linux/include/net/checksum.h
Paul Chaignon 6043b794c7 net: Fix checksum update for ILA adj-transport
During ILA address translations, the L4 checksums can be handled in
different ways. One of them, adj-transport, consist in parsing the
transport layer and updating any found checksum. This logic relies on
inet_proto_csum_replace_by_diff and produces an incorrect skb->csum when
in state CHECKSUM_COMPLETE.

This bug can be reproduced with a simple ILA to SIR mapping, assuming
packets are received with CHECKSUM_COMPLETE:

  $ ip a show dev eth0
  14: eth0@if15: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default qlen 1000
      link/ether 62:ae:35:9e:0f:8d brd ff:ff:ff:ff:ff:ff link-netnsid 0
      inet6 3333:0:0:1::c078/64 scope global
         valid_lft forever preferred_lft forever
      inet6 fd00:10:244:1::c078/128 scope global nodad
         valid_lft forever preferred_lft forever
      inet6 fe80::60ae:35ff:fe9e:f8d/64 scope link proto kernel_ll
         valid_lft forever preferred_lft forever
  $ ip ila add loc_match fd00:10:244:1 loc 3333:0:0:1 \
      csum-mode adj-transport ident-type luid dev eth0

Then I hit [fd00:10:244:1::c078]:8000 with a server listening only on
[3333:0:0:1::c078]:8000. With the bug, the SYN packet is dropped with
SKB_DROP_REASON_TCP_CSUM after inet_proto_csum_replace_by_diff changed
skb->csum. The translation and drop are visible on pwru [1] traces:

  IFACE   TUPLE                                                        FUNC
  eth0:9  [fd00:10:244:3::3d8]:51420->[fd00:10:244:1::c078]:8000(tcp)  ipv6_rcv
  eth0:9  [fd00:10:244:3::3d8]:51420->[fd00:10:244:1::c078]:8000(tcp)  ip6_rcv_core
  eth0:9  [fd00:10:244:3::3d8]:51420->[fd00:10:244:1::c078]:8000(tcp)  nf_hook_slow
  eth0:9  [fd00:10:244:3::3d8]:51420->[fd00:10:244:1::c078]:8000(tcp)  inet_proto_csum_replace_by_diff
  eth0:9  [fd00:10:244:3::3d8]:51420->[3333:0:0:1::c078]:8000(tcp)     tcp_v6_early_demux
  eth0:9  [fd00:10:244:3::3d8]:51420->[3333:0:0:1::c078]:8000(tcp)     ip6_route_input
  eth0:9  [fd00:10:244:3::3d8]:51420->[3333:0:0:1::c078]:8000(tcp)     ip6_input
  eth0:9  [fd00:10:244:3::3d8]:51420->[3333:0:0:1::c078]:8000(tcp)     ip6_input_finish
  eth0:9  [fd00:10:244:3::3d8]:51420->[3333:0:0:1::c078]:8000(tcp)     ip6_protocol_deliver_rcu
  eth0:9  [fd00:10:244:3::3d8]:51420->[3333:0:0:1::c078]:8000(tcp)     raw6_local_deliver
  eth0:9  [fd00:10:244:3::3d8]:51420->[3333:0:0:1::c078]:8000(tcp)     ipv6_raw_deliver
  eth0:9  [fd00:10:244:3::3d8]:51420->[3333:0:0:1::c078]:8000(tcp)     tcp_v6_rcv
  eth0:9  [fd00:10:244:3::3d8]:51420->[3333:0:0:1::c078]:8000(tcp)     __skb_checksum_complete
  eth0:9  [fd00:10:244:3::3d8]:51420->[3333:0:0:1::c078]:8000(tcp)     kfree_skb_reason(SKB_DROP_REASON_TCP_CSUM)
  eth0:9  [fd00:10:244:3::3d8]:51420->[3333:0:0:1::c078]:8000(tcp)     skb_release_head_state
  eth0:9  [fd00:10:244:3::3d8]:51420->[3333:0:0:1::c078]:8000(tcp)     skb_release_data
  eth0:9  [fd00:10:244:3::3d8]:51420->[3333:0:0:1::c078]:8000(tcp)     skb_free_head
  eth0:9  [fd00:10:244:3::3d8]:51420->[3333:0:0:1::c078]:8000(tcp)     kfree_skbmem

This is happening because inet_proto_csum_replace_by_diff is updating
skb->csum when it shouldn't. The L4 checksum is updated such that it
"cancels" the IPv6 address change in terms of checksum computation, so
the impact on skb->csum is null.

Note this would be different for an IPv4 packet since three fields
would be updated: the IPv4 address, the IP checksum, and the L4
checksum. Two would cancel each other and skb->csum would still need
to be updated to take the L4 checksum change into account.

This patch fixes it by passing an ipv6 flag to
inet_proto_csum_replace_by_diff, to skip the skb->csum update if we're
in the IPv6 case. Note the behavior of the only other user of
inet_proto_csum_replace_by_diff, the BPF subsystem, is left as is in
this patch and fixed in the subsequent patch.

With the fix, using the reproduction from above, I can confirm
skb->csum is not touched by inet_proto_csum_replace_by_diff and the TCP
SYN proceeds to the application after the ILA translation.

