From 3058e01d31bbdbe50e02cafece2b22817a6a0eae Mon Sep 17 00:00:00 2001 From: Hoang Le Date: Mon, 10 May 2021 09:57:38 +0700 Subject: tipc: make node link identity publish thread safe The using of the node address and node link identity are not thread safe, meaning that two publications may be published the same values, as result one of them will get failure because of already existing in the name table. To avoid this we have to use the node address and node link identity values from inside the node item's write lock protection. Fixes: 50a3499ab853 ("tipc: simplify signature of tipc_namtbl_publish()") Acked-by: Jon Maloy Signed-off-by: Hoang Le Signed-off-by: David S. Miller --- net/tipc/node.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'net/tipc') diff --git a/net/tipc/node.c b/net/tipc/node.c index 8217905348f4..81af92954c6c 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -423,18 +423,18 @@ static void tipc_node_write_unlock(struct tipc_node *n) write_unlock_bh(&n->lock); if (flags & TIPC_NOTIFY_NODE_DOWN) - tipc_publ_notify(net, publ_list, n->addr, n->capabilities); + tipc_publ_notify(net, publ_list, sk.node, n->capabilities); if (flags & TIPC_NOTIFY_NODE_UP) - tipc_named_node_up(net, n->addr, n->capabilities); + tipc_named_node_up(net, sk.node, n->capabilities); if (flags & TIPC_NOTIFY_LINK_UP) { - tipc_mon_peer_up(net, n->addr, bearer_id); - tipc_nametbl_publish(net, &ua, &sk, n->link_id); + tipc_mon_peer_up(net, sk.node, bearer_id); + tipc_nametbl_publish(net, &ua, &sk, sk.ref); } if (flags & TIPC_NOTIFY_LINK_DOWN) { - tipc_mon_peer_down(net, n->addr, bearer_id); - tipc_nametbl_withdraw(net, &ua, &sk, n->link_id); + tipc_mon_peer_down(net, sk.node, bearer_id); + tipc_nametbl_withdraw(net, &ua, &sk, sk.ref); } } -- cgit v1.2.3 From 75016891357a628d2b8acc09e2b9b2576c18d318 Mon Sep 17 00:00:00 2001 From: Hoang Le Date: Fri, 14 May 2021 08:23:03 +0700 Subject: Revert "net:tipc: Fix a double free in tipc_sk_mcast_rcv" This reverts commit 6bf24dc0cc0cc43b29ba344b66d78590e687e046. Above fix is not correct and caused memory leak issue. Fixes: 6bf24dc0cc0c ("net:tipc: Fix a double free in tipc_sk_mcast_rcv") Acked-by: Jon Maloy Acked-by: Tung Nguyen Signed-off-by: Hoang Le Signed-off-by: David S. Miller --- net/tipc/socket.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'net/tipc') diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 58935cd0d068..53af72824c9c 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1262,7 +1262,10 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, spin_lock_bh(&inputq->lock); if (skb_peek(arrvq) == skb) { skb_queue_splice_tail_init(&tmpq, inputq); - __skb_dequeue(arrvq); + /* Decrease the skb's refcnt as increasing in the + * function tipc_skb_peek + */ + kfree_skb(__skb_dequeue(arrvq)); } spin_unlock_bh(&inputq->lock); __skb_queue_purge(&tmpq); -- cgit v1.2.3 From b7df21cf1b79ab7026f545e7bf837bd5750ac026 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 8 May 2021 03:57:03 +0800 Subject: tipc: skb_linearize the head skb when reassembling msgs It's not a good idea to append the frag skb to a skb's frag_list if the frag_list already has skbs from elsewhere, such as this skb was created by pskb_copy() where the frag_list was cloned (all the skbs in it were skb_get'ed) and shared by multiple skbs. However, the new appended frag skb should have been only seen by the current skb. Otherwise, it will cause use after free crashes as this appended frag skb are seen by multiple skbs but it only got skb_get called once. The same thing happens with a skb updated by pskb_may_pull() with a skb_cloned skb. Li Shuang has reported quite a few crashes caused by this when doing testing over macvlan devices: [] kernel BUG at net/core/skbuff.c:1970! [] Call Trace: [] skb_clone+0x4d/0xb0 [] macvlan_broadcast+0xd8/0x160 [macvlan] [] macvlan_process_broadcast+0x148/0x150 [macvlan] [] process_one_work+0x1a7/0x360 [] worker_thread+0x30/0x390 [] kernel BUG at mm/usercopy.c:102! [] Call Trace: [] __check_heap_object+0xd3/0x100 [] __check_object_size+0xff/0x16b [] simple_copy_to_iter+0x1c/0x30 [] __skb_datagram_iter+0x7d/0x310 [] __skb_datagram_iter+0x2a5/0x310 [] skb_copy_datagram_iter+0x3b/0x90 [] tipc_recvmsg+0x14a/0x3a0 [tipc] [] ____sys_recvmsg+0x91/0x150 [] ___sys_recvmsg+0x7b/0xc0 [] kernel BUG at mm/slub.c:305! [] Call Trace: [] [] kmem_cache_free+0x3ff/0x400 [] __netif_receive_skb_core+0x12c/0xc40 [] ? kmem_cache_alloc+0x12e/0x270 [] netif_receive_skb_internal+0x3d/0xb0 [] ? get_rx_page_info+0x8e/0xa0 [be2net] [] be_poll+0x6ef/0xd00 [be2net] [] ? irq_exit+0x4f/0x100 [] net_rx_action+0x149/0x3b0 ... This patch is to fix it by linearizing the head skb if it has frag_list set in tipc_buf_append(). Note that we choose to do this before calling skb_unshare(), as __skb_linearize() will avoid skb_copy(). Also, we can not just drop the frag_list either as the early time. Fixes: 45c8b7b175ce ("tipc: allow non-linear first fragment buffer") Reported-by: Li Shuang Signed-off-by: Xin Long Acked-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/msg.