From 1799d8abeabc68ec05679292aaf6cba93b343c05 Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Tue, 27 Jan 2026 19:38:44 +0800 Subject: [PATCH 1/3] xfrm6: fix uninitialized saddr in xfrm6_get_saddr() xfrm6_get_saddr() does not check the return value of ipv6_dev_get_saddr(). When ipv6_dev_get_saddr() fails to find a suitable source address (returns -EADDRNOTAVAIL), saddr->in6 is left uninitialized, but xfrm6_get_saddr() still returns 0 (success). This causes the caller xfrm_tmpl_resolve_one() to use the uninitialized address in xfrm_state_find(), triggering KMSAN warning: ===================================================== BUG: KMSAN: uninit-value in xfrm_state_find+0x2424/0xa940 xfrm_state_find+0x2424/0xa940 xfrm_resolve_and_create_bundle+0x906/0x5a20 xfrm_lookup_with_ifid+0xcc0/0x3770 xfrm_lookup_route+0x63/0x2b0 ip_route_output_flow+0x1ce/0x270 udp_sendmsg+0x2ce1/0x3400 inet_sendmsg+0x1ef/0x2a0 __sock_sendmsg+0x278/0x3d0 __sys_sendto+0x593/0x720 __x64_sys_sendto+0x130/0x200 x64_sys_call+0x332b/0x3e70 do_syscall_64+0xd3/0xf80 entry_SYSCALL_64_after_hwframe+0x77/0x7f Local variable tmp.i.i created at: xfrm_resolve_and_create_bundle+0x3e3/0x5a20 xfrm_lookup_with_ifid+0xcc0/0x3770 ===================================================== Fix by checking the return value of ipv6_dev_get_saddr() and propagating the error. Fixes: a1e59abf8249 ("[XFRM]: Fix wildcard as tunnel source") Reported-by: syzbot+e136d86d34b42399a8b1@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/68bf1024.a70a0220.7a912.02c2.GAE@google.com/T/ Signed-off-by: Jiayuan Chen Signed-off-by: Jiayuan Chen Reviewed-by: Simon Horman Signed-off-by: Steffen Klassert --- net/ipv6/xfrm6_policy.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 1f19b6f14484..125ea9a5b8a0 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -57,6 +57,7 @@ static int xfrm6_get_saddr(xfrm_address_t *saddr, struct dst_entry *dst; struct net_device *dev; struct inet6_dev *idev; + int err; dst = xfrm6_dst_lookup(params); if (IS_ERR(dst)) @@ -68,9 +69,11 @@ static int xfrm6_get_saddr(xfrm_address_t *saddr, return -EHOSTUNREACH; } dev = idev->dev; - ipv6_dev_get_saddr(dev_net(dev), dev, ¶ms->daddr->in6, 0, - &saddr->in6); + err = ipv6_dev_get_saddr(dev_net(dev), dev, ¶ms->daddr->in6, 0, + &saddr->in6); dst_release(dst); + if (err) + return -EHOSTUNREACH; return 0; } From 0a4524bc69882a4ddb235bb6b279597721bda197 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 27 Jan 2026 14:49:23 +0200 Subject: [PATCH 2/3] xfrm: skip templates check for packet offload tunnel mode In packet offload, hardware is responsible to check templates. The result of its operation is forwarded through secpath by relevant drivers. That secpath is actually removed in __xfrm_policy_check2(). In case packet is forwarded, this secpath is reset in RX, but pushed again to TX where policy is rechecked again against dummy secpath in xfrm_policy_ok(). Such situation causes to unexpected XfrmInTmplMismatch increase. As a solution, simply skip template mismatch check. Fixes: 600258d555f0 ("xfrm: delete intermediate secpath entry in packet offload mode") Signed-off-by: Leon Romanovsky Reviewed-by: Jianbo Liu Reviewed-by: Cosmin Ratiu Signed-off-by: Tariq Toukan Reviewed-by: Simon Horman Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 62486f866975..5428185196a1 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3801,8 +3801,8 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, struct xfrm_tmpl *tp[XFRM_MAX_DEPTH]; struct xfrm_tmpl *stp[XFRM_MAX_DEPTH]; struct xfrm_tmpl **tpp = tp; + int i, k = 0; int ti = 0; - int i, k; sp = skb_sec_path(skb); if (!sp) @@ -3828,6 +3828,12 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, tpp = stp; } + if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET && sp == &dummy) + /* This policy template was already checked by HW + * and secpath was removed in __xfrm_policy_check2. + */ + goto out; + /* For each tunnel xfrm, find the first matching tmpl. * For each tmpl before that, find corresponding xfrm. * Order is _important_. Later we will implement @@ -3837,7 +3843,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, * verified to allow them to be skipped in future policy * checks (e.g. nested tunnels). */ - for (i = xfrm_nr-1, k = 