- Kernel - mailweb.openeuler.org

[PATCH OLK-5.10] netfilter: allow exp not to be removed in nf_ct_find_expectation
by Dong Chenchen 30 Jan '26

30 Jan '26

From: Xin Long <lucien.xin(a)gmail.com> mainline inclusion from mainline-v6.6-rc1 commit 4914109a8e1e494c6aa9852f9e84ec77a5fc643f category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/11115 CVE: CVE-2023-52927 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Currently nf_conntrack_in() calling nf_ct_find_expectation() will remove the exp from the hash table. However, in some scenario, we expect the exp not to be removed when the created ct will not be confirmed, like in OVS and TC conntrack in the following patches. This patch allows exp not to be removed by setting IPS_CONFIRMED in the status of the tmpl. Signed-off-by: Xin Long <lucien.xin(a)gmail.com> Acked-by: Aaron Conole <aconole(a)redhat.com> Acked-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Conflicts: net/netfilter/nf_conntrack_core.c net/netfilter/nf_conntrack_expect.c net/netfilter/nft_ct.c [commit 50bfbb8957ab remove pr_debug calls, which lead to conflicts in init_conntrack(). commit c53bd0e96662 move ct counter to net_generic data which not merged lead to conflict in nf_ct_find_expectation(). commit 719774377 convert to refcount_t api in conntrack, which not merged lead to conflicts] Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- include/net/netfilter/nf_conntrack_expect.h | 2 +- net/netfilter/nf_conntrack_core.c | 2 +- net/netfilter/nf_conntrack_expect.c | 4 ++-- net/netfilter/nft_ct.c | 2 ++ 4 files changed, 6 insertions(+), 4 deletions(-) diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index 0855b60fba17..f642a87ea330 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -100,7 +100,7 @@ nf_ct_expect_find_get(struct net *net, struct nf_conntrack_expect * nf_ct_find_expectation(struct net *net, const struct nf_conntrack_zone *zone, - const struct nf_conntrack_tuple *tuple); + const struct nf_conntrack_tuple *tuple, bool unlink); void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp, u32 portid, int report); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 9090d677ddfa..371aef7774f6 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1583,7 +1583,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, local_bh_disable(); if (net->ct.expect_count) { spin_lock(&nf_conntrack_expect_lock); - exp = nf_ct_find_expectation(net, zone, tuple); + exp = nf_ct_find_expectation(net, zone, tuple, !tmpl || nf_ct_is_confirmed(tmpl)); if (exp) { pr_debug("expectation arrives ct=%p exp=%p\n", ct, exp); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 42557d2b6a90..45f29e28aba3 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -156,7 +156,7 @@ EXPORT_SYMBOL_GPL(nf_ct_expect_find_get); struct nf_conntrack_expect * nf_ct_find_expectation(struct net *net, const struct nf_conntrack_zone *zone, - const struct nf_conntrack_tuple *tuple) + const struct nf_conntrack_tuple *tuple, bool unlink) { struct nf_conntrack_expect *i, *exp = NULL; unsigned int h; @@ -195,7 +195,7 @@ nf_ct_find_expectation(struct net *net, !atomic_inc_not_zero(&exp->master->ct_general.use))) return NULL; - if (exp->flags & NF_CT_EXPECT_PERMANENT) { + if (exp->flags & NF_CT_EXPECT_PERMANENT || !unlink) { refcount_inc(&exp->use); return exp; } else if (del_timer(&exp->timeout)) { diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 2a8dfa68f6e2..32b83333e834 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -268,6 +268,7 @@ static void nft_ct_set_zone_eval(const struct nft_expr *expr, regs->verdict.code = NF_DROP; return; } + __set_bit(IPS_CONFIRMED_BIT, &ct->status); } atomic_inc(&ct->ct_general.use); @@ -375,6 +376,7 @@ static bool nft_ct_tmpl_alloc_pcpu(void) return false; } + __set_bit(IPS_CONFIRMED_BIT, &tmp->status); atomic_set(&tmp->ct_general.use, 1); per_cpu(nft_ct_pcpu_template, cpu) = tmp; } -- 2.25.1

2 1

[PATCH OLK-5.10] bpf, sockmap: Avoid using sk_socket after free when sending
by Dong Chenchen 30 Jan '26

