | |(RX) | | | | | | v | +---------+ Switch +---------+ | PASSIVE |<----------------| ACTIVE | +---------+ (RX) +---------+ (user = 1) (user >= 1) The number of TFMs is 10 by default and can be changed via the procfs 'net/tipc/max_tfms'. At this moment, as for simplicity, this file is also used to print the crypto statistics at runtime: echo 0xfff1 > /proc/sys/net/tipc/max_tfms The patch defines a new TIPC version (v7) for the encryption message (- backward compatibility as well). The message is basically encapsulated as follows: +----------------------------------------------------------+ | TIPCv7 encryption | Original TIPCv2 | Authentication | | header | packet (encrypted) | Tag | +----------------------------------------------------------+ The throughput is about ~40% for small messages (compared with non- encryption) and ~9% for large messages. With the support from hardware crypto i.e. the Intel AES-NI CPU instructions, the throughput increases upto ~85% for small messages and ~55% for large messages. By default, the new feature is inactive (i.e. no encryption) until user sets a key for TIPC. There is however also a new option - "TIPC_CRYPTO" in the kernel configuration to enable/disable the new code when needed. MAINTAINERS | add two new files 'crypto.h' & 'crypto.c' in tipc Acked-by: Ying Xue Acked-by: Jon Maloy Signed-off-by: Tuong Lien Signed-off-by: David S. Miller --- net/tipc/bcast.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/tipc/bcast.c') diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 6ef1abdd525f..f41096a759fa 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -84,7 +84,7 @@ static struct tipc_bc_base *tipc_bc_base(struct net *net) */ int tipc_bcast_get_mtu(struct net *net) { - return tipc_link_mtu(tipc_bc_sndlink(net)) - INT_H_SIZE; + return tipc_link_mss(tipc_bc_sndlink(net)); } void tipc_bcast_disable_rcast(struct net *net) -- cgit v1.2.3 From ba5f6a8617f4cd8e77da0a190b9647065014eade Mon Sep 17 00:00:00 2001 From: Hoang Le Date: Thu, 21 Nov 2019 10:01:09 +0700 Subject: tipc: update replicast capability for broadcast send link When setting up a cluster with non-replicast/replicast capability supported. This capability will be disabled for broadcast send link in order to be backwards compatible. However, when these non-support nodes left and be removed out the cluster. We don't update this capability on broadcast send link. Then, some of features that based on this capability will also disabling as unexpected. In this commit, we make sure the broadcast send link capabilities will be re-calculated as soon as a node removed/rejoined a cluster. Acked-by: Jon Maloy Signed-off-by: Hoang Le Signed-off-by: David S. Miller --- net/tipc/bcast.c | 4 ++-- net/tipc/bcast.h | 2 +- net/tipc/link.c | 2 +- net/tipc/node.c | 8 +++++++- 4 files changed, 11 insertions(+), 5 deletions(-) (limited to 'net/tipc/bcast.c') diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index f41096a759fa..55aeba681cf4 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -87,9 +87,9 @@ int tipc_bcast_get_mtu(struct net *net) return tipc_link_mss(tipc_bc_sndlink(net)); } -void tipc_bcast_disable_rcast(struct net *net) +void tipc_bcast_toggle_rcast(struct net *net, bool supp) { - tipc_bc_base(net)->rcast_support = false; + tipc_bc_base(net)->rcast_support = supp; } static void tipc_bcbase_calc_bc_threshold(struct net *net) diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index dadad953e2be..9e847d9617d3 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -85,7 +85,7 @@ void tipc_bcast_remove_peer(struct net *net, struct tipc_link *rcv_bcl); void tipc_bcast_inc_bearer_dst_cnt(struct net *net, int bearer_id); void tipc_bcast_dec_bearer_dst_cnt(struct net *net, int bearer_id); int tipc_bcast_get_mtu(struct net *net); -void tipc_bcast_disable_rcast(struct net *net); +void tipc_bcast_toggle_rcast(struct net *net, bool supp); int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts, struct tipc_mc_method *method, struct tipc_nlist *dests, u16 *cong_link_cnt); diff --git a/net/tipc/link.c b/net/tipc/link.c index fb72031228c9..24d4d10756d3 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -550,7 +550,7 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, /* Disable replicast if even a single peer doesn't support it */ if (link_is_bc_rcvlink(l) && !