- Kernel - mailweb.openeuler.org

[PATCH OLK-5.10] rtnetlink: Allocate vfinfo size for VF GUIDs when supported
by Wang Liang 21 Aug '25

21 Aug '25

From: Mark Zhang <markzhang(a)nvidia.com> stable inclusion from stable-v5.10.236 commit 0f5489707cf528f9df2f39a3045c1ee713ec90e7 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IC1QR5 CVE: CVE-2025-22075 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 23f00807619d15063d676218f36c5dfeda1eb420 ] Commit 30aad41721e0 ("net/core: Add support for getting VF GUIDs") added support for getting VF port and node GUIDs in netlink ifinfo messages, but their size was not taken into consideration in the function that allocates the netlink message, causing the following warning when a netlink message is filled with many VF port and node GUIDs: # echo 64 > /sys/bus/pci/devices/0000\:08\:00.0/sriov_numvfs # ip link show dev ib0 RTNETLINK answers: Message too long Cannot send link get request: Message too long Kernel warning: ------------[ cut here ]------------ WARNING: CPU: 2 PID: 1930 at net/core/rtnetlink.c:4151 rtnl_getlink+0x586/0x5a0 Modules linked in: xt_conntrack xt_MASQUERADE nfnetlink xt_addrtype iptable_nat nf_nat br_netfilter overlay mlx5_ib macsec mlx5_core tls rpcrdma rdma_ucm ib_uverbs ib_iser libiscsi scsi_transport_iscsi ib_umad rdma_cm iw_cm ib_ipoib fuse ib_cm ib_core CPU: 2 UID: 0 PID: 1930 Comm: ip Not tainted 6.14.0-rc2+ #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:rtnl_getlink+0x586/0x5a0 Code: cb 82 e8 3d af 0a 00 4d 85 ff 0f 84 08 ff ff ff 4c 89 ff 41 be ea ff ff ff e8 66 63 5b ff 49 c7 07 80 4f cb 82 e9 36 fc ff ff <0f> 0b e9 16 fe ff ff e8 de a0 56 00 66 66 2e 0f 1f 84 00 00 00 00 RSP: 0018:ffff888113557348 EFLAGS: 00010246 RAX: 00000000ffffffa6 RBX: ffff88817e87aa34 RCX: dffffc0000000000 RDX: 0000000000000003 RSI: 0000000000000000 RDI: ffff88817e87afb8 RBP: 0000000000000009 R08: ffffffff821f44aa R09: 0000000000000000 R10: ffff8881260f79a8 R11: ffff88817e87af00 R12: ffff88817e87aa00 R13: ffffffff8563d300 R14: 00000000ffffffa6 R15: 00000000ffffffff FS: 00007f63a5dbf280(0000) GS:ffff88881ee00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f63a5ba4493 CR3: 00000001700fe002 CR4: 0000000000772eb0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <TASK> ? __warn+0xa5/0x230 ? rtnl_getlink+0x586/0x5a0 ? report_bug+0x22d/0x240 ? handle_bug+0x53/0xa0 ? exc_invalid_op+0x14/0x50 ? asm_exc_invalid_op+0x16/0x20 ? skb_trim+0x6a/0x80 ? rtnl_getlink+0x586/0x5a0 ? __pfx_rtnl_getlink+0x10/0x10 ? rtnetlink_rcv_msg+0x1e5/0x860 ? __pfx___mutex_lock+0x10/0x10 ? rcu_is_watching+0x34/0x60 ? __pfx_lock_acquire+0x10/0x10 ? stack_trace_save+0x90/0xd0 ? filter_irq_stacks+0x1d/0x70 ? kasan_save_stack+0x30/0x40 ? kasan_save_stack+0x20/0x40 ? kasan_save_track+0x10/0x30 rtnetlink_rcv_msg+0x21c/0x860 ? entry_SYSCALL_64_after_hwframe+0x76/0x7e ? __pfx_rtnetlink_rcv_msg+0x10/0x10 ? arch_stack_walk+0x9e/0xf0 ? rcu_is_watching+0x34/0x60 ? lock_acquire+0xd5/0x410 ? rcu_is_watching+0x34/0x60 netlink_rcv_skb+0xe0/0x210 ? __pfx_rtnetlink_rcv_msg+0x10/0x10 ? __pfx_netlink_rcv_skb+0x10/0x10 ? rcu_is_watching+0x34/0x60 ? __pfx___netlink_lookup+0x10/0x10 ? lock_release+0x62/0x200 ? netlink_deliver_tap+0xfd/0x290 ? rcu_is_watching+0x34/0x60 ? lock_release+0x62/0x200 ? netlink_deliver_tap+0x95/0x290 netlink_unicast+0x31f/0x480 ? __pfx_netlink_unicast+0x10/0x10 ? rcu_is_watching+0x34/0x60 ? lock_acquire+0xd5/0x410 netlink_sendmsg+0x369/0x660 ? lock_release+0x62/0x200 ? __pfx_netlink_sendmsg+0x10/0x10 ? import_ubuf+0xb9/0xf0 ? __import_iovec+0x254/0x2b0 ? lock_release+0x62/0x200 ? __pfx_netlink_sendmsg+0x10/0x10 ____sys_sendmsg+0x559/0x5a0 ? __pfx_____sys_sendmsg+0x10/0x10 ? __pfx_copy_msghdr_from_user+0x10/0x10 ? rcu_is_watching+0x34/0x60 ? do_read_fault+0x213/0x4a0 ? rcu_is_watching+0x34/0x60 ___sys_sendmsg+0xe4/0x150 ? __pfx____sys_sendmsg+0x10/0x10 ? do_fault+0x2cc/0x6f0 ? handle_pte_fault+0x2e3/0x3d0 ? __pfx_handle_pte_fault+0x10/0x10 ? preempt_count_sub+0x14/0xc0 ? __down_read_trylock+0x150/0x270 ? __handle_mm_fault+0x404/0x8e0 ? __pfx___handle_mm_fault+0x10/0x10 ? lock_release+0x62/0x200 ? __rcu_read_unlock+0x65/0x90 ? rcu_is_watching+0x34/0x60 __sys_sendmsg+0xd5/0x150 ? __pfx___sys_sendmsg+0x10/0x10 ? __up_read+0x192/0x480 ? lock_release+0x62/0x200 ? __rcu_read_unlock+0x65/0x90 ? rcu_is_watching+0x34/0x60 do_syscall_64+0x6d/0x140 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f63a5b13367 Code: 0e 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b9 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 89 54 24 1c 48 89 74 24 10 RSP: 002b:00007fff8c726bc8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000067b687c2 RCX: 00007f63a5b13367 RDX: 0000000000000000 RSI: 00007fff8c726c30 RDI: 0000000000000004 RBP: 00007fff8c726cb8 R08: 0000000000000000 R09: 0000000000000034 R10: 00007fff8c726c7c R11: 0000000000000246 R12: 0000000000000001 R13: 0000000000000000 R14: 00007fff8c726cd0 R15: 00007fff8c726cd0 </TASK> irq event stamp: 0 hardirqs last enabled at (0): [<0000000000000000>] 0x0 hardirqs last disabled at (0): [<ffffffff813f9e58>] copy_process+0xd08/0x2830 softirqs last enabled at (0): [<ffffffff813f9e58>] copy_process+0xd08/0x2830 softirqs last disabled at (0): [<0000000000000000>] 0x0 ---[ end trace 0000000000000000 ]--- Thus, when calculating ifinfo message size, take VF GUIDs sizes into account when supported. Fixes: 30aad41721e0 ("net/core: Add support for getting VF GUIDs") Signed-off-by: Mark Zhang <markzhang(a)nvidia.com> Reviewed-by: Maher Sanalla <msanalla(a)nvidia.com> Signed-off-by: Mark Bloch <mbloch(a)nvidia.com> Reviewed-by: Sabrina Dubroca <sd(a)queasysnail.net> Link: https://patch.msgid.link/20250325090226.749730-1-mbloch@nvidia.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wang Liang <wangliang74(a)huawei.com> --- net/core/rtnetlink.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 21d11f5b9af3..d95f0a8efe20 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -950,6 +950,9 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, /* IFLA_VF_STATS_TX_DROPPED */ nla_total_size_64bit(sizeof(__u64))); } + if (dev->netdev_ops->ndo_get_vf_guid) + size += num_vfs * 2 * + nla_total_size(sizeof(struct ifla_vf_guid)); return size; } else return 0; -- 2.33.0