30 Jan '26

From: Jiayuan Chen <jiayuan.chen(a)linux.dev> mainline inclusion from mainline-v6.15-rc4 commit 8259eb0e06d8f64c700f5fbdb28a5c18e10de291 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/9634 CVE: CVE-2025-38154 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- The sk->sk_socket is not locked or referenced in backlog thread, and during the call to skb_send_sock(), there is a race condition with the release of sk_socket. All types of sockets(tcp/udp/unix/vsock) will be affected. Race conditions: ''' CPU0 CPU1 backlog::skb_send_sock sendmsg_unlocked sock_sendmsg sock_sendmsg_nosec close(fd): ... ops->release() -> sock_map_close() sk_socket->ops = NULL free(socket) sock->ops->sendmsg ^ panic here ''' The ref of psock become 0 after sock_map_close() executed. ''' void sock_map_close() { ... if (likely(psock)) { ... // !! here we remove psock and the ref of psock become 0 sock_map_remove_links(sk, psock) psock = sk_psock_get(sk); if (unlikely(!psock)) goto no_psock; <=== Control jumps here via goto ... cancel_delayed_work_sync(&psock->work); <=== not executed sk_psock_put(sk, psock); ... } ''' Based on the fact that we already wait for the workqueue to finish in sock_map_close() if psock is held, we simply increase the psock reference count to avoid race conditions. With this patch, if the backlog thread is running, sock_map_close() will wait for the backlog thread to complete and cancel all pending work. If no backlog running, any pending work that hasn't started by then will fail when invoked by sk_psock_get(), as the psock reference count have been zeroed, and sk_psock_drop() will cancel all jobs via cancel_delayed_work_sync(). In summary, we require synchronization to coordinate the backlog thread and close() thread. The panic I catched: ''' Workqueue: events sk_psock_backlog RIP: 0010:sock_sendmsg+0x21d/0x440 RAX: 0000000000000000 RBX: ffffc9000521fad8 RCX: 0000000000000001 ... Call Trace: <TASK> ? die_addr+0x40/0xa0 ? exc_general_protection+0x14c/0x230 ? asm_exc_general_protection+0x26/0x30 ? sock_sendmsg+0x21d/0x440 ? sock_sendmsg+0x3e0/0x440 ? __pfx_sock_sendmsg+0x10/0x10 __skb_send_sock+0x543/0xb70 sk_psock_backlog+0x247/0xb80 ... ''' Fixes: 4b4647add7d3 ("sock_map: avoid race between sock_map_close and sk_psock_put") Reported-by: Michal Luczaj <mhal(a)rbox.co> Signed-off-by: Jiayuan Chen <jiayuan.chen(a)linux.dev> Signed-off-by: Martin KaFai Lau <martin.lau(a)kernel.org> Reviewed-by: John Fastabend <john.fastabend(a)gmail.com> Link: https://lore.kernel.org/r/20250516141713.291150-1-jiayuan.chen@linux.dev Conflicts: net/core/skmsg.c [commit 3b4f14b79428 is not backport] Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/core/skmsg.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index cc6570d71911..5150fc93dd9b 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -543,6 +543,13 @@ static void sk_psock_backlog(struct work_struct *work) u32 len, off; int ret; + /* Increment the psock refcnt to synchronize with close(fd) path in + * sock_map_close(), ensuring we wait for backlog thread completion + * before sk_socket freed. If refcnt increment fails, it indicates + * sock_map_close() completed with sk_socket potentially already freed. + */ + if (!sk_psock_get(psock->sk)) + return; mutex_lock(&psock->work_mutex); if (unlikely(state->skb)) { spin_lock_bh(&psock->ingress_lock); @@ -586,6 +593,7 @@ static void sk_psock_backlog(struct work_struct *work) } end: mutex_unlock(&psock->work_mutex); + sk_psock_put(psock->sk, psock); } struct sk_psock *sk_psock_init(struct sock *sk, int node) -- 2.25.1

2 1

[PATCH OLK-5.10] can: bcm: add locking for bcm_op runtime updates
by Dong Chenchen 30 Jan '26

