linux/net/ipv4/ipcomp.c
Linus Torvalds dbe69e4337 Networking changes for 5.14.
Core:
 
  - BPF:
    - add syscall program type and libbpf support for generating
      instructions and bindings for in-kernel BPF loaders (BPF loaders
      for BPF), this is a stepping stone for signed BPF programs
    - infrastructure to migrate TCP child sockets from one listener
      to another in the same reuseport group/map to improve flexibility
      of service hand-off/restart
    - add broadcast support to XDP redirect
 
  - allow bypass of the lockless qdisc to improving performance
    (for pktgen: +23% with one thread, +44% with 2 threads)
 
  - add a simpler version of "DO_ONCE()" which does not require
    jump labels, intended for slow-path usage
 
  - virtio/vsock: introduce SOCK_SEQPACKET support
 
  - add getsocketopt to retrieve netns cookie
 
  - ip: treat lowest address of a IPv4 subnet as ordinary unicast address
        allowing reclaiming of precious IPv4 addresses
 
  - ipv6: use prandom_u32() for ID generation
 
  - ip: add support for more flexible field selection for hashing
        across multi-path routes (w/ offload to mlxsw)
 
  - icmp: add support for extended RFC 8335 PROBE (ping)
 
  - seg6: add support for SRv6 End.DT46 behavior
 
  - mptcp:
     - DSS checksum support (RFC 8684) to detect middlebox meddling
     - support Connection-time 'C' flag
     - time stamping support
 
  - sctp: packetization Layer Path MTU Discovery (RFC 8899)
 
  - xfrm: speed up state addition with seq set
 
  - WiFi:
     - hidden AP discovery on 6 GHz and other HE 6 GHz improvements
     - aggregation handling improvements for some drivers
     - minstrel improvements for no-ack frames
     - deferred rate control for TXQs to improve reaction times
     - switch from round robin to virtual time-based airtime scheduler
 
  - add trace points:
     - tcp checksum errors
     - openvswitch - action execution, upcalls
     - socket errors via sk_error_report
 
 Device APIs:
 
  - devlink: add rate API for hierarchical control of max egress rate
             of virtual devices (VFs, SFs etc.)
 
  - don't require RCU read lock to be held around BPF hooks
    in NAPI context
 
  - page_pool: generic buffer recycling
 
 New hardware/drivers:
 
  - mobile:
     - iosm: PCIe Driver for Intel M.2 Modem
     - support for Qualcomm MSM8998 (ipa)
 
  - WiFi: Qualcomm QCN9074 and WCN6855 PCI devices
 
  - sparx5: Microchip SparX-5 family of Enterprise Ethernet switches
 
  - Mellanox BlueField Gigabit Ethernet (control NIC of the DPU)
 
  - NXP SJA1110 Automotive Ethernet 10-port switch
 
  - Qualcomm QCA8327 switch support (qca8k)
 
  - Mikrotik 10/25G NIC (atl1c)
 
 Driver changes:
 
  - ACPI support for some MDIO, MAC and PHY devices from Marvell and NXP
    (our first foray into MAC/PHY description via ACPI)
 
  - HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx
 
  - Mellanox/Nvidia NIC (mlx5)
    - NIC VF offload of L2 bridging
    - support IRQ distribution to Sub-functions
 
  - Marvell (prestera):
     - add flower and match all
     - devlink trap
     - link aggregation
 
  - Netronome (nfp): connection tracking offload
 
  - Intel 1GE (igc): add AF_XDP support
 
  - Marvell DPU (octeontx2): ingress ratelimit offload
 
  - Google vNIC (gve): new ring/descriptor format support
 
  - Qualcomm mobile (rmnet & ipa): inline checksum offload support
 
  - MediaTek WiFi (mt76)
     - mt7915 MSI support
     - mt7915 Tx status reporting
     - mt7915 thermal sensors support
     - mt7921 decapsulation offload
     - mt7921 enable runtime pm and deep sleep
 
  - Realtek WiFi (rtw88)
     - beacon filter support
     - Tx antenna path diversity support
     - firmware crash information via devcoredump
 
  - Qualcomm 60GHz WiFi (wcn36xx)
     - Wake-on-WLAN support with magic packets and GTK rekeying
 