0; i >= 0; i--) { + for (i = xfrm_nr - 1; i >= 0; i--) { k = xfrm_policy_ok(tpp[i], sp, k, family, if_id); if (k < 0) { if (k < -1) @@ -3853,6 +3859,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, goto reject; } +out: xfrm_pols_put(pols, npols); sp->verified_cnt = k; From 4efa91a28576054aae0e6dad9cba8fed8293aef8 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Fri, 30 Jan 2026 19:42:47 +0900 Subject: [PATCH 3/3] xfrm: always flush state and policy upon NETDEV_UNREGISTER event syzbot is reporting that "struct xfrm_state" refcount is leaking. unregister_netdevice: waiting for netdevsim0 to become free. Usage count = 2 ref_tracker: netdev@ffff888052f24618 has 1/1 users at __netdev_tracker_alloc include/linux/netdevice.h:4400 [inline] netdev_tracker_alloc include/linux/netdevice.h:4412 [inline] xfrm_dev_state_add+0x3a5/0x1080 net/xfrm/xfrm_device.c:316 xfrm_state_construct net/xfrm/xfrm_user.c:986 [inline] xfrm_add_sa+0x34ff/0x5fa0 net/xfrm/xfrm_user.c:1022 xfrm_user_rcv_msg+0x58e/0xc00 net/xfrm/xfrm_user.c:3507 netlink_rcv_skb+0x158/0x420 net/netlink/af_netlink.c:2550 xfrm_netlink_rcv+0x71/0x90 net/xfrm/xfrm_user.c:3529 netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline] netlink_unicast+0x5aa/0x870 net/netlink/af_netlink.c:1344 netlink_sendmsg+0x8c8/0xdd0 net/netlink/af_netlink.c:1894 sock_sendmsg_nosec net/socket.c:727 [inline] __sock_sendmsg net/socket.c:742 [inline] ____sys_sendmsg+0xa5d/0xc30 net/socket.c:2592 ___sys_sendmsg+0x134/0x1d0 net/socket.c:2646 __sys_sendmsg+0x16d/0x220 net/socket.c:2678 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xcd/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f This is because commit d77e38e612a0 ("xfrm: Add an IPsec hardware offloading API") implemented xfrm_dev_unregister() as no-op despite xfrm_dev_state_add() from xfrm_state_construct() acquires a reference to "struct net_device". I guess that that commit expected that NETDEV_DOWN event is fired before NETDEV_UNREGISTER event fires, and also assumed that xfrm_dev_state_add() is called only if (dev->features & NETIF_F_HW_ESP) != 0. Sabrina Dubroca identified steps to reproduce the same symptoms as below. echo 0 > /sys/bus/netdevsim/new_device dev=$(ls -1 /sys/bus/netdevsim/devices/netdevsim0/net/) ip xfrm state add src 192.168.13.1 dst 192.168.13.2 proto esp \ spi 0x1000 mode tunnel aead 'rfc4106(gcm(aes))' $key 128 \ offload crypto dev $dev dir out ethtool -K $dev esp-hw-offload off echo 0 > /sys/bus/netdevsim/del_device Like these steps indicate, the NETIF_F_HW_ESP bit can be cleared after xfrm_dev_state_add() acquired a reference to "struct net_device". Also, xfrm_dev_state_add() does not check for the NETIF_F_HW_ESP bit when acquiring a reference to "struct net_device". Commit 03891f820c21 ("xfrm: handle NETDEV_UNREGISTER for xfrm device") re-introduced the NETDEV_UNREGISTER event to xfrm_dev_event(), but that commit for unknown reason chose to share xfrm_dev_down() between the NETDEV_DOWN event and the NETDEV_UNREGISTER event. I guess that that commit missed the behavior in the previous paragraph. Therefore, we need to re-introduce xfrm_dev_unregister() in order to release the reference to "struct net_device" by unconditionally flushing state and policy. Reported-by: syzbot+881d65229ca4f9ae8c84@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=881d65229ca4f9ae8c84 Fixes: d77e38e612a0 ("xfrm: Add an IPsec hardware offloading API") Cc: Sabrina Dubroca Signed-off-by: Tetsuo Handa Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_device.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 52ae0e034d29..550457e4c4f0 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -544,6 +544,14 @@ static int xfrm_dev_down(struct net_device *dev) return NOTIFY_DONE; } +static int xfrm_dev_unregister(struct net_device *dev) +{ + xfrm_dev_state_flush(dev_net(dev), dev, true); + xfrm_dev_policy_flush(dev_net(dev), dev, true); + + return NOTIFY_DONE; +} + static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); @@ -556,8 +564,10 @@ static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void return xfrm_api_check(dev); case NETDEV_DOWN: - case NETDEV_UNREGISTER: return xfrm_dev_down(dev); + + case NETDEV_UNREGISTER: + return xfrm_dev_unregister(dev); } return NOTIFY_DONE; }