From c2ff4dad290b05eeee431b28940c45bba709b423 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 8 Jan 2024 19:06:18 +0800 Subject: [PATCH 01/12] net: annotate data-races around sk->sk_tx_queue_mapping stable inclusion from stable-v4.19.300 commit bd4f1843a141fc77995108b08d9cc07f67d5d894 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8UH13 CVE: NA -------------------------------- [ Upstream commit 0bb4d124d34044179b42a769a0c76f389ae973b6 ] This field can be read or written without socket lock being held. Add annotations to avoid load-store tearing. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin Signed-off-by: Yongqiang Liu --- include/net/sock.h | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index ea4d80348351..aa32cc54c1ad 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1806,21 +1806,33 @@ static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) /* sk_tx_queue_mapping accept only upto a 16-bit value */ if (WARN_ON_ONCE((unsigned short)tx_queue >= USHRT_MAX)) return; - sk->sk_tx_queue_mapping = tx_queue; + /* Paired with READ_ONCE() in sk_tx_queue_get() and + * other WRITE_ONCE() because socket lock might be not held. + */ + WRITE_ONCE(sk->sk_tx_queue_mapping, tx_queue); } #define NO_QUEUE_MAPPING USHRT_MAX static inline void sk_tx_queue_clear(struct sock *sk) { - sk->sk_tx_queue_mapping = NO_QUEUE_MAPPING; + /* Paired with READ_ONCE() in sk_tx_queue_get() and + * other WRITE_ONCE() because socket lock might be not held. + */ + WRITE_ONCE(sk->sk_tx_queue_mapping, NO_QUEUE_MAPPING); } static inline int sk_tx_queue_get(const struct sock *sk) { - if (sk && sk->sk_tx_queue_mapping != NO_QUEUE_MAPPING) - return sk->sk_tx_queue_mapping; + if (sk) { + /* Paired with WRITE_ONCE() in sk_tx_queue_clear() + * and sk_tx_queue_set(). + */ + int val = READ_ONCE(sk->sk_tx_queue_mapping); + if (val != NO_QUEUE_MAPPING) + return val; + } return -1; } -- Gitee From 995f9b676121d9bb5ba7bdbed5eaff5a520397c3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 8 Jan 2024 19:06:19 +0800 Subject: [PATCH 02/12] net: annotate data-races around sk->sk_dst_pending_confirm stable inclusion from stable-v4.19.300 commit ac41b10e834f5f7479f91220668e90c505808d1c category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8UH13 CVE: NA -------------------------------- [ Upstream commit eb44ad4e635132754bfbcb18103f1dcb7058aedd ] This field can be read or written without socket lock being held. Add annotations to avoid load-store tearing. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin Signed-off-by: Yongqiang Liu --- include/net/sock.h | 6 +++--- net/core/sock.c | 2 +- net/ipv4/tcp_output.c | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index aa32cc54c1ad..a1bfb777a1af 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1965,7 +1965,7 @@ static inline void dst_negative_advice(struct sock *sk) if (ndst != dst) { rcu_assign_pointer(sk->sk_dst_cache, ndst); sk_tx_queue_clear(sk); - sk->sk_dst_pending_confirm = 0; + WRITE_ONCE(sk->sk_dst_pending_confirm, 0); } } } @@ -1976,7 +1976,7 @@ __sk_dst_set(struct sock *sk, struct dst_entry *dst) struct dst_entry *old_dst; sk_tx_queue_clear(sk); - sk->sk_dst_pending_confirm = 0; + WRITE_ONCE(sk->sk_dst_pending_confirm, 0); old_dst = rcu_dereference_protected(sk->sk_dst_cache, lockdep_sock_is_held(sk)); rcu_assign_pointer(sk->sk_dst_cache, dst); @@ -1989,7 +1989,7 @@ sk_dst_set(struct sock *sk, struct dst_entry *dst) struct dst_entry *old_dst; sk_tx_queue_clear(sk); - sk->sk_dst_pending_confirm = 0; + WRITE_ONCE(sk->sk_dst_pending_confirm, 0); old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst); dst_release(old_dst); } diff --git a/net/core/sock.c b/net/core/sock.c index deef28942090..cc286bf0f1a4 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -496,7 +496,7 @@ struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { sk_tx_queue_clear(sk); - sk->sk_dst_pending_confirm = 0; + WRITE_ONCE(sk->sk_dst_pending_confirm, 0); RCU_INIT_POINTER(sk->sk_dst_cache, NULL); dst_release(dst); return NULL; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 97d9ed2bf50e..d9c47869e43a 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1143,7 +1143,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, skb_set_hash_from_sk(skb, sk); refcount_add(skb->truesize, &sk->sk_wmem_alloc); - skb_set_dst_pending_confirm(skb, sk->sk_dst_pending_confirm); + skb_set_dst_pending_confirm(skb, READ_ONCE(sk->sk_dst_pending_confirm)); /* Build TCP header and checksum it. */ th = (struct tcphdr *)skb->data; -- Gitee From 48ed2d918cdfa244a00968c07ae66aa4cab62535 Mon Sep 17 00:00:00 2001 From: Shigeru Yoshida Date: Mon, 8 Jan 2024 19:06:20 +0800 Subject: [PATCH 03/12] tty: Fix uninit-value access in ppp_sync_receive() stable inclusion from stable-v4.19.300 commit f48592892620769e452f8983b789885728e44c65 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8UH13 CVE: NA -------------------------------- [ Upstream commit 719639853d88071dfdfd8d9971eca9c283ff314c ] KMSAN reported the following uninit-value