30 Jan '26

From: Oliver Hartkopp <socketcan(a)hartkopp.net> stable inclusion from stable-v5.10.238 commit 7595de7bc56e0e52b74e56c90f7e247bf626d628 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/10070 CVE: CVE-2025-38004 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit c2aba69d0c36a496ab4f2e81e9c2b271f2693fd7 upstream. The CAN broadcast manager (CAN BCM) can send a sequence of CAN frames via hrtimer. The content and also the length of the sequence can be changed resp reduced at runtime where the 'currframe' counter is then set to zero. Although this appeared to be a safe operation the updates of 'currframe' can be triggered from user space and hrtimer context in bcm_can_tx(). Anderson Nascimento created a proof of concept that triggered a KASAN slab-out-of-bounds read access which can be prevented with a spin_lock_bh. At the rework of bcm_can_tx() the 'count' variable has been moved into the protected section as this variable can be modified from both contexts too. Fixes: ffd980f976e7 ("[CAN]: Add broadcast manager (bcm) protocol") Reported-by: Anderson Nascimento <anderson(a)allelesecurity.com> Tested-by: Anderson Nascimento <anderson(a)allelesecurity.com> Reviewed-by: Marc Kleine-Budde <mkl(a)pengutronix.de> Signed-off-by: Oliver Hartkopp <socketcan(a)hartkopp.net> Link: https://patch.msgid.link/20250519125027.11900-1-socketcan@hartkopp.net Cc: stable(a)vger.kernel.org Signed-off-by: Marc Kleine-Budde <mkl(a)pengutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/can/bcm.c | 66 +++++++++++++++++++++++++++++++++++---------------- 1 file changed, 45 insertions(+), 21 deletions(-) diff --git a/net/can/bcm.c b/net/can/bcm.c index cb849b5a8c14..9ce1e5c777f2 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -58,6 +58,7 @@ #include <linux/can/skb.h> #include <linux/can/bcm.h> #include <linux/slab.h> +#include <linux/spinlock.h> #include <net/sock.h> #include <net/net_namespace.h> @@ -120,6 +121,7 @@ struct bcm_op { struct canfd_frame last_sframe; struct sock *sk; struct net_device *rx_reg_dev; + spinlock_t bcm_tx_lock; /* protect currframe/count in runtime updates */ }; struct bcm_sock { @@ -273,13 +275,18 @@ static void bcm_can_tx(struct bcm_op *op) { struct sk_buff *skb; struct net_device *dev; - struct canfd_frame *cf = op->frames + op->cfsiz * op->currframe; + struct canfd_frame *cf; int err; /* no target device? => exit */ if (!op->ifindex) return; + /* read currframe under lock protection */ + spin_lock_bh(&op->bcm_tx_lock); + cf = op->frames + op->cfsiz * op->currframe; + spin_unlock_bh(&op->bcm_tx_lock); + dev = dev_get_by_index(sock_net(op->sk), op->ifindex); if (!dev) { /* RFC: should this bcm_op remove itself here? */ @@ -300,6 +307,10 @@ static void bcm_can_tx(struct bcm_op *op) skb->dev = dev; can_skb_set_owner(skb, op->sk); err = can_send(skb, 1); + + /* update currframe and count under lock protection */ + spin_lock_bh(&op->bcm_tx_lock); + if (!err) op->frames_abs++; @@ -308,6 +319,11 @@ static void bcm_can_tx(struct bcm_op *op) /* reached last frame? */ if (op->currframe >= op->nframes) op->currframe = 0; + + if (op->count > 0) + op->count--; + + spin_unlock_bh(&op->bcm_tx_lock); out: dev_put(dev); } @@ -404,7 +420,7 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) struct bcm_msg_head msg_head; if (op->kt_ival1 && (op->count > 0)) { - op->count--; + bcm_can_tx(op); if (!op->count && (op->flags & TX_COUNTEVT)) { /* create notification to user */ @@ -419,7 +435,6 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) bcm_send_to_user(op, &msg_head, NULL, 0); } - bcm_can_tx(op); } else if (op->kt_ival2) { bcm_can_tx(op); @@ -909,6 +924,27 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, } op->flags = msg_head->flags; + /* only lock for unlikely count/nframes/currframe changes */ + if (op->nframes != msg_head->nframes || + op->flags & TX_RESET_MULTI_IDX || + op->flags & SETTIMER) { + + spin_lock_bh(&op->bcm_tx_lock); + + if (op->nframes != msg_head->nframes || + op->flags & TX_RESET_MULTI_IDX) { + /* potentially update changed nframes */ + op->nframes = msg_head->nframes; + /* restart multiple frame transmission */ + op->currframe = 0; + } + + if (op->flags & SETTIMER) + op->count = msg_head->count; + + spin_unlock_bh(&op->bcm_tx_lock); + } + } else { /* insert new BCM operation for the given can_id */ @@ -916,9 +952,14 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, if (!op) return -ENOMEM; + spin_lock_init(&op->bcm_tx_lock); op->can_id = msg_head->can_id; op->cfsiz = CFSIZ(msg_head->flags); op->flags = msg_head->flags; + op->nframes = msg_head->nframes; + + if (op->flags & SETTIMER) + op->count = msg_head->count; /* create array for CAN frames and copy the data */ if (msg_head->nframes > 1) { @@ -977,22 +1018,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, } /* if ((op = bcm_find_op(&bo->tx_ops, msg_head->can_id, ifindex))) */ - if (op->nframes != msg_head->nframes) { - op->nframes = msg_head->nframes; - /* start multiple frame transmission with index 0 */ - op->currframe = 0; - } - - /* check flags */ - - if (op->flags & TX_RESET_MULTI_IDX) { - /* start multiple frame transmission with index 0 */ - op->currframe = 0; - } - if (op->flags & SETTIMER) { /* set timer values */ - op->count = msg_head->count; op->ival1 = msg_head->ival1; op->ival2 = msg_head->ival2; op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); @@ -1009,11 +1036,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, op->flags |= TX_ANNOUNCE; } - if (op->flags & TX_ANNOUNCE) { + if (op->flags & TX_ANNOUNCE) bcm_can_tx(op); - if (op->count) - op->count--; - } if (op->flags & STARTTIMER) bcm_tx_start_timer(op); -- 2.25.1