2 1

[PATCH OLK-5.10] net_sched: hfsc: Fix a UAF vulnerability in class handling
by Wang Liang 21 Aug '25

21 Aug '25

From: Cong Wang <xiyou.wangcong(a)gmail.com> stable inclusion from stable-v5.10.237 commit 39b9095dd3b55d9b2743df038c32138efa34a9de category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IC5D95 CVE: CVE-2025-37797 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 3df275ef0a6ae181e8428a6589ef5d5231e58b5c ] This patch fixes a Use-After-Free vulnerability in the HFSC qdisc class handling. The issue occurs due to a time-of-check/time-of-use condition in hfsc_change_class() when working with certain child qdiscs like netem or codel. The vulnerability works as follows: 1. hfsc_change_class() checks if a class has packets (q.qlen != 0) 2. It then calls qdisc_peek_len(), which for certain qdiscs (e.g., codel, netem) might drop packets and empty the queue 3. The code continues assuming the queue is still non-empty, adding the class to vttree 4. This breaks HFSC scheduler assumptions that only non-empty classes are in vttree 5. Later, when the class is destroyed, this can lead to a Use-After-Free The fix adds a second queue length check after qdisc_peek_len() to verify the queue wasn't emptied. Fixes: 21f4d5cc25ec ("net_sched/hfsc: fix curve activation in hfsc_change_class()") Reported-by: Gerrard Tai <gerrard.tai(a)starlabs.sg> Reviewed-by: Konstantin Khlebnikov <koct9i(a)gmail.com> Signed-off-by: Cong Wang <xiyou.wangcong(a)gmail.com> Reviewed-by: Jamal Hadi Salim <jhs(a)mojatatu.com> Link: https://patch.msgid.link/20250417184732.943057-2-xiyou.wangcong@gmail.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wang Liang <wangliang74(a)huawei.com> --- net/sched/sch_hfsc.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 79a470f57fc5..2454bafbbb11 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -967,6 +967,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl != NULL) { int old_flags; + int len = 0; if (parentid) { if (cl->cl_parent && @@ -997,9 +998,13 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (usc != NULL) hfsc_change_usc(cl, usc, cur_time); + if (cl->qdisc->q.qlen != 0) + len = qdisc_peek_len(cl->qdisc); + /* Check queue length again since some qdisc implementations + * (e.g., netem/codel) might empty the queue during the peek + * operation. + */ if (cl->qdisc->q.qlen != 0) { - int len = qdisc_peek_len(cl->qdisc); - if (cl->cl_flags & HFSC_RSC) { if (old_flags & HFSC_RSC) update_ed(cl, len); -- 2.33.0

2 1

[PATCH OLK-5.10] tipc: fix null-ptr-deref when acquiring remote ip of ethernet bearer
by Wang Liang 21 Aug '25

