Re: [PATCH net v2 1/2] net: Fix UDP length overflow with PMTU discover and big MTU

[Willem de Bruijn <willemdebruijn.kernel@gmail.com>]

Alice Mikityanska wrote:
> From: Alice Mikityanska <alice@isovalent.com>
> 
> This commit bounds cork->base.fragsize to IP(6)_MAX_MTU to avoid a
> possible overflow of UDP length that triggers a WARN in
> udp_set_len_short when setsockopt IP(V6)_MTU_DISCOVER is set to
> IPV6_PMTUDISC_DO or IP(V6)_PMTUDISC_PROBE, and a large packet is sent
> over a netdev with an unusually large MTU.
> 
> Steps to reproduce (included in the new selftest):
> 
> 1. Set device MTU bigger than IP6_MAX_MTU (or IP_MAX_MTU + 20).
>    cork->base.fragsize will be set to that MTU in ip(6)_setup_cork.
> 2. Set IP(V6)_MTU_DISCOVER to IP(V6)_PMTUDISC_PROBE or IPV6_PMTUDISC_DO.
>    It lets maxnonfragsize be set to device MTU (cork->fragsize) in
>    __ip(6)_append_data, rather than to IP(6)_MAX_MTU.
> 3. Send 65528 bytes of payload (+8 bytes of UDP header, +20/40 bytes of
>    IPv4/IPv6 header). Device MTU allows it (it's only one byte bigger
>    than IP6_MAX_MTU or IP_MAX_MTU + IPv4 header, and the device MTU is
>    bigger than that).
> 4. The UDP length in the built packet is 65536, which overflows the
>    16-bit length field and triggers the WARN in udp_set_len_short.
> 
> Note: IP_PMTUDISC_DO with IPv4 is safe, because ip_dst_mtu_maybe_forward
> always clamps at IP_MAX_MTU, unlike ip6_dst_mtu_maybe_forward.
> 
> The Fixes tag points at the first commit where I could reproduce the
> overflow with IPv4 and IP_PMTUDISC_PROBE.
> 
> Fixes: daba287b299e ("ipv4: fix DO and PROBE pmtu mode regarding local fragmentation with UFO/CORK")
> Reported-by: syzbot+ce13c07d96d04716eaa2@syzkaller.appspotmail.com
> Closes: https://lore.kernel.org/netdev/6a6a966c.86abc875.e5c3d.0054.GAE@google.com/
> Signed-off-by: Alice Mikityanska <alice@isovalent.com>
> Assisted-by: Claude:claude-sonnet-4.6
> Cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com>

Not sure whether IPv4 and IPv6 should be separate patches.
IPv6 will have a different Fixes tag.

Per maintainer-netdev.rst, mixing code and test changes in the same
patch is also discouraged.

> ---
>  net/ipv4/ip_output.c                         |  2 +
>  net/ipv6/ip6_output.c                        |  2 +-
>  tools/testing/selftests/net/Makefile         |  1 +
>  tools/testing/selftests/net/cork_fragsize.py | 77 ++++++++++++++++++++
>  4 files changed, 81 insertions(+), 1 deletion(-)
>  create mode 100755 tools/testing/selftests/net/cork_fragsize.py
> 
> diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
> index e6dd1e5b8c32..2bc997c4fa7b 100644
> --- a/net/ipv4/ip_output.c
> +++ b/net/ipv4/ip_output.c
> @@ -1299,6 +1299,8 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
>  
>  	cork->fragsize = ip_sk_use_pmtu(sk) ?
>  			 dst4_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu);
> +	if (cork->fragsize > IP_MAX_MTU)
> +		cork->fragsize = IP_MAX_MTU;

if respinning: use min(), like IPv6? It's even more concise and easier to read.

>  
>  	if (!inetdev_valid_mtu(cork->fragsize))
>  		return -ENETUNREACH;
> diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
> index 2c44e5ed6171..81fb61b94759 100644
> --- a/net/ipv6/ip6_output.c
> +++ b/net/ipv6/ip6_output.c
> @@ -1430,7 +1430,7 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
>  	if (frag_size && frag_size < mtu)
>  		mtu = frag_size;
>  
> -	cork->base.fragsize = mtu;
> +	cork->base.fragsize = min(mtu, IP6_MAX_MTU);

Not sure whether a limitation that we seriously have to care about, but:

This restricts all IPv6 protocols, while only UDP has the length field
limitation.

With IPv6 jumbo frames and RAW sockets, could there be a valid case
for larger fragsize?

