Initial commit: Linux kernel 4.19 for Unplugged OS

This commit is contained in:
ziv committed 2025-10-06 13:52:42 +00:00
commit d30235b04c
80519 files changed
+35800681

No files matched your search

+756
View File
@@ -0,0 +1,756 @@
#
# IP configuration
#
config IP_MULTICAST
bool "IP: multicasting"
help
This is code for addressing several networked computers at once,
enlarging your kernel by about 2 KB. You need multicasting if you
intend to participate in the MBONE, a high bandwidth network on top
of the Internet which carries audio and video broadcasts. More
information about the MBONE is on the WWW at
<http://www.savetz.com/mbone/>. For most people, it's safe to say N.
config IP_ADVANCED_ROUTER
bool "IP: advanced router"
---help---
If you intend to run your Linux box mostly as a router, i.e. as a
computer that forwards and redistributes network packets, say Y; you
will then be presented with several options that allow more precise
control about the routing process.
The answer to this question won't directly affect the kernel:
answering N will just cause the configurator to skip all the
questions about advanced routing.
Note that your box can only act as a router if you enable IP
forwarding in your kernel; you can do that by saying Y to "/proc
file system support" and "Sysctl support" below and executing the
line
echo "1" > /proc/sys/net/ipv4/ip_forward
at boot time after the /proc file system has been mounted.
If you turn on IP forwarding, you should consider the rp_filter, which
automatically rejects incoming packets if the routing table entry
for their source address doesn't match the network interface they're
arriving on. This has security advantages because it prevents the
so-called IP spoofing, however it can pose problems if you use
asymmetric routing (packets from you to a host take a different path
than packets from that host to you) or if you operate a non-routing
host which has several IP addresses on different interfaces. To turn
rp_filter on use:
echo 1 > /proc/sys/net/ipv4/conf/<device>/rp_filter
or
echo 1 > /proc/sys/net/ipv4/conf/all/rp_filter
Note that some distributions enable it in startup scripts.
For details about rp_filter strict and loose mode read
<file:Documentation/networking/ip-sysctl.txt>.
If unsure, say N here.
config IP_FIB_TRIE_STATS
bool "FIB TRIE statistics"
depends on IP_ADVANCED_ROUTER
---help---
Keep track of statistics on structure of FIB TRIE table.
Useful for testing and measuring TRIE performance.
config IP_MULTIPLE_TABLES
bool "IP: policy routing"
depends on IP_ADVANCED_ROUTER
select FIB_RULES
---help---
Normally, a router decides what to do with a received packet based
solely on the packet's final destination address. If you say Y here,
the Linux router will also be able to take the packet's source
address into account. Furthermore, the TOS (Type-Of-Service) field
of the packet can be used for routing decisions as well.
If you need more information, see the Linux Advanced
Routing and Traffic Control documentation at
<http://lartc.org/howto/lartc.rpdb.html>
If unsure, say N.
config IP_ROUTE_MULTIPATH
bool "IP: equal cost multipath"
depends on IP_ADVANCED_ROUTER
help
Normally, the routing tables specify a single action to be taken in
a deterministic manner for a given packet. If you say Y here
however, it becomes possible to attach several actions to a packet
pattern, in effect specifying several alternative paths to travel
for those packets. The router considers all these paths to be of
equal "cost" and chooses one of them in a non-deterministic fashion
if a matching packet arrives.
config IP_ROUTE_VERBOSE
bool "IP: verbose route monitoring"
depends on IP_ADVANCED_ROUTER
help
If you say Y here, which is recommended, then the kernel will print
verbose messages regarding the routing, for example warnings about
received packets which look strange and could be evidence of an
attack or a misconfigured system somewhere. The information is
handled by the klogd daemon which is responsible for kernel messages
("man klogd").
config IP_ROUTE_CLASSID
bool
config IP_PNP
bool "IP: kernel level autoconfiguration"
help
This enables automatic configuration of IP addresses of devices and
of the routing table during kernel boot, based on either information
supplied on the kernel command line or by BOOTP or RARP protocols.
You need to say Y only for diskless machines requiring network
access to boot (in which case you want to say Y to "Root file system
on NFS" as well), because all other machines configure the network
in their startup scripts.
config IP_PNP_DHCP
bool "IP: DHCP support"
depends on IP_PNP
---help---
If you want your Linux box to mount its whole root file system (the
one containing the directory /) from some other computer over the
net via NFS and you want the IP address of your computer to be
discovered automatically at boot time using the DHCP protocol (a
special protocol designed for doing this job), say Y here. In case
the boot ROM of your network card was designed for booting Linux and
does DHCP itself, providing all necessary information on the kernel
command line, you can say N here.
If unsure, say Y. Note that if you want to use DHCP, a DHCP server
must be operating on your network. Read
<file:Documentation/filesystems/nfs/nfsroot.txt> for details.
config IP_PNP_BOOTP
bool "IP: BOOTP support"
depends on IP_PNP
---help---
If you want your Linux box to mount its whole root file system (the
one containing the directory /) from some other computer over the
net via NFS and you want the IP address of your computer to be
discovered automatically at boot time using the BOOTP protocol (a
special protocol designed for doing this job), say Y here. In case
the boot ROM of your network card was designed for booting Linux and
does BOOTP itself, providing all necessary information on the kernel
command line, you can say N here. If unsure, say Y. Note that if you
want to use BOOTP, a BOOTP server must be operating on your network.
Read <file:Documentation/filesystems/nfs/nfsroot.txt> for details.
config IP_PNP_RARP
bool "IP: RARP support"
depends on IP_PNP
help
If you want your Linux box to mount its whole root file system (the
one containing the directory /) from some other computer over the
net via NFS and you want the IP address of your computer to be
discovered automatically at boot time using the RARP protocol (an
older protocol which is being obsoleted by BOOTP and DHCP), say Y
here. Note that if you want to use RARP, a RARP server must be
operating on your network. Read
<file:Documentation/filesystems/nfs/nfsroot.txt> for details.
config NET_IPIP
tristate "IP: tunneling"
select INET_TUNNEL
select NET_IP_TUNNEL
---help---
Tunneling means encapsulating data of one protocol type within
another protocol and sending it over a channel that understands the
encapsulating protocol. This particular tunneling driver implements
encapsulation of IP within IP, which sounds kind of pointless, but
can be useful if you want to make your (or some other) machine
appear on a different network than it physically is, or to use
mobile-IP facilities (allowing laptops to seamlessly move between
networks without changing their IP addresses).
Saying Y to this option will produce two modules ( = code which can
be inserted in and removed from the running kernel whenever you
want). Most people won't need this and can say N.
config NET_IPGRE_DEMUX
tristate "IP: GRE demultiplexer"
help
This is helper module to demultiplex GRE packets on GRE version field criteria.
Required by ip_gre and pptp modules.
config NET_IP_TUNNEL
tristate
select DST_CACHE
select GRO_CELLS
default n
config NET_IPGRE
tristate "IP: GRE tunnels over IP"
depends on (IPV6 || IPV6=n) && NET_IPGRE_DEMUX
select NET_IP_TUNNEL
help
Tunneling means encapsulating data of one protocol type within
another protocol and sending it over a channel that understands the
encapsulating protocol. This particular tunneling driver implements
GRE (Generic Routing Encapsulation) and at this time allows
encapsulating of IPv4 or IPv6 over existing IPv4 infrastructure.
This driver is useful if the other endpoint is a Cisco router: Cisco
likes GRE much better than the other Linux tunneling driver ("IP
tunneling" above). In addition, GRE allows multicast redistribution
through the tunnel.
config NET_IPGRE_BROADCAST
bool "IP: broadcast GRE over IP"
depends on IP_MULTICAST && NET_IPGRE
help
One application of GRE/IP is to construct a broadcast WAN (Wide Area
Network), which looks like a normal Ethernet LAN (Local Area
Network), but can be distributed all over the Internet. If you want
to do that, say Y here and to "IP multicast routing" below.
config IP_MROUTE_COMMON
bool
depends on IP_MROUTE || IPV6_MROUTE
config IP_MROUTE
bool "IP: multicast routing"
depends on IP_MULTICAST
select IP_MROUTE_COMMON
help
This is used if you want your machine to act as a router for IP
packets that have several destination addresses. It is needed on the
MBONE, a high bandwidth network on top of the Internet which carries
audio and video broadcasts. In order to do that, you would most
likely run the program mrouted. If you haven't heard about it, you
don't need it.
config IP_MROUTE_MULTIPLE_TABLES
bool "IP: multicast policy routing"
depends on IP_MROUTE && IP_ADVANCED_ROUTER
select FIB_RULES
help
Normally, a multicast router runs a userspace daemon and decides
what to do with a multicast packet based on the source and
destination addresses. If you say Y here, the multicast router
will also be able to take interfaces and packet marks into
account and run multiple instances of userspace daemons
simultaneously, each one handling a single table.
If unsure, say N.
config IP_PIMSM_V1
bool "IP: PIM-SM version 1 support"
depends on IP_MROUTE
help
Kernel side support for Sparse Mode PIM (Protocol Independent
Multicast) version 1. This multicast routing protocol is used widely
because Cisco supports it. You need special software to use it
(pimd-v1). Please see <http://netweb.usc.edu/pim/> for more
information about PIM.
Say Y if you want to use PIM-SM v1. Note that you can say N here if
you just want to use Dense Mode PIM.
config IP_PIMSM_V2
bool "IP: PIM-SM version 2 support"
depends on IP_MROUTE
help
Kernel side support for Sparse Mode PIM version 2. In order to use
this, you need an experimental routing daemon supporting it (pimd or
gated-5). This routing protocol is not used widely, so say N unless
you want to play with it.
config SYN_COOKIES
bool "IP: TCP syncookie support"
---help---
Normal TCP/IP networking is open to an attack known as "SYN
flooding". This denial-of-service attack prevents legitimate remote
users from being able to connect to your computer during an ongoing
attack and requires very little work from the attacker, who can
operate from anywhere on the Internet.
SYN cookies provide protection against this type of attack. If you
say Y here, the TCP/IP stack will use a cryptographic challenge
protocol known as "SYN cookies" to enable legitimate users to
continue to connect, even when your machine is under attack. There
is no need for the legitimate users to change their TCP/IP software;
SYN cookies work transparently to them. For technical information
about SYN cookies, check out <http://cr.yp.to/syncookies.html>.
If you are SYN flooded, the source address reported by the kernel is
likely to have been forged by the attacker; it is only reported as
an aid in tracing the packets to their actual source and should not
be taken as absolute truth.
SYN cookies may prevent correct error reporting on clients when the
server is really overloaded. If this happens frequently better turn
them off.
If you say Y here, you can disable SYN cookies at run time by
saying Y to "/proc file system support" and
"Sysctl support" below and executing the command
echo 0 > /proc/sys/net/ipv4/tcp_syncookies
after the /proc file system has been mounted.
If unsure, say N.
config NET_IPVTI
tristate "Virtual (secure) IP: tunneling"
depends on IPV6 || IPV6=n
select INET_TUNNEL
select NET_IP_TUNNEL
depends on INET_XFRM_MODE_TUNNEL
---help---
Tunneling means encapsulating data of one protocol type within
another protocol and sending it over a channel that understands the
encapsulating protocol. This can be used with xfrm mode tunnel to give
the notion of a secure tunnel for IPSEC and then use routing protocol
on top.
config NET_UDP_TUNNEL
tristate
select NET_IP_TUNNEL
default n
config NET_FOU
tristate "IP: Foo (IP protocols) over UDP"
select XFRM
select NET_UDP_TUNNEL
---help---
Foo over UDP allows any IP protocol to be directly encapsulated
over UDP include tunnels (IPIP, GRE, SIT). By encapsulating in UDP
network mechanisms and optimizations for UDP (such as ECMP
and RSS) can be leveraged to provide better service.
config NET_FOU_IP_TUNNELS
bool "IP: FOU encapsulation of IP tunnels"
depends on NET_IPIP || NET_IPGRE || IPV6_SIT
select NET_FOU
---help---
Allow configuration of FOU or GUE encapsulation for IP tunnels.
When this option is enabled IP tunnels can be configured to use
FOU or GUE encapsulation.
config INET_AH
tristate "IP: AH transformation"
select XFRM_ALGO
select CRYPTO
select CRYPTO_HMAC
select CRYPTO_MD5
select CRYPTO_SHA1
---help---
Support for IPsec AH.
If unsure, say Y.
config INET_ESP
tristate "IP: ESP transformation"
select XFRM_ALGO
select CRYPTO
select CRYPTO_AUTHENC
select CRYPTO_HMAC
select CRYPTO_MD5
select CRYPTO_CBC
select CRYPTO_SHA1
select CRYPTO_DES
select CRYPTO_ECHAINIV
---help---
Support for IPsec ESP.
If unsure, say Y.
config INET_ESP_OFFLOAD
tristate "IP: ESP transformation offload"
depends on INET_ESP
select XFRM_OFFLOAD
default n
---help---
Support for ESP transformation offload. This makes sense
only if this system really does IPsec and want to do it
with high throughput. A typical desktop system does not
need it, even if it does IPsec.
If unsure, say N.
config INET_IPCOMP
tristate "IP: IPComp transformation"
select INET_XFRM_TUNNEL
select XFRM_IPCOMP
---help---
Support for IP Payload Compression Protocol (IPComp) (RFC3173),
typically needed for IPsec.
If unsure, say Y.
config INET_XFRM_TUNNEL
tristate
select INET_TUNNEL
default n
config INET_TUNNEL
tristate
default n
config INET_XFRM_MODE_TRANSPORT
tristate "IP: IPsec transport mode"
default y
select XFRM
---help---
Support for IPsec transport mode.
If unsure, say Y.
config INET_XFRM_MODE_TUNNEL
tristate "IP: IPsec tunnel mode"
default y
select XFRM
---help---
Support for IPsec tunnel mode.
If unsure, say Y.
config INET_XFRM_MODE_BEET
tristate "IP: IPsec BEET mode"
default y
select XFRM
---help---
Support for IPsec BEET mode.
If unsure, say Y.
config INET_DIAG
tristate "INET: socket monitoring interface"
default y
---help---
Support for INET (TCP, DCCP, etc) socket monitoring interface used by
native Linux tools such as ss. ss is included in iproute2, currently
downloadable at:
http://www.linuxfoundation.org/collaborate/workgroups/networking/iproute2
If unsure, say Y.
config INET_TCP_DIAG
depends on INET_DIAG
def_tristate INET_DIAG
config INET_UDP_DIAG
tristate "UDP: socket monitoring interface"
depends on INET_DIAG && (IPV6 || IPV6=n)
default n
---help---
Support for UDP socket monitoring interface used by the ss tool.
If unsure, say Y.
config INET_RAW_DIAG
tristate "RAW: socket monitoring interface"
depends on INET_DIAG && (IPV6 || IPV6=n)
default n
---help---
Support for RAW socket monitoring interface used by the ss tool.
If unsure, say Y.
config INET_DIAG_DESTROY
bool "INET: allow privileged process to administratively close sockets"
depends on INET_DIAG
default n
---help---
Provides a SOCK_DESTROY operation that allows privileged processes
(e.g., a connection manager or a network administration tool such as
ss) to close sockets opened by other processes. Closing a socket in
this way interrupts any blocking read/write/connect operations on
the socket and causes future socket calls to behave as if the socket
had been disconnected.
If unsure, say N.
menuconfig TCP_CONG_ADVANCED
bool "TCP: advanced congestion control"
---help---
Support for selection of various TCP congestion control
modules.
Nearly all users can safely say no here, and a safe default
selection will be made (CUBIC with new Reno as a fallback).
If unsure, say N.
if TCP_CONG_ADVANCED
config TCP_CONG_BIC
tristate "Binary Increase Congestion (BIC) control"
default m
---help---
BIC-TCP is a sender-side only change that ensures a linear RTT
fairness under large windows while offering both scalability and
bounded TCP-friendliness. The protocol combines two schemes
called additive increase and binary search increase. When the
congestion window is large, additive increase with a large
increment ensures linear RTT fairness as well as good
scalability. Under small congestion windows, binary search
increase provides TCP friendliness.
See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/
config TCP_CONG_CUBIC
tristate "CUBIC TCP"
default y
---help---
This is version 2.0 of BIC-TCP which uses a cubic growth function
among other techniques.
See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/cubic-paper.pdf
config TCP_CONG_WESTWOOD
tristate "TCP Westwood+"
default m
---help---
TCP Westwood+ is a sender-side only modification of the TCP Reno
protocol stack that optimizes the performance of TCP congestion
control. It is based on end-to-end bandwidth estimation to set
congestion window and slow start threshold after a congestion
episode. Using this estimation, TCP Westwood+ adaptively sets a
slow start threshold and a congestion window which takes into
account the bandwidth used at the time congestion is experienced.
TCP Westwood+ significantly increases fairness wrt TCP Reno in
wired networks and throughput over wireless links.
config TCP_CONG_HTCP
tristate "H-TCP"
default m
---help---
H-TCP is a send-side only modifications of the TCP Reno
protocol stack that optimizes the performance of TCP
congestion control for high speed network links. It uses a
modeswitch to change the alpha and beta parameters of TCP Reno
based on network conditions and in a way so as to be fair with
other Reno and H-TCP flows.
config TCP_CONG_HSTCP
tristate "High Speed TCP"
default n
---help---
Sally Floyd's High Speed TCP (RFC 3649) congestion control.
A modification to TCP's congestion control mechanism for use
with large congestion windows. A table indicates how much to
increase the congestion window by when an ACK is received.
For more detail see http://www.icir.org/floyd/hstcp.html
config TCP_CONG_HYBLA
tristate "TCP-Hybla congestion control algorithm"
default n
---help---
TCP-Hybla is a sender-side only change that eliminates penalization of
long-RTT, large-bandwidth connections, like when satellite legs are
involved, especially when sharing a common bottleneck with normal
terrestrial connections.
config TCP_CONG_VEGAS
tristate "TCP Vegas"
default n
---help---
TCP Vegas is a sender-side only change to TCP that anticipates
the onset of congestion by estimating the bandwidth. TCP Vegas
adjusts the sending rate by modifying the congestion
window. TCP Vegas should provide less packet loss, but it is
not as aggressive as TCP Reno.
config TCP_CONG_NV
tristate "TCP NV"
default n
---help---
TCP NV is a follow up to TCP Vegas. It has been modified to deal with
10G networks, measurement noise introduced by LRO, GRO and interrupt
coalescence. In addition, it will decrease its cwnd multiplicatively
instead of linearly.
Note that in general congestion avoidance (cwnd decreased when # packets
queued grows) cannot coexist with congestion control (cwnd decreased only
when there is packet loss) due to fairness issues. One scenario when they
can coexist safely is when the CA flows have RTTs << CC flows RTTs.
For further details see http://www.brakmo.org/networking/tcp-nv/
config TCP_CONG_SCALABLE
tristate "Scalable TCP"
default n
---help---
Scalable TCP is a sender-side only change to TCP which uses a
MIMD congestion control algorithm which has some nice scaling
properties, though is known to have fairness issues.
See http://www.deneholme.net/tom/scalable/
config TCP_CONG_LP
tristate "TCP Low Priority"
default n
---help---
TCP Low Priority (TCP-LP), a distributed algorithm whose goal is
to utilize only the excess network bandwidth as compared to the
``fair share`` of bandwidth as targeted by TCP.
See http://www-ece.rice.edu/networks/TCP-LP/
config TCP_CONG_VENO
tristate "TCP Veno"
default n
---help---
TCP Veno is a sender-side only enhancement of TCP to obtain better
throughput over wireless networks. TCP Veno makes use of state
distinguishing to circumvent the difficult judgment of the packet loss
type. TCP Veno cuts down less congestion window in response to random
loss packets.
See <http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1177186>
config TCP_CONG_YEAH
tristate "YeAH TCP"
select TCP_CONG_VEGAS
default n
---help---
YeAH-TCP is a sender-side high-speed enabled TCP congestion control
algorithm, which uses a mixed loss/delay approach to compute the
congestion window. It's design goals target high efficiency,
internal, RTT and Reno fairness, resilience to link loss while
keeping network elements load as low as possible.
For further details look here:
http://wil.cs.caltech.edu/pfldnet2007/paper/YeAH_TCP.pdf
config TCP_CONG_ILLINOIS
tristate "TCP Illinois"
default n
---help---
TCP-Illinois is a sender-side modification of TCP Reno for
high speed long delay links. It uses round-trip-time to
adjust the alpha and beta parameters to achieve a higher average
throughput and maintain fairness.
For further details see:
http://www.ews.uiuc.edu/~shaoliu/tcpillinois/index.html
config TCP_CONG_DCTCP
tristate "DataCenter TCP (DCTCP)"
default n
---help---
DCTCP leverages Explicit Congestion Notification (ECN) in the network to
provide multi-bit feedback to the end hosts. It is designed to provide:
- High burst tolerance (incast due to partition/aggregate),
- Low latency (short flows, queries),
- High throughput (continuous data updates, large file transfers) with
commodity, shallow-buffered switches.
All switches in the data center network running DCTCP must support
ECN marking and be configured for marking when reaching defined switch
buffer thresholds. The default ECN marking threshold heuristic for
DCTCP on switches is 20 packets (30KB) at 1Gbps, and 65 packets
(~100KB) at 10Gbps, but might need further careful tweaking.
For further details see:
http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf
config TCP_CONG_CDG
tristate "CAIA Delay-Gradient (CDG)"
default n
---help---
CAIA Delay-Gradient (CDG) is a TCP congestion control that modifies
the TCP sender in order to:
o Use the delay gradient as a congestion signal.
o Back off with an average probability that is independent of the RTT.
o Coexist with flows that use loss-based congestion control.
o Tolerate packet loss unrelated to congestion.
For further details see:
D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using
delay gradients." In Networking 2011. Preprint: http://goo.gl/No3vdg
config TCP_CONG_BBR
tristate "BBR TCP"
default n
---help---
BBR (Bottleneck Bandwidth and RTT) TCP congestion control aims to
maximize network utilization and minimize queues. It builds an explicit
model of the the bottleneck delivery rate and path round-trip
propagation delay. It tolerates packet loss and delay unrelated to
congestion. It can operate over LAN, WAN, cellular, wifi, or cable
modem links. It can coexist with flows that use loss-based congestion
control, and can operate with shallow buffers, deep buffers,
bufferbloat, policers, or AQM schemes that do not provide a delay
signal. It requires the fq ("Fair Queue") pacing packet scheduler.
choice
prompt "Default TCP congestion control"
default DEFAULT_CUBIC
help
Select the TCP congestion control that will be used by default
for all connections.
config DEFAULT_BIC
bool "Bic" if TCP_CONG_BIC=y
config DEFAULT_CUBIC
bool "Cubic" if TCP_CONG_CUBIC=y
config DEFAULT_HTCP
bool "Htcp" if TCP_CONG_HTCP=y
config DEFAULT_HYBLA
bool "Hybla" if TCP_CONG_HYBLA=y
config DEFAULT_VEGAS
bool "Vegas" if TCP_CONG_VEGAS=y
config DEFAULT_VENO
bool "Veno" if TCP_CONG_VENO=y
config DEFAULT_WESTWOOD
bool "Westwood" if TCP_CONG_WESTWOOD=y
config DEFAULT_DCTCP
bool "DCTCP" if TCP_CONG_DCTCP=y
config DEFAULT_CDG
bool "CDG" if TCP_CONG_CDG=y
config DEFAULT_BBR
bool "BBR" if TCP_CONG_BBR=y
config DEFAULT_RENO
bool "Reno"
endchoice
endif
config TCP_CONG_CUBIC
tristate
depends on !TCP_CONG_ADVANCED
default y
config DEFAULT_TCP_CONG
string
default "bic" if DEFAULT_BIC
default "cubic" if DEFAULT_CUBIC
default "htcp" if DEFAULT_HTCP
default "hybla" if DEFAULT_HYBLA
default "vegas" if DEFAULT_VEGAS
default "westwood" if DEFAULT_WESTWOOD
default "veno" if DEFAULT_VENO
default "reno" if DEFAULT_RENO
default "dctcp" if DEFAULT_DCTCP
default "cdg" if DEFAULT_CDG
default "bbr" if DEFAULT_BBR
default "cubic"
config TCP_MD5SIG
bool "TCP: MD5 Signature Option support (RFC2385)"
select CRYPTO
select CRYPTO_MD5
---help---
RFC2385 specifies a method of giving MD5 protection to TCP sessions.
Its main (only?) use is to protect BGP sessions between core routers
on the Internet.
If unsure, say N.
+69
View File
@@ -0,0 +1,69 @@
# SPDX-License-Identifier: GPL-2.0
#
# Makefile for the Linux TCP/IP (INET) layer.
#
obj-y := route.o inetpeer.o protocol.o \
ip_input.o ip_fragment.o ip_forward.o ip_options.o \
ip_output.o ip_sockglue.o inet_hashtables.o \
inet_timewait_sock.o inet_connection_sock.o \
tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \
tcp_minisocks.o tcp_cong.o tcp_metrics.o tcp_fastopen.o \
tcp_rate.o tcp_recovery.o tcp_ulp.o \
tcp_offload.o datagram.o raw.o udp.o udplite.o \
udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \
fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \
inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o \
metrics.o netlink.o
obj-$(CONFIG_BPFILTER) += bpfilter/
obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o
obj-$(CONFIG_IP_MROUTE) += ipmr.o
obj-$(CONFIG_IP_MROUTE_COMMON) += ipmr_base.o
obj-$(CONFIG_NET_IPIP) += ipip.o
gre-y := gre_demux.o
obj-$(CONFIG_NET_FOU) += fou.o
obj-$(CONFIG_NET_IPGRE_DEMUX) += gre.o
obj-$(CONFIG_NET_IPGRE) += ip_gre.o
obj-$(CONFIG_NET_UDP_TUNNEL) += udp_tunnel.o
obj-$(CONFIG_NET_IPVTI) += ip_vti.o
obj-$(CONFIG_SYN_COOKIES) += syncookies.o
obj-$(CONFIG_INET_AH) += ah4.o
obj-$(CONFIG_INET_ESP) += esp4.o
obj-$(CONFIG_INET_ESP_OFFLOAD) += esp4_offload.o
obj-$(CONFIG_INET_IPCOMP) += ipcomp.o
obj-$(CONFIG_INET_XFRM_TUNNEL) += xfrm4_tunnel.o
obj-$(CONFIG_INET_XFRM_MODE_BEET) += xfrm4_mode_beet.o
obj-$(CONFIG_INET_TUNNEL) += tunnel4.o
obj-$(CONFIG_INET_XFRM_MODE_TRANSPORT) += xfrm4_mode_transport.o
obj-$(CONFIG_INET_XFRM_MODE_TUNNEL) += xfrm4_mode_tunnel.o
obj-$(CONFIG_IP_PNP) += ipconfig.o
obj-$(CONFIG_NETFILTER) += netfilter.o netfilter/
obj-$(CONFIG_INET_DIAG) += inet_diag.o
obj-$(CONFIG_INET_TCP_DIAG) += tcp_diag.o
obj-$(CONFIG_INET_UDP_DIAG) += udp_diag.o
obj-$(CONFIG_INET_RAW_DIAG) += raw_diag.o
obj-$(CONFIG_TCP_CONG_BBR) += tcp_bbr.o
obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o
obj-$(CONFIG_TCP_CONG_CDG) += tcp_cdg.o
obj-$(CONFIG_TCP_CONG_CUBIC) += tcp_cubic.o
obj-$(CONFIG_TCP_CONG_DCTCP) += tcp_dctcp.o
obj-$(CONFIG_TCP_CONG_WESTWOOD) += tcp_westwood.o
obj-$(CONFIG_TCP_CONG_HSTCP) += tcp_highspeed.o
obj-$(CONFIG_TCP_CONG_HYBLA) += tcp_hybla.o
obj-$(CONFIG_TCP_CONG_HTCP) += tcp_htcp.o
obj-$(CONFIG_TCP_CONG_VEGAS) += tcp_vegas.o
obj-$(CONFIG_TCP_CONG_NV) += tcp_nv.o
obj-$(CONFIG_TCP_CONG_VENO) += tcp_veno.o
obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o
obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o
obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o
obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o
obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
xfrm4_output.o xfrm4_protocol.o
+2052
View File
File diff suppressed because it is too large. Load diff
+599
View File
@@ -0,0 +1,599 @@
#define pr_fmt(fmt) "IPsec: " fmt
#include <crypto/algapi.h>
#include <crypto/hash.h>
#include <linux/err.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <net/ip.h>
#include <net/xfrm.h>
#include <net/ah.h>
#include <linux/crypto.h>
#include <linux/pfkeyv2.h>
#include <linux/scatterlist.h>
#include <net/icmp.h>
#include <net/protocol.h>
struct ah_skb_cb {
struct xfrm_skb_cb xfrm;
void *tmp;
};
#define AH_SKB_CB(__skb) ((struct ah_skb_cb *)&((__skb)->cb[0]))
static void *ah_alloc_tmp(struct crypto_ahash *ahash, int nfrags,
unsigned int size)
{
unsigned int len;
len = size + crypto_ahash_digestsize(ahash) +
(crypto_ahash_alignmask(ahash) &
~(crypto_tfm_ctx_alignment() - 1));
len = ALIGN(len, crypto_tfm_ctx_alignment());
len += sizeof(struct ahash_request) + crypto_ahash_reqsize(ahash);
len = ALIGN(len, __alignof__(struct scatterlist));
len += sizeof(struct scatterlist) * nfrags;
return kmalloc(len, GFP_ATOMIC);
}
static inline u8 *ah_tmp_auth(void *tmp, unsigned int offset)
{
return tmp + offset;
}
static inline u8 *ah_tmp_icv(struct crypto_ahash *ahash, void *tmp,
unsigned int offset)
{
return PTR_ALIGN((u8 *)tmp + offset, crypto_ahash_alignmask(ahash) + 1);
}
static inline struct ahash_request *ah_tmp_req(struct crypto_ahash *ahash,
u8 *icv)
{
struct ahash_request *req;
req = (void *)PTR_ALIGN(icv + crypto_ahash_digestsize(ahash),
crypto_tfm_ctx_alignment());
ahash_request_set_tfm(req, ahash);
return req;
}
static inline struct scatterlist *ah_req_sg(struct crypto_ahash *ahash,
struct ahash_request *req)
{
return (void *)ALIGN((unsigned long)(req + 1) +
crypto_ahash_reqsize(ahash),
__alignof__(struct scatterlist));
}
/* Clear mutable options and find final destination to substitute
* into IP header for icv calculation. Options are already checked
* for validity, so paranoia is not required. */
static int ip_clear_mutable_options(const struct iphdr *iph, __be32 *daddr)
{
unsigned char *optptr = (unsigned char *)(iph+1);
int l = iph->ihl*4 - sizeof(struct iphdr);
int optlen;
while (l > 0) {
switch (*optptr) {
case IPOPT_END:
return 0;
case IPOPT_NOOP:
l--;
optptr++;
continue;
}
optlen = optptr[1];
if (optlen<2 || optlen>l)
return -EINVAL;
switch (*optptr) {
case IPOPT_SEC:
case 0x85: /* Some "Extended Security" crap. */
case IPOPT_CIPSO:
case IPOPT_RA:
case 0x80|21: /* RFC1770 */
break;
case IPOPT_LSRR:
case IPOPT_SSRR:
if (optlen < 6)
return -EINVAL;
memcpy(daddr, optptr+optlen-4, 4);
/* Fall through */
default:
memset(optptr, 0, optlen);
}
l -= optlen;
optptr += optlen;
}
return 0;
}
static void ah_output_done(struct crypto_async_request *base, int err)
{
u8 *icv;
struct iphdr *iph;
struct sk_buff *skb = base->data;
struct xfrm_state *x = skb_dst(skb)->xfrm;
struct ah_data *ahp = x->data;
struct iphdr *top_iph = ip_hdr(skb);
struct ip_auth_hdr *ah = ip_auth_hdr(skb);
int ihl = ip_hdrlen(skb);
iph = AH_SKB_CB(skb)->tmp;
icv = ah_tmp_icv(ahp->ahash, iph, ihl);
memcpy(ah->auth_data, icv, ahp->icv_trunc_len);
top_iph->tos = iph->tos;
top_iph->ttl = iph->ttl;
top_iph->frag_off = iph->frag_off;
if (top_iph->ihl != 5) {
top_iph->daddr = iph->daddr;
memcpy(top_iph+1, iph+1, top_iph->ihl*4 - sizeof(struct iphdr));
}
kfree(AH_SKB_CB(skb)->tmp);
xfrm_output_resume(skb, err);
}
static int ah_output(struct xfrm_state *x, struct sk_buff *skb)
{
int err;
int nfrags;
int ihl;
u8 *icv;
struct sk_buff *trailer;
struct crypto_ahash *ahash;
struct ahash_request *req;
struct scatterlist *sg;
struct iphdr *iph, *top_iph;
struct ip_auth_hdr *ah;
struct ah_data *ahp;
int seqhi_len = 0;
__be32 *seqhi;
int sglists = 0;
struct scatterlist *seqhisg;
ahp = x->data;
ahash = ahp->ahash;
if ((err = skb_cow_data(skb, 0, &trailer)) < 0)
goto out;
nfrags = err;
skb_push(skb, -skb_network_offset(skb));
ah = ip_auth_hdr(skb);
ihl = ip_hdrlen(skb);
if (x->props.flags & XFRM_STATE_ESN) {
sglists = 1;
seqhi_len = sizeof(*seqhi);
}
err = -ENOMEM;
iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl + seqhi_len);
if (!iph)
goto out;
seqhi = (__be32 *)((char *)iph + ihl);
icv = ah_tmp_icv(ahash, seqhi, seqhi_len);
req = ah_tmp_req(ahash, icv);
sg = ah_req_sg(ahash, req);
seqhisg = sg + nfrags;
memset(ah->auth_data, 0, ahp->icv_trunc_len);
top_iph = ip_hdr(skb);
iph->tos = top_iph->tos;
iph->ttl = top_iph->ttl;
iph->frag_off = top_iph->frag_off;
if (top_iph->ihl != 5) {
iph->daddr = top_iph->daddr;
memcpy(iph+1, top_iph+1, top_iph->ihl*4 - sizeof(struct iphdr));
err = ip_clear_mutable_options(top_iph, &top_iph->daddr);
if (err)
goto out_free;
}
ah->nexthdr = *skb_mac_header(skb);
*skb_mac_header(skb) = IPPROTO_AH;
top_iph->tos = 0;
top_iph->tot_len = htons(skb->len);
top_iph->frag_off = 0;
top_iph->ttl = 0;
top_iph->check = 0;
if (x->props.flags & XFRM_STATE_ALIGN4)
ah->hdrlen = (XFRM_ALIGN4(sizeof(*ah) + ahp->icv_trunc_len) >> 2) - 2;
else
ah->hdrlen = (XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len) >> 2) - 2;
ah->reserved = 0;
ah->spi = x->id.spi;
ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
sg_init_table(sg, nfrags + sglists);
err = skb_to_sgvec_nomark(skb, sg, 0, skb->len);
if (unlikely(err < 0))
goto out_free;
if (x->props.flags & XFRM_STATE_ESN) {
/* Attach seqhi sg right after packet payload */
*seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
sg_set_buf(seqhisg, seqhi, seqhi_len);
}
ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len);
ahash_request_set_callback(req, 0, ah_output_done, skb);
AH_SKB_CB(skb)->tmp = iph;
err = crypto_ahash_digest(req);
if (err) {
if (err == -EINPROGRESS)
goto out;
if (err == -ENOSPC)
err = NET_XMIT_DROP;
goto out_free;
}
memcpy(ah->auth_data, icv, ahp->icv_trunc_len);
top_iph->tos = iph->tos;
top_iph->ttl = iph->ttl;
top_iph->frag_off = iph->frag_off;
if (top_iph->ihl != 5) {
top_iph->daddr = iph->daddr;
memcpy(top_iph+1, iph+1, top_iph->ihl*4 - sizeof(struct iphdr));
}
out_free:
kfree(iph);
out:
return err;
}
static void ah_input_done(struct crypto_async_request *base, int err)
{
u8 *auth_data;
u8 *icv;
struct iphdr *work_iph;
struct sk_buff *skb = base->data;
struct xfrm_state *x = xfrm_input_state(skb);
struct ah_data *ahp = x->data;
struct ip_auth_hdr *ah = ip_auth_hdr(skb);
int ihl = ip_hdrlen(skb);
int ah_hlen = (ah->hdrlen + 2) << 2;
if (err)
goto out;
work_iph = AH_SKB_CB(skb)->tmp;
auth_data = ah_tmp_auth(work_iph, ihl);
icv = ah_tmp_icv(ahp->ahash, auth_data, ahp->icv_trunc_len);
err = crypto_memneq(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0;
if (err)
goto out;
err = ah->nexthdr;
skb->network_header += ah_hlen;
memcpy(skb_network_header(skb), work_iph, ihl);
__skb_pull(skb, ah_hlen + ihl);
if (x->props.mode == XFRM_MODE_TUNNEL)
skb_reset_transport_header(skb);
else
skb_set_transport_header(skb, -ihl);
out:
kfree(AH_SKB_CB(skb)->tmp);
xfrm_input_resume(skb, err);
}
static int ah_input(struct xfrm_state *x, struct sk_buff *skb)
{
int ah_hlen;
int ihl;
int nexthdr;
int nfrags;
u8 *auth_data;
u8 *icv;
struct sk_buff *trailer;
struct crypto_ahash *ahash;
struct ahash_request *req;
struct scatterlist *sg;
struct iphdr *iph, *work_iph;
struct ip_auth_hdr *ah;
struct ah_data *ahp;
int err = -ENOMEM;
int seqhi_len = 0;
__be32 *seqhi;
int sglists = 0;
struct scatterlist *seqhisg;
if (!pskb_may_pull(skb, sizeof(*ah)))
goto out;
ah = (struct ip_auth_hdr *)skb->data;
ahp = x->data;
ahash = ahp->ahash;
nexthdr = ah->nexthdr;
ah_hlen = (ah->hdrlen + 2) << 2;
if (x->props.flags & XFRM_STATE_ALIGN4) {
if (ah_hlen != XFRM_ALIGN4(sizeof(*ah) + ahp->icv_full_len) &&
ah_hlen != XFRM_ALIGN4(sizeof(*ah) + ahp->icv_trunc_len))
goto out;
} else {
if (ah_hlen != XFRM_ALIGN8(sizeof(*ah) + ahp->icv_full_len) &&
ah_hlen != XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len))
goto out;
}
if (!pskb_may_pull(skb, ah_hlen))
goto out;
/* We are going to _remove_ AH header to keep sockets happy,
* so... Later this can change. */
if (skb_unclone(skb, GFP_ATOMIC))
goto out;
skb->ip_summed = CHECKSUM_NONE;
if ((err = skb_cow_data(skb, 0, &trailer)) < 0)
goto out;
nfrags = err;
ah = (struct ip_auth_hdr *)skb->data;
iph = ip_hdr(skb);
ihl = ip_hdrlen(skb);
if (x->props.flags & XFRM_STATE_ESN) {
sglists = 1;
seqhi_len = sizeof(*seqhi);
}
work_iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl +
ahp->icv_trunc_len + seqhi_len);
if (!work_iph) {
err = -ENOMEM;
goto out;
}
seqhi = (__be32 *)((char *)work_iph + ihl);
auth_data = ah_tmp_auth(seqhi, seqhi_len);
icv = ah_tmp_icv(ahash, auth_data, ahp->icv_trunc_len);
req = ah_tmp_req(ahash, icv);
sg = ah_req_sg(ahash, req);
seqhisg = sg + nfrags;
memcpy(work_iph, iph, ihl);
memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len);
memset(ah->auth_data, 0, ahp->icv_trunc_len);
iph->ttl = 0;
iph->tos = 0;
iph->frag_off = 0;
iph->check = 0;
if (ihl > sizeof(*iph)) {
__be32 dummy;
err = ip_clear_mutable_options(iph, &dummy);
if (err)
goto out_free;
}
skb_push(skb, ihl);
sg_init_table(sg, nfrags + sglists);
err = skb_to_sgvec_nomark(skb, sg, 0, skb->len);
if (unlikely(err < 0))
goto out_free;
if (x->props.flags & XFRM_STATE_ESN) {
/* Attach seqhi sg right after packet payload */
*seqhi = XFRM_SKB_CB(skb)->seq.input.hi;
sg_set_buf(seqhisg, seqhi, seqhi_len);
}
ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len);
ahash_request_set_callback(req, 0, ah_input_done, skb);
AH_SKB_CB(skb)->tmp = work_iph;
err = crypto_ahash_digest(req);
if (err) {
if (err == -EINPROGRESS)
goto out;
goto out_free;
}
err = crypto_memneq(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0;
if (err)
goto out_free;
skb->network_header += ah_hlen;
memcpy(skb_network_header(skb), work_iph, ihl);
__skb_pull(skb, ah_hlen + ihl);
if (x->props.mode == XFRM_MODE_TUNNEL)
skb_reset_transport_header(skb);
else
skb_set_transport_header(skb, -ihl);
err = nexthdr;
out_free:
kfree (work_iph);
out:
return err;
}
static int ah4_err(struct sk_buff *skb, u32 info)
{
struct net *net = dev_net(skb->dev);
const struct iphdr *iph = (const struct iphdr *)skb->data;
struct ip_auth_hdr *ah = (struct ip_auth_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;
case ICMP_REDIRECT:
break;
default:
return 0;
}
x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
ah->spi, IPPROTO_AH, AF_INET);
if (!x)
return 0;
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0);
else
ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0);
xfrm_state_put(x);
return 0;
}
static int ah_init_state(struct xfrm_state *x)
{
struct ah_data *ahp = NULL;
struct xfrm_algo_desc *aalg_desc;
struct crypto_ahash *ahash;
if (!x->aalg)
goto error;
if (x->encap)
goto error;
ahp = kzalloc(sizeof(*ahp), GFP_KERNEL);
if (!ahp)
return -ENOMEM;
ahash = crypto_alloc_ahash(x->aalg->alg_name, 0, 0);
if (IS_ERR(ahash))
goto error;
ahp->ahash = ahash;
if (crypto_ahash_setkey(ahash, x->aalg->alg_key,
(x->aalg->alg_key_len + 7) / 8))
goto error;
/*
* Lookup the algorithm description maintained by xfrm_algo,
* verify crypto transform properties, and store information
* we need for AH processing. This lookup cannot fail here
* after a successful crypto_alloc_ahash().
*/
aalg_desc = xfrm_aalg_get_byname(x->aalg->alg_name, 0);
BUG_ON(!aalg_desc);
if (aalg_desc->uinfo.auth.icv_fullbits/8 !=
crypto_ahash_digestsize(ahash)) {
pr_info("%s: %s digestsize %u != %hu\n",
__func__, x->aalg->alg_name,
crypto_ahash_digestsize(ahash),
aalg_desc->uinfo.auth.icv_fullbits / 8);
goto error;
}
ahp->icv_full_len = aalg_desc->uinfo.auth.icv_fullbits/8;
ahp->icv_trunc_len = x->aalg->alg_trunc_len/8;
if (x->props.flags & XFRM_STATE_ALIGN4)
x->props.header_len = XFRM_ALIGN4(sizeof(struct ip_auth_hdr) +
ahp->icv_trunc_len);
else
x->props.header_len = XFRM_ALIGN8(sizeof(struct ip_auth_hdr) +
ahp->icv_trunc_len);
if (x->props.mode == XFRM_MODE_TUNNEL)
x->props.header_len += sizeof(struct iphdr);
x->data = ahp;
return 0;
error:
if (ahp) {
crypto_free_ahash(ahp->ahash);
kfree(ahp);
}
return -EINVAL;
}
static void ah_destroy(struct xfrm_state *x)
{
struct ah_data *ahp = x->data;
if (!ahp)
return;
crypto_free_ahash(ahp->ahash);
kfree(ahp);
}
static int ah4_rcv_cb(struct sk_buff *skb, int err)
{
return 0;
}
static const struct xfrm_type ah_type =
{
.description = "AH4",
.owner = THIS_MODULE,
.proto = IPPROTO_AH,
.flags = XFRM_TYPE_REPLAY_PROT,
.init_state = ah_init_state,
.destructor = ah_destroy,
.input = ah_input,
.output = ah_output
};
static struct xfrm4_protocol ah4_protocol = {
.handler = xfrm4_rcv,
.input_handler = xfrm_input,
.cb_handler = ah4_rcv_cb,
.err_handler = ah4_err,
.priority = 0,
};
static int __init ah4_init(void)
{
if (xfrm_register_type(&ah_type, AF_INET) < 0) {
pr_info("%s: can't add xfrm type\n", __func__);
return -EAGAIN;
}
if (xfrm4_protocol_register(&ah4_protocol, IPPROTO_AH) < 0) {
pr_info("%s: can't add protocol\n", __func__);
xfrm_unregister_type(&ah_type, AF_INET);
return -EAGAIN;
}
return 0;
}
static void __exit ah4_fini(void)
{
if (xfrm4_protocol_deregister(&ah4_protocol, IPPROTO_AH) < 0)
pr_info("%s: can't remove protocol\n", __func__);
if (xfrm_unregister_type(&ah_type, AF_INET) < 0)
pr_info("%s: can't remove xfrm type\n", __func__);
}
module_init(ah4_init);
module_exit(ah4_fini);
MODULE_LICENSE("GPL");
MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_AH);
+1453
View File
File diff suppressed because it is too large. Load diff
+1
View File
@@ -0,0 +1 @@
obj-$(CONFIG_BPFILTER) += sockopt.o
+43
View File
@@ -0,0 +1,43 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/uaccess.h>
#include <linux/bpfilter.h>
#include <uapi/linux/bpf.h>
#include <linux/wait.h>
#include <linux/kmod.h>
int (*bpfilter_process_sockopt)(struct sock *sk, int optname,
char __user *optval,
unsigned int optlen, bool is_set);
EXPORT_SYMBOL_GPL(bpfilter_process_sockopt);
static int bpfilter_mbox_request(struct sock *sk, int optname,
char __user *optval,
unsigned int optlen, bool is_set)
{
if (!bpfilter_process_sockopt) {
int err = request_module("bpfilter");
if (err)
return err;
if (!bpfilter_process_sockopt)
return -ECHILD;
}
return bpfilter_process_sockopt(sk, optname, optval, optlen, is_set);
}
int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval,
unsigned int optlen)
{
return bpfilter_mbox_request(sk, optname, optval, optlen, true);
}
int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval,
int __user *optlen)
{
int len;
if (get_user(len, optlen))
return -EFAULT;
return bpfilter_mbox_request(sk, optname, optval, len, false);
}
File diff suppressed because it is too large. Load diff
+133
View File
@@ -0,0 +1,133 @@
/*
* common UDP/RAW code
* Linux INET implementation
*
* Authors:
* Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/types.h>
#include <linux/module.h>
#include <linux/ip.h>
#include <linux/in.h>
#include <net/ip.h>
#include <net/sock.h>
#include <net/route.h>
#include <net/tcp_states.h>
#include <net/sock_reuseport.h>
int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct inet_sock *inet = inet_sk(sk);
struct sockaddr_in *usin = (struct sockaddr_in *) uaddr;
struct flowi4 *fl4;
struct rtable *rt;
__be32 saddr;
int oif;
int err;
if (addr_len < sizeof(*usin))
return -EINVAL;
if (usin->sin_family != AF_INET)
return -EAFNOSUPPORT;
sk_dst_reset(sk);
oif = sk->sk_bound_dev_if;
saddr = inet->inet_saddr;
if (ipv4_is_multicast(usin->sin_addr.s_addr)) {
if (!oif)
oif = inet->mc_index;
if (!saddr)
saddr = inet->mc_addr;
}
fl4 = &inet->cork.fl.u.ip4;
rt = ip_route_connect(fl4, usin->sin_addr.s_addr, saddr,
RT_CONN_FLAGS(sk), oif,
sk->sk_protocol,
inet->inet_sport, usin->sin_port, sk);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
if (err == -ENETUNREACH)
IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
goto out;
}
if ((rt->rt_flags & RTCF_BROADCAST) && !sock_flag(sk, SOCK_BROADCAST)) {
ip_rt_put(rt);
err = -EACCES;
goto out;
}
if (!inet->inet_saddr)
inet->inet_saddr = fl4->saddr; /* Update source address */
if (!inet->inet_rcv_saddr) {
inet->inet_rcv_saddr = fl4->saddr;
if (sk->sk_prot->rehash)
sk->sk_prot->rehash(sk);
}
inet->inet_daddr = fl4->daddr;
inet->inet_dport = usin->sin_port;
reuseport_has_conns(sk, true);
sk->sk_state = TCP_ESTABLISHED;
sk_set_txhash(sk);
inet->inet_id = prandom_u32();
sk_dst_set(sk, &rt->dst);
err = 0;
out:
return err;
}
EXPORT_SYMBOL(__ip4_datagram_connect);
int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
int res;
lock_sock(sk);
res = __ip4_datagram_connect(sk, uaddr, addr_len);
release_sock(sk);
return res;
}
EXPORT_SYMBOL(ip4_datagram_connect);
/* Because UDP xmit path can manipulate sk_dst_cache without holding
* socket lock, we need to use sk_dst_set() here,
* even if we own the socket lock.