21 Aug '25

From: Haixia Qu <hxqu(a)hillstonenet.com> stable inclusion from stable-v5.10.239 commit c2e17984752b9131061d1a2ca1199da2706337fd category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/ICK4S5 CVE: CVE-2025-38184 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit f82727adcf2992822e12198792af450a76ebd5ef ] The reproduction steps: 1. create a tun interface 2. enable l2 bearer 3. TIPC_NL_UDP_GET_REMOTEIP with media name set to tun tipc: Started in network mode tipc: Node identity 8af312d38a21, cluster identity 4711 tipc: Enabled bearer <eth:syz_tun>, priority 1 Oops: general protection fault KASAN: null-ptr-deref in range CPU: 1 UID: 1000 PID: 559 Comm: poc Not tainted 6.16.0-rc1+ #117 PREEMPT Hardware name: QEMU Ubuntu 24.04 PC RIP: 0010:tipc_udp_nl_dump_remoteip+0x4a4/0x8f0 the ub was in fact a struct dev. when bid != 0 && skip_cnt != 0, bearer_list[bid] may be NULL or other media when other thread changes it. fix this by checking media_id. Fixes: 832629ca5c313 ("tipc: add UDP remoteip dump to netlink API") Signed-off-by: Haixia Qu <hxqu(a)hillstonenet.com> Reviewed-by: Tung Nguyen <tung.quang.nguyen(a)est.tech> Link: https://patch.msgid.link/20250617055624.2680-1-hxqu@hillstonenet.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wang Liang <wangliang74(a)huawei.com> --- net/tipc/udp_media.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 25e733919131..881f4c160dbf 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -481,7 +481,7 @@ int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb) rtnl_lock(); b = tipc_bearer_find(net, bname); - if (!b) { + if (!b || b->bcast_addr.media_id != TIPC_MEDIA_TYPE_UDP) { rtnl_unlock(); return -EINVAL; } @@ -492,7 +492,7 @@ int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb) rtnl_lock(); b = rtnl_dereference(tn->bearer_list[bid]); - if (!b) { + if (!b || b->bcast_addr.media_id != TIPC_MEDIA_TYPE_UDP) { rtnl_unlock(); return -EINVAL; } -- 2.33.0

2 1

[PATCH OLK-5.10 0/2] CVE-2025-38052
by Wang Liang 21 Aug '25

21 Aug '25

Charalampos Mitrodimas (1): net: tipc: fix refcount warning in tipc_aead_encrypt Wang Liang (1): net/tipc: fix slab-use-after-free Read in tipc_aead_encrypt_done net/tipc/crypto.c | 9 +++++++++ 1 file changed, 9 insertions(+) -- 2.33.0

2 3

[PATCH OLK-5.10] net: clear the dst when changing skb protocol
by Wang Liang 21 Aug '25

21 Aug '25

From: Jakub Kicinski <kuba(a)kernel.org> mainline inclusion from mainline-v6.16-rc2 commit ba9db6f907ac02215e30128770f85fbd7db2fcf9 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/ICK4OH CVE: CVE-2025-38192 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- A not-so-careful NAT46 BPF program can crash the kernel if it indiscriminately flips ingress packets from v4 to v6: BUG: kernel NULL pointer dereference, address: 0000000000000000 ip6_rcv_core (net/ipv6/ip6_input.c:190:20) ipv6_rcv (net/ipv6/ip6_input.c:306:8) process_backlog (net/core/dev.c:6186:4) napi_poll (net/core/dev.c:6906:9) net_rx_action (net/core/dev.c:7028:13) do_softirq (kernel/softirq.c:462:3) netif_rx (net/core/dev.c:5326:3) dev_loopback_xmit (net/core/dev.c:4015:2) ip_mc_finish_output (net/ipv4/ip_output.c:363:8) NF_HOOK (./include/linux/netfilter.h:314:9) ip_mc_output (net/ipv4/ip_output.c:400:5) dst_output (./include/net/dst.h:459:9) ip_local_out (net/ipv4/ip_output.c:130:9) ip_send_skb (net/ipv4/ip_output.c:1496:8) udp_send_skb (net/ipv4/udp.c:1040:8) udp_sendmsg (net/ipv4/udp.c:1328:10) The output interface has a 4->6 program attached at ingress. We try to loop the multicast skb back to the sending socket. Ingress BPF runs as part of netif_rx(), pushes a valid v6 hdr and changes skb->protocol to v6. We enter ip6_rcv_core which tries to use skb_dst(). But the dst is still an IPv4 one left after IPv4 mcast output. Clear the dst in all BPF helpers which change the protocol. Try to preserve metadata dsts, those may carry non-routing metadata. Cc: stable(a)vger.kernel.org Reviewed-by: Maciej Żenczykowski <maze(a)google.com> Acked-by: Daniel Borkmann <daniel(a)iogearbox.net> Fixes: d219df60a70e ("bpf: Add ipip6 and ip6ip decap support for bpf_skb_adjust_room()") Fixes: 1b00e0dfe7d0 ("bpf: update skb->protocol in bpf_skb_net_grow") Fixes: 6578171a7ff0 ("bpf: add bpf_skb_change_proto helper") Reviewed-by: Willem de Bruijn <willemb(a)google.com> Link: https://patch.msgid.link/20250610001245.1981782-1-kuba@kernel.org Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: net/core/filter.c [conflicts due to not merge d219df60a70e ("bpf: Add ipip6 and ip6ip decap support for bpf_skb_adjust_room()")] Signed-off-by: Wang Liang <wangliang74(a)huawei.com> --- net/core/filter.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/net/core/filter.c b/net/core/filter.c index eb15cc793fbf..d3e64273b3c4 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3201,6 +3201,13 @@ static const struct bpf_func_proto bpf_skb_vlan_pop_proto = { .arg1_type = ARG_PTR_TO_CTX, }; +static void bpf_skb_change_protocol(struct sk_buff *skb, u16 proto) +{ + skb->protocol = htons(proto); + if (skb_valid_dst(skb)) + skb_dst_drop(skb); +} + static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len) { /* Caller already did skb_cow() with len as headroom, @@ -3306,7 +3313,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) shinfo->gso_segs = 0; } - skb->protocol = htons(ETH_P_IPV6); + bpf_skb_change_protocol(skb, ETH_P_IPV6); skb_clear_hash(skb); return 0; @@ -3345,7 +3352,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) shinfo->gso_segs = 0; } - skb->protocol = htons(ETH_P_IP); + bpf_skb_change_protocol(skb, ETH_P_IP); skb_clear_hash(skb); return 0; @@ -3523,10 +3530,10 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff, /* Match skb->protocol to new outer l3 protocol */ if (skb->protocol == htons(ETH_P_IP) && flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) - skb->protocol = htons(ETH_P_IPV6); + bpf_skb_change_protocol(skb, ETH_P_IPV6); else if (skb->protocol == htons(ETH_P_IPV6) && flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4) - skb->protocol = htons(ETH_P_IP); + bpf_skb_change_protocol(skb, ETH_P_IP); } if (skb_is_gso(skb)) { -- 2.33.0

