From 28be7ca4fcfd69a2d52aaa331adbf9dbe91f9e6e Mon Sep 17 00:00:00 2001 From: Mark Tomlinson Date: Mon, 10 Oct 2022 15:46:13 +1300 Subject: tipc: Fix recognition of trial period The trial period exists until jiffies is after addr_trial_end. But as jiffies will eventually overflow, just using time_after will eventually give incorrect results. As the node address is set once the trial period ends, this can be used to know that we are not in the trial period. Fixes: e415577f57f4 ("tipc: correct discovery message handling during address trial period") Signed-off-by: Mark Tomlinson Signed-off-by: David S. Miller --- net/tipc/discover.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/tipc') diff --git a/net/tipc/discover.c b/net/tipc/discover.c index da69e1abf68f..e8630707901e 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -148,8 +148,8 @@ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d, { struct net *net = d->net; struct tipc_net *tn = tipc_net(net); - bool trial = time_before(jiffies, tn->addr_trial_end); u32 self = tipc_own_addr(net); + bool trial = time_before(jiffies, tn->addr_trial_end) && !self; if (mtyp == DSC_TRIAL_FAIL_MSG) { if (!trial) -- cgit From 777ecaabd614d47c482a5c9031579e66da13989a Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Wed, 12 Oct 2022 17:25:14 +0200 Subject: tipc: fix an information leak in tipc_topsrv_kern_subscr Use a 8-byte write to initialize sub.usr_handle in tipc_topsrv_kern_subscr(), otherwise four bytes remain uninitialized when issuing setsockopt(..., SOL_TIPC, ...). This resulted in an infoleak reported by KMSAN when the packet was received: ===================================================== BUG: KMSAN: kernel-infoleak in copyout+0xbc/0x100 lib/iov_iter.c:169 instrument_copy_to_user ./include/linux/instrumented.h:121 copyout+0xbc/0x100 lib/iov_iter.c:169 _copy_to_iter+0x5c0/0x20a0 lib/iov_iter.c:527 copy_to_iter ./include/linux/uio.h:176 simple_copy_to_iter+0x64/0xa0 net/core/datagram.c:513 __skb_datagram_iter+0x123/0xdc0 net/core/datagram.c:419 skb_copy_datagram_iter+0x58/0x200 net/core/datagram.c:527 skb_copy_datagram_msg ./include/linux/skbuff.h:3903 packet_recvmsg+0x521/0x1e70 net/packet/af_packet.c:3469 ____sys_recvmsg+0x2c4/0x810 net/socket.c:? ___sys_recvmsg+0x217/0x840 net/socket.c:2743 __sys_recvmsg net/socket.c:2773 __do_sys_recvmsg net/socket.c:2783 __se_sys_recvmsg net/socket.c:2780 __x64_sys_recvmsg+0x364/0x540 net/socket.c:2780 do_syscall_x64 arch/x86/entry/common.c:50 do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd arch/x86/entry/entry_64.S:120 ... Uninit was stored to memory at: tipc_sub_subscribe+0x42d/0xb50 net/tipc/subscr.c:156 tipc_conn_rcv_sub+0x246/0x620 net/tipc/topsrv.c:375 tipc_topsrv_kern_subscr+0x2e8/0x400 net/tipc/topsrv.c:579 tipc_group_create+0x4e7/0x7d0 net/tipc/group.c:190 tipc_sk_join+0x2a8/0x770 net/tipc/socket.c:3084 tipc_setsockopt+0xae5/0xe40 net/tipc/socket.c:3201 __sys_setsockopt+0x87f/0xdc0 net/socket.c:2252 __do_sys_setsockopt net/socket.c:2263 __se_sys_setsockopt net/socket.c:2260 __x64_sys_setsockopt+0xe0/0x160 net/socket.c:2260 do_syscall_x64 arch/x86/entry/common.c:50 do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd arch/x86/entry/entry_64.S:120 Local variable sub created at: tipc_topsrv_kern_subscr+0x57/0x400 net/tipc/topsrv.c:562 tipc_group_create+0x4e7/0x7d0 net/tipc/group.c:190 Bytes 84-87 of 88 are uninitialized Memory access of size 88 starts