From 89fa538fbc58e89a23f85f9f2d0f1cc934208db8 Mon Sep 17 00:00:00 2001 From: Sicong Huang Date: Tue, 16 Apr 2024 16:03:13 +0800 Subject: [PATCH 1/6] greybus: Fix use-after-free bug in gb_interface_release due to race condition. stable inclusion from stable-5.10.221 commit 2b6bb0b4abfd79b8698ee161bb73c0936a2aaf83 category: bugfix issue: #IAEK1E CVE: CVE-2024-39495 Signed-off-by: wanxiaoqing --------------------------------------- commit 5c9c5d7f26acc2c669c1dcf57d1bb43ee99220ce upstream. In gb_interface_create, &intf->mode_switch_completion is bound with gb_interface_mode_switch_work. Then it will be started by gb_interface_request_mode_switch. Here is the relevant code. if (!queue_work(system_long_wq, &intf->mode_switch_work)) { ... } If we call gb_interface_release to make cleanup, there may be an unfinished work. This function will call kfree to free the object "intf". However, if gb_interface_mode_switch_work is scheduled to run after kfree, it may cause use-after-free error as gb_interface_mode_switch_work will use the object "intf". The possible execution flow that may lead to the issue is as follows: CPU0 CPU1 | gb_interface_create | gb_interface_request_mode_switch gb_interface_release | kfree(intf) (free) | | gb_interface_mode_switch_work | mutex_lock(&intf->mutex) (use) Fix it by canceling the work before kfree. Signed-off-by: Sicong Huang Link: https://lore.kernel.org/r/20240416080313.92306-1-congei42@163.com Cc: Ronnie Sahlberg Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- drivers/greybus/interface.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/greybus/interface.c b/drivers/greybus/interface.c index 9ec949a438ef..52ef6be9d449 100644 --- a/drivers/greybus/interface.c +++ b/drivers/greybus/interface.c @@ -694,6 +694,7 @@ static void gb_interface_release(struct device *dev) trace_gb_interface_release(intf); + cancel_work_sync(&intf->mode_switch_work); kfree(intf); } -- Gitee From a1bcffe8ad28031294a43288b874fdffa653cf50 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Fri, 11 Aug 2023 10:55:29 +0800 Subject: [PATCH 2/6] net: tcp: fix unexcepted socket die when snd_wnd is 0 stable inclusion from stable-5.10.195 commit 88bc7122dba23441c819eb1be2428ba47bfad394 category: bugfix issue: NA CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit e89688e3e97868451a5d05b38a9d2633d6785cd4 ] In tcp_retransmit_timer(), a window shrunk connection will be regarded as timeout if 'tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX'. This is not right all the time. The retransmits will become zero-window probes in tcp_retransmit_timer() if the 'snd_wnd==0'. Therefore, the icsk->icsk_rto will come up to TCP_RTO_MAX sooner or later. However, the timer can be delayed and be triggered after 122877ms, not TCP_RTO_MAX, as I tested. Therefore, 'tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX' is always true once the RTO come up to TCP_RTO_MAX, and the socket will die. Fix this by replacing the 'tcp_jiffies32' with '(u32)icsk->icsk_timeout', which is exact the timestamp of the timeout. However, "tp->rcv_tstamp" can restart from idle, then tp->rcv_tstamp could already be a long time (minutes or hours) in the past even on the first RTO. So we double check the timeout with the duration of the retransmission. Meanwhile, making "2 * TCP_RTO_MAX" as the timeout to avoid the socket dying too soon. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Link: https://lore.kernel.org/netdev/CADxym3YyMiO+zMD4zj03YPM3FBi-1LHi6gSD2XT8pyAMM096pg@mail.gmail.com/ Signed-off-by: Menglong Dong Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- net/ipv4/tcp_timer.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 888683f2ff3e..7a83ba4e2063 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -433,6 +433,22 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX); } +static bool tcp_rtx_probe0_timed_out(const struct sock *sk, + const struct sk_buff *skb) +{ + const struct tcp_sock *tp = tcp_sk(sk); + const int timeout = TCP_RTO_MAX * 2; + u32 rcv_delta, rtx_delta; + + rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp; + if (rcv_delta <= timeout) + return false; + + rtx_delta = (u32)msecs_to_jiffies(tcp_time_stamp(tp) - + (tp->retrans_stamp ?: tcp_skb_timestamp(skb))); + + return rtx_delta > timeout; +} /** * tcp_retransmit_timer() - The TCP retransmit timeout handler @@ -498,7 +514,7 @@ void tcp_retransmit_timer(struct sock *sk) tp->snd_una, tp->snd_nxt); } #endif - if (tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX) { + if (tcp_rtx_probe0_timed_out(sk, skb)) { tcp_write_err(sk); goto out; } -- Gitee From