2 1

[PATCH OLK-5.10] RDMA/rxe: Fix slab-use-after-free Read in rxe_queue_cleanup bug
by Dong Chenchen 30 Jan '26

30 Jan '26

From: Zhu Yanjun <yanjun.zhu(a)linux.dev> stable inclusion from stable-v5.10.238 commit 3a3b73e135e3bd18423d0baa72571319c7feb759 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/9719 CVE: CVE-2025-38024 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit f81b33582f9339d2dc17c69b92040d3650bb4bae ] Call Trace: <TASK> __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x7d/0xa0 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xcf/0x610 mm/kasan/report.c:489 kasan_report+0xb5/0xe0 mm/kasan/report.c:602 rxe_queue_cleanup+0xd0/0xe0 drivers/infiniband/sw/rxe/rxe_queue.c:195 rxe_cq_cleanup+0x3f/0x50 drivers/infiniband/sw/rxe/rxe_cq.c:132 __rxe_cleanup+0x168/0x300 drivers/infiniband/sw/rxe/rxe_pool.c:232 rxe_create_cq+0x22e/0x3a0 drivers/infiniband/sw/rxe/rxe_verbs.c:1109 create_cq+0x658/0xb90 drivers/infiniband/core/uverbs_cmd.c:1052 ib_uverbs_create_cq+0xc7/0x120 drivers/infiniband/core/uverbs_cmd.c:1095 ib_uverbs_write+0x969/0xc90 drivers/infiniband/core/uverbs_main.c:679 vfs_write fs/read_write.c:677 [inline] vfs_write+0x26a/0xcc0 fs/read_write.c:659 ksys_write+0x1b8/0x200 fs/read_write.c:731 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xaa/0x1b0 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f In the function rxe_create_cq, when rxe_cq_from_init fails, the function rxe_cleanup will be called to handle the allocated resources. In fact, some memory resources have already been freed in the function rxe_cq_from_init. Thus, this problem will occur. The solution is to let rxe_cleanup do all the work. Fixes: 8700e3e7c485 ("Soft RoCE driver") Link: https://paste.ubuntu.com/p/tJgC42wDf6/ Tested-by: liuyi <liuy22(a)mails.tsinghua.edu.cn> Signed-off-by: Zhu Yanjun <yanjun.zhu(a)linux.dev> Link: https://patch.msgid.link/20250412075714.3257358-1-yanjun.zhu@linux.dev Reviewed-by: Daisuke Matsuda <matsuda-daisuke(a)fujitsu.com> Signed-off-by: Leon Romanovsky <leon(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- drivers/infiniband/sw/rxe/rxe_cq.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_cq.c b/drivers/infiniband/sw/rxe/rxe_cq.c index 43394c3f29d4..129576a79698 100644 --- a/drivers/infiniband/sw/rxe/rxe_cq.c +++ b/drivers/infiniband/sw/rxe/rxe_cq.c @@ -69,11 +69,8 @@ int rxe_cq_from_init(struct rxe_dev *rxe, struct rxe_cq *cq, int cqe, err = do_mmap_info(rxe, uresp ? &uresp->mi : NULL, udata, cq->queue->buf, cq->queue->buf_size, &cq->queue->ip); - if (err) { - vfree(cq->queue->buf); - kfree(cq->queue); + if (err) return err; - } if (uresp) cq->is_user = 1; -- 2.25.1