at ffff88801ed57cd0 Data copied to user address 0000000020000400 ... ===================================================== Signed-off-by: Alexander Potapenko Fixes: 026321c6d056a5 ("tipc: rename tipc_server to tipc_topsrv") Signed-off-by: David S. Miller --- net/tipc/topsrv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/tipc') diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 5522865deae9..14fd05fd6107 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -568,7 +568,7 @@ bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower, sub.seq.upper = upper; sub.timeout = TIPC_WAIT_FOREVER; sub.filter = filter; - *(u32 *)&sub.usr_handle = port; + *(u64 *)&sub.usr_handle = (u64)port; con = tipc_conn_alloc(tipc_topsrv(net)); if (IS_ERR(con)) -- cgit From 82cb4e4612c633a9ce320e1773114875604a3cce Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 18 Oct 2022 15:19:50 -0400 Subject: tipc: fix a null-ptr-deref in tipc_topsrv_accept syzbot found a crash in tipc_topsrv_accept: KASAN: null-ptr-deref in range [0x0000000000000008-0x000000000000000f] Workqueue: tipc_rcv tipc_topsrv_accept RIP: 0010:kernel_accept+0x22d/0x350 net/socket.c:3487 Call Trace: tipc_topsrv_accept+0x197/0x280 net/tipc/topsrv.c:460 process_one_work+0x991/0x1610 kernel/workqueue.c:2289 worker_thread+0x665/0x1080 kernel/workqueue.c:2436 kthread+0x2e4/0x3a0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:306 It was caused by srv->listener that might be set to null by tipc_topsrv_stop() in net .exit whereas it's still used in tipc_topsrv_accept() worker. srv->listener is protected by srv->idr_lock in tipc_topsrv_stop(), so add a check for srv->listener under srv->idr_lock in tipc_topsrv_accept() to avoid the null-ptr-deref. To ensure the lsock is not released during the tipc_topsrv_accept(), move sock_release() after tipc_topsrv_work_stop() where it's waiting until the tipc_topsrv_accept worker to be done. Note that sk_callback_lock is used to protect sk->sk_user_data instead of srv->listener, and it should check srv in tipc_topsrv_listener_data_ready() instead. This also ensures that no more tipc_topsrv_accept worker will be started after tipc_conn_close() is called in tipc_topsrv_stop() where it sets sk->sk_user_data to null. Fixes: 0ef897be12b8 ("tipc: separate topology server listener socket from subcsriber sockets") Reported-by: syzbot+c5ce866a8d30f4be0651@syzkaller.appspotmail.com Signed-off-by: Xin Long Acked-by: Jon Maloy Link: https://lore.kernel.org/r/4eee264380c409c61c6451af1059b7fb271a7e7b.1666120790.git.lucien.xin@gmail.com Signed-off-by: Jakub Kicinski --- net/tipc/topsrv.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'net/tipc') diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 14fd05fd6107..d92ec92f0b71 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -450,12 +450,19 @@ static void tipc_conn_data_ready(struct sock *sk) static void tipc_topsrv_accept(struct work_struct *work) { struct tipc_topsrv *srv = container_of(work, struct tipc_topsrv, awork); - struct socket *lsock = srv->listener; - struct socket *newsock; + struct socket *newsock, *lsock; struct tipc_conn *con; struct sock *newsk; int ret; + spin_lock_bh(&srv->idr_lock); + if (!srv->listener) { + spin_unlock_bh(&srv->idr_lock); + return; + } + lsock = srv->listener; + spin_unlock_bh(&srv->idr_lock); + while (1) { ret = kernel_accept(lsock, &newsock, O_NONBLOCK); if (ret < 0) @@ -489,7 +496,7 @@ static