*/
void ip4_datagram_release_cb(struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
const struct ip_options_rcu *inet_opt;
__be32 daddr = inet->inet_daddr;
struct dst_entry *dst;
struct flowi4 fl4;
struct rtable *rt;
rcu_read_lock();
dst = __sk_dst_get(sk);
if (!dst || !dst->obsolete || dst->ops->check(dst, 0)) {
rcu_read_unlock();
return;
}
inet_opt = rcu_dereference(inet->inet_opt);
if (inet_opt && inet_opt->opt.srr)
daddr = inet_opt->opt.faddr;
rt = ip_route_output_ports(sock_net(sk), &fl4, sk, daddr,
inet->inet_saddr, inet->inet_dport,
inet->inet_sport, sk->sk_protocol,
RT_CONN_FLAGS(sk), sk->sk_bound_dev_if);
dst = !IS_ERR(rt) ? &rt->dst : NULL;
sk_dst_set(sk, dst);
rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(ip4_datagram_release_cb);
+2538
View File
File diff suppressed because it is too large. Load diff
+1068
View File
File diff suppressed because it is too large. Load diff
+281
View File
@@ -0,0 +1,281 @@
/*
* IPV4 GSO/GRO offload support
* Linux INET implementation
*
* Copyright (C) 2016 secunet Security Networks AG
* Author: Steffen Klassert <steffen.klassert@secunet.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* ESP GRO support
*/
#include <linux/skbuff.h>
#include <linux/init.h>
#include <net/protocol.h>
#include <crypto/aead.h>
#include <crypto/authenc.h>
#include <linux/err.h>
#include <linux/module.h>
#include <net/ip.h>
#include <net/xfrm.h>
#include <net/esp.h>
#include <linux/scatterlist.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <net/udp.h>
static struct sk_buff *esp4_gro_receive(struct list_head *head,
struct sk_buff *skb)
{
int offset = skb_gro_offset(skb);
struct xfrm_offload *xo;
struct xfrm_state *x;
__be32 seq;
__be32 spi;
int err;
if (!pskb_pull(skb, offset))
return NULL;
if ((err = xfrm_parse_spi(skb, IPPROTO_ESP, &spi, &seq)) != 0)
goto out;
xo = xfrm_offload(skb);
if (!xo || !(xo->flags & CRYPTO_DONE)) {
err = secpath_set(skb);
if (err)
goto out;
if (skb->sp->len == XFRM_MAX_DEPTH)
goto out;
x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
(xfrm_address_t *)&ip_hdr(skb)->daddr,
spi, IPPROTO_ESP, AF_INET);
if (!x)
goto out;
skb->sp->xvec[skb->sp->len++] = x;
skb->sp->olen++;
xo = xfrm_offload(skb);
if (!xo) {
xfrm_state_put(x);
goto out;
}
}
xo->flags |= XFRM_GRO;
XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
XFRM_SPI_SKB_CB(skb)->family = AF_INET;
XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
XFRM_SPI_SKB_CB(skb)->seq = seq;
/* We don't need to handle errors from xfrm_input, it does all
* the error handling and frees the resources on error. */
xfrm_input(skb, IPPROTO_ESP, spi, -2);
return ERR_PTR(-EINPROGRESS);
out:
skb_push(skb, offset);
NAPI_GRO_CB(skb)->same_flow = 0;
NAPI_GRO_CB(skb)->flush = 1;
return NULL;
}
static void esp4_gso_encap(struct xfrm_state *x, struct sk_buff *skb)
{
struct ip_esp_hdr *esph;
struct iphdr *iph = ip_hdr(skb);
struct xfrm_offload *xo = xfrm_offload(skb);
int proto = iph->protocol;
skb_push(skb, -skb_network_offset(skb));
esph = ip_esp_hdr(skb);
*skb_mac_header(skb) = IPPROTO_ESP;
esph->spi = x->id.spi;
esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
xo->proto = proto;
}
static struct sk_buff *esp4_gso_segment(struct sk_buff *skb,
netdev_features_t features)
{
struct xfrm_state *x;
struct ip_esp_hdr *esph;
struct crypto_aead *aead;
netdev_features_t esp_features = features;
struct xfrm_offload *xo = xfrm_offload(skb);
if (!xo)
return ERR_PTR(-EINVAL);
if (!(skb_shinfo(skb)->gso_type & SKB_GSO_ESP))
return ERR_PTR(-EINVAL);
x = skb->sp->xvec[skb->sp->len - 1];
aead = x->data;
esph = ip_esp_hdr(skb);
if (esph->spi != x->id.spi)
return ERR_PTR(-EINVAL);
if (!pskb_may_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead)))
return ERR_PTR(-EINVAL);
__skb_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead));
skb->encap_hdr_csum = 1;
if (!(features & NETIF_F_HW_ESP) || x->xso.dev != skb->dev)
esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK);
else if (!(features & NETIF_F_HW_ESP_TX_CSUM))
esp_features = features & ~NETIF_F_CSUM_MASK;
xo->flags |= XFRM_GSO_SEGMENT;
return x->outer_mode->gso_segment(x, skb, esp_features);
}
static int esp_input_tail(struct xfrm_state *x, struct sk_buff *skb)
{
struct crypto_aead *aead = x->data;
struct xfrm_offload *xo = xfrm_offload(skb);
if (!pskb_may_pull(skb, sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead)))
return -EINVAL;
if (!(xo->flags & CRYPTO_DONE))
skb->ip_summed = CHECKSUM_NONE;
return esp_input_done2(skb, 0);
}
static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features)
{
int err;
int alen;
int blksize;
struct xfrm_offload *xo;
struct ip_esp_hdr *esph;
struct crypto_aead *aead;
struct esp_info esp;
bool hw_offload = true;
__u32 seq;
esp.inplace = true;
xo = xfrm_offload(skb);
if (!xo)
return -EINVAL;
if (!(features & NETIF_F_HW_ESP) || x->xso.dev != skb->dev) {
xo->flags |= CRYPTO_FALLBACK;
hw_offload = false;
}
esp.proto = xo->proto;
/* skb is pure payload to encrypt */
aead = x->data;
alen = crypto_aead_authsize(aead);
esp.tfclen = 0;
/* XXX: Add support for tfc padding here. */
blksize = ALIGN(crypto_aead_blocksize(aead), 4);
esp.clen = ALIGN(skb->len + 2 + esp.tfclen, blksize);
esp.plen = esp.clen - skb->len - esp.tfclen;
esp.tailen = esp.tfclen + esp.plen + alen;
esp.esph = ip_esp_hdr(skb);
if (!hw_offload || (hw_offload && !skb_is_gso(skb))) {
esp.nfrags = esp_output_head(x, skb, &esp);
if (esp.nfrags < 0)
return esp.nfrags;
}
seq = xo->seq.low;
esph = esp.esph;
esph->spi = x->id.spi;
skb_push(skb, -skb_network_offset(skb));
if (xo->flags & XFRM_GSO_SEGMENT) {
esph->seq_no = htonl(seq);
if (!skb_is_gso(skb))
xo->seq.low++;
else
xo->seq.low += skb_shinfo(skb)->gso_segs;
}
esp.seqno = cpu_to_be64(seq + ((u64)xo->seq.hi << 32));
ip_hdr(skb)->tot_len = htons(skb->len);
ip_send_check(ip_hdr(skb));
if (hw_offload)
return 0;
err = esp_output_tail(x, skb, &esp);
if (err)
return err;
secpath_reset(skb);
return 0;
}
static const struct net_offload esp4_offload = {
.callbacks = {
.gro_receive = esp4_gro_receive,
.gso_segment = esp4_gso_segment,
},
};
static const struct xfrm_type_offload esp_type_offload = {
.description = "ESP4 OFFLOAD",
.owner = THIS_MODULE,
.proto = IPPROTO_ESP,
.input_tail = esp_input_tail,
.xmit = esp_xmit,
.encap = esp4_gso_encap,
};
static int __init esp4_offload_init(void)
{
if (xfrm_register_type_offload(&esp_type_offload, AF_INET) < 0) {
pr_info("%s: can't add xfrm type offload\n", __func__);
return -EAGAIN;
}
return inet_add_offload(&esp4_offload, IPPROTO_ESP);
}
static void __exit esp4_offload_exit(void)
{
if (xfrm_unregister_type_offload(&esp_type_offload, AF_INET) < 0)
pr_info("%s: can't remove xfrm type offload\n", __func__);
inet_del_offload(&esp4_offload, IPPROTO_ESP);
}
module_init(esp4_offload_init);
module_exit(esp4_offload_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>");
MODULE_ALIAS_XFRM_OFFLOAD_TYPE(AF_INET, XFRM_PROTO_ESP);
File diff suppressed because it is too large. Load diff
+57
View File
@@ -0,0 +1,57 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _FIB_LOOKUP_H
#define _FIB_LOOKUP_H
#include <linux/types.h>
#include <linux/list.h>
#include <net/ip_fib.h>
struct fib_alias {
struct hlist_node fa_list;
struct fib_info *fa_info;
u8 fa_tos;
u8 fa_type;
u8 fa_state;
u8 fa_slen;
u32 tb_id;
s16 fa_default;
struct rcu_head rcu;
};
#define FA_S_ACCESSED 0x01
/* Dont write on fa_state unless needed, to keep it shared on all cpus */
static inline void fib_alias_accessed(struct fib_alias *fa)
{
if (!(fa->fa_state & FA_S_ACCESSED))
fa->fa_state |= FA_S_ACCESSED;
}
/* Exported by fib_semantics.c */
void fib_release_info(struct fib_info *);
struct fib_info *fib_create_info(struct fib_config *cfg,
struct netlink_ext_ack *extack);
int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
struct netlink_ext_ack *extack);
bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi);
int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u32 tb_id,
u8 type, __be32 dst, int dst_len, u8 tos, struct fib_info *fi,
unsigned int);
void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, int dst_len,
u32 tb_id, const struct nl_info *info, unsigned int nlm_flags);
static inline void fib_result_assign(struct fib_result *res,
struct fib_info *fi)
{
/* we used to play games with refcounts, but we now use RCU */
res->fi = fi;
}
struct fib_prop {
int error;
u8 scope;
};
extern const struct fib_prop fib_props[RTN_MAX + 1];
#endif /* _FIB_LOOKUP_H */
+74
View File
@@ -0,0 +1,74 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/rtnetlink.h>
#include <linux/notifier.h>
#include <linux/socket.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <net/net_namespace.h>
#include <net/fib_notifier.h>
#include <net/netns/ipv4.h>
#include <net/ip_fib.h>
int call_fib4_notifier(struct notifier_block *nb, struct net *net,
enum fib_event_type event_type,
struct fib_notifier_info *info)
{
info->family = AF_INET;
return call_fib_notifier(nb, net, event_type, info);
}
int call_fib4_notifiers(struct net *net, enum fib_event_type event_type,
struct fib_notifier_info *info)
{
ASSERT_RTNL();
info->family = AF_INET;
net->ipv4.fib_seq++;
return call_fib_notifiers(net, event_type, info);
}
static unsigned int fib4_seq_read(struct net *net)
{
ASSERT_RTNL();
return net->ipv4.fib_seq + fib4_rules_seq_read(net);
}
static int fib4_dump(struct net *net, struct notifier_block *nb)
{
int err;
err = fib4_rules_dump(net, nb);
if (err)
return err;
fib_notify(net, nb);
return 0;
}
static const struct fib_notifier_ops fib4_notifier_ops_template = {
.family = AF_INET,
.fib_seq_read = fib4_seq_read,
.fib_dump = fib4_dump,
.owner = THIS_MODULE,
};
int __net_init fib4_notifier_init(struct net *net)
{
struct fib_notifier_ops *ops;
net->ipv4.fib_seq = 0;
ops = fib_notifier_ops_register(&fib4_notifier_ops_template, net);
if (IS_ERR(ops))
return PTR_ERR(ops);
net->ipv4.notifier_ops = ops;
return 0;
}
void __net_exit fib4_notifier_exit(struct net *net)
{
fib_notifier_ops_unregister(net->ipv4.notifier_ops);
}
+425
View File
@@ -0,0 +1,425 @@
/*
* 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.
*
* IPv4 Forwarding Information Base: policy rules.
*
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
* Thomas Graf <tgraf@suug.ch>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* Fixes:
* Rani Assaf : local_rule cannot be deleted
* Marc Boucher : routing by fwmark
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/netlink.h>
#include <linux/inetdevice.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/rcupdate.h>
#include <linux/export.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/tcp.h>
#include <net/ip_fib.h>
#include <net/fib_rules.h>
struct fib4_rule {
struct fib_rule common;
u8 dst_len;
u8 src_len;
u8 tos;
__be32 src;
__be32 srcmask;
__be32 dst;
__be32 dstmask;
#ifdef CONFIG_IP_ROUTE_CLASSID
u32 tclassid;
#endif
};
static bool fib4_rule_matchall(const struct fib_rule *rule)
{
struct fib4_rule *r = container_of(rule, struct fib4_rule, common);
if (r->dst_len || r->src_len || r->tos)
return false;
return fib_rule_matchall(rule);
}
bool fib4_rule_default(const struct fib_rule *rule)
{
if (!fib4_rule_matchall(rule) || rule->action != FR_ACT_TO_TBL ||
rule->l3mdev)
return false;
if (rule->table != RT_TABLE_LOCAL && rule->table != RT_TABLE_MAIN &&
rule->table != RT_TABLE_DEFAULT)
return false;
return true;
}
EXPORT_SYMBOL_GPL(fib4_rule_default);
int fib4_rules_dump(struct net *net, struct notifier_block *nb)
{
return fib_rules_dump(net, nb, AF_INET);
}
unsigned int fib4_rules_seq_read(struct net *net)
{
return fib_rules_seq_read(net, AF_INET);
}
int __fib_lookup(struct net *net, struct flowi4 *flp,
struct fib_result *res, unsigned int flags)
{
struct fib_lookup_arg arg = {
.result = res,
.flags = flags,
};
int err;
/* update flow if oif or iif point to device enslaved to l3mdev */
l3mdev_update_flow(net, flowi4_to_flowi(flp));
err = fib_rules_lookup(net->ipv4.rules_ops, flowi4_to_flowi(flp), 0, &arg);
#ifdef CONFIG_IP_ROUTE_CLASSID
if (arg.rule)
res->tclassid = ((struct fib4_rule *)arg.rule)->tclassid;
else
res->tclassid = 0;
#endif
if (err == -ESRCH)
err = -ENETUNREACH;
return err;
}
EXPORT_SYMBOL_GPL(__fib_lookup);
static int fib4_rule_action(struct fib_rule *rule, struct flowi *flp,
int flags, struct fib_lookup_arg *arg)
{
int err = -EAGAIN;
struct fib_table *tbl;
u32 tb_id;
switch (rule->action) {
case FR_ACT_TO_TBL:
break;
case FR_ACT_UNREACHABLE:
return -ENETUNREACH;
case FR_ACT_PROHIBIT:
return -EACCES;
case FR_ACT_BLACKHOLE:
default:
return -EINVAL;
}
rcu_read_lock();
tb_id = fib_rule_get_table(rule, arg);
tbl = fib_get_table(rule->fr_net, tb_id);
if (tbl)
err = fib_table_lookup(tbl, &flp->u.ip4,
(struct fib_result *)arg->result,
arg->flags);
rcu_read_unlock();
return err;
}
static bool fib4_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg)
{
struct fib_result *result = (struct fib_result *) arg->result;
struct net_device *dev = NULL;
if (result->fi)
dev = result->fi->fib_dev;
/* do not accept result if the route does
* not meet the required prefix length
*/
if (result->prefixlen <= rule->suppress_prefixlen)
goto suppress_route;
/* do not accept result if the route uses a device
* belonging to a forbidden interface group
*/
if (rule->suppress_ifgroup != -1 && dev && dev->group == rule->suppress_ifgroup)
goto suppress_route;
return false;
suppress_route:
if (!(arg->flags & FIB_LOOKUP_NOREF))
fib_info_put(result->fi);
return true;
}
static int fib4_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
{
struct fib4_rule *r = (struct fib4_rule *) rule;
struct flowi4 *fl4 = &fl->u.ip4;
__be32 daddr = fl4->daddr;
__be32 saddr = fl4->saddr;
if (((saddr ^ r->src) & r->srcmask) ||
((daddr ^ r->dst) & r->dstmask))
return 0;
if (r->tos && (r->tos != fl4->flowi4_tos))
return 0;
if (rule->ip_proto && (rule->ip_proto != fl4->flowi4_proto))
return 0;
if (fib_rule_port_range_set(&rule->sport_range) &&
!fib_rule_port_inrange(&rule->sport_range, fl4->fl4_sport))
return 0;
if (fib_rule_port_range_set(&rule->dport_range) &&
!fib_rule_port_inrange(&rule->dport_range, fl4->fl4_dport))
return 0;
return 1;
}
static struct fib_table *fib_empty_table(struct net *net)
{
u32 id;
for (id = 1; id <= RT_TABLE_MAX; id++)
if (!fib_get_table(net, id))
return fib_new_table(net, id);
return NULL;
}
static const struct nla_policy fib4_rule_policy[FRA_MAX+1] = {
FRA_GENERIC_POLICY,
[FRA_FLOW] = { .type = NLA_U32 },
};
static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
struct fib_rule_hdr *frh,
struct nlattr **tb,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
int err = -EINVAL;
struct fib4_rule *rule4 = (struct fib4_rule *) rule;
if (frh->tos & ~IPTOS_TOS_MASK) {
NL_SET_ERR_MSG(extack, "Invalid tos");
goto errout;
}
/* split local/main if they are not already split */
err = fib_unmerge(net);
if (err)
goto errout;
if (rule->table == RT_TABLE_UNSPEC && !rule->l3mdev) {
if (rule->action == FR_ACT_TO_TBL) {
struct fib_table *table;
table = fib_empty_table(net);
if (!table) {
err = -ENOBUFS;
goto errout;
}
rule->table = table->tb_id;
}
}
if (frh->src_len)
rule4->src = nla_get_in_addr(tb[FRA_SRC]);
if (frh->dst_len)
rule4->dst = nla_get_in_addr(tb[FRA_DST]);
#ifdef CONFIG_IP_ROUTE_CLASSID
if (tb[FRA_FLOW]) {
rule4->tclassid = nla_get_u32(tb[FRA_FLOW]);
if (rule4->tclassid)
net->ipv4.fib_num_tclassid_users++;
}
#endif
if (fib_rule_requires_fldissect(rule))
net->ipv4.fib_rules_require_fldissect++;
rule4->src_len = frh->src_len;
rule4->srcmask = inet_make_mask(rule4->src_len);
rule4->dst_len = frh->dst_len;
rule4->dstmask = inet_make_mask(rule4->dst_len);
rule4->tos = frh->tos;
net->ipv4.fib_has_custom_rules = true;
err = 0;
errout:
return err;
}
static int fib4_rule_delete(struct fib_rule *rule)
{
struct net *net = rule->fr_net;
int err;
/* split local/main if they are not already split */
err = fib_unmerge(net);
if (err)
goto errout;
#ifdef CONFIG_IP_ROUTE_CLASSID
if (((struct fib4_rule *)rule)->tclassid)
net->ipv4.fib_num_tclassid_users--;
#endif
net->ipv4.fib_has_custom_rules = true;
if (net->ipv4.fib_rules_require_fldissect &&
fib_rule_requires_fldissect(rule))
net->ipv4.fib_rules_require_fldissect--;
errout:
return err;
}
static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
struct nlattr **tb)
{
struct fib4_rule *rule4 = (struct fib4_rule *) rule;
if (frh->src_len && (rule4->src_len != frh->src_len))
return 0;
if (frh->dst_len && (rule4->dst_len != frh->dst_len))
return 0;
if (frh->tos && (rule4->tos != frh->tos))
return 0;
#ifdef CONFIG_IP_ROUTE_CLASSID
if (tb[FRA_FLOW] && (rule4->tclassid != nla_get_u32(tb[FRA_FLOW])))
return 0;
#endif
if (frh->src_len && (rule4->src != nla_get_in_addr(tb[FRA_SRC])))
return 0;
if (frh->dst_len && (rule4->dst != nla_get_in_addr(tb[FRA_DST])))
return 0;
return 1;
}
static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
struct fib_rule_hdr *frh)
{
struct fib4_rule *rule4 = (struct fib4_rule *) rule;
frh->dst_len = rule4->dst_len;
frh->src_len = rule4->src_len;
frh->tos = rule4->tos;
if ((rule4->dst_len &&
nla_put_in_addr(skb, FRA_DST, rule4->dst)) ||
(rule4->src_len &&
nla_put_in_addr(skb, FRA_SRC, rule4->src)))
goto nla_put_failure;
#ifdef CONFIG_IP_ROUTE_CLASSID
if (rule4->tclassid &&
nla_put_u32(skb, FRA_FLOW, rule4->tclassid))
goto nla_put_failure;
#endif
return 0;
nla_put_failure:
return -ENOBUFS;
}
static size_t fib4_rule_nlmsg_payload(struct fib_rule *rule)
{
return nla_total_size(4) /* dst */
+ nla_total_size(4) /* src */
+ nla_total_size(4); /* flow */
}
static void fib4_rule_flush_cache(struct fib_rules_ops *ops)
{
rt_cache_flush(ops->fro_net);
}
static const struct fib_rules_ops __net_initconst fib4_rules_ops_template = {
.family = AF_INET,
.rule_size = sizeof(struct fib4_rule),
.addr_size = sizeof(u32),
.action = fib4_rule_action,
.suppress = fib4_rule_suppress,
.match = fib4_rule_match,
.configure = fib4_rule_configure,
.delete = fib4_rule_delete,
.compare = fib4_rule_compare,
.fill = fib4_rule_fill,
.nlmsg_payload = fib4_rule_nlmsg_payload,
.flush_cache = fib4_rule_flush_cache,
.nlgroup = RTNLGRP_IPV4_RULE,
.policy = fib4_rule_policy,
.owner = THIS_MODULE,
};
static int fib_default_rules_init(struct fib_rules_ops *ops)
{
int err;
err = fib_default_rule_add(ops, 0, RT_TABLE_LOCAL, 0);
if (err < 0)
return err;
err = fib_default_rule_add(ops, 0x7FFE, RT_TABLE_MAIN, 0);
if (err < 0)
return err;
err = fib_default_rule_add(ops, 0x7FFF, RT_TABLE_DEFAULT, 0);
if (err < 0)
return err;
return 0;
}
int __net_init fib4_rules_init(struct net *net)
{
int err;
struct fib_rules_ops *ops;
ops = fib_rules_register(&fib4_rules_ops_template, net);
if (IS_ERR(ops))
return PTR_ERR(ops);
err = fib_default_rules_init(ops);
if (err < 0)
goto fail;
net->ipv4.rules_ops = ops;
net->ipv4.fib_has_custom_rules = false;
net->ipv4.fib_rules_require_fldissect = 0;
return 0;
fail:
/* also cleans all rules already added */
fib_rules_unregister(ops);
return err;
}
void __net_exit fib4_rules_exit(struct net *net)
{
fib_rules_unregister(net->ipv4.rules_ops);
}
File diff suppressed because it is too large. Load diff
+2751
View File
File diff suppressed because it is too large. Load diff
+1119
View File
File diff suppressed because it is too large. Load diff
+222
View File
@@ -0,0 +1,222 @@
/*
* GRE over IPv4 demultiplexer driver
*
* Authors: Dmitry Kozlov (xeb@mail.ru)
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/if.h>
#include <linux/icmp.h>
#include <linux/kernel.h>
#include <linux/kmod.h>
#include <linux/skbuff.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/netdevice.h>
#include <linux/if_tunnel.h>
#include <linux/spinlock.h>
#include <net/protocol.h>
#include <net/gre.h>
#include <net/erspan.h>
#include <net/icmp.h>
#include <net/route.h>
#include <net/xfrm.h>
static const struct gre_protocol __rcu *gre_proto[GREPROTO_MAX] __read_mostly;
int gre_add_protocol(const struct gre_protocol *proto, u8 version)
{
if (version >= GREPROTO_MAX)
return -EINVAL;
return (cmpxchg((const struct gre_protocol **)&gre_proto[version], NULL, proto) == NULL) ?
0 : -EBUSY;
}
EXPORT_SYMBOL_GPL(gre_add_protocol);
int gre_del_protocol(const struct gre_protocol *proto, u8 version)
{
int ret;
if (version >= GREPROTO_MAX)
return -EINVAL;
ret = (cmpxchg((const struct gre_protocol **)&gre_proto[version], proto, NULL) == proto) ?
0 : -EBUSY;
if (ret)
return ret;
synchronize_rcu();
return 0;
}
EXPORT_SYMBOL_GPL(gre_del_protocol);
/* Fills in tpi and returns header length to be pulled.
* Note that caller must use pskb_may_pull() before pulling GRE header.
*/
int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
bool *csum_err, __be16 proto, int nhs)
{
const struct gre_base_hdr *greh;
__be32 *options;
int hdr_len;
if (unlikely(!pskb_may_pull(skb, nhs + sizeof(struct gre_base_hdr))))
return -EINVAL;
greh = (struct gre_base_hdr *)(skb->data + nhs);
if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING)))
return -EINVAL;
tpi->flags = gre_flags_to_tnl_flags(greh->flags);
hdr_len = gre_calc_hlen(tpi->flags);
if (!pskb_may_pull(skb, nhs + hdr_len))
return -EINVAL;
greh = (struct gre_base_hdr *)(skb->data + nhs);
tpi->proto = greh->protocol;
options = (__be32 *)(greh + 1);
if (greh->flags & GRE_CSUM) {
if (!skb_checksum_simple_validate(skb)) {
skb_checksum_try_convert(skb, IPPROTO_GRE, 0,
null_compute_pseudo);
} else if (csum_err) {
*csum_err = true;
return -EINVAL;
}
options++;
}
if (greh->flags & GRE_KEY) {
tpi->key = *options;
options++;
} else {
tpi->key = 0;
}
if (unlikely(greh->flags & GRE_SEQ)) {
tpi->seq = *options;
options++;
} else {
tpi->seq = 0;
}
/* WCCP version 1 and 2 protocol decoding.
* - Change protocol to IPv4/IPv6
* - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
*/
if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) {
u8 _val, *val;
val = skb_header_pointer(skb, nhs + hdr_len,
sizeof(_val), &_val);
if (!val)
return -EINVAL;
tpi->proto = proto;
if ((*val & 0xF0) != 0x40)
hdr_len += 4;
}
tpi->hdr_len = hdr_len;
/* ERSPAN ver 1 and 2 protocol sets GRE key field
* to 0 and sets the configured key in the
* inner erspan header field
*/
if ((greh->protocol == htons(ETH_P_ERSPAN) && hdr_len != 4) ||
greh->protocol == htons(ETH_P_ERSPAN2)) {
struct erspan_base_hdr *ershdr;
if (!pskb_may_pull(skb, nhs + hdr_len + sizeof(*ershdr)))
return -EINVAL;
ershdr = (struct erspan_base_hdr *)(skb->data + nhs + hdr_len);
tpi->key = cpu_to_be32(get_session_id(ershdr));
}
return hdr_len;
}
EXPORT_SYMBOL(gre_parse_header);
static int gre_rcv(struct sk_buff *skb)
{
const struct gre_protocol *proto;
u8 ver;
int ret;
if (!pskb_may_pull(skb, 12))
goto drop;
ver = skb->data[1]&0x7f;
if (ver >= GREPROTO_MAX)
goto drop;
rcu_read_lock();
proto = rcu_dereference(gre_proto[ver]);
if (!proto || !proto->handler)
goto drop_unlock;
ret = proto->handler(skb);
rcu_read_unlock();
return ret;
drop_unlock:
rcu_read_unlock();
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
static void gre_err(struct sk_buff *skb, u32 info)
{
const struct gre_protocol *proto;
const struct iphdr *iph = (const struct iphdr *)skb->data;
u8 ver = skb->data[(iph->ihl<<2) + 1]&0x7f;
if (ver >= GREPROTO_MAX)
return;
rcu_read_lock();
proto = rcu_dereference(gre_proto[ver]);
if (proto && proto->err_handler)
proto->err_handler(skb, info);
rcu_read_unlock();
}
static const struct net_protocol net_gre_protocol = {
.handler = gre_rcv,
.err_handler = gre_err,
.netns_ok = 1,
};
static int __init gre_init(void)
{
pr_info("GRE over IPv4 demultiplexor driver\n");
if (inet_add_protocol(&net_gre_protocol, IPPROTO_GRE) < 0) {
pr_err("can't add protocol\n");
return -EAGAIN;
}
return 0;
}
static void __exit gre_exit(void)
{
inet_del_protocol(&net_gre_protocol, IPPROTO_GRE);
}
module_init(gre_init);
module_exit(gre_exit);
MODULE_DESCRIPTION("GRE over IPv4 demultiplexer driver");
MODULE_AUTHOR("D. Kozlov (xeb@mail.ru)");
MODULE_LICENSE("GPL");
+294
View File
@@ -0,0 +1,294 @@
/*
* IPV4 GSO/GRO offload support
* Linux INET implementation
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* GRE GSO support
*/
#include <linux/skbuff.h>
#include <linux/init.h>
#include <net/protocol.h>
#include <net/gre.h>
static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
netdev_features_t features)
{
int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
bool need_csum, need_recompute_csum, gso_partial;
struct sk_buff *segs = ERR_PTR(-EINVAL);
u16 mac_offset = skb->mac_header;
__be16 protocol = skb->protocol;
u16 mac_len = skb->mac_len;
int gre_offset, outer_hlen;
if (!skb->encapsulation)
goto out;
if (unlikely(tnl_hlen < sizeof(struct gre_base_hdr)))
goto out;
if (unlikely(!pskb_may_pull(skb, tnl_hlen)))
goto out;
/* setup inner skb. */
skb->encapsulation = 0;
SKB_GSO_CB(skb)->encap_level = 0;
__skb_pull(skb, tnl_hlen);
skb_reset_mac_header(skb);
skb_set_network_header(skb, skb_inner_network_offset(skb));
skb->mac_len = skb_inner_network_offset(skb);
skb->protocol = skb->inner_protocol;
need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE_CSUM);
need_recompute_csum = skb->csum_not_inet;
skb->encap_hdr_csum = need_csum;
features &= skb->dev->hw_enc_features;
/* segment inner packet. */
segs = skb_mac_gso_segment(skb, features);
if (IS_ERR_OR_NULL(segs)) {
skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset,
mac_len);
goto out;
}
gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL);
outer_hlen = skb_tnl_header_len(skb);
gre_offset = outer_hlen - tnl_hlen;
skb = segs;
do {
struct gre_base_hdr *greh;
__sum16 *pcsum;
/* Set up inner headers if we are offloading inner checksum */
if (skb->ip_summed == CHECKSUM_PARTIAL) {
skb_reset_inner_headers(skb);
skb->encapsulation = 1;
}
skb->mac_len = mac_len;
skb->protocol = protocol;
__skb_push(skb, outer_hlen);
skb_reset_mac_header(skb);
skb_set_network_header(skb, mac_len);
skb_set_transport_header(skb, gre_offset);
if (!need_csum)
continue;
greh = (struct gre_base_hdr *)skb_transport_header(skb);
pcsum = (__sum16 *)(greh + 1);
if (gso_partial && skb_is_gso(skb)) {
unsigned int partial_adj;
/* Adjust checksum to account for the fact that
* the partial checksum is based on actual size
* whereas headers should be based on MSS size.
*/
partial_adj = skb->len + skb_headroom(skb) -
SKB_GSO_CB(skb)->data_offset -
skb_shinfo(skb)->gso_size;
*pcsum = ~csum_fold((__force __wsum)htonl(partial_adj));
} else {
*pcsum = 0;
}
*(pcsum + 1) = 0;
if (need_recompute_csum && !skb_is_gso(skb)) {
__wsum csum;
csum = skb_checksum(skb, gre_offset,
skb->len - gre_offset, 0);
*pcsum = csum_fold(csum);
} else {
*pcsum = gso_make_checksum(skb, 0);
}
} while ((skb = skb->next));
out:
return segs;
}
static struct sk_buff *gre_gro_receive(struct list_head *head,
struct sk_buff *skb)
{
struct sk_buff *pp = NULL;
struct sk_buff *p;
const struct gre_base_hdr *greh;
unsigned int hlen, grehlen;
unsigned int off;
int flush = 1;
struct packet_offload *ptype;
__be16 type;
if (NAPI_GRO_CB(skb)->encap_mark)
goto out;
NAPI_GRO_CB(skb)->encap_mark = 1;
off = skb_gro_offset(skb);
hlen = off + sizeof(*greh);
greh = skb_gro_header_fast(skb, off);
if (skb_gro_header_hard(skb, hlen)) {
greh = skb_gro_header_slow(skb, hlen, off);
if (unlikely(!greh))
goto out;
}
/* Only support version 0 and K (key), C (csum) flags. Note that
* although the support for the S (seq#) flag can be added easily
* for GRO, this is problematic for GSO hence can not be enabled
* here because a GRO pkt may end up in the forwarding path, thus
* requiring GSO support to break it up correctly.
*/
if ((greh->flags & ~(GRE_KEY|GRE_CSUM)) != 0)
goto out;
/* We can only support GRE_CSUM if we can track the location of
* the GRE header. In the case of FOU/GUE we cannot because the
* outer UDP header displaces the GRE header leaving us in a state
* of limbo.
*/
if ((greh->flags & GRE_CSUM) && NAPI_GRO_CB(skb)->is_fou)
goto out;
type = greh->protocol;
rcu_read_lock();
ptype = gro_find_receive_by_type(type);
if (!ptype)
goto out_unlock;
grehlen = GRE_HEADER_SECTION;
if (greh->flags & GRE_KEY)
grehlen += GRE_HEADER_SECTION;
if (greh->flags & GRE_CSUM)
grehlen += GRE_HEADER_SECTION;
hlen = off + grehlen;
if (skb_gro_header_hard(skb, hlen)) {
greh = skb_gro_header_slow(skb, hlen, off);
if (unlikely(!greh))
goto out_unlock;
}
/* Don't bother verifying checksum if we're going to flush anyway. */
if ((greh->flags & GRE_CSUM) && !NAPI_GRO_CB(skb)->flush) {
if (skb_gro_checksum_simple_validate(skb))
goto out_unlock;
skb_gro_checksum_try_convert(skb, IPPROTO_GRE, 0,
null_compute_pseudo);
}
list_for_each_entry(p, head, list) {
const struct gre_base_hdr *greh2;
if (!NAPI_GRO_CB(p)->same_flow)
continue;
/* The following checks are needed to ensure only pkts
* from the same tunnel are considered for aggregation.
* The criteria for "the same tunnel" includes:
* 1) same version (we only support version 0 here)
* 2) same protocol (we only support ETH_P_IP for now)
* 3) same set of flags
* 4) same key if the key field is present.
*/
greh2 = (struct gre_base_hdr *)(p->data + off);
if (greh2->flags != greh->flags ||
greh2->protocol != greh->protocol) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
if (greh->flags & GRE_KEY) {
/* compare keys */
if (*(__be32 *)(greh2+1) != *(__be32 *)(greh+1)) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
}
}
skb_gro_pull(skb, grehlen);
/* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/
skb_gro_postpull_rcsum(skb, greh, grehlen);
pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
flush = 0;
out_unlock:
rcu_read_unlock();
out:
skb_gro_flush_final(skb, pp, flush);
return pp;
}
static int gre_gro_complete(struct sk_buff *skb, int nhoff)
{
struct gre_base_hdr *greh = (struct gre_base_hdr *)(skb->data + nhoff);
struct packet_offload *ptype;
unsigned int grehlen = sizeof(*greh);
int err = -ENOENT;
__be16 type;
skb->encapsulation = 1;
skb_shinfo(skb)->gso_type = SKB_GSO_GRE;
type = greh->protocol;
if (greh->flags & GRE_KEY)
grehlen += GRE_HEADER_SECTION;
if (greh->flags & GRE_CSUM)
grehlen += GRE_HEADER_SECTION;
rcu_read_lock();
ptype = gro_find_complete_by_type(type);
if (ptype)
err = ptype->callbacks.gro_complete(skb, nhoff + grehlen);
rcu_read_unlock();
skb_set_inner_mac_header(skb, nhoff + grehlen);
return err;
}
static const struct net_offload gre_offload = {
.callbacks = {
.gso_segment = gre_gso_segment,
.gro_receive = gre_gro_receive,
.gro_complete = gre_gro_complete,
},
};
static int __init gre_offload_init(void)
{
int err;
err = inet_add_offload(&gre_offload, IPPROTO_GRE);
#if IS_ENABLED(CONFIG_IPV6)
if (err)
return err;
err = inet6_add_offload(&gre_offload, IPPROTO_GRE);
if (err)
inet_del_offload(&gre_offload, IPPROTO_GRE);
#endif
return err;
}
device_initcall(gre_offload_init);
+1305
View File
File diff suppressed because it is too large. Load diff
+3103
View File
File diff suppressed because it is too large. Load diff
File diff suppressed because it is too large. Load diff
+1322
View File
File diff suppressed because it is too large. Load diff
+519
View File
@@ -0,0 +1,519 @@
/*
* inet fragments management
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* Authors: Pavel Emelyanov <xemul@openvz.org>
* Started as consolidation of ipv4/ip_fragment.c,
* ipv6/reassembly. and ipv6 nf conntrack reassembly
*/
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/module.h>
#include <linux/timer.h>
#include <linux/mm.h>
#include <linux/random.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/slab.h>
#include <linux/rhashtable.h>
#include <net/sock.h>
#include <net/inet_frag.h>
#include <net/inet_ecn.h>
#include <net/ip.h>
#include <net/ipv6.h>
/* Use skb->cb to track consecutive/adjacent fragments coming at
* the end of the queue. Nodes in the rb-tree queue will
* contain "runs" of one or more adjacent fragments.
*
* Invariants:
* - next_frag is NULL at the tail of a "run";
* - the head of a "run" has the sum of all fragment lengths in frag_run_len.
*/
struct ipfrag_skb_cb {
union {
struct inet_skb_parm h4;
struct inet6_skb_parm h6;
};
struct sk_buff *next_frag;
int frag_run_len;
};
#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb))
static void fragcb_clear(struct sk_buff *skb)
{
RB_CLEAR_NODE(&skb->rbnode);
FRAG_CB(skb)->next_frag = NULL;
FRAG_CB(skb)->frag_run_len = skb->len;
}
/* Append skb to the last "run". */
static void fragrun_append_to_last(struct inet_frag_queue *q,
struct sk_buff *skb)
{
fragcb_clear(skb);
FRAG_CB(q->last_run_head)->frag_run_len += skb->len;
FRAG_CB(q->fragments_tail)->next_frag = skb;
q->fragments_tail = skb;
}
/* Create a new "run" with the skb. */
static void fragrun_create(struct inet_frag_queue *q, struct sk_buff *skb)
{
BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb));
fragcb_clear(skb);
if (q->last_run_head)
rb_link_node(&skb->rbnode, &q->last_run_head->rbnode,
&q->last_run_head->rbnode.rb_right);
else
rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node);
rb_insert_color(&skb->rbnode, &q->rb_fragments);
q->fragments_tail = skb;
q->last_run_head = skb;
}
/* Given the OR values of all fragments, apply RFC 3168 5.3 requirements
* Value : 0xff if frame should be dropped.
* 0 or INET_ECN_CE value, to be ORed in to final iph->tos field
*/
const u8 ip_frag_ecn_table[16] = {
/* at least one fragment had CE, and others ECT_0 or ECT_1 */
[IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0] = INET_ECN_CE,
[IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1] = INET_ECN_CE,
[IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = INET_ECN_CE,
/* invalid combinations : drop frame */
[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE] = 0xff,
[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0] = 0xff,
[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_1] = 0xff,
[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff,
[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0] = 0xff,
[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1] = 0xff,
[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff,
};
EXPORT_SYMBOL(ip_frag_ecn_table);
int inet_frags_init(struct inet_frags *f)
{
f->frags_cachep = kmem_cache_create(f->frags_cache_name, f->qsize, 0, 0,
NULL);
if (!f->frags_cachep)
return -ENOMEM;
return 0;
}
EXPORT_SYMBOL(inet_frags_init);
void inet_frags_fini(struct inet_frags *f)
{
/* We must wait that all inet_frag_destroy_rcu() have completed. */
rcu_barrier();
kmem_cache_destroy(f->frags_cachep);
f->frags_cachep = NULL;
}
EXPORT_SYMBOL(inet_frags_fini);
static void inet_frags_free_cb(void *ptr, void *arg)
{
struct inet_frag_queue *fq = ptr;
/* If we can not cancel the timer, it means this frag_queue
* is already disappearing, we have nothing to do.
* Otherwise, we own a refcount until the end of this function.
*/
if (!del_timer(&fq->timer))
return;
spin_lock_bh(&fq->lock);
if (!(fq->flags & INET_FRAG_COMPLETE)) {
fq->flags |= INET_FRAG_COMPLETE;
refcount_dec(&fq->refcnt);
}
spin_unlock_bh(&fq->lock);
inet_frag_put(fq);
}
void inet_frags_exit_net(struct netns_frags *nf)
{
nf->high_thresh = 0; /* prevent creation of new frags */
rhashtable_free_and_destroy(&nf->rhashtable, inet_frags_free_cb, NULL);
}
EXPORT_SYMBOL(inet_frags_exit_net);
void inet_frag_kill(struct inet_frag_queue *fq)
{
if (del_timer(&fq->timer))
refcount_dec(&fq->refcnt);
if (!(fq->flags & INET_FRAG_COMPLETE)) {
struct netns_frags *nf = fq->net;
fq->flags |= INET_FRAG_COMPLETE;
rhashtable_remove_fast(&nf->rhashtable, &fq->node, nf->f->rhash_params);
refcount_dec(&fq->refcnt);
}
}
EXPORT_SYMBOL(inet_frag_kill);
static void inet_frag_destroy_rcu(struct rcu_head *head)
{
struct inet_frag_queue *q = container_of(head, struct inet_frag_queue,
rcu);
struct inet_frags *f = q->net->f;
if (f->destructor)
f->destructor(q);
kmem_cache_free(f->frags_cachep, q);
}
unsigned int inet_frag_rbtree_purge(struct rb_root *root)
{
struct rb_node *p = rb_first(root);
unsigned int sum = 0;
while (p) {
struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);
p = rb_next(p);
rb_erase(&skb->rbnode, root);
while (skb) {
struct sk_buff *next = FRAG_CB(skb)->next_frag;
sum += skb->truesize;
kfree_skb(skb);
skb = next;
}
}
return sum;
}
EXPORT_SYMBOL(inet_frag_rbtree_purge);
void inet_frag_destroy(struct inet_frag_queue *q)
{
struct sk_buff *fp;
struct netns_frags *nf;
unsigned int sum, sum_truesize = 0;
struct inet_frags *f;
WARN_ON(!(q->flags & INET_FRAG_COMPLETE));
WARN_ON(del_timer(&q->timer) != 0);
/* Release all fragment data. */
fp = q->fragments;
nf = q->net;
f = nf->f;
if (fp) {
do {
struct sk_buff *xp = fp->next;
sum_truesize += fp->truesize;
kfree_skb(fp);
fp = xp;
} while (fp);
} else {
sum_truesize = inet_frag_rbtree_purge(&q->rb_fragments);
}
sum = sum_truesize + f->qsize;
call_rcu(&q->rcu, inet_frag_destroy_rcu);
sub_frag_mem_limit(nf, sum);
}
EXPORT_SYMBOL(inet_frag_destroy);
static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
struct inet_frags *f,
void *arg)
{
struct inet_frag_queue *q;
q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC);
if (!q)
return NULL;
q->net = nf;
f->constructor(q, arg);
add_frag_mem_limit(nf, f->qsize);
timer_setup(&q->timer, f->frag_expire, 0);
spin_lock_init(&q->lock);
refcount_set(&q->refcnt, 3);
return q;
}
static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
void *arg,
struct inet_frag_queue **prev)
{
struct inet_frags *f = nf->f;
struct inet_frag_queue *q;
q = inet_frag_alloc(nf, f, arg);
if (!q) {
*prev = ERR_PTR(-ENOMEM);
return NULL;
}
mod_timer(&q->timer, jiffies + nf->timeout);
*prev = rhashtable_lookup_get_insert_key(&nf->rhashtable, &q->key,
&q->node, f->rhash_params);
if (*prev) {
q->flags |= INET_FRAG_COMPLETE;
inet_frag_kill(q);
inet_frag_destroy(q);
return NULL;
}
return q;
}
/* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */
struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
{
struct inet_frag_queue *fq = NULL, *prev;
if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh)
return NULL;
rcu_read_lock();
prev = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
if (!prev)
fq = inet_frag_create(nf, key, &prev);
if (prev && !IS_ERR(prev)) {
fq = prev;
if (!refcount_inc_not_zero(&fq->refcnt))
fq = NULL;
}
rcu_read_unlock();
return fq;
}
EXPORT_SYMBOL(inet_frag_find);
int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
int offset, int end)
{
struct sk_buff *last = q->fragments_tail;
/* RFC5722, Section 4, amended by Errata ID : 3089
* When reassembling an IPv6 datagram, if
* one or more its constituent fragments is determined to be an
* overlapping fragment, the entire datagram (and any constituent
* fragments) MUST be silently discarded.
*
* Duplicates, however, should be ignored (i.e. skb dropped, but the
* queue/fragments kept for later reassembly).
*/
if (!last)
fragrun_create(q, skb); /* First fragment. */
else if (last->ip_defrag_offset + last->len < end) {
/* This is the common case: skb goes to the end. */
/* Detect and discard overlaps. */
if (offset < last->ip_defrag_offset + last->len)
return IPFRAG_OVERLAP;
if (offset == last->ip_defrag_offset + last->len)
fragrun_append_to_last(q, skb);
else
fragrun_create(q, skb);
} else {
/* Binary search. Note that skb can become the first fragment,
* but not the last (covered above).
*/
struct rb_node **rbn, *parent;
rbn = &q->rb_fragments.rb_node;
do {
struct sk_buff *curr;
int curr_run_end;
parent = *rbn;
curr = rb_to_skb(parent);
curr_run_end = curr->ip_defrag_offset +
FRAG_CB(curr)->frag_run_len;
if (end <= curr->ip_defrag_offset)
rbn = &parent->rb_left;
else if (offset >= curr_run_end)
rbn = &parent->rb_right;
else if (offset >= curr->ip_defrag_offset &&
end <= curr_run_end)
return IPFRAG_DUP;
else
return IPFRAG_OVERLAP;
} while (*rbn);
/* Here we have parent properly set, and rbn pointing to
* one of its NULL left/right children. Insert skb.
*/
fragcb_clear(skb);
rb_link_node(&skb->rbnode, parent, rbn);
rb_insert_color(&skb->rbnode, &q->rb_fragments);
}
skb->ip_defrag_offset = offset;
return IPFRAG_OK;
}
EXPORT_SYMBOL(inet_frag_queue_insert);
void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
struct sk_buff *parent)
{
struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments);
struct sk_buff **nextp;
int delta;
if (head != skb) {
fp = skb_clone(skb, GFP_ATOMIC);
if (!fp)
return NULL;
FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag;
if (RB_EMPTY_NODE(&skb->rbnode))
FRAG_CB(parent)->next_frag = fp;
else
rb_replace_node(&skb->rbnode, &fp->rbnode,
&q->rb_fragments);
if (q->fragments_tail == skb)
q->fragments_tail = fp;
skb_morph(skb, head);
FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag;
rb_replace_node(&head->rbnode, &skb->rbnode,
&q->rb_fragments);
consume_skb(head);
head = skb;
}
WARN_ON(head->ip_defrag_offset != 0);
delta = -head->truesize;
/* Head of list must not be cloned. */
if (skb_unclone(head, GFP_ATOMIC))
return NULL;
delta += head->truesize;
if (delta)
add_frag_mem_limit(q->net, delta);
/* If the first fragment is fragmented itself, we split
* it to two chunks: the first with data and paged part
* and the second, holding only fragments.
*/
if (skb_has_frag_list(head)) {
struct sk_buff *clone;
int i, plen = 0;
clone = alloc_skb(0, GFP_ATOMIC);
if (!clone)
return NULL;
skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
skb_frag_list_init(head);
for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
clone->data_len = head->data_len - plen;
clone->len = clone->data_len;
head->truesize += clone->truesize;
clone->csum = 0;
clone->ip_summed = head->ip_summed;
add_frag_mem_limit(q->net, clone->truesize);
skb_shinfo(head)->frag_list = clone;
nextp = &clone->next;
} else {
nextp = &skb_shinfo(head)->frag_list;
}
return nextp;
}
EXPORT_SYMBOL(inet_frag_reasm_prepare);
void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
void *reasm_data)
{
struct sk_buff **nextp = (struct sk_buff **)reasm_data;
struct rb_node *rbn;
struct sk_buff *fp;
skb_push(head, head->data - skb_network_header(head));
/* Traverse the tree in order, to build frag_list. */
fp = FRAG_CB(head)->next_frag;
rbn = rb_next(&head->rbnode);
rb_erase(&head->rbnode, &q->rb_fragments);
while (rbn || fp) {
/* fp points to the next sk_buff in the current run;
* rbn points to the next run.