access issue: ===================================================== BUG: KMSAN: uninit-value in ppp_sync_input drivers/net/ppp/ppp_synctty.c:690 [inline] BUG: KMSAN: uninit-value in ppp_sync_receive+0xdc9/0xe70 drivers/net/ppp/ppp_synctty.c:334 ppp_sync_input drivers/net/ppp/ppp_synctty.c:690 [inline] ppp_sync_receive+0xdc9/0xe70 drivers/net/ppp/ppp_synctty.c:334 tiocsti+0x328/0x450 drivers/tty/tty_io.c:2295 tty_ioctl+0x808/0x1920 drivers/tty/tty_io.c:2694 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:871 [inline] __se_sys_ioctl+0x211/0x400 fs/ioctl.c:857 __x64_sys_ioctl+0x97/0xe0 fs/ioctl.c:857 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x44/0x110 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x63/0x6b Uninit was created at: __alloc_pages+0x75d/0xe80 mm/page_alloc.c:4591 __alloc_pages_node include/linux/gfp.h:238 [inline] alloc_pages_node include/linux/gfp.h:261 [inline] __page_frag_cache_refill+0x9a/0x2c0 mm/page_alloc.c:4691 page_frag_alloc_align+0x91/0x5d0 mm/page_alloc.c:4722 page_frag_alloc include/linux/gfp.h:322 [inline] __netdev_alloc_skb+0x215/0x6d0 net/core/skbuff.c:728 netdev_alloc_skb include/linux/skbuff.h:3225 [inline] dev_alloc_skb include/linux/skbuff.h:3238 [inline] ppp_sync_input drivers/net/ppp/ppp_synctty.c:669 [inline] ppp_sync_receive+0x237/0xe70 drivers/net/ppp/ppp_synctty.c:334 tiocsti+0x328/0x450 drivers/tty/tty_io.c:2295 tty_ioctl+0x808/0x1920 drivers/tty/tty_io.c:2694 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:871 [inline] __se_sys_ioctl+0x211/0x400 fs/ioctl.c:857 __x64_sys_ioctl+0x97/0xe0 fs/ioctl.c:857 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x44/0x110 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x63/0x6b CPU: 0 PID: 12950 Comm: syz-executor.1 Not tainted 6.6.0-14500-g1c41041124bd #10 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-1.fc38 04/01/2014 ===================================================== ppp_sync_input() checks the first 2 bytes of the data are PPP_ALLSTATIONS and PPP_UI. However, if the data length is 1 and the first byte is PPP_ALLSTATIONS, an access to an uninitialized value occurs when checking PPP_UI. This patch resolves this issue by checking the data length. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Shigeru Yoshida Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin Signed-off-by: Yongqiang Liu --- drivers/net/ppp/ppp_synctty.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c index 047f6c68a441..e0de8b32df46 100644 --- a/drivers/net/ppp/ppp_synctty.c +++ b/drivers/net/ppp/ppp_synctty.c @@ -702,7 +702,7 @@ ppp_sync_input(struct syncppp *ap, const unsigned char *buf, /* strip address/control field if present */ p = skb->data; - if (p[0] == PPP_ALLSTATIONS && p[1] == PPP_UI) { + if (skb->len >= 2 && p[0] == PPP_ALLSTATIONS && p[1] == PPP_UI) { /* chop off address/control */ if (skb->len < 3) goto err; -- Gitee From 7c47581ec5f55dd9c2a56cacbd8326bba5e0e367 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 8 Jan 2024 19:06:21 +0800 Subject: [PATCH 04/12] ppp: limit MRU to 64K stable inclusion from stable-v4.19.300 commit f52caac943f311a037ccdf429827b30d8bb7c2e0 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8UH13 CVE: NA -------------------------------- [ Upstream commit c0a2a1b0d631fc460d830f52d06211838874d655 ] ppp_sync_ioctl allows setting device MRU, but does not sanity check this input. Limit to a sane upper bound of 64KB. No implementation I could find generates larger than 64KB frames. RFC 2823 mentions an upper bound of PPP over SDL of 64KB based on the 16-bit length field. Other protocols will be smaller, such as PPPoE (9KB jumbo frame) and PPPoA (18190 maximum CPCS-SDU size, RFC 2364). PPTP and L2TP encapsulate in IP. Syzbot managed to trigger alloc warning in __alloc_pages: if (WARN_ON_ONCE_GFP(order > MAX_ORDER, gfp)) WARNING: CPU: 1 PID: 37 at mm/page_alloc.c:4544 __alloc_pages+0x3ab/0x4a0 mm/page_alloc.c:4544 __alloc_skb+0x12b/0x330 net/core/skbuff.c:651 __netdev_alloc_skb+0x72/0x3f0 net/core/skbuff.c:715 netdev_alloc_skb include/linux/skbuff.h:3225 [inline] dev_alloc_skb include/linux/skbuff.h:3238 [inline] ppp_sync_input drivers/net/ppp/ppp_synctty.c:669 [inline] ppp_sync_receive+0xff/0x680 drivers/net/ppp/ppp_synctty.c:334 tty_ldisc_receive_buf+0x14c/0x180 drivers/tty/tty_buffer.c:390 tty_port_default_receive_buf+0x70/0xb0 drivers/tty/tty_port.c:37 receive_buf drivers/tty/tty_buffer.c:444 [inline] flush_to_ldisc+0x261/0x780 drivers/tty/tty_buffer.c:494 process_one_work+0x884/0x15c0 kernel/workqueue.c:2630 With call ioctl$PPPIOCSMRU1(r1, 0x40047452, &(0x7f0000000100)=0x5e6417a8) Similar code exists in other drivers that implement ppp_channel_ops ioctl PPPIOCSMRU. Those might also be in scope. Notably excluded from this are pppol2tp_ioctl and pppoe_ioctl. This code goes back to the start of git history. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot+6177e1f90d92583bcc58@syzkaller.appspotmail.com Signed-off-by: Willem de Bruijn Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin Signed-off-by: Yongqiang Liu --- drivers/net/ppp/ppp_synctty.