2 1

[PATCH OLK-5.10] tipc: Fix use-after-free in tipc_conn_close().
by Wang Liang 21 Aug '25

21 Aug '25

From: Kuniyuki Iwashima <kuniyu(a)google.com> stable inclusion from stable-v5.10.240 commit 15a6f4971e2f157d57e09ea748d1fbc714277aa4 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/ICOXOS CVE: CVE-2025-38464 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 667eeab4999e981c96b447a4df5f20bdf5c26f13 ] syzbot reported a null-ptr-deref in tipc_conn_close() during netns dismantle. [0] tipc_topsrv_stop() iterates tipc_net(net)->topsrv->conn_idr and calls tipc_conn_close() for each tipc_conn. The problem is that tipc_conn_close() is called after releasing the IDR lock. At the same time, there might be tipc_conn_recv_work() running and it could call tipc_conn_close() for the same tipc_conn and release its last ->kref. Once we release the IDR lock in tipc_topsrv_stop(), there is no guarantee that the tipc_conn is alive. Let's hold the ref before releasing the lock and put the ref after tipc_conn_close() in tipc_topsrv_stop(). [0]: BUG: KASAN: use-after-free in tipc_conn_close+0x122/0x140 net/tipc/topsrv.c:165 Read of size 8 at addr ffff888099305a08 by task kworker/u4:3/435 CPU: 0 PID: 435 Comm: kworker/u4:3 Not tainted 4.19.204-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: netns cleanup_net Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1fc/0x2ef lib/dump_stack.c:118 print_address_description.cold+0x54/0x219 mm/kasan/report.c:256 kasan_report_error.cold+0x8a/0x1b9 mm/kasan/report.c:354 kasan_report mm/kasan/report.c:412 [inline] __asan_report_load8_noabort+0x88/0x90 mm/kasan/report.c:433 tipc_conn_close+0x122/0x140 net/tipc/topsrv.c:165 tipc_topsrv_stop net/tipc/topsrv.c:701 [inline] tipc_topsrv_exit_net+0x27b/0x5c0 net/tipc/topsrv.c:722 ops_exit_list+0xa5/0x150 net/core/net_namespace.c:153 cleanup_net+0x3b4/0x8b0 net/core/net_namespace.c:553 process_one_work+0x864/0x1570 kernel/workqueue.c:2153 worker_thread+0x64c/0x1130 kernel/workqueue.c:2296 kthread+0x33f/0x460 kernel/kthread.c:259 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:415 Allocated by task 23: kmem_cache_alloc_trace+0x12f/0x380 mm/slab.c:3625 kmalloc include/linux/slab.h:515 [inline] kzalloc include/linux/slab.h:709 [inline] tipc_conn_alloc+0x43/0x4f0 net/tipc/topsrv.c:192 tipc_topsrv_accept+0x1b5/0x280 net/tipc/topsrv.c:470 process_one_work+0x864/0x1570 kernel/workqueue.c:2153 worker_thread+0x64c/0x1130 kernel/workqueue.c:2296 kthread+0x33f/0x460 kernel/kthread.c:259 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:415 Freed by task 23: __cache_free mm/slab.c:3503 [inline] kfree+0xcc/0x210 mm/slab.c:3822 tipc_conn_kref_release net/tipc/topsrv.c:150 [inline] kref_put include/linux/kref.h:70 [inline] conn_put+0x2cd/0x3a0 net/tipc/topsrv.c:155 process_one_work+0x864/0x1570 kernel/workqueue.c:2153 worker_thread+0x64c/0x1130 kernel/workqueue.c:2296 kthread+0x33f/0x460 kernel/kthread.c:259 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:415 The buggy address belongs to the object at ffff888099305a00 which belongs to the cache kmalloc-512 of size 512 The buggy address is located 8 bytes inside of 512-byte region [ffff888099305a00, ffff888099305c00) The buggy address belongs to the page: page:ffffea000264c140 count:1 mapcount:0 mapping:ffff88813bff0940 index:0x0 flags: 0xfff00000000100(slab) raw: 00fff00000000100 ffffea00028b6b88 ffffea0002cd2b08 ffff88813bff0940 raw: 0000000000000000 ffff888099305000 0000000100000006 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888099305900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888099305980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff888099305a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff888099305a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888099305b00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: c5fa7b3cf3cb ("tipc: introduce new TIPC server infrastructure") Reported-by: syzbot+d333febcf8f4bc5f6110(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=27169a847a70550d17be Signed-off-by: Kuniyuki Iwashima <kuniyu(a)google.com> Reviewed-by: Tung Nguyen <tung.quang.nguyen(a)est.tech> Link: https://patch.msgid.link/20250702014350.692213-1-kuniyu@google.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wang Liang <wangliang74(a)huawei.com> --- net/tipc/topsrv.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 89d8a2bd30cd..d914c5eb2517 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -699,8 +699,10 @@ static void tipc_topsrv_stop(struct net *net) for (id = 0; srv->idr_in_use; id++) { con = idr_find(&srv->conn_idr, id); if (con) { + conn_get(con); spin_unlock_bh(&srv->idr_lock); tipc_conn_close(con); + conn_put(con); spin_lock_bh(&srv->idr_lock); } } -- 2.33.0