*/
/* Go through the current run. */
while (fp) {
*nextp = fp;
nextp = &fp->next;
fp->prev = NULL;
memset(&fp->rbnode, 0, sizeof(fp->rbnode));
fp->sk = NULL;
head->data_len += fp->len;
head->len += fp->len;
if (head->ip_summed != fp->ip_summed)
head->ip_summed = CHECKSUM_NONE;
else if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_add(head->csum, fp->csum);
head->truesize += fp->truesize;
fp = FRAG_CB(fp)->next_frag;
}
/* Move to the next run. */
if (rbn) {
struct rb_node *rbnext = rb_next(rbn);
fp = rb_to_skb(rbn);
rb_erase(rbn, &q->rb_fragments);
rbn = rbnext;
}
}
sub_frag_mem_limit(q->net, head->truesize);
*nextp = NULL;
skb_mark_not_on_list(head);
head->prev = NULL;
head->tstamp = q->stamp;
}
EXPORT_SYMBOL(inet_frag_reasm_finish);
struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q)
{
struct sk_buff *head;
if (q->fragments) {
head = q->fragments;
q->fragments = head->next;
} else {
struct sk_buff *skb;
head = skb_rb_first(&q->rb_fragments);
if (!head)
return NULL;
skb = FRAG_CB(head)->next_frag;
if (skb)
rb_replace_node(&head->rbnode, &skb->rbnode,
&q->rb_fragments);
else
rb_erase(&head->rbnode, &q->rb_fragments);
memset(&head->rbnode, 0, sizeof(head->rbnode));
barrier();
}
if (head == q->fragments_tail)
q->fragments_tail = NULL;
sub_frag_mem_limit(q->net, head->truesize);
return head;
}
EXPORT_SYMBOL(inet_frag_pull_head);
+850
View File
@@ -0,0 +1,850 @@
/*
* 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.
*
* Generic INET transport hashtables
*
* Authors: Lotsa people, from code originally in tcp
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/module.h>
#include <linux/random.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/wait.h>
#include <linux/vmalloc.h>
#include <linux/bootmem.h>
#include <net/addrconf.h>
#include <net/inet_connection_sock.h>
#include <net/inet_hashtables.h>
#include <net/secure_seq.h>
#include <net/ip.h>
#include <net/tcp.h>
#include <net/sock_reuseport.h>
static u32 inet_ehashfn(const struct net *net, const __be32 laddr,
const __u16 lport, const __be32 faddr,
const __be16 fport)
{
static u32 inet_ehash_secret __read_mostly;
net_get_random_once(&inet_ehash_secret, sizeof(inet_ehash_secret));
return __inet_ehashfn(laddr, lport, faddr, fport,
inet_ehash_secret + net_hash_mix(net));
}
/* This function handles inet_sock, but also timewait and request sockets
* for IPv4/IPv6.
*/
static u32 sk_ehashfn(const struct sock *sk)
{
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == AF_INET6 &&
!ipv6_addr_v4mapped(&sk->sk_v6_daddr))
return inet6_ehashfn(sock_net(sk),
&sk->sk_v6_rcv_saddr, sk->sk_num,
&sk->sk_v6_daddr, sk->sk_dport);
#endif
return inet_ehashfn(sock_net(sk),
sk->sk_rcv_saddr, sk->sk_num,
sk->sk_daddr, sk->sk_dport);
}
/*
* Allocate and initialize a new local port bind bucket.
* The bindhash mutex for snum's hash chain must be held here.
*/
struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
struct net *net,
struct inet_bind_hashbucket *head,
const unsigned short snum)
{
struct inet_bind_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC);
if (tb) {
write_pnet(&tb->ib_net, net);
tb->port = snum;
tb->fastreuse = 0;
tb->fastreuseport = 0;
INIT_HLIST_HEAD(&tb->owners);
hlist_add_head(&tb->node, &head->chain);
}
return tb;
}
/*
* Caller must hold hashbucket lock for this tb with local BH disabled
*/
void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket *tb)
{
if (hlist_empty(&tb->owners)) {
__hlist_del(&tb->node);
kmem_cache_free(cachep, tb);
}
}
void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
const unsigned short snum)
{
inet_sk(sk)->inet_num = snum;
sk_add_bind_node(sk, &tb->owners);
inet_csk(sk)->icsk_bind_hash = tb;
}
/*
* Get rid of any references to a local port held by the given sock.
*/
static void __inet_put_port(struct sock *sk)
{
struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
const int bhash = inet_bhashfn(sock_net(sk), inet_sk(sk)->inet_num,
hashinfo->bhash_size);
struct inet_bind_hashbucket *head = &hashinfo->bhash[bhash];
struct inet_bind_bucket *tb;
spin_lock(&head->lock);
tb = inet_csk(sk)->icsk_bind_hash;
__sk_del_bind_node(sk);
inet_csk(sk)->icsk_bind_hash = NULL;
inet_sk(sk)->inet_num = 0;
inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
spin_unlock(&head->lock);
}
void inet_put_port(struct sock *sk)
{
local_bh_disable();
__inet_put_port(sk);
local_bh_enable();
}
EXPORT_SYMBOL(inet_put_port);
int __inet_inherit_port(const struct sock *sk, struct sock *child)
{
struct inet_hashinfo *table = sk->sk_prot->h.hashinfo;
unsigned short port = inet_sk(child)->inet_num;
const int bhash = inet_bhashfn(sock_net(sk), port,
table->bhash_size);
struct inet_bind_hashbucket *head = &table->bhash[bhash];
struct inet_bind_bucket *tb;
spin_lock(&head->lock);
tb = inet_csk(sk)->icsk_bind_hash;
if (unlikely(!tb)) {
spin_unlock(&head->lock);
return -ENOENT;
}
if (tb->port != port) {
/* NOTE: using tproxy and redirecting skbs to a proxy
* on a different listener port breaks the assumption
* that the listener socket's icsk_bind_hash is the same
* as that of the child socket. We have to look up or
* create a new bind bucket for the child here. */
inet_bind_bucket_for_each(tb, &head->chain) {
if (net_eq(ib_net(tb), sock_net(sk)) &&
tb->port == port)
break;
}
if (!tb) {
tb = inet_bind_bucket_create(table->bind_bucket_cachep,
sock_net(sk), head, port);
if (!tb) {
spin_unlock(&head->lock);
return -ENOMEM;
}
}
inet_csk_update_fastreuse(tb, child);
}
inet_bind_hash(child, tb, port);
spin_unlock(&head->lock);
return 0;
}
EXPORT_SYMBOL_GPL(__inet_inherit_port);
static struct inet_listen_hashbucket *
inet_lhash2_bucket_sk(struct inet_hashinfo *h, struct sock *sk)
{
u32 hash;
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == AF_INET6)
hash = ipv6_portaddr_hash(sock_net(sk),
&sk->sk_v6_rcv_saddr,
inet_sk(sk)->inet_num);
else
#endif
hash = ipv4_portaddr_hash(sock_net(sk),
inet_sk(sk)->inet_rcv_saddr,
inet_sk(sk)->inet_num);
return inet_lhash2_bucket(h, hash);
}
static void inet_hash2(struct inet_hashinfo *h, struct sock *sk)
{
struct inet_listen_hashbucket *ilb2;
if (!h->lhash2)
return;
ilb2 = inet_lhash2_bucket_sk(h, sk);
spin_lock(&ilb2->lock);
if (sk->sk_reuseport && sk->sk_family == AF_INET6)
hlist_add_tail_rcu(&inet_csk(sk)->icsk_listen_portaddr_node,
&ilb2->head);
else
hlist_add_head_rcu(&inet_csk(sk)->icsk_listen_portaddr_node,
&ilb2->head);
ilb2->count++;
spin_unlock(&ilb2->lock);
}
static void inet_unhash2(struct inet_hashinfo *h, struct sock *sk)
{
struct inet_listen_hashbucket *ilb2;
if (!h->lhash2 ||
WARN_ON_ONCE(hlist_unhashed(&inet_csk(sk)->icsk_listen_portaddr_node)))
return;
ilb2 = inet_lhash2_bucket_sk(h, sk);
spin_lock(&ilb2->lock);
hlist_del_init_rcu(&inet_csk(sk)->icsk_listen_portaddr_node);
ilb2->count--;
spin_unlock(&ilb2->lock);
}
static inline int compute_score(struct sock *sk, struct net *net,
const unsigned short hnum, const __be32 daddr,
const int dif, const int sdif, bool exact_dif)
{
int score = -1;
struct inet_sock *inet = inet_sk(sk);
if (net_eq(sock_net(sk), net) && inet->inet_num == hnum &&
!ipv6_only_sock(sk)) {
__be32 rcv_saddr = inet->inet_rcv_saddr;
score = sk->sk_family == PF_INET ? 2 : 1;
if (rcv_saddr) {
if (rcv_saddr != daddr)
return -1;
score += 4;
}
if (sk->sk_bound_dev_if || exact_dif) {
bool dev_match = (sk->sk_bound_dev_if == dif ||
sk->sk_bound_dev_if == sdif);
if (!dev_match)
return -1;
if (sk->sk_bound_dev_if)
score += 4;
}
if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
score++;
}
return score;
}
/*
* Here are some nice properties to exploit here. The BSD API
* does not allow a listening sock to specify the remote port nor the
* remote address for the connection. So always assume those are both
* wildcarded during the search since they can never be otherwise.
*/
/* called with rcu_read_lock() : No refcount taken on the socket */
static struct sock *inet_lhash2_lookup(struct net *net,
struct inet_listen_hashbucket *ilb2,
struct sk_buff *skb, int doff,
const __be32 saddr, __be16 sport,
const __be32 daddr, const unsigned short hnum,
const int dif, const int sdif)
{
bool exact_dif = inet_exact_dif_match(net, skb);
struct inet_connection_sock *icsk;
struct sock *sk, *result = NULL;
int score, hiscore = 0;
u32 phash = 0;
inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) {
sk = (struct sock *)icsk;
score = compute_score(sk, net, hnum, daddr,
dif, sdif, exact_dif);
if (score > hiscore) {
if (sk->sk_reuseport) {
phash = inet_ehashfn(net, daddr, hnum,
saddr, sport);
result = reuseport_select_sock(sk, phash,
skb, doff);
if (result)
return result;
}
result = sk;
hiscore = score;
}
}
return result;
}
struct sock *__inet_lookup_listener(struct net *net,
struct inet_hashinfo *hashinfo,
struct sk_buff *skb, int doff,
const __be32 saddr, __be16 sport,
const __be32 daddr, const unsigned short hnum,
const int dif, const int sdif)
{
unsigned int hash = inet_lhashfn(net, hnum);
struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
bool exact_dif = inet_exact_dif_match(net, skb);
struct inet_listen_hashbucket *ilb2;
struct sock *sk, *result = NULL;
struct hlist_nulls_node *node;
int score, hiscore = 0;
unsigned int hash2;
u32 phash = 0;
if (ilb->count <= 10 || !hashinfo->lhash2)
goto port_lookup;
/* Too many sk in the ilb bucket (which is hashed by port alone).
* Try lhash2 (which is hashed by port and addr) instead.
*/
hash2 = ipv4_portaddr_hash(net, daddr, hnum);
ilb2 = inet_lhash2_bucket(hashinfo, hash2);
if (ilb2->count > ilb->count)
goto port_lookup;
result = inet_lhash2_lookup(net, ilb2, skb, doff,
saddr, sport, daddr, hnum,
dif, sdif);
if (result)
goto done;
/* Lookup lhash2 with INADDR_ANY */
hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
ilb2 = inet_lhash2_bucket(hashinfo, hash2);
if (ilb2->count > ilb->count)
goto port_lookup;
result = inet_lhash2_lookup(net, ilb2, skb, doff,
saddr, sport, daddr, hnum,
dif, sdif);
goto done;
port_lookup:
sk_nulls_for_each_rcu(sk, node, &ilb->nulls_head) {
score = compute_score(sk, net, hnum, daddr,
dif, sdif, exact_dif);
if (score > hiscore) {
if (sk->sk_reuseport) {
phash = inet_ehashfn(net, daddr, hnum,
saddr, sport);
result = reuseport_select_sock(sk, phash,
skb, doff);
if (result)
goto done;
}
result = sk;
hiscore = score;
}
}
done:
if (unlikely(IS_ERR(result)))
return NULL;
return result;
}
EXPORT_SYMBOL_GPL(__inet_lookup_listener);
/* All sockets share common refcount, but have different destructors */
void sock_gen_put(struct sock *sk)
{
if (!refcount_dec_and_test(&sk->sk_refcnt))
return;
if (sk->sk_state == TCP_TIME_WAIT)
inet_twsk_free(inet_twsk(sk));
else if (sk->sk_state == TCP_NEW_SYN_RECV)
reqsk_free(inet_reqsk(sk));
else
sk_free(sk);
}
EXPORT_SYMBOL_GPL(sock_gen_put);
void sock_edemux(struct sk_buff *skb)
{
sock_gen_put(skb->sk);
}
EXPORT_SYMBOL(sock_edemux);
struct sock *__inet_lookup_established(struct net *net,
struct inet_hashinfo *hashinfo,
const __be32 saddr, const __be16 sport,
const __be32 daddr, const u16 hnum,
const int dif, const int sdif)
{
INET_ADDR_COOKIE(acookie, saddr, daddr);
const __portpair ports = INET_COMBINED_PORTS(sport, hnum);
struct sock *sk;
const struct hlist_nulls_node *node;
/* Optimize here for direct hit, only listening connections can
* have wildcards anyways.
*/
unsigned int hash = inet_ehashfn(net, daddr, hnum, saddr, sport);
unsigned int slot = hash & hashinfo->ehash_mask;
struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
begin:
sk_nulls_for_each_rcu(sk, node, &head->chain) {
if (sk->sk_hash != hash)
continue;
if (likely(INET_MATCH(sk, net, acookie,
saddr, daddr, ports, dif, sdif))) {
if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
goto out;
if (unlikely(!INET_MATCH(sk, net, acookie,
saddr, daddr, ports,
dif, sdif))) {
sock_gen_put(sk);
goto begin;
}
goto found;
}
}
/*
* if the nulls value we got at the end of this lookup is
* not the expected one, we must restart lookup.
* We probably met an item that was moved to another chain.
*/
if (get_nulls_value(node) != slot)
goto begin;
out:
sk = NULL;
found:
return sk;
}
EXPORT_SYMBOL_GPL(__inet_lookup_established);
/* called with local bh disabled */
static int __inet_check_established(struct inet_timewait_death_row *death_row,
struct sock *sk, __u16 lport,
struct inet_timewait_sock **twp)
{
struct inet_hashinfo *hinfo = death_row->hashinfo;
struct inet_sock *inet = inet_sk(sk);
__be32 daddr = inet->inet_rcv_saddr;
__be32 saddr = inet->inet_daddr;
int dif = sk->sk_bound_dev_if;
struct net *net = sock_net(sk);
int sdif = l3mdev_master_ifindex_by_index(net, dif);
INET_ADDR_COOKIE(acookie, saddr, daddr);
const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
unsigned int hash = inet_ehashfn(net, daddr, lport,
saddr, inet->inet_dport);
struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
spinlock_t *lock = inet_ehash_lockp(hinfo, hash);
struct sock *sk2;
const struct hlist_nulls_node *node;
struct inet_timewait_sock *tw = NULL;
spin_lock(lock);
sk_nulls_for_each(sk2, node, &head->chain) {
if (sk2->sk_hash != hash)
continue;
if (likely(INET_MATCH(sk2, net, acookie,
saddr, daddr, ports, dif, sdif))) {
if (sk2->sk_state == TCP_TIME_WAIT) {
tw = inet_twsk(sk2);
if (twsk_unique(sk, sk2, twp))
break;
}
goto not_unique;
}
}
/* Must record num and sport now. Otherwise we will see
* in hash table socket with a funny identity.
*/
inet->inet_num = lport;
inet->inet_sport = htons(lport);
sk->sk_hash = hash;
WARN_ON(!sk_unhashed(sk));
__sk_nulls_add_node_rcu(sk, &head->chain);
if (tw) {
sk_nulls_del_node_init_rcu((struct sock *)tw);
__NET_INC_STATS(net, LINUX_MIB_TIMEWAITRECYCLED);
}
spin_unlock(lock);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
if (twp) {
*twp = tw;
} else if (tw) {
/* Silly. Should hash-dance instead... */
inet_twsk_deschedule_put(tw);
}
return 0;
not_unique:
spin_unlock(lock);
return -EADDRNOTAVAIL;
}
static u32 inet_sk_port_offset(const struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
return secure_ipv4_port_ephemeral(inet->inet_rcv_saddr,
inet->inet_daddr,
inet->inet_dport);
}
/* insert a socket into ehash, and eventually remove another one
* (The another one can be a SYN_RECV or TIMEWAIT
*/
bool inet_ehash_insert(struct sock *sk, struct sock *osk)
{
struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
struct hlist_nulls_head *list;
struct inet_ehash_bucket *head;
spinlock_t *lock;
bool ret = true;
WARN_ON_ONCE(!sk_unhashed(sk));
sk->sk_hash = sk_ehashfn(sk);
head = inet_ehash_bucket(hashinfo, sk->sk_hash);
list = &head->chain;
lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
spin_lock(lock);
if (osk) {
WARN_ON_ONCE(sk->sk_hash != osk->sk_hash);
ret = sk_nulls_del_node_init_rcu(osk);
}
if (ret)
__sk_nulls_add_node_rcu(sk, list);
spin_unlock(lock);
return ret;
}
bool inet_ehash_nolisten(struct sock *sk, struct sock *osk)
{
bool ok = inet_ehash_insert(sk, osk);
if (ok) {
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
} else {
percpu_counter_inc(sk->sk_prot->orphan_count);
inet_sk_set_state(sk, TCP_CLOSE);
sock_set_flag(sk, SOCK_DEAD);
inet_csk_destroy_sock(sk);
}
return ok;
}
EXPORT_SYMBOL_GPL(inet_ehash_nolisten);
static int inet_reuseport_add_sock(struct sock *sk,
struct inet_listen_hashbucket *ilb)
{
struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash;
const struct hlist_nulls_node *node;
struct sock *sk2;
kuid_t uid = sock_i_uid(sk);
sk_nulls_for_each_rcu(sk2, node, &ilb->nulls_head) {
if (sk2 != sk &&
sk2->sk_family == sk->sk_family &&
ipv6_only_sock(sk2) == ipv6_only_sock(sk) &&
sk2->sk_bound_dev_if == sk->sk_bound_dev_if &&
inet_csk(sk2)->icsk_bind_hash == tb &&
sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) &&
inet_rcv_saddr_equal(sk, sk2, false))
return reuseport_add_sock(sk, sk2,
inet_rcv_saddr_any(sk));
}
return reuseport_alloc(sk, inet_rcv_saddr_any(sk));
}
int __inet_hash(struct sock *sk, struct sock *osk)
{
struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
struct inet_listen_hashbucket *ilb;
int err = 0;
if (sk->sk_state != TCP_LISTEN) {
inet_ehash_nolisten(sk, osk);
return 0;
}
WARN_ON(!sk_unhashed(sk));
ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
spin_lock(&ilb->lock);
if (sk->sk_reuseport) {
err = inet_reuseport_add_sock(sk, ilb);
if (err)
goto unlock;
}
if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
sk->sk_family == AF_INET6)
__sk_nulls_add_node_tail_rcu(sk, &ilb->nulls_head);
else
__sk_nulls_add_node_rcu(sk, &ilb->nulls_head);
inet_hash2(hashinfo, sk);
ilb->count++;
sock_set_flag(sk, SOCK_RCU_FREE);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
unlock:
spin_unlock(&ilb->lock);
return err;
}
EXPORT_SYMBOL(__inet_hash);
int inet_hash(struct sock *sk)
{
int err = 0;
if (sk->sk_state != TCP_CLOSE) {
local_bh_disable();
err = __inet_hash(sk, NULL);
local_bh_enable();
}
return err;
}
EXPORT_SYMBOL_GPL(inet_hash);
void inet_unhash(struct sock *sk)
{
struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
struct inet_listen_hashbucket *ilb = NULL;
spinlock_t *lock;
if (sk_unhashed(sk))
return;
if (sk->sk_state == TCP_LISTEN) {
ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
lock = &ilb->lock;
} else {
lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
}
spin_lock_bh(lock);
if (sk_unhashed(sk))
goto unlock;
if (rcu_access_pointer(sk->sk_reuseport_cb))
reuseport_detach_sock(sk);
if (ilb) {
inet_unhash2(hashinfo, sk);
ilb->count--;
}
__sk_nulls_del_node_init_rcu(sk);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
unlock:
spin_unlock_bh(lock);
}
EXPORT_SYMBOL_GPL(inet_unhash);
int __inet_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk, u32 port_offset,
int (*check_established)(struct inet_timewait_death_row *,
struct sock *, __u16, struct inet_timewait_sock **))
{
struct inet_hashinfo *hinfo = death_row->hashinfo;
struct inet_timewait_sock *tw = NULL;
struct inet_bind_hashbucket *head;
int port = inet_sk(sk)->inet_num;
struct net *net = sock_net(sk);
struct inet_bind_bucket *tb;
u32 remaining, offset;
int ret, i, low, high;
static u32 hint;
if (port) {
head = &hinfo->bhash[inet_bhashfn(net, port,
hinfo->bhash_size)];
tb = inet_csk(sk)->icsk_bind_hash;
spin_lock_bh(&head->lock);
if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) {
inet_ehash_nolisten(sk, NULL);
spin_unlock_bh(&head->lock);
return 0;
}
spin_unlock(&head->lock);
/* No definite answer... Walk to established hash table */
ret = check_established(death_row, sk, port, NULL);
local_bh_enable();
return ret;
}
inet_get_local_port_range(net, &low, &high);
high++; /* [32768, 60999] -> [32768, 61000[ */
remaining = high - low;
if (likely(remaining > 1))
remaining &= ~1U;
offset = (hint + port_offset) % remaining;
/* In first pass we try ports of @low parity.
* inet_csk_get_port() does the opposite choice.
*/
offset &= ~1U;
other_parity_scan:
port = low + offset;
for (i = 0; i < remaining; i += 2, port += 2) {
if (unlikely(port >= high))
port -= remaining;
if (inet_is_local_reserved_port(net, port))
continue;
head = &hinfo->bhash[inet_bhashfn(net, port,
hinfo->bhash_size)];
spin_lock_bh(&head->lock);
/* Does not bother with rcv_saddr checks, because
* the established check is already unique enough.
*/
inet_bind_bucket_for_each(tb, &head->chain) {
if (net_eq(ib_net(tb), net) && tb->port == port) {
if (tb->fastreuse >= 0 ||
tb->fastreuseport >= 0)
goto next_port;
WARN_ON(hlist_empty(&tb->owners));
if (!check_established(death_row, sk,
port, &tw))
goto ok;
goto next_port;
}
}
tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
net, head, port);
if (!tb) {
spin_unlock_bh(&head->lock);
return -ENOMEM;
}
tb->fastreuse = -1;
tb->fastreuseport = -1;
goto ok;
next_port:
spin_unlock_bh(&head->lock);
cond_resched();
}
offset++;
if ((offset & 1) && remaining > 1)
goto other_parity_scan;
return -EADDRNOTAVAIL;
ok:
hint += i + 2;
/* Head lock still held and bh's disabled */
inet_bind_hash(sk, tb, port);
if (sk_unhashed(sk)) {
inet_sk(sk)->inet_sport = htons(port);
inet_ehash_nolisten(sk, (struct sock *)tw);
}
if (tw)
inet_twsk_bind_unhash(tw, hinfo);
spin_unlock(&head->lock);
if (tw)
inet_twsk_deschedule_put(tw);
local_bh_enable();
return 0;
}
/*
* Bind a port for a connect operation and hash it.
*/
int inet_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk)
{
u32 port_offset = 0;
if (!inet_sk(sk)->inet_num)
port_offset = inet_sk_port_offset(sk);
return __inet_hash_connect(death_row, sk, port_offset,
__inet_check_established);
}
EXPORT_SYMBOL_GPL(inet_hash_connect);
void inet_hashinfo_init(struct inet_hashinfo *h)
{
int i;
for (i = 0; i < INET_LHTABLE_SIZE; i++) {
spin_lock_init(&h->listening_hash[i].lock);
INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].nulls_head,
i + LISTENING_NULLS_BASE);
h->listening_hash[i].count = 0;
}
h->lhash2 = NULL;
}
EXPORT_SYMBOL_GPL(inet_hashinfo_init);
void __init inet_hashinfo2_init(struct inet_hashinfo *h, const char *name,
unsigned long numentries, int scale,
unsigned long low_limit,
unsigned long high_limit)
{
unsigned int i;
h->lhash2 = alloc_large_system_hash(name,
sizeof(*h->lhash2),
numentries,
scale,
0,
NULL,
&h->lhash2_mask,
low_limit,
high_limit);
for (i = 0; i <= h->lhash2_mask; i++) {
spin_lock_init(&h->lhash2[i].lock);
INIT_HLIST_HEAD(&h->lhash2[i].head);
h->lhash2[i].count = 0;
}
}
int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo)
{
unsigned int locksz = sizeof(spinlock_t);
unsigned int i, nblocks = 1;
if (locksz != 0) {
/* allocate 2 cache lines or at least one spinlock per cpu */
nblocks = max(2U * L1_CACHE_BYTES / locksz, 1U);
nblocks = roundup_pow_of_two(nblocks * num_possible_cpus());
/* no more locks than number of hash buckets */
nblocks = min(nblocks, hashinfo->ehash_mask + 1);
hashinfo->ehash_locks = kvmalloc_array(nblocks, locksz, GFP_KERNEL);
if (!hashinfo->ehash_locks)
return -ENOMEM;
for (i = 0; i < nblocks; i++)
spin_lock_init(&hashinfo->ehash_locks[i]);
}
hashinfo->ehash_locks_mask = nblocks - 1;
return 0;
}
EXPORT_SYMBOL_GPL(inet_ehash_locks_alloc);
+301
View File
@@ -0,0 +1,301 @@
/*
* 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.
*
* Generic TIME_WAIT sockets functions
*
* From code orinally in TCP
*/
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <net/inet_hashtables.h>
#include <net/inet_timewait_sock.h>
#include <net/ip.h>
/**
* inet_twsk_bind_unhash - unhash a timewait socket from bind hash
* @tw: timewait socket
* @hashinfo: hashinfo pointer
*
* unhash a timewait socket from bind hash, if hashed.
* bind hash lock must be held by caller.
* Returns 1 if caller should call inet_twsk_put() after lock release.
*/
void inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
struct inet_hashinfo *hashinfo)
{
struct inet_bind_bucket *tb = tw->tw_tb;
if (!tb)
return;
__hlist_del(&tw->tw_bind_node);
tw->tw_tb = NULL;
inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
__sock_put((struct sock *)tw);
}
/* Must be called with locally disabled BHs. */
static void inet_twsk_kill(struct inet_timewait_sock *tw)
{
struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo;
spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash);
struct inet_bind_hashbucket *bhead;
spin_lock(lock);
sk_nulls_del_node_init_rcu((struct sock *)tw);
spin_unlock(lock);
/* Disassociate with bind bucket. */
bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num,
hashinfo->bhash_size)];
spin_lock(&bhead->lock);
inet_twsk_bind_unhash(tw, hashinfo);
spin_unlock(&bhead->lock);
atomic_dec(&tw->tw_dr->tw_count);
inet_twsk_put(tw);
}
void inet_twsk_free(struct inet_timewait_sock *tw)
{
struct module *owner = tw->tw_prot->owner;
twsk_destructor((struct sock *)tw);
#ifdef SOCK_REFCNT_DEBUG
pr_debug("%s timewait_sock %p released\n", tw->tw_prot->name, tw);
#endif
kmem_cache_free(tw->tw_prot->twsk_prot->twsk_slab, tw);
module_put(owner);
}
void inet_twsk_put(struct inet_timewait_sock *tw)
{
if (refcount_dec_and_test(&tw->tw_refcnt))
inet_twsk_free(tw);
}
EXPORT_SYMBOL_GPL(inet_twsk_put);
static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
struct hlist_nulls_head *list)
{
hlist_nulls_add_head_rcu(&tw->tw_node, list);
}
static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
struct hlist_head *list)
{
hlist_add_head(&tw->tw_bind_node, list);
}
/*
* Enter the time wait state. This is called with locally disabled BH.
* Essentially we whip up a timewait bucket, copy the relevant info into it
* from the SK, and mess with hash chains and list linkage.
*/
void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
struct inet_hashinfo *hashinfo)
{
const struct inet_sock *inet = inet_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_ehash_bucket *ehead = inet_ehash_bucket(hashinfo, sk->sk_hash);
spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
struct inet_bind_hashbucket *bhead;
/* Step 1: Put TW into bind hash. Original socket stays there too.
Note, that any socket with inet->num != 0 MUST be bound in
binding cache, even if it is closed.
*/
bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num,
hashinfo->bhash_size)];
spin_lock(&bhead->lock);
tw->tw_tb = icsk->icsk_bind_hash;
WARN_ON(!icsk->icsk_bind_hash);
inet_twsk_add_bind_node(tw, &tw->tw_tb->owners);
spin_unlock(&bhead->lock);
spin_lock(lock);
inet_twsk_add_node_rcu(tw, &ehead->chain);
/* Step 3: Remove SK from hash chain */
if (__sk_nulls_del_node_init_rcu(sk))
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
spin_unlock(lock);
/* tw_refcnt is set to 3 because we have :
* - one reference for bhash chain.
* - one reference for ehash chain.
* - one reference for timer.
* We can use atomic_set() because prior spin_lock()/spin_unlock()
* committed into memory all tw fields.
* Also note that after this point, we lost our implicit reference
* so we are not allowed to use tw anymore.
*/
refcount_set(&tw->tw_refcnt, 3);
}
EXPORT_SYMBOL_GPL(inet_twsk_hashdance);
static void tw_timer_handler(struct timer_list *t)
{
struct inet_timewait_sock *tw = from_timer(tw, t, tw_timer);
if (tw->tw_kill)
__NET_INC_STATS(twsk_net(tw), LINUX_MIB_TIMEWAITKILLED);
else
__NET_INC_STATS(twsk_net(tw), LINUX_MIB_TIMEWAITED);
inet_twsk_kill(tw);
}
struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
struct inet_timewait_death_row *dr,
const int state)
{
struct inet_timewait_sock *tw;
if (atomic_read(&dr->tw_count) >= dr->sysctl_max_tw_buckets)
return NULL;
tw = kmem_cache_alloc(sk->sk_prot_creator->twsk_prot->twsk_slab,
GFP_ATOMIC);
if (tw) {
const struct inet_sock *inet = inet_sk(sk);
tw->tw_dr = dr;
/* Give us an identity. */
tw->tw_daddr = inet->inet_daddr;
tw->tw_rcv_saddr = inet->inet_rcv_saddr;
tw->tw_bound_dev_if = sk->sk_bound_dev_if;
tw->tw_tos = inet->tos;
tw->tw_num = inet->inet_num;
tw->tw_state = TCP_TIME_WAIT;
tw->tw_substate = state;
tw->tw_sport = inet->inet_sport;
tw->tw_dport = inet->inet_dport;
tw->tw_family = sk->sk_family;
tw->tw_reuse = sk->sk_reuse;
tw->tw_reuseport = sk->sk_reuseport;
tw->tw_hash = sk->sk_hash;
tw->tw_ipv6only = 0;
tw->tw_transparent = inet->transparent;
tw->tw_prot = sk->sk_prot_creator;
atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie));
twsk_net_set(tw, sock_net(sk));
timer_setup(&tw->tw_timer, tw_timer_handler, TIMER_PINNED);
/*
* Because we use RCU lookups, we should not set tw_refcnt
* to a non null value before everything is setup for this
* timewait socket.
*/
refcount_set(&tw->tw_refcnt, 0);
__module_get(tw->tw_prot->owner);
}
return tw;
}
EXPORT_SYMBOL_GPL(inet_twsk_alloc);
/* These are always called from BH context. See callers in
* tcp_input.c to verify this.
*/
/* This is for handling early-kills of TIME_WAIT sockets.
* Warning : consume reference.
* Caller should not access tw anymore.
*/
void inet_twsk_deschedule_put(struct inet_timewait_sock *tw)
{
if (del_timer_sync(&tw->tw_timer))
inet_twsk_kill(tw);
inet_twsk_put(tw);
}
EXPORT_SYMBOL(inet_twsk_deschedule_put);
void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm)
{
/* timeout := RTO * 3.5
*
* 3.5 = 1+2+0.5 to wait for two retransmits.
*
* RATIONALE: if FIN arrived and we entered TIME-WAIT state,
* our ACK acking that FIN can be lost. If N subsequent retransmitted
* FINs (or previous seqments) are lost (probability of such event
* is p^(N+1), where p is probability to lose single packet and
* time to detect the loss is about RTO*(2^N - 1) with exponential
* backoff). Normal timewait length is calculated so, that we
* waited at least for one retransmitted FIN (maximal RTO is 120sec).
* [ BTW Linux. following BSD, violates this requirement waiting
* only for 60sec, we should wait at least for 240 secs.
* Well, 240 consumes too much of resources 8)
* ]
* This interval is not reduced to catch old duplicate and
* responces to our wandering segments living for two MSLs.
* However, if we use PAWS to detect
* old duplicates, we can reduce the interval to bounds required
* by RTO, rather than MSL. So, if peer understands PAWS, we
* kill tw bucket after 3.5*RTO (it is important that this number
* is greater than TS tick!) and detect old duplicates with help
* of PAWS.
*/
tw->tw_kill = timeo <= 4*HZ;
if (!rearm) {
BUG_ON(mod_timer(&tw->tw_timer, jiffies + timeo));
atomic_inc(&tw->tw_dr->tw_count);
} else {
mod_timer_pending(&tw->tw_timer, jiffies + timeo);
}
}
EXPORT_SYMBOL_GPL(__inet_twsk_schedule);
void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family)
{
struct inet_timewait_sock *tw;
struct sock *sk;
struct hlist_nulls_node *node;
unsigned int slot;
for (slot = 0; slot <= hashinfo->ehash_mask; slot++) {
struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
restart_rcu:
cond_resched();
rcu_read_lock();
restart:
sk_nulls_for_each_rcu(sk, node, &head->chain) {
if (sk->sk_state != TCP_TIME_WAIT)
continue;
tw = inet_twsk(sk);
if ((tw->tw_family != family) ||
refcount_read(&twsk_net(tw)->count))
continue;
if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt)))
continue;
if (unlikely((tw->tw_family != family) ||
refcount_read(&twsk_net(tw)->count))) {
inet_twsk_put(tw);
goto restart;
}
rcu_read_unlock();
local_bh_disable();
inet_twsk_deschedule_put(tw);
local_bh_enable();
goto restart_rcu;
}
/* If the nulls value we got at the end of this lookup is
* not the expected one, we must restart lookup.
* We probably met an item that was moved to another chain.
*/
if (get_nulls_value(node) != slot)
goto restart;
rcu_read_unlock();
}
}
EXPORT_SYMBOL_GPL(inet_twsk_purge);
+311
View File
@@ -0,0 +1,311 @@
/*
* INETPEER - A storage for permanent information about peers
*
* This source is covered by the GNU GPL, the same as all kernel sources.
*
* Authors: Andrey V. Savochkin <saw@msu.ru>
*/
#include <linux/cache.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/spinlock.h>
#include <linux/random.h>
#include <linux/timer.h>
#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/net.h>
#include <linux/workqueue.h>
#include <net/ip.h>
#include <net/inetpeer.h>
#include <net/secure_seq.h>
/*
* Theory of operations.
* We keep one entry for each peer IP address. The nodes contains long-living
* information about the peer which doesn't depend on routes.
*
* Nodes are removed only when reference counter goes to 0.
* When it's happened the node may be removed when a sufficient amount of
* time has been passed since its last use. The less-recently-used entry can
* also be removed if the pool is overloaded i.e. if the total amount of
* entries is greater-or-equal than the threshold.
*
* Node pool is organised as an RB tree.
* Such an implementation has been chosen not just for fun. It's a way to
* prevent easy and efficient DoS attacks by creating hash collisions. A huge
* amount of long living nodes in a single hash slot would significantly delay
* lookups performed with disabled BHs.
*
* Serialisation issues.
* 1. Nodes may appear in the tree only with the pool lock held.
* 2. Nodes may disappear from the tree only with the pool lock held
* AND reference count being 0.
* 3. Global variable peer_total is modified under the pool lock.
* 4. struct inet_peer fields modification:
* rb_node: pool lock
* refcnt: atomically against modifications on other CPU;
* usually under some other lock to prevent node disappearing
* daddr: unchangeable
*/
static struct kmem_cache *peer_cachep __ro_after_init;
void inet_peer_base_init(struct inet_peer_base *bp)
{
bp->rb_root = RB_ROOT;
seqlock_init(&bp->lock);
bp->total = 0;
}
EXPORT_SYMBOL_GPL(inet_peer_base_init);
#define PEER_MAX_GC 32
/* Exported for sysctl_net_ipv4. */
int inet_peer_threshold __read_mostly = 65536 + 128; /* start to throw entries more
* aggressively at this stage */
int inet_peer_minttl __read_mostly = 120 * HZ; /* TTL under high load: 120 sec */
int inet_peer_maxttl __read_mostly = 10 * 60 * HZ; /* usual time to live: 10 min */
/* Called from ip_output.c:ip_init */
void __init inet_initpeers(void)
{
struct sysinfo si;
/* Use the straight interface to information about memory. */
si_meminfo(&si);
/* The values below were suggested by Alexey Kuznetsov
* <kuznet@ms2.inr.ac.ru>. I don't have any opinion about the values
* myself. --SAW
*/
if (si.totalram <= (32768*1024)/PAGE_SIZE)
inet_peer_threshold >>= 1; /* max pool size about 1MB on IA32 */
if (si.totalram <= (16384*1024)/PAGE_SIZE)
inet_peer_threshold >>= 1; /* about 512KB */
if (si.totalram <= (8192*1024)/PAGE_SIZE)
inet_peer_threshold >>= 2; /* about 128KB */
peer_cachep = kmem_cache_create("inet_peer_cache",
sizeof(struct inet_peer),
0, SLAB_HWCACHE_ALIGN | SLAB_PANIC,
NULL);
}
/* Called with rcu_read_lock() or base->lock held */
static struct inet_peer *lookup(const struct inetpeer_addr *daddr,
struct inet_peer_base *base,
unsigned int seq,
struct inet_peer *gc_stack[],
unsigned int *gc_cnt,
struct rb_node **parent_p,
struct rb_node ***pp_p)
{
struct rb_node **pp, *parent, *next;
struct inet_peer *p;
pp = &base->rb_root.rb_node;
parent = NULL;
while (1) {
int cmp;
next = rcu_dereference_raw(*pp);
if (!next)
break;
parent = next;
p = rb_entry(parent, struct inet_peer, rb_node);
cmp = inetpeer_addr_cmp(daddr, &p->daddr);
if (cmp == 0) {
if (!refcount_inc_not_zero(&p->refcnt))
break;
return p;
}
if (gc_stack) {
if (*gc_cnt < PEER_MAX_GC)
gc_stack[(*gc_cnt)++] = p;
} else if (unlikely(read_seqretry(&base->lock, seq))) {
break;
}
if (cmp == -1)
pp = &next->rb_left;
else
pp = &next->rb_right;
}
*parent_p = parent;
*pp_p = pp;
return NULL;
}
static void inetpeer_free_rcu(struct rcu_head *head)
{
kmem_cache_free(peer_cachep, container_of(head, struct inet_peer, rcu));
}
/* perform garbage collect on all items stacked during a lookup */
static void inet_peer_gc(struct inet_peer_base *base,
struct inet_peer *gc_stack[],
unsigned int gc_cnt)
{
struct inet_peer *p;
__u32 delta, ttl;
int i;
if (base->total >= inet_peer_threshold)
ttl = 0; /* be aggressive */
else
ttl = inet_peer_maxttl
- (inet_peer_maxttl - inet_peer_minttl) / HZ *
base->total / inet_peer_threshold * HZ;
for (i = 0; i < gc_cnt; i++) {
p = gc_stack[i];
/* The READ_ONCE() pairs with the WRITE_ONCE()
* in inet_putpeer()
*/
delta = (__u32)jiffies - READ_ONCE(p->dtime);
if (delta < ttl || !refcount_dec_if_one(&p->refcnt))
gc_stack[i] = NULL;
}
for (i = 0; i < gc_cnt; i++) {
p = gc_stack[i];
if (p) {
rb_erase(&p->rb_node, &base->rb_root);
base->total--;
call_rcu(&p->rcu, inetpeer_free_rcu);
}
}
}
struct inet_peer *inet_getpeer(struct inet_peer_base *base,
const struct inetpeer_addr *daddr,
int create)
{
struct inet_peer *p, *gc_stack[PEER_MAX_GC];
struct rb_node **pp, *parent;
unsigned int gc_cnt, seq;
int invalidated;
/* Attempt a lockless lookup first.
* Because of a concurrent writer, we might not find an existing entry.
*/
rcu_read_lock();
seq = read_seqbegin(&base->lock);
p = lookup(daddr, base, seq, NULL, &gc_cnt, &parent, &pp);
invalidated = read_seqretry(&base->lock, seq);
rcu_read_unlock();
if (p)
return p;
/* If no writer did a change during our lookup, we can return early. */
if (!create && !invalidated)
return NULL;
/* retry an exact lookup, taking the lock before.
* At least, nodes should be hot in our cache.
*/
parent = NULL;
write_seqlock_bh(&base->lock);
gc_cnt = 0;
p = lookup(daddr, base, seq, gc_stack, &gc_cnt, &parent, &pp);
if (!p && create) {
p = kmem_cache_alloc(peer_cachep, GFP_ATOMIC);
if (p) {
p->daddr = *daddr;
p->dtime = (__u32)jiffies;
refcount_set(&p->refcnt, 2);
atomic_set(&p->rid, 0);
p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
p->rate_tokens = 0;
p->n_redirects = 0;
/* 60*HZ is arbitrary, but chosen enough high so that the first
* calculation of tokens is at its maximum.
*/
p->rate_last = jiffies - 60*HZ;
rb_link_node(&p->rb_node, parent, pp);
rb_insert_color(&p->rb_node, &base->rb_root);
base->total++;
}
}
if (gc_cnt)
inet_peer_gc(base, gc_stack, gc_cnt);
write_sequnlock_bh(&base->lock);
return p;
}
EXPORT_SYMBOL_GPL(inet_getpeer);
void inet_putpeer(struct inet_peer *p)
{
/* The WRITE_ONCE() pairs with itself (we run lockless)
* and the READ_ONCE() in inet_peer_gc()
*/
WRITE_ONCE(p->dtime, (__u32)jiffies);
if (refcount_dec_and_test(&p->refcnt))
call_rcu(&p->rcu, inetpeer_free_rcu);
}
EXPORT_SYMBOL_GPL(inet_putpeer);
/*
* Check transmit rate limitation for given message.
* The rate information is held in the inet_peer entries now.
* This function is generic and could be used for other purposes
* too. It uses a Token bucket filter as suggested by Alexey Kuznetsov.
*
* Note that the same inet_peer fields are modified by functions in
* route.c too, but these work for packet destinations while xrlim_allow
* works for icmp destinations. This means the rate limiting information
* for one "ip object" is shared - and these ICMPs are twice limited:
* by source and by destination.
*
* RFC 1812: 4.3.2.8 SHOULD be able to limit error message rate
* SHOULD allow setting of rate limits
*
* Shared between ICMPv4 and ICMPv6.
*/
#define XRLIM_BURST_FACTOR 6
bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout)
{
unsigned long now, token;
bool rc = false;
if (!peer)
return true;
token = peer->rate_tokens;
now = jiffies;
token += now - peer->rate_last;
peer->rate_last = now;
if (token > XRLIM_BURST_FACTOR * timeout)
token = XRLIM_BURST_FACTOR * timeout;
if (token >= timeout) {
token -= timeout;
rc = true;
}
peer->rate_tokens = token;
return rc;
}
EXPORT_SYMBOL(inet_peer_xrlim_allow);
void inetpeer_invalidate_tree(struct inet_peer_base *base)
{
struct rb_node *p = rb_first(&base->rb_root);
while (p) {
struct inet_peer *peer = rb_entry(p, struct inet_peer, rb_node);
p = rb_next(p);
rb_erase(&peer->rb_node, &base->rb_root);
inet_putpeer(peer);
cond_resched();
}
base->total = 0;
}
EXPORT_SYMBOL(inetpeer_invalidate_tree);
+168
View File
@@ -0,0 +1,168 @@
// SPDX-License-Identifier: GPL-2.0
/*
* 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.
*
* The IP forwarding functionality.
*
* Authors: see ip.c
*
* Fixes:
* Many : Split from ip.c , see ip_input.c for
* history.
* Dave Gregorich : NULL ip_rt_put fix for multicast
* routing.
* Jos Vos : Add call_out_firewall before sending,
* use output device for accounting.
* Jos Vos : Call forward firewall after routing
* (always use output device).
* Mike McLagan : Routing by source
*/
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/skbuff.h>
#include <linux/ip.h>
#include <linux/icmp.h>
#include <linux/netdevice.h>
#include <linux/slab.h>
#include <net/sock.h>
#include <net/ip.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/icmp.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/netfilter_ipv4.h>
#include <net/checksum.h>
#include <linux/route.h>
#include <net/route.h>
#include <net/xfrm.h>
static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
{
if (skb->len <= mtu)
return false;
if (unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0))
return false;
/* original fragment exceeds mtu and DF is set */
if (unlikely(IPCB(skb)->frag_max_size > mtu))
return true;
if (skb->ignore_df)
return false;
if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
return false;
return true;
}
static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct ip_options *opt = &(IPCB(skb)->opt);
__IP_INC_STATS(net, IPSTATS_MIB_OUTFORWDATAGRAMS);
__IP_ADD_STATS(net, IPSTATS_MIB_OUTOCTETS, skb->len);
if (unlikely(opt->optlen))
ip_forward_options(skb);
skb->tstamp = 0;
return dst_output(net, sk, skb);
}
int ip_forward(struct sk_buff *skb)
{
u32 mtu;
struct iphdr *iph; /* Our header */
struct rtable *rt; /* Route we use */
struct ip_options *opt = &(IPCB(skb)->opt);
struct net *net;
/* that should never happen */
if (skb->pkt_type != PACKET_HOST)
goto drop;
if (unlikely(skb->sk))
goto drop;
if (skb_warn_if_lro(skb))
goto drop;
if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb))
goto drop;
if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb))
return NET_RX_SUCCESS;
skb_forward_csum(skb);
net = dev_net(skb->dev);
/*
* According to the RFC, we must first decrease the TTL field. If
* that reaches zero, we must reply an ICMP control message telling
* that the packet's lifetime expired.
*/
if (ip_hdr(skb)->ttl <= 1)
goto too_many_hops;
if (!xfrm4_route_forward(skb))
goto drop;
rt = skb_rtable(skb);
if (opt->is_strictroute && rt->rt_uses_gateway)
goto sr_failed;
IPCB(skb)->flags |= IPSKB_FORWARDED;
mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
if (ip_exceeds_mtu(skb, mtu)) {
IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
goto drop;
}
/* We are about to mangle packet. Copy it! */
if (skb_cow(skb, LL_RESERVED_SPACE(rt->dst.dev)+rt->dst.header_len))
goto drop;
iph = ip_hdr(skb);
/* Decrease ttl after skb cow done */
ip_decrease_ttl(iph);
/*
* We now generate an ICMP HOST REDIRECT giving the route
* we calculated.
*/
if (IPCB(skb)->flags & IPSKB_DOREDIRECT && !opt->srr &&
!skb_sec_path(skb))
ip_rt_send_redirect(skb);
if (net->ipv4.sysctl_ip_fwd_update_priority)
skb->priority = rt_tos2priority(iph->tos);
return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD,
net, NULL, skb, skb->dev, rt->dst.dev,
ip_forward_finish);
sr_failed:
/*
* Strict routing permits no gatewaying
*/
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_SR_FAILED, 0);
goto drop;
too_many_hops:
/* Tell the sender its packet died... */
__IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS);
icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
+752
View File
@@ -0,0 +1,752 @@
// SPDX-License-Identifier: GPL-2.0
/*
* 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.
*
* The IP fragmentation functionality.
*
* Authors: Fred N. van Kempen <waltje@uWalt.NL.Mugnet.ORG>
* Alan Cox <alan@lxorguk.ukuu.org.uk>
*
* Fixes:
* Alan Cox : Split from ip.c , see ip_input.c for history.
* David S. Miller : Begin massive cleanup...
* Andi Kleen : Add sysctls.
* xxxx : Overlapfrag bug.
* Ultima : ip_expire() kernel panic.
* Bill Hawes : Frag accounting and evictor fixes.