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c index e0de8b32df46..7a1b903d3fb8 100644 --- a/drivers/net/ppp/ppp_synctty.c +++ b/drivers/net/ppp/ppp_synctty.c @@ -467,6 +467,10 @@ ppp_sync_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg) case PPPIOCSMRU: if (get_user(val, (int __user *) argp)) break; + if (val > U16_MAX) { + err = -EINVAL; + break; + } if (val < PPP_MRU) val = PPP_MRU; ap->mru = val; -- Gitee From 721d0e461ab68752795725538b4932f48390dc57 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 8 Jan 2024 19:06:22 +0800 Subject: [PATCH 05/12] macvlan: Don't propagate promisc change to lower dev in passthru stable inclusion from stable-v4.19.300 commit 5df0c8e7e2b2ba58f971b6b20247e27e09fe4583 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8UH13 CVE: NA -------------------------------- [ Upstream commit 7e1caeace0418381f36b3aa8403dfd82fc57fc53 ] Macvlan device in passthru mode sets its lower device promiscuous mode according to its MACVLAN_FLAG_NOPROMISC flag instead of synchronizing it to its own promiscuity setting. However, macvlan_change_rx_flags() function doesn't check the mode before propagating such changes to the lower device which can cause net_device->promiscuity counter overflow as illustrated by reproduction example [0] and resulting dmesg log [1]. Fix the issue by first verifying the mode in macvlan_change_rx_flags() function before propagating promiscuous mode change to the lower device. [0]: ip link add macvlan1 link enp8s0f0 type macvlan mode passthru ip link set macvlan1 promisc on ip l set dev macvlan1 up ip link set macvlan1 promisc off ip l set dev macvlan1 down ip l set dev macvlan1 up [1]: [ 5156.281724] macvlan1: entered promiscuous mode [ 5156.285467] mlx5_core 0000:08:00.0 enp8s0f0: entered promiscuous mode [ 5156.287639] macvlan1: left promiscuous mode [ 5156.288339] mlx5_core 0000:08:00.0 enp8s0f0: left promiscuous mode [ 5156.290907] mlx5_core 0000:08:00.0 enp8s0f0: entered promiscuous mode [ 5156.317197] mlx5_core 0000:08:00.0 enp8s0f0: promiscuity touches roof, set promiscuity failed. promiscuity feature of device might be broken. Fixes: efdbd2b30caa ("macvlan: Propagate promiscuity setting to lower devices.") Reviewed-by: Gal Pressman Signed-off-by: Vlad Buslov Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/20231114175915.1649154-1-vladbu@nvidia.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin Signed-off-by: Yongqiang Liu --- drivers/net/macvlan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 956ebfb41921..8c60e0fc52a6 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -768,7 +768,7 @@ static void macvlan_change_rx_flags(struct net_device *dev, int change) if (dev->flags & IFF_UP) { if (change & IFF_ALLMULTI) dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1); - if (change & IFF_PROMISC) + if (!macvlan_passthru(vlan->port) && change & IFF_PROMISC) dev_set_promiscuity(lowerdev, dev->flags & IFF_PROMISC ? 1 : -1); -- Gitee From 8652ced73c049614cff4bf5d3c088f277f498f5b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 8 Jan 2024 19:06:23 +0800 Subject: [PATCH 06/12] net: sched: fix race condition in qdisc_graft() stable inclusion from stable-v4.19.300 commit f782929b90b5ac88d4445c853949d9efa6db6bae category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8UH13 CVE: NA -------------------------------- commit ebda44da44f6f309d302522b049f43d6f829f7aa upstream. We had one syzbot report [1] in syzbot queue for a while. I was waiting for more occurrences and/or a repro but Dmitry Vyukov spotted the issue right away. qdisc_graft() drops reference to qdisc in notify_and_destroy while it's still assigned to dev->qdisc Indeed, RCU rules are clear when replacing a data structure. The visible pointer (dev->qdisc in this case) must be updated to the new object _before_ RCU grace period is started (qdisc_put(old) in this case). [1] BUG: KASAN: use-after-free in __tcf_qdisc_find.part.0+0xa3a/0xac0 net/sched/cls_api.c:1066 Read of size 4 at addr ffff88802065e038 by task syz-executor.4/21027 CPU: 0 PID: 21027 Comm: syz-executor.4 Not tainted 6.0.0-rc3-syzkaller-00363-g7726d4c3e60b #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/26/2022 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:317 [inline] print_report.cold+0x2ba/0x719 mm/kasan/report.c:433 kasan_report+0xb1/0x1e0 mm/kasan/report.c:495 __tcf_qdisc_find.part.0+0xa3a/0xac0 net/sched/cls_api.c:1066 __tcf_qdisc_find net/sched/cls_api.c:1051 [inline] tc_new_tfilter+0x34f/0x2200 net/sched/cls_api.c:2018 rtnetlink_rcv_msg+0x955/0xca0 net/core/rtnetlink.c:6081 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2501 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x543/0x7f0 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x917/0xe10 net/netlink/af_netlink.c:1921 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:734 ____sys_sendmsg+0x6eb/0x810 net/socket.c:2482 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2536 __sys_sendmsg+0xf3/0x1c0 net/socket.c:2565 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f5efaa89279 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f5efbc31168 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f5efab9bf80 RCX: 00007f5efaa89279 RDX: 0000000000000000 RSI: 0000000020000140 RDI: 0000000000000005 RBP: 00007f5efaae32e9 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007f5efb0cfb1f R14: 00007f5efbc31300 R15: 0000000000022000 Allocated by task 21027: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 kasan_set_track mm/kasan/common.c:45 [inline] set_alloc_info mm/kasan/common.c:437 [inline] ____kasan_kmalloc mm/kasan/common.c:516 [inline] ____kasan_kmalloc mm/kasan/common.c:475 [inline] __kasan_kmalloc+0xa9/0xd0 mm/kasan/common.c:525 kmalloc_node include/linux/slab.h:623 [inline] kzalloc_node include/linux/slab.h:744 [inline] qdisc_alloc+0xb0/0xc50 net/sched/sch_generic.c:938 qdisc_create_dflt+0x71/0x4a0 net/sched/sch_generic.c:997 attach_one_default_qdisc net/sched/sch_generic.c:1152 [inline] netdev_for_each_tx_queue include/linux/netdevice.h:2437 [inline] attach_default_qdiscs net/sched/sch_generic.c:1170 [inline] dev_activate+0x760/0xcd0 net/sched/sch_generic.c:1229 __dev_open+0x393/0x4d0 net/core/dev.c:1441 __dev_change_flags+0x583/0x750 net/core/dev.c:8556 rtnl_configure_link+0xee/0x240 net/core/rtnetlink.c:3189 rtnl_newlink_create net/core/rtnetlink.c:3371 [inline] __rtnl_newlink+0x10b8/0x17e0 net/core/rtnetlink.c:3580 rtnl_newlink+0x64/0xa0 net/core/rtnetlink.c:3593 rtnetlink_rcv_msg+0x43a/0xca0 net/core/rtnetlink.c:6090 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2501 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x543/0x7f0 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x917/0xe10 net/netlink/af_netlink.c:1921 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:734 ____sys_sendmsg+0x6eb/0x810 net/socket.c:2482 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2536 __sys_sendmsg+0xf3/0x1c0 net/socket.c:2565 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Freed by task 21020: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 kasan_set_track+0x21/0x30 mm/kasan/common.c:45 kasan_set_free_info+0x20/0x30 mm/kasan/generic.c:370 ____kasan_slab_free mm/kasan/common.c:367 [inline] ____kasan_slab_free+0x166/0x1c0 mm/kasan/common.c:329 kasan_slab_free include/linux/kasan.h:200 [inline] slab_free_hook mm/slub.c:1754 [inline] slab_free_freelist_hook+0x8b/0x1c0 mm/slub.c:1780 slab_free mm/slub.c:3534 [inline] kfree+0xe2/0x580 mm/slub.c:4562 rcu_do_batch kernel/rcu/tree.c:2245 [inline] rcu_core+0x7b5/0x1890 kernel/rcu/tree.c:2505 __do_softirq+0x1d3/0x9c6 kernel/softirq.c:571 Last potentially related work creation: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 __kasan_record_aux_stack+0xbe/0xd0 mm/kasan/generic.c:348 call_rcu+0x99/0x790 kernel/rcu/tree.c:2793 qdisc_put+0xcd/0xe0 net/sched/sch_generic.c:1083 notify_and_destroy net/sched/sch_api.c:1012 [inline] qdisc_graft+0xeb1/0x1270 net/sched/sch_api.c:1084 tc_modify_qdisc+0xbb7/0x1a00 net/sched/sch_api.c:1671 rtnetlink_rcv_msg+0x43a/0xca0 net/core/rtnetlink.c:6090 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2501 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x543/0x7f0 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x917/0xe10 net/netlink/af_netlink.c:1921 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:734 ____sys_sendmsg+0x6eb/0x810 net/socket.c:2482 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2536 __sys_sendmsg+0xf3/0x1c0 net/socket.c:2565 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Second to last potentially related work creation: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 __kasan_record_aux_stack+0xbe/0xd0 mm/kasan/generic.c:348 kvfree_call_rcu+0x74/0x940 kernel/rcu/tree.c:3322 neigh_destroy+0x431/0x630 net/core/neighbour.c:912 neigh_release include/net/neighbour.h:454 [inline] neigh_cleanup_and_release+0x1f8/0x330 net/core/neighbour.c:103 neigh_del net/core/neighbour.c:225 [inline] neigh_remove_one+0x37d/0x460 net/core/neighbour.c:246 neigh_forced_gc net/core/neighbour.c:276 [inline] neigh_alloc net/core/neighbour.c:447 [inline] ___neigh_create+0x18b5/0x29a0 net/core/neighbour.c:642 ip6_finish_output2+0xfb8/0x1520 net/ipv6/ip6_output.c:125 __ip6_finish_output net/ipv6/ip6_output.c:195 [inline] ip6_finish_output+0x690/0x1160 net/ipv6/ip6_output.c:206 NF_HOOK_COND include/linux/netfilter.h:296 [inline] ip6_output+0x1ed/0x540 net/ipv6/ip6_output.c:227 dst_output include/net/dst.h:451 [inline] NF_HOOK include/linux/netfilter.h:307 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] mld_sendpack+0xa09/0xe70 net/ipv6/mcast.c:1820 mld_send_cr net/ipv6/mcast.c:2121 [inline] mld_ifc_work+0x71c/0xdc0 net/ipv6/mcast.c:2653 process_one_work+0x991/0x1610 kernel/workqueue.c:2289 worker_thread+0x665/0x1080 kernel/workqueue.c:2436 kthread+0x2e4/0x3a0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:306 The buggy address belongs to the object at ffff88802065e000 