  - Micrel PHY (ksz886x/ksz8081): add cable test support
 
 Signed-off-by: Jakub Kicinski <kuba@kernel.org>
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEE6jPA+I1ugmIBA4hXMUZtbf5SIrsFAmDb+fUACgkQMUZtbf5S
 Irs2Jg//aqN0Q8CgIvYCVhPxQw1tY7pTAbgyqgBZ01vwjyvtIOgJiWzSfFEU84mX
 M8fcpFX5eTKrOyJ9S6UFfQ/JG114n3hjAxFFT4Hxk2gC1Tg0vHuFQTDHcUl28bUE
 mTm61e1YpdorILnv2k5JVQ/wu0vs5QKDrjcYcrcPnh+j93wvnPOgAfDBV95nZzjS
 OTt4q2fR8GzLcSYWWsclMbDNkzyTG50RW/0Yd6aGjr5QGvXfrMeXfUJNz533PMf/
 w5lNyjRKv+x9mdTZJzU0+msNUrZgUdRz7W8Ey8lD3hJZRE+D6/uU7FtsE8Mi3+uc
 HWxeZUyzA3YF1MfVl/eesbxyPT7S/OkLzk4O5B35FbqP0YltaP+bOjq1/nM3ce1/
 io9Dx9pIl/2JANUgRCAtLi8Z2dkvRoqTaBxZ/nPudCCljFwDwl6joTMJ7Ow22i5Y
 5aIkcXFmZq4LbJDiHvbTlqT7yiuaEvu2UK/23bSIg/K3nF4eAmkY9Y1EgiMf60OF
 78Ttw0wk2tUegwaS5MZnCniKBKDyl9gM2F6rbZ/IxQRR2LTXFc1B6gC+ynUxgXfh
 Ub8O++6qGYGYZ0XvQH4pzco79p3qQWBTK5beIp2eu6BOAjBVIXq4AibUfoQLACsu
 hX7jMPYd0kc3WFgUnKgQP8EnjFSwbf4XiaE7fIXvWBY8hzCw2h4=
 =LvtX
 -----END PGP SIGNATURE-----

Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - BPF:
      - add syscall program type and libbpf support for generating
        instructions and bindings for in-kernel BPF loaders (BPF loaders
        for BPF), this is a stepping stone for signed BPF programs
      - infrastructure to migrate TCP child sockets from one listener to
        another in the same reuseport group/map to improve flexibility
        of service hand-off/restart
      - add broadcast support to XDP redirect

   - allow bypass of the lockless qdisc to improving performance (for
     pktgen: +23% with one thread, +44% with 2 threads)

   - add a simpler version of "DO_ONCE()" which does not require jump
     labels, intended for slow-path usage

   - virtio/vsock: introduce SOCK_SEQPACKET support

   - add getsocketopt to retrieve netns cookie

   - ip: treat lowest address of a IPv4 subnet as ordinary unicast
     address allowing reclaiming of precious IPv4 addresses

   - ipv6: use prandom_u32() for ID generation

   - ip: add support for more flexible field selection for hashing
     across multi-path routes (w/ offload to mlxsw)

   - icmp: add support for extended RFC 8335 PROBE (ping)

   - seg6: add support for SRv6 End.DT46 behavior

   - mptcp:
      - DSS checksum support (RFC 8684) to detect middlebox meddling
      - support Connection-time 'C' flag
      - time stamping support

   - sctp: packetization Layer Path MTU Discovery (RFC 8899)

   - xfrm: speed up state addition with seq set

   - WiFi:
      - hidden AP discovery on 6 GHz and other HE 6 GHz improvements
      - aggregation handling improvements for some drivers
      - minstrel improvements for no-ack frames
      - deferred rate control for TXQs to improve reaction times
      - switch from round robin to virtual time-based airtime scheduler

   - add trace points:
      - tcp checksum errors
      - openvswitch - action execution, upcalls
      - socket errors via sk_error_report

  Device APIs:

   - devlink: add rate API for hierarchical control of max egress rate
     of virtual devices (VFs, SFs etc.)