2 1

[PATCH OLK-6.6] bpf: Check skb->transport_header is set in bpf_skb_check_mtu
by Dong Chenchen 30 Jan '26

30 Jan '26

From: Martin KaFai Lau <martin.lau(a)kernel.org> mainline inclusion from mainline-v6.19-rc1 commit d946f3c98328171fa50ddb908593cf833587f725 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/12719 CVE: CVE-2025-68363 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- The bpf_skb_check_mtu helper needs to use skb->transport_header when the BPF_MTU_CHK_SEGS flag is used: bpf_skb_check_mtu(skb, ifindex, &mtu_len, 0, BPF_MTU_CHK_SEGS) The transport_header is not always set. There is a WARN_ON_ONCE report when CONFIG_DEBUG_NET is enabled + skb->gso_size is set + bpf_prog_test_run is used: WARNING: CPU: 1 PID: 2216 at ./include/linux/skbuff.h:3071 skb_gso_validate_network_len bpf_skb_check_mtu bpf_prog_3920e25740a41171_tc_chk_segs_flag # A test in the next patch bpf_test_run bpf_prog_test_run_skb For a normal ingress skb (not test_run), skb_reset_transport_header is performed but there is plan to avoid setting it as described in commit 2170a1f09148 ("net: no longer reset transport_header in __netif_receive_skb_core()"). This patch fixes the bpf helper by checking skb_transport_header_was_set(). The check is done just before skb->transport_header is used, to avoid breaking the existing bpf prog. The WARN_ON_ONCE is limited to bpf_prog_test_run, so targeting bpf-next. Fixes: 34b2021cc616 ("bpf: Add BPF-helper for MTU checking") Cc: Jesper Dangaard Brouer <hawk(a)kernel.org> Reported-by: Kaiyan Mei <M202472210(a)hust.edu.cn> Reported-by: Yinhao Hu <dddddd(a)hust.edu.cn> Signed-off-by: Martin KaFai Lau <martin.lau(a)kernel.org> Link: https://lore.kernel.org/r/20251112232331.1566074-1-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/core/filter.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/core/filter.c b/net/core/filter.c index c9d4910f3f55..c8bb4537e0fc 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6360,9 +6360,12 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb, */ if (skb_is_gso(skb)) { ret = BPF_MTU_CHK_RET_SUCCESS; - if (flags & BPF_MTU_CHK_SEGS && - !skb_gso_validate_network_len(skb, mtu)) - ret = BPF_MTU_CHK_RET_SEGS_TOOBIG; + if (flags & BPF_MTU_CHK_SEGS) { + if (!skb_transport_header_was_set(skb)) + return -EINVAL; + if (!skb_gso_validate_network_len(skb, mtu)) + ret = BPF_MTU_CHK_RET_SEGS_TOOBIG; + } } out: *mtu_len = mtu; -- 2.25.1

2 1

[PATCH OLK-6.6] bpf: Do not let BPF test infra emit invalid GSO types to stack
by Dong Chenchen 30 Jan '26