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 56 bytes inside of 1024-byte region [ffff88802065e000, ffff88802065e400) The buggy address belongs to the physical page: page:ffffea0000819600 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x20658 head:ffffea0000819600 order:3 compound_mapcount:0 compound_pincount:0 flags: 0xfff00000010200(slab|head|node=0|zone=1|lastcpupid=0x7ff) raw: 00fff00000010200 0000000000000000 dead000000000001 ffff888011841dc0 raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as allocated page last allocated via order 3, migratetype Unmovable, gfp_mask 0xd20c0(__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC), pid 3523, tgid 3523 (sshd), ts 41495190986, free_ts 41417713212 prep_new_page mm/page_alloc.c:2532 [inline] get_page_from_freelist+0x109b/0x2ce0 mm/page_alloc.c:4283 __alloc_pages+0x1c7/0x510 mm/page_alloc.c:5515 alloc_pages+0x1a6/0x270 mm/mempolicy.c:2270 alloc_slab_page mm/slub.c:1824 [inline] allocate_slab+0x27e/0x3d0 mm/slub.c:1969 new_slab mm/slub.c:2029 [inline] ___slab_alloc+0x7f1/0xe10 mm/slub.c:3031 __slab_alloc.constprop.0+0x4d/0xa0 mm/slub.c:3118 slab_alloc_node mm/slub.c:3209 [inline] __kmalloc_node_track_caller+0x2f2/0x380 mm/slub.c:4955 kmalloc_reserve net/core/skbuff.c:358 [inline] __alloc_skb+0xd9/0x2f0 net/core/skbuff.c:430 alloc_skb_fclone include/linux/skbuff.h:1307 [inline] tcp_stream_alloc_skb+0x38/0x580 net/ipv4/tcp.c:861 tcp_sendmsg_locked+0xc36/0x2f80 net/ipv4/tcp.c:1325 tcp_sendmsg+0x2b/0x40 net/ipv4/tcp.c:1483 inet_sendmsg+0x99/0xe0 net/ipv4/af_inet.c:819 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:734 sock_write_iter+0x291/0x3d0 net/socket.c:1108 call_write_iter include/linux/fs.h:2187 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x9e9/0xdd0 fs/read_write.c:578 ksys_write+0x1e8/0x250 fs/read_write.c:631 page last free stack trace: reset_page_owner include/linux/page_owner.h:24 [inline] free_pages_prepare mm/page_alloc.c:1449 [inline] free_pcp_prepare+0x5e4/0xd20 mm/page_alloc.c:1499 free_unref_page_prepare mm/page_alloc.c:3380 [inline] free_unref_page+0x19/0x4d0 mm/page_alloc.c:3476 __unfreeze_partials+0x17c/0x1a0 mm/slub.c:2548 qlink_free mm/kasan/quarantine.c:168 [inline] qlist_free_all+0x6a/0x170 mm/kasan/quarantine.c:187 kasan_quarantine_reduce+0x180/0x200 mm/kasan/quarantine.c:294 __kasan_slab_alloc+0xa2/0xc0 mm/kasan/common.c:447 kasan_slab_alloc include/linux/kasan.h:224 [inline] slab_post_alloc_hook mm/slab.h:727 [inline] slab_alloc_node mm/slub.c:3243 [inline] slab_alloc mm/slub.c:3251 [inline] __kmem_cache_alloc_lru mm/slub.c:3258 [inline] kmem_cache_alloc+0x267/0x3b0 mm/slub.c:3268 kmem_cache_zalloc include/linux/slab.h:723 [inline] alloc_buffer_head+0x20/0x140 fs/buffer.c:2974 alloc_page_buffers+0x280/0x790 fs/buffer.c:829 create_empty_buffers+0x2c/0xee0 fs/buffer.c:1558 ext4_block_write_begin+0x1004/0x1530 fs/ext4/inode.c:1074 ext4_da_write_begin+0x422/0xae0 fs/ext4/inode.c:2996 generic_perform_write+0x246/0x560 mm/filemap.c:3738 ext4_buffered_write_iter+0x15b/0x460 fs/ext4/file.c:270 ext4_file_write_iter+0x44a/0x1660 fs/ext4/file.c:679 call_write_iter include/linux/fs.h:2187 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x9e9/0xdd0 fs/read_write.c:578 Fixes: af356afa010f ("net_sched: reintroduce dev->qdisc for use by sch_api") Reported-by: syzbot Diagnosed-by: Dmitry Vyukov Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20221018203258.2793282-1-edumazet@google.com Signed-off-by: Jakub Kicinski [ mheyne: removed rtnl_dereference due to missing commit 5891cd5ec46c ("net_sched: add __rcu annotation to netdev->qdisc") ] Signed-off-by: Maximilian Heyne Signed-off-by: Greg Kroah-Hartman Signed-off-by: Yongqiang Liu --- net/sched/sch_api.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 27166a48293c..458f9e733cf0 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1004,12 +1004,13 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, skip: if (!ingress) { - notify_and_destroy(net, skb, n, classid, - dev->qdisc, new); + old = dev->qdisc; if (new && !new->ops->attach) qdisc_refcount_inc(new); dev->qdisc = new ? : &noop_qdisc; + notify_and_destroy(net, skb, n, classid, old, new); + if (new && new->ops->attach) new->ops->attach(new); } else { -- Gitee From 3aeffaa97e95ef1dca6a944b4c55e44dcc02e0d7 Mon Sep 17 00:00:00 2001 From: Kunwu Chan Date: Mon, 8 Jan 2024 19:06:24 +0800 Subject: [PATCH 07/12] ipv4: Correct/silence an endian warning in __ip_do_redirect stable inclusion from stable-v4.19.301 commit 996f39b6ab7e22c5ea2d79a6738b98305a94b889 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8UH13 CVE: NA -------------------------------- [ Upstream commit c0e2926266af3b5acf28df0a8fc6e4d90effe0bb ] net/ipv4/route.c:783:46: warning: incorrect type in argument 2 (different base types) net/ipv4/route.c:783:46: expected unsigned int [usertype] key net/ipv4/route.c:783:46: got restricted __be32 [usertype] new_gw Fixes: 969447f226b4 ("ipv4: use new_gw for redirect neigh lookup") Suggested-by: Eric Dumazet Signed-off-by: Kunwu