* John McDonald : 0 length frag bug.
* Alexey Kuznetsov: SMP races, threading, cleanup.
* Patrick McHardy : LRU queue of frag heads for evictor.
*/
#define pr_fmt(fmt) "IPv4: " fmt
#include <linux/compiler.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/jiffies.h>
#include <linux/skbuff.h>
#include <linux/list.h>
#include <linux/ip.h>
#include <linux/icmp.h>
#include <linux/netdevice.h>
#include <linux/jhash.h>
#include <linux/random.h>
#include <linux/slab.h>
#include <net/route.h>
#include <net/dst.h>
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/checksum.h>
#include <net/inetpeer.h>
#include <net/inet_frag.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/inet.h>
#include <linux/netfilter_ipv4.h>
#include <net/inet_ecn.h>
#include <net/l3mdev.h>
/* NOTE. Logic of IP defragmentation is parallel to corresponding IPv6
* code now. If you change something here, _PLEASE_ update ipv6/reassembly.c
* as well. Or notify me, at least. --ANK
*/
static const char ip_frag_cache_name[] = "ip4-frags";
/* Describe an entry in the "incomplete datagrams" queue. */
struct ipq {
struct inet_frag_queue q;
u8 ecn; /* RFC3168 support */
u16 max_df_size; /* largest frag with DF set seen */
int iif;
unsigned int rid;
struct inet_peer *peer;
};
static u8 ip4_frag_ecn(u8 tos)
{
return 1 << (tos & INET_ECN_MASK);
}
static struct inet_frags ip4_frags;
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
struct sk_buff *prev_tail, struct net_device *dev);
static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
{
struct ipq *qp = container_of(q, struct ipq, q);
struct netns_ipv4 *ipv4 = container_of(q->net, struct netns_ipv4,
frags);
struct net *net = container_of(ipv4, struct net, ipv4);
const struct frag_v4_compare_key *key = a;
q->key.v4 = *key;
qp->ecn = 0;
qp->peer = q->net->max_dist ?
inet_getpeer_v4(net->ipv4.peers, key->saddr, key->vif, 1) :
NULL;
}
static void ip4_frag_free(struct inet_frag_queue *q)
{
struct ipq *qp;
qp = container_of(q, struct ipq, q);
if (qp->peer)
inet_putpeer(qp->peer);
}
/* Destruction primitives. */
static void ipq_put(struct ipq *ipq)
{
inet_frag_put(&ipq->q);
}
/* Kill ipq entry. It is not destroyed immediately,
* because caller (and someone more) holds reference count.
*/
static void ipq_kill(struct ipq *ipq)
{
inet_frag_kill(&ipq->q);
}
static bool frag_expire_skip_icmp(u32 user)
{
return user == IP_DEFRAG_AF_PACKET ||
ip_defrag_user_in_between(user, IP_DEFRAG_CONNTRACK_IN,
__IP_DEFRAG_CONNTRACK_IN_END) ||
ip_defrag_user_in_between(user, IP_DEFRAG_CONNTRACK_BRIDGE_IN,
__IP_DEFRAG_CONNTRACK_BRIDGE_IN);
}
/*
* Oops, a fragment queue timed out. Kill it and send an ICMP reply.
*/
static void ip_expire(struct timer_list *t)
{
struct inet_frag_queue *frag = from_timer(frag, t, timer);
const struct iphdr *iph;
struct sk_buff *head = NULL;
struct net *net;
struct ipq *qp;
int err;
qp = container_of(frag, struct ipq, q);
net = container_of(qp->q.net, struct net, ipv4.frags);
rcu_read_lock();
spin_lock(&qp->q.lock);
if (qp->q.flags & INET_FRAG_COMPLETE)
goto out;
ipq_kill(qp);
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
if (!(qp->q.flags & INET_FRAG_FIRST_IN))
goto out;
/* sk_buff::dev and sk_buff::rbnode are unionized. So we
* pull the head out of the tree in order to be able to
* deal with head->dev.
*/
head = inet_frag_pull_head(&qp->q);
if (!head)
goto out;
head->dev = dev_get_by_index_rcu(net, qp->iif);
if (!head->dev)
goto out;
/* skb has no dst, perform route lookup again */
iph = ip_hdr(head);
err = ip_route_input_noref(head, iph->daddr, iph->saddr,
iph->tos, head->dev);
if (err)
goto out;
/* Only an end host needs to send an ICMP
* "Fragment Reassembly Timeout" message, per RFC792.
*/
if (frag_expire_skip_icmp(qp->q.key.v4.user) &&
(skb_rtable(head)->rt_type != RTN_LOCAL))
goto out;
spin_unlock(&qp->q.lock);
icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
goto out_rcu_unlock;
out:
spin_unlock(&qp->q.lock);
out_rcu_unlock:
rcu_read_unlock();
if (head)
kfree_skb(head);
ipq_put(qp);
}
/* Find the correct entry in the "incomplete datagrams" queue for
* this IP datagram, and create new one, if nothing is found.
*/
static struct ipq *ip_find(struct net *net, struct iphdr *iph,
u32 user, int vif)
{
struct frag_v4_compare_key key = {
.saddr = iph->saddr,
.daddr = iph->daddr,
.user = user,
.vif = vif,
.id = iph->id,
.protocol = iph->protocol,
};
struct inet_frag_queue *q;
q = inet_frag_find(&net->ipv4.frags, &key);
if (!q)
return NULL;
return container_of(q, struct ipq, q);
}
/* Is the fragment too far ahead to be part of ipq? */
static int ip_frag_too_far(struct ipq *qp)
{
struct inet_peer *peer = qp->peer;
unsigned int max = qp->q.net->max_dist;
unsigned int start, end;
int rc;
if (!peer || !max)
return 0;
start = qp->rid;
end = atomic_inc_return(&peer->rid);
qp->rid = end;
rc = qp->q.fragments_tail && (end - start) > max;
if (rc) {
struct net *net;
net = container_of(qp->q.net, struct net, ipv4.frags);
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
}
return rc;
}
static int ip_frag_reinit(struct ipq *qp)
{
unsigned int sum_truesize = 0;
if (!mod_timer(&qp->q.timer, jiffies + qp->q.net->timeout)) {
refcount_inc(&qp->q.refcnt);
return -ETIMEDOUT;
}
sum_truesize = inet_frag_rbtree_purge(&qp->q.rb_fragments);
sub_frag_mem_limit(qp->q.net, sum_truesize);
qp->q.flags = 0;
qp->q.len = 0;
qp->q.meat = 0;
qp->q.fragments = NULL;
qp->q.rb_fragments = RB_ROOT;
qp->q.fragments_tail = NULL;
qp->q.last_run_head = NULL;
qp->iif = 0;
qp->ecn = 0;
return 0;
}
/* Add new segment to existing queue. */
static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
{
struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
int ihl, end, flags, offset;
struct sk_buff *prev_tail;
struct net_device *dev;
unsigned int fragsize;
int err = -ENOENT;
u8 ecn;
if (qp->q.flags & INET_FRAG_COMPLETE)
goto err;
if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) &&
unlikely(ip_frag_too_far(qp)) &&
unlikely(err = ip_frag_reinit(qp))) {
ipq_kill(qp);
goto err;
}
ecn = ip4_frag_ecn(ip_hdr(skb)->tos);
offset = ntohs(ip_hdr(skb)->frag_off);
flags = offset & ~IP_OFFSET;
offset &= IP_OFFSET;
offset <<= 3; /* offset is in 8-byte chunks */
ihl = ip_hdrlen(skb);
/* Determine the position of this fragment. */
end = offset + skb->len - skb_network_offset(skb) - ihl;
err = -EINVAL;
/* Is this the final fragment? */
if ((flags & IP_MF) == 0) {
/* If we already have some bits beyond end
* or have different end, the segment is corrupted.
*/
if (end < qp->q.len ||
((qp->q.flags & INET_FRAG_LAST_IN) && end != qp->q.len))
goto discard_qp;
qp->q.flags |= INET_FRAG_LAST_IN;
qp->q.len = end;
} else {
if (end&7) {
end &= ~7;
if (skb->ip_summed != CHECKSUM_UNNECESSARY)
skb->ip_summed = CHECKSUM_NONE;
}
if (end > qp->q.len) {
/* Some bits beyond end -> corruption. */
if (qp->q.flags & INET_FRAG_LAST_IN)
goto discard_qp;
qp->q.len = end;
}
}
if (end == offset)
goto discard_qp;
err = -ENOMEM;
if (!pskb_pull(skb, skb_network_offset(skb) + ihl))
goto discard_qp;
err = pskb_trim_rcsum(skb, end - offset);
if (err)
goto discard_qp;
/* Note : skb->rbnode and skb->dev share the same location. */
dev = skb->dev;
/* Makes sure compiler wont do silly aliasing games */
barrier();
prev_tail = qp->q.fragments_tail;
err = inet_frag_queue_insert(&qp->q, skb, offset, end);
if (err)
goto insert_error;
if (dev)
qp->iif = dev->ifindex;
qp->q.stamp = skb->tstamp;
qp->q.meat += skb->len;
qp->ecn |= ecn;
add_frag_mem_limit(qp->q.net, skb->truesize);
if (offset == 0)
qp->q.flags |= INET_FRAG_FIRST_IN;
fragsize = skb->len + ihl;
if (fragsize > qp->q.max_size)
qp->q.max_size = fragsize;
if (ip_hdr(skb)->frag_off & htons(IP_DF) &&
fragsize > qp->max_df_size)
qp->max_df_size = fragsize;
if (qp->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
qp->q.meat == qp->q.len) {
unsigned long orefdst = skb->_skb_refdst;
skb->_skb_refdst = 0UL;
err = ip_frag_reasm(qp, skb, prev_tail, dev);
skb->_skb_refdst = orefdst;
if (err)
inet_frag_kill(&qp->q);
return err;
}
skb_dst_drop(skb);
return -EINPROGRESS;
insert_error:
if (err == IPFRAG_DUP) {
kfree_skb(skb);
return -EINVAL;
}
err = -EINVAL;
__IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS);
discard_qp:
inet_frag_kill(&qp->q);
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
err:
kfree_skb(skb);
return err;
}
/* Build a new IP datagram from all its fragments. */
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
struct sk_buff *prev_tail, struct net_device *dev)
{
struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
struct iphdr *iph;
void *reasm_data;
int len, err;
u8 ecn;
ipq_kill(qp);
ecn = ip_frag_ecn_table[qp->ecn];
if (unlikely(ecn == 0xff)) {
err = -EINVAL;
goto out_fail;
}
/* Make the one we just received the head. */
reasm_data = inet_frag_reasm_prepare(&qp->q, skb, prev_tail);
if (!reasm_data)
goto out_nomem;
len = ip_hdrlen(skb) + qp->q.len;
err = -E2BIG;
if (len > 65535)
goto out_oversize;
inet_frag_reasm_finish(&qp->q, skb, reasm_data);
skb->dev = dev;
IPCB(skb)->frag_max_size = max(qp->max_df_size, qp->q.max_size);
iph = ip_hdr(skb);
iph->tot_len = htons(len);
iph->tos |= ecn;
/* When we set IP_DF on a refragmented skb we must also force a
* call to ip_fragment to avoid forwarding a DF-skb of size s while
* original sender only sent fragments of size f (where f < s).
*
* We only set DF/IPSKB_FRAG_PMTU if such DF fragment was the largest
* frag seen to avoid sending tiny DF-fragments in case skb was built
* from one very small df-fragment and one large non-df frag.
*/
if (qp->max_df_size == qp->q.max_size) {
IPCB(skb)->flags |= IPSKB_FRAG_PMTU;
iph->frag_off = htons(IP_DF);
} else {
iph->frag_off = 0;
}
ip_send_check(iph);
__IP_INC_STATS(net, IPSTATS_MIB_REASMOKS);
qp->q.fragments = NULL;
qp->q.rb_fragments = RB_ROOT;
qp->q.fragments_tail = NULL;
qp->q.last_run_head = NULL;
return 0;
out_nomem:
net_dbg_ratelimited("queue_glue: no memory for gluing queue %p\n", qp);
err = -ENOMEM;
goto out_fail;
out_oversize:
net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->q.key.v4.saddr);
out_fail:
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
return err;
}
/* Process an incoming IP datagram fragment. */
int ip_defrag(struct net *net, struct sk_buff *skb, u32 user)
{
struct net_device *dev = skb->dev ? : skb_dst(skb)->dev;
int vif = l3mdev_master_ifindex_rcu(dev);
struct ipq *qp;
__IP_INC_STATS(net, IPSTATS_MIB_REASMREQDS);
skb_orphan(skb);
/* Lookup (or create) queue header */
qp = ip_find(net, ip_hdr(skb), user, vif);
if (qp) {
int ret;
spin_lock(&qp->q.lock);
ret = ip_frag_queue(qp, skb);
spin_unlock(&qp->q.lock);
ipq_put(qp);
return ret;
}
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
kfree_skb(skb);
return -ENOMEM;
}
EXPORT_SYMBOL(ip_defrag);
struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
{
struct iphdr iph;
int netoff;
u32 len;
if (skb->protocol != htons(ETH_P_IP))
return skb;
netoff = skb_network_offset(skb);
if (skb_copy_bits(skb, netoff, &iph, sizeof(iph)) < 0)
return skb;
if (iph.ihl < 5 || iph.version != 4)
return skb;
len = ntohs(iph.tot_len);
if (skb->len < netoff + len || len < (iph.ihl * 4))
return skb;
if (ip_is_fragment(&iph)) {
skb = skb_share_check(skb, GFP_ATOMIC);
if (skb) {
if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) {
kfree_skb(skb);
return NULL;
}
if (pskb_trim_rcsum(skb, netoff + len)) {
kfree_skb(skb);
return NULL;
}
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
if (ip_defrag(net, skb, user))
return NULL;
skb_clear_hash(skb);
}
}
return skb;
}
EXPORT_SYMBOL(ip_check_defrag);
#ifdef CONFIG_SYSCTL
static int dist_min;
static struct ctl_table ip4_frags_ns_ctl_table[] = {
{
.procname = "ipfrag_high_thresh",
.data = &init_net.ipv4.frags.high_thresh,
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
.extra1 = &init_net.ipv4.frags.low_thresh
},
{
.procname = "ipfrag_low_thresh",
.data = &init_net.ipv4.frags.low_thresh,
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
.extra2 = &init_net.ipv4.frags.high_thresh
},
{
.procname = "ipfrag_time",
.data = &init_net.ipv4.frags.timeout,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "ipfrag_max_dist",
.data = &init_net.ipv4.frags.max_dist,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &dist_min,
},
{ }
};
/* secret interval has been deprecated */
static int ip4_frags_secret_interval_unused;
static struct ctl_table ip4_frags_ctl_table[] = {
{
.procname = "ipfrag_secret_interval",
.data = &ip4_frags_secret_interval_unused,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{ }
};
static int __net_init ip4_frags_ns_ctl_register(struct net *net)
{
struct ctl_table *table;
struct ctl_table_header *hdr;
table = ip4_frags_ns_ctl_table;
if (!net_eq(net, &init_net)) {
table = kmemdup(table, sizeof(ip4_frags_ns_ctl_table), GFP_KERNEL);
if (!table)
goto err_alloc;
table[0].data = &net->ipv4.frags.high_thresh;
table[0].extra1 = &net->ipv4.frags.low_thresh;
table[0].extra2 = &init_net.ipv4.frags.high_thresh;
table[1].data = &net->ipv4.frags.low_thresh;
table[1].extra2 = &net->ipv4.frags.high_thresh;
table[2].data = &net->ipv4.frags.timeout;
table[3].data = &net->ipv4.frags.max_dist;
}
hdr = register_net_sysctl(net, "net/ipv4", table);
if (!hdr)
goto err_reg;
net->ipv4.frags_hdr = hdr;
return 0;
err_reg:
if (!net_eq(net, &init_net))
kfree(table);
err_alloc:
return -ENOMEM;
}
static void __net_exit ip4_frags_ns_ctl_unregister(struct net *net)
{
struct ctl_table *table;
table = net->ipv4.frags_hdr->ctl_table_arg;
unregister_net_sysctl_table(net->ipv4.frags_hdr);
kfree(table);
}
static void __init ip4_frags_ctl_register(void)
{
register_net_sysctl(&init_net, "net/ipv4", ip4_frags_ctl_table);
}
#else
static int ip4_frags_ns_ctl_register(struct net *net)
{
return 0;
}
static void ip4_frags_ns_ctl_unregister(struct net *net)
{
}
static void __init ip4_frags_ctl_register(void)
{
}
#endif
static int __net_init ipv4_frags_init_net(struct net *net)
{
int res;
/* Fragment cache limits.
*
* The fragment memory accounting code, (tries to) account for
* the real memory usage, by measuring both the size of frag
* queue struct (inet_frag_queue (ipv4:ipq/ipv6:frag_queue))
* and the SKB's truesize.
*
* A 64K fragment consumes 129736 bytes (44*2944)+200
* (1500 truesize == 2944, sizeof(struct ipq) == 200)
*
* We will commit 4MB at one time. Should we cross that limit
* we will prune down to 3MB, making room for approx 8 big 64K
* fragments 8x128k.
*/
net->ipv4.frags.high_thresh = 4 * 1024 * 1024;
net->ipv4.frags.low_thresh = 3 * 1024 * 1024;
/*
* Important NOTE! Fragment queue must be destroyed before MSL expires.
* RFC791 is wrong proposing to prolongate timer each fragment arrival
* by TTL.
*/
net->ipv4.frags.timeout = IP_FRAG_TIME;
net->ipv4.frags.max_dist = 64;
net->ipv4.frags.f = &ip4_frags;
res = inet_frags_init_net(&net->ipv4.frags);
if (res < 0)
return res;
res = ip4_frags_ns_ctl_register(net);
if (res < 0)
inet_frags_exit_net(&net->ipv4.frags);
return res;
}
static void __net_exit ipv4_frags_exit_net(struct net *net)
{
ip4_frags_ns_ctl_unregister(net);
inet_frags_exit_net(&net->ipv4.frags);
}
static struct pernet_operations ip4_frags_ops = {
.init = ipv4_frags_init_net,
.exit = ipv4_frags_exit_net,
};
static u32 ip4_key_hashfn(const void *data, u32 len, u32 seed)
{
return jhash2(data,
sizeof(struct frag_v4_compare_key) / sizeof(u32), seed);
}
static u32 ip4_obj_hashfn(const void *data, u32 len, u32 seed)
{
const struct inet_frag_queue *fq = data;
return jhash2((const u32 *)&fq->key.v4,
sizeof(struct frag_v4_compare_key) / sizeof(u32), seed);
}
static int ip4_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
{
const struct frag_v4_compare_key *key = arg->key;
const struct inet_frag_queue *fq = ptr;
return !!memcmp(&fq->key, key, sizeof(*key));
}
static const struct rhashtable_params ip4_rhash_params = {
.head_offset = offsetof(struct inet_frag_queue, node),
.key_offset = offsetof(struct inet_frag_queue, key),
.key_len = sizeof(struct frag_v4_compare_key),
.hashfn = ip4_key_hashfn,
.obj_hashfn = ip4_obj_hashfn,
.obj_cmpfn = ip4_obj_cmpfn,
.automatic_shrinking = true,
};
void __init ipfrag_init(void)
{
ip4_frags.constructor = ip4_frag_init;
ip4_frags.destructor = ip4_frag_free;
ip4_frags.qsize = sizeof(struct ipq);
ip4_frags.frag_expire = ip_expire;
ip4_frags.frags_cache_name = ip_frag_cache_name;
ip4_frags.rhash_params = ip4_rhash_params;
if (inet_frags_init(&ip4_frags))
panic("IP: failed to allocate ip4_frags cache\n");
ip4_frags_ctl_register();
register_pernet_subsys(&ip4_frags_ops);
}
+1839
View File
File diff suppressed because it is too large. Load diff
+619
View File
@@ -0,0 +1,619 @@
/*
* 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.
*
* The Internet Protocol (IP) module.
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Donald Becker, <becker@super.org>
* Alan Cox, <alan@lxorguk.ukuu.org.uk>
* Richard Underwood
* Stefan Becker, <stefanb@yello.ping.de>
* Jorge Cwik, <jorge@laser.satlink.net>
* Arnt Gulbrandsen, <agulbra@nvg.unit.no>
*
*
* Fixes:
* Alan Cox : Commented a couple of minor bits of surplus code
* Alan Cox : Undefining IP_FORWARD doesn't include the code
* (just stops a compiler warning).
* Alan Cox : Frames with >=MAX_ROUTE record routes, strict routes or loose routes
* are junked rather than corrupting things.
* Alan Cox : Frames to bad broadcast subnets are dumped
* We used to process them non broadcast and
* boy could that cause havoc.
* Alan Cox : ip_forward sets the free flag on the
* new frame it queues. Still crap because
* it copies the frame but at least it
* doesn't eat memory too.
* Alan Cox : Generic queue code and memory fixes.
* Fred Van Kempen : IP fragment support (borrowed from NET2E)
* Gerhard Koerting: Forward fragmented frames correctly.
* Gerhard Koerting: Fixes to my fix of the above 8-).
* Gerhard Koerting: IP interface addressing fix.
* Linus Torvalds : More robustness checks
* Alan Cox : Even more checks: Still not as robust as it ought to be
* Alan Cox : Save IP header pointer for later
* Alan Cox : ip option setting
* Alan Cox : Use ip_tos/ip_ttl settings
* Alan Cox : Fragmentation bogosity removed
* (Thanks to Mark.Bush@prg.ox.ac.uk)
* Dmitry Gorodchanin : Send of a raw packet crash fix.
* Alan Cox : Silly ip bug when an overlength
* fragment turns up. Now frees the
* queue.
* Linus Torvalds/ : Memory leakage on fragmentation
* Alan Cox : handling.
* Gerhard Koerting: Forwarding uses IP priority hints
* Teemu Rantanen : Fragment problems.
* Alan Cox : General cleanup, comments and reformat
* Alan Cox : SNMP statistics
* Alan Cox : BSD address rule semantics. Also see
* UDP as there is a nasty checksum issue
* if you do things the wrong way.
* Alan Cox : Always defrag, moved IP_FORWARD to the config.in file
* Alan Cox : IP options adjust sk->priority.
* Pedro Roque : Fix mtu/length error in ip_forward.
* Alan Cox : Avoid ip_chk_addr when possible.
* Richard Underwood : IP multicasting.
* Alan Cox : Cleaned up multicast handlers.
* Alan Cox : RAW sockets demultiplex in the BSD style.
* Gunther Mayer : Fix the SNMP reporting typo
* Alan Cox : Always in group 224.0.0.1
* Pauline Middelink : Fast ip_checksum update when forwarding
* Masquerading support.
* Alan Cox : Multicast loopback error for 224.0.0.1
* Alan Cox : IP_MULTICAST_LOOP option.
* Alan Cox : Use notifiers.
* Bjorn Ekwall : Removed ip_csum (from slhc.c too)
* Bjorn Ekwall : Moved ip_fast_csum to ip.h (inline!)
* Stefan Becker : Send out ICMP HOST REDIRECT
* Arnt Gulbrandsen : ip_build_xmit
* Alan Cox : Per socket routing cache
* Alan Cox : Fixed routing cache, added header cache.
* Alan Cox : Loopback didn't work right in original ip_build_xmit - fixed it.
* Alan Cox : Only send ICMP_REDIRECT if src/dest are the same net.
* Alan Cox : Incoming IP option handling.
* Alan Cox : Set saddr on raw output frames as per BSD.
* Alan Cox : Stopped broadcast source route explosions.
* Alan Cox : Can disable source routing
* Takeshi Sone : Masquerading didn't work.
* Dave Bonn,Alan Cox : Faster IP forwarding whenever possible.
* Alan Cox : Memory leaks, tramples, misc debugging.
* Alan Cox : Fixed multicast (by popular demand 8))
* Alan Cox : Fixed forwarding (by even more popular demand 8))
* Alan Cox : Fixed SNMP statistics [I think]
* Gerhard Koerting : IP fragmentation forwarding fix
* Alan Cox : Device lock against page fault.
* Alan Cox : IP_HDRINCL facility.
* Werner Almesberger : Zero fragment bug
* Alan Cox : RAW IP frame length bug
* Alan Cox : Outgoing firewall on build_xmit
* A.N.Kuznetsov : IP_OPTIONS support throughout the kernel
* Alan Cox : Multicast routing hooks
* Jos Vos : Do accounting *before* call_in_firewall
* Willy Konynenberg : Transparent proxying support
*
*
*
* To Fix:
* IP fragmentation wants rewriting cleanly. The RFC815 algorithm is much more efficient
* and could be made very efficient with the addition of some virtual memory hacks to permit
* the allocation of a buffer that can then be 'grown' by twiddling page tables.
* Output fragmentation wants updating along with the buffer management to use a single
* interleaved copy algorithm so that fragmenting has a one copy overhead. Actual packet
* output should probably do its own fragmentation at the UDP/RAW layer. TCP shouldn't cause
* fragmentation anyway.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#define pr_fmt(fmt) "IPv4: " fmt
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/net.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/inetdevice.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <net/snmp.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/route.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/arp.h>
#include <net/icmp.h>
#include <net/raw.h>
#include <net/checksum.h>
#include <net/inet_ecn.h>
#include <linux/netfilter_ipv4.h>
#include <net/xfrm.h>
#include <linux/mroute.h>
#include <linux/netlink.h>
#include <net/dst_metadata.h>
/*
* Process Router Attention IP option (RFC 2113)
*/
bool ip_call_ra_chain(struct sk_buff *skb)
{
struct ip_ra_chain *ra;
u8 protocol = ip_hdr(skb)->protocol;
struct sock *last = NULL;
struct net_device *dev = skb->dev;
struct net *net = dev_net(dev);
for (ra = rcu_dereference(net->ipv4.ra_chain); ra; ra = rcu_dereference(ra->next)) {
struct sock *sk = ra->sk;
/* If socket is bound to an interface, only report
* the packet if it came from that interface.
*/
if (sk && inet_sk(sk)->inet_num == protocol &&
(!sk->sk_bound_dev_if ||
sk->sk_bound_dev_if == dev->ifindex)) {
if (ip_is_fragment(ip_hdr(skb))) {
if (ip_defrag(net, skb, IP_DEFRAG_CALL_RA_CHAIN))
return true;
}
if (last) {
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
if (skb2)
raw_rcv(last, skb2);
}
last = sk;
}
}
if (last) {
raw_rcv(last, skb);
return true;
}
return false;
}
void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int protocol)
{
const struct net_protocol *ipprot;
int raw, ret;
resubmit:
raw = raw_local_deliver(skb, protocol);
ipprot = rcu_dereference(inet_protos[protocol]);
if (ipprot) {
if (!ipprot->no_policy) {
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
kfree_skb(skb);
return;
}
nf_reset(skb);
}
ret = ipprot->handler(skb);
if (ret < 0) {
protocol = -ret;
goto resubmit;
}
__IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS);
} else {
if (!raw) {
if (xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
__IP_INC_STATS(net, IPSTATS_MIB_INUNKNOWNPROTOS);
icmp_send(skb, ICMP_DEST_UNREACH,
ICMP_PROT_UNREACH, 0);
}
kfree_skb(skb);
} else {
__IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS);
consume_skb(skb);
}
}
}
static int ip_local_deliver_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
__skb_pull(skb, skb_network_header_len(skb));
rcu_read_lock();
ip_protocol_deliver_rcu(net, skb, ip_hdr(skb)->protocol);
rcu_read_unlock();
return 0;
}
/*
* Deliver IP Packets to the higher protocol layers.
*/
int ip_local_deliver(struct sk_buff *skb)
{
/*
* Reassemble IP fragments.
*/
struct net *net = dev_net(skb->dev);
if (ip_is_fragment(ip_hdr(skb))) {
if (ip_defrag(net, skb, IP_DEFRAG_LOCAL_DELIVER))
return 0;
}
return NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_IN,
net, NULL, skb, skb->dev, NULL,
ip_local_deliver_finish);
}
static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev)
{
struct ip_options *opt;
const struct iphdr *iph;
/* It looks as overkill, because not all
IP options require packet mangling.
But it is the easiest for now, especially taking
into account that combination of IP options
and running sniffer is extremely rare condition.
--ANK (980813)
*/
if (skb_cow(skb, skb_headroom(skb))) {
__IP_INC_STATS(dev_net(dev), IPSTATS_MIB_INDISCARDS);
goto drop;
}
iph = ip_hdr(skb);
opt = &(IPCB(skb)->opt);
opt->optlen = iph->ihl*4 - sizeof(struct iphdr);
if (ip_options_compile(dev_net(dev), opt, skb)) {
__IP_INC_STATS(dev_net(dev), IPSTATS_MIB_INHDRERRORS);
goto drop;
}
if (unlikely(opt->srr)) {
struct in_device *in_dev = __in_dev_get_rcu(dev);
if (in_dev) {
if (!IN_DEV_SOURCE_ROUTE(in_dev)) {
if (IN_DEV_LOG_MARTIANS(in_dev))
net_info_ratelimited("source route option %pI4 -> %pI4\n",
&iph->saddr,
&iph->daddr);
goto drop;
}
}
if (ip_options_rcv_srr(skb, dev))
goto drop;
}
return false;
drop:
return true;
}
static int ip_rcv_finish_core(struct net *net, struct sock *sk,
struct sk_buff *skb, struct net_device *dev)
{
const struct iphdr *iph = ip_hdr(skb);
int (*edemux)(struct sk_buff *skb);
struct rtable *rt;
int err;
if (net->ipv4.sysctl_ip_early_demux &&
!skb_dst(skb) &&
!skb->sk &&
!ip_is_fragment(iph)) {
const struct net_protocol *ipprot;
int protocol = iph->protocol;
ipprot = rcu_dereference(inet_protos[protocol]);
if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) {
err = edemux(skb);
if (unlikely(err))
goto drop_error;
/* must reload iph, skb->head might have changed */
iph = ip_hdr(skb);
}
}
/*
* Initialise the virtual path cache for the packet. It describes
* how the packet travels inside Linux networking.
*/
if (!skb_valid_dst(skb)) {
err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
iph->tos, dev);
if (unlikely(err))
goto drop_error;
}
#ifdef CONFIG_IP_ROUTE_CLASSID
if (unlikely(skb_dst(skb)->tclassid)) {
struct ip_rt_acct *st = this_cpu_ptr(ip_rt_acct);
u32 idx = skb_dst(skb)->tclassid;
st[idx&0xFF].o_packets++;
st[idx&0xFF].o_bytes += skb->len;
st[(idx>>16)&0xFF].i_packets++;
st[(idx>>16)&0xFF].i_bytes += skb->len;
}
#endif
if (iph->ihl > 5 && ip_rcv_options(skb, dev))
goto drop;
rt = skb_rtable(skb);
if (rt->rt_type == RTN_MULTICAST) {
__IP_UPD_PO_STATS(net, IPSTATS_MIB_INMCAST, skb->len);
} else if (rt->rt_type == RTN_BROADCAST) {
__IP_UPD_PO_STATS(net, IPSTATS_MIB_INBCAST, skb->len);
} else if (skb->pkt_type == PACKET_BROADCAST ||
skb->pkt_type == PACKET_MULTICAST) {
struct in_device *in_dev = __in_dev_get_rcu(dev);
/* RFC 1122 3.3.6:
*
* When a host sends a datagram to a link-layer broadcast
* address, the IP destination address MUST be a legal IP
* broadcast or IP multicast address.
*
* A host SHOULD silently discard a datagram that is received
* via a link-layer broadcast (see Section 2.4) but does not
* specify an IP multicast or broadcast destination address.
*
* This doesn't explicitly say L2 *broadcast*, but broadcast is
* in a way a form of multicast and the most common use case for
* this is 802.11 protecting against cross-station spoofing (the
* so-called "hole-196" attack) so do it for both.
*/
if (in_dev &&
IN_DEV_ORCONF(in_dev, DROP_UNICAST_IN_L2_MULTICAST))
goto drop;
}
return NET_RX_SUCCESS;
drop:
kfree_skb(skb);
return NET_RX_DROP;
drop_error:
if (err == -EXDEV)
__NET_INC_STATS(net, LINUX_MIB_IPRPFILTER);
goto drop;
}
static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
int ret;
/* if ingress device is enslaved to an L3 master device pass the
* skb to its handler for processing
*/
skb = l3mdev_ip_rcv(skb);
if (!skb)
return NET_RX_SUCCESS;
ret = ip_rcv_finish_core(net, sk, skb, dev);
if (ret != NET_RX_DROP)
ret = dst_input(skb);
return ret;
}
/*
* Main IP Receive routine.
*/
static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)
{
const struct iphdr *iph;
u32 len;
/* When the interface is in promisc. mode, drop all the crap
* that it receives, do not try to analyse it.
*/
if (skb->pkt_type == PACKET_OTHERHOST)
goto drop;
__IP_UPD_PO_STATS(net, IPSTATS_MIB_IN, skb->len);
skb = skb_share_check(skb, GFP_ATOMIC);
if (!skb) {
__IP_INC_STATS(net, IPSTATS_MIB_INDISCARDS);
goto out;
}
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto inhdr_error;
iph = ip_hdr(skb);
/*
* RFC1122: 3.2.1.2 MUST silently discard any IP frame that fails the checksum.
*
* Is the datagram acceptable?
*
* 1. Length at least the size of an ip header
* 2. Version of 4
* 3. Checksums correctly. [Speed optimisation for later, skip loopback checksums]
* 4. Doesn't have a bogus length
*/
if (iph->ihl < 5 || iph->version != 4)
goto inhdr_error;
BUILD_BUG_ON(IPSTATS_MIB_ECT1PKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_ECT_1);
BUILD_BUG_ON(IPSTATS_MIB_ECT0PKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_ECT_0);
BUILD_BUG_ON(IPSTATS_MIB_CEPKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_CE);
__IP_ADD_STATS(net,
IPSTATS_MIB_NOECTPKTS + (iph->tos & INET_ECN_MASK),
max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
if (!pskb_may_pull(skb, iph->ihl*4))
goto inhdr_error;
iph = ip_hdr(skb);
if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
goto csum_error;
len = ntohs(iph->tot_len);
if (skb->len < len) {
__IP_INC_STATS(net, IPSTATS_MIB_INTRUNCATEDPKTS);
goto drop;
} else if (len < (iph->ihl*4))
goto inhdr_error;
/* Our transport medium may have padded the buffer out. Now we know it
* is IP we can trim to the true length of the frame.
* Note this now means skb->len holds ntohs(iph->tot_len).
*/
if (pskb_trim_rcsum(skb, len)) {
__IP_INC_STATS(net, IPSTATS_MIB_INDISCARDS);
goto drop;
}
iph = ip_hdr(skb);
skb->transport_header = skb->network_header + iph->ihl*4;
/* Remove any debris in the socket control block */
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
IPCB(skb)->iif = skb->skb_iif;
/* Must drop socket now because of tproxy. */
skb_orphan(skb);
return skb;
csum_error:
__IP_INC_STATS(net, IPSTATS_MIB_CSUMERRORS);
inhdr_error:
__IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS);
drop:
kfree_skb(skb);
out:
return NULL;
}
/*
* IP receive entry point
*/
int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
struct net_device *orig_dev)
{
struct net *net = dev_net(dev);
skb = ip_rcv_core(skb, net);
if (skb == NULL)
return NET_RX_DROP;
return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
net, NULL, skb, dev, NULL,
ip_rcv_finish);
}
static void ip_sublist_rcv_finish(struct list_head *head)
{
struct sk_buff *skb, *next;
list_for_each_entry_safe(skb, next, head, list) {
list_del(&skb->list);
/* Handle ip{6}_forward case, as sch_direct_xmit have
* another kind of SKB-list usage (see validate_xmit_skb_list)
*/
skb->next = NULL;
dst_input(skb);
}
}
static void ip_list_rcv_finish(struct net *net, struct sock *sk,
struct list_head *head)
{
struct dst_entry *curr_dst = NULL;
struct sk_buff *skb, *next;
struct list_head sublist;
INIT_LIST_HEAD(&sublist);
list_for_each_entry_safe(skb, next, head, list) {
struct net_device *dev = skb->dev;
struct dst_entry *dst;
skb_list_del_init(skb);
/* if ingress device is enslaved to an L3 master device pass the
* skb to its handler for processing
*/
skb = l3mdev_ip_rcv(skb);
if (!skb)
continue;
if (ip_rcv_finish_core(net, sk, skb, dev) == NET_RX_DROP)
continue;
dst = skb_dst(skb);
if (curr_dst != dst) {
/* dispatch old sublist */
if (!list_empty(&sublist))
ip_sublist_rcv_finish(&sublist);
/* start new sublist */
INIT_LIST_HEAD(&sublist);
curr_dst = dst;
}
list_add_tail(&skb->list, &sublist);
}
/* dispatch final sublist */
ip_sublist_rcv_finish(&sublist);
}
static void ip_sublist_rcv(struct list_head *head, struct net_device *dev,
struct net *net)
{
NF_HOOK_LIST(NFPROTO_IPV4, NF_INET_PRE_ROUTING, net, NULL,
head, dev, NULL, ip_rcv_finish);
ip_list_rcv_finish(net, NULL, head);
}
/* Receive a list of IP packets */
void ip_list_rcv(struct list_head *head, struct packet_type *pt,
struct net_device *orig_dev)
{
struct net_device *curr_dev = NULL;
struct net *curr_net = NULL;
struct sk_buff *skb, *next;
struct list_head sublist;
INIT_LIST_HEAD(&sublist);
list_for_each_entry_safe(skb, next, head, list) {
struct net_device *dev = skb->dev;
struct net *net = dev_net(dev);
skb_list_del_init(skb);
skb = ip_rcv_core(skb, net);
if (skb == NULL)
continue;
if (curr_dev != dev || curr_net != net) {
/* dispatch old sublist */
if (!list_empty(&sublist))
ip_sublist_rcv(&sublist, curr_dev, curr_net);
/* start new sublist */
INIT_LIST_HEAD(&sublist);
curr_dev = dev;
curr_net = net;
}
list_add_tail(&skb->list, &sublist);
}
/* dispatch final sublist */
ip_sublist_rcv(&sublist, curr_dev, curr_net);
}
+671
View File
@@ -0,0 +1,671 @@
// SPDX-License-Identifier: GPL-2.0
/*
* 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.
*
* The options processing module for ip.c
*
* Authors: A.N.Kuznetsov
*
*/
#define pr_fmt(fmt) "IPv4: " fmt
#include <linux/capability.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/uaccess.h>
#include <asm/unaligned.h>
#include <linux/skbuff.h>
#include <linux/ip.h>
#include <linux/icmp.h>
#include <linux/netdevice.h>
#include <linux/rtnetlink.h>
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/route.h>
#include <net/cipso_ipv4.h>
#include <net/ip_fib.h>
/*
* Write options to IP header, record destination address to
* source route option, address of outgoing interface
* (we should already know it, so that this function is allowed be
* called only after routing decision) and timestamp,
* if we originate this datagram.
*
* daddr is real destination address, next hop is recorded in IP header.
* saddr is address of outgoing interface.
*/
void ip_options_build(struct sk_buff *skb, struct ip_options *opt,
__be32 daddr, struct rtable *rt, int is_frag)
{
unsigned char *iph = skb_network_header(skb);
memcpy(&(IPCB(skb)->opt), opt, sizeof(struct ip_options));
memcpy(iph+sizeof(struct iphdr), opt->__data, opt->optlen);
opt = &(IPCB(skb)->opt);
if (opt->srr)
memcpy(iph+opt->srr+iph[opt->srr+1]-4, &daddr, 4);
if (!is_frag) {
if (opt->rr_needaddr)
ip_rt_get_source(iph+opt->rr+iph[opt->rr+2]-5, skb, rt);
if (opt->ts_needaddr)
ip_rt_get_source(iph+opt->ts+iph[opt->ts+2]-9, skb, rt);
if (opt->ts_needtime) {
__be32 midtime;
midtime = inet_current_timestamp();
memcpy(iph+opt->ts+iph[opt->ts+2]-5, &midtime, 4);
}
return;
}
if (opt->rr) {
memset(iph+opt->rr, IPOPT_NOP, iph[opt->rr+1]);
opt->rr = 0;
opt->rr_needaddr = 0;
}
if (opt->ts) {
memset(iph+opt->ts, IPOPT_NOP, iph[opt->ts+1]);
opt->ts = 0;
opt->ts_needaddr = opt->ts_needtime = 0;
}
}
/*
* Provided (sopt, skb) points to received options,
* build in dopt compiled option set appropriate for answering.
* i.e. invert SRR option, copy anothers,
* and grab room in RR/TS options.
*
* NOTE: dopt cannot point to skb.
*/
int __ip_options_echo(struct net *net, struct ip_options *dopt,
struct sk_buff *skb, const struct ip_options *sopt)
{
unsigned char *sptr, *dptr;
int soffset, doffset;
int optlen;
memset(dopt, 0, sizeof(struct ip_options));
if (sopt->optlen == 0)
return 0;
sptr = skb_network_header(skb);
dptr = dopt->__data;
if (sopt->rr) {
optlen = sptr[sopt->rr+1];
soffset = sptr[sopt->rr+2];
dopt->rr = dopt->optlen + sizeof(struct iphdr);
memcpy(dptr, sptr+sopt->rr, optlen);
if (sopt->rr_needaddr && soffset <= optlen) {
if (soffset + 3 > optlen)
return -EINVAL;
dptr[2] = soffset + 4;
dopt->rr_needaddr = 1;
}
dptr += optlen;
dopt->optlen += optlen;
}
if (sopt->ts) {
optlen = sptr[sopt->ts+1];
soffset = sptr[sopt->ts+2];
dopt->ts = dopt->optlen + sizeof(struct iphdr);
memcpy(dptr, sptr+sopt->ts, optlen);
if (soffset <= optlen) {
if (sopt->ts_needaddr) {
if (soffset + 3 > optlen)
return -EINVAL;
dopt->ts_needaddr = 1;
soffset += 4;
}
if (sopt->ts_needtime) {
if (soffset + 3 > optlen)
return -EINVAL;
if ((dptr[3]&0xF) != IPOPT_TS_PRESPEC) {
dopt->ts_needtime = 1;
soffset += 4;
} else {
dopt->ts_needtime = 0;
if (soffset + 7 <= optlen) {
__be32 addr;
memcpy(&addr, dptr+soffset-1, 4);
if (inet_addr_type(net, addr) != RTN_UNICAST) {
dopt->ts_needtime = 1;
soffset += 8;
}
}
}
}
dptr[2] = soffset;
}
dptr += optlen;
dopt->optlen += optlen;
}
if (sopt->srr) {
unsigned char *start = sptr+sopt->srr;
__be32 faddr;
optlen = start[1];
soffset = start[2];
doffset = 0;
if (soffset > optlen)
soffset = optlen + 1;
soffset -= 4;
if (soffset > 3) {
memcpy(&faddr, &start[soffset-1], 4);
for (soffset -= 4, doffset = 4; soffset > 3; soffset -= 4, doffset += 4)
memcpy(&dptr[doffset-1], &start[soffset-1], 4);
/*
* RFC1812 requires to fix illegal source routes.
*/
if (memcmp(&ip_hdr(skb)->saddr,
&start[soffset + 3], 4) == 0)
doffset -= 4;
}
if (doffset > 3) {
dopt->faddr = faddr;
dptr[0] = start[0];
dptr[1] = doffset+3;
dptr[2] = 4;
dptr += doffset+3;
dopt->srr = dopt->optlen + sizeof(struct iphdr);
dopt->optlen += doffset+3;
dopt->is_strictroute = sopt->is_strictroute;
}
}
if (sopt->cipso) {
optlen = sptr[sopt->cipso+1];
dopt->cipso = dopt->optlen+sizeof(struct iphdr);
memcpy(dptr, sptr+sopt->cipso, optlen);
dptr += optlen;
dopt->optlen += optlen;
}
while (dopt->optlen & 3) {
*dptr++ = IPOPT_END;
dopt->optlen++;
}
return 0;
}
/*
* Options "fragmenting", just fill options not
* allowed in fragments with NOOPs.
* Simple and stupid 8), but the most efficient way.
*/
void ip_options_fragment(struct sk_buff *skb)
{
unsigned char *optptr = skb_network_header(skb) + sizeof(struct iphdr);
struct ip_options *opt = &(IPCB(skb)->opt);
int l = opt->optlen;
int optlen;
while (l > 0) {
switch (*optptr) {
case IPOPT_END:
return;
case IPOPT_NOOP:
l--;
optptr++;
continue;
}
optlen = optptr[1];
if (optlen < 2 || optlen > l)
return;
if (!IPOPT_COPIED(*optptr))
memset(optptr, IPOPT_NOOP, optlen);
l -= optlen;
optptr += optlen;
}
opt->ts = 0;
opt->rr = 0;
opt->rr_needaddr = 0;
opt->ts_needaddr = 0;
opt->ts_needtime = 0;
}
/* helper used by ip_options_compile() to call fib_compute_spec_dst()
* at most one time.
*/
static void spec_dst_fill(__be32 *spec_dst, struct sk_buff *skb)
{
if (*spec_dst == htonl(INADDR_ANY))
*spec_dst = fib_compute_spec_dst(skb);
}
/*
* Verify options and fill pointers in struct options.
* Caller should clear *opt, and set opt->data.
* If opt == NULL, then skb->data should point to IP header.
*/
int __ip_options_compile(struct net *net,
struct ip_options *opt, struct sk_buff *skb,
__be32 *info)
{
__be32 spec_dst = htonl(INADDR_ANY);
unsigned char *pp_ptr = NULL;
struct rtable *rt = NULL;
unsigned char *optptr;
unsigned char *iph;
int optlen, l;
if (skb) {
rt = skb_rtable(skb);
optptr = (unsigned char *)&(ip_hdr(skb)[1]);
} else
optptr = opt->__data;
iph = optptr - sizeof(struct iphdr);
for (l = opt->optlen; l > 0; ) {
switch (*optptr) {
case IPOPT_END:
for (optptr++, l--; l > 0; optptr++, l--) {
if (*optptr != IPOPT_END) {
*optptr = IPOPT_END;
opt->is_changed = 1;
}
}
goto eol;
case IPOPT_NOOP:
l--;
optptr++;
continue;
}
if (unlikely(l < 2)) {
pp_ptr = optptr;
goto error;
}
optlen = optptr[1];
if (optlen < 2 || optlen > l) {
pp_ptr = optptr;
goto error;
}
switch (*optptr) {
case IPOPT_SSRR:
case IPOPT_LSRR:
if (optlen < 3) {
pp_ptr = optptr + 1;
goto error;
}
if (optptr[2] < 4) {
pp_ptr = optptr + 2;
goto error;
}
/* NB: cf RFC-1812 5.2.4.1 */
if (opt->srr) {
pp_ptr = optptr;
goto error;
}
if (!skb) {
if (optptr[2] != 4 || optlen < 7 || ((optlen-3) & 3)) {
pp_ptr = optptr + 1;
goto error;
}
memcpy(&opt->faddr, &optptr[3], 4);
if (optlen > 7)
memmove(&optptr[3], &optptr[7], optlen-7);
}
opt->is_strictroute = (optptr[0] == IPOPT_SSRR);
opt->srr = optptr - iph;
break;
case IPOPT_RR:
if (opt->rr) {
pp_ptr = optptr;
goto error;
}
if (optlen < 3) {
pp_ptr = optptr + 1;
goto error;
}
if (optptr[2] < 4) {
pp_ptr = optptr + 2;
goto error;
}
if (optptr[2] <= optlen) {
if (optptr[2]+3 > optlen) {
pp_ptr = optptr + 2;
goto error;
}
if (rt) {
spec_dst_fill(&spec_dst, skb);
memcpy(&optptr[optptr[2]-1], &spec_dst, 4);
opt->is_changed = 1;
}
optptr[2] += 4;
opt->rr_needaddr = 1;
}
opt->rr = optptr - iph;
break;
case IPOPT_TIMESTAMP:
if (opt->ts) {
pp_ptr = optptr;
goto error;
}
if (optlen < 4) {
pp_ptr = optptr + 1;
goto error;
}
if (optptr[2] < 5) {
pp_ptr = optptr + 2;
goto error;
}
if (optptr[2] <= optlen) {
unsigned char *timeptr = NULL;
if (optptr[2]+3 > optlen) {
pp_ptr = optptr + 2;
goto error;
}
switch (optptr[3]&0xF) {
case IPOPT_TS_TSONLY:
if (skb)
timeptr = &optptr[optptr[2]-1];
opt->ts_needtime = 1;
optptr[2] += 4;
break;
case IPOPT_TS_TSANDADDR:
if (optptr[2]+7 > optlen) {
pp_ptr = optptr + 2;
goto error;
}
if (rt) {
spec_dst_fill(&spec_dst, skb);
memcpy(&optptr[optptr[2]-1], &spec_dst, 4);
timeptr = &optptr[optptr[2]+3];
}
opt->ts_needaddr = 1;
opt->ts_needtime = 1;
optptr[2] += 8;
break;
case IPOPT_TS_PRESPEC:
if (optptr[2]+7 > optlen) {
pp_ptr = optptr + 2;
goto error;
}
{
__be32 addr;
memcpy(&addr, &optptr[optptr[2]-1], 4);
if (inet_addr_type(net, addr) == RTN_UNICAST)
break;
if (skb)
timeptr = &optptr[optptr[2]+3];
}
opt->ts_needtime = 1;
optptr[2] += 8;
break;
default:
if (!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) {
pp_ptr = optptr + 3;
goto error;
}
break;
}
if (timeptr) {
__be32 midtime;
midtime = inet_current_timestamp();
memcpy(timeptr, &midtime, 4);
opt->is_changed = 1;
}
} else if ((optptr[3]&0xF) != IPOPT_TS_PRESPEC) {
unsigned int overflow = optptr[3]>>4;
if (overflow == 15) {
pp_ptr = optptr + 3;
goto error;
}
if (skb) {
optptr[3] = (optptr[3]&0xF)|((overflow+1)<<4);
opt->is_changed = 1;
}
}
opt->ts = optptr - iph;
break;
case IPOPT_RA:
if (optlen < 4) {
pp_ptr = optptr + 1;
goto error;
}
if (optptr[2] == 0 && optptr[3] == 0)
opt->router_alert = optptr - iph;
break;
case IPOPT_CIPSO:
if ((!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) || opt->cipso) {
pp_ptr = optptr;
goto error;
}
opt->cipso = optptr - iph;
if (cipso_v4_validate(skb, &optptr)) {
pp_ptr = optptr;
goto error;
}
break;
case IPOPT_SEC:
case IPOPT_SID:
default:
if (!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) {
pp_ptr = optptr;
goto error;
}
break;
}
l -= optlen;
optptr += optlen;
}
eol:
if (!pp_ptr)
return 0;
error:
if (info)
*info = htonl((pp_ptr-iph)<<24);
return -EINVAL;
}
int ip_options_compile(struct net *net,
struct ip_options *opt, struct sk_buff *skb)
{
int ret;
__be32 info;
ret = __ip_options_compile(net, opt, skb, &info);
if (ret != 0 && skb)
icmp_send(skb, ICMP_PARAMETERPROB, 0, info);
return ret;
}
EXPORT_SYMBOL(ip_options_compile);
/*
* Undo all the changes done by ip_options_compile().
