netdev - [PATCH net] xdp: use multi-buff only if receive queue supports page pool

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250924060843.2280499-1-tavip@google.com>
Date: Wed, 24 Sep 2025 06:08:42 +0000
From: Octavian Purdila <tavip@...gle.com>
To: kuba@...nel.org
Cc: davem@...emloft.net, edumazet@...gle.com, pabeni@...hat.com, 
	horms@...nel.org, ast@...nel.org, daniel@...earbox.net, hawk@...nel.org, 
	john.fastabend@...il.com, sdf@...ichev.me, uniyu@...gle.com, 
	ahmed.zaki@...el.com, aleksander.lobakin@...el.com, toke@...hat.com, 
	lorenzo@...nel.org, netdev@...r.kernel.org, bpf@...r.kernel.org, 
	Octavian Purdila <tavip@...gle.com>, syzbot+ff145014d6b0ce64a173@...kaller.appspotmail.com
Subject: [PATCH net] xdp: use multi-buff only if receive queue supports page pool

When a BPF program that supports BPF_F_XDP_HAS_FRAGS is issuing
bpf_xdp_adjust_tail and a large packet is injected via /dev/net/tun a
crash occurs due to detecting a bad page state (page_pool leak).

This is because xdp_buff does not record the type of memory and
instead relies on the netdev receive queue xdp info. Since the TUN/TAP
driver is using a MEM_TYPE_PAGE_SHARED memory model buffer, shrinking
will eventually call page_frag_free. But with current multi-buff
support for BPF_F_XDP_HAS_FRAGS programs buffers are allocated via the
page pool.

To fix this issue check that the receive queue memory mode is of
MEM_TYPE_PAGE_POOL before using multi-buffs.

Reported-by: syzbot+ff145014d6b0ce64a173@...kaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/6756c37b.050a0220.a30f1.019a.GAE@google.com/
Fixes: e6d5dbdd20aa ("xdp: add multi-buff support for xdp running in generic mode")
Signed-off-by: Octavian Purdila <tavip@...gle.com>
---
 net/core/dev.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 8d49b2198d07..b195ee3068c2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5335,13 +5335,18 @@ static int
 netif_skb_check_for_xdp(struct sk_buff **pskb, const struct bpf_prog *prog)
 {
 	struct sk_buff *skb = *pskb;
+	struct netdev_rx_queue *rxq;
 	int err, hroom, troom;
 
-	local_lock_nested_bh(&system_page_pool.bh_lock);
-	err = skb_cow_data_for_xdp(this_cpu_read(system_page_pool.pool), pskb, prog);
-	local_unlock_nested_bh(&system_page_pool.bh_lock);
-	if (!err)
-		return 0;
+	rxq = netif_get_rxqueue(skb);
+	if (rxq->xdp_rxq.mem.type == MEM_TYPE_PAGE_POOL) {
+		local_lock_nested_bh(&system_page_pool.bh_lock);
+		err = skb_cow_data_for_xdp(this_cpu_read(system_page_pool.pool),
+					   pskb, prog);
+		local_unlock_nested_bh(&system_page_pool.bh_lock);
+		if (!err)
+			return 0;
+	}
 
 	/* In case we have to go down the path and also linearize,
 	 * then lets do the pskb_expand_head() work just once here.
-- 
2.51.0.534.gc79095c0ca-goog