   - don't require RCU read lock to be held around BPF hooks in NAPI
     context

   - page_pool: generic buffer recycling

  New hardware/drivers:

   - mobile:
      - iosm: PCIe Driver for Intel M.2 Modem
      - support for Qualcomm MSM8998 (ipa)

   - WiFi: Qualcomm QCN9074 and WCN6855 PCI devices

   - sparx5: Microchip SparX-5 family of Enterprise Ethernet switches

   - Mellanox BlueField Gigabit Ethernet (control NIC of the DPU)

   - NXP SJA1110 Automotive Ethernet 10-port switch

   - Qualcomm QCA8327 switch support (qca8k)

   - Mikrotik 10/25G NIC (atl1c)

  Driver changes:

   - ACPI support for some MDIO, MAC and PHY devices from Marvell and
     NXP (our first foray into MAC/PHY description via ACPI)

   - HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx

   - Mellanox/Nvidia NIC (mlx5)
      - NIC VF offload of L2 bridging
      - support IRQ distribution to Sub-functions

   - Marvell (prestera):
      - add flower and match all
      - devlink trap
      - link aggregation

   - Netronome (nfp): connection tracking offload

   - Intel 1GE (igc): add AF_XDP support

   - Marvell DPU (octeontx2): ingress ratelimit offload

   - Google vNIC (gve): new ring/descriptor format support

   - Qualcomm mobile (rmnet & ipa): inline checksum offload support

   - MediaTek WiFi (mt76)
      - mt7915 MSI support
      - mt7915 Tx status reporting
      - mt7915 thermal sensors support
      - mt7921 decapsulation offload
      - mt7921 enable runtime pm and deep sleep

   - Realtek WiFi (rtw88)
      - beacon filter support
      - Tx antenna path diversity support
      - firmware crash information via devcoredump

   - Qualcomm WiFi (wcn36xx)
      - Wake-on-WLAN support with magic packets and GTK rekeying

   - Micrel PHY (ksz886x/ksz8081): add cable test support"

* tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits)
  tcp: change ICSK_CA_PRIV_SIZE definition
  tcp_yeah: check struct yeah size at compile time
  gve: DQO: Fix off by one in gve_rx_dqo()
  stmmac: intel: set PCI_D3hot in suspend
  stmmac: intel: Enable PHY WOL option in EHL
  net: stmmac: option to enable PHY WOL with PMT enabled
  net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del}
  net: use netdev_info in ndo_dflt_fdb_{add,del}
  ptp: Set lookup cookie when creating a PTP PPS source.
  net: sock: add trace for socket errors
  net: sock: introduce sk_error_report
  net: dsa: replay the local bridge FDB entries pointing to the bridge dev too
  net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev
  net: dsa: include fdb entries pointing to bridge in the host fdb list
  net: dsa: include bridge addresses which are local in the host fdb list
  net: dsa: sync static FDB entries on foreign interfaces to hardware
  net: dsa: install the host MDB and FDB entries in the master's RX filter
  net: dsa: reference count the FDB addresses at the cross-chip notifier level
  net: dsa: introduce a separate cross-chip notifier type for host FDBs
  net: dsa: reference count the MDB entries at the cross-chip notifier level
  ...
2021-06-30 15:51:09 -07:00