Link: https://github.com/cilium/pwru [1]
Fixes: 65d7ab8de5 ("net: Identifier Locator Addressing module")
Signed-off-by: Paul Chaignon <paul.chaignon@gmail.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://patch.msgid.link/b5539869e3550d46068504feb02d37653d939c0b.1748509484.git.paul.chaignon@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-05-30 19:53:51 -07:00

191 lines
4.8 KiB
C

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Checksumming functions for IP, TCP, UDP and so on
*
* Authors: Jorge Cwik, <jorge@laser.satlink.net>
* Arnt Gulbrandsen, <agulbra@nvg.unit.no>
* Borrows very liberally from tcp.c and ip.c, see those
* files for more names.
*/
#ifndef _CHECKSUM_H
#define _CHECKSUM_H
#include <linux/errno.h>
#include <asm/types.h>
#include <asm/byteorder.h>
#include <asm/checksum.h>
#if !defined(_HAVE_ARCH_COPY_AND_CSUM_FROM_USER) || !defined(HAVE_CSUM_COPY_USER)
#include <linux/uaccess.h>
#endif
#ifndef _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
static __always_inline
__wsum csum_and_copy_from_user (const void __user *src, void *dst,
int len)
{
if (copy_from_user(dst, src, len))
return 0;
return csum_partial(dst, len, ~0U);
}
#endif
#ifndef HAVE_CSUM_COPY_USER
static __always_inline __wsum csum_and_copy_to_user
(const void *src, void __user *dst, int len)
{
__wsum sum = csum_partial(src, len, ~0U);
if (copy_to_user(dst, src, len) == 0)
return sum;
return 0;
}
#endif
#ifndef _HAVE_ARCH_CSUM_AND_COPY
static __always_inline __wsum
csum_partial_copy_nocheck(const void *src, void *dst, int len)
{
memcpy(dst, src, len);
return csum_partial(dst, len, 0);
}
#endif
#ifndef HAVE_ARCH_CSUM_ADD
static __always_inline __wsum csum_add(__wsum csum, __wsum addend)
{
u32 res = (__force u32)csum;
res += (__force u32)addend;
return (__force __wsum)(res + (res < (__force u32)addend));
}
#endif
static __always_inline __wsum csum_sub(__wsum csum, __wsum addend)
{
return csum_add(csum, ~addend);
}
static __always_inline __sum16 csum16_add(__sum16 csum, __be16 addend)
{
u16 res = (__force u16)csum;
res += (__force u16)addend;
return (__force __sum16)(res + (res < (__force u16)addend));
}
static __always_inline __sum16 csum16_sub(__sum16 csum, __be16 addend)
{
return csum16_add(csum, ~addend);
}
#ifndef HAVE_ARCH_CSUM_SHIFT
static __always_inline __wsum csum_shift(__wsum sum, int offset)
{
/* rotate sum to align it with a 16b boundary */
if (offset & 1)
return (__force __wsum)ror32((__force u32)sum, 8);
return sum;
}
#endif
static __always_inline __wsum
csum_block_add(__wsum csum, __wsum csum2, int offset)
{
return csum_add(csum, csum_shift(csum2, offset));
}
static __always_inline __wsum
csum_block_sub(__wsum csum, __wsum csum2, int offset)
{
return csum_block_add(csum, ~csum2, offset);
}
static __always_inline __wsum csum_unfold(__sum16 n)
{
return (__force __wsum)n;
}
#define CSUM_MANGLED_0 ((__force __sum16)0xffff)
static __always_inline void csum_replace_by_diff(__sum16 *sum, __wsum diff)
{
*sum = csum_fold(csum_add(diff, ~csum_unfold(*sum)));
}
static __always_inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to)
{
__wsum tmp = csum_sub(~csum_unfold(*sum), (__force __wsum)from);
*sum = csum_fold(csum_add(tmp, (__force __wsum)to));
}
/* Implements RFC 1624 (Incremental Internet Checksum)
* 3. Discussion states :
* HC' = ~(~HC + ~m + m')
* m : old value of a 16bit field
* m' : new value of a 16bit field
*/
static __always_inline void csum_replace2(__sum16 *sum, __be16 old, __be16 new)
{
*sum = ~csum16_add(csum16_sub(~(*sum), old), new);
}
static inline void csum_replace(__wsum *csum, __wsum old, __wsum new)
{
*csum = csum_add(csum_sub(*csum, old), new);
}
static inline unsigned short csum_from32to16(unsigned int sum)
{
sum += (sum >> 16) | (sum << 16);
return (unsigned short)(sum >> 16);
}
struct sk_buff;
void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb,
__be32 from, __be32 to, bool pseudohdr);
void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb,
const __be32 *from, const __be32 *to,
bool pseudohdr);
void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb,
__wsum diff, bool pseudohdr, bool ipv6);
static __always_inline
void inet_proto_csum_replace2(__sum16 *sum, struct sk_buff *skb,
__be16 from, __be16 to, bool pseudohdr)
{
inet_proto_csum_replace4(sum, skb, (__force __be32)from,
(__force __be32)to, pseudohdr);
}
static __always_inline __wsum remcsum_adjust(void *ptr, __wsum csum,
int start, int offset)
{
__sum16 *psum = (__sum16 *)(ptr + offset);
__wsum delta;
/* Subtract out checksum up to start */
csum = csum_sub(csum, csum_partial(ptr, start, 0));
/* Set derived checksum in packet */
delta = csum_sub((__force __wsum)csum_fold(csum),
(__force __wsum)*psum);
*psum = csum_fold(csum);
return delta;
}
static __always_inline void remcsum_unadjust(__sum16 *psum, __wsum delta)
{
*psum = csum_fold(csum_sub(delta, (__force __wsum)*psum));
}
static __always_inline __wsum wsum_negate(__wsum val)
{
return (__force __wsum)-((__force u32)val);
}
#endif