Chan Link: https://lore.kernel.org/r/20231119141759.420477-1-chentao@kylinos.cn Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin Signed-off-by: Yongqiang Liu --- net/ipv4/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 86096e2e43b0..dcb16e6747da 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -789,7 +789,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow goto reject_redirect; } - n = __ipv4_neigh_lookup(rt->dst.dev, new_gw); + n = __ipv4_neigh_lookup(rt->dst.dev, (__force u32)new_gw); if (!n) n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev); if (!IS_ERR(n)) { -- Gitee From 718b1164e222ec328aa40d8dfd721d9bd8e0153e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 8 Jan 2024 19:06:25 +0800 Subject: [PATCH 08/12] ipv6: fix potential NULL deref in fib6_add() stable inclusion from stable-v4.19.302 commit 22a9d504748433f079aa1633697c05de68fb352d category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8UH13 CVE: NA -------------------------------- [ Upstream commit 75475bb51e78a3f54ad2f69380f2a1c985e85f2d ] If fib6_find_prefix() returns NULL, we should silently fallback using fib6_null_entry regardless of RT6_DEBUG value. syzbot reported: WARNING: CPU: 0 PID: 5477 at net/ipv6/ip6_fib.c:1516 fib6_add+0x310d/0x3fa0 net/ipv6/ip6_fib.c:1516 Modules linked in: CPU: 0 PID: 5477 Comm: syz-executor.0 Not tainted 6.7.0-rc2-syzkaller-00029-g9b6de136b5f0 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/10/2023 RIP: 0010:fib6_add+0x310d/0x3fa0 net/ipv6/ip6_fib.c:1516 Code: 00 48 8b 54 24 68 e8 42 22 00 00 48 85 c0 74 14 49 89 c6 e8 d5 d3 c2 f7 eb 5d e8 ce d3 c2 f7 e9 ca 00 00 00 e8 c4 d3 c2 f7 90 <0f> 0b 90 48 b8 00 00 00 00 00 fc ff df 48 8b 4c 24 38 80 3c 01 00 RSP: 0018:ffffc90005067740 EFLAGS: 00010293 RAX: ffffffff89cba5bc RBX: ffffc90005067ab0 RCX: ffff88801a2e9dc0 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000 RBP: ffffc90005067980 R08: ffffffff89cbca85 R09: 1ffff110040d4b85 R10: dffffc0000000000 R11: ffffed10040d4b86 R12: 00000000ffffffff R13: 1ffff110051c3904 R14: ffff8880206a5c00 R15: ffff888028e1c820 FS: 00007f763783c6c0(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f763783bff8 CR3: 000000007f74d000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: __ip6_ins_rt net/ipv6/route.c:1303 [inline] ip6_route_add+0x88/0x120 net/ipv6/route.c:3847 ipv6_route_ioctl+0x525/0x7b0 net/ipv6/route.c:4467 inet6_ioctl+0x21a/0x270 net/ipv6/af_inet6.c:575 sock_do_ioctl+0x152/0x460 net/socket.c:1220 sock_ioctl+0x615/0x8c0 net/socket.c:1339 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:871 [inline] __se_sys_ioctl+0xf8/0x170 fs/ioctl.c:857 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x45/0x110 arch/x86/entry/common.c:82 Fixes: 7bbfe00e0252 ("ipv6: fix general protection fault in fib6_add()") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Wei Wang Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20231129160630.3509216-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin Signed-off-by: Yongqiang Liu --- net/ipv6/ip6_fib.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 5ff67cb8b6ac..92bc56028b8b 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1351,13 +1351,9 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) { pn_leaf = fib6_find_prefix(info->nl_net, table, pn); -#if RT6_DEBUG >= 2 - if (!pn_leaf) { - WARN_ON(!pn_leaf); + if (!pn_leaf) pn_leaf = info->nl_net->ipv6.fib6_null_entry; - } -#endif fib6_info_hold(pn_leaf); rcu_assign_pointer(pn->leaf, pn_leaf); } -- Gitee From 70b09f35281c06521fcbc0b5231ac2aa12e0edd7 Mon Sep 17 00:00:00 2001 From: Shigeru Yoshida Date: Mon, 8 Jan 2024 19:06:26 +0800 Subject: [PATCH 09/12] ipv4: ip_gre: Avoid skb_pull() failure in ipgre_xmit() stable inclusion from stable-v4.19.302 commit 1fbcc804891c4eafd7155e72ebec9001537711c8 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8UH13 CVE: NA -------------------------------- [ Upstream commit 80d875cfc9d3711a029f234ef7d680db79e8fa4b ] In ipgre_xmit(), skb_pull() may fail even if pskb_inet_may_pull() returns true. For example, applications can use PF_PACKET to create a malformed packet with no IP header. This type of packet causes a problem such as uninit-value access. This patch ensures that skb_pull() can pull the required size by checking the skb with pskb_network_may_pull() before skb_pull(). Fixes: c54419321455 ("GRE: Refactor GRE tunneling code.") Signed-off-by: Shigeru Yoshida Reviewed-by: Eric Dumazet Reviewed-by: Suman Ghosh Link: https://lore.kernel.org/r/20231202161441.221135-1-syoshida@redhat.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin Signed-off-by: Yongqiang Liu --- net/ipv4/ip_gre.