b75f0731f52624410f83f110113b67260570f4d1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 7 Jun 2024 12:56:52 +0000 Subject: [PATCH 3/6] tcp: use signed arithmetic in tcp_rtx_probe0_timed_out() stable inclusion from stable-5.10.222 commit 24b9fafe34641a6dcf8df36f5e0de17d9cdccce8 category: bugfix issue: NA CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 36534d3c54537bf098224a32dc31397793d4594d upstream. Due to timer wheel implementation, a timer will usually fire after its schedule. For instance, for HZ=1000, a timeout between 512ms and 4s has a granularity of 64ms. For this range of values, the extra delay could be up to 63ms. For TCP, this means that tp->rcv_tstamp may be after inet_csk(sk)->icsk_timeout whenever the timer interrupt finally triggers, if one packet came during the extra delay. We need to make sure tcp_rtx_probe0_timed_out() handles this case. Fixes: e89688e3e978 ("net: tcp: fix unexcepted socket die when snd_wnd is 0") Signed-off-by: Eric Dumazet Cc: Menglong Dong Acked-by: Neal Cardwell Reviewed-by: Jason Xing Link: https://lore.kernel.org/r/20240607125652.1472540-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- net/ipv4/tcp_timer.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 7a83ba4e2063..da1793a2d3c5 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -438,8 +438,13 @@ static bool tcp_rtx_probe0_timed_out(const struct sock *sk, { const struct tcp_sock *tp = tcp_sk(sk); const int timeout = TCP_RTO_MAX * 2; - u32 rcv_delta, rtx_delta; + u32 rtx_delta; + s32 rcv_delta; + /* Note: timer interrupt might have been delayed by at least one jiffy, + * and tp->rcv_tstamp might very well have been written recently. + * rcv_delta can thus be negative. + */ rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp; if (rcv_delta <= timeout) return false; -- Gitee From ffe7e56edd04db5b562c464a2e41316b403a4210 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 10 Jul 2024 00:14:01 +0000 Subject: [PATCH 4/6] tcp: avoid too many retransmit packets stable inclusion from stable-5.10.222 commit 5d7e64d70a11d988553a08239c810a658e841982 category: bugfix issue: #IAEK1R CVE: CVE-2024-41007 Signed-off-by: wanxiaoqing --------------------------------------- commit 97a9063518f198ec0adb2ecb89789de342bb8283 upstream. If a TCP socket is using TCP_USER_TIMEOUT, and the other peer retracted its window to zero, tcp_retransmit_timer() can retransmit a packet every two jiffies (2 ms for HZ=1000), for about 4 minutes after TCP_USER_TIMEOUT has 'expired'. The fix is to make sure tcp_rtx_probe0_timed_out() takes icsk->icsk_user_timeout into account. Before blamed commit, the socket would not timeout after icsk->icsk_user_timeout, but would use standard exponential backoff for the retransmits. Also worth noting that before commit e89688e3e978 ("net: tcp: fix unexcepted socket die when snd_wnd is 0"), the issue would last 2 minutes instead of 4. Fixes: b701a99e431d ("tcp: Add tcp_clamp_rto_to_user_timeout() helper to improve accuracy") Signed-off-by: Eric Dumazet Cc: Neal Cardwell Reviewed-by: Jason Xing Reviewed-by: Jon Maxwell Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20240710001402.2758273-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- net/ipv4/tcp_timer.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index da1793a2d3c5..ae9d52722620 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -436,22 +436,34 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) static bool tcp_rtx_probe0_timed_out(const struct sock *sk, const struct sk_buff *skb) { + const struct inet_connection_sock *icsk = inet_csk(sk); + u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout); const struct tcp_sock *tp = tcp_sk(sk); - const int timeout = TCP_RTO_MAX * 2; + int timeout = TCP_RTO_MAX * 2; u32 rtx_delta; s32 rcv_delta; + rtx_delta = (u32)msecs_to_jiffies(tcp_time_stamp(tp) - + (tp->retrans_stamp ?: tcp_skb_timestamp(skb))); + + if (user_timeout) { + /* If user application specified a TCP_USER_TIMEOUT, + * it does not want win 0 packets to 'reset the timer' + * while retransmits are not making progress. + */ + if (rtx_delta > user_timeout) + return true; + timeout = min_t(u32, timeout, msecs_to_jiffies(user_timeout)); + } + /* Note: timer interrupt might have been delayed by at least one jiffy, * and tp->rcv_tstamp might very well have been written recently. * rcv_delta can thus be negative. */ - rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp; + rcv_delta = icsk->icsk_timeout - tp->rcv_tstamp; if (rcv_delta <= timeout) return false; - rtx_delta = (u32)msecs_to_jiffies(tcp_time_stamp(tp) - - (tp->retrans_stamp ?: tcp_skb_timestamp(skb))); - return