*/
void ip_options_undo(struct ip_options *opt)
{
if (opt->srr) {
unsigned char *optptr = opt->__data+opt->srr-sizeof(struct iphdr);
memmove(optptr+7, optptr+3, optptr[1]-7);
memcpy(optptr+3, &opt->faddr, 4);
}
if (opt->rr_needaddr) {
unsigned char *optptr = opt->__data+opt->rr-sizeof(struct iphdr);
optptr[2] -= 4;
memset(&optptr[optptr[2]-1], 0, 4);
}
if (opt->ts) {
unsigned char *optptr = opt->__data+opt->ts-sizeof(struct iphdr);
if (opt->ts_needtime) {
optptr[2] -= 4;
memset(&optptr[optptr[2]-1], 0, 4);
if ((optptr[3]&0xF) == IPOPT_TS_PRESPEC)
optptr[2] -= 4;
}
if (opt->ts_needaddr) {
optptr[2] -= 4;
memset(&optptr[optptr[2]-1], 0, 4);
}
}
}
static struct ip_options_rcu *ip_options_get_alloc(const int optlen)
{
return kzalloc(sizeof(struct ip_options_rcu) + ((optlen + 3) & ~3),
GFP_KERNEL);
}
static int ip_options_get_finish(struct net *net, struct ip_options_rcu **optp,
struct ip_options_rcu *opt, int optlen)
{
while (optlen & 3)
opt->opt.__data[optlen++] = IPOPT_END;
opt->opt.optlen = optlen;
if (optlen && ip_options_compile(net, &opt->opt, NULL)) {
kfree(opt);
return -EINVAL;
}
kfree(*optp);
*optp = opt;
return 0;
}
int ip_options_get_from_user(struct net *net, struct ip_options_rcu **optp,
unsigned char __user *data, int optlen)
{
struct ip_options_rcu *opt = ip_options_get_alloc(optlen);
if (!opt)
return -ENOMEM;
if (optlen && copy_from_user(opt->opt.__data, data, optlen)) {
kfree(opt);
return -EFAULT;
}
return ip_options_get_finish(net, optp, opt, optlen);
}
int ip_options_get(struct net *net, struct ip_options_rcu **optp,
unsigned char *data, int optlen)
{
struct ip_options_rcu *opt = ip_options_get_alloc(optlen);
if (!opt)
return -ENOMEM;
if (optlen)
memcpy(opt->opt.__data, data, optlen);
return ip_options_get_finish(net, optp, opt, optlen);
}
void ip_forward_options(struct sk_buff *skb)
{
struct ip_options *opt = &(IPCB(skb)->opt);
unsigned char *optptr;
struct rtable *rt = skb_rtable(skb);
unsigned char *raw = skb_network_header(skb);
if (opt->rr_needaddr) {
optptr = (unsigned char *)raw + opt->rr;
ip_rt_get_source(&optptr[optptr[2]-5], skb, rt);
opt->is_changed = 1;
}
if (opt->srr_is_hit) {
int srrptr, srrspace;
optptr = raw + opt->srr;
for ( srrptr = optptr[2], srrspace = optptr[1];
srrptr <= srrspace;
srrptr += 4
) {
if (srrptr + 3 > srrspace)
break;
if (memcmp(&opt->nexthop, &optptr[srrptr-1], 4) == 0)
break;
}
if (srrptr + 3 <= srrspace) {
opt->is_changed = 1;
ip_hdr(skb)->daddr = opt->nexthop;
ip_rt_get_source(&optptr[srrptr-1], skb, rt);
optptr[2] = srrptr+4;
} else {
net_crit_ratelimited("%s(): Argh! Destination lost!\n",
__func__);
}
if (opt->ts_needaddr) {
optptr = raw + opt->ts;
ip_rt_get_source(&optptr[optptr[2]-9], skb, rt);
opt->is_changed = 1;
}
}
if (opt->is_changed) {
opt->is_changed = 0;
ip_send_check(ip_hdr(skb));
}
}
int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev)
{
struct ip_options *opt = &(IPCB(skb)->opt);
int srrspace, srrptr;
__be32 nexthop;
struct iphdr *iph = ip_hdr(skb);
unsigned char *optptr = skb_network_header(skb) + opt->srr;
struct rtable *rt = skb_rtable(skb);
struct rtable *rt2;
unsigned long orefdst;
int err;
if (!rt)
return 0;
if (skb->pkt_type != PACKET_HOST)
return -EINVAL;
if (rt->rt_type == RTN_UNICAST) {
if (!opt->is_strictroute)
return 0;
icmp_send(skb, ICMP_PARAMETERPROB, 0, htonl(16<<24));
return -EINVAL;
}
if (rt->rt_type != RTN_LOCAL)
return -EINVAL;
for (srrptr = optptr[2], srrspace = optptr[1]; srrptr <= srrspace; srrptr += 4) {
if (srrptr + 3 > srrspace) {
icmp_send(skb, ICMP_PARAMETERPROB, 0, htonl((opt->srr+2)<<24));
return -EINVAL;
}
memcpy(&nexthop, &optptr[srrptr-1], 4);
orefdst = skb->_skb_refdst;
skb_dst_set(skb, NULL);
err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, dev);
rt2 = skb_rtable(skb);
if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) {
skb_dst_drop(skb);
skb->_skb_refdst = orefdst;
return -EINVAL;
}
refdst_drop(orefdst);
if (rt2->rt_type != RTN_LOCAL)
break;
/* Superfast 8) loopback forward */
iph->daddr = nexthop;
opt->is_changed = 1;
}
if (srrptr <= srrspace) {
opt->srr_is_hit = 1;
opt->nexthop = nexthop;
opt->is_changed = 1;
}
return 0;
}
EXPORT_SYMBOL(ip_options_rcv_srr);
+1617
View File
File diff suppressed because it is too large. Load diff
File diff suppressed because it is too large. Load diff
+1231
View File
File diff suppressed because it is too large. Load diff
+457
View File
@@ -0,0 +1,457 @@
/*
* Copyright (c) 2013 Nicira, Inc.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
* 02110-1301, USA
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/in.h>
#include <linux/if_arp.h>
#include <linux/init.h>
#include <linux/in6.h>
#include <linux/inetdevice.h>
#include <linux/netfilter_ipv4.h>
#include <linux/etherdevice.h>
#include <linux/if_ether.h>
#include <linux/if_vlan.h>
#include <linux/static_key.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/ip_tunnels.h>
#include <net/ip6_tunnel.h>
#include <net/arp.h>
#include <net/checksum.h>
#include <net/dsfield.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/rtnetlink.h>
#include <net/dst_metadata.h>
const struct ip_tunnel_encap_ops __rcu *
iptun_encaps[MAX_IPTUN_ENCAP_OPS] __read_mostly;
EXPORT_SYMBOL(iptun_encaps);
const struct ip6_tnl_encap_ops __rcu *
ip6tun_encaps[MAX_IPTUN_ENCAP_OPS] __read_mostly;
EXPORT_SYMBOL(ip6tun_encaps);
void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
__be32 src, __be32 dst, __u8 proto,
__u8 tos, __u8 ttl, __be16 df, bool xnet)
{
int pkt_len = skb->len - skb_inner_network_offset(skb);
struct net *net = dev_net(rt->dst.dev);
struct net_device *dev = skb->dev;
struct iphdr *iph;
int err;
skb_scrub_packet(skb, xnet);
skb_clear_hash_if_not_l4(skb);
skb_dst_set(skb, &rt->dst);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
/* Push down and install the IP header. */
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = ip_mtu_locked(&rt->dst) ? 0 : df;
iph->protocol = proto;
iph->tos = tos;
iph->daddr = dst;
iph->saddr = src;
iph->ttl = ttl;
__ip_select_ident(net, iph, skb_shinfo(skb)->gso_segs ?: 1);
err = ip_local_out(net, sk, skb);
if (dev) {
if (unlikely(net_xmit_eval(err)))
pkt_len = 0;
iptunnel_xmit_stats(dev, pkt_len);
}
}
EXPORT_SYMBOL_GPL(iptunnel_xmit);
int __iptunnel_pull_header(struct sk_buff *skb, int hdr_len,
__be16 inner_proto, bool raw_proto, bool xnet)
{
if (unlikely(!pskb_may_pull(skb, hdr_len)))
return -ENOMEM;
skb_pull_rcsum(skb, hdr_len);
if (!raw_proto && inner_proto == htons(ETH_P_TEB)) {
struct ethhdr *eh;
if (unlikely(!pskb_may_pull(skb, ETH_HLEN)))
return -ENOMEM;
eh = (struct ethhdr *)skb->data;
if (likely(eth_proto_is_802_3(eh->h_proto)))
skb->protocol = eh->h_proto;
else
skb->protocol = htons(ETH_P_802_2);
} else {
skb->protocol = inner_proto;
}
skb_clear_hash_if_not_l4(skb);
skb->vlan_tci = 0;
skb_set_queue_mapping(skb, 0);
skb_scrub_packet(skb, xnet);
return iptunnel_pull_offloads(skb);
}
EXPORT_SYMBOL_GPL(__iptunnel_pull_header);
struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
gfp_t flags)
{
struct metadata_dst *res;
struct ip_tunnel_info *dst, *src;
if (!md || md->type != METADATA_IP_TUNNEL ||
md->u.tun_info.mode & IP_TUNNEL_INFO_TX)
return NULL;
res = metadata_dst_alloc(0, METADATA_IP_TUNNEL, flags);
if (!res)
return NULL;
dst = &res->u.tun_info;
src = &md->u.tun_info;
dst->key.tun_id = src->key.tun_id;
if (src->mode & IP_TUNNEL_INFO_IPV6)
memcpy(&dst->key.u.ipv6.dst, &src->key.u.ipv6.src,
sizeof(struct in6_addr));
else
dst->key.u.ipv4.dst = src->key.u.ipv4.src;
dst->mode = src->mode | IP_TUNNEL_INFO_TX;
return res;
}
EXPORT_SYMBOL_GPL(iptunnel_metadata_reply);
int iptunnel_handle_offloads(struct sk_buff *skb,
int gso_type_mask)
{
int err;
if (likely(!skb->encapsulation)) {
skb_reset_inner_headers(skb);
skb->encapsulation = 1;
}
if (skb_is_gso(skb)) {
err = skb_header_unclone(skb, GFP_ATOMIC);
if (unlikely(err))
return err;
skb_shinfo(skb)->gso_type |= gso_type_mask;
return 0;
}
if (skb->ip_summed != CHECKSUM_PARTIAL) {
skb->ip_summed = CHECKSUM_NONE;
/* We clear encapsulation here to prevent badly-written
* drivers potentially deciding to offload an inner checksum
* if we set CHECKSUM_PARTIAL on the outer header.
* This should go away when the drivers are all fixed.
*/
skb->encapsulation = 0;
}
return 0;
}
EXPORT_SYMBOL_GPL(iptunnel_handle_offloads);
/* Often modified stats are per cpu, other are shared (netdev->stats) */
void ip_tunnel_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *tot)
{
int i;
netdev_stats_to_stats64(tot, &dev->stats);
for_each_possible_cpu(i) {
const struct pcpu_sw_netstats *tstats =
per_cpu_ptr(dev->tstats, i);
u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
unsigned int start;
do {
start = u64_stats_fetch_begin_irq(&tstats->syncp);
rx_packets = tstats->rx_packets;
tx_packets = tstats->tx_packets;
rx_bytes = tstats->rx_bytes;
tx_bytes = tstats->tx_bytes;
} while (u64_stats_fetch_retry_irq(&tstats->syncp, start));
tot->rx_packets += rx_packets;
tot->tx_packets += tx_packets;
tot->rx_bytes += rx_bytes;
tot->tx_bytes += tx_bytes;
}
}
EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = {
[LWTUNNEL_IP_ID] = { .type = NLA_U64 },
[LWTUNNEL_IP_DST] = { .type = NLA_U32 },
[LWTUNNEL_IP_SRC] = { .type = NLA_U32 },
[LWTUNNEL_IP_TTL] = { .type = NLA_U8 },
[LWTUNNEL_IP_TOS] = { .type = NLA_U8 },
[LWTUNNEL_IP_FLAGS] = { .type = NLA_U16 },
};
static int ip_tun_build_state(struct nlattr *attr,
unsigned int family, const void *cfg,
struct lwtunnel_state **ts,
struct netlink_ext_ack *extack)
{
struct ip_tunnel_info *tun_info;
struct lwtunnel_state *new_state;
struct nlattr *tb[LWTUNNEL_IP_MAX + 1];
int err;
err = nla_parse_nested(tb, LWTUNNEL_IP_MAX, attr, ip_tun_policy,
extack);
if (err < 0)
return err;
new_state = lwtunnel_state_alloc(sizeof(*tun_info));
if (!new_state)
return -ENOMEM;
new_state->type = LWTUNNEL_ENCAP_IP;
tun_info = lwt_tun_info(new_state);
if (tb[LWTUNNEL_IP_ID])
tun_info->key.tun_id = nla_get_be64(tb[LWTUNNEL_IP_ID]);
if (tb[LWTUNNEL_IP_DST])
tun_info->key.u.ipv4.dst = nla_get_in_addr(tb[LWTUNNEL_IP_DST]);
if (tb[LWTUNNEL_IP_SRC])
tun_info->key.u.ipv4.src = nla_get_in_addr(tb[LWTUNNEL_IP_SRC]);
if (tb[LWTUNNEL_IP_TTL])
tun_info->key.ttl = nla_get_u8(tb[LWTUNNEL_IP_TTL]);
if (tb[LWTUNNEL_IP_TOS])
tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP_TOS]);
if (tb[LWTUNNEL_IP_FLAGS])
tun_info->key.tun_flags = nla_get_be16(tb[LWTUNNEL_IP_FLAGS]);
tun_info->mode = IP_TUNNEL_INFO_TX;
tun_info->options_len = 0;
*ts = new_state;
return 0;
}
static int ip_tun_fill_encap_info(struct sk_buff *skb,
struct lwtunnel_state *lwtstate)
{
struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate);
if (nla_put_be64(skb, LWTUNNEL_IP_ID, tun_info->key.tun_id,
LWTUNNEL_IP_PAD) ||
nla_put_in_addr(skb, LWTUNNEL_IP_DST, tun_info->key.u.ipv4.dst) ||
nla_put_in_addr(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) ||
nla_put_u8(skb, LWTUNNEL_IP_TOS, tun_info->key.tos) ||
nla_put_u8(skb, LWTUNNEL_IP_TTL, tun_info->key.ttl) ||
nla_put_be16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags))
return -ENOMEM;
return 0;
}
static int ip_tun_encap_nlsize(struct lwtunnel_state *lwtstate)
{
return nla_total_size_64bit(8) /* LWTUNNEL_IP_ID */
+ nla_total_size(4) /* LWTUNNEL_IP_DST */
+ nla_total_size(4) /* LWTUNNEL_IP_SRC */
+ nla_total_size(1) /* LWTUNNEL_IP_TOS */
+ nla_total_size(1) /* LWTUNNEL_IP_TTL */
+ nla_total_size(2); /* LWTUNNEL_IP_FLAGS */
}
static int ip_tun_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b)
{
return memcmp(lwt_tun_info(a), lwt_tun_info(b),
sizeof(struct ip_tunnel_info));
}
static const struct lwtunnel_encap_ops ip_tun_lwt_ops = {
.build_state = ip_tun_build_state,
.fill_encap = ip_tun_fill_encap_info,
.get_encap_size = ip_tun_encap_nlsize,
.cmp_encap = ip_tun_cmp_encap,
.owner = THIS_MODULE,
};
static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = {
[LWTUNNEL_IP6_ID] = { .type = NLA_U64 },
[LWTUNNEL_IP6_DST] = { .len = sizeof(struct in6_addr) },
[LWTUNNEL_IP6_SRC] = { .len = sizeof(struct in6_addr) },
[LWTUNNEL_IP6_HOPLIMIT] = { .type = NLA_U8 },
[LWTUNNEL_IP6_TC] = { .type = NLA_U8 },
[LWTUNNEL_IP6_FLAGS] = { .type = NLA_U16 },
};
static int ip6_tun_build_state(struct nlattr *attr,
unsigned int family, const void *cfg,
struct lwtunnel_state **ts,
struct netlink_ext_ack *extack)
{
struct ip_tunnel_info *tun_info;
struct lwtunnel_state *new_state;
struct nlattr *tb[LWTUNNEL_IP6_MAX + 1];
int err;
err = nla_parse_nested(tb, LWTUNNEL_IP6_MAX, attr, ip6_tun_policy,
extack);
if (err < 0)
return err;
new_state = lwtunnel_state_alloc(sizeof(*tun_info));
if (!new_state)
return -ENOMEM;
new_state->type = LWTUNNEL_ENCAP_IP6;
tun_info = lwt_tun_info(new_state);
if (tb[LWTUNNEL_IP6_ID])
tun_info->key.tun_id = nla_get_be64(tb[LWTUNNEL_IP6_ID]);
if (tb[LWTUNNEL_IP6_DST])
tun_info->key.u.ipv6.dst = nla_get_in6_addr(tb[LWTUNNEL_IP6_DST]);
if (tb[LWTUNNEL_IP6_SRC])
tun_info->key.u.ipv6.src = nla_get_in6_addr(tb[LWTUNNEL_IP6_SRC]);
if (tb[LWTUNNEL_IP6_HOPLIMIT])
tun_info->key.ttl = nla_get_u8(tb[LWTUNNEL_IP6_HOPLIMIT]);
if (tb[LWTUNNEL_IP6_TC])
tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP6_TC]);
if (tb[LWTUNNEL_IP6_FLAGS])
tun_info->key.tun_flags = nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]);
tun_info->mode = IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_IPV6;
tun_info->options_len = 0;
*ts = new_state;
return 0;
}
static int ip6_tun_fill_encap_info(struct sk_buff *skb,
struct lwtunnel_state *lwtstate)
{
struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate);
if (nla_put_be64(skb, LWTUNNEL_IP6_ID, tun_info->key.tun_id,
LWTUNNEL_IP6_PAD) ||
nla_put_in6_addr(skb, LWTUNNEL_IP6_DST, &tun_info->key.u.ipv6.dst) ||
nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) ||
nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.tos) ||
nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.ttl) ||
nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags))
return -ENOMEM;
return 0;
}
static int ip6_tun_encap_nlsize(struct lwtunnel_state *lwtstate)
{
return nla_total_size_64bit(8) /* LWTUNNEL_IP6_ID */
+ nla_total_size(16) /* LWTUNNEL_IP6_DST */
+ nla_total_size(16) /* LWTUNNEL_IP6_SRC */
+ nla_total_size(1) /* LWTUNNEL_IP6_HOPLIMIT */
+ nla_total_size(1) /* LWTUNNEL_IP6_TC */
+ nla_total_size(2); /* LWTUNNEL_IP6_FLAGS */
}
static const struct lwtunnel_encap_ops ip6_tun_lwt_ops = {
.build_state = ip6_tun_build_state,
.fill_encap = ip6_tun_fill_encap_info,
.get_encap_size = ip6_tun_encap_nlsize,
.cmp_encap = ip_tun_cmp_encap,
.owner = THIS_MODULE,
};
void __init ip_tunnel_core_init(void)
{
/* If you land here, make sure whether increasing ip_tunnel_info's
* options_len is a reasonable choice with its usage in front ends
* (f.e., it's part of flow keys, etc).
*/
BUILD_BUG_ON(IP_TUNNEL_OPTS_MAX != 255);
lwtunnel_encap_add_ops(&ip_tun_lwt_ops, LWTUNNEL_ENCAP_IP);
lwtunnel_encap_add_ops(&ip6_tun_lwt_ops, LWTUNNEL_ENCAP_IP6);
}
DEFINE_STATIC_KEY_FALSE(ip_tunnel_metadata_cnt);
EXPORT_SYMBOL(ip_tunnel_metadata_cnt);
void ip_tunnel_need_metadata(void)
{
static_branch_inc(&ip_tunnel_metadata_cnt);
}
EXPORT_SYMBOL_GPL(ip_tunnel_need_metadata);
void ip_tunnel_unneed_metadata(void)
{
static_branch_dec(&ip_tunnel_metadata_cnt);
}
EXPORT_SYMBOL_GPL(ip_tunnel_unneed_metadata);
/* Returns either the correct skb->protocol value, or 0 if invalid. */
__be16 ip_tunnel_parse_protocol(const struct sk_buff *skb)
{
if (skb_network_header(skb) >= skb->head &&
(skb_network_header(skb) + sizeof(struct iphdr)) <= skb_tail_pointer(skb) &&
ip_hdr(skb)->version == 4)
return htons(ETH_P_IP);
if (skb_network_header(skb) >= skb->head &&
(skb_network_header(skb) + sizeof(struct ipv6hdr)) <= skb_tail_pointer(skb) &&
ipv6_hdr(skb)->version == 6)
return htons(ETH_P_IPV6);
return 0;
}
EXPORT_SYMBOL(ip_tunnel_parse_protocol);
+724
View File
@@ -0,0 +1,724 @@
/*
* Linux NET3: IP/IP protocol decoder modified to support
* virtual tunnel interface
*
* Authors:
* Saurabh Mohan (saurabh.mohan@vyatta.com) 05/07/2012
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
*/
/*
This version of net/ipv4/ip_vti.c is cloned of net/ipv4/ipip.c
For comments look at net/ipv4/ip_gre.c --ANK
*/
#include <linux/capability.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/uaccess.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/in.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/if_arp.h>
#include <linux/init.h>
#include <linux/netfilter_ipv4.h>
#include <linux/if_ether.h>
#include <linux/icmpv6.h>
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/ip_tunnels.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
static struct rtnl_link_ops vti_link_ops __read_mostly;
static unsigned int vti_net_id __read_mostly;
static int vti_tunnel_init(struct net_device *dev);
static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi,
int encap_type, bool update_skb_dev)
{
struct ip_tunnel *tunnel;
const struct iphdr *iph = ip_hdr(skb);
struct net *net = dev_net(skb->dev);
struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
iph->saddr, iph->daddr, 0);
if (tunnel) {
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
if (update_skb_dev)
skb->dev = tunnel->dev;
return xfrm_input(skb, nexthdr, spi, encap_type);
}
return -EINVAL;
drop:
kfree_skb(skb);
return 0;
}
static int vti_input_proto(struct sk_buff *skb, int nexthdr, __be32 spi,
int encap_type)
{
return vti_input(skb, nexthdr, spi, encap_type, false);
}
static int vti_rcv(struct sk_buff *skb, __be32 spi, bool update_skb_dev)
{
XFRM_SPI_SKB_CB(skb)->family = AF_INET;
XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
return vti_input(skb, ip_hdr(skb)->protocol, spi, 0, update_skb_dev);
}
static int vti_rcv_proto(struct sk_buff *skb)
{
return vti_rcv(skb, 0, false);
}
static int vti_rcv_tunnel(struct sk_buff *skb)
{
struct ip_tunnel_net *itn = net_generic(dev_net(skb->dev), vti_net_id);
const struct iphdr *iph = ip_hdr(skb);
struct ip_tunnel *tunnel;
tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
iph->saddr, iph->daddr, 0);
if (tunnel) {
struct tnl_ptk_info tpi = {
.proto = htons(ETH_P_IP),
};
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
if (iptunnel_pull_header(skb, 0, tpi.proto, false))
goto drop;
return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, false);
}
return -EINVAL;
drop:
kfree_skb(skb);
return 0;
}
static int vti_rcv_cb(struct sk_buff *skb, int err)
{
unsigned short family;
struct net_device *dev;
struct pcpu_sw_netstats *tstats;
struct xfrm_state *x;
struct xfrm_mode *inner_mode;
struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4;
u32 orig_mark = skb->mark;
int ret;
if (!tunnel)
return 1;
dev = tunnel->dev;
if (err) {
dev->stats.rx_errors++;
dev->stats.rx_dropped++;
return 0;
}
x = xfrm_input_state(skb);
inner_mode = x->inner_mode;
if (x->sel.family == AF_UNSPEC) {
inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
if (inner_mode == NULL) {
XFRM_INC_STATS(dev_net(skb->dev),
LINUX_MIB_XFRMINSTATEMODEERROR);
return -EINVAL;
}
}
family = inner_mode->afinfo->family;
skb->mark = be32_to_cpu(tunnel->parms.i_key);
ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
skb->mark = orig_mark;
if (!ret)
return -EPERM;
skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev)));
skb->dev = dev;
tstats = this_cpu_ptr(dev->tstats);
u64_stats_update_begin(&tstats->syncp);
tstats->rx_packets++;
tstats->rx_bytes += skb->len;
u64_stats_update_end(&tstats->syncp);
return 0;
}
static bool vti_state_check(const struct xfrm_state *x, __be32 dst, __be32 src)
{
xfrm_address_t *daddr = (xfrm_address_t *)&dst;
xfrm_address_t *saddr = (xfrm_address_t *)&src;
/* if there is no transform then this tunnel is not functional.
* Or if the xfrm is not mode tunnel.
*/
if (!x || x->props.mode != XFRM_MODE_TUNNEL ||
x->props.family != AF_INET)
return false;
if (!dst)
return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET);
if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET))
return false;
return true;
}
static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
struct flowi *fl)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct ip_tunnel_parm *parms = &tunnel->parms;
struct dst_entry *dst = skb_dst(skb);
struct net_device *tdev; /* Device to other host */
int pkt_len = skb->len;
int err;
int mtu;
if (!dst) {
switch (skb->protocol) {
case htons(ETH_P_IP): {
struct rtable *rt;
fl->u.ip4.flowi4_oif = dev->ifindex;
fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC;
rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4);
if (IS_ERR(rt)) {
dev->stats.tx_carrier_errors++;
goto tx_error_icmp;
}
dst = &rt->dst;
skb_dst_set(skb, dst);
break;
}
#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
fl->u.ip6.flowi6_oif = dev->ifindex;
fl->u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC;
dst = ip6_route_output(dev_net(dev), NULL, &fl->u.ip6);
if (dst->error) {
dst_release(dst);
dst = NULL;
dev->stats.tx_carrier_errors++;
goto tx_error_icmp;
}
skb_dst_set(skb, dst);
break;
#endif
default:
dev->stats.tx_carrier_errors++;
goto tx_error_icmp;
}
}
dst_hold(dst);
dst = xfrm_lookup(tunnel->net, dst, fl, NULL, 0);
if (IS_ERR(dst)) {
dev->stats.tx_carrier_errors++;
goto tx_error_icmp;
}
if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) {
dev->stats.tx_carrier_errors++;
dst_release(dst);
goto tx_error_icmp;
}
tdev = dst->dev;
if (tdev == dev) {
dst_release(dst);
dev->stats.collisions++;
goto tx_error;
}
mtu = dst_mtu(dst);
if (skb->len > mtu) {
skb_dst_update_pmtu_no_confirm(skb, mtu);
if (skb->protocol == htons(ETH_P_IP)) {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
} else {
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
}
dst_release(dst);
goto tx_error;
}
skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev)));
skb_dst_set(skb, dst);
skb->dev = skb_dst(skb)->dev;
err = dst_output(tunnel->net, skb->sk, skb);
if (net_xmit_eval(err) == 0)
err = pkt_len;
iptunnel_xmit_stats(dev, err);
return NETDEV_TX_OK;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
dev->stats.tx_errors++;
kfree_skb(skb);
return NETDEV_TX_OK;
}
/* This function assumes it is being called from dev_queue_xmit()
* and that skb is filled properly by that function.
*/
static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct flowi fl;
if (!pskb_inet_may_pull(skb))
goto tx_err;
memset(&fl, 0, sizeof(fl));
switch (skb->protocol) {
case htons(ETH_P_IP):
xfrm_decode_session(skb, &fl, AF_INET);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
break;
case htons(ETH_P_IPV6):
xfrm_decode_session(skb, &fl, AF_INET6);
memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
break;
default:
goto tx_err;
}
/* override mark with tunnel output key */
fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key);
return vti_xmit(skb, dev, &fl);
tx_err:
dev->stats.tx_errors++;
kfree_skb(skb);
return NETDEV_TX_OK;
}
static int vti4_err(struct sk_buff *skb, u32 info)
{
__be32 spi;
__u32 mark;
struct xfrm_state *x;
struct ip_tunnel *tunnel;
struct ip_esp_hdr *esph;
struct ip_auth_hdr *ah ;
struct ip_comp_hdr *ipch;
struct net *net = dev_net(skb->dev);
const struct iphdr *iph = (const struct iphdr *)skb->data;
int protocol = iph->protocol;
struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
iph->daddr, iph->saddr, 0);
if (!tunnel)
return -1;
mark = be32_to_cpu(tunnel->parms.o_key);
switch (protocol) {
case IPPROTO_ESP:
esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2));
spi = esph->spi;
break;
case IPPROTO_AH:
ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2));
spi = ah->spi;
break;
case IPPROTO_COMP:
ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2));
spi = htonl(ntohs(ipch->cpi));
break;
default:
return 0;
}
switch (icmp_hdr(skb)->type) {
case ICMP_DEST_UNREACH:
if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
return 0;
case ICMP_REDIRECT:
break;
default:
return 0;
}
x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr,
spi, protocol, AF_INET);
if (!x)
return 0;
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, 0, protocol, 0);
else
ipv4_redirect(skb, net, 0, 0, protocol, 0);
xfrm_state_put(x);
return 0;
}
static int
vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
int err = 0;
struct ip_tunnel_parm p;
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
return -EFAULT;
if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) {
if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP ||
p.iph.ihl != 5)
return -EINVAL;
}
if (!(p.i_flags & GRE_KEY))
p.i_key = 0;
if (!(p.o_flags & GRE_KEY))
p.o_key = 0;
p.i_flags = VTI_ISVTI;
err = ip_tunnel_ioctl(dev, &p, cmd);
if (err)
return err;
if (cmd != SIOCDELTUNNEL) {
p.i_flags |= GRE_KEY;
p.o_flags |= GRE_KEY;
}
if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
return -EFAULT;
return 0;
}
static const struct net_device_ops vti_netdev_ops = {
.ndo_init = vti_tunnel_init,
.ndo_uninit = ip_tunnel_uninit,
.ndo_start_xmit = vti_tunnel_xmit,
.ndo_do_ioctl = vti_tunnel_ioctl,
.ndo_change_mtu = ip_tunnel_change_mtu,
.ndo_get_stats64 = ip_tunnel_get_stats64,
.ndo_get_iflink = ip_tunnel_get_iflink,
};
static void vti_tunnel_setup(struct net_device *dev)
{
dev->netdev_ops = &vti_netdev_ops;
dev->type = ARPHRD_TUNNEL;
ip_tunnel_setup(dev, vti_net_id);
}
static int vti_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct iphdr *iph = &tunnel->parms.iph;
memcpy(dev->dev_addr, &iph->saddr, 4);
memcpy(dev->broadcast, &iph->daddr, 4);
dev->flags = IFF_NOARP;
dev->addr_len = 4;
dev->features |= NETIF_F_LLTX;
netif_keep_dst(dev);
return ip_tunnel_init(dev);
}
static void __net_init vti_fb_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct iphdr *iph = &tunnel->parms.iph;
iph->version = 4;
iph->protocol = IPPROTO_IPIP;
iph->ihl = 5;
}
static struct xfrm4_protocol vti_esp4_protocol __read_mostly = {
.handler = vti_rcv_proto,
.input_handler = vti_input_proto,
.cb_handler = vti_rcv_cb,
.err_handler = vti4_err,
.priority = 100,
};
static struct xfrm4_protocol vti_ah4_protocol __read_mostly = {
.handler = vti_rcv_proto,
.input_handler = vti_input_proto,
.cb_handler = vti_rcv_cb,
.err_handler = vti4_err,
.priority = 100,
};
static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = {
.handler = vti_rcv_proto,
.input_handler = vti_input_proto,
.cb_handler = vti_rcv_cb,
.err_handler = vti4_err,
.priority = 100,
};
static struct xfrm_tunnel ipip_handler __read_mostly = {
.handler = vti_rcv_tunnel,
.err_handler = vti4_err,
.priority = 0,
};
static int __net_init vti_init_net(struct net *net)
{
int err;
struct ip_tunnel_net *itn;
err = ip_tunnel_init_net(net, vti_net_id, &vti_link_ops, "ip_vti0");
if (err)
return err;
itn = net_generic(net, vti_net_id);
if (itn->fb_tunnel_dev)
vti_fb_tunnel_init(itn->fb_tunnel_dev);
return 0;
}
static void __net_exit vti_exit_batch_net(struct list_head *list_net)
{
ip_tunnel_delete_nets(list_net, vti_net_id, &vti_link_ops);
}
static struct pernet_operations vti_net_ops = {
.init = vti_init_net,
.exit_batch = vti_exit_batch_net,
.id = &vti_net_id,
.size = sizeof(struct ip_tunnel_net),
};
static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
return 0;
}
static void vti_netlink_parms(struct nlattr *data[],
struct ip_tunnel_parm *parms,
__u32 *fwmark)
{
memset(parms, 0, sizeof(*parms));
parms->iph.protocol = IPPROTO_IPIP;
if (!data)
return;
parms->i_flags = VTI_ISVTI;
if (data[IFLA_VTI_LINK])
parms->link = nla_get_u32(data[IFLA_VTI_LINK]);
if (data[IFLA_VTI_IKEY])
parms->i_key = nla_get_be32(data[IFLA_VTI_IKEY]);
if (data[IFLA_VTI_OKEY])
parms->o_key = nla_get_be32(data[IFLA_VTI_OKEY]);
if (data[IFLA_VTI_LOCAL])
parms->iph.saddr = nla_get_in_addr(data[IFLA_VTI_LOCAL]);
if (data[IFLA_VTI_REMOTE])
parms->iph.daddr = nla_get_in_addr(data[IFLA_VTI_REMOTE]);
if (data[IFLA_VTI_FWMARK])
*fwmark = nla_get_u32(data[IFLA_VTI_FWMARK]);
}
static int vti_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
struct ip_tunnel_parm parms;
__u32 fwmark = 0;
vti_netlink_parms(data, &parms, &fwmark);
return ip_tunnel_newlink(dev, tb, &parms, fwmark);
}
static int vti_changelink(struct net_device *dev, struct nlattr *tb[],
struct nlattr *data[],
struct netlink_ext_ack *extack)
{
struct ip_tunnel *t = netdev_priv(dev);
__u32 fwmark = t->fwmark;
struct ip_tunnel_parm p;
vti_netlink_parms(data, &p, &fwmark);
return ip_tunnel_changelink(dev, tb, &p, fwmark);
}
static size_t vti_get_size(const struct net_device *dev)
{
return
/* IFLA_VTI_LINK */
nla_total_size(4) +
/* IFLA_VTI_IKEY */
nla_total_size(4) +
/* IFLA_VTI_OKEY */
nla_total_size(4) +
/* IFLA_VTI_LOCAL */
nla_total_size(4) +
/* IFLA_VTI_REMOTE */
nla_total_size(4) +
/* IFLA_VTI_FWMARK */
nla_total_size(4) +
0;
}
static int vti_fill_info(struct sk_buff *skb, const struct net_device *dev)
{
struct ip_tunnel *t = netdev_priv(dev);
struct ip_tunnel_parm *p = &t->parms;
if (nla_put_u32(skb, IFLA_VTI_LINK, p->link) ||
nla_put_be32(skb, IFLA_VTI_IKEY, p->i_key) ||
nla_put_be32(skb, IFLA_VTI_OKEY, p->o_key) ||
nla_put_in_addr(skb, IFLA_VTI_LOCAL, p->iph.saddr) ||
nla_put_in_addr(skb, IFLA_VTI_REMOTE, p->iph.daddr) ||
nla_put_u32(skb, IFLA_VTI_FWMARK, t->fwmark))
return -EMSGSIZE;
return 0;
}
static const struct nla_policy vti_policy[IFLA_VTI_MAX + 1] = {
[IFLA_VTI_LINK] = { .type = NLA_U32 },
[IFLA_VTI_IKEY] = { .type = NLA_U32 },
[IFLA_VTI_OKEY] = { .type = NLA_U32 },
[IFLA_VTI_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) },
[IFLA_VTI_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) },
[IFLA_VTI_FWMARK] = { .type = NLA_U32 },
};
static struct rtnl_link_ops vti_link_ops __read_mostly = {
.kind = "vti",
.maxtype = IFLA_VTI_MAX,
.policy = vti_policy,
.priv_size = sizeof(struct ip_tunnel),
.setup = vti_tunnel_setup,
.validate = vti_tunnel_validate,
.newlink = vti_newlink,
.changelink = vti_changelink,
.dellink = ip_tunnel_dellink,
.get_size = vti_get_size,
.fill_info = vti_fill_info,
.get_link_net = ip_tunnel_get_link_net,
};
static int __init vti_init(void)
{
const char *msg;
int err;
pr_info("IPv4 over IPsec tunneling driver\n");
msg = "tunnel device";
err = register_pernet_device(&vti_net_ops);
if (err < 0)
goto pernet_dev_failed;
msg = "tunnel protocols";
err = xfrm4_protocol_register(&vti_esp4_protocol, IPPROTO_ESP);
if (err < 0)
goto xfrm_proto_esp_failed;
err = xfrm4_protocol_register(&vti_ah4_protocol, IPPROTO_AH);
if (err < 0)
goto xfrm_proto_ah_failed;
err = xfrm4_protocol_register(&vti_ipcomp4_protocol, IPPROTO_COMP);
if (err < 0)
goto xfrm_proto_comp_failed;
msg = "ipip tunnel";
err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
if (err < 0)
goto xfrm_tunnel_failed;
msg = "netlink interface";
err = rtnl_link_register(&vti_link_ops);
if (err < 0)
goto rtnl_link_failed;
return err;
rtnl_link_failed:
xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
xfrm_tunnel_failed:
xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
xfrm_proto_comp_failed:
xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
xfrm_proto_ah_failed:
xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
xfrm_proto_esp_failed:
unregister_pernet_device(&vti_net_ops);
pernet_dev_failed:
pr_err("vti init: failed to register %s\n", msg);
return err;
}
static void __exit vti_fini(void)
{
rtnl_link_unregister(&vti_link_ops);
xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
unregister_pernet_device(&vti_net_ops);
}
module_init(vti_init);
module_exit(vti_fini);
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("vti");
MODULE_ALIAS_NETDEV("ip_vti0");
+204
View File
@@ -0,0 +1,204 @@
/*
* IP Payload Compression Protocol (IPComp) - RFC3173.
*
* Copyright (c) 2003 James Morris <jmorris@intercode.com.au>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the Free
* Software Foundation; either version 2 of the License, or (at your option)
* any later version.
*
* 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;
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, 0, IPPROTO_COMP, 0);
else
ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0);
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));
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 = {
.description = "IPCOMP4",
.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__);
if (xfrm_unregister_type(&ipcomp_type, AF_INET) < 0)
pr_info("%s: can't remove xfrm type\n", __func__);
}
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);
+1791
View File
File diff suppressed because it is too large. Load diff
+733
View File
@@ -0,0 +1,733 @@
/*
* Linux NET3: IP/IP protocol decoder.
*
* Authors:
* Sam Lantinga (slouken@cs.ucdavis.edu) 02/01/95
*
* Fixes:
* Alan Cox : Merged and made usable non modular (its so tiny its silly as
* a module taking up 2 pages).
* Alan Cox : Fixed bug with 1.3.18 and IPIP not working (now needs to set skb->h.iph)
* to keep ip_forward happy.
* Alan Cox : More fixes for 1.3.21, and firewall fix. Maybe this will work soon 8).
* Kai Schulte : Fixed #defines for IP_FIREWALL->FIREWALL
* David Woodhouse : Perform some basic ICMP handling.
* IPIP Routing without decapsulation.
* Carlos Picoto : GRE over IP support
* Alexey Kuznetsov: Reworked. Really, now it is truncated version of ipv4/ip_gre.c.
* I do not want to merge them together.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
*/
/* tunnel.c: an IP tunnel driver
The purpose of this driver is to provide an IP tunnel through
which you can tunnel network traffic transparently across subnets.
This was written by looking at Nick Holloway's dummy driver
Thanks for the great code!
-Sam Lantinga (slouken@cs.ucdavis.edu) 02/01/95
Minor tweaks:
Cleaned up the code a little and added some pre-1.3.0 tweaks.
dev->hard_header/hard_header_len changed to use no headers.
Comments/bracketing tweaked.
Made the tunnels use dev->name not tunnel: when error reporting.
Added tx_dropped stat
-Alan Cox (alan@lxorguk.ukuu.org.uk) 21 March 95
Reworked:
Changed to tunnel to destination gateway in addition to the
tunnel's pointopoint address
Almost completely rewritten
Note: There is currently no firewall or ICMP handling done.
-Sam Lantinga (slouken@cs.ucdavis.edu) 02/13/96
*/
/* Things I wish I had known when writing the tunnel driver:
When the tunnel_xmit() function is called, the skb contains the
packet to be sent (plus a great deal of extra info), and dev
contains the tunnel device that _we_ are.
When we are passed a packet, we are expected to fill in the
source address with our source IP address.
What is the proper way to allocate, copy and free a buffer?
After you allocate it, it is a "0 length" chunk of memory
starting at zero. If you want to add headers to the buffer
later, you'll have to call "skb_reserve(skb, amount)" with
the amount of memory you want reserved. Then, you call
"skb_put(skb, amount)" with the amount of space you want in
the buffer. skb_put() returns a pointer to the top (#0) of
that buffer. skb->len is set to the amount of space you have
"allocated" with skb_put(). You can then write up to skb->len
bytes to that buffer. If you need more, you can call skb_put()
again with the additional amount of space you need. You can
find out how much more space you can allocate by calling
"skb_tailroom(skb)".
Now, to add header space, call "skb_push(skb, header_len)".
This creates space at the beginning of the buffer and returns
a pointer to this new space. If later you need to strip a
header from a buffer, call "skb_pull(skb, header_len)".
skb_headroom() will return how much space is left at the top
of the buffer (before the main data). Remember, this headroom
space must be reserved before the skb_put() function is called.
*/
/*
This version of net/ipv4/ipip.c is cloned of net/ipv4/ip_gre.c
For comments look at net/ipv4/ip_gre.c --ANK
*/
#include <linux/capability.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/in.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/if_arp.h>
#include <linux/init.h>
#include <linux/netfilter_ipv4.h>
#include <linux/if_ether.h>
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/ip_tunnels.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/dst_metadata.h>
static bool log_ecn_error = true;
module_param(log_ecn_error, bool, 0644);
MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
static unsigned int ipip_net_id __read_mostly;
static int ipip_tunnel_init(struct net_device *dev);
static struct rtnl_link_ops ipip_link_ops __read_mostly;
static int ipip_err(struct sk_buff *skb, u32 info)
{
/* All the routers (except for Linux) return only
* 8 bytes of packet payload. It means, that precise relaying of
* ICMP in the real Internet is absolutely infeasible.
*/
struct net *net = dev_net(skb->dev);
struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
const struct iphdr *iph = (const struct iphdr *)skb->data;
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
struct ip_tunnel *t;
int err = 0;
switch (type) {
case ICMP_DEST_UNREACH:
switch (code) {
case ICMP_SR_FAILED:
/* Impossible event. */
goto out;
default:
/* All others are translated to HOST_UNREACH.
* rfc2003 contains "deep thoughts" about NET_UNREACH,
* I believe they are just ether pollution. --ANK
*/
break;
}
break;
case ICMP_TIME_EXCEEDED:
if (code != ICMP_EXC_TTL)
goto out;
break;
case ICMP_REDIRECT:
break;
default:
goto out;
}
t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
iph->daddr, iph->saddr, 0);
if (!t) {
err = -ENOENT;
goto out;
}
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
ipv4_update_pmtu(skb, net, info, t->parms.link, 0,
iph->protocol, 0);
goto out;
}
if (type == ICMP_REDIRECT) {
ipv4_redirect(skb, net, t->parms.link, 0, iph->protocol, 0);
goto out;
}
if (t->parms.iph.daddr == 0) {
err = -ENOENT;
goto out;
}
if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
goto out;
if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
t->err_count++;
else
t->err_count = 1;
t->err_time = jiffies;
out:
return err;
}
static const struct tnl_ptk_info ipip_tpi = {
/* no tunnel info required for ipip. */
.proto = htons(ETH_P_IP),
};
#if IS_ENABLED(CONFIG_MPLS)
static const struct tnl_ptk_info mplsip_tpi = {
/* no tunnel info required for mplsip. */
.proto = htons(ETH_P_MPLS_UC),
};
#endif
static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto)
{
struct net *net = dev_net(skb->dev);
struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
struct metadata_dst *tun_dst = NULL;
struct ip_tunnel *tunnel;
const struct iphdr *iph;
iph = ip_hdr(skb);
tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
iph->saddr, iph->daddr, 0);
if (tunnel) {
const struct tnl_ptk_info *tpi;
if (tunnel->parms.iph.protocol != ipproto &&
tunnel->parms.iph.protocol != 0)
goto drop;
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
#if IS_ENABLED(CONFIG_MPLS)
if (ipproto == IPPROTO_MPLS)
tpi = &mplsip_tpi;
else
#endif
tpi = &ipip_tpi;
if (iptunnel_pull_header(skb, 0, tpi->proto, false))
goto drop;
if (tunnel->collect_md) {
tun_dst = ip_tun_rx_dst(skb, 0, 0, 0);
if (!tun_dst)
return 0;
}
return ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error);
}
return -1;
drop:
kfree_skb(skb);
return 0;
}
static int ipip_rcv(struct sk_buff *skb)
{
return ipip_tunnel_rcv(skb, IPPROTO_IPIP);
}
#if IS_ENABLED(CONFIG_MPLS)
static int mplsip_rcv(struct sk_buff *skb)
{
return ipip_tunnel_rcv(skb, IPPROTO_MPLS);
}
#endif
/*
* This function assumes it is being called from dev_queue_xmit()
* and that skb is filled properly by that function.
