From 5bcd66e23b8b9335257036d534485921280aa80f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Oct 2024 08:02:29 +0000 Subject: [PATCH 1/5] netfilter: nf_reject_ipv6: fix potential crash in nf_send_reset6() mainline inclusion from mainline-v6.12-rc6 commit 4ed234fe793f27a3b151c43d2106df2ff0d81aac category: bugfix issue: #IBDSFS CVE: CVE-2024-50256 Signed-off-by: wukuan --------------------------------------- I got a syzbot report without a repro [1] crashing in nf_send_reset6() I think the issue is that dev->hard_header_len is zero, and we attempt later to push an Ethernet header. Use LL_MAX_HEADER, as other functions in net/ipv6/netfilter/nf_reject_ipv6.c. [1] skbuff: skb_under_panic: text:ffffffff89b1d008 len:74 put:14 head:ffff88803123aa00 data:ffff88803123a9f2 tail:0x3c end:0x140 dev:syz_tun kernel BUG at net/core/skbuff.c:206 ! Oops: invalid opcode: 0000 [#1] PREEMPT SMP KASAN PTI CPU: 0 UID: 0 PID: 7373 Comm: syz.1.568 Not tainted 6.12.0-rc2-syzkaller-00631-g6d858708d465 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024 RIP: 0010:skb_panic net/core/skbuff.c:206 [inline] RIP: 0010:skb_under_panic+0x14b/0x150 net/core/skbuff.c:216 Code: 0d 8d 48 c7 c6 60 a6 29 8e 48 8b 54 24 08 8b 0c 24 44 8b 44 24 04 4d 89 e9 50 41 54 41 57 41 56 e8 ba 30 38 02 48 83 c4 20 90 <0f> 0b 0f 1f 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 RSP: 0018:ffffc900045269b0 EFLAGS: 00010282 RAX: 0000000000000088 RBX: dffffc0000000000 RCX: cd66dacdc5d8e800 RDX: 0000000000000000 RSI: 0000000000000200 RDI: 0000000000000000 RBP: ffff88802d39a3d0 R08: ffffffff8174afec R09: 1ffff920008a4ccc R10: dffffc0000000000 R11: fffff520008a4ccd R12: 0000000000000140 R13: ffff88803123aa00 R14: ffff88803123a9f2 R15: 000000000000003c FS: 00007fdbee5ff6c0(0000) GS:ffff8880b8600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000005d322000 CR4: 00000000003526f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: skb_push+0xe5/0x100 net/core/skbuff.c:2636 eth_header+0x38/0x1f0 net/ethernet/eth.c:83 dev_hard_header include/linux/netdevice.h:3208 [inline] nf_send_reset6+0xce6/0x1270 net/ipv6/netfilter/nf_reject_ipv6.c:358 nft_reject_inet_eval+0x3b9/0x690 net/netfilter/nft_reject_inet.c:48 expr_call_ops_eval net/netfilter/nf_tables_core.c:240 [inline] nft_do_chain+0x4ad/0x1da0 net/netfilter/nf_tables_core.c:288 nft_do_chain_inet+0x418/0x6b0 net/netfilter/nft_chain_filter.c:161 nf_hook_entry_hookfn include/linux/netfilter.h:154 [inline] nf_hook_slow+0xc3/0x220 net/netfilter/core.c:626 nf_hook include/linux/netfilter.h:269 [inline] NF_HOOK include/linux/netfilter.h:312 [inline] br_nf_pre_routing_ipv6+0x63e/0x770 net/bridge/br_netfilter_ipv6.c:184 nf_hook_entry_hookfn include/linux/netfilter.h:154 [inline] nf_hook_bridge_pre net/bridge/br_input.c:277 [inline] br_handle_frame+0x9fd/0x1530 net/bridge/br_input.c:424 __netif_receive_skb_core+0x13e8/0x4570 net/core/dev.c:5562 __netif_receive_skb_one_core net/core/dev.c:5666 [inline] __netif_receive_skb+0x12f/0x650 net/core/dev.c:5781 netif_receive_skb_internal net/core/dev.c:5867 [inline] netif_receive_skb+0x1e8/0x890 net/core/dev.c:5926 tun_rx_batched+0x1b7/0x8f0 drivers/net/tun.c:1550 tun_get_user+0x3056/0x47e0 drivers/net/tun.c:2007 tun_chr_write_iter+0x10d/0x1f0 drivers/net/tun.c:2053 new_sync_write fs/read_write.c:590 [inline] vfs_write+0xa6d/0xc90 fs/read_write.c:683 ksys_write+0x183/0x2b0 fs/read_write.c:736 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fdbeeb7d1ff Code: 89 54 24 18 48 89 74 24 