From 3b9a324e646d3657a8d9806dfbfe4f3e4066e882 Mon Sep 17 00:00:00 2001 From: Qihang Tang Date: Wed, 5 Aug 2026 20:57:27 +0800 Subject: [PATCH 1/3] net: remove CAP_SYS_RAWIO zero-padding in dev_validate_header dev_validate_header() reads dev->hard_header_len directly when zero-padding short link layer headers for CAP_SYS_RAWIO holders: if (capable(CAP_SYS_RAWIO)) { memset(ll_header + len, 0, dev->hard_header_len - len); return true; } Packet send paths call dev_validate_header() on skbs whose headroom was allocated from an earlier hard_header_len read. If the device is reconfigured so that dev->hard_header_len increases before validation, the memset writes past the reserved buffer, an out-of-bounds write. This out-of-bounds write is masked in some SOCK_RAW paths today because the same concurrent increase can first make skb_push() exceed the reserved headroom and trigger skb_under_panic(). Remove the zero-padding branch before making those hard_header_len reads consistent, so the snapshot fixes do not turn a loud panic into a silent overwrite. This path is only reached for variable length L2 protocols, where len < hard_header_len but len >= min_header_len. No remaining in-tree variable length L2 protocol implements header_ops->validate, and the CAP_SYS_RAWIO bypass that zero-pads and accepts short headers has no real value beyond allowing testing of intentionally malformed input. Drop the CAP_SYS_RAWIO branch. The remaining reads of dev->hard_header_len in dev_validate_header() are comparisons only and have no memory safety impact. Suggested-by: Willem de Bruijn Fixes: 2793a23aacbd ("net: validate variable length ll headers") Cc: stable@vger.kernel.org Signed-off-by: Qihang Tang Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20260805125729.19220-2-q.h.hack.winter@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 5 ----- 1 file changed, 5 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9981d637f8b5..9a770eb823ce 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3531,11 +3531,6 @@ static inline bool dev_validate_header(const struct net_device *dev, if (len < dev->min_header_len) return false; - if (capable(CAP_SYS_RAWIO)) { - memset(ll_header + len, 0, dev->hard_header_len - len); - return true; - } - if (dev->header_ops && dev->header_ops->validate) return dev->header_ops->validate(ll_header, len); From 03390aa32e669cc4ecd7d34108e2e1afc13d689d Mon Sep 17 00:00:00 2001 From: Qihang Tang Date: Wed, 5 Aug 2026 20:57:28 +0800 Subject: [PATCH 2/3] packet: use consistent hard_header_len in non-ring send paths packet_snd() reads dev->hard_header_len multiple times while allocating and constructing an skb. Device reconfiguration can change this value concurrently, for example through bonding device type changes. For SOCK_RAW, packet_snd() can save a larger value in reserve and later allocate headroom using a smaller value. Moving skb->data back by reserve then places it before skb->head, and the following copy from userspace can attempt an out-of-bounds write. packet_sendmsg_spkt() has the same issue because it calculates its reservation and header offset from separate reads before dropping the RCU read lock to allocate the skb. Add LL_RESERVED_SPACE_EX() for callers that already saved a header length. Read hard_header_len once in packet_snd() and use it for allocation and construction. In packet_sendmsg_spkt(), preserve the allocation-time value through the device lookup retry. The separate SOCK_DGRAM consistency problem between hard_header_len and header_ops->create is not addressed here. Fixes: b84bbaf7a6c8 ("packet: in packet_snd start writing at link layer allocation") Cc: stable@vger.kernel.org Signed-off-by: Qihang Tang Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20260805125729.19220-3-q.h.hack.winter@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 6 ++++-- net/packet/af_packet.c | 26 ++++++++++++++++---------- 2 files changed, 20 insertions(+), 12 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9a770eb823ce..8840b126979f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -300,9 +300,11 @@ struct hh_cache { * We could use other alignment values, but we must maintain the * relationship HH alignment <= LL alignment. */ -#define LL_RESERVED_SPACE(dev) \ - ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom)) \ +#define LL_RESERVED_SPACE_EX(dev, hlen) \ + ((((hlen) + READ_ONCE((dev)->needed_headroom)) \ & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) +#define LL_RESERVED_SPACE(dev) \ + LL_RESERVED_SPACE_EX(dev, (dev)->hard_header_len) #define LL_RESERVED_SPACE_EXTRA(dev,extra) \ ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom) + (extra)) \ & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 0e1355be89f6..b7af45c809e4 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1966,8 +1966,9 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg, struct net_device *dev; struct sockcm_cookie sockc; __be16 proto = 0; - int err; + int hard_header_len; int extra_len = 0; + int err; /* * Get and verify the address. @@ -2010,14 +2011,18 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg, extra_len = 4; /* We're doing our own CRC */ } + /* Keep the allocation-time header length across retry. */ + if (!skb) + hard_header_len = READ_ONCE(dev->hard_header_len); + err = -EMSGSIZE; - if (len > dev->mtu + dev->hard_header_len + VLAN_HLEN + extra_len) + if (len > dev->mtu + hard_header_len + VLAN_HLEN + extra_len) goto out_unlock; if (!skb) { - size_t reserved = LL_RESERVED_SPACE(dev); + size_t reserved = LL_RESERVED_SPACE_EX(dev, hard_header_len); int tlen = dev->needed_tailroom; - unsigned int hhlen = dev->header_ops ? dev->hard_header_len : 0; + unsigned int hhlen = dev->header_ops ? hard_header_len : 0; rcu_read_unlock(); skb = sock_wmalloc(sk, len + reserved + tlen, 0, GFP_KERNEL); @@ -2047,7 +2052,7 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg, err = -EINVAL; goto out_unlock; } - if (len > (dev->mtu + dev->hard_header_len + extra_len) && + if (len > (dev->mtu + hard_header_len + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { err = -EMSGSIZE; goto out_unlock; @@ -2969,7 +2974,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) int offset = 0; struct packet_sock *po = pkt_sk(sk); int vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); - int hlen, tlen, linear; + int hard_header_len, hlen, tlen, linear; int extra_len = 0; /* @@ -3009,8 +3014,9 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_unlock; } + hard_header_len = READ_ONCE(dev->hard_header_len); if (sock->type == SOCK_RAW) - reserve = dev->hard_header_len; + reserve = hard_header_len; if (vnet_hdr_sz) { err = packet_snd_vnet_parse(msg, &len, &vnet_hdr, vnet_hdr_sz); if (err) @@ -3031,10 +3037,10 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_unlock; err = -ENOBUFS; - hlen = LL_RESERVED_SPACE(dev); + hlen = LL_RESERVED_SPACE_EX(dev, hard_header_len); tlen = dev->needed_tailroom; linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len); - linear = max(linear, min_t(int, len, dev->hard_header_len)); + linear = max(linear, min_t(int, len, hard_header_len)); skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, linear, msg->msg_flags & MSG_DONTWAIT, &err); if (skb == NULL) @@ -3050,7 +3056,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) } else if (reserve) { skb_reserve(skb, -reserve); if (len < reserve + sizeof(struct ipv6hdr) && - dev->min_header_len != dev->hard_header_len) + dev->min_header_len != hard_header_len) skb_reset_network_header(skb); } From 21b5953e7494c16a42e6cd8cf110e18d13ae4a6b Mon Sep 17 00:00:00 2001 From: Qihang Tang Date: Wed, 5 Aug 2026 20:57:29 +0800 Subject: [PATCH 3/3] packet: use consistent hard_header_len in TX_RING send path tpacket_snd() reads dev->hard_header_len independently for skb allocation and header construction in tpacket_fill_skb(). Concurrent netdevice reconfiguration can therefore make the reserved headroom smaller than the amount later pushed, or make copylen - hard_header_len negative. Snapshot hard_header_len once before processing ring frames and use it for the frame limit, headroom allocation, copy length, and skb construction. Pass the snapshot to tpacket_fill_skb(). The separate SOCK_DGRAM consistency problem between hard_header_len and header_ops->create is not addressed here. Fixes: 69e3c75f4d54 ("net: TX_RING and packet mmap") Cc: stable@vger.kernel.org Signed-off-by: Qihang Tang Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20260805125729.19220-4-q.h.hack.winter@gmail.com Signed-off-by: Jakub Kicinski --- net/packet/af_packet.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index b7af45c809e4..435756877aba 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2587,6 +2587,7 @@ static int packet_snd_vnet_parse(struct msghdr *msg, size_t *len, static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, void *frame, struct net_device *dev, void *data, int tp_len, __be16 proto, unsigned char *addr, int hlen, int copylen, + int hard_header_len, const struct sockcm_cookie *sockc) { union tpacket_uhdr ph; @@ -2618,8 +2619,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, } else if (copylen) { int hdrlen = min_t(int, copylen, tp_len); - skb_push(skb, dev->hard_header_len); - skb_put(skb, copylen - dev->hard_header_len); + skb_push(skb, hard_header_len); + skb_put(skb, copylen - hard_header_len); err = skb_store_bits(skb, 0, data, hdrlen); if (unlikely(err)) return err; @@ -2750,7 +2751,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) void *data; int len_sum = 0; int status = TP_STATUS_AVAILABLE; - int hlen, tlen, copylen = 0; + int hard_header_len, hlen, tlen, copylen = 0; long timeo; mutex_lock(&po->pg_vec_lock); @@ -2797,8 +2798,9 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) goto out_put; } + hard_header_len = READ_ONCE(dev->hard_header_len); if (po->sk.sk_socket->type == SOCK_RAW) - reserve = dev->hard_header_len; + reserve = hard_header_len; size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); @@ -2835,7 +2837,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) goto tpacket_error; status = TP_STATUS_SEND_REQUEST; - hlen = LL_RESERVED_SPACE(dev); + hlen = LL_RESERVED_SPACE_EX(dev, hard_header_len); tlen = dev->needed_tailroom; if (vnet_hdr_sz) { data += vnet_hdr_sz; @@ -2853,10 +2855,10 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) vnet_hdr.hdr_len); has_vnet_hdr = true; } - copylen = max_t(int, copylen, dev->hard_header_len); + copylen = max_t(int, copylen, hard_header_len); skb = sock_alloc_send_skb(&po->sk, hlen + tlen + sizeof(struct sockaddr_ll) + - (copylen - dev->hard_header_len), + (copylen - hard_header_len), !need_wait, &err); if (unlikely(skb == NULL)) { @@ -2866,7 +2868,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) goto out_status; } tp_len = tpacket_fill_skb(po, skb, ph, dev, data, tp_len, proto, - addr, hlen, copylen, &sockc); + addr, hlen, copylen, hard_header_len, + &sockc); if (likely(tp_len >= 0) && tp_len > dev->mtu + reserve && !vnet_hdr_sz &&