void tipc_topsrv_listener_data_ready(struct sock *sk) read_lock_bh(&sk->sk_callback_lock); srv = sk->sk_user_data; - if (srv->listener) + if (srv) queue_work(srv->rcv_wq, &srv->awork); read_unlock_bh(&sk->sk_callback_lock); } @@ -699,8 +706,9 @@ static void tipc_topsrv_stop(struct net *net) __module_get(lsock->sk->sk_prot_creator->owner); srv->listener = NULL; spin_unlock_bh(&srv->idr_lock); - sock_release(lsock); + tipc_topsrv_work_stop(srv); + sock_release(lsock); idr_destroy(&srv->conn_idr); kfree(srv); } -- cgit From 1c075b192fe41030457cd4a5f7dea730412bca40 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 4 Nov 2022 16:48:53 -0400 Subject: tipc: fix the msg->req tlv len check in tipc_nl_compat_name_table_dump_header This is a follow-up for commit 974cb0e3e7c9 ("tipc: fix uninit-value in tipc_nl_compat_name_table_dump") where it should have type casted sizeof(..) to int to work when TLV_GET_DATA_LEN() returns a negative value. syzbot reported a call trace because of it: BUG: KMSAN: uninit-value in ... tipc_nl_compat_name_table_dump+0x841/0xea0 net/tipc/netlink_compat.c:934 __tipc_nl_compat_dumpit+0xab2/0x1320 net/tipc/netlink_compat.c:238 tipc_nl_compat_dumpit+0x991/0xb50 net/tipc/netlink_compat.c:321 tipc_nl_compat_recv+0xb6e/0x1640 net/tipc/netlink_compat.c:1324 genl_family_rcv_msg_doit net/netlink/genetlink.c:731 [inline] genl_family_rcv_msg net/netlink/genetlink.c:775 [inline] genl_rcv_msg+0x103f/0x1260 net/netlink/genetlink.c:792 netlink_rcv_skb+0x3a5/0x6c0 net/netlink/af_netlink.c:2501 genl_rcv+0x3c/0x50 net/netlink/genetlink.c:803 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0xf3b/0x1270 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x1288/0x1440 net/netlink/af_netlink.c:1921 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] Reported-by: syzbot+e5dbaaa238680ce206ea@syzkaller.appspotmail.com Fixes: 974cb0e3e7c9 ("tipc: fix uninit-value in tipc_nl_compat_name_table_dump") Signed-off-by: Xin Long Link: https://lore.kernel.org/r/ccd6a7ea801b15aec092c3b532a883b4c5708695.1667594933.git.lucien.xin@gmail.com Signed-off-by: Jakub Kicinski --- net/tipc/netlink_compat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/tipc') diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index fc68733673ba..dfea27a906f2 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -880,7 +880,7 @@ static int tipc_nl_compat_name_table_dump_header(struct tipc_nl_compat_msg *msg) }; ntq = (struct tipc_name_table_query *)TLV_DATA(msg->req); - if (TLV_GET_DATA_LEN(msg->req) < sizeof(struct tipc_name_table_query)) + if (TLV_GET_DATA_LEN(msg->req) < (int)sizeof(struct tipc_name_table_query)) return -EINVAL; depth = ntohl(ntq->depth); -- cgit From 8032bf1233a74627ce69b803608e650f3f35971c Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Sun, 9 Oct 2022 20:44:02 -0600 Subject: treewide: use get_random_u32_below() instead of deprecated function This is a simple mechanical transformation done by: @@ expression E; @@ - prandom_u32_max + get_random_u32_below (E) Reviewed-by: Kees Cook Reviewed-by: Greg Kroah-Hartman Acked-by: Darrick J. Wong # for xfs Reviewed-by: SeongJae Park # for damon Reviewed-by: Jason Gunthorpe # for infiniband Reviewed-by: Russell King (Oracle) # for arm Acked-by: Ulf Hansson # for mmc Signed-off-by: Jason A. Donenfeld --- net/tipc/socket.