10 89 7c 24 08 e8 c9 8d 02 00 48 8b 54 24 18 48 8b 74 24 10 41 89 c0 8b 7c 24 08 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 31 44 89 c7 48 89 44 24 08 e8 1c 8e 02 00 48 RSP: 002b:00007fdbee5ff000 EFLAGS: 00000293 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 00007fdbeed36058 RCX: 00007fdbeeb7d1ff RDX: 000000000000008e RSI: 0000000020000040 RDI: 00000000000000c8 RBP: 00007fdbeebf12be R08: 0000000000000000 R09: 0000000000000000 R10: 000000000000008e R11: 0000000000000293 R12: 0000000000000000 R13: 0000000000000000 R14: 00007fdbeed36058 R15: 00007ffc38de06e8 Fixes: c8d7b98bec43 ("netfilter: move nf_send_resetX() code to nf_reject_ipvX modules") Reported-by: syzbot Signed-off-by: Eric Dumazet Signed-off-by: Pablo Neira Ayuso Signed-off-by: wukuan --- net/ipv6/netfilter/nf_reject_ipv6.c | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-) diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index 832d9f9cd10a..2b76f5b2118e 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -144,14 +144,12 @@ static int nf_reject6_fill_skb_dst(struct sk_buff *skb_in) void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, int hook) { - struct net_device *br_indev __maybe_unused; - struct sk_buff *nskb; - struct tcphdr _otcph; - const struct tcphdr *otcph; - unsigned int otcplen, hh_len; const struct ipv6hdr *oip6h = ipv6_hdr(oldskb); - struct ipv6hdr *ip6h; struct dst_entry *dst = NULL; + const struct tcphdr *otcph; + struct sk_buff *nskb; + struct tcphdr _otcph; + unsigned int otcplen; struct flowi6 fl6; if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) || @@ -190,9 +188,8 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, if (IS_ERR(dst)) return; - hh_len = (dst->dev->hard_header_len + 15)&~15; - nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr) - + sizeof(struct tcphdr) + dst->trailer_len, + nskb = alloc_skb(LL_MAX_HEADER + sizeof(struct ipv6hdr) + + sizeof(struct tcphdr) + dst->trailer_len, GFP_ATOMIC); if (!nskb) { @@ -205,9 +202,8 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, nskb->mark = fl6.flowi6_mark; - skb_reserve(nskb, hh_len + dst->header_len); - ip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP, - ip6_dst_hoplimit(dst)); + skb_reserve(nskb, LL_MAX_HEADER); + nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP, ip6_dst_hoplimit(dst)); nf_reject_ip6_tcphdr_put(nskb, oldskb, otcph, otcplen); nf_ct_attach(nskb, oldskb); -- Gitee From 36cfa32b91be6134b593601ad00a133fc9b1e96e Mon Sep 17 00:00:00 2001 From: David Disseldorp Date: Wed, 30 Oct 2024 03:55:10 +0000 Subject: [PATCH 2/5] initramfs: avoid filename buffer overrun mainline inclusion from mainline-v6.13-rc1 commit e017671f534dd3f568db9e47b0583e853d2da9b5 category: bugfix issue: NA CVE: CVE-2024-53142 Signed-off-by: wukuan --------------------------------------- The initramfs filename field is defined in Documentation/driver-api/early-userspace/buffer-format.rst as: 37 cpio_file := ALGN(4) + cpio_header + filename + "\0" + ALGN(4) + data ... 55 ============= ================== ========================= 56 Field name Field size Meaning 57 ============= ================== ========================= ... 