From: Kuniyuki Iwashima <kuniyu@google.com> stable inclusion from stable-v6.6.99 commit 55baecb9eb90238f60a8350660d6762046ebd3bd category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/ICOXOT CVE: CVE-2025-38465 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... -------------------------------- [ Upstream commit ae8f160e7eb24240a2a79fc4c815c6a0d4ee16cc ] Netlink has this pattern in some places if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) atomic_add(skb->truesize, &sk->sk_rmem_alloc); , which has the same problem fixed by commit 5a465a0da13e ("udp: Fix multiple wraparounds of sk->sk_rmem_alloc."). For example, if we set INT_MAX to SO_RCVBUFFORCE, the condition is always false as the two operands are of int. Then, a single socket can eat as many skb as possible until OOM happens, and we can see multiple wraparounds of sk->sk_rmem_alloc. Let's fix it by using atomic_add_return() and comparing the two variables as unsigned int. Before: [root@fedora ~]# ss -f netlink Recv-Q Send-Q Local Address:Port Peer Address:Port -1668710080 0 rtnl:nl_wraparound/293 * After: [root@fedora ~]# ss -f netlink Recv-Q Send-Q Local Address:Port Peer Address:Port 2147483072 0 rtnl:nl_wraparound/290 * ^ `--- INT_MAX - 576 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Jason Baron <jbaron@akamai.com> Closes: https://lore.kernel.org/netdev/cover.1750285100.git.jbaron@akamai.com/ Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com> Link: https://patch.msgid.link/20250704054824.1580222-1-kuniyu@google.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org> Signed-off-by: Wang Liang <wangliang74@huawei.com> --- net/netlink/af_netlink.c | 81 ++++++++++++++++++++++++---------------- 1 file changed, 49 insertions(+), 32 deletions(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index cdb66eb0c3fa..01509d953d20 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -387,7 +387,6 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk) WARN_ON(skb->sk != NULL); skb->sk = sk; skb->destructor = netlink_skb_destructor; - atomic_add(skb->truesize, &sk->sk_rmem_alloc); sk_mem_charge(sk, skb->truesize); } @@ -1213,41 +1212,48 @@ static struct sk_buff *netlink_alloc_large_skb(unsigned int size, int netlink_attachskb(struct sock *sk, struct sk_buff *skb, long *timeo, struct sock *ssk) { + DECLARE_WAITQUEUE(wait, current); struct netlink_sock *nlk; + unsigned int rmem; nlk = nlk_sk(sk); + rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc); - if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || - test_bit(NETLINK_S_CONGESTED, &nlk->state))) { - DECLARE_WAITQUEUE(wait, current); - if (!*timeo) { - if (!ssk || netlink_is_kernel(ssk)) - netlink_overrun(sk); - sock_put(sk); - kfree_skb(skb); - return -EAGAIN; - } - - __set_current_state(TASK_INTERRUPTIBLE); - add_wait_queue(&nlk->wait, &wait); + if ((rmem == skb->truesize || rmem < READ_ONCE(sk->sk_rcvbuf)) && + !test_bit(NETLINK_S_CONGESTED, &nlk->state)) { + netlink_skb_set_owner_r(skb, sk); + return 0; + } - if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || - test_bit(NETLINK_S_CONGESTED, &nlk->state)) && - !sock_flag(sk, SOCK_DEAD)) - *timeo = schedule_timeout(*timeo); + atomic_sub(skb->truesize, &sk->sk_rmem_alloc); - __set_current_state(TASK_RUNNING); - remove_wait_queue(&nlk->wait, &wait); + if (!*timeo) { + if (!ssk || netlink_is_kernel(ssk)) + netlink_overrun(sk); sock_put(sk); + kfree_skb(skb); + return -EAGAIN; + } - if (signal_pending(current)) { - kfree_skb(skb); - return sock_intr_errno(*timeo); - } - return 1; + __set_current_state(TASK_INTERRUPTIBLE); + add_wait_queue(&nlk->wait, &wait); + rmem = atomic_read(&sk->sk_rmem_alloc); + + if (((rmem && rmem + skb->truesize > READ_ONCE(sk->sk_rcvbuf)) || + test_bit(NETLINK_S_CONGESTED, &nlk->state)) && + !sock_flag(sk, SOCK_DEAD)) + *timeo = schedule_timeout(*timeo); + + __set_current_state(TASK_RUNNING); + remove_wait_queue(&nlk->wait, &wait); + sock_put(sk); + + if (signal_pending(current)) { + kfree_skb(skb); + return sock_intr_errno(*timeo); } - netlink_skb_set_owner_r(skb, sk); - return 0; + + return 1; } static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb) @@ -1307,6 +1313,7 @@ static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb, ret = -ECONNREFUSED; if (nlk->netlink_rcv != NULL) { ret = skb->len; + atomic_add(skb->truesize, &sk->sk_rmem_alloc); netlink_skb_set_owner_r(skb, sk); NETLINK_CB(skb).sk = ssk; netlink_deliver_tap_kernel(sk, ssk, skb); @@ -1383,13 +1390,19 @@ EXPORT_SYMBOL_GPL(netlink_strict_get_check); static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb) { struct netlink_sock *nlk = nlk_sk(sk); + unsigned int rmem, rcvbuf; - if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && + rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc); + rcvbuf = READ_ONCE(sk->sk_rcvbuf); + + if ((rmem != skb->truesize || rmem <= rcvbuf) && !test_bit(NETLINK_S_CONGESTED, &nlk->state)) { netlink_skb_set_owner_r(skb, sk); __netlink_sendskb(sk, skb); - return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1); + return rmem > (rcvbuf >> 1); } + + atomic_sub(skb->truesize, &sk->sk_rmem_alloc); return -1; } @@ -2180,6 +2193,7 @@ static int netlink_dump(struct sock *sk, bool lock_taken) struct module *module; int err = -ENOBUFS; int alloc_min_size; + unsigned int rmem; int alloc_size; if (!lock_taken) @@ -2189,9 +2203,6 @@ static int netlink_dump(struct sock *sk, bool lock_taken) goto errout_skb; } - if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) - goto errout_skb; - /* NLMSG_GOODSIZE is small to avoid high order allocations being * required, but it makes sense to _attempt_ a 16K bytes allocation * to reduce number of system calls on dump operations, if user @@ -2214,6 +2225,12 @@ static int netlink_dump(struct sock *sk, bool lock_taken) if (!skb) goto errout_skb; + rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc); + if (rmem >= READ_ONCE(sk->sk_rcvbuf)) { + atomic_sub(skb->truesize, &sk->sk_rmem_alloc); + goto errout_skb; + } + /* Trim skb to allocated size. User is expected to provide buffer as * large as max(min_dump_alloc, 16KiB (mac_recvmsg_len capped at * netlink_recvmsg())). dump will pack as many smaller messages as -- 2.33.0

From: Jakub Kicinski <kuba@kernel.org> stable inclusion from stable-v6.6.99 commit c31ee1695b6d88042d7bd6b2a77babb70f941451 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/ICOXOT CVE: CVE-2025-38465 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... -------------------------------- commit a215b5723922f8099078478122f02100e489cb80 upstream. Commit under Fixes tightened up the memory accounting for Netlink sockets. Looks like the accounting is too strict for some existing use cases, Marek reported issues with nl80211 / WiFi iw CLI. To reduce number of iterations Netlink dumps try to allocate messages based on the size of the buffer passed to previous recvmsg() calls. If user space uses a larger buffer in recvmsg() than sk_rcvbuf we will allocate an skb we won't be able to queue. Make sure we always allow at least one skb to be queued. Same workaround is already present in netlink_attachskb(). Alternative would be to cap the allocation size to rcvbuf - rmem_alloc but as I said, the workaround is already present in other places. Reported-by: Marek Szyprowski <m.szyprowski@samsung.com> Link: https://lore.kernel.org/9794af18-4905-46c6-b12c-365ea2f05858@samsung.com Fixes: ae8f160e7eb2 ("netlink: Fix wraparounds of sk->sk_rmem_alloc.") Tested-by: Marek Szyprowski <m.szyprowski@samsung.com> Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com> Link: https://patch.msgid.link/20250711001121.3649033-1-kuba@kernel.org Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Wang Liang <wangliang74@huawei.com> --- net/netlink/af_netlink.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index ad5178b096ea..0c0ffa720868 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2189,11 +2189,11 @@ static int netlink_dump(struct sock *sk, bool lock_taken) struct netlink_ext_ack extack = {}; struct netlink_callback *cb; struct sk_buff *skb = NULL; + unsigned int rmem, rcvbuf; size_t max_recvmsg_len; struct module *module; int err = -ENOBUFS; int alloc_min_size; - unsigned int rmem; int alloc_size; if (!lock_taken) @@ -2225,8 +2225,9 @@ static int netlink_dump(struct sock *sk, bool lock_taken) if (!skb) goto errout_skb; + rcvbuf = READ_ONCE(sk->sk_rcvbuf); rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc); - if (rmem >= READ_ONCE(sk->sk_rcvbuf)) { + if (rmem != skb->truesize && rmem >= rcvbuf) { atomic_sub(skb->truesize, &sk->sk_rmem_alloc); goto errout_skb; } -- 2.33.0