2 1

[PATCH OLK-5.10] net_sched: sch_sfq: fix a potential crash on gso_skb handling
by Wang Liang 21 Aug '25

21 Aug '25

From: Eric Dumazet <edumazet(a)google.com> stable inclusion from stable-v5.10.239 commit b44f791f27b14c9eb6b907fbe51f2ba8bec32085 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/ICJTA4 CVE: CVE-2025-38115 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 82ffbe7776d0ac084031f114167712269bf3d832 ] SFQ has an assumption of always being able to queue at least one packet. However, after the blamed commit, sch->q.len can be inflated by packets in sch->gso_skb, and an enqueue() on an empty SFQ qdisc can be followed by an immediate drop. Fix sfq_drop() to properly clear q->tail in this situation. Tested: ip netns add lb ip link add dev to-lb type veth peer name in-lb netns lb ethtool -K to-lb tso off # force qdisc to requeue gso_skb ip netns exec lb ethtool -K in-lb gro on # enable NAPI ip link set dev to-lb up ip -netns lb link set dev in-lb up ip addr add dev to-lb 192.168.20.1/24 ip -netns lb addr add dev in-lb 192.168.20.2/24 tc qdisc replace dev to-lb root sfq limit 100 ip netns exec lb netserver netperf -H 192.168.20.2 -l 100 & netperf -H 192.168.20.2 -l 100 & netperf -H 192.168.20.2 -l 100 & netperf -H 192.168.20.2 -l 100 & Fixes: a53851e2c321 ("net: sched: explicit locking in gso_cpu fallback") Reported-by: Marcus Wichelmann <marcus.wichelmann(a)hetzner-cloud.de> Closes: https://lore.kernel.org/netdev/9da42688-bfaa-4364-8797-e9271f3bdaef@hetzner… Signed-off-by: Eric Dumazet <edumazet(a)google.com> Reviewed-by: Toke Høiland-Jørgensen <toke(a)redhat.com> Link: https://patch.msgid.link/20250606165127.3629486-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wang Liang <wangliang74(a)huawei.com> --- net/sched/sch_sfq.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 066754a18569..6b65c5efb378 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -317,7 +317,10 @@ static unsigned int sfq_drop(struct Qdisc *sch, struct sk_buff **to_free) /* It is difficult to believe, but ALL THE SLOTS HAVE LENGTH 1. */ x = q->tail->next; slot = &q->slots[x]; - q->tail->next = slot->next; + if (slot->next == x) + q->tail = NULL; /* no more active slots */ + else + q->tail->next = slot->next; q->ht[slot->hash] = SFQ_EMPTY_SLOT; goto drop; } -- 2.33.0

2 1

[PATCH OLK-5.10] net: fix udp gso skb_segment after pull from frag_list
by Wang Liang 21 Aug '25

21 Aug '25

From: Shiming Cheng <shiming.cheng(a)mediatek.com> mainline inclusion from mainline-v6.16-rc1 commit 3382a1ed7f778db841063f5d7e317ac55f9e7f72 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/ICJTGK CVE: CVE-2025-38124 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Commit a1e40ac5b5e9 ("net: gso: fix udp gso fraglist segmentation after pull from frag_list") detected invalid geometry in frag_list skbs and redirects them from skb_segment_list to more robust skb_segment. But some packets with modified geometry can also hit bugs in that code. We don't know how many such cases exist. Addressing each one by one also requires touching the complex skb_segment code, which risks introducing bugs for other types of skbs. Instead, linearize all these packets that fail the basic invariants on gso fraglist skbs. That is more robust. If only part of the fraglist payload is pulled into head_skb, it will always cause exception when splitting skbs by skb_segment. For detailed call stack information, see below. Valid SKB_GSO_FRAGLIST skbs - consist of two or more segments - the head_skb holds the protocol headers plus first gso_size - one or more frag_list skbs hold exactly one segment - all but the last must be gso_size Optional datapath hooks such as NAT and BPF (bpf_skb_pull_data) can modify fraglist skbs, breaking these invariants. In extreme cases they pull one part of data into skb linear. For UDP, this causes three payloads with lengths of (11,11,10) bytes were pulled tail to become (12,10,10) bytes. The skbs no longer meets the above SKB_GSO_FRAGLIST conditions because payload was pulled into head_skb, it needs to be linearized before pass to regular skb_segment. skb_segment+0xcd0/0xd14 __udp_gso_segment+0x334/0x5f4 udp4_ufo_fragment+0x118/0x15c inet_gso_segment+0x164/0x338 skb_mac_gso_segment+0xc4/0x13c __skb_gso_segment+0xc4/0x124 validate_xmit_skb+0x9c/0x2c0 validate_xmit_skb_list+0x4c/0x80 sch_direct_xmit+0x70/0x404 __dev_queue_xmit+0x64c/0xe5c neigh_resolve_output+0x178/0x1c4 ip_finish_output2+0x37c/0x47c __ip_finish_output+0x194/0x240 ip_finish_output+0x20/0xf4 ip_output+0x100/0x1a0 NF_HOOK+0xc4/0x16c ip_forward+0x314/0x32c ip_rcv+0x90/0x118 __netif_receive_skb+0x74/0x124 process_backlog+0xe8/0x1a4 __napi_poll+0x5c/0x1f8 net_rx_action+0x154/0x314 handle_softirqs+0x154/0x4b8 [118.376811] [C201134] rxq0_pus: [name:bug&]kernel BUG at net/core/skbuff.c:4278! [118.376829] [C201134] rxq0_pus: [name:traps&]Internal error: Oops - BUG: 00000000f2000800 [#1] PREEMPT SMP [118.470774] [C201134] rxq0_pus: [name:mrdump&]Kernel Offset: 0x178cc00000 from 0xffffffc008000000 [118.470810] [C201134] rxq0_pus: [name:mrdump&]PHYS_OFFSET: 0x40000000 [118.470827] [C201134] rxq0_pus: [name:mrdump&]pstate: 60400005 (nZCv daif +PAN -UAO) [118.470848] [C201134] rxq0_pus: [name:mrdump&]pc : [0xffffffd79598aefc] skb_segment+0xcd0/0xd14 [118.470900] [C201134] rxq0_pus: [name:mrdump&]lr : [0xffffffd79598a5e8] skb_segment+0x3bc/0xd14 [118.470928] [C201134] rxq0_pus: [name:mrdump&]sp : ffffffc008013770 Fixes: a1e40ac5b5e9 ("gso: fix udp gso fraglist segmentation after pull from frag_list") Signed-off-by: Shiming Cheng <shiming.cheng(a)mediatek.com> Reviewed-by: Willem de Bruijn <willemb(a)google.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Wang Liang <wangliang74(a)huawei.com> --- net/ipv4/udp_offload.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 9024c55db2a6..a910ae497fbc 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -269,6 +269,7 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, bool copy_dtor; __sum16 check; __be16 newlen; + int ret = 0; mss = skb_shinfo(gso_skb)->gso_size; if (gso_skb->len <= sizeof(*uh) + mss) @@ -291,6 +292,10 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, if (skb_pagelen(gso_skb) - sizeof(*uh) == skb_shinfo(gso_skb)->gso_size) return __udp_gso_segment_list(gso_skb, features, is_ipv6); + ret = __skb_linearize(gso_skb); + if (ret) + return ERR_PTR(ret); + /* Setup csum, as fraglist skips this in udp4_gro_receive. */ gso_skb->csum_start = skb_transport_header(gso_skb) - gso_skb->head; gso_skb->csum_offset = offsetof(struct udphdr, check); -- 2.33.0