70 c_namesize 8 bytes Length of filename, including final \0 When extracting an initramfs cpio archive, the kernel's do_name() path handler assumes a zero-terminated path at @collected, passing it directly to filp_open() / init_mkdir() / init_mknod(). If a specially crafted cpio entry carries a non-zero-terminated filename and is followed by uninitialized memory, then a file may be created with trailing characters that represent the uninitialized memory. The ability to create an initramfs entry would imply already having full control of the system, so the buffer overrun shouldn't be considered a security vulnerability. Append the output of the following bash script to an existing initramfs and observe any created /initramfs_test_fname_overrunAA* path. E.g. ./reproducer.sh | gzip >> /myinitramfs It's easiest to observe non-zero uninitialized memory when the output is gzipped, as it'll overflow the heap allocated @out_buf in __gunzip(), rather than the initrd_start+initrd_size block. ---- reproducer.sh ---- nilchar="A" # change to "\0" to properly zero terminate / pad magic="070701" ino=1 mode=$(( 0100777 )) uid=0 gid=0 nlink=1 mtime=1 filesize=0 devmajor=0 devminor=1 rdevmajor=0 rdevminor=0 csum=0 fname="initramfs_test_fname_overrun" namelen=$(( ${#fname} + 1 )) # plus one to account for terminator printf "%s%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x%s" \ $magic $ino $mode $uid $gid $nlink $mtime $filesize \ $devmajor $devminor $rdevmajor $rdevminor $namelen $csum $fname termpadlen=$(( 1 + ((4 - ((110 + $namelen) & 3)) % 4) )) printf "%.s${nilchar}" $(seq 1 $termpadlen) ---- reproducer.sh ---- Symlink filename fields handled in do_symlink() won't overrun past the data segment, due to the explicit zero-termination of the symlink target. Fix filename buffer overrun by aborting the initramfs FSM if any cpio entry doesn't carry a zero-terminator at the expected (name_len - 1) offset. Fixes: 1da177e4c3f41 ("Linux-2.6.12-rc2") Signed-off-by: David Disseldorp Link: https://lore.kernel.org/r/20241030035509.20194-2-ddiss@suse.de Signed-off-by: Christian Brauner Signed-off-by: wukuan --- init/initramfs.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/init/initramfs.c b/init/initramfs.c index 55b74d7e5260..4534c6611fa5 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -325,6 +325,15 @@ static int __init do_name(void) { state = SkipIt; next_state = Reset; + + /* name_len > 0 && name_len <= PATH_MAX checked in do_header */ + if (collected[name_len - 1] != '\0') { + pr_err("initramfs name without nulterm: %.*s\n", + (int)name_len, collected); + error("malformed archive"); + return 1; + } + if (strcmp(collected, "TRAILER!!!") == 0) { free_hash(); return 0; @@ -390,6 +399,12 @@ static int __init do_copy(void) static int __init do_symlink(void) { + if (collected[name_len - 1] != '\0') { + pr_err("initramfs symlink without nulterm: %.*s\n", + (int)name_len, collected); + error("malformed archive"); + return 1; + } collected[N_ALIGN(name_len) + body_len] = '\0'; clean_path(collected, 0); init_symlink(collected + N_ALIGN(name_len), collected); -- Gitee From bf951fe9782d07ae4d0b9567c757a7a78a741904 Mon Sep 17 00:00:00 2001 From: Wang Liang Date: Thu, 7 Nov 2024 10:34:05 +0800 Subject: [PATCH 3/5] net: fix data-races around sk->sk_forward_alloc mainline inclusion from mainline-v6.12 commit 073d89808c065ac4c672c0a613a71b27a80691cb category: bugfix issue: NA CVE: CVE-2024-53124 Signed-off-by: wukuan --------------------------------------- Syzkaller reported this warning: ------------[ cut here ]------------ WARNING: CPU: 0 PID: 16 at net/ipv4/af_inet.c:156 inet_sock_destruct+0x1c5/0x1e0 Modules linked in: CPU: 0 UID: 0 PID: 16 Comm: ksoftirqd/0 Not tainted 6.12.0-rc5 #26 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 RIP: 