(peer_caps & TIPC_BCAST_RCAST)) - tipc_bcast_disable_rcast(net); + tipc_bcast_toggle_rcast(net, false); return true; } diff --git a/net/tipc/node.c b/net/tipc/node.c index aaf595613e6e..ab04e00cb95b 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -496,6 +496,9 @@ update: tn->capabilities &= temp_node->capabilities; } + tipc_bcast_toggle_rcast(net, + (tn->capabilities & TIPC_BCAST_RCAST)); + goto exit; } n = kzalloc(sizeof(*n), GFP_ATOMIC); @@ -557,6 +560,7 @@ update: list_for_each_entry_rcu(temp_node, &tn->node_list, list) { tn->capabilities &= temp_node->capabilities; } + tipc_bcast_toggle_rcast(net, (tn->capabilities & TIPC_BCAST_RCAST)); trace_tipc_node_create(n, true, " "); exit: spin_unlock_bh(&tn->node_list_lock); @@ -740,7 +744,8 @@ static bool tipc_node_cleanup(struct tipc_node *peer) list_for_each_entry_rcu(temp_node, &tn->node_list, list) { tn->capabilities &= temp_node->capabilities; } - + tipc_bcast_toggle_rcast(peer->net, + (tn->capabilities & TIPC_BCAST_RCAST)); spin_unlock_bh(&tn->node_list_lock); return deleted; } @@ -2198,6 +2203,7 @@ int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info) list_for_each_entry_rcu(temp_node, &tn->node_list, list) { tn->capabilities &= temp_node->capabilities; } + tipc_bcast_toggle_rcast(net, (tn->capabilities & TIPC_BCAST_RCAST)); err = 0; err_out: tipc_node_put(peer); -- cgit v1.2.3 From dca4a17d24ee9d878836ce5eb8dc25be1ffa5729 Mon Sep 17 00:00:00 2001 From: Tuong Lien Date: Tue, 10 Dec 2019 15:21:03 +0700 Subject: tipc: fix potential hanging after b/rcast changing In commit c55c8edafa91 ("tipc: smooth change between replicast and broadcast"), we allow instant switching between replicast and broadcast by sending a dummy 'SYN' packet on the last used link to synchronize packets on the links. The 'SYN' message is an object of link congestion also, so if that happens, a 'SOCK_WAKEUP' will be scheduled to be sent back to the socket... However, in that commit, we simply use the same socket 'cong_link_cnt' counter for both the 'SYN' & normal payload message sending. Therefore, if both the replicast & broadcast links are congested, the counter will be not updated correctly but overwritten by the latter congestion. Later on, when the 'SOCK_WAKEUP' messages are processed, the counter is reduced one by one and eventually overflowed. Consequently, further activities on the socket will only wait for the false congestion signal to disappear but never been met. Because sending the 'SYN' message is vital for the mechanism, it should be done anyway. This commit fixes the issue by marking the message with an error code e.g. 'TIPC_ERR_NO_PORT', so its sending should not face a link congestion, there is no need to touch the socket 'cong_link_cnt' either. In addition, in the event of any error (e.g. -ENOBUFS), we will purge the entire payload message queue and make a return immediately. Fixes: c55c8edafa91 ("tipc: smooth change between replicast and broadcast") Acked-by: Jon Maloy Signed-off-by: Tuong Lien Signed-off-by: David S. Miller --- net/tipc/bcast.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) (limited to 'net/tipc/bcast.c') diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 55aeba681cf4..656ebc79c64e 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -305,17 +305,17 @@ static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts, * @skb: socket buffer to copy * @method: send method to be used * @dests: destination nodes for message. - * @cong_link_cnt: returns number of encountered congested destination links * Returns 0 if success, otherwise errno */ static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb, struct tipc_mc_method *method, - struct tipc_nlist *dests, - u16 *cong_link_cnt) + struct tipc_nlist *dests) { struct tipc_msg *hdr, *_hdr; struct sk_buff_head tmpq; struct sk_buff *_skb; + u16 cong_link_cnt; + int rc = 0; /* Is a cluster supporting with new capabilities ? */ if (!(tipc_net(net)->capabilities & TIPC_MCAST_RBCTL)) @@ -343,18 +343,19 @@ static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb, _hdr = buf_msg(_skb); msg_set_size(_hdr, MCAST_H_SIZE); msg_set_is_rcast(_hdr, !msg_is_rcast(hdr)); + msg_set_errcode(_hdr, TIPC_ERR_NO_PORT); __skb_queue_head_init(&tmpq); __skb_queue_tail(&tmpq, _skb); if (method->rcast) - tipc_bcast_xmit(net, &tmpq, cong_link_cnt); + rc = tipc_bcast_xmit(net, &tmpq, &cong_link_cnt); else - tipc_rcast_xmit(net, &tmpq, dests, cong_link_cnt); + rc = tipc_rcast_xmit(net, &tmpq, dests, &cong_link_cnt); /* This queue should normally be empty by now */ __skb_queue_purge(&tmpq); - return 0; + return rc; } /* tipc_mcast_xmit - deliver message to indicated destination nodes @@ -396,9 +397,14 @@ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts, msg_set_is_rcast(hdr, method->rcast); /* Switch method ? */ - if (rcast != method->rcast) - tipc_mcast_send_sync(net, skb, method, - dests, cong_link_cnt); + if (rcast != method->rcast) { + rc = tipc_mcast_send_sync(net, skb, method, dests); + if (unlikely(rc)) { + pr_err("Unable to send SYN: method %d, rc %d\n", + rcast, rc); + goto exit; + } + } if (method->rcast) rc = tipc_rcast_xmit(net, pkts, dests, cong_link_cnt); -- cgit v1.2.3