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/tipc') diff --git a/net/tipc/socket.c b/net/tipc/socket.c index e902b01ea3cb..b35c8701876a 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -3010,7 +3010,7 @@ static int tipc_sk_insert(struct tipc_sock *tsk) struct net *net = sock_net(sk); struct tipc_net *tn = net_generic(net, tipc_net_id); u32 remaining = (TIPC_MAX_PORT - TIPC_MIN_PORT) + 1; - u32 portid = prandom_u32_max(remaining) + TIPC_MIN_PORT; + u32 portid = get_random_u32_below(remaining) + TIPC_MIN_PORT; while (remaining--) { portid++; -- cgit From 0e5d56c64afcd6fd2d132ea972605b66f8a7d3c4 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 18 Nov 2022 16:45:00 -0500 Subject: tipc: set con sock in tipc_conn_alloc A crash was reported by Wei Chen: BUG: kernel NULL pointer dereference, address: 0000000000000018 RIP: 0010:tipc_conn_close+0x12/0x100 Call Trace: tipc_topsrv_exit_net+0x139/0x320 ops_exit_list.isra.9+0x49/0x80 cleanup_net+0x31a/0x540 process_one_work+0x3fa/0x9f0 worker_thread+0x42/0x5c0 It was caused by !con->sock in tipc_conn_close(). In tipc_topsrv_accept(), con is allocated in conn_idr then its sock is set: con = tipc_conn_alloc(); ... <----[1] con->sock = newsock; If tipc_conn_close() is called in anytime of [1], the null-pointer-def is triggered by con->sock->sk due to con->sock is not yet set. This patch fixes it by moving the con->sock setting to tipc_conn_alloc() under s->idr_lock. So that con->sock can never be NULL when getting the con from s->conn_idr. It will be also safer to move con->server and flag CF_CONNECTED setting under s->idr_lock, as they should all be set before tipc_conn_alloc() is called. Fixes: c5fa7b3cf3cb ("tipc: introduce new TIPC server infrastructure") Reported-by: Wei Chen Signed-off-by: Xin Long Acked-by: Jon Maloy Signed-off-by: Jakub Kicinski --- net/tipc/topsrv.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'net/tipc') diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index d92ec92f0b71..b0f9aa521670 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -176,7 +176,7 @@ static void tipc_conn_close(struct tipc_conn *con) conn_put(con); } -static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s) +static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s, struct socket *sock) { struct tipc_conn *con; int ret; @@ -202,10 +202,11 @@ static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s) } con->conid = ret; s->idr_in_use++; - spin_unlock_bh(&s->idr_lock); set_bit(CF_CONNECTED, &con->flags); con->server = s; + con->sock = sock; + spin_unlock_bh(&s->idr_lock); return con; } @@ -467,7 +468,7 @@ static void tipc_topsrv_accept(struct work_struct *work) ret = kernel_accept(lsock, &newsock, O_NONBLOCK); if (ret < 0) return; - con = tipc_conn_alloc(srv); + con = tipc_conn_alloc(srv, newsock); if (IS_ERR(con)) { ret = PTR_ERR(con); sock_release(newsock); @@ -479,7 +480,6 @@ static void tipc_topsrv_accept(struct work_struct *work) newsk->sk_data_ready = tipc_conn_data_ready; newsk->sk_write_space = tipc_conn_write_space; newsk->sk_user_data = con; - con->sock = newsock; write_unlock_bh(&newsk->sk_callback_lock); /* Wake up receive process in case of 'SYN+' message */ @@ -577,12 +577,11 @@ bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower, sub.filter = filter; *(u64 *)&sub.usr_handle = (u64)port; - con = tipc_conn_alloc(tipc_topsrv(net)); + con = tipc_conn_alloc(tipc_topsrv(net), NULL); if (IS_ERR(con)) return false; *conid = con->conid; - con->sock = NULL; rc = tipc_conn_rcv_sub(tipc_topsrv(net), con, &sub); if (rc >= 0) return true; -- cgit From a7b42969d63f47320853a802efd879fbdc4e010e Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 18 Nov 2022 16:45:01 -0500 Subject: tipc: add an extra conn_get in tipc_conn_alloc One extra conn_get() is needed in tipc_conn_alloc(), as after tipc_conn_alloc() is called, tipc_conn_close() may free this con before deferencing it in tipc_topsrv_accept(): tipc_conn_alloc(); newsk = newsock->sk; <---- tipc_conn_close(); write_lock_bh(&sk->sk_callback_lock); newsk->sk_data_ready = tipc_conn_data_ready; Then an uaf issue can be triggered: BUG: KASAN: use-after-free in tipc_topsrv_accept+0x1e7/0x370 [tipc] Call Trace: dump_stack_lvl+0x33/0x46 print_report+0x178/0x4b0 kasan_report+0x8c/0x100 kasan_check_range+0x179/0x1e0 tipc_topsrv_accept+0x1e7/0x370 [tipc] process_one_work+0x6a3/0x1030 worker_thread+0x8a/0xdf0 This patch fixes it by holding it in tipc_conn_alloc(), then after all accessing in tipc_topsrv_accept() releasing it. Note when does this in tipc_topsrv_kern_subscr(), as tipc_conn_rcv_sub() returns 0 or -1 only, we don't need to check for "> 0". Fixes: c5fa7b3cf3cb ("tipc: introduce new TIPC server infrastructure") Signed-off-by: Xin Long Acked-by: Jon Maloy Signed-off-by: Jakub Kicinski --- net/tipc/topsrv.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'net/tipc') diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index b0f9aa521670..e3b427a70398 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -206,6 +206,7 @@ static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s, struct socket *s set_bit(CF_CONNECTED, &con->flags); con->server = s; con->sock = sock; + conn_get(con); spin_unlock_bh(&s->idr_lock); return con; @@ -484,6 +485,7 @@ static void tipc_topsrv_accept(struct work_struct *work) /* Wake up receive process in case of 'SYN+' message */ newsk->sk_data_ready(newsk); + conn_put(con); } } @@ -583,10 +585,11 @@ bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower, *conid = con->conid; rc = tipc_conn_rcv_sub(tipc_topsrv(net), con, &sub); - if (rc >= 0) - return true; + if (rc) + conn_put(con); + conn_put(con); - return false; + return !rc; } void tipc_topsrv_kern_unsubscr(struct net *net, int conid) -- cgit From cd0f6421162201e4b22ce757a1966729323185eb Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Sat, 19 Nov 2022 15:28:32 +0800 Subject: tipc: check skb_linearize() return value in tipc_disc_rcv() If skb_linearize() fails in tipc_disc_rcv(), we need to free the skb instead of handle it. Fixes: 25b0b9c4e835 ("tipc: handle collisions of 32-bit node address hash values") Signed-off-by: YueHaibing Acked-by: Jon Maloy Link: https://lore.kernel.org/r/20221119072832.7896-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- net/tipc/discover.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'net/tipc') diff --git a/net/tipc/discover.c b/net/tipc/discover.c index e8630707901e..e8dcdf267c0c 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -211,7 +211,10 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb, u32 self; int err; - skb_linearize(skb); + if (skb_linearize(skb)) { + kfree_skb(skb); + return; + } hdr = buf_msg(skb); if (caps & TIPC_NODE_ID128) -- cgit From de4eda9de2d957ef2d6a8365a01e26a435e958cb Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 15 Sep 2022 20:25:47 -0400 Subject: use less confusing names for iov_iter direction initializers READ/WRITE proved to