net: guard timestamp cmsgs to real error queue skbs

skb_is_err_queue() treats PACKET_OUTGOING as the sole marker for an skb
from sk_error_queue. That assumption is not true for AF_PACKET sockets:
outgoing packet taps are also delivered to packet sockets with
skb->pkt_type == PACKET_OUTGOING, but their skb->cb is owned by AF_PACKET
instead of struct sock_exterr_skb.

If such an skb is received with timestamping enabled, the generic
timestamp cmsg path can read AF_PACKET control-buffer state as
sock_exterr_skb::opt_stats. With SO_RXQ_OVFL enabled, the packet drop
counter overlaps opt_stats. An odd drop count makes the path emit
SCM_TIMESTAMPING_OPT_STATS with skb->len and skb->data. For non-linear
skbs this copies past the linear head and can trigger hardened usercopy or
disclose adjacent heap contents.

Keep skb_is_err_queue() local to net/socket.c, but make it verify that
the PACKET_OUTGOING marker is paired with the sock_rmem_free destructor
installed by sock_queue_err_skb(). AF_PACKET receive skbs use normal
receive ownership and no longer pass as error-queue skbs, while legitimate
sk_error_queue entries keep the PACKET_OUTGOING marker and sock_rmem_free
ownership.

Fixes: 8605330aac5a ("tcp: fix SCM_TIMESTAMPING_OPT_STATS for normal skbs")
Signed-off-by: Kyle Zeng <kylebot@openai.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20260607021819.49698-1-kylebot@openai.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/include/net/sock.h b/include/net/sock.h
index dccd3738c3687056b67c8de44fce9842dcc365ec..95e157eee8d9ba964e074828b2ce974850139691 100644 (file)
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1856,6 +1856,7 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
                             gfp_t priority);
 void skb_orphan_partial(struct sk_buff *skb);
 void sock_rfree(struct sk_buff *skb);
+void sock_rmem_free(struct sk_buff *skb);
 void sock_efree(struct sk_buff *skb);
 #ifdef CONFIG_INET
 void sock_edemux(struct sk_buff *skb);

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c02f0a507ba8c429f55471522dcf1f25c849d9eb..8eab8eb5006ab5dd6af51587ecb499e49e82d6e9 100644 (file)
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5450,7 +5450,7 @@ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer)
 }
 EXPORT_SYMBOL_GPL(skb_cow_data);
 
-static void sock_rmem_free(struct sk_buff *skb)
+void sock_rmem_free(struct sk_buff *skb)
 {
        struct sock *sk = skb->sk;
 
@@ -5459,8 +5459,8 @@ static void sock_rmem_free(struct sk_buff *skb)
 
 static void skb_set_err_queue(struct sk_buff *skb)
 {
-       /* pkt_type of skbs received on local sockets is never PACKET_OUTGOING.
-        * So, it is safe to (mis)use it to mark skbs on the error queue.
+       /* The error-queue test in skb_is_err_queue() matches this marker
+        * with the sock_rmem_free destructor installed by sock_queue_err_skb().
         */
        skb->pkt_type = PACKET_OUTGOING;
        BUILD_BUG_ON(PACKET_OUTGOING == 0);

diff --git a/net/socket.c b/net/socket.c
index 22a412fdec079cf8fd829a15236de9daea09d2f2..c2698a1441a7ddce2c5ca276ed573b29a13f1cc0 100644 (file)
--- a/net/socket.c
+++ b/net/socket.c
@@ -852,12 +852,13 @@ EXPORT_SYMBOL(kernel_sendmsg);
 
 static bool skb_is_err_queue(const struct sk_buff *skb)
 {
-       /* pkt_type of skbs enqueued on the error queue are set to
-        * PACKET_OUTGOING in skb_set_err_queue(). This is only safe to do
-        * in recvmsg, since skbs received on a local socket will never
-        * have a pkt_type of PACKET_OUTGOING.
+       /* Error-queue skbs are marked as PACKET_OUTGOING in
+        * skb_set_err_queue() and use the destructor installed by
+        * sock_queue_err_skb(). PACKET_OUTGOING alone is not unique:
+        * AF_PACKET outgoing taps use the same pkt_type.
         */
-       return skb->pkt_type == PACKET_OUTGOING;
+       return skb->pkt_type == PACKET_OUTGOING &&
+              skb->destructor == sock_rmem_free;
 }
 
 /* On transmit, software and hardware timestamps are returned independently.