2 1

[PATCH OLK-5.10] atm: Fix NULL pointer dereference
by Wang Liang 21 Aug '25

21 Aug '25

From: Minjoong Kim <pwn9uin(a)gmail.com> stable inclusion from stable-v5.10.236 commit 1505f9b720656b17865e4166ab002960162bf679 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IC1KBC CVE: CVE-2025-22018 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit bf2986fcf82a449441f9ee4335df19be19e83970 upstream. When MPOA_cache_impos_rcvd() receives the msg, it can trigger Null Pointer Dereference Vulnerability if both entry and holding_time are NULL. Because there is only for the situation where entry is NULL and holding_time exists, it can be passed when both entry and holding_time are NULL. If these are NULL, the entry will be passd to eg_cache_put() as parameter and it is referenced by entry->use code in it. kasan log: [ 3.316691] Oops: general protection fault, probably for non-canonical address 0xdffffc0000000006:I [ 3.317568] KASAN: null-ptr-deref in range [0x0000000000000030-0x0000000000000037] [ 3.318188] CPU: 3 UID: 0 PID: 79 Comm: ex Not tainted 6.14.0-rc2 #102 [ 3.318601] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 [ 3.319298] RIP: 0010:eg_cache_remove_entry+0xa5/0x470 [ 3.319677] Code: c1 f7 6e fd 48 c7 c7 00 7e 38 b2 e8 95 64 54 fd 48 c7 c7 40 7e 38 b2 48 89 ee e80 [ 3.321220] RSP: 0018:ffff88800583f8a8 EFLAGS: 00010006 [ 3.321596] RAX: 0000000000000006 RBX: ffff888005989000 RCX: ffffffffaecc2d8e [ 3.322112] RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000030 [ 3.322643] RBP: 0000000000000000 R08: 0000000000000000 R09: fffffbfff6558b88 [ 3.323181] R10: 0000000000000003 R11: 203a207972746e65 R12: 1ffff11000b07f15 [ 3.323707] R13: dffffc0000000000 R14: ffff888005989000 R15: ffff888005989068 [ 3.324185] FS: 000000001b6313c0(0000) GS:ffff88806d380000(0000) knlGS:0000000000000000 [ 3.325042] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 3.325545] CR2: 00000000004b4b40 CR3: 000000000248e000 CR4: 00000000000006f0 [ 3.326430] Call Trace: [ 3.326725] <TASK> [ 3.326927] ? die_addr+0x3c/0xa0 [ 3.327330] ? exc_general_protection+0x161/0x2a0 [ 3.327662] ? asm_exc_general_protection+0x26/0x30 [ 3.328214] ? vprintk_emit+0x15e/0x420 [ 3.328543] ? eg_cache_remove_entry+0xa5/0x470 [ 3.328910] ? eg_cache_remove_entry+0x9a/0x470 [ 3.329294] ? __pfx_eg_cache_remove_entry+0x10/0x10 [ 3.329664] ? console_unlock+0x107/0x1d0 [ 3.329946] ? __pfx_console_unlock+0x10/0x10 [ 3.330283] ? do_syscall_64+0xa6/0x1a0 [ 3.330584] ? entry_SYSCALL_64_after_hwframe+0x47/0x7f [ 3.331090] ? __pfx_prb_read_valid+0x10/0x10 [ 3.331395] ? down_trylock+0x52/0x80 [ 3.331703] ? vprintk_emit+0x15e/0x420 [ 3.331986] ? __pfx_vprintk_emit+0x10/0x10 [ 3.332279] ? down_trylock+0x52/0x80 [ 3.332527] ? _printk+0xbf/0x100 [ 3.332762] ? __pfx__printk+0x10/0x10 [ 3.333007] ? _raw_write_lock_irq+0x81/0xe0 [ 3.333284] ? __pfx__raw_write_lock_irq+0x10/0x10 [ 3.333614] msg_from_mpoad+0x1185/0x2750 [ 3.333893] ? __build_skb_around+0x27b/0x3a0 [ 3.334183] ? __pfx_msg_from_mpoad+0x10/0x10 [ 3.334501] ? __alloc_skb+0x1c0/0x310 [ 3.334809] ? __pfx___alloc_skb+0x10/0x10 [ 3.335283] ? _raw_spin_lock+0xe0/0xe0 [ 3.335632] ? finish_wait+0x8d/0x1e0 [ 