*/
static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb,
struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *tiph = &tunnel->parms.iph;
u8 ipproto;
if (!pskb_inet_may_pull(skb))
goto tx_error;
switch (skb->protocol) {
case htons(ETH_P_IP):
ipproto = IPPROTO_IPIP;
break;
#if IS_ENABLED(CONFIG_MPLS)
case htons(ETH_P_MPLS_UC):
ipproto = IPPROTO_MPLS;
break;
#endif
default:
goto tx_error;
}
if (tiph->protocol != ipproto && tiph->protocol != 0)
goto tx_error;
if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4))
goto tx_error;
skb_set_inner_ipproto(skb, ipproto);
if (tunnel->collect_md)
ip_md_tunnel_xmit(skb, dev, ipproto);
else
ip_tunnel_xmit(skb, dev, tiph, ipproto);
return NETDEV_TX_OK;
tx_error:
kfree_skb(skb);
dev->stats.tx_errors++;
return NETDEV_TX_OK;
}
static bool ipip_tunnel_ioctl_verify_protocol(u8 ipproto)
{
switch (ipproto) {
case 0:
case IPPROTO_IPIP:
#if IS_ENABLED(CONFIG_MPLS)
case IPPROTO_MPLS:
#endif
return true;
}
return false;
}
static int
ipip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
int err = 0;
struct ip_tunnel_parm p;
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
return -EFAULT;
if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) {
if (p.iph.version != 4 ||
!ipip_tunnel_ioctl_verify_protocol(p.iph.protocol) ||
p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
return -EINVAL;
}
p.i_key = p.o_key = 0;
p.i_flags = p.o_flags = 0;
err = ip_tunnel_ioctl(dev, &p, cmd);
if (err)
return err;
if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
return -EFAULT;
return 0;
}
static const struct net_device_ops ipip_netdev_ops = {
.ndo_init = ipip_tunnel_init,
.ndo_uninit = ip_tunnel_uninit,
.ndo_start_xmit = ipip_tunnel_xmit,
.ndo_do_ioctl = ipip_tunnel_ioctl,
.ndo_change_mtu = ip_tunnel_change_mtu,
.ndo_get_stats64 = ip_tunnel_get_stats64,
.ndo_get_iflink = ip_tunnel_get_iflink,
};
#define IPIP_FEATURES (NETIF_F_SG | \
NETIF_F_FRAGLIST | \
NETIF_F_HIGHDMA | \
NETIF_F_GSO_SOFTWARE | \
NETIF_F_HW_CSUM)
static void ipip_tunnel_setup(struct net_device *dev)
{
dev->netdev_ops = &ipip_netdev_ops;
dev->type = ARPHRD_TUNNEL;
dev->flags = IFF_NOARP;
dev->addr_len = 4;
dev->features |= NETIF_F_LLTX;
netif_keep_dst(dev);
dev->features |= IPIP_FEATURES;
dev->hw_features |= IPIP_FEATURES;
ip_tunnel_setup(dev, ipip_net_id);
}
static int ipip_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
tunnel->tun_hlen = 0;
tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen;
return ip_tunnel_init(dev);
}
static int ipip_tunnel_validate(struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
u8 proto;
if (!data || !data[IFLA_IPTUN_PROTO])
return 0;
proto = nla_get_u8(data[IFLA_IPTUN_PROTO]);
if (proto != IPPROTO_IPIP && proto != IPPROTO_MPLS && proto != 0)
return -EINVAL;
return 0;
}
static void ipip_netlink_parms(struct nlattr *data[],
struct ip_tunnel_parm *parms, bool *collect_md,
__u32 *fwmark)
{
memset(parms, 0, sizeof(*parms));
parms->iph.version = 4;
parms->iph.protocol = IPPROTO_IPIP;
parms->iph.ihl = 5;
*collect_md = false;
if (!data)
return;
if (data[IFLA_IPTUN_LINK])
parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]);
if (data[IFLA_IPTUN_LOCAL])
parms->iph.saddr = nla_get_in_addr(data[IFLA_IPTUN_LOCAL]);
if (data[IFLA_IPTUN_REMOTE])
parms->iph.daddr = nla_get_in_addr(data[IFLA_IPTUN_REMOTE]);
if (data[IFLA_IPTUN_TTL]) {
parms->iph.ttl = nla_get_u8(data[IFLA_IPTUN_TTL]);
if (parms->iph.ttl)
parms->iph.frag_off = htons(IP_DF);
}
if (data[IFLA_IPTUN_TOS])
parms->iph.tos = nla_get_u8(data[IFLA_IPTUN_TOS]);
if (data[IFLA_IPTUN_PROTO])
parms->iph.protocol = nla_get_u8(data[IFLA_IPTUN_PROTO]);
if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC]))
parms->iph.frag_off = htons(IP_DF);
if (data[IFLA_IPTUN_COLLECT_METADATA])
*collect_md = true;
if (data[IFLA_IPTUN_FWMARK])
*fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]);
}
/* This function returns true when ENCAP attributes are present in the nl msg */
static bool ipip_netlink_encap_parms(struct nlattr *data[],
struct ip_tunnel_encap *ipencap)
{
bool ret = false;
memset(ipencap, 0, sizeof(*ipencap));
if (!data)
return ret;
if (data[IFLA_IPTUN_ENCAP_TYPE]) {
ret = true;
ipencap->type = nla_get_u16(data[IFLA_IPTUN_ENCAP_TYPE]);
}
if (data[IFLA_IPTUN_ENCAP_FLAGS]) {
ret = true;
ipencap->flags = nla_get_u16(data[IFLA_IPTUN_ENCAP_FLAGS]);
}
if (data[IFLA_IPTUN_ENCAP_SPORT]) {
ret = true;
ipencap->sport = nla_get_be16(data[IFLA_IPTUN_ENCAP_SPORT]);
}
if (data[IFLA_IPTUN_ENCAP_DPORT]) {
ret = true;
ipencap->dport = nla_get_be16(data[IFLA_IPTUN_ENCAP_DPORT]);
}
return ret;
}
static int ipip_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
struct ip_tunnel *t = netdev_priv(dev);
struct ip_tunnel_parm p;
struct ip_tunnel_encap ipencap;
__u32 fwmark = 0;
if (ipip_netlink_encap_parms(data, &ipencap)) {
int err = ip_tunnel_encap_setup(t, &ipencap);
if (err < 0)
return err;
}
ipip_netlink_parms(data, &p, &t->collect_md, &fwmark);
return ip_tunnel_newlink(dev, tb, &p, fwmark);
}
static int ipip_changelink(struct net_device *dev, struct nlattr *tb[],
struct nlattr *data[],
struct netlink_ext_ack *extack)
{
struct ip_tunnel *t = netdev_priv(dev);
struct ip_tunnel_parm p;
struct ip_tunnel_encap ipencap;
bool collect_md;
__u32 fwmark = t->fwmark;
if (ipip_netlink_encap_parms(data, &ipencap)) {
int err = ip_tunnel_encap_setup(t, &ipencap);
if (err < 0)
return err;
}
ipip_netlink_parms(data, &p, &collect_md, &fwmark);
if (collect_md)
return -EINVAL;
if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) ||
(!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr))
return -EINVAL;
return ip_tunnel_changelink(dev, tb, &p, fwmark);
}
static size_t ipip_get_size(const struct net_device *dev)
{
return
/* IFLA_IPTUN_LINK */
nla_total_size(4) +
/* IFLA_IPTUN_LOCAL */
nla_total_size(4) +
/* IFLA_IPTUN_REMOTE */
nla_total_size(4) +
/* IFLA_IPTUN_TTL */
nla_total_size(1) +
/* IFLA_IPTUN_TOS */
nla_total_size(1) +
/* IFLA_IPTUN_PROTO */
nla_total_size(1) +
/* IFLA_IPTUN_PMTUDISC */
nla_total_size(1) +
/* IFLA_IPTUN_ENCAP_TYPE */
nla_total_size(2) +
/* IFLA_IPTUN_ENCAP_FLAGS */
nla_total_size(2) +
/* IFLA_IPTUN_ENCAP_SPORT */
nla_total_size(2) +
/* IFLA_IPTUN_ENCAP_DPORT */
nla_total_size(2) +
/* IFLA_IPTUN_COLLECT_METADATA */
nla_total_size(0) +
/* IFLA_IPTUN_FWMARK */
nla_total_size(4) +
0;
}
static int ipip_fill_info(struct sk_buff *skb, const struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct ip_tunnel_parm *parm = &tunnel->parms;
if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) ||
nla_put_in_addr(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) ||
nla_put_in_addr(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) ||
nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) ||
nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) ||
nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->iph.protocol) ||
nla_put_u8(skb, IFLA_IPTUN_PMTUDISC,
!!(parm->iph.frag_off & htons(IP_DF))) ||
nla_put_u32(skb, IFLA_IPTUN_FWMARK, tunnel->fwmark))
goto nla_put_failure;
if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE,
tunnel->encap.type) ||
nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT,
tunnel->encap.sport) ||
nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT,
tunnel->encap.dport) ||
nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS,
tunnel->encap.flags))
goto nla_put_failure;
if (tunnel->collect_md)
if (nla_put_flag(skb, IFLA_IPTUN_COLLECT_METADATA))
goto nla_put_failure;
return 0;
nla_put_failure:
return -EMSGSIZE;
}
static const struct nla_policy ipip_policy[IFLA_IPTUN_MAX + 1] = {
[IFLA_IPTUN_LINK] = { .type = NLA_U32 },
[IFLA_IPTUN_LOCAL] = { .type = NLA_U32 },
[IFLA_IPTUN_REMOTE] = { .type = NLA_U32 },
[IFLA_IPTUN_TTL] = { .type = NLA_U8 },
[IFLA_IPTUN_TOS] = { .type = NLA_U8 },
[IFLA_IPTUN_PROTO] = { .type = NLA_U8 },
[IFLA_IPTUN_PMTUDISC] = { .type = NLA_U8 },
[IFLA_IPTUN_ENCAP_TYPE] = { .type = NLA_U16 },
[IFLA_IPTUN_ENCAP_FLAGS] = { .type = NLA_U16 },
[IFLA_IPTUN_ENCAP_SPORT] = { .type = NLA_U16 },
[IFLA_IPTUN_ENCAP_DPORT] = { .type = NLA_U16 },
[IFLA_IPTUN_COLLECT_METADATA] = { .type = NLA_FLAG },
[IFLA_IPTUN_FWMARK] = { .type = NLA_U32 },
};
static struct rtnl_link_ops ipip_link_ops __read_mostly = {
.kind = "ipip",
.maxtype = IFLA_IPTUN_MAX,
.policy = ipip_policy,
.priv_size = sizeof(struct ip_tunnel),
.setup = ipip_tunnel_setup,
.validate = ipip_tunnel_validate,
.newlink = ipip_newlink,
.changelink = ipip_changelink,
.dellink = ip_tunnel_dellink,
.get_size = ipip_get_size,
.fill_info = ipip_fill_info,
.get_link_net = ip_tunnel_get_link_net,
};
static struct xfrm_tunnel ipip_handler __read_mostly = {
.handler = ipip_rcv,
.err_handler = ipip_err,
.priority = 1,
};
#if IS_ENABLED(CONFIG_MPLS)
static struct xfrm_tunnel mplsip_handler __read_mostly = {
.handler = mplsip_rcv,
.err_handler = ipip_err,
.priority = 1,
};
#endif
static int __net_init ipip_init_net(struct net *net)
{
return ip_tunnel_init_net(net, ipip_net_id, &ipip_link_ops, "tunl0");
}
static void __net_exit ipip_exit_batch_net(struct list_head *list_net)
{
ip_tunnel_delete_nets(list_net, ipip_net_id, &ipip_link_ops);
}
static struct pernet_operations ipip_net_ops = {
.init = ipip_init_net,
.exit_batch = ipip_exit_batch_net,
.id = &ipip_net_id,
.size = sizeof(struct ip_tunnel_net),
};
static int __init ipip_init(void)
{
int err;
pr_info("ipip: IPv4 and MPLS over IPv4 tunneling driver\n");
err = register_pernet_device(&ipip_net_ops);
if (err < 0)
return err;
err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
if (err < 0) {
pr_info("%s: can't register tunnel\n", __func__);
goto xfrm_tunnel_ipip_failed;
}
#if IS_ENABLED(CONFIG_MPLS)
err = xfrm4_tunnel_register(&mplsip_handler, AF_MPLS);
if (err < 0) {
pr_info("%s: can't register tunnel\n", __func__);
goto xfrm_tunnel_mplsip_failed;
}
#endif
err = rtnl_link_register(&ipip_link_ops);
if (err < 0)
goto rtnl_link_failed;
out:
return err;
rtnl_link_failed:
#if IS_ENABLED(CONFIG_MPLS)
xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS);
xfrm_tunnel_mplsip_failed:
#endif
xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
xfrm_tunnel_ipip_failed:
unregister_pernet_device(&ipip_net_ops);
goto out;
}
static void __exit ipip_fini(void)
{
rtnl_link_unregister(&ipip_link_ops);
if (xfrm4_tunnel_deregister(&ipip_handler, AF_INET))
pr_info("%s: can't deregister tunnel\n", __func__);
#if IS_ENABLED(CONFIG_MPLS)
if (xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS))
pr_info("%s: can't deregister tunnel\n", __func__);
#endif
unregister_pernet_device(&ipip_net_ops);
}
module_init(ipip_init);
module_exit(ipip_fini);
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("ipip");
MODULE_ALIAS_NETDEV("tunl0");
+3051
View File
File diff suppressed because it is too large. Load diff
+369
View File
@@ -0,0 +1,369 @@
/* Linux multicast routing support
* Common logic shared by IPv4 [ipmr] and IPv6 [ip6mr] implementation
*/
#include <linux/rhashtable.h>
#include <linux/mroute_base.h>
/* Sets everything common except 'dev', since that is done under locking */
void vif_device_init(struct vif_device *v,
struct net_device *dev,
unsigned long rate_limit,
unsigned char threshold,
unsigned short flags,
unsigned short get_iflink_mask)
{
v->dev = NULL;
v->bytes_in = 0;
v->bytes_out = 0;
v->pkt_in = 0;
v->pkt_out = 0;
v->rate_limit = rate_limit;
v->flags = flags;
v->threshold = threshold;
if (v->flags & get_iflink_mask)
v->link = dev_get_iflink(dev);
else
v->link = dev->ifindex;
}
EXPORT_SYMBOL(vif_device_init);
struct mr_table *
mr_table_alloc(struct net *net, u32 id,
struct mr_table_ops *ops,
void (*expire_func)(struct timer_list *t),
void (*table_set)(struct mr_table *mrt,
struct net *net))
{
struct mr_table *mrt;
int err;
mrt = kzalloc(sizeof(*mrt), GFP_KERNEL);
if (!mrt)
return ERR_PTR(-ENOMEM);
mrt->id = id;
write_pnet(&mrt->net, net);
mrt->ops = *ops;
err = rhltable_init(&mrt->mfc_hash, mrt->ops.rht_params);
if (err) {
kfree(mrt);
return ERR_PTR(err);
}
INIT_LIST_HEAD(&mrt->mfc_cache_list);
INIT_LIST_HEAD(&mrt->mfc_unres_queue);
timer_setup(&mrt->ipmr_expire_timer, expire_func, 0);
mrt->mroute_reg_vif_num = -1;
table_set(mrt, net);
return mrt;
}
EXPORT_SYMBOL(mr_table_alloc);
void *mr_mfc_find_parent(struct mr_table *mrt, void *hasharg, int parent)
{
struct rhlist_head *tmp, *list;
struct mr_mfc *c;
list = rhltable_lookup(&mrt->mfc_hash, hasharg, *mrt->ops.rht_params);
rhl_for_each_entry_rcu(c, tmp, list, mnode)
if (parent == -1 || parent == c->mfc_parent)
return c;
return NULL;
}
EXPORT_SYMBOL(mr_mfc_find_parent);
void *mr_mfc_find_any_parent(struct mr_table *mrt, int vifi)
{
struct rhlist_head *tmp, *list;
struct mr_mfc *c;
list = rhltable_lookup(&mrt->mfc_hash, mrt->ops.cmparg_any,
*mrt->ops.rht_params);
rhl_for_each_entry_rcu(c, tmp, list, mnode)
if (c->mfc_un.res.ttls[vifi] < 255)
return c;
return NULL;
}
EXPORT_SYMBOL(mr_mfc_find_any_parent);
void *mr_mfc_find_any(struct mr_table *mrt, int vifi, void *hasharg)
{
struct rhlist_head *tmp, *list;
struct mr_mfc *c, *proxy;
list = rhltable_lookup(&mrt->mfc_hash, hasharg, *mrt->ops.rht_params);
rhl_for_each_entry_rcu(c, tmp, list, mnode) {
if (c->mfc_un.res.ttls[vifi] < 255)
return c;
/* It's ok if the vifi is part of the static tree */
proxy = mr_mfc_find_any_parent(mrt, c->mfc_parent);
if (proxy && proxy->mfc_un.res.ttls[vifi] < 255)
return c;
}
return mr_mfc_find_any_parent(mrt, vifi);
}
EXPORT_SYMBOL(mr_mfc_find_any);
#ifdef CONFIG_PROC_FS
void *mr_vif_seq_idx(struct net *net, struct mr_vif_iter *iter, loff_t pos)
{
struct mr_table *mrt = iter->mrt;
for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) {
if (!VIF_EXISTS(mrt, iter->ct))
continue;
if (pos-- == 0)
return &mrt->vif_table[iter->ct];
}
return NULL;
}
EXPORT_SYMBOL(mr_vif_seq_idx);
void *mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct mr_vif_iter *iter = seq->private;
struct net *net = seq_file_net(seq);
struct mr_table *mrt = iter->mrt;
++*pos;
if (v == SEQ_START_TOKEN)
return mr_vif_seq_idx(net, iter, 0);
while (++iter->ct < mrt->maxvif) {
if (!VIF_EXISTS(mrt, iter->ct))
continue;
return &mrt->vif_table[iter->ct];
}
return NULL;
}
EXPORT_SYMBOL(mr_vif_seq_next);
void *mr_mfc_seq_idx(struct net *net,
struct mr_mfc_iter *it, loff_t pos)
{
struct mr_table *mrt = it->mrt;
struct mr_mfc *mfc;
rcu_read_lock();
it->cache = &mrt->mfc_cache_list;
list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list)
if (pos-- == 0)
return mfc;
rcu_read_unlock();
spin_lock_bh(it->lock);
it->cache = &mrt->mfc_unres_queue;
list_for_each_entry(mfc, it->cache, list)
if (pos-- == 0)
return mfc;
spin_unlock_bh(it->lock);
it->cache = NULL;
return NULL;
}
EXPORT_SYMBOL(mr_mfc_seq_idx);
void *mr_mfc_seq_next(struct seq_file *seq, void *v,
loff_t *pos)
{
struct mr_mfc_iter *it = seq->private;
struct net *net = seq_file_net(seq);
struct mr_table *mrt = it->mrt;
struct mr_mfc *c = v;
++*pos;
if (v == SEQ_START_TOKEN)
return mr_mfc_seq_idx(net, seq->private, 0);
if (c->list.next != it->cache)
return list_entry(c->list.next, struct mr_mfc, list);
if (it->cache == &mrt->mfc_unres_queue)
goto end_of_list;
/* exhausted cache_array, show unresolved */
rcu_read_unlock();
it->cache = &mrt->mfc_unres_queue;
spin_lock_bh(it->lock);
if (!list_empty(it->cache))
return list_first_entry(it->cache, struct mr_mfc, list);
end_of_list:
spin_unlock_bh(it->lock);
it->cache = NULL;
return NULL;
}
EXPORT_SYMBOL(mr_mfc_seq_next);
#endif
int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
struct mr_mfc *c, struct rtmsg *rtm)
{
struct rta_mfc_stats mfcs;
struct nlattr *mp_attr;
struct rtnexthop *nhp;
unsigned long lastuse;
int ct;
/* If cache is unresolved, don't try to parse IIF and OIF */
if (c->mfc_parent >= MAXVIFS) {
rtm->rtm_flags |= RTNH_F_UNRESOLVED;
return -ENOENT;
}
if (VIF_EXISTS(mrt, c->mfc_parent) &&
nla_put_u32(skb, RTA_IIF,
mrt->vif_table[c->mfc_parent].dev->ifindex) < 0)
return -EMSGSIZE;
if (c->mfc_flags & MFC_OFFLOAD)
rtm->rtm_flags |= RTNH_F_OFFLOAD;
mp_attr = nla_nest_start(skb, RTA_MULTIPATH);
if (!mp_attr)
return -EMSGSIZE;
for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) {
if (VIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) {
struct vif_device *vif;
nhp = nla_reserve_nohdr(skb, sizeof(*nhp));
if (!nhp) {
nla_nest_cancel(skb, mp_attr);
return -EMSGSIZE;
}
nhp->rtnh_flags = 0;
nhp->rtnh_hops = c->mfc_un.res.ttls[ct];
vif = &mrt->vif_table[ct];
nhp->rtnh_ifindex = vif->dev->ifindex;
nhp->rtnh_len = sizeof(*nhp);
}
}
nla_nest_end(skb, mp_attr);
lastuse = READ_ONCE(c->mfc_un.res.lastuse);
lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0;
mfcs.mfcs_packets = c->mfc_un.res.pkt;
mfcs.mfcs_bytes = c->mfc_un.res.bytes;
mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if;
if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) ||
nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse),
RTA_PAD))
return -EMSGSIZE;
rtm->rtm_type = RTN_MULTICAST;
return 1;
}
EXPORT_SYMBOL(mr_fill_mroute);
int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb,
struct mr_table *(*iter)(struct net *net,
struct mr_table *mrt),
int (*fill)(struct mr_table *mrt,
struct sk_buff *skb,
u32 portid, u32 seq, struct mr_mfc *c,
int cmd, int flags),
spinlock_t *lock)
{
unsigned int t = 0, e = 0, s_t = cb->args[0], s_e = cb->args[1];
struct net *net = sock_net(skb->sk);
struct mr_table *mrt;
struct mr_mfc *mfc;
rcu_read_lock();
for (mrt = iter(net, NULL); mrt; mrt = iter(net, mrt)) {
if (t < s_t)
goto next_table;
list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) {
if (e < s_e)
goto next_entry;
if (fill(mrt, skb, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, mfc,
RTM_NEWROUTE, NLM_F_MULTI) < 0)
goto done;
next_entry:
e++;
}
spin_lock_bh(lock);
list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) {
if (e < s_e)
goto next_entry2;
if (fill(mrt, skb, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, mfc,
RTM_NEWROUTE, NLM_F_MULTI) < 0) {
spin_unlock_bh(lock);
goto done;
}
next_entry2:
e++;
}
spin_unlock_bh(lock);
e = 0;
s_e = 0;
next_table:
t++;
}
done:
rcu_read_unlock();
cb->args[1] = e;
cb->args[0] = t;
return skb->len;
}
EXPORT_SYMBOL(mr_rtm_dumproute);
int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family,
int (*rules_dump)(struct net *net,
struct notifier_block *nb),
struct mr_table *(*mr_iter)(struct net *net,
struct mr_table *mrt),
rwlock_t *mrt_lock)
{
struct mr_table *mrt;
int err;
err = rules_dump(net, nb);
if (err)
return err;
for (mrt = mr_iter(net, NULL); mrt; mrt = mr_iter(net, mrt)) {
struct vif_device *v = &mrt->vif_table[0];
struct mr_mfc *mfc;
int vifi;
/* Notifiy on table VIF entries */
read_lock(mrt_lock);
for (vifi = 0; vifi < mrt->maxvif; vifi++, v++) {
if (!v->dev)
continue;
mr_call_vif_notifier(nb, net, family,
FIB_EVENT_VIF_ADD,
v, vifi, mrt->id);
}
read_unlock(mrt_lock);
/* Notify on table MFC entries */
list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list)
mr_call_mfc_notifier(nb, net, family,
FIB_EVENT_ENTRY_ADD,
mfc, mrt->id);
}
return 0;
}
EXPORT_SYMBOL(mr_dump);
+55
View File
@@ -0,0 +1,55 @@
#include <linux/netlink.h>
#include <linux/rtnetlink.h>
#include <linux/types.h>
#include <net/ip.h>
#include <net/net_namespace.h>
#include <net/tcp.h>
int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, int fc_mx_len,
u32 *metrics)
{
bool ecn_ca = false;
struct nlattr *nla;
int remaining;
if (!fc_mx)
return 0;
nla_for_each_attr(nla, fc_mx, fc_mx_len, remaining) {
int type = nla_type(nla);
u32 val;
if (!type)
continue;
if (type > RTAX_MAX)
return -EINVAL;
if (type == RTAX_CC_ALGO) {
char tmp[TCP_CA_NAME_MAX];
nla_strlcpy(tmp, nla, sizeof(tmp));
val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca);
if (val == TCP_CA_UNSPEC)
return -EINVAL;
} else {
if (nla_len(nla) != sizeof(u32))
return -EINVAL;
val = nla_get_u32(nla);
}
if (type == RTAX_ADVMSS && val > 65535 - 40)
val = 65535 - 40;
if (type == RTAX_MTU && val > 65535 - 15)
val = 65535 - 15;
if (type == RTAX_HOPLIMIT && val > 255)
val = 255;
if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
return -EINVAL;
metrics[type - 1] = val;
}
if (ecn_ca)
metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;
return 0;
}
EXPORT_SYMBOL_GPL(ip_metrics_convert);
+112
View File
@@ -0,0 +1,112 @@
/*
* IPv4 specific functions of netfilter core
*
* Rusty Russell (C) 2000 -- This code is GPL.
* Patrick McHardy (C) 2006-2012
*/
#include <linux/kernel.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>
#include <linux/ip.h>
#include <linux/skbuff.h>
#include <linux/gfp.h>
#include <linux/export.h>
#include <net/route.h>
#include <net/xfrm.h>
#include <net/ip.h>
#include <net/netfilter/nf_queue.h>
/* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int addr_type)
{
const struct iphdr *iph = ip_hdr(skb);
struct rtable *rt;
struct flowi4 fl4 = {};
__be32 saddr = iph->saddr;
__u8 flags;
struct net_device *dev = skb_dst(skb)->dev;
unsigned int hh_len;
sk = sk_to_full_sk(sk);
flags = sk ? inet_sk_flowi_flags(sk) : 0;
if (addr_type == RTN_UNSPEC)
addr_type = inet_addr_type_dev_table(net, dev, saddr);
if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST)
flags |= FLOWI_FLAG_ANYSRC;
else
saddr = 0;
/* some non-standard hacks like ipt_REJECT.c:send_reset() can cause
* packets with foreign saddr to appear on the NF_INET_LOCAL_OUT hook.
*/
fl4.daddr = iph->daddr;
fl4.saddr = saddr;
fl4.flowi4_tos = RT_TOS(iph->tos);
fl4.flowi4_oif = sk ? sk->sk_bound_dev_if : 0;
if (!fl4.flowi4_oif)
fl4.flowi4_oif = l3mdev_master_ifindex(dev);
fl4.flowi4_mark = skb->mark;
fl4.flowi4_flags = flags;
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt))
return PTR_ERR(rt);
/* Drop old route. */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
if (skb_dst(skb)->error)
return skb_dst(skb)->error;
#ifdef CONFIG_XFRM
if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
xfrm_decode_session(skb, flowi4_to_flowi(&fl4), AF_INET) == 0) {
struct dst_entry *dst = skb_dst(skb);
skb_dst_set(skb, NULL);
dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), sk, 0);
if (IS_ERR(dst))
return PTR_ERR(dst);
skb_dst_set(skb, dst);
}
#endif
/* Change in oif may mean change in hh_len. */
hh_len = skb_dst(skb)->dev->hard_header_len;
if (skb_headroom(skb) < hh_len &&
pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)),
0, GFP_ATOMIC))
return -ENOMEM;
return 0;
}
EXPORT_SYMBOL(ip_route_me_harder);
int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry)
{
const struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry);
if (entry->state.hook == NF_INET_LOCAL_OUT) {
const struct iphdr *iph = ip_hdr(skb);
if (!(iph->tos == rt_info->tos &&
skb->mark == rt_info->mark &&
iph->daddr == rt_info->daddr &&
iph->saddr == rt_info->saddr))
return ip_route_me_harder(entry->state.net, entry->state.sk,
skb, RTN_UNSPEC);
}
return 0;
}
EXPORT_SYMBOL_GPL(nf_ip_reroute);
int nf_ip_route(struct net *net, struct dst_entry **dst, struct flowi *fl,
bool strict __always_unused)
{
struct rtable *rt = ip_route_output_key(net, &fl->u.ip4);
if (IS_ERR(rt))
return PTR_ERR(rt);
*dst = &rt->dst;
return 0;
}
EXPORT_SYMBOL_GPL(nf_ip_route);
+422
View File
@@ -0,0 +1,422 @@
#
# IP netfilter configuration
#
menu "IP: Netfilter Configuration"
depends on INET && NETFILTER
config NF_DEFRAG_IPV4
tristate
default n
config NF_SOCKET_IPV4
tristate "IPv4 socket lookup support"
help
This option enables the IPv4 socket lookup infrastructure. This is
is required by the {ip,nf}tables socket match.
config NF_TPROXY_IPV4
tristate "IPv4 tproxy support"
if NF_TABLES
config NF_TABLES_IPV4
bool "IPv4 nf_tables support"
help
This option enables the IPv4 support for nf_tables.
if NF_TABLES_IPV4
config NFT_CHAIN_ROUTE_IPV4
tristate "IPv4 nf_tables route chain support"
help
This option enables the "route" chain for IPv4 in nf_tables. This
chain type is used to force packet re-routing after mangling header
fields such as the source, destination, type of service and
the packet mark.
config NFT_REJECT_IPV4
select NF_REJECT_IPV4
default NFT_REJECT
tristate
config NFT_DUP_IPV4
tristate "IPv4 nf_tables packet duplication support"
depends on !NF_CONNTRACK || NF_CONNTRACK
select NF_DUP_IPV4
help
This module enables IPv4 packet duplication support for nf_tables.
config NFT_FIB_IPV4
select NFT_FIB
tristate "nf_tables fib / ip route lookup support"
help
This module enables IPv4 FIB lookups, e.g. for reverse path filtering.
It also allows query of the FIB for the route type, e.g. local, unicast,
multicast or blackhole.
endif # NF_TABLES_IPV4
config NF_TABLES_ARP
bool "ARP nf_tables support"
select NETFILTER_FAMILY_ARP
help
This option enables the ARP support for nf_tables.
endif # NF_TABLES
config NF_FLOW_TABLE_IPV4
tristate "Netfilter flow table IPv4 module"
depends on NF_FLOW_TABLE
help
This option adds the flow table IPv4 support.
To compile it as a module, choose M here.
config NF_DUP_IPV4
tristate "Netfilter IPv4 packet duplication to alternate destination"
depends on !NF_CONNTRACK || NF_CONNTRACK
help
This option enables the nf_dup_ipv4 core, which duplicates an IPv4
packet to be rerouted to another destination.
config NF_LOG_ARP
tristate "ARP packet logging"
default m if NETFILTER_ADVANCED=n
select NF_LOG_COMMON
config NF_LOG_IPV4
tristate "IPv4 packet logging"
default m if NETFILTER_ADVANCED=n
select NF_LOG_COMMON
config NF_REJECT_IPV4
tristate "IPv4 packet rejection"
default m if NETFILTER_ADVANCED=n
config NF_NAT_IPV4
tristate "IPv4 NAT"
depends on NF_CONNTRACK
default m if NETFILTER_ADVANCED=n
select NF_NAT
help
The IPv4 NAT option allows masquerading, port forwarding and other
forms of full Network Address Port Translation. This can be
controlled by iptables or nft.
if NF_NAT_IPV4
config NF_NAT_MASQUERADE_IPV4
bool
if NF_TABLES
config NFT_CHAIN_NAT_IPV4
depends on NF_TABLES_IPV4
tristate "IPv4 nf_tables nat chain support"
help
This option enables the "nat" chain for IPv4 in nf_tables. This
chain type is used to perform Network Address Translation (NAT)
packet transformations such as the source, destination address and
source and destination ports.
config NFT_MASQ_IPV4
tristate "IPv4 masquerading support for nf_tables"
depends on NF_TABLES_IPV4
depends on NFT_MASQ
select NF_NAT_MASQUERADE_IPV4
help
This is the expression that provides IPv4 masquerading support for
nf_tables.
config NFT_REDIR_IPV4
tristate "IPv4 redirect support for nf_tables"
depends on NF_TABLES_IPV4
depends on NFT_REDIR
select NF_NAT_REDIRECT
help
This is the expression that provides IPv4 redirect support for
nf_tables.
endif # NF_TABLES
config NF_NAT_SNMP_BASIC
tristate "Basic SNMP-ALG support"
depends on NF_CONNTRACK_SNMP
depends on NETFILTER_ADVANCED
default NF_NAT && NF_CONNTRACK_SNMP
select ASN1
---help---
This module implements an Application Layer Gateway (ALG) for
SNMP payloads. In conjunction with NAT, it allows a network
management system to access multiple private networks with
conflicting addresses. It works by modifying IP addresses
inside SNMP payloads to match IP-layer NAT mapping.
This is the "basic" form of SNMP-ALG, as described in RFC 2962
To compile it as a module, choose M here. If unsure, say N.
config NF_NAT_PROTO_GRE
tristate
depends on NF_CT_PROTO_GRE
config NF_NAT_PPTP
tristate
depends on NF_CONNTRACK
default NF_CONNTRACK_PPTP
select NF_NAT_PROTO_GRE
config NF_NAT_H323
tristate
depends on NF_CONNTRACK
default NF_CONNTRACK_H323
endif # NF_NAT_IPV4
config IP_NF_IPTABLES
tristate "IP tables support (required for filtering/masq/NAT)"
default m if NETFILTER_ADVANCED=n
select NETFILTER_XTABLES
help
iptables is a general, extensible packet identification framework.
The packet filtering and full NAT (masquerading, port forwarding,
etc) subsystems now use this: say `Y' or `M' here if you want to use
either of those.
To compile it as a module, choose M here. If unsure, say N.
if IP_NF_IPTABLES
# The matches.
config IP_NF_MATCH_AH
tristate '"ah" match support'
depends on NETFILTER_ADVANCED
help
This match extension allows you to match a range of SPIs
inside AH header of IPSec packets.
To compile it as a module, choose M here. If unsure, say N.
config IP_NF_MATCH_ECN
tristate '"ecn" match support'
depends on NETFILTER_ADVANCED
select NETFILTER_XT_MATCH_ECN
---help---
This is a backwards-compat option for the user's convenience
(e.g. when running oldconfig). It selects
CONFIG_NETFILTER_XT_MATCH_ECN.
config IP_NF_MATCH_RPFILTER
tristate '"rpfilter" reverse path filter match support'
depends on NETFILTER_ADVANCED
depends on IP_NF_MANGLE || IP_NF_RAW
---help---
This option allows you to match packets whose replies would
go out via the interface the packet came in.
To compile it as a module, choose M here. If unsure, say N.
The module will be called ipt_rpfilter.
config IP_NF_MATCH_TTL
tristate '"ttl" match support'
depends on NETFILTER_ADVANCED
select NETFILTER_XT_MATCH_HL
---help---
This is a backwards-compat option for the user's convenience
(e.g. when running oldconfig). It selects
CONFIG_NETFILTER_XT_MATCH_HL.
# `filter', generic and specific targets
config IP_NF_FILTER
tristate "Packet filtering"
default m if NETFILTER_ADVANCED=n
help
Packet filtering defines a table `filter', which has a series of
rules for simple packet filtering at local input, forwarding and
local output. See the man page for iptables(8).
To compile it as a module, choose M here. If unsure, say N.
config IP_NF_TARGET_REJECT
tristate "REJECT target support"
depends on IP_NF_FILTER
select NF_REJECT_IPV4
default m if NETFILTER_ADVANCED=n
help
The REJECT target allows a filtering rule to specify that an ICMP
error should be issued in response to an incoming packet, rather
than silently being dropped.
To compile it as a module, choose M here. If unsure, say N.
config IP_NF_TARGET_SYNPROXY
tristate "SYNPROXY target support"
depends on NF_CONNTRACK && NETFILTER_ADVANCED
select NETFILTER_SYNPROXY
select SYN_COOKIES
help
The SYNPROXY target allows you to intercept TCP connections and
establish them using syncookies before they are passed on to the
server. This allows to avoid conntrack and server resource usage
during SYN-flood attacks.
To compile it as a module, choose M here. If unsure, say N.
# NAT + specific targets: nf_conntrack
config IP_NF_NAT
tristate "iptables NAT support"
depends on NF_CONNTRACK
default m if NETFILTER_ADVANCED=n
select NF_NAT
select NF_NAT_IPV4
select NETFILTER_XT_NAT
help
This enables the `nat' table in iptables. This allows masquerading,
port forwarding and other forms of full Network Address Port
Translation.
To compile it as a module, choose M here. If unsure, say N.
if IP_NF_NAT
config IP_NF_TARGET_MASQUERADE
tristate "MASQUERADE target support"
select NF_NAT_MASQUERADE_IPV4
default m if NETFILTER_ADVANCED=n
help
Masquerading is a special case of NAT: all outgoing connections are
changed to seem to come from a particular interface's address, and
if the interface goes down, those connections are lost. This is
only useful for dialup accounts with dynamic IP address (ie. your IP
address will be different on next dialup).
To compile it as a module, choose M here. If unsure, say N.
config IP_NF_TARGET_NETMAP
tristate "NETMAP target support"
depends on NETFILTER_ADVANCED
select NETFILTER_XT_TARGET_NETMAP
---help---
This is a backwards-compat option for the user's convenience
(e.g. when running oldconfig). It selects
CONFIG_NETFILTER_XT_TARGET_NETMAP.
config IP_NF_TARGET_REDIRECT
tristate "REDIRECT target support"
depends on NETFILTER_ADVANCED
select NETFILTER_XT_TARGET_REDIRECT
---help---
This is a backwards-compat option for the user's convenience
(e.g. when running oldconfig). It selects
CONFIG_NETFILTER_XT_TARGET_REDIRECT.
endif # IP_NF_NAT
# mangle + specific targets
config IP_NF_MANGLE
tristate "Packet mangling"
default m if NETFILTER_ADVANCED=n
help
This option adds a `mangle' table to iptables: see the man page for
iptables(8). This table is used for various packet alterations
which can effect how the packet is routed.
To compile it as a module, choose M here. If unsure, say N.
config IP_NF_TARGET_CLUSTERIP
tristate "CLUSTERIP target support"
depends on IP_NF_MANGLE
depends on NF_CONNTRACK
depends on NETFILTER_ADVANCED
select NF_CONNTRACK_MARK
select NETFILTER_FAMILY_ARP
help
The CLUSTERIP target allows you to build load-balancing clusters of
network servers without having a dedicated load-balancing
router/server/switch.
To compile it as a module, choose M here. If unsure, say N.
config IP_NF_TARGET_ECN
tristate "ECN target support"
depends on IP_NF_MANGLE
depends on NETFILTER_ADVANCED
---help---
This option adds a `ECN' target, which can be used in the iptables mangle
table.
You can use this target to remove the ECN bits from the IPv4 header of
an IP packet. This is particularly useful, if you need to work around
existing ECN blackholes on the internet, but don't want to disable
ECN support in general.
To compile it as a module, choose M here. If unsure, say N.
config IP_NF_TARGET_TTL
tristate '"TTL" target support'
depends on NETFILTER_ADVANCED && IP_NF_MANGLE
select NETFILTER_XT_TARGET_HL
---help---
This is a backwards-compatible option for the user's convenience
(e.g. when running oldconfig). It selects
CONFIG_NETFILTER_XT_TARGET_HL.
# raw + specific targets
config IP_NF_RAW
tristate 'raw table support (required for NOTRACK/TRACE)'
help
This option adds a `raw' table to iptables. This table is the very
first in the netfilter framework and hooks in at the PREROUTING
and OUTPUT chains.
If you want to compile it as a module, say M here and read
<file:Documentation/kbuild/modules.txt>. If unsure, say `N'.
# security table for MAC policy
config IP_NF_SECURITY
tristate "Security table"
depends on SECURITY
depends on NETFILTER_ADVANCED
help
This option adds a `security' table to iptables, for use
with Mandatory Access Control (MAC) policy.
If unsure, say N.
endif # IP_NF_IPTABLES
# ARP tables
config IP_NF_ARPTABLES
tristate "ARP tables support"
select NETFILTER_XTABLES
select NETFILTER_FAMILY_ARP
depends on NETFILTER_ADVANCED
help
arptables is a general, extensible packet identification framework.
The ARP packet filtering and mangling (manipulation)subsystems
use this: say Y or M here if you want to use either of those.
To compile it as a module, choose M here. If unsure, say N.
if IP_NF_ARPTABLES
config IP_NF_ARPFILTER
tristate "ARP packet filtering"
help
ARP packet filtering defines a table `filter', which has a series of
rules for simple ARP packet filtering at local input and
local output. On a bridge, you can also specify filtering rules
for forwarded ARP packets. See the man page for arptables(8).
To compile it as a module, choose M here. If unsure, say N.
config IP_NF_ARP_MANGLE
tristate "ARP payload mangling"
help
Allows altering the ARP packet payload: source and destination
hardware and network addresses.
endif # IP_NF_ARPTABLES
endmenu
+73
View File
@@ -0,0 +1,73 @@
# SPDX-License-Identifier: GPL-2.0
#
# Makefile for the netfilter modules on top of IPv4.
#
nf_nat_ipv4-y := nf_nat_l3proto_ipv4.o nf_nat_proto_icmp.o
nf_nat_ipv4-$(CONFIG_NF_NAT_MASQUERADE_IPV4) += nf_nat_masquerade_ipv4.o
obj-$(CONFIG_NF_NAT_IPV4) += nf_nat_ipv4.o
# defrag
obj-$(CONFIG_NF_DEFRAG_IPV4) += nf_defrag_ipv4.o
obj-$(CONFIG_NF_SOCKET_IPV4) += nf_socket_ipv4.o
obj-$(CONFIG_NF_TPROXY_IPV4) += nf_tproxy_ipv4.o
# logging
obj-$(CONFIG_NF_LOG_ARP) += nf_log_arp.o
obj-$(CONFIG_NF_LOG_IPV4) += nf_log_ipv4.o
# reject
obj-$(CONFIG_NF_REJECT_IPV4) += nf_reject_ipv4.o
# NAT helpers (nf_conntrack)
obj-$(CONFIG_NF_NAT_H323) += nf_nat_h323.o
obj-$(CONFIG_NF_NAT_PPTP) += nf_nat_pptp.o
nf_nat_snmp_basic-y := nf_nat_snmp_basic.asn1.o nf_nat_snmp_basic_main.o
$(obj)/nf_nat_snmp_basic_main.o: $(obj)/nf_nat_snmp_basic.asn1.h
obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o
# NAT protocols (nf_nat)
obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o
obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o
obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o
obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
obj-$(CONFIG_NFT_FIB_IPV4) += nft_fib_ipv4.o
obj-$(CONFIG_NFT_MASQ_IPV4) += nft_masq_ipv4.o
obj-$(CONFIG_NFT_REDIR_IPV4) += nft_redir_ipv4.o
obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o
# flow table support
obj-$(CONFIG_NF_FLOW_TABLE_IPV4) += nf_flow_table_ipv4.o
# generic IP tables
obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o
# the three instances of ip_tables
obj-$(CONFIG_IP_NF_FILTER) += iptable_filter.o
obj-$(CONFIG_IP_NF_MANGLE) += iptable_mangle.o
obj-$(CONFIG_IP_NF_NAT) += iptable_nat.o
obj-$(CONFIG_IP_NF_RAW) += iptable_raw.o
obj-$(CONFIG_IP_NF_SECURITY) += iptable_security.o
# matches
obj-$(CONFIG_IP_NF_MATCH_AH) += ipt_ah.o
obj-$(CONFIG_IP_NF_MATCH_RPFILTER) += ipt_rpfilter.o
# targets
obj-$(CONFIG_IP_NF_TARGET_CLUSTERIP) += ipt_CLUSTERIP.o
obj-$(CONFIG_IP_NF_TARGET_ECN) += ipt_ECN.o
obj-$(CONFIG_IP_NF_TARGET_MASQUERADE) += ipt_MASQUERADE.o
obj-$(CONFIG_IP_NF_TARGET_REJECT) += ipt_REJECT.o
obj-$(CONFIG_IP_NF_TARGET_SYNPROXY) += ipt_SYNPROXY.o
# generic ARP tables
obj-$(CONFIG_IP_NF_ARPTABLES) += arp_tables.o
obj-$(CONFIG_IP_NF_ARP_MANGLE) += arpt_mangle.o
# just filtering instance of ARP tables for now
obj-$(CONFIG_IP_NF_ARPFILTER) += arptable_filter.o
obj-$(CONFIG_NF_DUP_IPV4) += nf_dup_ipv4.o
File diff suppressed because it is too large. Load diff
+91
View File
@@ -0,0 +1,91 @@
/* module that allows mangling of the arp payload */
#include <linux/module.h>
#include <linux/netfilter.h>
#include <linux/netfilter_arp/arpt_mangle.h>
#include <net/sock.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Bart De Schuymer <bdschuym@pandora.be>");
MODULE_DESCRIPTION("arptables arp payload mangle target");
static unsigned int
target(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct arpt_mangle *mangle = par->targinfo;
const struct arphdr *arp;
unsigned char *arpptr;
int pln, hln;
if (!skb_make_writable(skb, skb->len))
return NF_DROP;
arp = arp_hdr(skb);
arpptr = skb_network_header(skb) + sizeof(*arp);
pln = arp->ar_pln;
hln = arp->ar_hln;
/* We assume that pln and hln were checked in the match */
if (mangle->flags & ARPT_MANGLE_SDEV) {
if (ARPT_DEV_ADDR_LEN_MAX < hln ||
(arpptr + hln > skb_tail_pointer(skb)))
return NF_DROP;
memcpy(arpptr, mangle->src_devaddr, hln);
}
arpptr += hln;
if (mangle->flags & ARPT_MANGLE_SIP) {
if (ARPT_MANGLE_ADDR_LEN_MAX < pln ||
(arpptr + pln > skb_tail_pointer(skb)))
return NF_DROP;
memcpy(arpptr, &mangle->u_s.src_ip, pln);
}
arpptr += pln;
if (mangle->flags & ARPT_MANGLE_TDEV) {
if (ARPT_DEV_ADDR_LEN_MAX < hln ||
(arpptr + hln > skb_tail_pointer(skb)))
return NF_DROP;
memcpy(arpptr, mangle->tgt_devaddr, hln);
}
arpptr += hln;
if (mangle->flags & ARPT_MANGLE_TIP) {
if (ARPT_MANGLE_ADDR_LEN_MAX < pln ||
(arpptr + pln > skb_tail_pointer(skb)))
return NF_DROP;
memcpy(arpptr, &mangle->u_t.tgt_ip, pln);
}
return mangle->target;
}
static int checkentry(const struct xt_tgchk_param *par)
{
const struct arpt_mangle *mangle = par->targinfo;
if (mangle->flags & ~ARPT_MANGLE_MASK ||
!(mangle->flags & ARPT_MANGLE_MASK))
return -EINVAL;
if (mangle->target != NF_DROP && mangle->target != NF_ACCEPT &&
mangle->target != XT_CONTINUE)
return -EINVAL;
return 0;
}
static struct xt_target arpt_mangle_reg __read_mostly = {
.name = "mangle",
.family = NFPROTO_ARP,
.target = target,
.targetsize = sizeof(struct arpt_mangle),
.checkentry = checkentry,
.me = THIS_MODULE,
};
static int __init arpt_mangle_init(void)
{
return xt_register_target(&arpt_mangle_reg);
}
static void __exit arpt_mangle_fini(void)
{
xt_unregister_target(&arpt_mangle_reg);
}
module_init(arpt_mangle_init);
module_exit(arpt_mangle_fini);
+100
View File
@@ -0,0 +1,100 @@
/*
* Filtering ARP tables module.