201 lines
4.4 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* IP Payload Compression Protocol (IPComp) - RFC3173.
*
* Copyright (c) 2003 James Morris <jmorris@intercode.com.au>
*
* Todo:
* - Tunable compression parameters.
* - Compression stats.
* - Adaptive compression.
*/
#include <linux/module.h>
#include <linux/err.h>
#include <linux/rtnetlink.h>
#include <net/ip.h>
#include <net/xfrm.h>
#include <net/icmp.h>
#include <net/ipcomp.h>
#include <net/protocol.h>
#include <net/sock.h>
static int ipcomp4_err(struct sk_buff *skb, u32 info)
{
struct net *net = dev_net(skb->dev);
__be32 spi;
const struct iphdr *iph = (const struct iphdr *)skb->data;
struct ip_comp_hdr *ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2));
struct xfrm_state *x;
switch (icmp_hdr(skb)->type) {
case ICMP_DEST_UNREACH:
if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
return 0;
break;
case ICMP_REDIRECT:
break;
default:
return 0;
}
spi = htonl(ntohs(ipch->cpi));
x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
spi, IPPROTO_COMP, AF_INET);
if (!x)
return 0;
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, IPPROTO_COMP);
else
ipv4_redirect(skb, net, 0, IPPROTO_COMP);
xfrm_state_put(x);
return 0;
}
/* We always hold one tunnel user reference to indicate a tunnel */
static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x)
{
struct net *net = xs_net(x);
struct xfrm_state *t;
t = xfrm_state_alloc(net);
if (!t)
goto out;
t->id.proto = IPPROTO_IPIP;
t->id.spi = x->props.saddr.a4;
t->id.daddr.a4 = x->id.daddr.a4;
memcpy(&t->sel, &x->sel, sizeof(t->sel));
t->props.family = AF_INET;
t->props.mode = x->props.mode;
t->props.saddr.a4 = x->props.saddr.a4;
t->props.flags = x->props.flags;
t->props.extra_flags = x->props.extra_flags;
memcpy(&t->mark, &x->mark, sizeof(t->mark));
t->if_id = x->if_id;
if (xfrm_init_state(t))
goto error;
atomic_set(&t->tunnel_users, 1);
out:
return t;
error:
t->km.state = XFRM_STATE_DEAD;
xfrm_state_put(t);
t = NULL;
goto out;
}
/*
* Must be protected by xfrm_cfg_mutex. State and tunnel user references are
* always incremented on success.
*/
static int ipcomp_tunnel_attach(struct xfrm_state *x)
{
struct net *net = xs_net(x);
int err = 0;
struct xfrm_state *t;
u32 mark = x->mark.v & x->mark.m;
t = xfrm_state_lookup(net, mark, (xfrm_address_t *)&x->id.daddr.a4,
x->props.saddr.a4, IPPROTO_IPIP, AF_INET);
if (!t) {
t = ipcomp_tunnel_create(x);
if (!t) {
err = -EINVAL;
goto out;
}
xfrm_state_insert(t);
xfrm_state_hold(t);
}
x->tunnel = t;
atomic_inc(&t->tunnel_users);
out:
return err;
}
static int ipcomp4_init_state(struct xfrm_state *x)
{
int err = -EINVAL;
x->props.header_len = 0;
switch (x->props.mode) {
case XFRM_MODE_TRANSPORT:
break;
case XFRM_MODE_TUNNEL:
x->props.header_len += sizeof(struct iphdr);
break;
default:
goto out;
}
err = ipcomp_init_state(x);
if (err)
goto out;
if (x->props.mode == XFRM_MODE_TUNNEL) {
err = ipcomp_tunnel_attach(x);
if (err)
goto out;
}
err = 0;
out:
return err;
}
static int ipcomp4_rcv_cb(struct sk_buff *skb, int err)
{
return 0;
}
static const struct xfrm_type ipcomp_type = {
.owner = THIS_MODULE,
.proto = IPPROTO_COMP,
.init_state = ipcomp4_init_state,
.destructor = ipcomp_destroy,
.input = ipcomp_input,
.output = ipcomp_output
};
static struct xfrm4_protocol ipcomp4_protocol = {
.handler = xfrm4_rcv,
.input_handler = xfrm_input,
.cb_handler = ipcomp4_rcv_cb,
.err_handler = ipcomp4_err,
.priority = 0,
};
static int __init ipcomp4_init(void)
{
if (xfrm_register_type(&ipcomp_type, AF_INET) < 0) {
pr_info("%s: can't add xfrm type\n", __func__);
return -EAGAIN;
}
if (xfrm4_protocol_register(&ipcomp4_protocol, IPPROTO_COMP) < 0) {
pr_info("%s: can't add protocol\n", __func__);
xfrm_unregister_type(&ipcomp_type, AF_INET);
return -EAGAIN;
}
return 0;
}
static void __exit ipcomp4_fini(void)
{
if (xfrm4_protocol_deregister(&ipcomp4_protocol, IPPROTO_COMP) < 0)
pr_info("%s: can't remove protocol\n", __func__);
xfrm_unregister_type(&ipcomp_type, AF_INET);
}
module_init(ipcomp4_init);
module_exit(ipcomp4_fini);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("IP Payload Compression Protocol (IPComp/IPv4) - RFC3173");
MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>");
MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_COMP);