be actively confusing - the meanings are "data destination, as used with read(2)" and "data source, as used with write(2)", but people keep interpreting those as "we read data from it" and "we write data to it", i.e. exactly the wrong way. Call them ITER_DEST and ITER_SOURCE - at least that is harder to misinterpret... Signed-off-by: Al Viro --- net/tipc/topsrv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/tipc') diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index d92ec92f0b71..d7166d84a7b2 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -394,7 +394,7 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con) iov.iov_base = &s; iov.iov_len = sizeof(s); msg.msg_name = NULL; - iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, iov.iov_len); + iov_iter_kvec(&msg.msg_iter, ITER_DEST, &iov, 1, iov.iov_len); ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT); if (ret == -EWOULDBLOCK) return -EWOULDBLOCK; -- cgit From 3067bc61fcfe3081bf4807ce65560f499e895e77 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 25 Nov 2022 12:46:43 -0500 Subject: tipc: re-fetch skb cb after tipc_msg_validate As the call trace shows, the original skb was freed in tipc_msg_validate(), and dereferencing the old skb cb would cause an use-after-free crash. BUG: KASAN: use-after-free in tipc_crypto_rcv_complete+0x1835/0x2240 [tipc] Call Trace: tipc_crypto_rcv_complete+0x1835/0x2240 [tipc] tipc_crypto_rcv+0xd32/0x1ec0 [tipc] tipc_rcv+0x744/0x1150 [tipc] ... Allocated by task 47078: kmem_cache_alloc_node+0x158/0x4d0 __alloc_skb+0x1c1/0x270 tipc_buf_acquire+0x1e/0xe0 [tipc] tipc_msg_create+0x33/0x1c0 [tipc] tipc_link_build_proto_msg+0x38a/0x2100 [tipc] tipc_link_timeout+0x8b8/0xef0 [tipc] tipc_node_timeout+0x2a1/0x960 [tipc] call_timer_fn+0x2d/0x1c0 ... Freed by task 47078: tipc_msg_validate+0x7b/0x440 [tipc] tipc_crypto_rcv_complete+0x4b5/0x2240 [tipc] tipc_crypto_rcv+0xd32/0x1ec0 [tipc] tipc_rcv+0x744/0x1150 [tipc] This patch fixes it by re-fetching the skb cb from the new allocated skb after calling tipc_msg_validate(). Fixes: fc1b6d6de220 ("tipc: introduce TIPC encryption & authentication") Reported-by: Shuang Li Signed-off-by: Xin Long Link: https://lore.kernel.org/r/1b1cdba762915325bd8ef9a98d0276eb673df2a5.1669398403.git.lucien.xin@gmail.com Signed-off-by: Jakub Kicinski --- net/tipc/crypto.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net/tipc') diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index f09316a9035f..d67440de011e 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -1971,6 +1971,9 @@ rcv: /* Ok, everything's fine, try to synch own keys according to peers' */ tipc_crypto_key_synch(rx, *skb); + /* Re-fetch skb cb as skb might be changed in tipc_msg_validate */ + skb_cb = TIPC_SKB_CB(*skb); + /* Mark skb decrypted */ skb_cb->decrypted = 1; -- cgit From 743117a997bbd4840e827295c07e59bcd7f7caa3 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Sat, 3 Dec 2022 17:46:35 +0800 Subject: tipc: Fix potential OOB in tipc_link_proto_rcv() Fix the potential risk of OOB if skb_linearize() fails in tipc_link_proto_rcv(). Fixes: 5cbb28a4bf65 ("tipc: linearize arriving NAME_DISTR and LINK_PROTO buffers") Signed-off-by: YueHaibing Link: https://lore.kernel.org/r/20221203094635.29024-1-yuehaibing@huawei.com Signed-off-by: Paolo Abeni --- net/tipc/link.