0010:inet_sock_destruct+0x1c5/0x1e0 Code: 24 12 4c 89 e2 5b 48 c7 c7 98 ec bb 82 41 5c e9 d1 18 17 ff 4c 89 e6 5b 48 c7 c7 d0 ec bb 82 41 5c e9 bf 18 17 ff 0f 0b eb 83 <0f> 0b eb 97 0f 0b eb 87 0f 0b e9 68 ff ff ff 66 66 2e 0f 1f 84 00 RSP: 0018:ffffc9000008bd90 EFLAGS: 00010206 RAX: 0000000000000300 RBX: ffff88810b172a90 RCX: 0000000000000007 RDX: 0000000000000002 RSI: 0000000000000300 RDI: ffff88810b172a00 RBP: ffff88810b172a00 R08: ffff888104273c00 R09: 0000000000100007 R10: 0000000000020000 R11: 0000000000000006 R12: ffff88810b172a00 R13: 0000000000000004 R14: 0000000000000000 R15: ffff888237c31f78 FS: 0000000000000000(0000) GS:ffff888237c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffc63fecac8 CR3: 000000000342e000 CR4: 00000000000006f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? __warn+0x88/0x130 ? inet_sock_destruct+0x1c5/0x1e0 ? report_bug+0x18e/0x1a0 ? handle_bug+0x53/0x90 ? exc_invalid_op+0x18/0x70 ? asm_exc_invalid_op+0x1a/0x20 ? inet_sock_destruct+0x1c5/0x1e0 __sk_destruct+0x2a/0x200 rcu_do_batch+0x1aa/0x530 ? rcu_do_batch+0x13b/0x530 rcu_core+0x159/0x2f0 handle_softirqs+0xd3/0x2b0 ? __pfx_smpboot_thread_fn+0x10/0x10 run_ksoftirqd+0x25/0x30 smpboot_thread_fn+0xdd/0x1d0 kthread+0xd3/0x100 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x34/0x50 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 ---[ end trace 0000000000000000 ]--- Its possible that two threads call tcp_v6_do_rcv()/sk_forward_alloc_add() concurrently when sk->sk_state == TCP_LISTEN with sk->sk_lock unlocked, which triggers a data-race around sk->sk_forward_alloc: tcp_v6_rcv tcp_v6_do_rcv skb_clone_and_charge_r sk_rmem_schedule __sk_mem_schedule sk_forward_alloc_add() skb_set_owner_r sk_mem_charge sk_forward_alloc_add() __kfree_skb skb_release_all skb_release_head_state sock_rfree sk_mem_uncharge sk_forward_alloc_add() sk_mem_reclaim // set local var reclaimable __sk_mem_reclaim sk_forward_alloc_add() In this syzkaller testcase, two threads call tcp_v6_do_rcv() with skb->truesize=768, the sk_forward_alloc changes like this: (cpu 1) | (cpu 2) | sk_forward_alloc ... | ... | 0 __sk_mem_schedule() | | +4096 = 4096 | __sk_mem_schedule() | +4096 = 8192 sk_mem_charge() | | -768 = 7424 | sk_mem_charge() | -768 = 6656 ... | ... | sk_mem_uncharge() | | +768 = 7424 reclaimable=7424 | | | sk_mem_uncharge() | +768 = 8192 | reclaimable=8192 | __sk_mem_reclaim() | | -4096 = 4096 | __sk_mem_reclaim() | -8192 = -4096 != 0 The skb_clone_and_charge_r() should not be called in tcp_v6_do_rcv() when sk->sk_state is TCP_LISTEN, it happens later in tcp_v6_syn_recv_sock(). Fix the same issue in dccp_v6_do_rcv(). Suggested-by: Eric Dumazet Reviewed-by: Eric Dumazet Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets") Signed-off-by: Wang Liang Link: https://patch.msgid.link/20241107023405.889239-1-wangliang74@huawei.com Signed-off-by: Jakub Kicinski Signed-off-by: wukuan --- net/dccp/ipv6.c | 2 +- net/ipv6/tcp_ipv6.c | 4 +--- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 991ca2dc2c02..aa311ab960b6 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -602,7 +602,7 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) by tcp. Feel free to propose better solution. --ANK (980728) */ - if (np->rxopt.all) + if (np->rxopt.all && sk->sk_state != DCCP_LISTEN) opt_skb = skb_clone_and_charge_r(skb, sk); if (sk->sk_state == DCCP_OPEN) { /* Fast path */ diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d175e673a243..7187fc0971dc 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1483,7 +1483,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) by tcp. Feel free to propose better solution. --ANK (980728) */ - if (np->rxopt.all) + if (np->rxopt.all && sk->sk_state != TCP_LISTEN) opt_skb = skb_clone_and_charge_r(skb, sk); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ @@ -1520,8 +1520,6 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (nsk != sk) { if (tcp_child_process(sk, nsk, skb)) goto reset; - if (opt_skb) - __kfree_skb(opt_skb); return 0; } } else -- Gitee From 9d6c4a063ec2069ac9831232138c5ff83763996c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 5 Nov 2024 17:52:34 -0800 Subject: [PATCH 4/5] netlink: terminate outstanding dump on socket close mainline inclusion from mainline-v6.12 commit 1904fb9ebf911441f90a68e96b22aa73e4410505 category: bugfix issue: NA CVE: CVE-2024-53140 Signed-off-by: wukuan --------------------------------------- Netlink supports iterative dumping of data. It provides the families the following ops: - start - (optional) kicks off the dumping process - dump - actual dump helper, keeps getting called until it returns 0 - done - (optional) pairs with .start, can be used for cleanup The whole process is asynchronous and the repeated calls to .dump don't actually happen in a tight loop, but rather are triggered in response to recvmsg() on the socket. This gives the user full control over the dump, but also means that the user can close the socket without getting to the end of the dump. To make sure .start is always paired with .done we check if there is an ongoing dump before freeing the socket, and if so call .done. The complication is that sockets can get freed from BH and .done is allowed to sleep. So we use a workqueue to defer the call, when needed. Unfortunately this does not work correctly. What we defer is not the cleanup but rather releasing a reference on the socket. We have no guarantee that we own the last reference, if someone else holds the socket they may release it in BH and we're back to square one. The whole dance, however, appears to be unnecessary. Only the user can interact with dumps, so we can clean up when socket is closed. And close always happens in process context. Some async code may still access the socket after close, queue notification skbs to it etc. but no dumps can start, end or otherwise make progress. Delete the workqueue and flush the dump state directly from the release handler. Note that further cleanup is possible in -next, for instance we now always call .done before releasing the main module reference, so dump doesn't have to take a reference of its own. Reported-by: syzkaller Fixes: ed5d7788a934 ("netlink: Do not schedule work from sk_destruct") Reviewed-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20241106015235.2458807-1-kuba@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: wukuan --- net/netlink/af_netlink.c | 31 ++++++++----------------------- net/netlink/af_netlink.h | 2 -- 2 files changed, 8 insertions(+), 25 deletions(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index fd5c7d76b0fc..9c603bdf37ba 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -385,15 +385,6 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk) static void netlink_sock_destruct(struct sock *sk) { - struct netlink_sock *nlk = nlk_sk(sk); - - if (nlk->cb_running) { - if (nlk->cb.done) - nlk->cb.done(&nlk->cb); - module_put(nlk->cb.module); - kfree_skb(nlk->cb.skb); - } - skb_queue_purge(&sk->sk_receive_queue); if (!sock_flag(sk, SOCK_DEAD)) { @@ -406,14 +397,6 @@ static void netlink_sock_destruct(struct sock *sk) WARN_ON(nlk_sk(sk)->groups); } -static void netlink_sock_destruct_work(struct work_struct *work) -{ - struct netlink_sock *nlk = container_of(work, struct netlink_sock, - work); - - sk_free(&nlk->sk); -} - /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on * SMP. Look, when several writers sleep and reader wakes them up, all but one * immediately hit write lock and grab all the cpus. Exclusive sleep solves @@ -730,12 +713,6 @@ static void deferred_put_nlk_sk(struct rcu_head *head) if (!refcount_dec_and_test(&sk->sk_refcnt)) return; - if (nlk->cb_running && nlk->cb.done) { - INIT_WORK(&nlk->work, netlink_sock_destruct_work); - schedule_work(&nlk->work); - return; - } - sk_free(sk); } @@ -785,6 +762,14 @@ static int netlink_release(struct socket *sock) NETLINK_URELEASE, &n); } + /* Terminate any outstanding dump */ + if (nlk->cb_running) { + if (nlk->cb.done) + nlk->cb.done(&nlk->cb); + module_put(nlk->cb.module); + kfree_skb(nlk->cb.skb); + } + module_put(nlk->module); if (netlink_is_kernel(sk)) { diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index 5f454c8de6a4..fca955684888 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -4,7 +4,6 @@ #include #include -#include #include /* flags */ @@ -46,7 +45,6 @@ struct netlink_sock { struct rhash_head node; struct rcu_head rcu; - struct work_struct work; }; static inline struct netlink_sock *nlk_sk(struct sock *sk) -- Gitee From dacbcd8cf933cd3eff8d2122571db78113ebed54 Mon Sep 17 00:00:00 2001 From: Wang Liang Date: Wed, 23 Oct 2024 11:52:13 +0800 Subject: [PATCH 5/5] net: fix crash when config small gso_max_size/gso_ipv4_max_size mainline inclusion from mainline-v6.12-rc6 commit 9ab5cf19fb0e4680f95e506d6c544259bf1111c4 category: bugfix issue: NA CVE: CVE-2024-50258 Signed-off-by: wukuan --------------------------------------- Config a small gso_max_size/gso_ipv4_max_size will lead to an underflow in sk_dst_gso_max_size(), which may trigger a BUG_ON crash, because sk->sk_gso_max_size would be much bigger than device limits. Call Trace: tcp_write_xmit tso_segs = tcp_init_tso_segs(skb, mss_now); tcp_set_skb_tso_segs tcp_skb_pcount_set // skb->len = 524288, mss_now = 8 // u16 tso_segs = 524288/8 = 65535 -> 0 tso_segs = DIV_ROUND_UP(skb->len, mss_now) BUG_ON(!tso_segs) Add check for the minimum value of gso_max_size and gso_ipv4_max_size. Fixes: 46e6b992c250 ("rtnetlink: allow GSO maximums to be set on device creation") Fixes: 9eefedd58ae1 ("net: add gso_ipv4_max_size and gro_ipv4_max_size per device") Signed-off-by: Wang Liang Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20241023035213.517386-1-wangliang74@huawei.com Signed-off-by: Jakub Kicinski Signed-off-by: wukuan --- net/core/rtnetlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 2806b9ed6387..d6dbb042489f 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1864,7 +1864,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_NUM_TX_QUEUES] = { .type = NLA_U32 }, [IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 }, [IFLA_GSO_MAX_SEGS] = { .type = NLA_U32 }, - [IFLA_GSO_MAX_SIZE] = { .type = NLA_U32 }, + [IFLA_GSO_MAX_SIZE] = NLA_POLICY_MIN(NLA_U32, MAX_TCP_HEADER + 1), [IFLA_PHYS_PORT_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN }, [IFLA_CARRIER_CHANGES] = { .type = NLA_U32 }, /* ignored */ [IFLA_PHYS_SWITCH_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN }, -- Gitee