3.335975] vcc_sendmsg+0x684/0xba0 [ 3.336250] ? __pfx_vcc_sendmsg+0x10/0x10 [ 3.336587] ? __pfx_autoremove_wake_function+0x10/0x10 [ 3.337056] ? fdget+0x176/0x3e0 [ 3.337348] __sys_sendto+0x4a2/0x510 [ 3.337663] ? __pfx___sys_sendto+0x10/0x10 [ 3.337969] ? ioctl_has_perm.constprop.0.isra.0+0x284/0x400 [ 3.338364] ? sock_ioctl+0x1bb/0x5a0 [ 3.338653] ? __rseq_handle_notify_resume+0x825/0xd20 [ 3.339017] ? __pfx_sock_ioctl+0x10/0x10 [ 3.339316] ? __pfx___rseq_handle_notify_resume+0x10/0x10 [ 3.339727] ? selinux_file_ioctl+0xa4/0x260 [ 3.340166] __x64_sys_sendto+0xe0/0x1c0 [ 3.340526] ? syscall_exit_to_user_mode+0x123/0x140 [ 3.340898] do_syscall_64+0xa6/0x1a0 [ 3.341170] entry_SYSCALL_64_after_hwframe+0x77/0x7f [ 3.341533] RIP: 0033:0x44a380 [ 3.341757] Code: 0f 1f 84 00 00 00 00 00 66 90 f3 0f 1e fa 41 89 ca 64 8b 04 25 18 00 00 00 85 c00 [ 3.343078] RSP: 002b:00007ffc1d404098 EFLAGS: 00000246 ORIG_RAX: 000000000000002c [ 3.343631] RAX: ffffffffffffffda RBX: 00007ffc1d404458 RCX: 000000000044a380 [ 3.344306] RDX: 000000000000019c RSI: 00007ffc1d4040b0 RDI: 0000000000000003 [ 3.344833] RBP: 00007ffc1d404260 R08: 0000000000000000 R09: 0000000000000000 [ 3.345381] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000001 [ 3.346015] R13: 00007ffc1d404448 R14: 00000000004c17d0 R15: 0000000000000001 [ 3.346503] </TASK> [ 3.346679] Modules linked in: [ 3.346956] ---[ end trace 0000000000000000 ]--- [ 3.347315] RIP: 0010:eg_cache_remove_entry+0xa5/0x470 [ 3.347737] Code: c1 f7 6e fd 48 c7 c7 00 7e 38 b2 e8 95 64 54 fd 48 c7 c7 40 7e 38 b2 48 89 ee e80 [ 3.349157] RSP: 0018:ffff88800583f8a8 EFLAGS: 00010006 [ 3.349517] RAX: 0000000000000006 RBX: ffff888005989000 RCX: ffffffffaecc2d8e [ 3.350103] RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000030 [ 3.350610] RBP: 0000000000000000 R08: 0000000000000000 R09: fffffbfff6558b88 [ 3.351246] R10: 0000000000000003 R11: 203a207972746e65 R12: 1ffff11000b07f15 [ 3.351785] R13: dffffc0000000000 R14: ffff888005989000 R15: ffff888005989068 [ 3.352404] FS: 000000001b6313c0(0000) GS:ffff88806d380000(0000) knlGS:0000000000000000 [ 3.353099] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 3.353544] CR2: 00000000004b4b40 CR3: 000000000248e000 CR4: 00000000000006f0 [ 3.354072] note: ex[79] exited with irqs disabled [ 3.354458] note: ex[79] exited with preempt_count 1 Signed-off-by: Minjoong Kim <pwn9uin(a)gmail.com> Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reviewed-by: Simon Horman <horms(a)kernel.org> Link: https://patch.msgid.link/20250322105200.14981-1-pwn9uin@gmail.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Wang Liang <wangliang74(a)huawei.com> --- net/atm/mpc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 033871e718a3..583c27131b7d 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -1314,6 +1314,8 @@ static void MPOA_cache_impos_rcvd(struct k_message *msg, holding_time = msg->content.eg_info.holding_time; dprintk("(%s) entry = %p, holding_time = %u\n", mpc->dev->name, entry, holding_time); + if (entry == NULL && !holding_time) + return; if (entry == NULL && holding_time) { entry = mpc->eg_ops->add_entry(msg, mpc); mpc->eg_ops->put(entry); -- 2.33.0