*
* Copyright (C) 2002 David S. Miller (davem@redhat.com)
*
*/
#include <linux/module.h>
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter_arp/arp_tables.h>
#include <linux/slab.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("David S. Miller <davem@redhat.com>");
MODULE_DESCRIPTION("arptables filter table");
#define FILTER_VALID_HOOKS ((1 << NF_ARP_IN) | (1 << NF_ARP_OUT) | \
(1 << NF_ARP_FORWARD))
static int __net_init arptable_filter_table_init(struct net *net);
static const struct xt_table packet_filter = {
.name = "filter",
.valid_hooks = FILTER_VALID_HOOKS,
.me = THIS_MODULE,
.af = NFPROTO_ARP,
.priority = NF_IP_PRI_FILTER,
.table_init = arptable_filter_table_init,
};
/* The work comes in here from netfilter.c */
static unsigned int
arptable_filter_hook(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
return arpt_do_table(skb, state, state->net->ipv4.arptable_filter);
}
static struct nf_hook_ops *arpfilter_ops __read_mostly;
static int __net_init arptable_filter_table_init(struct net *net)
{
struct arpt_replace *repl;
int err;
if (net->ipv4.arptable_filter)
return 0;
repl = arpt_alloc_initial_table(&packet_filter);
if (repl == NULL)
return -ENOMEM;
err = arpt_register_table(net, &packet_filter, repl, arpfilter_ops,
&net->ipv4.arptable_filter);
kfree(repl);
return err;
}
static void __net_exit arptable_filter_net_exit(struct net *net)
{
if (!net->ipv4.arptable_filter)
return;
arpt_unregister_table(net, net->ipv4.arptable_filter, arpfilter_ops);
net->ipv4.arptable_filter = NULL;
}
static struct pernet_operations arptable_filter_net_ops = {
.exit = arptable_filter_net_exit,
};
static int __init arptable_filter_init(void)
{
int ret;
arpfilter_ops = xt_hook_ops_alloc(&packet_filter, arptable_filter_hook);
if (IS_ERR(arpfilter_ops))
return PTR_ERR(arpfilter_ops);
ret = register_pernet_subsys(&arptable_filter_net_ops);
if (ret < 0) {
kfree(arpfilter_ops);
return ret;
}
ret = arptable_filter_table_init(&init_net);
if (ret) {
unregister_pernet_subsys(&arptable_filter_net_ops);
kfree(arpfilter_ops);
}
return ret;
}
static void __exit arptable_filter_fini(void)
{
unregister_pernet_subsys(&arptable_filter_net_ops);
kfree(arpfilter_ops);
}
module_init(arptable_filter_init);
module_exit(arptable_filter_fini);
File diff suppressed because it is too large. Load diff
+912
View File
@@ -0,0 +1,912 @@
/* Cluster IP hashmark target
* (C) 2003-2004 by Harald Welte <laforge@netfilter.org>
* based on ideas of Fabio Olive Leite <olive@unixforge.org>
*
* Development of this code funded by SuSE Linux AG, http://www.suse.com/
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/jhash.h>
#include <linux/bitops.h>
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/icmp.h>
#include <linux/if_arp.h>
#include <linux/seq_file.h>
#include <linux/refcount.h>
#include <linux/netfilter_arp.h>
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter_ipv4/ip_tables.h>
#include <linux/netfilter_ipv4/ipt_CLUSTERIP.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/checksum.h>
#include <net/ip.h>
#define CLUSTERIP_VERSION "0.8"
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>");
MODULE_DESCRIPTION("Xtables: CLUSTERIP target");
struct clusterip_config {
struct list_head list; /* list of all configs */
refcount_t refcount; /* reference count */
refcount_t entries; /* number of entries/rules
* referencing us */
__be32 clusterip; /* the IP address */
u_int8_t clustermac[ETH_ALEN]; /* the MAC address */
int ifindex; /* device ifindex */
u_int16_t num_total_nodes; /* total number of nodes */
unsigned long local_nodes; /* node number array */
#ifdef CONFIG_PROC_FS
struct proc_dir_entry *pde; /* proc dir entry */
#endif
enum clusterip_hashmode hash_mode; /* which hashing mode */
u_int32_t hash_initval; /* hash initialization */
struct rcu_head rcu; /* for call_rcu_bh */
struct net *net; /* netns for pernet list */
char ifname[IFNAMSIZ]; /* device ifname */
};
#ifdef CONFIG_PROC_FS
static const struct file_operations clusterip_proc_fops;
#endif
struct clusterip_net {
struct list_head configs;
/* lock protects the configs list */
spinlock_t lock;
#ifdef CONFIG_PROC_FS
struct proc_dir_entry *procdir;
/* mutex protects the config->pde*/
struct mutex mutex;
#endif
};
static unsigned int clusterip_net_id __read_mostly;
static inline struct clusterip_net *clusterip_pernet(struct net *net)
{
return net_generic(net, clusterip_net_id);
}
static inline void
clusterip_config_get(struct clusterip_config *c)
{
refcount_inc(&c->refcount);
}
static void clusterip_config_rcu_free(struct rcu_head *head)
{
struct clusterip_config *config;
struct net_device *dev;
config = container_of(head, struct clusterip_config, rcu);
dev = dev_get_by_name(config->net, config->ifname);
if (dev) {
dev_mc_del(dev, config->clustermac);
dev_put(dev);
}
kfree(config);
}
static inline void
clusterip_config_put(struct clusterip_config *c)
{
if (refcount_dec_and_test(&c->refcount))
call_rcu_bh(&c->rcu, clusterip_config_rcu_free);
}
/* decrease the count of entries using/referencing this config. If last
* entry(rule) is removed, remove the config from lists, but don't free it
* yet, since proc-files could still be holding references */
static inline void
clusterip_config_entry_put(struct clusterip_config *c)
{
struct clusterip_net *cn = clusterip_pernet(c->net);
local_bh_disable();
if (refcount_dec_and_lock(&c->entries, &cn->lock)) {
list_del_rcu(&c->list);
spin_unlock(&cn->lock);
local_bh_enable();
/* In case anyone still accesses the file, the open/close
* functions are also incrementing the refcount on their own,
* so it's safe to remove the entry even if it's in use. */
#ifdef CONFIG_PROC_FS
mutex_lock(&cn->mutex);
if (cn->procdir)
proc_remove(c->pde);
mutex_unlock(&cn->mutex);
#endif
return;
}
local_bh_enable();
}
static struct clusterip_config *
__clusterip_config_find(struct net *net, __be32 clusterip)
{
struct clusterip_config *c;
struct clusterip_net *cn = clusterip_pernet(net);
list_for_each_entry_rcu(c, &cn->configs, list) {
if (c->clusterip == clusterip)
return c;
}
return NULL;
}
static inline struct clusterip_config *
clusterip_config_find_get(struct net *net, __be32 clusterip, int entry)
{
struct clusterip_config *c;
rcu_read_lock_bh();
c = __clusterip_config_find(net, clusterip);
if (c) {
#ifdef CONFIG_PROC_FS
if (!c->pde)
c = NULL;
else
#endif
if (unlikely(!refcount_inc_not_zero(&c->refcount)))
c = NULL;
else if (entry) {
if (unlikely(!refcount_inc_not_zero(&c->entries))) {
clusterip_config_put(c);
c = NULL;
}
}
}
rcu_read_unlock_bh();
return c;
}
static void
clusterip_config_init_nodelist(struct clusterip_config *c,
const struct ipt_clusterip_tgt_info *i)
{
int n;
for (n = 0; n < i->num_local_nodes; n++)
set_bit(i->local_nodes[n] - 1, &c->local_nodes);
}
static int
clusterip_netdev_event(struct notifier_block *this, unsigned long event,
void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net *net = dev_net(dev);
struct clusterip_net *cn = clusterip_pernet(net);
struct clusterip_config *c;
spin_lock_bh(&cn->lock);
list_for_each_entry_rcu(c, &cn->configs, list) {
switch (event) {
case NETDEV_REGISTER:
if (!strcmp(dev->name, c->ifname)) {
c->ifindex = dev->ifindex;
dev_mc_add(dev, c->clustermac);
}
break;
case NETDEV_UNREGISTER:
if (dev->ifindex == c->ifindex) {
dev_mc_del(dev, c->clustermac);
c->ifindex = -1;
}
break;
case NETDEV_CHANGENAME:
if (!strcmp(dev->name, c->ifname)) {
c->ifindex = dev->ifindex;
dev_mc_add(dev, c->clustermac);
} else if (dev->ifindex == c->ifindex) {
dev_mc_del(dev, c->clustermac);
c->ifindex = -1;
}
break;
}
}
spin_unlock_bh(&cn->lock);
return NOTIFY_DONE;
}
static struct clusterip_config *
clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i,
__be32 ip, const char *iniface)
{
struct clusterip_net *cn = clusterip_pernet(net);
struct clusterip_config *c;
struct net_device *dev;
int err;
if (iniface[0] == '\0') {
pr_info("Please specify an interface name\n");
return ERR_PTR(-EINVAL);
}
c = kzalloc(sizeof(*c), GFP_ATOMIC);
if (!c)
return ERR_PTR(-ENOMEM);
dev = dev_get_by_name(net, iniface);
if (!dev) {
pr_info("no such interface %s\n", iniface);
kfree(c);
return ERR_PTR(-ENOENT);
}
c->ifindex = dev->ifindex;
strcpy(c->ifname, dev->name);
memcpy(&c->clustermac, &i->clustermac, ETH_ALEN);
dev_mc_add(dev, c->clustermac);
dev_put(dev);
c->clusterip = ip;
c->num_total_nodes = i->num_total_nodes;
clusterip_config_init_nodelist(c, i);
c->hash_mode = i->hash_mode;
c->hash_initval = i->hash_initval;
c->net = net;
refcount_set(&c->refcount, 1);
spin_lock_bh(&cn->lock);
if (__clusterip_config_find(net, ip)) {
err = -EBUSY;
goto out_config_put;
}
list_add_rcu(&c->list, &cn->configs);
spin_unlock_bh(&cn->lock);
#ifdef CONFIG_PROC_FS
{
char buffer[16];
/* create proc dir entry */
sprintf(buffer, "%pI4", &ip);
mutex_lock(&cn->mutex);
c->pde = proc_create_data(buffer, 0600,
cn->procdir,
&clusterip_proc_fops, c);
mutex_unlock(&cn->mutex);
if (!c->pde) {
err = -ENOMEM;
goto err;
}
}
#endif
refcount_set(&c->entries, 1);
return c;
#ifdef CONFIG_PROC_FS
err:
#endif
spin_lock_bh(&cn->lock);
list_del_rcu(&c->list);
out_config_put:
spin_unlock_bh(&cn->lock);
clusterip_config_put(c);
return ERR_PTR(err);
}
#ifdef CONFIG_PROC_FS
static int
clusterip_add_node(struct clusterip_config *c, u_int16_t nodenum)
{
if (nodenum == 0 ||
nodenum > c->num_total_nodes)
return 1;
/* check if we already have this number in our bitfield */
if (test_and_set_bit(nodenum - 1, &c->local_nodes))
return 1;
return 0;
}
static bool
clusterip_del_node(struct clusterip_config *c, u_int16_t nodenum)
{
if (nodenum == 0 ||
nodenum > c->num_total_nodes)
return true;
if (test_and_clear_bit(nodenum - 1, &c->local_nodes))
return false;
return true;
}
#endif
static inline u_int32_t
clusterip_hashfn(const struct sk_buff *skb,
const struct clusterip_config *config)
{
const struct iphdr *iph = ip_hdr(skb);
unsigned long hashval;
u_int16_t sport = 0, dport = 0;
int poff;
poff = proto_ports_offset(iph->protocol);
if (poff >= 0) {
const u_int16_t *ports;
u16 _ports[2];
ports = skb_header_pointer(skb, iph->ihl * 4 + poff, 4, _ports);
if (ports) {
sport = ports[0];
dport = ports[1];
}
} else {
net_info_ratelimited("unknown protocol %u\n", iph->protocol);
}
switch (config->hash_mode) {
case CLUSTERIP_HASHMODE_SIP:
hashval = jhash_1word(ntohl(iph->saddr),
config->hash_initval);
break;
case CLUSTERIP_HASHMODE_SIP_SPT:
hashval = jhash_2words(ntohl(iph->saddr), sport,
config->hash_initval);
break;
case CLUSTERIP_HASHMODE_SIP_SPT_DPT:
hashval = jhash_3words(ntohl(iph->saddr), sport, dport,
config->hash_initval);
break;
default:
/* to make gcc happy */
hashval = 0;
/* This cannot happen, unless the check function wasn't called
* at rule load time */
pr_info("unknown mode %u\n", config->hash_mode);
BUG();
break;
}
/* node numbers are 1..n, not 0..n */
return reciprocal_scale(hashval, config->num_total_nodes) + 1;
}
static inline int
clusterip_responsible(const struct clusterip_config *config, u_int32_t hash)
{
return test_bit(hash - 1, &config->local_nodes);
}
/***********************************************************************
* IPTABLES TARGET
***********************************************************************/
static unsigned int
clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct ipt_clusterip_tgt_info *cipinfo = par->targinfo;
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
u_int32_t hash;
/* don't need to clusterip_config_get() here, since refcount
* is only decremented by destroy() - and ip_tables guarantees
* that the ->target() function isn't called after ->destroy() */
ct = nf_ct_get(skb, &ctinfo);
if (ct == NULL)
return NF_DROP;
/* special case: ICMP error handling. conntrack distinguishes between
* error messages (RELATED) and information requests (see below) */
if (ip_hdr(skb)->protocol == IPPROTO_ICMP &&
(ctinfo == IP_CT_RELATED ||
ctinfo == IP_CT_RELATED_REPLY))
return XT_CONTINUE;
/* ip_conntrack_icmp guarantees us that we only have ICMP_ECHO,
* TIMESTAMP, INFO_REQUEST or ADDRESS type icmp packets from here
* on, which all have an ID field [relevant for hashing]. */
hash = clusterip_hashfn(skb, cipinfo->config);
switch (ctinfo) {
case IP_CT_NEW:
ct->mark = hash;
break;
case IP_CT_RELATED:
case IP_CT_RELATED_REPLY:
/* FIXME: we don't handle expectations at the moment.
* They can arrive on a different node than
* the master connection (e.g. FTP passive mode) */
case IP_CT_ESTABLISHED:
case IP_CT_ESTABLISHED_REPLY:
break;
default: /* Prevent gcc warnings */
break;
}
#ifdef DEBUG
nf_ct_dump_tuple_ip(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
#endif
pr_debug("hash=%u ct_hash=%u ", hash, ct->mark);
if (!clusterip_responsible(cipinfo->config, hash)) {
pr_debug("not responsible\n");
return NF_DROP;
}
pr_debug("responsible\n");
/* despite being received via linklayer multicast, this is
* actually a unicast IP packet. TCP doesn't like PACKET_MULTICAST */
skb->pkt_type = PACKET_HOST;
return XT_CONTINUE;
}
static int clusterip_tg_check(const struct xt_tgchk_param *par)
{
struct ipt_clusterip_tgt_info *cipinfo = par->targinfo;
const struct ipt_entry *e = par->entryinfo;
struct clusterip_config *config;
int ret, i;
if (par->nft_compat) {
pr_err("cannot use CLUSTERIP target from nftables compat\n");
return -EOPNOTSUPP;
}
if (cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP &&
cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP_SPT &&
cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP_SPT_DPT) {
pr_info("unknown mode %u\n", cipinfo->hash_mode);
return -EINVAL;
}
if (e->ip.dmsk.s_addr != htonl(0xffffffff) ||
e->ip.dst.s_addr == 0) {
pr_info("Please specify destination IP\n");
return -EINVAL;
}
if (cipinfo->num_local_nodes > ARRAY_SIZE(cipinfo->local_nodes)) {
pr_info("bad num_local_nodes %u\n", cipinfo->num_local_nodes);
return -EINVAL;
}
for (i = 0; i < cipinfo->num_local_nodes; i++) {
if (cipinfo->local_nodes[i] - 1 >=
sizeof(config->local_nodes) * 8) {
pr_info("bad local_nodes[%d] %u\n",
i, cipinfo->local_nodes[i]);
return -EINVAL;
}
}
config = clusterip_config_find_get(par->net, e->ip.dst.s_addr, 1);
if (!config) {
if (!(cipinfo->flags & CLUSTERIP_FLAG_NEW)) {
pr_info("no config found for %pI4, need 'new'\n",
&e->ip.dst.s_addr);
return -EINVAL;
} else {
config = clusterip_config_init(par->net, cipinfo,
e->ip.dst.s_addr,
e->ip.iniface);
if (IS_ERR(config))
return PTR_ERR(config);
}
} else if (memcmp(&config->clustermac, &cipinfo->clustermac, ETH_ALEN))
return -EINVAL;
ret = nf_ct_netns_get(par->net, par->family);
if (ret < 0) {
pr_info("cannot load conntrack support for proto=%u\n",
par->family);
clusterip_config_entry_put(config);
clusterip_config_put(config);
return ret;
}
if (!par->net->xt.clusterip_deprecated_warning) {
pr_info("ipt_CLUSTERIP is deprecated and it will removed soon, "
"use xt_cluster instead\n");
par->net->xt.clusterip_deprecated_warning = true;
}
cipinfo->config = config;
return ret;
}
/* drop reference count of cluster config when rule is deleted */
static void clusterip_tg_destroy(const struct xt_tgdtor_param *par)
{
const struct ipt_clusterip_tgt_info *cipinfo = par->targinfo;
/* if no more entries are referencing the config, remove it
* from the list and destroy the proc entry */
clusterip_config_entry_put(cipinfo->config);
clusterip_config_put(cipinfo->config);
nf_ct_netns_put(par->net, par->family);
}
#ifdef CONFIG_COMPAT
struct compat_ipt_clusterip_tgt_info
{
u_int32_t flags;
u_int8_t clustermac[6];
u_int16_t num_total_nodes;
u_int16_t num_local_nodes;
u_int16_t local_nodes[CLUSTERIP_MAX_NODES];
u_int32_t hash_mode;
u_int32_t hash_initval;
compat_uptr_t config;
};
#endif /* CONFIG_COMPAT */
static struct xt_target clusterip_tg_reg __read_mostly = {
.name = "CLUSTERIP",
.family = NFPROTO_IPV4,
.target = clusterip_tg,
.checkentry = clusterip_tg_check,
.destroy = clusterip_tg_destroy,
.targetsize = sizeof(struct ipt_clusterip_tgt_info),
.usersize = offsetof(struct ipt_clusterip_tgt_info, config),
#ifdef CONFIG_COMPAT
.compatsize = sizeof(struct compat_ipt_clusterip_tgt_info),
#endif /* CONFIG_COMPAT */
.me = THIS_MODULE
};
/***********************************************************************
* ARP MANGLING CODE
***********************************************************************/
/* hardcoded for 48bit ethernet and 32bit ipv4 addresses */
struct arp_payload {
u_int8_t src_hw[ETH_ALEN];
__be32 src_ip;
u_int8_t dst_hw[ETH_ALEN];
__be32 dst_ip;
} __packed;
#ifdef DEBUG
static void arp_print(struct arp_payload *payload)
{
#define HBUFFERLEN 30
char hbuffer[HBUFFERLEN];
int j, k;
for (k = 0, j = 0; k < HBUFFERLEN - 3 && j < ETH_ALEN; j++) {
hbuffer[k++] = hex_asc_hi(payload->src_hw[j]);
hbuffer[k++] = hex_asc_lo(payload->src_hw[j]);
hbuffer[k++] = ':';
}
hbuffer[--k] = '\0';
pr_debug("src %pI4@%s, dst %pI4\n",
&payload->src_ip, hbuffer, &payload->dst_ip);
}
#endif
static unsigned int
arp_mangle(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
struct arphdr *arp = arp_hdr(skb);
struct arp_payload *payload;
struct clusterip_config *c;
struct net *net = state->net;
/* we don't care about non-ethernet and non-ipv4 ARP */
if (arp->ar_hrd != htons(ARPHRD_ETHER) ||
arp->ar_pro != htons(ETH_P_IP) ||
arp->ar_pln != 4 || arp->ar_hln != ETH_ALEN)
return NF_ACCEPT;
/* we only want to mangle arp requests and replies */
if (arp->ar_op != htons(ARPOP_REPLY) &&
arp->ar_op != htons(ARPOP_REQUEST))
return NF_ACCEPT;
payload = (void *)(arp+1);
/* if there is no clusterip configuration for the arp reply's
* source ip, we don't want to mangle it */
c = clusterip_config_find_get(net, payload->src_ip, 0);
if (!c)
return NF_ACCEPT;
/* normally the linux kernel always replies to arp queries of
* addresses on different interfacs. However, in the CLUSTERIP case
* this wouldn't work, since we didn't subscribe the mcast group on
* other interfaces */
if (c->ifindex != state->out->ifindex) {
pr_debug("not mangling arp reply on different interface: cip'%d'-skb'%d'\n",
c->ifindex, state->out->ifindex);
clusterip_config_put(c);
return NF_ACCEPT;
}
/* mangle reply hardware address */
memcpy(payload->src_hw, c->clustermac, arp->ar_hln);
#ifdef DEBUG
pr_debug("mangled arp reply: ");
arp_print(payload);
#endif
clusterip_config_put(c);
return NF_ACCEPT;
}
static const struct nf_hook_ops cip_arp_ops = {
.hook = arp_mangle,
.pf = NFPROTO_ARP,
.hooknum = NF_ARP_OUT,
.priority = -1
};
/***********************************************************************
* PROC DIR HANDLING
***********************************************************************/
#ifdef CONFIG_PROC_FS
struct clusterip_seq_position {
unsigned int pos; /* position */
unsigned int weight; /* number of bits set == size */
unsigned int bit; /* current bit */
unsigned long val; /* current value */
};
static void *clusterip_seq_start(struct seq_file *s, loff_t *pos)
{
struct clusterip_config *c = s->private;
unsigned int weight;
u_int32_t local_nodes;
struct clusterip_seq_position *idx;
/* FIXME: possible race */
local_nodes = c->local_nodes;
weight = hweight32(local_nodes);
if (*pos >= weight)
return NULL;
idx = kmalloc(sizeof(struct clusterip_seq_position), GFP_KERNEL);
if (!idx)
return ERR_PTR(-ENOMEM);
idx->pos = *pos;
idx->weight = weight;
idx->bit = ffs(local_nodes);
idx->val = local_nodes;
clear_bit(idx->bit - 1, &idx->val);
return idx;
}
static void *clusterip_seq_next(struct seq_file *s, void *v, loff_t *pos)
{
struct clusterip_seq_position *idx = v;
*pos = ++idx->pos;
if (*pos >= idx->weight) {
kfree(v);
return NULL;
}
idx->bit = ffs(idx->val);
clear_bit(idx->bit - 1, &idx->val);
return idx;
}
static void clusterip_seq_stop(struct seq_file *s, void *v)
{
if (!IS_ERR(v))
kfree(v);
}
static int clusterip_seq_show(struct seq_file *s, void *v)
{
struct clusterip_seq_position *idx = v;
if (idx->pos != 0)
seq_putc(s, ',');
seq_printf(s, "%u", idx->bit);
if (idx->pos == idx->weight - 1)
seq_putc(s, '\n');
return 0;
}
static const struct seq_operations clusterip_seq_ops = {
.start = clusterip_seq_start,
.next = clusterip_seq_next,
.stop = clusterip_seq_stop,
.show = clusterip_seq_show,
};
static int clusterip_proc_open(struct inode *inode, struct file *file)
{
int ret = seq_open(file, &clusterip_seq_ops);
if (!ret) {
struct seq_file *sf = file->private_data;
struct clusterip_config *c = PDE_DATA(inode);
sf->private = c;
clusterip_config_get(c);
}
return ret;
}
static int clusterip_proc_release(struct inode *inode, struct file *file)
{
struct clusterip_config *c = PDE_DATA(inode);
int ret;
ret = seq_release(inode, file);
if (!ret)
clusterip_config_put(c);
return ret;
}
static ssize_t clusterip_proc_write(struct file *file, const char __user *input,
size_t size, loff_t *ofs)
{
struct clusterip_config *c = PDE_DATA(file_inode(file));
#define PROC_WRITELEN 10
char buffer[PROC_WRITELEN+1];
unsigned long nodenum;
int rc;
if (size > PROC_WRITELEN)
return -EIO;
if (copy_from_user(buffer, input, size))
return -EFAULT;
buffer[size] = 0;
if (*buffer == '+') {
rc = kstrtoul(buffer+1, 10, &nodenum);
if (rc)
return rc;
if (clusterip_add_node(c, nodenum))
return -ENOMEM;
} else if (*buffer == '-') {
rc = kstrtoul(buffer+1, 10, &nodenum);
if (rc)
return rc;
if (clusterip_del_node(c, nodenum))
return -ENOENT;
} else
return -EIO;
return size;
}
static const struct file_operations clusterip_proc_fops = {
.open = clusterip_proc_open,
.read = seq_read,
.write = clusterip_proc_write,
.llseek = seq_lseek,
.release = clusterip_proc_release,
};
#endif /* CONFIG_PROC_FS */
static int clusterip_net_init(struct net *net)
{
struct clusterip_net *cn = clusterip_pernet(net);
int ret;
INIT_LIST_HEAD(&cn->configs);
spin_lock_init(&cn->lock);
ret = nf_register_net_hook(net, &cip_arp_ops);
if (ret < 0)
return ret;
#ifdef CONFIG_PROC_FS
cn->procdir = proc_mkdir("ipt_CLUSTERIP", net->proc_net);
if (!cn->procdir) {
nf_unregister_net_hook(net, &cip_arp_ops);
pr_err("Unable to proc dir entry\n");
return -ENOMEM;
}
mutex_init(&cn->mutex);
#endif /* CONFIG_PROC_FS */
return 0;
}
static void clusterip_net_exit(struct net *net)
{
#ifdef CONFIG_PROC_FS
struct clusterip_net *cn = clusterip_pernet(net);
mutex_lock(&cn->mutex);
proc_remove(cn->procdir);
cn->procdir = NULL;
mutex_unlock(&cn->mutex);
#endif
nf_unregister_net_hook(net, &cip_arp_ops);
}
static struct pernet_operations clusterip_net_ops = {
.init = clusterip_net_init,
.exit = clusterip_net_exit,
.id = &clusterip_net_id,
.size = sizeof(struct clusterip_net),
};
struct notifier_block cip_netdev_notifier = {
.notifier_call = clusterip_netdev_event
};
static int __init clusterip_tg_init(void)
{
int ret;
ret = register_pernet_subsys(&clusterip_net_ops);
if (ret < 0)
return ret;
ret = xt_register_target(&clusterip_tg_reg);
if (ret < 0)
goto cleanup_subsys;
ret = register_netdevice_notifier(&cip_netdev_notifier);
if (ret < 0)
goto unregister_target;
pr_info("ClusterIP Version %s loaded successfully\n",
CLUSTERIP_VERSION);
return 0;
unregister_target:
xt_unregister_target(&clusterip_tg_reg);
cleanup_subsys:
unregister_pernet_subsys(&clusterip_net_ops);
return ret;
}
static void __exit clusterip_tg_exit(void)
{
pr_info("ClusterIP Version %s unloading\n", CLUSTERIP_VERSION);
unregister_netdevice_notifier(&cip_netdev_notifier);
xt_unregister_target(&clusterip_tg_reg);
unregister_pernet_subsys(&clusterip_net_ops);
/* Wait for completion of call_rcu_bh()'s (clusterip_config_rcu_free) */
rcu_barrier_bh();
}
module_init(clusterip_tg_init);
module_exit(clusterip_tg_exit);
+136
View File
@@ -0,0 +1,136 @@
/* iptables module for the IPv4 and TCP ECN bits, Version 1.5
*
* (C) 2002 by Harald Welte <laforge@netfilter.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/in.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/ip.h>
#include <net/ip.h>
#include <linux/tcp.h>
#include <net/checksum.h>
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter_ipv4/ip_tables.h>
#include <linux/netfilter_ipv4/ipt_ECN.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>");
MODULE_DESCRIPTION("Xtables: Explicit Congestion Notification (ECN) flag modification");
/* set ECT codepoint from IP header.
* return false if there was an error. */
static inline bool
set_ect_ip(struct sk_buff *skb, const struct ipt_ECN_info *einfo)
{
struct iphdr *iph = ip_hdr(skb);
if ((iph->tos & IPT_ECN_IP_MASK) != (einfo->ip_ect & IPT_ECN_IP_MASK)) {
__u8 oldtos;
if (!skb_make_writable(skb, sizeof(struct iphdr)))
return false;
iph = ip_hdr(skb);
oldtos = iph->tos;
iph->tos &= ~IPT_ECN_IP_MASK;
iph->tos |= (einfo->ip_ect & IPT_ECN_IP_MASK);
csum_replace2(&iph->check, htons(oldtos), htons(iph->tos));
}
return true;
}
/* Return false if there was an error. */
static inline bool
set_ect_tcp(struct sk_buff *skb, const struct ipt_ECN_info *einfo)
{
struct tcphdr _tcph, *tcph;
__be16 oldval;
/* Not enough header? */
tcph = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_tcph), &_tcph);
if (!tcph)
return false;
if ((!(einfo->operation & IPT_ECN_OP_SET_ECE) ||
tcph->ece == einfo->proto.tcp.ece) &&
(!(einfo->operation & IPT_ECN_OP_SET_CWR) ||
tcph->cwr == einfo->proto.tcp.cwr))
return true;
if (!skb_make_writable(skb, ip_hdrlen(skb) + sizeof(*tcph)))
return false;
tcph = (void *)ip_hdr(skb) + ip_hdrlen(skb);
oldval = ((__be16 *)tcph)[6];
if (einfo->operation & IPT_ECN_OP_SET_ECE)
tcph->ece = einfo->proto.tcp.ece;
if (einfo->operation & IPT_ECN_OP_SET_CWR)
tcph->cwr = einfo->proto.tcp.cwr;
inet_proto_csum_replace2(&tcph->check, skb,
oldval, ((__be16 *)tcph)[6], false);
return true;
}
static unsigned int
ecn_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct ipt_ECN_info *einfo = par->targinfo;
if (einfo->operation & IPT_ECN_OP_SET_IP)
if (!set_ect_ip(skb, einfo))
return NF_DROP;
if (einfo->operation & (IPT_ECN_OP_SET_ECE | IPT_ECN_OP_SET_CWR) &&
ip_hdr(skb)->protocol == IPPROTO_TCP)
if (!set_ect_tcp(skb, einfo))
return NF_DROP;
return XT_CONTINUE;
}
static int ecn_tg_check(const struct xt_tgchk_param *par)
{
const struct ipt_ECN_info *einfo = par->targinfo;
const struct ipt_entry *e = par->entryinfo;
if (einfo->operation & IPT_ECN_OP_MASK)
return -EINVAL;
if (einfo->ip_ect & ~IPT_ECN_IP_MASK)
return -EINVAL;
if ((einfo->operation & (IPT_ECN_OP_SET_ECE|IPT_ECN_OP_SET_CWR)) &&
(e->ip.proto != IPPROTO_TCP || (e->ip.invflags & XT_INV_PROTO))) {
pr_info_ratelimited("cannot use operation on non-tcp rule\n");
return -EINVAL;
}
return 0;
}
static struct xt_target ecn_tg_reg __read_mostly = {
.name = "ECN",
.family = NFPROTO_IPV4,
.target = ecn_tg,
.targetsize = sizeof(struct ipt_ECN_info),
.table = "mangle",
.checkentry = ecn_tg_check,
.me = THIS_MODULE,
};
static int __init ecn_tg_init(void)
{
return xt_register_target(&ecn_tg_reg);
}
static void __exit ecn_tg_exit(void)
{
xt_unregister_target(&ecn_tg_reg);
}
module_init(ecn_tg_init);
module_exit(ecn_tg_exit);
+101
View File
@@ -0,0 +1,101 @@
/* Masquerade. Simple mapping which alters range to a local IP address
(depending on route). */
/* (C) 1999-2001 Paul `Rusty' Russell
* (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/types.h>
#include <linux/inetdevice.h>
#include <linux/ip.h>
#include <linux/timer.h>
#include <linux/module.h>
#include <linux/netfilter.h>
#include <net/protocol.h>
#include <net/ip.h>
#include <net/checksum.h>
#include <net/route.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter/x_tables.h>
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/ipv4/nf_nat_masquerade.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
MODULE_DESCRIPTION("Xtables: automatic-address SNAT");
/* FIXME: Multiple targets. --RR */
static int masquerade_tg_check(const struct xt_tgchk_param *par)
{
const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
if (mr->range[0].flags & NF_NAT_RANGE_MAP_IPS) {
pr_debug("bad MAP_IPS.\n");
return -EINVAL;
}
if (mr->rangesize != 1) {
pr_debug("bad rangesize %u\n", mr->rangesize);
return -EINVAL;
}
return nf_ct_netns_get(par->net, par->family);
}
static unsigned int
masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
struct nf_nat_range2 range;
const struct nf_nat_ipv4_multi_range_compat *mr;
mr = par->targinfo;
range.flags = mr->range[0].flags;
range.min_proto = mr->range[0].min;
range.max_proto = mr->range[0].max;
return nf_nat_masquerade_ipv4(skb, xt_hooknum(par), &range,
xt_out(par));
}
static void masquerade_tg_destroy(const struct xt_tgdtor_param *par)
{
nf_ct_netns_put(par->net, par->family);
}
static struct xt_target masquerade_tg_reg __read_mostly = {
.name = "MASQUERADE",
.family = NFPROTO_IPV4,
.target = masquerade_tg,
.targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat),
.table = "nat",
.hooks = 1 << NF_INET_POST_ROUTING,
.checkentry = masquerade_tg_check,
.destroy = masquerade_tg_destroy,
.me = THIS_MODULE,
};
static int __init masquerade_tg_init(void)
{
int ret;
ret = xt_register_target(&masquerade_tg_reg);
if (ret)
return ret;
ret = nf_nat_masquerade_ipv4_register_notifier();
if (ret)
xt_unregister_target(&masquerade_tg_reg);
return ret;
}
static void __exit masquerade_tg_exit(void)
{
xt_unregister_target(&masquerade_tg_reg);
nf_nat_masquerade_ipv4_unregister_notifier();
}
module_init(masquerade_tg_init);
module_exit(masquerade_tg_exit);
+113
View File
@@ -0,0 +1,113 @@
/*
* This is a module which is used for rejecting packets.
*/
/* (C) 1999-2001 Paul `Rusty' Russell
* (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/ip.h>
#include <linux/udp.h>
#include <linux/icmp.h>
#include <net/icmp.h>
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter_ipv4/ip_tables.h>
#include <linux/netfilter_ipv4/ipt_REJECT.h>
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
#include <linux/netfilter_bridge.h>
#endif
#include <net/netfilter/ipv4/nf_reject.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
MODULE_DESCRIPTION("Xtables: packet \"rejection\" target for IPv4");
static unsigned int
reject_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct ipt_reject_info *reject = par->targinfo;
int hook = xt_hooknum(par);
switch (reject->with) {
case IPT_ICMP_NET_UNREACHABLE:
nf_send_unreach(skb, ICMP_NET_UNREACH, hook);
break;
case IPT_ICMP_HOST_UNREACHABLE:
nf_send_unreach(skb, ICMP_HOST_UNREACH, hook);
break;
case IPT_ICMP_PROT_UNREACHABLE:
nf_send_unreach(skb, ICMP_PROT_UNREACH, hook);
break;
case IPT_ICMP_PORT_UNREACHABLE:
nf_send_unreach(skb, ICMP_PORT_UNREACH, hook);
break;
case IPT_ICMP_NET_PROHIBITED:
nf_send_unreach(skb, ICMP_NET_ANO, hook);
break;
case IPT_ICMP_HOST_PROHIBITED:
nf_send_unreach(skb, ICMP_HOST_ANO, hook);
break;
case IPT_ICMP_ADMIN_PROHIBITED:
nf_send_unreach(skb, ICMP_PKT_FILTERED, hook);
break;
case IPT_TCP_RESET:
nf_send_reset(xt_net(par), skb, hook);
case IPT_ICMP_ECHOREPLY:
/* Doesn't happen. */
break;
}
return NF_DROP;
}
static int reject_tg_check(const struct xt_tgchk_param *par)
{
const struct ipt_reject_info *rejinfo = par->targinfo;
const struct ipt_entry *e = par->entryinfo;
if (rejinfo->with == IPT_ICMP_ECHOREPLY) {
pr_info_ratelimited("ECHOREPLY no longer supported.\n");
return -EINVAL;
} else if (rejinfo->with == IPT_TCP_RESET) {
/* Must specify that it's a TCP packet */
if (e->ip.proto != IPPROTO_TCP ||
(e->ip.invflags & XT_INV_PROTO)) {
pr_info_ratelimited("TCP_RESET invalid for non-tcp\n");
return -EINVAL;
}
}
return 0;
}
static struct xt_target reject_tg_reg __read_mostly = {
.name = "REJECT",
.family = NFPROTO_IPV4,
.target = reject_tg,
.targetsize = sizeof(struct ipt_reject_info),
.table = "filter",
.hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD) |
(1 << NF_INET_LOCAL_OUT),
.checkentry = reject_tg_check,
.me = THIS_MODULE,
};
static int __init reject_tg_init(void)
{
return xt_register_target(&reject_tg_reg);
}
static void __exit reject_tg_exit(void)
{
xt_unregister_target(&reject_tg_reg);
}
module_init(reject_tg_init);
module_exit(reject_tg_exit);
+504
View File
@@ -0,0 +1,504 @@
/*
* Copyright (c) 2013 Patrick McHardy <kaber@trash.net>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/module.h>
#include <linux/skbuff.h>
#include <net/tcp.h>
#include <linux/netfilter_ipv4/ip_tables.h>
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter/xt_SYNPROXY.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_seqadj.h>
#include <net/netfilter/nf_conntrack_synproxy.h>
#include <net/netfilter/nf_conntrack_ecache.h>
static struct iphdr *
synproxy_build_ip(struct net *net, struct sk_buff *skb, __be32 saddr,
__be32 daddr)
{
struct iphdr *iph;
skb_reset_network_header(skb);
iph = skb_put(skb, sizeof(*iph));
iph->version = 4;
iph->ihl = sizeof(*iph) / 4;
iph->tos = 0;
iph->id = 0;
iph->frag_off = htons(IP_DF);
iph->ttl = net->ipv4.sysctl_ip_default_ttl;
iph->protocol = IPPROTO_TCP;
iph->check = 0;
iph->saddr = saddr;
iph->daddr = daddr;
return iph;
}
static void
synproxy_send_tcp(struct net *net,
const struct sk_buff *skb, struct sk_buff *nskb,
struct nf_conntrack *nfct, enum ip_conntrack_info ctinfo,
struct iphdr *niph, struct tcphdr *nth,
unsigned int tcp_hdr_size)
{
nth->check = ~tcp_v4_check(tcp_hdr_size, niph->saddr, niph->daddr, 0);
nskb->ip_summed = CHECKSUM_PARTIAL;
nskb->csum_start = (unsigned char *)nth - nskb->head;
nskb->csum_offset = offsetof(struct tcphdr, check);
skb_dst_set_noref(nskb, skb_dst(skb));
nskb->protocol = htons(ETH_P_IP);
if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC))
goto free_nskb;
if (nfct) {
nf_ct_set(nskb, (struct nf_conn *)nfct, ctinfo);
nf_conntrack_get(nfct);
}
ip_local_out(net, nskb->sk, nskb);
return;
free_nskb:
kfree_skb(nskb);
}
static void
synproxy_send_client_synack(struct net *net,
const struct sk_buff *skb, const struct tcphdr *th,
const struct synproxy_options *opts)
{
struct sk_buff *nskb;
struct iphdr *iph, *niph;
struct tcphdr *nth;
unsigned int tcp_hdr_size;
u16 mss = opts->mss;
iph = ip_hdr(skb);
tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts);
nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER,
GFP_ATOMIC);
if (nskb == NULL)
return;
skb_reserve(nskb, MAX_TCP_HEADER);
niph = synproxy_build_ip(net, nskb, iph->daddr, iph->saddr);
skb_reset_transport_header(nskb);
nth = skb_put(nskb, tcp_hdr_size);
nth->source = th->dest;
nth->dest = th->source;
nth->seq = htonl(__cookie_v4_init_sequence(iph, th, &mss));
nth->ack_seq = htonl(ntohl(th->seq) + 1);
tcp_flag_word(nth) = TCP_FLAG_SYN | TCP_FLAG_ACK;
if (opts->options & XT_SYNPROXY_OPT_ECN)
tcp_flag_word(nth) |= TCP_FLAG_ECE;
nth->doff = tcp_hdr_size / 4;
nth->window = 0;
nth->check = 0;
nth->urg_ptr = 0;
synproxy_build_options(nth, opts);
synproxy_send_tcp(net, skb, nskb, skb_nfct(skb),
IP_CT_ESTABLISHED_REPLY, niph, nth, tcp_hdr_size);
}
static void
synproxy_send_server_syn(struct net *net,
const struct sk_buff *skb, const struct tcphdr *th,
const struct synproxy_options *opts, u32 recv_seq)
{
struct synproxy_net *snet = synproxy_pernet(net);
struct sk_buff *nskb;
struct iphdr *iph, *niph;
struct tcphdr *nth;
unsigned int tcp_hdr_size;
iph = ip_hdr(skb);
tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts);
nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER,
GFP_ATOMIC);
if (nskb == NULL)
return;
skb_reserve(nskb, MAX_TCP_HEADER);
niph = synproxy_build_ip(net, nskb, iph->saddr, iph->daddr);
skb_reset_transport_header(nskb);
nth = skb_put(nskb, tcp_hdr_size);
nth->source = th->source;
nth->dest = th->dest;
nth->seq = htonl(recv_seq - 1);
/* ack_seq is used to relay our ISN to the synproxy hook to initialize
* sequence number translation once a connection tracking entry exists.
*/
nth->ack_seq = htonl(ntohl(th->ack_seq) - 1);
tcp_flag_word(nth) = TCP_FLAG_SYN;
if (opts->options & XT_SYNPROXY_OPT_ECN)
tcp_flag_word(nth) |= TCP_FLAG_ECE | TCP_FLAG_CWR;
nth->doff = tcp_hdr_size / 4;
nth->window = th->window;
nth->check = 0;
nth->urg_ptr = 0;
synproxy_build_options(nth, opts);
synproxy_send_tcp(net, skb, nskb, &snet->tmpl->ct_general, IP_CT_NEW,
niph, nth, tcp_hdr_size);
}
static void
synproxy_send_server_ack(struct net *net,
const struct ip_ct_tcp *state,
const struct sk_buff *skb, const struct tcphdr *th,
const struct synproxy_options *opts)
{
struct sk_buff *nskb;
struct iphdr *iph, *niph;
struct tcphdr *nth;
unsigned int tcp_hdr_size;
iph = ip_hdr(skb);
tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts);
nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER,
GFP_ATOMIC);
if (nskb == NULL)
return;
skb_reserve(nskb, MAX_TCP_HEADER);
niph = synproxy_build_ip(net, nskb, iph->daddr, iph->saddr);
skb_reset_transport_header(nskb);
nth = skb_put(nskb, tcp_hdr_size);
nth->source = th->dest;
nth->dest = th->source;
nth->seq = htonl(ntohl(th->ack_seq));
nth->ack_seq = htonl(ntohl(th->seq) + 1);
tcp_flag_word(nth) = TCP_FLAG_ACK;
nth->doff = tcp_hdr_size / 4;
nth->window = htons(state->seen[IP_CT_DIR_ORIGINAL].td_maxwin);
nth->check = 0;
nth->urg_ptr = 0;
synproxy_build_options(nth, opts);
synproxy_send_tcp(net, skb, nskb, NULL, 0, niph, nth, tcp_hdr_size);
}
static void
synproxy_send_client_ack(struct net *net,
const struct sk_buff *skb, const struct tcphdr *th,
const struct synproxy_options *opts)
{
struct sk_buff *nskb;
struct iphdr *iph, *niph;
struct tcphdr *nth;
unsigned int tcp_hdr_size;
iph = ip_hdr(skb);
tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts);
nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER,
GFP_ATOMIC);
if (nskb == NULL)
return;
skb_reserve(nskb, MAX_TCP_HEADER);
niph = synproxy_build_ip(net, nskb, iph->saddr, iph->daddr);
skb_reset_transport_header(nskb);
nth = skb_put(nskb, tcp_hdr_size);
nth->source = th->source;
nth->dest = th->dest;
nth->seq = htonl(ntohl(th->seq) + 1);
nth->ack_seq = th->ack_seq;
tcp_flag_word(nth) = TCP_FLAG_ACK;
nth->doff = tcp_hdr_size / 4;
nth->window = htons(ntohs(th->window) >> opts->wscale);
nth->check = 0;
nth->urg_ptr = 0;
synproxy_build_options(nth, opts);
synproxy_send_tcp(net, skb, nskb, skb_nfct(skb),
IP_CT_ESTABLISHED_REPLY, niph, nth, tcp_hdr_size);
}
static bool
synproxy_recv_client_ack(struct net *net,
const struct sk_buff *skb, const struct tcphdr *th,
struct synproxy_options *opts, u32 recv_seq)
{
struct synproxy_net *snet = synproxy_pernet(net);
int mss;
mss = __cookie_v4_check(ip_hdr(skb), th, ntohl(th->ack_seq) - 1);
if (mss == 0) {
this_cpu_inc(snet->stats->cookie_invalid);
return false;
}
this_cpu_inc(snet->stats->cookie_valid);
opts->mss = mss;
opts->options |= XT_SYNPROXY_OPT_MSS;
if (opts->options & XT_SYNPROXY_OPT_TIMESTAMP)
synproxy_check_timestamp_cookie(opts);
synproxy_send_server_syn(net, skb, th, opts, recv_seq);
return true;
}
static unsigned int
synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_synproxy_info *info = par->targinfo;
struct net *net = xt_net(par);
struct synproxy_net *snet = synproxy_pernet(net);
struct synproxy_options opts = {};
struct tcphdr *th, _th;
if (nf_ip_checksum(skb, xt_hooknum(par), par->thoff, IPPROTO_TCP))
return NF_DROP;
th = skb_header_pointer(skb, par->thoff, sizeof(_th), &_th);
if (th == NULL)
return NF_DROP;
if (!synproxy_parse_options(skb, par->thoff, th, &opts))
return NF_DROP;
if (th->syn && !(th->ack || th->fin || th->rst)) {
/* Initial SYN from client */
this_cpu_inc(snet->stats->syn_received);
if (th->ece && th->cwr)
opts.options |= XT_SYNPROXY_OPT_ECN;
opts.options &= info->options;
if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP)
synproxy_init_timestamp_cookie(info, &opts);
else
opts.options &= ~(XT_SYNPROXY_OPT_WSCALE |
XT_SYNPROXY_OPT_SACK_PERM |
XT_SYNPROXY_OPT_ECN);
synproxy_send_client_synack(net, skb, th, &opts);
consume_skb(skb);
return NF_STOLEN;
} else if (th->ack && !(th->fin || th->rst || th->syn)) {
/* ACK from client */
if (synproxy_recv_client_ack(net, skb, th, &opts, ntohl(th->seq))) {
consume_skb(skb);
return NF_STOLEN;
} else {
return NF_DROP;
}
}
return XT_CONTINUE;
}
static unsigned int ipv4_synproxy_hook(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *nhs)
{
struct net *net = nhs->net;
struct synproxy_net *snet = synproxy_pernet(net);
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
struct nf_conn_synproxy *synproxy;
struct synproxy_options opts = {};
const struct ip_ct_tcp *state;
struct tcphdr *th, _th;
unsigned int thoff;
ct = nf_ct_get(skb, &ctinfo);
if (ct == NULL)
return NF_ACCEPT;
synproxy = nfct_synproxy(ct);
if (synproxy == NULL)
return NF_ACCEPT;
if (nf_is_loopback_packet(skb) ||
ip_hdr(skb)->protocol != IPPROTO_TCP)
return NF_ACCEPT;
thoff = ip_hdrlen(skb);
th = skb_header_pointer(skb, thoff, sizeof(_th), &_th);
if (th == NULL)
return NF_DROP;
state = &ct->proto.tcp;
switch (state->state) {
case TCP_CONNTRACK_CLOSE:
if (th->rst && !test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
nf_ct_seqadj_init(ct, ctinfo, synproxy->isn -
ntohl(th->seq) + 1);
break;
}
if (!th->syn || th->ack ||
CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
break;
/* Reopened connection - reset the sequence number and timestamp
* adjustments, they will get initialized once the connection is
* reestablished.
*/
nf_ct_seqadj_init(ct, ctinfo, 0);
synproxy->tsoff = 0;
this_cpu_inc(snet->stats->conn_reopened);
/* fall through */
case TCP_CONNTRACK_SYN_SENT:
if (!synproxy_parse_options(skb, thoff, th, &opts))
return NF_DROP;
if (!th->syn && th->ack &&
CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
/* Keep-Alives are sent with SEG.SEQ = SND.NXT-1,
* therefore we need to add 1 to make the SYN sequence
* number match the one of first SYN.