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net/tipc') diff --git a/net/tipc/link.c b/net/tipc/link.c index e260c0d557f5..b3ce24823f50 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -2224,7 +2224,9 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, if (tipc_own_addr(l->net) > msg_prevnode(hdr)) l->net_plane = msg_net_plane(hdr); - skb_linearize(skb); + if (skb_linearize(skb)) + goto exit; + hdr = buf_msg(skb); data = msg_data(hdr); -- cgit From 88956177db179e4eba7cd590971961857d1565b8 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 3 Dec 2022 18:37:21 -0500 Subject: tipc: call tipc_lxc_xmit without holding node_read_lock When sending packets between nodes in netns, it calls tipc_lxc_xmit() for peer node to receive the packets where tipc_sk_mcast_rcv()/tipc_sk_rcv() might be called, and it's pretty much like in tipc_rcv(). Currently the local 'node rw lock' is held during calling tipc_lxc_xmit() to protect the peer_net not being freed by another thread. However, when receiving these packets, tipc_node_add_conn() might be called where the peer 'node rw lock' is acquired. Then a dead lock warning is triggered by lockdep detector, although it is not a real dead lock: WARNING: possible recursive locking detected -------------------------------------------- conn_server/1086 is trying to acquire lock: ffff8880065cb020 (&n->lock#2){++--}-{2:2}, \ at: tipc_node_add_conn.cold.76+0xaa/0x211 [tipc] but task is already holding lock: ffff8880065cd020 (&n->lock#2){++--}-{2:2}, \ at: tipc_node_xmit+0x285/0xb30 [tipc] other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&n->lock#2); lock(&n->lock#2); *** DEADLOCK *** May be due to missing lock nesting notation 4 locks held by conn_server/1086: #0: ffff8880036d1e40 (sk_lock-AF_TIPC){+.+.}-{0:0}, \ at: tipc_accept+0x9c0/0x10b0 [tipc] #1: ffff8880036d5f80 (sk_lock-AF_TIPC/1){+.+.}-{0:0}, \ at: tipc_accept+0x363/0x10b0 [tipc] #2: ffff8880065cd020 (&n->lock#2){++--}-{2:2}, \ at: tipc_node_xmit+0x285/0xb30 [tipc] #3: ffff888012e13370 (slock-AF_TIPC){+...}-{2:2}, \ at: tipc_sk_rcv+0x2da/0x1b40 [tipc] Call Trace: dump_stack_lvl+0x44/0x5b __lock_acquire.cold.77+0x1f2/0x3d7 lock_acquire+0x1d2/0x610 _raw_write_lock_bh+0x38/0x80 tipc_node_add_conn.cold.76+0xaa/0x211 [tipc] tipc_sk_finish_conn+0x21e/0x640 [tipc] tipc_sk_filter_rcv+0x147b/0x3030 [tipc] tipc_sk_rcv+0xbb4/0x1b40 [tipc] tipc_lxc_xmit+0x225/0x26b [tipc] tipc_node_xmit.cold.82+0x4a/0x102 [tipc] __tipc_sendstream+0x879/0xff0 [tipc] tipc_accept+0x966/0x10b0 [tipc] do_accept+0x37d/0x590 This patch avoids this warning by not holding the 'node rw lock' before calling tipc_lxc_xmit(). As to protect the 'peer_net', rcu_read_lock() should be enough, as in cleanup_net() when freeing the netns, it calls synchronize_rcu() before the free is continued. Also since tipc_lxc_xmit() is like the RX path in tipc_rcv(), it makes sense to call it under rcu_read_lock(). Note that the right lock order must be: rcu_read_lock(); tipc_node_read_lock(n); tipc_node_read_unlock(n); tipc_lxc_xmit(); rcu_read_unlock(); instead of: tipc_node_read_lock(n); rcu_read_lock(); tipc_node_read_unlock(n); tipc_lxc_xmit(); rcu_read_unlock(); and we have to call tipc_node_read_lock/unlock() twice in tipc_node_xmit(). Fixes: f73b12812a3d ("tipc: improve throughput between nodes in netns") Reported-by: Shuang Li Signed-off-by: Xin Long Link: https://lore.kernel.org/r/5bdd1f8fee9db695cfff4528a48c9b9d0523fb00.1670110641.git.lucien.xin@gmail.com Signed-off-by: Paolo Abeni --- net/tipc/node.