2 1

[PATCH OLK-5.10] udp: Fix memory accounting leak.
by Wang Liang 21 Aug '25

21 Aug '25

From: Kuniyuki Iwashima <kuniyu(a)amazon.com> mainline inclusion from mainline-v6.15-rc1 commit df207de9d9e7a4d92f8567e2c539d9c8c12fd99d category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IC4CD8 CVE: CVE-2025-22058 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Matt Dowling reported a weird UDP memory usage issue. Under normal operation, the UDP memory usage reported in /proc/net/sockstat remains close to zero. However, it occasionally spiked to 524,288 pages and never dropped. Moreover, the value doubled when the application was terminated. Finally, it caused intermittent packet drops. We can reproduce the issue with the script below [0]: 1. /proc/net/sockstat reports 0 pages # cat /proc/net/sockstat | grep UDP: UDP: inuse 1 mem 0 2. Run the script till the report reaches 524,288 # python3 test.py & sleep 5 # cat /proc/net/sockstat | grep UDP: UDP: inuse 3 mem 524288 <-- (INT_MAX + 1) >> PAGE_SHIFT 3. Kill the socket and confirm the number never drops # pkill python3 && sleep 5 # cat /proc/net/sockstat | grep UDP: UDP: inuse 1 mem 524288 4. (necessary since v6.0) Trigger proto_memory_pcpu_drain() # python3 test.py & sleep 1 && pkill python3 5. The number doubles # cat /proc/net/sockstat | grep UDP: UDP: inuse 1 mem 1048577 The application set INT_MAX to SO_RCVBUF, which triggered an integer overflow in udp_rmem_release(). When a socket is close()d, udp_destruct_common() purges its receive queue and sums up skb->truesize in the queue. This total is calculated and stored in a local unsigned integer variable. The total size is then passed to udp_rmem_release() to adjust memory accounting. However, because the function takes a signed integer argument, the total size can wrap around, causing an overflow. Then, the released amount is calculated as follows: 1) Add size to sk->sk_forward_alloc. 2) Round down sk->sk_forward_alloc to the nearest lower multiple of PAGE_SIZE and assign it to amount. 3) Subtract amount from sk->sk_forward_alloc. 4) Pass amount >> PAGE_SHIFT to __sk_mem_reduce_allocated(). When the issue occurred, the total in udp_destruct_common() was 2147484480 (INT_MAX + 833), which was cast to -2147482816 in udp_rmem_release(). At 1) sk->sk_forward_alloc is changed from 3264 to -2147479552, and 2) sets -2147479552 to amount. 3) reverts the wraparound, so we don't see a warning in inet_sock_destruct(). However, udp_memory_allocated ends up doubling at 4). Since commit 3cd3399dd7a8 ("net: implement per-cpu reserves for memory_allocated"), memory usage no longer doubles immediately after a socket is close()d because __sk_mem_reduce_allocated() caches the amount in udp_memory_per_cpu_fw_alloc. However, the next time a UDP socket receives a packet, the subtraction takes effect, causing UDP memory usage to double. This issue makes further memory allocation fail once the socket's sk->sk_rmem_alloc exceeds net.ipv4.udp_rmem_min, resulting in packet drops. To prevent this issue, let's use unsigned int for the calculation and call sk_forward_alloc_add() only once for the small delta. Note that first_packet_length() also potentially has the same problem. [0]: from socket import * SO_RCVBUFFORCE = 33 INT_MAX = (2 ** 31) - 1 s = socket(AF_INET, SOCK_DGRAM) s.bind(('', 0)) s.setsockopt(SOL_SOCKET, SO_RCVBUFFORCE, INT_MAX) c = socket(AF_INET, SOCK_DGRAM) c.connect(s.getsockname()) data = b'a' * 100 while True: c.send(data) Fixes: f970bd9e3a06 ("udp: implement memory accounting helpers") Reported-by: Matt Dowling <madowlin(a)amazon.com> Signed-off-by: Kuniyuki Iwashima <kuniyu(a)amazon.com> Reviewed-by: Willem de Bruijn <willemb(a)google.com> Link: https://patch.msgid.link/20250401184501.67377-3-kuniyu@amazon.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: net/ipv4/udp.c [conflicts due to not merge 5e6300e7b3a4 ("net: annotate data-races around sk->sk_forward_alloc"), conflicts due to not merge 100fdd1faf50 ("net: remove SK_MEM_QUANTUM and SK_MEM_QUANTUM_SHIFT")] Signed-off-by: Wang Liang <wangliang74(a)huawei.com> --- net/ipv4/udp.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 907be248689a..8190e4619c27 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1442,12 +1442,12 @@ static bool udp_skb_has_head_state(struct sk_buff *skb) } /* fully reclaim rmem/fwd memory allocated for skb */ -static void udp_rmem_release(struct sock *sk, int size, int partial, - bool rx_queue_lock_held) +static void udp_rmem_release(struct sock *sk, unsigned int size, + int partial, bool rx_queue_lock_held) { struct udp_sock *up = udp_sk(sk); struct sk_buff_head *sk_queue; - int amt; + unsigned int amt; if (likely(partial)) { up->forward_deficit += size; @@ -1467,10 +1467,8 @@ static void udp_rmem_release(struct sock *sk, int size, int partial, if (!rx_queue_lock_held) spin_lock(&sk_queue->lock); - - sk->sk_forward_alloc += size; - amt = (sk->sk_forward_alloc - partial) & ~(SK_MEM_QUANTUM - 1); - sk->sk_forward_alloc -= amt; + amt = (size + sk->sk_forward_alloc - partial) & ~(SK_MEM_QUANTUM - 1); + sk->sk_forward_alloc = sk->sk_forward_alloc + size - amt; if (amt) __sk_mem_reduce_allocated(sk, amt >> SK_MEM_QUANTUM_SHIFT); @@ -1654,7 +1652,7 @@ EXPORT_SYMBOL_GPL(skb_consume_udp); static struct sk_buff *__first_packet_length(struct sock *sk, struct sk_buff_head *rcvq, - int *total) + unsigned int *total) { struct sk_buff *skb; @@ -1687,8 +1685,8 @@ static int first_packet_length(struct sock *sk) { struct sk_buff_head *rcvq = &udp_sk(sk)->reader_queue; struct sk_buff_head *sk_queue = &sk->sk_receive_queue; + unsigned int total = 0; struct sk_buff *skb; - int total = 0; int res; spin_lock_bh(&rcvq->lock); -- 2.33.0

2 1