Ido Schimmel 2d300ce0b7 net: fib_rules: Fix iif / oif matching on L3 master device
Before commit 40867d74c374 ("net: Add l3mdev index to flow struct and
avoid oif reset for port devices") it was possible to use FIB rules to
match on a L3 domain. This was done by having a FIB rule match on iif /
oif being a L3 master device. It worked because prior to the FIB rule
lookup the iif / oif fields in the flow structure were reset to the
index of the L3 master device to which the input / output device was
enslaved to.

The above scheme made it impossible to match on the original input /
output device. Therefore, cited commit stopped overwriting the iif / oif
fields in the flow structure and instead stored the index of the
enslaving L3 master device in a new field ('flowi_l3mdev') in the flow
structure.

While the change enabled new use cases, it broke the original use case
of matching on a L3 domain. Fix this by interpreting the iif / oif
matching on a L3 master device as a match against the L3 domain. In
other words, if the iif / oif in the FIB rule points to a L3 master
device, compare the provided index against 'flowi_l3mdev' rather than
'flowi_{i,o}if'.

Before cited commit, a FIB rule that matched on 'iif vrf1' would only
match incoming traffic from devices enslaved to 'vrf1'. With the
proposed change (i.e., comparing against 'flowi_l3mdev'), the rule would
also match traffic originating from a socket bound to 'vrf1'. Avoid that
by adding a new flow flag ('FLOWI_FLAG_L3MDEV_OIF') that indicates if
the L3 domain was derived from the output interface or the input
interface (when not set) and take this flag into account when evaluating
the FIB rule against the flow structure.

Avoid unnecessary checks in the data path by detecting that a rule
matches on a L3 master device when the rule is installed and marking it
as such.

Tested using the following script [1].

Output before 40867d74c374 (v5.4.291):

default dev dummy1 table 100 scope link
default dev dummy1 table 200 scope link

Output after 40867d74c374:

default dev dummy1 table 300 scope link
default dev dummy1 table 300 scope link

Output with this patch:

default dev dummy1 table 100 scope link
default dev dummy1 table 200 scope link

[1]
 #!/bin/bash

 ip link add name vrf1 up type vrf table 10
 ip link add name dummy1 up master vrf1 type dummy

 sysctl -wq net.ipv4.conf.all.forwarding=1
 sysctl -wq net.ipv4.conf.all.rp_filter=0

 ip route add table 100 default dev dummy1
 ip route add table 200 default dev dummy1
 ip route add table 300 default dev dummy1

 ip rule add prio 0 oif vrf1 table 100
 ip rule add prio 1 iif vrf1 table 200
 ip rule add prio 2 table 300

 ip route get 192.0.2.1 oif dummy1 fibmatch
 ip route get 192.0.2.1 iif dummy1 from 198.51.100.1 fibmatch

Fixes: 40867d74c374 ("net: Add l3mdev index to flow struct and avoid oif reset for port devices")
Reported-by: hanhuihui <hanhuihui5@huawei.com>
Closes: https://lore.kernel.org/netdev/ec671c4f821a4d63904d0da15d604b75@huawei.com/
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250414172022.242991-2-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-04-15 17:54:56 -07:00