30 Jan '26

From: Daniel Borkmann <daniel(a)iogearbox.net> mainline inclusion from mainline-v6.19-rc1 commit 04a899573fb87273a656f178b5f920c505f68875 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/12743 CVE: CVE-2025-68725 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Yinhao et al. reported that their fuzzer tool was able to trigger a skb_warn_bad_offload() from netif_skb_features() -> gso_features_check(). When a BPF program - triggered via BPF test infra - pushes the packet to the loopback device via bpf_clone_redirect() then mentioned offload warning can be seen. GSO-related features are then rightfully disabled. We get into this situation due to convert___skb_to_skb() setting gso_segs and gso_size but not gso_type. Technically, it makes sense that this warning triggers since the GSO properties are malformed due to the gso_type. Potentially, the gso_type could be marked non-trustworthy through setting it at least to SKB_GSO_DODGY without any other specific assumptions, but that also feels wrong given we should not go further into the GSO engine in the first place. The checks were added in 121d57af308d ("gso: validate gso_type in GSO handlers") because there were malicious (syzbot) senders that combine a protocol with a non-matching gso_type. If we would want to drop such packets, gso_features_check() currently only returns feature flags via netif_skb_features(), so one location for potentially dropping such skbs could be validate_xmit_unreadable_skb(), but then otoh it would be an additional check in the fast-path for a very corner case. Given bpf_clone_redirect() is the only place where BPF test infra could emit such packets, lets reject them right there. Fixes: 850a88cc4096 ("bpf: Expose __sk_buff wire_len/gso_segs to BPF_PROG_TEST_RUN") Fixes: cf62089b0edd ("bpf: Add gso_size to __sk_buff") Reported-by: Yinhao Hu <dddddd(a)hust.edu.cn> Reported-by: Kaiyan Mei <M202472210(a)hust.edu.cn> Reported-by: Dongliang Mu <dzm91(a)hust.edu.cn> Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Signed-off-by: Martin KaFai Lau <martin.lau(a)kernel.org> Link: https://patch.msgid.link/20251020075441.127980-1-daniel@iogearbox.net Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/bpf/test_run.c | 5 +++++ net/core/filter.c | 7 +++++++ 2 files changed, 12 insertions(+) diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 73fb9db55798..5394313c04ef 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -914,6 +914,11 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb) if (__skb->gso_segs > GSO_MAX_SEGS) return -EINVAL; + + /* Currently GSO type is zero/unset. If this gets extended with + * a small list of accepted GSO types in future, the filter for + * an unset GSO type in bpf_clone_redirect() can be lifted. + */ skb_shinfo(skb)->gso_segs = __skb->gso_segs; skb_shinfo(skb)->gso_size = __skb->gso_size; skb_shinfo(skb)->hwtstamps.hwtstamp = __skb->hwtstamp; diff --git a/net/core/filter.c b/net/core/filter.c index c9d4910f3f55..f3ae3f1babac 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2451,6 +2451,13 @@ BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) return -EINVAL; + /* BPF test infra's convert___skb_to_skb() can create type-less + * GSO packets. gso_features_check() will detect this as a bad + * offload. However, lets not leak them out in the first place. + */ + if (unlikely(skb_is_gso(skb) && !skb_shinfo(skb)->gso_type)) + return -EBADMSG; + dev = dev_get_by_index_rcu(dev_net(skb->dev), ifindex); if (unlikely(!dev)) return -EINVAL; -- 2.25.1

2 1

[PATCH OLK-6.6] tcp: use dst_dev_rcu() in tcp_fastopen_active_disable_ofo_check()
by Dong Chenchen 30 Jan '26

30 Jan '26

From: Eric Dumazet <edumazet(a)google.com> mainline inclusion from mainline-v6.18-rc1 commit b62a59c18b692f892dcb8109c1c2e653b2abc95c category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/11624 CVE: CVE-2025-68188 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Use RCU to avoid a pair of atomic operations and a potential UAF on dst_dev()->flags. Signed-off-by: Eric Dumazet <edumazet(a)google.com> Reviewed-by: David Ahern <dsahern(a)kernel.org> Link: https://patch.msgid.link/20250828195823.3958522-8-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: net/ipv4/tcp_fastopen.c [commit a74fc62eec15 is not backport] Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/ipv4/tcp_fastopen.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 408985eb74ee..f9460e7531ba 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -558,6 +558,7 @@ bool tcp_fastopen_active_should_disable(struct sock *sk) void tcp_fastopen_active_disable_ofo_check(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + struct net_device *dev; struct dst_entry *dst; struct sk_buff *skb; @@ -574,10 +575,12 @@ void tcp_fastopen_active_disable_ofo_check(struct sock *sk) } } else if (tp->syn_fastopen_ch && atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times)) { - dst = sk_dst_get(sk); - if (!(dst && dst->dev && (dst->dev->flags & IFF_LOOPBACK))) + rcu_read_lock(); + dst = __sk_dst_get(sk); + dev = dst ? dst_dev_rcu(dst) : NULL; + if (!(dev && (dev->flags & IFF_LOOPBACK))) atomic_set(&sock_net(sk)->ipv4.tfo_active_disable_times, 0); - dst_release(dst); + rcu_read_unlock(); } } -- 2.25.1

2 1

[PATCH OLK-6.6] netfilter: nft_ct: add seqadj extension for natted connections
by Dong Chenchen 30 Jan '26

