mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-18 00:24:39 +00:00
40867d74c3
The fundamental premise of VRF and l3mdev core code is binding a socket
to a device (l3mdev or netdev with an L3 domain) to indicate L3 scope.
Legacy code resets flowi_oif to the l3mdev losing any original port
device binding. Ben (among others) has demonstrated use cases where the
original port device binding is important and needs to be retained.
This patch handles that by adding a new entry to the common flow struct
that can indicate the l3mdev index for later rule and table matching
avoiding the need to reset flowi_oif.
In addition to allowing more use cases that require port device binds,
this patch brings a few datapath simplications:
1. l3mdev_fib_rule_match is only called when walking fib rules and
always after l3mdev_update_flow. That allows an optimization to bail
early for non-VRF type uses cases when flowi_l3mdev is not set. Also,
only that index needs to be checked for the FIB table id.
2. l3mdev_update_flow can be called with flowi_oif set to a l3mdev
(e.g., VRF) device. By resetting flowi_oif only for this case the
FLOWI_FLAG_SKIP_NH_OIF flag is not longer needed and can be removed,
removing several checks in the datapath. The flowi_iif path can be
simplified to only be called if the it is not loopback (loopback can
not be assigned to an L3 domain) and the l3mdev index is not already
set.
3. Avoid another device lookup in the output path when the fib lookup
returns a reject failure.
Note: 2 functional tests for local traffic with reject fib rules are
updated to reflect the new direct failure at FIB lookup time for ping
rather than the failure on packet path. The current code fails like this:
HINT: Fails since address on vrf device is out of device scope
COMMAND: ip netns exec ns-A ping -c1 -w1 -I eth1 172.16.3.1
ping: Warning: source address might be selected on device other than: eth1
PING 172.16.3.1 (172.16.3.1) from 172.16.3.1 eth1: 56(84) bytes of data.
--- 172.16.3.1 ping statistics ---
1 packets transmitted, 0 received, 100% packet loss, time 0ms
where the test now directly fails:
HINT: Fails since address on vrf device is out of device scope
COMMAND: ip netns exec ns-A ping -c1 -w1 -I eth1 172.16.3.1
ping: connect: No route to host
Signed-off-by: David Ahern <dsahern@kernel.org>
Tested-by: Ben Greear <greearb@candelatech.com>
Link: https://lore.kernel.org/r/20220314204551.16369-1-dsahern@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
221 lines
5.7 KiB
C
221 lines
5.7 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
*
|
|
* Generic internet FLOW.
|
|
*
|
|
*/
|
|
|
|
#ifndef _NET_FLOW_H
|
|
#define _NET_FLOW_H
|
|
|
|
#include <linux/socket.h>
|
|
#include <linux/in6.h>
|
|
#include <linux/atomic.h>
|
|
#include <net/flow_dissector.h>
|
|
#include <linux/uidgid.h>
|
|
|
|
/*
|
|
* 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
|
|
__u32 flowic_secid;
|
|
kuid_t flowic_uid;
|
|
struct flowi_tunnel flowic_tun_key;
|
|
__u32 flowic_multipath_hash;
|
|
};
|
|
|
|
union flowi_uli {
|
|
struct {
|
|
__be16 dport;
|
|
__be16 sport;
|
|
} ports;
|
|
|
|
struct {
|
|
__u8 type;
|
|
__u8 code;
|
|
} icmpt;
|
|
|
|
struct {
|
|
__le16 dport;
|
|
__le16 sport;
|
|
} dnports;
|
|
|
|
__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, __u8 tos,
|
|
__be32 daddr, __be32 saddr)
|
|
{
|
|
fl4->flowi4_oif = oif;
|
|
fl4->flowi4_tos = tos;
|
|
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 flowidn {
|
|
struct flowi_common __fl_common;
|
|
#define flowidn_oif __fl_common.flowic_oif
|
|
#define flowidn_iif __fl_common.flowic_iif
|
|
#define flowidn_mark __fl_common.flowic_mark
|
|
#define flowidn_scope __fl_common.flowic_scope
|
|
#define flowidn_proto __fl_common.flowic_proto
|
|
#define flowidn_flags __fl_common.flowic_flags
|
|
__le16 daddr;
|
|
__le16 saddr;
|
|
union flowi_uli uli;
|
|
#define fld_sport uli.ports.sport
|
|
#define fld_dport uli.ports.dport
|
|
} __attribute__((__aligned__(BITS_PER_LONG/8)));
|
|
|
|
struct flowi {
|
|
union {
|
|
struct flowi_common __fl_common;
|
|
struct flowi4 ip4;
|
|
struct flowi6 ip6;
|
|
struct flowidn dn;
|
|
} 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);
|
|
}
|
|
|
|
static inline struct flowi *flowidn_to_flowi(struct flowidn *fldn)
|
|
{
|
|
return container_of(fldn, struct flowi, u.dn);
|
|
}
|
|
|
|
__u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys);
|
|
|
|
#endif
|