>  	cork->base.gso_size = ipc6->gso_size;
>  	cork->base.tx_flags = 0;
>  	cork->base.mark = ipc6->sockc.mark;
> diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
> index 708d960ae07d..82a1407f6a69 100644
> --- a/tools/testing/selftests/net/Makefile
> +++ b/tools/testing/selftests/net/Makefile
> @@ -24,6 +24,7 @@ TEST_PROGS := \
>  	cmsg_so_mark.sh \
>  	cmsg_so_priority.sh \
>  	cmsg_time.sh \
> +	cork_fragsize.py \
>  	double_udp_encap.sh \
>  	drop_monitor_tests.sh \
>  	ecmp_rehash.sh \
> diff --git a/tools/testing/selftests/net/cork_fragsize.py b/tools/testing/selftests/net/cork_fragsize.py
> new file mode 100755
> index 000000000000..7a1bb069227a
> --- /dev/null
> +++ b/tools/testing/selftests/net/cork_fragsize.py
> @@ -0,0 +1,77 @@
> +#!/usr/bin/env python3
> +# SPDX-License-Identifier: GPL-2.0
> +
> +# Test possible UDP length overflow in udp_send_skb/udp_v6_send_skb.
> +
> +from lib.py import ksft_run, ksft_exit, ksft_true
> +from lib.py import ip, NetNS, NetNSEnter
> +import errno
> +import socket
> +import subprocess
> +
> +
> +IP_MTU_DISCOVER = 10
> +IP_PMTUDISC_PROBE = 3
> +IPV6_MTU_DISCOVER = 23
> +IPV6_PMTUDISC_DO = 2
> +
> +
> +def check_dmesg_clean(func) -> bool:
> +    dmesg = subprocess.Popen(['dmesg'], stdout=subprocess.PIPE)
> +    result = subprocess.run(['grep', '-q', f'WARNING:.*{func}'], stdin=dmesg.stdout)
> +    dmesg.wait()
> +    return result.returncode != 0 and dmesg.returncode == 0
> +
> +
> +def test_ipv6() -> None:
> +    with NetNS() as ns:
> +        ip('link add dummy type dummy', ns=ns)
> +        ip('link set dummy mtu 65576', ns=ns)
> +        ip('link set dummy up', ns=ns)
> +        ip('-6 addr add fd00::1/64 dev dummy nodad', ns=ns)
> +        ip('-6 neigh add fd00::2 lladdr 02:00:00:00:00:02 dev dummy nud permanent', ns=ns)
> +
> +        with NetNSEnter(ns):
> +            with socket.socket(socket.AF_INET6, socket.SOCK_DGRAM) as fd:
> +                fd.setsockopt(socket.IPPROTO_IPV6, IPV6_MTU_DISCOVER, IPV6_PMTUDISC_DO)
> +                try:
> +                    fd.sendto(b' ' * 65528, ('fd00::2', 1234))
> +                except OSError as e:
> +                    # Ignore EMSGSIZE: it happens on kernels with the fix.
> +                    if e.errno != errno.EMSGSIZE:
> +                        raise
> +
> +        ip('link del dummy', ns=ns)
> +
> +    ksft_true(check_dmesg_clean('udp_v6_send_skb'), 'WARNING detected in dmesg')
> +
> +
> +def test_ipv4() -> None:
> +    with NetNS() as ns:
> +        ip('link add dummy type dummy', ns=ns)
> +        ip('link set dummy mtu 65556', ns=ns)
> +        ip('link set dummy up', ns=ns)
> +        ip('addr add 10.0.0.1/24 dev dummy', ns=ns)
> +        ip('neigh add 10.0.0.2 lladdr 02:00:00:00:00:02 dev dummy nud permanent', ns=ns)
> +
> +        with NetNSEnter(ns):
> +            with socket.socket(socket.AF_INET, socket.SOCK_DGRAM) as fd:
> +                fd.setsockopt(socket.IPPROTO_IP, IP_MTU_DISCOVER, IP_PMTUDISC_PROBE)
> +                try:
> +                    fd.sendto(b' ' * 65528, ('10.0.0.2', 1234))
> +                except OSError as e:
> +                    # Ignore EMSGSIZE: the check happens after the WARN is printed.
> +                    if e.errno != errno.EMSGSIZE:
> +                        raise
> +
> +        ip('link del dummy', ns=ns)
> +
> +    ksft_true(check_dmesg_clean('udp_send_skb'), 'WARNING detected in dmesg')
> +
> +
> +if __name__ == "__main__":
> +    ksft_run([
> +        test_ipv6,
> +        test_ipv4,
> +    ])
> +    ksft_exit()
> -- 
> 2.55.0
>