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index c72432ce9bf5..449eeeb80fde 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -683,15 +683,18 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, } if (dev->header_ops) { + int pull_len = tunnel->hlen + sizeof(struct iphdr); + if (skb_cow_head(skb, 0)) goto free_skb; tnl_params = (const struct iphdr *)skb->data; - /* Pull skb since ip_tunnel_xmit() needs skb->data pointing - * to gre header. - */ - skb_pull(skb, tunnel->hlen + sizeof(struct iphdr)); + if (!pskb_network_may_pull(skb, pull_len)) + goto free_skb; + + /* ip_tunnel_xmit() needs skb->data pointing to gre header. */ + skb_pull(skb, pull_len); skb_reset_mac_header(skb); if (skb->ip_summed == CHECKSUM_PARTIAL && -- Gitee From 6acca9b1e016c2dfed990de4a5c1c704b2dd0e4a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 8 Jan 2024 19:06:27 +0800 Subject: [PATCH 10/12] tcp: do not accept ACK of bytes we never sent stable inclusion from stable-v4.19.302 commit 458f07ffeccd17f99942311e09ef574ddf4a414a category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8UH13 CVE: NA -------------------------------- [ Upstream commit 3d501dd326fb1c73f1b8206d4c6e1d7b15c07e27 ] This patch is based on a detailed report and ideas from Yepeng Pan and Christian Rossow. ACK seq validation is currently following RFC 5961 5.2 guidelines: The ACK value is considered acceptable only if it is in the range of ((SND.UNA - MAX.SND.WND) <= SEG.ACK <= SND.NXT). All incoming segments whose ACK value doesn't satisfy the above condition MUST be discarded and an ACK sent back. It needs to be noted that RFC 793 on page 72 (fifth check) says: "If the ACK is a duplicate (SEG.ACK < SND.UNA), it can be ignored. If the ACK acknowledges something not yet sent (SEG.ACK > SND.NXT) then send an ACK, drop the segment, and return". The "ignored" above implies that the processing of the incoming data segment continues, which means the ACK value is treated as acceptable. This mitigation makes the ACK check more stringent since any ACK < SND.UNA wouldn't be accepted, instead only ACKs that are in the range ((SND.UNA - MAX.SND.WND) <= SEG.ACK <= SND.NXT) get through. This can be refined for new (and possibly spoofed) flows, by not accepting ACK for bytes that were never sent. This greatly improves TCP security at a little cost. I added a Fixes: tag to make sure this patch will reach stable trees, even if the 'blamed' patch was adhering to the RFC. tp->bytes_acked was added in linux-4.2 Following packetdrill test (courtesy of Yepeng Pan) shows the issue at hand: 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 +0 bind(3, ..., ...) = 0 +0 listen(3, 1024) = 0 // ---------------- Handshake ------------------- // // when window scale is set to 14 the window size can be extended to // 65535 * (2^14) = 1073725440. Linux would accept an ACK packet // with ack number in (Server_ISN+1-1073725440. Server_ISN+1) // ,though this ack number acknowledges some data never // sent by the server. +0 < S 0:0(0) win 65535 +0 > S. 0:0(0) ack 1 <...> +0 < . 1:1(0) ack 1 win 65535 +0 accept(3, ..., ...) = 4 // For the established connection, we send an ACK packet, // the ack packet uses ack number 1 - 1073725300 + 2^32, // where 2^32 is used to wrap around. // Note: we used 1073725300 instead of 1073725440 to avoid possible // edge cases. // 1 - 1073725300 + 2^32 = 3221241997 // Oops, old kernels happily accept this packet. +0 < . 1:1001(1000) ack 3221241997 win 65535 // After the kernel fix the following will be replaced by a challenge ACK, // and prior malicious frame would be dropped. +0 > . 1:1(0) ack 1001 Fixes: 354e4aa391ed ("tcp: RFC 5961 5.2 Blind Data Injection Attack Mitigation") Signed-off-by: Eric Dumazet Reported-by: Yepeng Pan Reported-by: Christian Rossow Acked-by: Neal Cardwell Link: https://lore.kernel.org/r/20231205161841.2702925-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin Signed-off-by: Yongqiang Liu --- net/ipv4/tcp_input.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a12598dabb80..b3278fa1fcb8 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3630,8 +3630,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) * then we can probably ignore it. */ if (before(ack, prior_snd_una)) { + u32 max_window; + + /* do not accept ACK for bytes we never sent. */ + max_window = min_t(u64, tp->max_window, tp->bytes_acked); /* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */ - if (before(ack, prior_snd_una - tp->max_window)) { + if (before(ack, prior_snd_una - max_window)) { if (!(flag & FLAG_NO_CHALLENGE_ACK)) tcp_send_challenge_ack(sk, skb); return -1; -- Gitee From b2486f8ad86218b034ccaf37fe882f676cc9d122 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 8 Jan 2024 19:06:28 +0800 Subject: [PATCH 11/12] packet: Move reference count in packet_sock to atomic_long_t stable inclusion from stable-v4.19.302 commit f7fc9d47f0ad7cd2202497491ee378ee90460960 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8UH13 CVE: NA -------------------------------- commit db3fadacaf0c817b222090290d06ca2a338422d0 upstream. In some potential instances the reference count on struct packet_sock could be saturated and cause overflows which gets the kernel a bit confused. To prevent this, move to a 64-bit atomic reference count on 64-bit architectures to prevent the possibility of this type to overflow. Because we can not handle saturation, using refcount_t is not possible in this place. Maybe someday in the future if it changes it could be used. Also, instead of using plain atomic64_t, use atomic_long_t instead. 