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'net/tipc') diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 3f0a25345a7c..ce6ab54822d8 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -149,18 +149,13 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) if (unlikely(head)) goto err; *buf = NULL; + if (skb_has_frag_list(frag) && __skb_linearize(frag)) + goto err; frag = skb_unshare(frag, GFP_ATOMIC); if (unlikely(!frag)) goto err; head = *headbuf = frag; TIPC_SKB_CB(head)->tail = NULL; - if (skb_is_nonlinear(head)) { - skb_walk_frags(head, tail) { - TIPC_SKB_CB(head)->tail = tail; - } - } else { - skb_frag_list_init(head); - } return 0; } -- cgit v1.2.3 From 04c26faa51d1e2fe71cf13c45791f5174c37f986 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 17 May 2021 02:28:58 +0800 Subject: tipc: wait and exit until all work queues are done On some host, a crash could be triggered simply by repeating these commands several times: # modprobe tipc # tipc bearer enable media udp name UDP1 localip 127.0.0.1 # rmmod tipc [] BUG: unable to handle kernel paging request at ffffffffc096bb00 [] Workqueue: events 0xffffffffc096bb00 [] Call Trace: [] ? process_one_work+0x1a7/0x360 [] ? worker_thread+0x30/0x390 [] ? create_worker+0x1a0/0x1a0 [] ? kthread+0x116/0x130 [] ? kthread_flush_work_fn+0x10/0x10 [] ? ret_from_fork+0x35/0x40 When removing the TIPC module, the UDP tunnel sock will be delayed to release in a work queue as sock_release() can't be done in rtnl_lock(). If the work queue is schedule to run after the TIPC module is removed, kernel will crash as the work queue function cleanup_beareri() code no longer exists when trying to invoke it. To fix it, this patch introduce a member wq_count in tipc_net to track the numbers of work queues in schedule, and wait and exit until all work queues are done in tipc_exit_net(). Fixes: d0f91938bede ("tipc: add ip/udp media type") Reported-by: Shuang Li Signed-off-by: Xin Long Acked-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/core.c | 2 ++ net/tipc/core.h | 2 ++ net/tipc/udp_media.c | 2 ++ 3 files changed, 6 insertions(+) (limited to 'net/tipc') diff --git a/net/tipc/core.c b/net/tipc/core.c index 5cc1f0307215..72f3ac73779b 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -119,6 +119,8 @@ static void __net_exit tipc_exit_net(struct net *net) #ifdef CONFIG_TIPC_CRYPTO tipc_crypto_stop(&tipc_net(net)->crypto_tx); #endif + while (atomic_read(&tn->wq_count)) + cond_resched(); } static void __net_exit tipc_pernet_pre_exit(struct net *net) diff --git a/net/tipc/core.h b/net/tipc/core.h index 03de7b213f55..5741ae488bb5 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -149,6 +149,8 @@ struct tipc_net { #endif /* Work item for net finalize */ struct tipc_net_work final_work; + /* The numbers of work queues in schedule */ + atomic_t wq_count; }; static inline struct tipc_net *tipc_net(struct net *net) diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index e556d2cdc064..c2bb818704c8 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -814,6 +814,7 @@ static void cleanup_bearer(struct work_struct *work) kfree_rcu(rcast, rcu); } + atomic_dec(&tipc_net(sock_net(ub->ubsock->sk))->wq_count); dst_cache_destroy(&ub->rcast.dst_cache); udp_tunnel_sock_release(ub->ubsock); synchronize_net(); @@ -834,6 +835,7 @@ static void tipc_udp_disable(struct tipc_bearer *b) RCU_INIT_POINTER(ub->bearer, NULL); /* sock_release need to be done outside of rtnl lock */ + atomic_inc(&tipc_net(sock_net(ub->ubsock->sk))->wq_count); INIT_WORK(&ub->work, cleanup_bearer); schedule_work(&ub->work); } -- cgit v1.2.3 From be07f056396d6bb40963c45a02951c566ddeef8e Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 18 May 2021 10:09:08 +0800 Subject: tipc: simplify the finalize work queue This patch is to use "struct work_struct" for the finalize work queue instead of "struct tipc_net_work", as it can get the "net" and "addr" from tipc_net's other members and there is no need to add extra net and addr in tipc_net by defining "struct tipc_net_work". Note that it's safe to get net from tn->bcl as bcl is always released after the finalize work queue is done. Signed-off-by: Xin Long Acked-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/core.c | 4 ++-- net/tipc/core.h | 8 +------- net/tipc/discover.c | 4 ++-- net/tipc/link.c | 5 +++++ net/tipc/link.h | 1 + net/tipc/net.c | 15 +++------------ 6 files changed, 14 insertions(+), 23 deletions(-) (limited to 'net/tipc') diff --git a/net/tipc/core.c b/net/tipc/core.c index 72f3ac73779b..3f4542e0f065 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -60,7 +60,7 @@ static int __net_init tipc_init_net(struct net *net) tn->trial_addr = 0; tn->addr_trial_end = 0; tn->capabilities = TIPC_NODE_CAPABILITIES; - INIT_WORK(&tn->final_work.work, tipc_net_finalize_work); + INIT_WORK(&tn->work, tipc_net_finalize_work); memset(tn->node_id, 0, sizeof(tn->node_id)); memset(tn->node_id_string, 0, sizeof(tn->node_id_string)); tn->mon_threshold = TIPC_DEF_MON_THRESHOLD; @@ -110,7 +110,7 @@ static void __net_exit tipc_exit_net(struct net *net) tipc_detach_loopback(net); /* Make sure the tipc_net_finalize_work() finished */ - cancel_work_sync(&tn->final_work.work); + cancel_work_sync(&tn->work); tipc_net_stop(net); tipc_bcast_stop(net); diff --git a/net/tipc/core.h b/net/tipc/core.h index 5741ae488bb5..0a3f7a70a50a 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -91,12 +91,6 @@ extern unsigned int tipc_net_id __read_mostly; extern int sysctl_tipc_rmem[3] __read_mostly; extern int sysctl_tipc_named_timeout __read_mostly; -struct tipc_net_work { - struct work_struct work; - struct net *net; - u32 addr; -}; - struct tipc_net { u8 node_id[NODE_ID_LEN]; u32 node_addr; @@ -148,7 +142,7 @@ struct tipc_net { struct tipc_crypto *crypto_tx; #endif /* Work item for net finalize */ - struct tipc_net_work final_work; + struct work_struct work; /* The numbers of work queues in schedule */ atomic_t wq_count; }; diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 5380f605b851..da69e1abf68f 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -168,7 +168,7 @@ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d, /* Apply trial address if we just left trial period */ if (!trial && !self) { - tipc_sched_net_finalize(net, tn->trial_addr); + schedule_work(&tn->work); msg_set_prevnode(buf_msg(d->skb), tn->trial_addr); msg_set_type(buf_msg(d->skb), DSC_REQ_MSG); } @@ -308,7 +308,7 @@ static void tipc_disc_timeout(struct timer_list *t) if (!time_before(jiffies, tn->addr_trial_end) && !tipc_own_addr(net)) { mod_timer(&d->timer, jiffies + TIPC_DISC_INIT); spin_unlock_bh(&d->lock); - tipc_sched_net_finalize(net, tn->trial_addr); + schedule_work(&tn->work); return; } diff --git a/net/tipc/link.c b/net/tipc/link.c index 115109259430..c44b4bfaaee6 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -372,6 +372,11 @@ char tipc_link_plane(struct tipc_link *l) return l->net_plane; } +struct net *tipc_link_net(struct tipc_link *l) +{ + return l->net; +} + void tipc_link_update_caps(struct tipc_link *l, u16 capabilities) { l->peer_caps = capabilities; diff --git a/net/tipc/link.h b/net/tipc/link.h index fc07232c9a12..a16f401fdabd 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -156,4 +156,5 @@ int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr, int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *xmitq); bool tipc_link_too_silent(struct tipc_link *l); +struct net *tipc_link_net(struct tipc_link *l); #endif diff --git a/net/tipc/net.c b/net/tipc/net.c index a130195af188..0e95572e56b4 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -41,6 +41,7 @@ #include "socket.h" #include "node.h" #include "bcast.h" +#include "link.h" #include "netlink.h" #include "monitor.h" @@ -142,19 +143,9 @@ static void tipc_net_finalize(struct net *net, u32 addr) void tipc_net_finalize_work(struct work_struct *work) { - struct tipc_net_work *fwork; + struct tipc_net *tn = container_of(work, struct tipc_net, work); - fwork = container_of(work, struct tipc_net_work, work); - tipc_net_finalize(fwork->net, fwork->addr); -} - -void tipc_sched_net_finalize(struct net *net, u32 addr) -{ - struct tipc_net *tn = tipc_net(net); - - tn->final_work.net = net; - tn->final_work.addr = addr; - schedule_work(&tn->final_work.work); + tipc_net_finalize(tipc_link_net(tn->bcl), tn->trial_addr); } void tipc_net_stop(struct net *net) -- cgit v1.2.3