30 Jan '26

From: Andrii Melnychenko <a.melnychenko(a)vyos.io> mainline inclusion from mainline-v6.18-rc4 commit 90918e3b6404c2a37837b8f11692471b4c512de2 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/11571 CVE: CVE-2025-68206 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Sequence adjustment may be required for FTP traffic with PASV/EPSV modes. due to need to re-write packet payload (IP, port) on the ftp control connection. This can require changes to the TCP length and expected seq / ack_seq. The easiest way to reproduce this issue is with PASV mode. Example ruleset: table inet ftp_nat { ct helper ftp_helper { type "ftp" protocol tcp l3proto inet } chain prerouting { type filter hook prerouting priority 0; policy accept; tcp dport 21 ct state new ct helper set "ftp_helper" } } table ip nat { chain prerouting { type nat hook prerouting priority -100; policy accept; tcp dport 21 dnat ip prefix to ip daddr map { 192.168.100.1 : 192.168.13.2/32 } } chain postrouting { type nat hook postrouting priority 100 ; policy accept; tcp sport 21 snat ip prefix to ip saddr map { 192.168.13.2 : 192.168.100.1/32 } } } Note that the ftp helper gets assigned *after* the dnat setup. The inverse (nat after helper assign) is handled by an existing check in nf_nat_setup_info() and will not show the problem. Topoloy: +-------------------+ +----------------------------------+ | FTP: 192.168.13.2 | <-> | NAT: 192.168.13.3, 192.168.100.1 | +-------------------+ +----------------------------------+ | +-----------------------+ | Client: 192.168.100.2 | +-----------------------+ ftp nat changes do not work as expected in this case: Connected to 192.168.100.1. [..] ftp> epsv EPSV/EPRT on IPv4 off. ftp> ls 227 Entering passive mode (192,168,100,1,209,129). 421 Service not available, remote server has closed connection. Kernel logs: Missing nfct_seqadj_ext_add() setup call WARNING: CPU: 1 PID: 0 at net/netfilter/nf_conntrack_seqadj.c:41 [..] __nf_nat_mangle_tcp_packet+0x100/0x160 [nf_nat] nf_nat_ftp+0x142/0x280 [nf_nat_ftp] help+0x4d1/0x880 [nf_conntrack_ftp] nf_confirm+0x122/0x2e0 [nf_conntrack] nf_hook_slow+0x3c/0xb0 .. Fix this by adding the required extension when a conntrack helper is assigned to a connection that has a nat binding. Fixes: 1a64edf54f55 ("netfilter: nft_ct: add helper set support") Signed-off-by: Andrii Melnychenko <a.melnychenko(a)vyos.io> Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/netfilter/nft_ct.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index ab1214da99ff..a3750cc7099a 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -22,6 +22,7 @@ #include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_expect.h> +#include <net/netfilter/nf_conntrack_seqadj.h> struct nft_ct_helper_obj { struct nf_conntrack_helper *helper4; @@ -1173,6 +1174,10 @@ static void nft_ct_helper_obj_eval(struct nft_object *obj, if (help) { rcu_assign_pointer(help->helper, to_assign); set_bit(IPS_HELPER_BIT, &ct->status); + + if ((ct->status & IPS_NAT_MASK) && !nfct_seqadj(ct)) + if (!nfct_seqadj_ext_add(ct)) + regs->verdict.code = NF_DROP; } } -- 2.25.1

2 1

[PATCH OLK-6.6 0/2] net: xfrm: Fix CVE-2025-40215
by Dong Chenchen 30 Jan '26

30 Jan '26

Fix CVE-2025-40215 Sabrina Dubroca (2): xfrm: delete x->tunnel as we delete x xfrm: also call xfrm_state_delete_tunnel at destroy time for states that were never added include/net/xfrm.h | 1 - net/ipv4/ipcomp.c | 2 ++ net/ipv6/ipcomp6.c | 2 ++ net/ipv6/xfrm6_tunnel.c | 2 +- net/xfrm/xfrm_ipcomp.c | 1 - net/xfrm/xfrm_state.c | 20 +++++++++----------- 6 files changed, 14 insertions(+), 14 deletions(-) -- 2.25.1

2 3

[PATCH OLK-6.6] net/sched: sch_qfq: Fix null-deref in agg_dequeue
by Dong Chenchen 30 Jan '26