32-bit machines tend to be memory-limited (i.e. anything that increases a reference uses so much memory that you can't actually get to 2**32 references). 32-bit architectures also tend to have serious problems with 64-bit atomics. Hence, atomic_long_t is the more natural solution. Reported-by: "The UK's National Cyber Security Centre (NCSC)" Co-developed-by: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman Signed-off-by: Daniel Borkmann Cc: Linus Torvalds Cc: stable@kernel.org Reviewed-by: Willem de Bruijn Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20231201131021.19999-1-daniel@iogearbox.net Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman Signed-off-by: Yongqiang Liu --- net/packet/af_packet.c | 16 ++++++++-------- net/packet/internal.h | 2 +- 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 4e3766a72540..56eed0c707ee 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -4212,7 +4212,7 @@ static void packet_mm_open(struct vm_area_struct *vma) struct sock *sk = sock->sk; if (sk) - atomic_inc(&pkt_sk(sk)->mapped); + atomic_long_inc(&pkt_sk(sk)->mapped); } static void packet_mm_close(struct vm_area_struct *vma) @@ -4222,7 +4222,7 @@ static void packet_mm_close(struct vm_area_struct *vma) struct sock *sk = sock->sk; if (sk) - atomic_dec(&pkt_sk(sk)->mapped); + atomic_long_dec(&pkt_sk(sk)->mapped); } static const struct vm_operations_struct packet_mmap_ops = { @@ -4317,7 +4317,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, err = -EBUSY; if (!closing) { - if (atomic_read(&po->mapped)) + if (atomic_long_read(&po->mapped)) goto out; if (packet_read_pending(rb)) goto out; @@ -4420,7 +4420,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, err = -EBUSY; mutex_lock(&po->pg_vec_lock); - if (closing || atomic_read(&po->mapped) == 0) { + if (closing || atomic_long_read(&po->mapped) == 0) { err = 0; spin_lock_bh(&rb_queue->lock); swap(rb->pg_vec, pg_vec); @@ -4438,9 +4438,9 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, po->prot_hook.func = (po->rx_ring.pg_vec) ? tpacket_rcv : packet_rcv; skb_queue_purge(rb_queue); - if (atomic_read(&po->mapped)) - pr_err("packet_mmap: vma is busy: %d\n", - atomic_read(&po->mapped)); + if (atomic_long_read(&po->mapped)) + pr_err("packet_mmap: vma is busy: %ld\n", + atomic_long_read(&po->mapped)); } mutex_unlock(&po->pg_vec_lock); @@ -4518,7 +4518,7 @@ static int packet_mmap(struct file *file, struct socket *sock, } } - atomic_inc(&po->mapped); + atomic_long_inc(&po->mapped); vma->vm_ops = &packet_mmap_ops; err = 0; diff --git a/net/packet/internal.h b/net/packet/internal.h index 2b2b85dadf8e..878fcdca8c25 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -125,7 +125,7 @@ struct packet_sock { __be16 num; struct packet_rollover *rollover; struct packet_mclist *mclist; - atomic_t mapped; + atomic_long_t mapped; enum tpacket_versions tp_version; unsigned int tp_hdrlen; unsigned int tp_reserve; -- Gitee From ff206ede930b650392cdff9a57cccd69f1a0f078 Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Mon, 8 Jan 2024 19:06:29 +0800 Subject: [PATCH 12/12] team: Fix use-after-free when an option instance allocation fails stable inclusion from stable-v4.19.303 commit e900ebbc511d2493123c1fd83d5665fa2ad12eff category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8UH13 CVE: NA -------------------------------- commit c12296bbecc488623b7d1932080e394d08f3226b upstream. In __team_options_register, team_options are allocated and appended to the team's option_list. If one option instance allocation fails, the "inst_rollback" cleanup path frees the previously allocated options but doesn't remove them from the team's option_list. This leaves dangling pointers that can be dereferenced later by other parts of the team driver that iterate over options. This patch fixes the cleanup path to remove the dangling pointers from the list. As far as I can tell, this uaf doesn't have much security implications since it would be fairly hard to exploit (an attacker would need to make the allocation of that specific small object fail) but it's still nice to fix. Cc: stable@vger.kernel.org Fixes: 80f7c6683fe0 ("team: add support for per-port options") Signed-off-by: Florent Revest Reviewed-by: Jiri Pirko Reviewed-by: Hangbin Liu Link: https://lore.kernel.org/r/20231206123719.1963153-1-revest@chromium.org Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman Signed-off-by: Yongqiang Liu --- drivers/net/team/team.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 2f13181137ee..44263bd823f6 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -291,8 +291,10 @@ static int __team_options_register(struct team *team, return 0; inst_rollback: - for (i--; i >= 0; i--) + for (i--; i >= 0; i--) { __team_option_inst_del_option(team, dst_opts[i]); + list_del(&dst_opts[i]->list); + } i = option_count - 1; alloc_rollback: -- Gitee