197 lines
5.0 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
*
* Generic internet FLOW.
*
*/
#ifndef _NET_FLOW_H
#define _NET_FLOW_H
#include <linux/in6.h>
#include <linux/atomic.h>
#include <linux/container_of.h>
#include <linux/uidgid.h>
struct flow_keys;
/*
* ifindex generation is per-net namespace, and loopback is
* always the 1st device in ns (see net_dev_init), thus any
* loopback device should get ifindex 1
*/
#define LOOPBACK_IFINDEX 1
struct flowi_tunnel {
__be64 tun_id;
};
struct flowi_common {
int flowic_oif;
int flowic_iif;
int flowic_l3mdev;
__u32 flowic_mark;
__u8 flowic_tos;
__u8 flowic_scope;
__u8 flowic_proto;
__u8 flowic_flags;
#define FLOWI_FLAG_ANYSRC 0x01
#define FLOWI_FLAG_KNOWN_NH 0x02
#define FLOWI_FLAG_L3MDEV_OIF 0x04
__u32 flowic_secid;
kuid_t flowic_uid;
__u32 flowic_multipath_hash;
struct flowi_tunnel flowic_tun_key;
};
union flowi_uli {
struct {
__be16 dport;
__be16 sport;
} ports;
struct {
__u8 type;
__u8 code;
} icmpt;
__be32 gre_key;
struct {
__u8 type;
} mht;
};
struct flowi4 {
struct flowi_common __fl_common;
#define flowi4_oif __fl_common.flowic_oif
#define flowi4_iif __fl_common.flowic_iif
#define flowi4_l3mdev __fl_common.flowic_l3mdev
#define flowi4_mark __fl_common.flowic_mark
#define flowi4_tos __fl_common.flowic_tos
#define flowi4_scope __fl_common.flowic_scope
#define flowi4_proto __fl_common.flowic_proto
#define flowi4_flags __fl_common.flowic_flags
#define flowi4_secid __fl_common.flowic_secid
#define flowi4_tun_key __fl_common.flowic_tun_key
#define flowi4_uid __fl_common.flowic_uid
#define flowi4_multipath_hash __fl_common.flowic_multipath_hash
/* (saddr,daddr) must be grouped, same order as in IP header */
__be32 saddr;
__be32 daddr;
union flowi_uli uli;
#define fl4_sport uli.ports.sport
#define fl4_dport uli.ports.dport
#define fl4_icmp_type uli.icmpt.type
#define fl4_icmp_code uli.icmpt.code
#define fl4_mh_type uli.mht.type
#define fl4_gre_key uli.gre_key
} __attribute__((__aligned__(BITS_PER_LONG/8)));
static inline void flowi4_init_output(struct flowi4 *fl4, int oif,
__u32 mark, __u8 tos, __u8 scope,
__u8 proto, __u8 flags,
__be32 daddr, __be32 saddr,
__be16 dport, __be16 sport,
kuid_t uid)
{
fl4->flowi4_oif = oif;
fl4->flowi4_iif = LOOPBACK_IFINDEX;
fl4->flowi4_l3mdev = 0;
fl4->flowi4_mark = mark;
fl4->flowi4_tos = tos;
fl4->flowi4_scope = scope;
fl4->flowi4_proto = proto;
fl4->flowi4_flags = flags;
fl4->flowi4_secid = 0;
fl4->flowi4_tun_key.tun_id = 0;
fl4->flowi4_uid = uid;
fl4->daddr = daddr;
fl4->saddr = saddr;
fl4->fl4_dport = dport;
fl4->fl4_sport = sport;
fl4->flowi4_multipath_hash = 0;
}
/* Reset some input parameters after previous lookup */
static inline void flowi4_update_output(struct flowi4 *fl4, int oif,
__be32 daddr, __be32 saddr)
{
fl4->flowi4_oif = oif;
fl4->daddr = daddr;
fl4->saddr = saddr;
}
struct flowi6 {
struct flowi_common __fl_common;
#define flowi6_oif __fl_common.flowic_oif
#define flowi6_iif __fl_common.flowic_iif
#define flowi6_l3mdev __fl_common.flowic_l3mdev
#define flowi6_mark __fl_common.flowic_mark
#define flowi6_scope __fl_common.flowic_scope
#define flowi6_proto __fl_common.flowic_proto
#define flowi6_flags __fl_common.flowic_flags
#define flowi6_secid __fl_common.flowic_secid
#define flowi6_tun_key __fl_common.flowic_tun_key
#define flowi6_uid __fl_common.flowic_uid
struct in6_addr daddr;
struct in6_addr saddr;
/* Note: flowi6_tos is encoded in flowlabel, too. */
__be32 flowlabel;
union flowi_uli uli;
#define fl6_sport uli.ports.sport
#define fl6_dport uli.ports.dport
#define fl6_icmp_type uli.icmpt.type
#define fl6_icmp_code uli.icmpt.code
#define fl6_mh_type uli.mht.type
#define fl6_gre_key uli.gre_key
__u32 mp_hash;
} __attribute__((__aligned__(BITS_PER_LONG/8)));
struct flowi {
union {
struct flowi_common __fl_common;
struct flowi4 ip4;
struct flowi6 ip6;
} u;
#define flowi_oif u.__fl_common.flowic_oif
#define flowi_iif u.__fl_common.flowic_iif
#define flowi_l3mdev u.__fl_common.flowic_l3mdev
#define flowi_mark u.__fl_common.flowic_mark
#define flowi_tos u.__fl_common.flowic_tos
#define flowi_scope u.__fl_common.flowic_scope
#define flowi_proto u.__fl_common.flowic_proto
#define flowi_flags u.__fl_common.flowic_flags
#define flowi_secid u.__fl_common.flowic_secid
#define flowi_tun_key u.__fl_common.flowic_tun_key
#define flowi_uid u.__fl_common.flowic_uid
} __attribute__((__aligned__(BITS_PER_LONG/8)));
static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4)
{
return container_of(fl4, struct flowi, u.ip4);
}
static inline struct flowi_common *flowi4_to_flowi_common(struct flowi4 *fl4)
{
return &(fl4->__fl_common);
}
static inline struct flowi *flowi6_to_flowi(struct flowi6 *fl6)
{
return container_of(fl6, struct flowi, u.ip6);
}
static inline struct flowi_common *flowi6_to_flowi_common(struct flowi6 *fl6)
{
return &(fl6->__fl_common);
}
__u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys);
#endif