30 Jan '26

From: Xiang Mei <xmei5(a)asu.edu> mainline inclusion from mainline-v6.16-rc6 commit dd831ac8221e691e9e918585b1003c7071df0379 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/7786 CVE: CVE-2025-40083 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- To prevent a potential crash in agg_dequeue (net/sched/sch_qfq.c) when cl->qdisc->ops->peek(cl->qdisc) returns NULL, we check the return value before using it, similar to the existing approach in sch_hfsc.c. To avoid code duplication, the following changes are made: 1. Changed qdisc_warn_nonwc(include/net/pkt_sched.h) into a static inline function. 2. Moved qdisc_peek_len from net/sched/sch_hfsc.c to include/net/pkt_sched.h so that sch_qfq can reuse it. 3. Applied qdisc_peek_len in agg_dequeue to avoid crashing. Signed-off-by: Xiang Mei <xmei5(a)asu.edu> Reviewed-by: Cong Wang <xiyou.wangcong(a)gmail.com> Link: https://patch.msgid.link/20250705212143.3982664-1-xmei5@asu.edu Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- include/net/pkt_sched.h | 25 ++++++++++++++++++++++++- net/sched/sch_api.c | 10 ---------- net/sched/sch_hfsc.c | 16 ---------------- net/sched/sch_qfq.c | 2 +- 4 files changed, 25 insertions(+), 28 deletions(-) diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 15960564e0c3..4d72d24b1f33 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -112,7 +112,6 @@ struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct netlink_ext_ack *extack); void qdisc_put_rtab(struct qdisc_rate_table *tab); void qdisc_put_stab(struct qdisc_size_table *tab); -void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc); bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, struct net_device *dev, struct netdev_queue *txq, spinlock_t *root_lock, bool validate); @@ -306,4 +305,28 @@ static inline bool tc_qdisc_stats_dump(struct Qdisc *sch, return true; } +static inline void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc) +{ + if (!(qdisc->flags & TCQ_F_WARN_NONWC)) { + pr_warn("%s: %s qdisc %X: is non-work-conserving?\n", + txt, qdisc->ops->id, qdisc->handle >> 16); + qdisc->flags |= TCQ_F_WARN_NONWC; + } +} + +static inline unsigned int qdisc_peek_len(struct Qdisc *sch) +{ + struct sk_buff *skb; + unsigned int len; + + skb = sch->ops->peek(sch); + if (unlikely(skb == NULL)) { + qdisc_warn_nonwc("qdisc_peek_len", sch); + return 0; + } + len = qdisc_pkt_len(skb); + + return len; +} + #endif diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 13055d6069b3..ff7bad762496 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -599,16 +599,6 @@ void __qdisc_calculate_pkt_len(struct sk_buff *skb, qdisc_skb_cb(skb)->pkt_len = pkt_len; } -void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc) -{ - if (!(qdisc->flags & TCQ_F_WARN_NONWC)) { - pr_warn("%s: %s qdisc %X: is non-work-conserving?\n", - txt, qdisc->ops->id, qdisc->handle >> 16); - qdisc->flags |= TCQ_F_WARN_NONWC; - } -} -EXPORT_SYMBOL(qdisc_warn_nonwc); - static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer) { struct qdisc_watchdog *wd = container_of(timer, struct qdisc_watchdog, diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index afcb83d469ff..751b1e2c35b3 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -835,22 +835,6 @@ update_vf(struct hfsc_class *cl, unsigned int len, u64 cur_time) } } -static unsigned int -qdisc_peek_len(struct Qdisc *sch) -{ - struct sk_buff *skb; - unsigned int len; - - skb = sch->ops->peek(sch); - if (unlikely(skb == NULL)) { - qdisc_warn_nonwc("qdisc_peek_len", sch); - return 0; - } - len = qdisc_pkt_len(skb); - - return len; -} - static void hfsc_adjust_levels(struct hfsc_class *cl) { diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 042200066a79..a9db57d29739 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -1002,7 +1002,7 @@ static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg, if (cl->qdisc->q.qlen == 0) /* no more packets, remove from list */ list_del_init(&cl->alist); - else if (cl->deficit < qdisc_pkt_len(cl->qdisc->ops->peek(cl->qdisc))) { + else if (cl->deficit < qdisc_peek_len(cl->qdisc)) { cl->deficit += agg->lmax; list_move_tail(&cl->alist, &agg->active); } -- 2.25.1

2 1