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'net/tipc') diff --git a/net/tipc/node.c b/net/tipc/node.c index b48d97cbbe29..49ddc484c4fe 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1689,6 +1689,7 @@ int tipc_node_xmit(struct net *net, struct sk_buff_head *list, struct tipc_node *n; struct sk_buff_head xmitq; bool node_up = false; + struct net *peer_net; int bearer_id; int rc; @@ -1705,18 +1706,23 @@ int tipc_node_xmit(struct net *net, struct sk_buff_head *list, return -EHOSTUNREACH; } + rcu_read_lock(); tipc_node_read_lock(n); node_up = node_is_up(n); - if (node_up && n->peer_net && check_net(n->peer_net)) { + peer_net = n->peer_net; + tipc_node_read_unlock(n); + if (node_up && peer_net && check_net(peer_net)) { /* xmit inner linux container */ - tipc_lxc_xmit(n->peer_net, list); + tipc_lxc_xmit(peer_net, list); if (likely(skb_queue_empty(list))) { - tipc_node_read_unlock(n); + rcu_read_unlock(); tipc_node_put(n); return 0; } } + rcu_read_unlock(); + tipc_node_read_lock(n); bearer_id = n->active_links[selector & 1]; if (unlikely(bearer_id == INVALID_BEARER_ID)) { tipc_node_read_unlock(n); -- cgit From 292a089d78d3e2f7944e60bb897c977785a321e3 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 20 Dec 2022 13:45:19 -0500 Subject: treewide: Convert del_timer*() to timer_shutdown*() Due to several bugs caused by timers being re-armed after they are shutdown and just before they are freed, a new state of timers was added called "shutdown". After a timer is set to this state, then it can no longer be re-armed. The following script was run to find all the trivial locations where del_timer() or del_timer_sync() is called in the same function that the object holding the timer is freed. It also ignores any locations where the timer->function is modified between the del_timer*() and the free(), as that is not considered a "trivial" case. This was created by using a coccinelle script and the following commands: $ cat timer.cocci @@ expression ptr, slab; identifier timer, rfield; @@ ( - del_timer(&ptr->timer); + timer_shutdown(&ptr->timer); | - del_timer_sync(&ptr->timer); + timer_shutdown_sync(&ptr->timer); ) ... when strict when != ptr->timer ( kfree_rcu(ptr, rfield); | kmem_cache_free(slab, ptr); | kfree(ptr); ) $ spatch timer.cocci . > /tmp/t.patch $ patch -p1 < /tmp/t.patch Link: https://lore.kernel.org/lkml/20221123201306.823305113@linutronix.de/ Signed-off-by: Steven Rostedt (Google) Acked-by: Pavel Machek [ LED ] Acked-by: Kalle Valo [ wireless ] Acked-by: Paolo Abeni [ networking ] Signed-off-by: Linus Torvalds --- net/tipc/discover.c | 2 +- net/tipc/monitor.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'net/tipc') diff --git a/net/tipc/discover.c b/net/tipc/discover.c index e8dcdf267c0c..685389d4b245 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -388,7 +388,7 @@ int tipc_disc_create(struct net *net, struct tipc_bearer *b, */ void tipc_disc_delete(struct tipc_discoverer *d) { - del_timer_sync(&d->timer); + timer_shutdown_sync(&d->timer); kfree_skb(d->skb); kfree(d); } diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index 9618e4429f0f..77a3d016cade 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -700,7 +700,7 @@ void tipc_mon_delete(struct net *net, int bearer_id) } mon->self = NULL; write_unlock_bh(&mon->lock); - del_timer_sync(&mon->timer); + timer_shutdown_sync(&mon->timer); kfree(self->domain); kfree(self); kfree(mon); -- cgit