rtx_delta > timeout; } -- Gitee From 19fe0c725d0ef4aea0e1a7b2e4e029d357d146fe Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 13 May 2024 12:27:15 +0200 Subject: [PATCH 5/6] netfilter: tproxy: bail out if IP has been disabled on the device stable inclusion from stable-5.10.219 commit 07eeedafc59c45fe5de43958128542be3784764c category: bugfix issue: #IAFG4F CVE: CVE-2024-36270 Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit 21a673bddc8fd4873c370caf9ae70ffc6d47e8d3 ] syzbot reports: general protection fault, probably for non-canonical address 0xdffffc0000000003: 0000 [#1] PREEMPT SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000018-0x000000000000001f] [..] RIP: 0010:nf_tproxy_laddr4+0xb7/0x340 net/ipv4/netfilter/nf_tproxy_ipv4.c:62 Call Trace: nft_tproxy_eval_v4 net/netfilter/nft_tproxy.c:56 [inline] nft_tproxy_eval+0xa9a/0x1a00 net/netfilter/nft_tproxy.c:168 __in_dev_get_rcu() can return NULL, so check for this. Reported-and-tested-by: syzbot+b94a6818504ea90d7661@syzkaller.appspotmail.com Fixes: cc6eb4338569 ("tproxy: use the interface primary IP address as a default value for --on-ip") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- net/ipv4/netfilter/nf_tproxy_ipv4.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c index 61cb2341f50f..7c1a0cd9f435 100644 --- a/net/ipv4/netfilter/nf_tproxy_ipv4.c +++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c @@ -58,6 +58,8 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr) laddr = 0; indev = __in_dev_get_rcu(skb->dev); + if (!indev) + return daddr; in_dev_for_each_ifa_rcu(ifa, indev) { if (ifa->ifa_flags & IFA_F_SECONDARY) -- Gitee From 3842bb2847416cb3fa70e1402faac7a940e66b8e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 15 May 2024 13:23:39 +0000 Subject: [PATCH 6/6] netfilter: nfnetlink_queue: acquire rcu_read_lock() in instance_destroy_rcu() stable inclusion from stable-5.10.219 commit e01065b339e323b3dfa1be217fd89e9b3208b0ab category: bugfix issue: #IAFG52 CVE: CVE-2024-36286 Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit dc21c6cc3d6986d938efbf95de62473982c98dec ] syzbot reported that nf_reinject() could be called without rcu_read_lock() : WARNING: suspicious RCU usage 6.9.0-rc7-syzkaller-02060-g5c1672705a1a #0 Not tainted net/netfilter/nfnetlink_queue.c:263 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 2 locks held by syz-executor.4/13427: #0: ffffffff8e334f60 (rcu_callback){....}-{0:0}, at: rcu_lock_acquire include/linux/rcupdate.h:329 [inline] #0: ffffffff8e334f60 (rcu_callback){....}-{0:0}, at: rcu_do_batch kernel/rcu/tree.c:2190 [inline] #0: ffffffff8e334f60 (rcu_callback){....}-{0:0}, at: rcu_core+0xa86/0x1830 kernel/rcu/tree.c:2471 #1: ffff88801ca92958 (&inst->lock){+.-.}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:356 [inline] #1: ffff88801ca92958 (&inst->lock){+.-.}-{2:2}, at: nfqnl_flush net/netfilter/nfnetlink_queue.c:405 [inline] #1: ffff88801ca92958 (&inst->lock){+.-.}-{2:2}, at: instance_destroy_rcu+0x30/0x220 net/netfilter/nfnetlink_queue.c:172 stack backtrace: CPU: 0 PID: 13427 Comm: syz-executor.4 Not tainted 6.9.0-rc7-syzkaller-02060-g5c1672705a1a #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/02/2024 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114 lockdep_rcu_suspicious+0x221/0x340 kernel/locking/lockdep.c:6712 nf_reinject net/netfilter/nfnetlink_queue.c:323 [inline] nfqnl_reinject+0x6ec/0x1120 net/netfilter/nfnetlink_queue.c:397 nfqnl_flush net/netfilter/nfnetlink_queue.c:410 [inline] instance_destroy_rcu+0x1ae/0x220 net/netfilter/nfnetlink_queue.c:172 rcu_do_batch kernel/rcu/tree.c:2196 [inline] rcu_core+0xafd/0x1830 kernel/rcu/tree.c:2471 handle_softirqs+0x2d6/0x990 kernel/softirq.c:554 __do_softirq kernel/softirq.c:588 [inline] invoke_softirq kernel/softirq.c:428 [inline] __irq_exit_rcu+0xf4/0x1c0 kernel/softirq.c:637 irq_exit_rcu+0x9/0x30 kernel/softirq.c:649 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1043 [inline] sysvec_apic_timer_interrupt+0xa6/0xc0 arch/x86/kernel/apic/apic.c:1043 Fixes: 9872bec773c2 ("[NETFILTER]: nfnetlink: use RCU for queue instances hash") Reported-by: syzbot Signed-off-by: Eric Dumazet Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- net/netfilter/nfnetlink_queue.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 9d87606c76ff..dc6af1919dea 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -167,7 +167,9 @@ instance_destroy_rcu(struct rcu_head *head) struct nfqnl_instance *inst = container_of(head, struct nfqnl_instance, rcu); + rcu_read_lock(); nfqnl_flush(inst, NULL, 0); + rcu_read_unlock(); kfree(inst); module_put(THIS_MODULE); } -- Gitee