*/
if (synproxy_recv_client_ack(net, skb, th, &opts,
ntohl(th->seq) + 1)) {
this_cpu_inc(snet->stats->cookie_retrans);
consume_skb(skb);
return NF_STOLEN;
} else {
return NF_DROP;
}
}
synproxy->isn = ntohl(th->ack_seq);
if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP)
synproxy->its = opts.tsecr;
nf_conntrack_event_cache(IPCT_SYNPROXY, ct);
break;
case TCP_CONNTRACK_SYN_RECV:
if (!th->syn || !th->ack)
break;
if (!synproxy_parse_options(skb, thoff, th, &opts))
return NF_DROP;
if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) {
synproxy->tsoff = opts.tsval - synproxy->its;
nf_conntrack_event_cache(IPCT_SYNPROXY, ct);
}
opts.options &= ~(XT_SYNPROXY_OPT_MSS |
XT_SYNPROXY_OPT_WSCALE |
XT_SYNPROXY_OPT_SACK_PERM);
swap(opts.tsval, opts.tsecr);
synproxy_send_server_ack(net, state, skb, th, &opts);
nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - ntohl(th->seq));
nf_conntrack_event_cache(IPCT_SEQADJ, ct);
swap(opts.tsval, opts.tsecr);
synproxy_send_client_ack(net, skb, th, &opts);
consume_skb(skb);
return NF_STOLEN;
default:
break;
}
synproxy_tstamp_adjust(skb, thoff, th, ct, ctinfo, synproxy);
return NF_ACCEPT;
}
static const struct nf_hook_ops ipv4_synproxy_ops[] = {
{
.hook = ipv4_synproxy_hook,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_LOCAL_IN,
.priority = NF_IP_PRI_CONNTRACK_CONFIRM - 1,
},
{
.hook = ipv4_synproxy_hook,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_POST_ROUTING,
.priority = NF_IP_PRI_CONNTRACK_CONFIRM - 1,
},
};
static int synproxy_tg4_check(const struct xt_tgchk_param *par)
{
struct synproxy_net *snet = synproxy_pernet(par->net);
const struct ipt_entry *e = par->entryinfo;
int err;
if (e->ip.proto != IPPROTO_TCP ||
e->ip.invflags & XT_INV_PROTO)
return -EINVAL;
err = nf_ct_netns_get(par->net, par->family);
if (err)
return err;
if (snet->hook_ref4 == 0) {
err = nf_register_net_hooks(par->net, ipv4_synproxy_ops,
ARRAY_SIZE(ipv4_synproxy_ops));
if (err) {
nf_ct_netns_put(par->net, par->family);
return err;
}
}
snet->hook_ref4++;
return err;
}
static void synproxy_tg4_destroy(const struct xt_tgdtor_param *par)
{
struct synproxy_net *snet = synproxy_pernet(par->net);
snet->hook_ref4--;
if (snet->hook_ref4 == 0)
nf_unregister_net_hooks(par->net, ipv4_synproxy_ops,
ARRAY_SIZE(ipv4_synproxy_ops));
nf_ct_netns_put(par->net, par->family);
}
static struct xt_target synproxy_tg4_reg __read_mostly = {
.name = "SYNPROXY",
.family = NFPROTO_IPV4,
.hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD),
.target = synproxy_tg4,
.targetsize = sizeof(struct xt_synproxy_info),
.checkentry = synproxy_tg4_check,
.destroy = synproxy_tg4_destroy,
.me = THIS_MODULE,
};
static int __init synproxy_tg4_init(void)
{
return xt_register_target(&synproxy_tg4_reg);
}
static void __exit synproxy_tg4_exit(void)
{
xt_unregister_target(&synproxy_tg4_reg);
}
module_init(synproxy_tg4_init);
module_exit(synproxy_tg4_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+91
View File
@@ -0,0 +1,91 @@
/* Kernel module to match AH parameters. */
/* (C) 1999-2000 Yon Uriarte <yon@astaro.de>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/in.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/ip.h>
#include <linux/netfilter_ipv4/ipt_ah.h>
#include <linux/netfilter/x_tables.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Yon Uriarte <yon@astaro.de>");
MODULE_DESCRIPTION("Xtables: IPv4 IPsec-AH SPI match");
/* Returns 1 if the spi is matched by the range, 0 otherwise */
static inline bool
spi_match(u_int32_t min, u_int32_t max, u_int32_t spi, bool invert)
{
bool r;
pr_debug("spi_match:%c 0x%x <= 0x%x <= 0x%x\n",
invert ? '!' : ' ', min, spi, max);
r = (spi >= min && spi <= max) ^ invert;
pr_debug(" result %s\n", r ? "PASS" : "FAILED");
return r;
}
static bool ah_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
struct ip_auth_hdr _ahdr;
const struct ip_auth_hdr *ah;
const struct ipt_ah *ahinfo = par->matchinfo;
/* Must not be a fragment. */
if (par->fragoff != 0)
return false;
ah = skb_header_pointer(skb, par->thoff, sizeof(_ahdr), &_ahdr);
if (ah == NULL) {
/* We've been asked to examine this packet, and we
* can't. Hence, no choice but to drop.
*/
pr_debug("Dropping evil AH tinygram.\n");
par->hotdrop = true;
return false;
}
return spi_match(ahinfo->spis[0], ahinfo->spis[1],
ntohl(ah->spi),
!!(ahinfo->invflags & IPT_AH_INV_SPI));
}
static int ah_mt_check(const struct xt_mtchk_param *par)
{
const struct ipt_ah *ahinfo = par->matchinfo;
/* Must specify no unknown invflags */
if (ahinfo->invflags & ~IPT_AH_INV_MASK) {
pr_debug("unknown flags %X\n", ahinfo->invflags);
return -EINVAL;
}
return 0;
}
static struct xt_match ah_mt_reg __read_mostly = {
.name = "ah",
.family = NFPROTO_IPV4,
.match = ah_mt,
.matchsize = sizeof(struct ipt_ah),
.proto = IPPROTO_AH,
.checkentry = ah_mt_check,
.me = THIS_MODULE,
};
static int __init ah_mt_init(void)
{
return xt_register_match(&ah_mt_reg);
}
static void __exit ah_mt_exit(void)
{
xt_unregister_match(&ah_mt_reg);
}
module_init(ah_mt_init);
module_exit(ah_mt_exit);
+144
View File
@@ -0,0 +1,144 @@
/*
* Copyright (c) 2011 Florian Westphal <fw@strlen.de>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* based on fib_frontend.c; Author: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/ip.h>
#include <net/ip.h>
#include <net/ip_fib.h>
#include <net/route.h>
#include <linux/netfilter/xt_rpfilter.h>
#include <linux/netfilter/x_tables.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
MODULE_DESCRIPTION("iptables: ipv4 reverse path filter match");
/* don't try to find route from mcast/bcast/zeronet */
static __be32 rpfilter_get_saddr(__be32 addr)
{
if (ipv4_is_multicast(addr) || ipv4_is_lbcast(addr) ||
ipv4_is_zeronet(addr))
return 0;
return addr;
}
static bool rpfilter_lookup_reverse(struct net *net, struct flowi4 *fl4,
const struct net_device *dev, u8 flags)
{
struct fib_result res;
bool dev_match;
int ret __maybe_unused;
if (fib_lookup(net, fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE))
return false;
if (res.type != RTN_UNICAST) {
if (res.type != RTN_LOCAL || !(flags & XT_RPFILTER_ACCEPT_LOCAL))
return false;
}
dev_match = false;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
for (ret = 0; ret < res.fi->fib_nhs; ret++) {
struct fib_nh *nh = &res.fi->fib_nh[ret];
if (nh->nh_dev == dev) {
dev_match = true;
break;
}
}
#else
if (FIB_RES_DEV(res) == dev)
dev_match = true;
#endif
return dev_match || flags & XT_RPFILTER_LOOSE;
}
static bool
rpfilter_is_loopback(const struct sk_buff *skb, const struct net_device *in)
{
return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK;
}
static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct xt_rpfilter_info *info;
const struct iphdr *iph;
struct flowi4 flow;
bool invert;
info = par->matchinfo;
invert = info->flags & XT_RPFILTER_INVERT;
if (rpfilter_is_loopback(skb, xt_in(par)))
return true ^ invert;
iph = ip_hdr(skb);
if (ipv4_is_zeronet(iph->saddr)) {
if (ipv4_is_lbcast(iph->daddr) ||
ipv4_is_local_multicast(iph->daddr))
return true ^ invert;
}
memset(&flow, 0, sizeof(flow));
flow.flowi4_iif = LOOPBACK_IFINDEX;
flow.daddr = iph->saddr;
flow.saddr = rpfilter_get_saddr(iph->daddr);
flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0;
flow.flowi4_tos = iph->tos & IPTOS_RT_MASK;
flow.flowi4_scope = RT_SCOPE_UNIVERSE;
flow.flowi4_oif = l3mdev_master_ifindex_rcu(xt_in(par));
return rpfilter_lookup_reverse(xt_net(par), &flow, xt_in(par), info->flags) ^ invert;
}
static int rpfilter_check(const struct xt_mtchk_param *par)
{
const struct xt_rpfilter_info *info = par->matchinfo;
unsigned int options = ~XT_RPFILTER_OPTION_MASK;
if (info->flags & options) {
pr_info_ratelimited("unknown options\n");
return -EINVAL;
}
if (strcmp(par->table, "mangle") != 0 &&
strcmp(par->table, "raw") != 0) {
pr_info_ratelimited("only valid in \'raw\' or \'mangle\' table, not \'%s\'\n",
par->table);
return -EINVAL;
}
return 0;
}
static struct xt_match rpfilter_mt_reg __read_mostly = {
.name = "rpfilter",
.family = NFPROTO_IPV4,
.checkentry = rpfilter_check,
.match = rpfilter_mt,
.matchsize = sizeof(struct xt_rpfilter_info),
.hooks = (1 << NF_INET_PRE_ROUTING),
.me = THIS_MODULE
};
static int __init rpfilter_mt_init(void)
{
return xt_register_match(&rpfilter_mt_reg);
}
static void __exit rpfilter_mt_exit(void)
{
xt_unregister_match(&rpfilter_mt_reg);
}
module_init(rpfilter_mt_init);
module_exit(rpfilter_mt_exit);
+114
View File
@@ -0,0 +1,114 @@
/*
* This is the 1999 rewrite of IP Firewalling, aiming for kernel 2.3.x.
*
* Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling
* Copyright (C) 2000-2004 Netfilter Core Team <coreteam@netfilter.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
*/
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/netfilter_ipv4/ip_tables.h>
#include <linux/slab.h>
#include <net/ip.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
MODULE_DESCRIPTION("iptables filter table");
#define FILTER_VALID_HOOKS ((1 << NF_INET_LOCAL_IN) | \
(1 << NF_INET_FORWARD) | \
(1 << NF_INET_LOCAL_OUT))
static int __net_init iptable_filter_table_init(struct net *net);
static const struct xt_table packet_filter = {
.name = "filter",
.valid_hooks = FILTER_VALID_HOOKS,
.me = THIS_MODULE,
.af = NFPROTO_IPV4,
.priority = NF_IP_PRI_FILTER,
.table_init = iptable_filter_table_init,
};
static unsigned int
iptable_filter_hook(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
return ipt_do_table(skb, state, state->net->ipv4.iptable_filter);
}
static struct nf_hook_ops *filter_ops __read_mostly;
/* Default to forward because I got too much mail already. */
static bool forward __read_mostly = true;
module_param(forward, bool, 0000);
static int __net_init iptable_filter_table_init(struct net *net)
{
struct ipt_replace *repl;
int err;
if (net->ipv4.iptable_filter)
return 0;
repl = ipt_alloc_initial_table(&packet_filter);
if (repl == NULL)
return -ENOMEM;
/* Entry 1 is the FORWARD hook */
((struct ipt_standard *)repl->entries)[1].target.verdict =
forward ? -NF_ACCEPT - 1 : -NF_DROP - 1;
err = ipt_register_table(net, &packet_filter, repl, filter_ops,
&net->ipv4.iptable_filter);
kfree(repl);
return err;
}
static int __net_init iptable_filter_net_init(struct net *net)
{
if (net == &init_net || !forward)
return iptable_filter_table_init(net);
return 0;
}
static void __net_exit iptable_filter_net_exit(struct net *net)
{
if (!net->ipv4.iptable_filter)
return;
ipt_unregister_table(net, net->ipv4.iptable_filter, filter_ops);
net->ipv4.iptable_filter = NULL;
}
static struct pernet_operations iptable_filter_net_ops = {
.init = iptable_filter_net_init,
.exit = iptable_filter_net_exit,
};
static int __init iptable_filter_init(void)
{
int ret;
filter_ops = xt_hook_ops_alloc(&packet_filter, iptable_filter_hook);
if (IS_ERR(filter_ops))
return PTR_ERR(filter_ops);
ret = register_pernet_subsys(&iptable_filter_net_ops);
if (ret < 0)
kfree(filter_ops);
return ret;
}
static void __exit iptable_filter_fini(void)
{
unregister_pernet_subsys(&iptable_filter_net_ops);
kfree(filter_ops);
}
module_init(iptable_filter_init);
module_exit(iptable_filter_fini);
+150
View File
@@ -0,0 +1,150 @@
/*
* This is the 1999 rewrite of IP Firewalling, aiming for kernel 2.3.x.
*
* Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling
* Copyright (C) 2000-2004 Netfilter Core Team <coreteam@netfilter.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/module.h>
#include <linux/netfilter_ipv4/ip_tables.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <net/sock.h>
#include <net/route.h>
#include <linux/ip.h>
#include <net/ip.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
MODULE_DESCRIPTION("iptables mangle table");
#define MANGLE_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | \
(1 << NF_INET_LOCAL_IN) | \
(1 << NF_INET_FORWARD) | \
(1 << NF_INET_LOCAL_OUT) | \
(1 << NF_INET_POST_ROUTING))
static int __net_init iptable_mangle_table_init(struct net *net);
static const struct xt_table packet_mangler = {
.name = "mangle",
.valid_hooks = MANGLE_VALID_HOOKS,
.me = THIS_MODULE,
.af = NFPROTO_IPV4,
.priority = NF_IP_PRI_MANGLE,
.table_init = iptable_mangle_table_init,
};
static unsigned int
ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state)
{
unsigned int ret;
const struct iphdr *iph;
u_int8_t tos;
__be32 saddr, daddr;
u_int32_t mark;
int err;
/* Save things which could affect route */
mark = skb->mark;
iph = ip_hdr(skb);
saddr = iph->saddr;
daddr = iph->daddr;
tos = iph->tos;
ret = ipt_do_table(skb, state, state->net->ipv4.iptable_mangle);
/* Reroute for ANY change. */
if (ret != NF_DROP && ret != NF_STOLEN) {
iph = ip_hdr(skb);
if (iph->saddr != saddr ||
iph->daddr != daddr ||
skb->mark != mark ||
iph->tos != tos) {
err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
if (err < 0)
ret = NF_DROP_ERR(err);
}
}
return ret;
}
/* The work comes in here from netfilter.c. */
static unsigned int
iptable_mangle_hook(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
if (state->hook == NF_INET_LOCAL_OUT)
return ipt_mangle_out(skb, state);
return ipt_do_table(skb, state, state->net->ipv4.iptable_mangle);
}
static struct nf_hook_ops *mangle_ops __read_mostly;
static int __net_init iptable_mangle_table_init(struct net *net)
{
struct ipt_replace *repl;
int ret;
if (net->ipv4.iptable_mangle)
return 0;
repl = ipt_alloc_initial_table(&packet_mangler);
if (repl == NULL)
return -ENOMEM;
ret = ipt_register_table(net, &packet_mangler, repl, mangle_ops,
&net->ipv4.iptable_mangle);
kfree(repl);
return ret;
}
static void __net_exit iptable_mangle_net_exit(struct net *net)
{
if (!net->ipv4.iptable_mangle)
return;
ipt_unregister_table(net, net->ipv4.iptable_mangle, mangle_ops);
net->ipv4.iptable_mangle = NULL;
}
static struct pernet_operations iptable_mangle_net_ops = {
.exit = iptable_mangle_net_exit,
};
static int __init iptable_mangle_init(void)
{
int ret;
mangle_ops = xt_hook_ops_alloc(&packet_mangler, iptable_mangle_hook);
if (IS_ERR(mangle_ops)) {
ret = PTR_ERR(mangle_ops);
return ret;
}
ret = register_pernet_subsys(&iptable_mangle_net_ops);
if (ret < 0) {
kfree(mangle_ops);
return ret;
}
ret = iptable_mangle_table_init(&init_net);
if (ret) {
unregister_pernet_subsys(&iptable_mangle_net_ops);
kfree(mangle_ops);
}
return ret;
}
static void __exit iptable_mangle_fini(void)
{
unregister_pernet_subsys(&iptable_mangle_net_ops);
kfree(mangle_ops);
}
module_init(iptable_mangle_init);
module_exit(iptable_mangle_fini);
+155
View File
@@ -0,0 +1,155 @@
/* (C) 1999-2001 Paul `Rusty' Russell
* (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
* (C) 2011 Patrick McHardy <kaber@trash.net>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/module.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_ipv4/ip_tables.h>
#include <linux/ip.h>
#include <net/ip.h>
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_nat_l3proto.h>
static int __net_init iptable_nat_table_init(struct net *net);
static const struct xt_table nf_nat_ipv4_table = {
.name = "nat",
.valid_hooks = (1 << NF_INET_PRE_ROUTING) |
(1 << NF_INET_POST_ROUTING) |
(1 << NF_INET_LOCAL_OUT) |
(1 << NF_INET_LOCAL_IN),
.me = THIS_MODULE,
.af = NFPROTO_IPV4,
.table_init = iptable_nat_table_init,
};
static unsigned int iptable_nat_do_chain(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
return ipt_do_table(skb, state, state->net->ipv4.nat_table);
}
static const struct nf_hook_ops nf_nat_ipv4_ops[] = {
{
.hook = iptable_nat_do_chain,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_PRE_ROUTING,
.priority = NF_IP_PRI_NAT_DST,
},
{
.hook = iptable_nat_do_chain,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_POST_ROUTING,
.priority = NF_IP_PRI_NAT_SRC,
},
{
.hook = iptable_nat_do_chain,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_LOCAL_OUT,
.priority = NF_IP_PRI_NAT_DST,
},
{
.hook = iptable_nat_do_chain,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_LOCAL_IN,
.priority = NF_IP_PRI_NAT_SRC,
},
};
static int ipt_nat_register_lookups(struct net *net)
{
int i, ret;
for (i = 0; i < ARRAY_SIZE(nf_nat_ipv4_ops); i++) {
ret = nf_nat_l3proto_ipv4_register_fn(net, &nf_nat_ipv4_ops[i]);
if (ret) {
while (i)
nf_nat_l3proto_ipv4_unregister_fn(net, &nf_nat_ipv4_ops[--i]);
return ret;
}
}
return 0;
}
static void ipt_nat_unregister_lookups(struct net *net)
{
int i;
for (i = 0; i < ARRAY_SIZE(nf_nat_ipv4_ops); i++)
nf_nat_l3proto_ipv4_unregister_fn(net, &nf_nat_ipv4_ops[i]);
}
static int __net_init iptable_nat_table_init(struct net *net)
{
struct ipt_replace *repl;
int ret;
if (net->ipv4.nat_table)
return 0;
repl = ipt_alloc_initial_table(&nf_nat_ipv4_table);
if (repl == NULL)
return -ENOMEM;
ret = ipt_register_table(net, &nf_nat_ipv4_table, repl,
NULL, &net->ipv4.nat_table);
if (ret < 0) {
kfree(repl);
return ret;
}
ret = ipt_nat_register_lookups(net);
if (ret < 0) {
ipt_unregister_table(net, net->ipv4.nat_table, NULL);
net->ipv4.nat_table = NULL;
}
kfree(repl);
return ret;
}
static void __net_exit iptable_nat_net_exit(struct net *net)
{
if (!net->ipv4.nat_table)
return;
ipt_nat_unregister_lookups(net);
ipt_unregister_table(net, net->ipv4.nat_table, NULL);
net->ipv4.nat_table = NULL;
}
static struct pernet_operations iptable_nat_net_ops = {
.exit = iptable_nat_net_exit,
};
static int __init iptable_nat_init(void)
{
int ret = register_pernet_subsys(&iptable_nat_net_ops);
if (ret)
return ret;
ret = iptable_nat_table_init(&init_net);
if (ret)
unregister_pernet_subsys(&iptable_nat_net_ops);
return ret;
}
static void __exit iptable_nat_exit(void)
{
unregister_pernet_subsys(&iptable_nat_net_ops);
}
module_init(iptable_nat_init);
module_exit(iptable_nat_exit);
MODULE_LICENSE("GPL");
+119
View File
@@ -0,0 +1,119 @@
/*
* 'raw' table, which is the very first hooked in at PRE_ROUTING and LOCAL_OUT .
*
* Copyright (C) 2003 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/netfilter_ipv4/ip_tables.h>
#include <linux/slab.h>
#include <net/ip.h>
#define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT))
static int __net_init iptable_raw_table_init(struct net *net);
static bool raw_before_defrag __read_mostly;
MODULE_PARM_DESC(raw_before_defrag, "Enable raw table before defrag");
module_param(raw_before_defrag, bool, 0000);
static const struct xt_table packet_raw = {
.name = "raw",
.valid_hooks = RAW_VALID_HOOKS,
.me = THIS_MODULE,
.af = NFPROTO_IPV4,
.priority = NF_IP_PRI_RAW,
.table_init = iptable_raw_table_init,
};
static const struct xt_table packet_raw_before_defrag = {
.name = "raw",
.valid_hooks = RAW_VALID_HOOKS,
.me = THIS_MODULE,
.af = NFPROTO_IPV4,
.priority = NF_IP_PRI_RAW_BEFORE_DEFRAG,
.table_init = iptable_raw_table_init,
};
/* The work comes in here from netfilter.c. */
static unsigned int
iptable_raw_hook(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
return ipt_do_table(skb, state, state->net->ipv4.iptable_raw);
}
static struct nf_hook_ops *rawtable_ops __read_mostly;
static int __net_init iptable_raw_table_init(struct net *net)
{
struct ipt_replace *repl;
const struct xt_table *table = &packet_raw;
int ret;
if (raw_before_defrag)
table = &packet_raw_before_defrag;
if (net->ipv4.iptable_raw)
return 0;
repl = ipt_alloc_initial_table(table);
if (repl == NULL)
return -ENOMEM;
ret = ipt_register_table(net, table, repl, rawtable_ops,
&net->ipv4.iptable_raw);
kfree(repl);
return ret;
}
static void __net_exit iptable_raw_net_exit(struct net *net)
{
if (!net->ipv4.iptable_raw)
return;
ipt_unregister_table(net, net->ipv4.iptable_raw, rawtable_ops);
net->ipv4.iptable_raw = NULL;
}
static struct pernet_operations iptable_raw_net_ops = {
.exit = iptable_raw_net_exit,
};
static int __init iptable_raw_init(void)
{
int ret;
const struct xt_table *table = &packet_raw;
if (raw_before_defrag) {
table = &packet_raw_before_defrag;
pr_info("Enabling raw table before defrag\n");
}
rawtable_ops = xt_hook_ops_alloc(table, iptable_raw_hook);
if (IS_ERR(rawtable_ops))
return PTR_ERR(rawtable_ops);
ret = register_pernet_subsys(&iptable_raw_net_ops);
if (ret < 0) {
kfree(rawtable_ops);
return ret;
}
ret = iptable_raw_table_init(&init_net);
if (ret) {
unregister_pernet_subsys(&iptable_raw_net_ops);
kfree(rawtable_ops);
}
return ret;
}
static void __exit iptable_raw_fini(void)
{
unregister_pernet_subsys(&iptable_raw_net_ops);
kfree(rawtable_ops);
}
module_init(iptable_raw_init);
module_exit(iptable_raw_fini);
MODULE_LICENSE("GPL");
+111
View File
@@ -0,0 +1,111 @@
/*
* "security" table
*
* This is for use by Mandatory Access Control (MAC) security models,
* which need to be able to manage security policy in separate context
* to DAC.
*
* Based on iptable_mangle.c
*
* Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling
* Copyright (C) 2000-2004 Netfilter Core Team <coreteam <at> netfilter.org>
* Copyright (C) 2008 Red Hat, Inc., James Morris <jmorris <at> redhat.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/module.h>
#include <linux/netfilter_ipv4/ip_tables.h>
#include <linux/slab.h>
#include <net/ip.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("James Morris <jmorris <at> redhat.com>");
MODULE_DESCRIPTION("iptables security table, for MAC rules");
#define SECURITY_VALID_HOOKS (1 << NF_INET_LOCAL_IN) | \
(1 << NF_INET_FORWARD) | \
(1 << NF_INET_LOCAL_OUT)
static int __net_init iptable_security_table_init(struct net *net);
static const struct xt_table security_table = {
.name = "security",
.valid_hooks = SECURITY_VALID_HOOKS,
.me = THIS_MODULE,
.af = NFPROTO_IPV4,
.priority = NF_IP_PRI_SECURITY,
.table_init = iptable_security_table_init,
};
static unsigned int
iptable_security_hook(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
return ipt_do_table(skb, state, state->net->ipv4.iptable_security);
}
static struct nf_hook_ops *sectbl_ops __read_mostly;
static int __net_init iptable_security_table_init(struct net *net)
{
struct ipt_replace *repl;
int ret;
if (net->ipv4.iptable_security)
return 0;
repl = ipt_alloc_initial_table(&security_table);
if (repl == NULL)
return -ENOMEM;
ret = ipt_register_table(net, &security_table, repl, sectbl_ops,
&net->ipv4.iptable_security);
kfree(repl);
return ret;
}
static void __net_exit iptable_security_net_exit(struct net *net)
{
if (!net->ipv4.iptable_security)
return;
ipt_unregister_table(net, net->ipv4.iptable_security, sectbl_ops);
net->ipv4.iptable_security = NULL;
}
static struct pernet_operations iptable_security_net_ops = {
.exit = iptable_security_net_exit,
};
static int __init iptable_security_init(void)
{
int ret;
sectbl_ops = xt_hook_ops_alloc(&security_table, iptable_security_hook);
if (IS_ERR(sectbl_ops))
return PTR_ERR(sectbl_ops);
ret = register_pernet_subsys(&iptable_security_net_ops);
if (ret < 0) {
kfree(sectbl_ops);
return ret;
}
ret = iptable_security_table_init(&init_net);
if (ret) {
unregister_pernet_subsys(&iptable_security_net_ops);
kfree(sectbl_ops);
}
return ret;
}
static void __exit iptable_security_fini(void)
{
unregister_pernet_subsys(&iptable_security_net_ops);
kfree(sectbl_ops);
}
module_init(iptable_security_init);
module_exit(iptable_security_fini);
+160
View File
@@ -0,0 +1,160 @@
/* (C) 1999-2001 Paul `Rusty' Russell
* (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/types.h>
#include <linux/ip.h>
#include <linux/netfilter.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <net/netns/generic.h>
#include <net/route.h>
#include <net/ip.h>
#include <linux/netfilter_bridge.h>
#include <linux/netfilter_ipv4.h>
#include <net/netfilter/ipv4/nf_defrag_ipv4.h>
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
#include <net/netfilter/nf_conntrack.h>
#endif
#include <net/netfilter/nf_conntrack_zones.h>
static DEFINE_MUTEX(defrag4_mutex);
static int nf_ct_ipv4_gather_frags(struct net *net, struct sk_buff *skb,
u_int32_t user)
{
int err;
local_bh_disable();
err = ip_defrag(net, skb, user);
local_bh_enable();
if (!err)
skb->ignore_df = 1;
return err;
}
static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum,
struct sk_buff *skb)
{
u16 zone_id = NF_CT_DEFAULT_ZONE_ID;
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
if (skb_nfct(skb)) {
enum ip_conntrack_info ctinfo;
const struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
zone_id = nf_ct_zone_id(nf_ct_zone(ct), CTINFO2DIR(ctinfo));
}
#endif
if (nf_bridge_in_prerouting(skb))
return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id;
if (hooknum == NF_INET_PRE_ROUTING)
return IP_DEFRAG_CONNTRACK_IN + zone_id;
else
return IP_DEFRAG_CONNTRACK_OUT + zone_id;
}
static unsigned int ipv4_conntrack_defrag(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
struct sock *sk = skb->sk;
if (sk && sk_fullsock(sk) && (sk->sk_family == PF_INET) &&
inet_sk(sk)->nodefrag)
return NF_ACCEPT;
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
#if !IS_ENABLED(CONFIG_NF_NAT)
/* Previously seen (loopback)? Ignore. Do this before
fragment check. */
if (skb_nfct(skb) && !nf_ct_is_template((struct nf_conn *)skb_nfct(skb)))
return NF_ACCEPT;
#endif
if (skb->_nfct == IP_CT_UNTRACKED)
return NF_ACCEPT;
#endif
/* Gather fragments. */
if (ip_is_fragment(ip_hdr(skb))) {
enum ip_defrag_users user =
nf_ct_defrag_user(state->hook, skb);
if (nf_ct_ipv4_gather_frags(state->net, skb, user))
return NF_STOLEN;
}
return NF_ACCEPT;
}
static const struct nf_hook_ops ipv4_defrag_ops[] = {
{
.hook = ipv4_conntrack_defrag,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_PRE_ROUTING,
.priority = NF_IP_PRI_CONNTRACK_DEFRAG,
},
{
.hook = ipv4_conntrack_defrag,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_LOCAL_OUT,
.priority = NF_IP_PRI_CONNTRACK_DEFRAG,
},
};
static void __net_exit defrag4_net_exit(struct net *net)
{
if (net->nf.defrag_ipv4) {
nf_unregister_net_hooks(net, ipv4_defrag_ops,
ARRAY_SIZE(ipv4_defrag_ops));
net->nf.defrag_ipv4 = false;
}
}
static struct pernet_operations defrag4_net_ops = {
.exit = defrag4_net_exit,
};
static int __init nf_defrag_init(void)
{
return register_pernet_subsys(&defrag4_net_ops);
}
static void __exit nf_defrag_fini(void)
{
unregister_pernet_subsys(&defrag4_net_ops);
}
int nf_defrag_ipv4_enable(struct net *net)
{
int err = 0;
might_sleep();
if (net->nf.defrag_ipv4)
return 0;
mutex_lock(&defrag4_mutex);
if (net->nf.defrag_ipv4)
goto out_unlock;
err = nf_register_net_hooks(net, ipv4_defrag_ops,
ARRAY_SIZE(ipv4_defrag_ops));
if (err == 0)
net->nf.defrag_ipv4 = true;
out_unlock:
mutex_unlock(&defrag4_mutex);
return err;
}
EXPORT_SYMBOL_GPL(nf_defrag_ipv4_enable);
module_init(nf_defrag_init);
module_exit(nf_defrag_fini);
MODULE_LICENSE("GPL");
+102
View File
@@ -0,0 +1,102 @@
/*
* (C) 2007 by Sebastian Claßen <sebastian.classen@freenet.ag>
* (C) 2007-2010 by Jan Engelhardt <jengelh@medozas.de>
*
* Extracted from xt_TEE.c
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 or later, as
* published by the Free Software Foundation.
*/
#include <linux/ip.h>
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/route.h>
#include <linux/skbuff.h>
#include <linux/netfilter.h>
#include <net/checksum.h>
#include <net/icmp.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/netfilter/ipv4/nf_dup_ipv4.h>
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
#include <net/netfilter/nf_conntrack.h>
#endif
static bool nf_dup_ipv4_route(struct net *net, struct sk_buff *skb,
const struct in_addr *gw, int oif)
{
const struct iphdr *iph = ip_hdr(skb);
struct rtable *rt;
struct flowi4 fl4;
memset(&fl4, 0, sizeof(fl4));
if (oif != -1)
fl4.flowi4_oif = oif;
fl4.daddr = gw->s_addr;
fl4.flowi4_tos = RT_TOS(iph->tos);
fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
fl4.flowi4_flags = FLOWI_FLAG_KNOWN_NH;
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt))
return false;
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
skb->dev = rt->dst.dev;
skb->protocol = htons(ETH_P_IP);
return true;
}
void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum,
const struct in_addr *gw, int oif)
{
struct iphdr *iph;
if (this_cpu_read(nf_skb_duplicated))
return;
/*
* Copy the skb, and route the copy. Will later return %XT_CONTINUE for
* the original skb, which should continue on its way as if nothing has
* happened. The copy should be independently delivered to the gateway.
*/
skb = pskb_copy(skb, GFP_ATOMIC);
if (skb == NULL)
return;
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
/* Avoid counting cloned packets towards the original connection. */
nf_reset(skb);
nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
#endif
/*
* If we are in PREROUTING/INPUT, decrease the TTL to mitigate potential
* loops between two hosts.
*
* Set %IP_DF so that the original source is notified of a potentially
* decreased MTU on the clone route. IPv6 does this too.
*
* IP header checksum will be recalculated at ip_local_out.
*/
iph = ip_hdr(skb);
iph->frag_off |= htons(IP_DF);
if (hooknum == NF_INET_PRE_ROUTING ||
hooknum == NF_INET_LOCAL_IN)
--iph->ttl;
if (nf_dup_ipv4_route(net, skb, gw, oif)) {
__this_cpu_write(nf_skb_duplicated, true);
ip_local_out(net, skb->sk, skb);
__this_cpu_write(nf_skb_duplicated, false);
} else {
kfree_skb(skb);
}
}
EXPORT_SYMBOL_GPL(nf_dup_ipv4);
MODULE_AUTHOR("Sebastian Claßen <sebastian.classen@freenet.ag>");
MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>");
MODULE_DESCRIPTION("nf_dup_ipv4: Duplicate IPv4 packet");
MODULE_LICENSE("GPL");
+33
View File
@@ -0,0 +1,33 @@
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/netfilter.h>
#include <net/netfilter/nf_flow_table.h>
#include <net/netfilter/nf_tables.h>
static struct nf_flowtable_type flowtable_ipv4 = {
.family = NFPROTO_IPV4,
.init = nf_flow_table_init,
.free = nf_flow_table_free,
.hook = nf_flow_offload_ip_hook,
.owner = THIS_MODULE,
};
static int __init nf_flow_ipv4_module_init(void)
{
nft_register_flowtable_type(&flowtable_ipv4);
return 0;
}
static void __exit nf_flow_ipv4_module_exit(void)
{
nft_unregister_flowtable_type(&flowtable_ipv4);
}
module_init(nf_flow_ipv4_module_init);
module_exit(nf_flow_ipv4_module_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
MODULE_ALIAS_NF_FLOWTABLE(AF_INET);
+175
View File
@@ -0,0 +1,175 @@
/*
* (C) 2014 by Pablo Neira Ayuso <pablo@netfilter.org>
*
* Based on code from ebt_log from:
*
* Bart De Schuymer <bdschuym@pandora.be>
* Harald Welte <laforge@netfilter.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/skbuff.h>
#include <linux/if_arp.h>
#include <linux/ip.h>
#include <net/route.h>
#include <linux/netfilter.h>
#include <linux/netfilter/xt_LOG.h>
#include <net/netfilter/nf_log.h>
static const struct nf_loginfo default_loginfo = {
.type = NF_LOG_TYPE_LOG,
.u = {
.log = {
.level = LOGLEVEL_NOTICE,
.logflags = NF_LOG_DEFAULT_MASK,
},
},
};
struct arppayload {
unsigned char mac_src[ETH_ALEN];
unsigned char ip_src[4];
unsigned char mac_dst[ETH_ALEN];
unsigned char ip_dst[4];
};
static void dump_arp_packet(struct nf_log_buf *m,
const struct nf_loginfo *info,
const struct sk_buff *skb, unsigned int nhoff)
{
const struct arppayload *ap;
struct arppayload _arpp;
const struct arphdr *ah;
unsigned int logflags;
struct arphdr _arph;
ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph);
if (ah == NULL) {
nf_log_buf_add(m, "TRUNCATED");
return;
}
if (info->type == NF_LOG_TYPE_LOG)
logflags = info->u.log.logflags;
else
logflags = NF_LOG_DEFAULT_MASK;
if (logflags & NF_LOG_MACDECODE) {
nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ",
eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest);
nf_log_dump_vlan(m, skb);
nf_log_buf_add(m, "MACPROTO=%04x ",
ntohs(eth_hdr(skb)->h_proto));
}
nf_log_buf_add(m, "ARP HTYPE=%d PTYPE=0x%04x OPCODE=%d",
ntohs(ah->ar_hrd), ntohs(ah->ar_pro), ntohs(ah->ar_op));
/* If it's for Ethernet and the lengths are OK, then log the ARP
* payload.
*/
if (ah->ar_hrd != htons(ARPHRD_ETHER) ||
ah->ar_hln != ETH_ALEN ||
ah->ar_pln != sizeof(__be32))
return;
ap = skb_header_pointer(skb, sizeof(_arph), sizeof(_arpp), &_arpp);
if (ap == NULL) {
nf_log_buf_add(m, " INCOMPLETE [%zu bytes]",
skb->len - sizeof(_arph));
return;
}
nf_log_buf_add(m, " MACSRC=%pM IPSRC=%pI4 MACDST=%pM IPDST=%pI4",
ap->mac_src, ap->ip_src, ap->mac_dst, ap->ip_dst);
}
static void nf_log_arp_packet(struct net *net, u_int8_t pf,
unsigned int hooknum, const struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
const struct nf_loginfo *loginfo,
const char *prefix)
{
struct nf_log_buf *m;
/* FIXME: Disabled from containers until syslog ns is supported */
if (!net_eq(net, &init_net) && !sysctl_nf_log_all_netns)
return;
m = nf_log_buf_open();
if (!loginfo)
loginfo = &default_loginfo;
nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo,
prefix);
dump_arp_packet(m, loginfo, skb, 0);
nf_log_buf_close(m);
}
static struct nf_logger nf_arp_logger __read_mostly = {
.name = "nf_log_arp",
.type = NF_LOG_TYPE_LOG,
.logfn = nf_log_arp_packet,
.me = THIS_MODULE,
};
static int __net_init nf_log_arp_net_init(struct net *net)
{
return nf_log_set(net, NFPROTO_ARP, &nf_arp_logger);
}
static void __net_exit nf_log_arp_net_exit(struct net *net)
{
nf_log_unset(net, &nf_arp_logger);
}
static struct pernet_operations nf_log_arp_net_ops = {
.init = nf_log_arp_net_init,
.exit = nf_log_arp_net_exit,
};
static int __init nf_log_arp_init(void)
{
int ret;
ret = register_pernet_subsys(&nf_log_arp_net_ops);
if (ret < 0)
return ret;
ret = nf_log_register(NFPROTO_ARP, &nf_arp_logger);
if (ret < 0) {
pr_err("failed to register logger\n");
goto err1;
}
return 0;
err1:
unregister_pernet_subsys(&nf_log_arp_net_ops);
return ret;
}
static void __exit nf_log_arp_exit(void)
{
unregister_pernet_subsys(&nf_log_arp_net_ops);
nf_log_unregister(&nf_arp_logger);
}
module_init(nf_log_arp_init);
module_exit(nf_log_arp_exit);
MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
MODULE_DESCRIPTION("Netfilter ARP packet logging");
MODULE_LICENSE("GPL");
MODULE_ALIAS_NF_LOGGER(3, 0);
+398
View File
@@ -0,0 +1,398 @@
/* (C) 1999-2001 Paul `Rusty' Russell
* (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/skbuff.h>
#include <linux/if_arp.h>
#include <linux/ip.h>
#include <net/ipv6.h>
#include <net/icmp.h>
#include <net/udp.h>
#include <net/tcp.h>
#include <net/route.h>
#include <linux/netfilter.h>
#include <linux/netfilter/xt_LOG.h>
#include <net/netfilter/nf_log.h>
static const struct nf_loginfo default_loginfo = {
.type = NF_LOG_TYPE_LOG,
.u = {
.log = {
.level = LOGLEVEL_NOTICE,
.logflags = NF_LOG_DEFAULT_MASK,
},
},
};
/* One level of recursion won't kill us */
static void dump_ipv4_packet(struct net *net, struct nf_log_buf *m,
const struct nf_loginfo *info,
const struct sk_buff *skb, unsigned int iphoff)
{
struct iphdr _iph;
const struct iphdr *ih;
unsigned int logflags;
if (info->type == NF_LOG_TYPE_LOG)
logflags = info->u.log.logflags;
else
logflags = NF_LOG_DEFAULT_MASK;
ih = skb_header_pointer(skb, iphoff, sizeof(_iph), &_iph);
if (ih == NULL) {
nf_log_buf_add(m, "TRUNCATED");
return;
}
/* Important fields:
* TOS, len, DF/MF, fragment offset, TTL, src, dst, options. */
/* Max length: 40 "SRC=255.255.255.255 DST=255.255.255.255 " */
nf_log_buf_add(m, "SRC=%pI4 DST=%pI4 ", &ih->saddr, &ih->daddr);
/* Max length: 46 "LEN=65535 TOS=0xFF PREC=0xFF TTL=255 ID=65535 " */
nf_log_buf_add(m, "LEN=%u TOS=0x%02X PREC=0x%02X TTL=%u ID=%u ",
ntohs(ih->tot_len), ih->tos & IPTOS_TOS_MASK,
ih->tos & IPTOS_PREC_MASK, ih->ttl, ntohs(ih->id));
/* Max length: 6 "CE DF MF " */
if (ntohs(ih->frag_off) & IP_CE)
nf_log_buf_add(m, "CE ");
if (ntohs(ih->frag_off) & IP_DF)
nf_log_buf_add(m, "DF ");
if (ntohs(ih->frag_off) & IP_MF)
nf_log_buf_add(m, "MF ");
/* Max length: 11 "FRAG:65535 " */
if (ntohs(ih->frag_off) & IP_OFFSET)
nf_log_buf_add(m, "FRAG:%u ", ntohs(ih->frag_off) & IP_OFFSET);
if ((logflags & NF_LOG_IPOPT) &&
ih->ihl * 4 > sizeof(struct iphdr)) {
const unsigned char *op;
unsigned char _opt[4 * 15 - sizeof(struct iphdr)];
unsigned int i, optsize;
optsize = ih->ihl * 4 - sizeof(struct iphdr);
op = skb_header_pointer(skb, iphoff+sizeof(_iph),
optsize, _opt);
if (op == NULL) {
nf_log_buf_add(m, "TRUNCATED");
return;
}
/* Max length: 127 "OPT (" 15*4*2chars ") " */
nf_log_buf_add(m, "OPT (");
for (i = 0; i < optsize; i++)
nf_log_buf_add(m, "%02X", op[i]);
nf_log_buf_add(m, ") ");
}
switch (ih->protocol) {
case IPPROTO_TCP:
if (nf_log_dump_tcp_header(m, skb, ih->protocol,
ntohs(ih->frag_off) & IP_OFFSET,
iphoff+ih->ihl*4, logflags))
return;
break;
case IPPROTO_UDP:
case IPPROTO_UDPLITE:
if (nf_log_dump_udp_header(m, skb, ih->protocol,
ntohs(ih->frag_off) & IP_OFFSET,
iphoff+ih->ihl*4))
return;
break;
case IPPROTO_ICMP: {
struct icmphdr _icmph;
const struct icmphdr *ich;
static const size_t required_len[NR_ICMP_TYPES+1]
= { [ICMP_ECHOREPLY] = 4,
[ICMP_DEST_UNREACH]
= 8 + sizeof(struct iphdr),
[ICMP_SOURCE_QUENCH]
= 8 + sizeof(struct iphdr),
[ICMP_REDIRECT]
= 8 + sizeof(struct iphdr),
[ICMP_ECHO] = 4,
[ICMP_TIME_EXCEEDED]
= 8 + sizeof(struct iphdr),
[ICMP_PARAMETERPROB]
= 8 + sizeof(struct iphdr),
[ICMP_TIMESTAMP] = 20,
[ICMP_TIMESTAMPREPLY] = 20,
[ICMP_ADDRESS] = 12,
[ICMP_ADDRESSREPLY] = 12 };
/* Max length: 11 "PROTO=ICMP " */
nf_log_buf_add(m, "PROTO=ICMP ");
if (ntohs(ih->frag_off) & IP_OFFSET)
break;
/* Max length: 25 "INCOMPLETE [65535 bytes] " */
ich = skb_header_pointer(skb, iphoff + ih->ihl * 4,
sizeof(_icmph), &_icmph);
if (ich == NULL) {
nf_log_buf_add(m, "INCOMPLETE [%u bytes] ",
skb->len - iphoff - ih->ihl*4);
break;
}
/* Max length: 18 "TYPE=255 CODE=255 " */
nf_log_buf_add(m, "TYPE=%u CODE=%u ", ich->type, ich->code);
/* Max length: 25 "INCOMPLETE [65535 bytes] " */
if (ich->type <= NR_ICMP_TYPES &&
required_len[ich->type] &&
skb->len-iphoff-ih->ihl*4 < required_len[ich->type]) {
nf_log_buf_add(m, "INCOMPLETE [%u bytes] ",
skb->len - iphoff - ih->ihl*4);
break;
}
switch (ich->type) {
case ICMP_ECHOREPLY:
case ICMP_ECHO:
/* Max length: 19 "ID=65535 SEQ=65535 " */
nf_log_buf_add(m, "ID=%u SEQ=%u ",
ntohs(ich->un.echo.id),
ntohs(ich->un.echo.sequence));
break;
case ICMP_PARAMETERPROB:
/* Max length: 14 "PARAMETER=255 " */
nf_log_buf_add(m, "PARAMETER=%u ",
ntohl(ich->un.gateway) >> 24);
break;
case ICMP_REDIRECT:
/* Max length: 24 "GATEWAY=255.255.255.255 " */
nf_log_buf_add(m, "GATEWAY=%pI4 ", &ich->un.gateway);
/* Fall through */
case ICMP_DEST_UNREACH:
case ICMP_SOURCE_QUENCH:
case ICMP_TIME_EXCEEDED:
/* Max length: 3+maxlen */
if (!iphoff) { /* Only recurse once. */
nf_log_buf_add(m, "[");
dump_ipv4_packet(net, m, info, skb,
iphoff + ih->ihl*4+sizeof(_icmph));
nf_log_buf_add(m, "] ");
}
/* Max length: 10 "MTU=65535 " */
if (ich->type == ICMP_DEST_UNREACH &&
ich->code == ICMP_FRAG_NEEDED) {
nf_log_buf_add(m, "MTU=%u ",
ntohs(ich->un.frag.mtu));
}
}
break;
}
/* Max Length */
case IPPROTO_AH: {
struct ip_auth_hdr _ahdr;
const struct ip_auth_hdr *ah;
if (ntohs(ih->frag_off) & IP_OFFSET)
break;
/* Max length: 9 "PROTO=AH " */
nf_log_buf_add(m, "PROTO=AH ");
/* Max length: 25 "INCOMPLETE [65535 bytes] " */
ah = skb_header_pointer(skb, iphoff+ih->ihl*4,
sizeof(_ahdr), &_ahdr);
if (ah == NULL) {
nf_log_buf_add(m, "INCOMPLETE [%u bytes] ",
skb->len - iphoff - ih->ihl*4);
break;
}
/* Length: 15 "SPI=0xF1234567 " */
nf_log_buf_add(m, "SPI=0x%x ", ntohl(ah->spi));
break;
}
case IPPROTO_ESP: {
struct ip_esp_hdr _esph;
const struct ip_esp_hdr *eh;
/* Max length: 10 "PROTO=ESP " */
nf_log_buf_add(m, "PROTO=ESP ");
if (ntohs(ih->frag_off) & IP_OFFSET)
break;
/* Max length: 25 "INCOMPLETE [65535 bytes] " */
eh = skb_header_pointer(skb, iphoff+ih->ihl*4,
sizeof(_esph), &_esph);
if (eh == NULL) {
nf_log_buf_add(m, "INCOMPLETE [%u bytes] ",
skb->len - iphoff - ih->ihl*4);
break;
}
/* Length: 15 "SPI=0xF1234567 " */
nf_log_buf_add(m, "SPI=0x%x ", ntohl(eh->spi));
break;
}
/* Max length: 10 "PROTO 255 " */
default:
nf_log_buf_add(m, "PROTO=%u ", ih->protocol);
}
/* Max length: 15 "UID=4294967295 " */
if ((logflags & NF_LOG_UID) && !iphoff)
nf_log_dump_sk_uid_gid(net, m, skb->sk);
/* Max length: 16 "MARK=0xFFFFFFFF " */
if (!iphoff && skb->mark)
nf_log_buf_add(m, "MARK=0x%x ", skb->mark);
/* Proto Max log string length */
/* IP: 40+46+6+11+127 = 230 */
/* TCP: 10+max(25,20+30+13+9+32+11+127) = 252 */
/* UDP: 10+max(25,20) = 35 */
/* UDPLITE: 14+max(25,20) = 39 */
/* ICMP: 11+max(25, 18+25+max(19,14,24+3+n+10,3+n+10)) = 91+n */
/* ESP: 10+max(25)+15 = 50 */
/* AH: 9+max(25)+15 = 49 */
/* unknown: 10 */
/* (ICMP allows recursion one level deep) */
/* maxlen = IP + ICMP + IP + max(TCP,UDP,ICMP,unknown) */
/* maxlen = 230+ 91 + 230 + 252 = 803 */
}
static void dump_ipv4_mac_header(struct nf_log_buf *m,
const struct nf_loginfo *info,
const struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
unsigned int logflags = 0;
if (info->type == NF_LOG_TYPE_LOG)
logflags = info->u.log.logflags;
if (!(logflags & NF_LOG_MACDECODE))
goto fallback;
switch (dev->type) {
case ARPHRD_ETHER:
nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ",
eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest);
nf_log_dump_vlan(m, skb);
nf_log_buf_add(m, "MACPROTO=%04x ",
ntohs(eth_hdr(skb)->h_proto));
return;
default:
break;
}
fallback:
nf_log_buf_add(m, "MAC=");
if (dev->hard_header_len &&
skb->mac_header != skb->network_header) {
const unsigned char *p = skb_mac_header(skb);
unsigned int i;
nf_log_buf_add(m, "%02x", *p++);
for (i = 1; i < dev->hard_header_len; i++, p++)
nf_log_buf_add(m, ":%02x", *p);
}
nf_log_buf_add(m, " ");
}
static void nf_log_ip_packet(struct net *net, u_int8_t pf,
unsigned int hooknum, const struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
const struct nf_loginfo *loginfo,
const char *prefix)
{
struct nf_log_buf *m;
/* FIXME: Disabled from containers until syslog ns is supported */
if (!net_eq(net, &init_net) && !sysctl_nf_log_all_netns)
return;
m = nf_log_buf_open();
if (!loginfo)
loginfo = &default_loginfo;
nf_log_dump_packet_common(m, pf, hooknum, skb, in,
out, loginfo, prefix);
if (in != NULL)
dump_ipv4_mac_header(m, loginfo, skb);
dump_ipv4_packet(net, m, loginfo, skb, 0);
nf_log_buf_close(m);
}
static struct nf_logger nf_ip_logger __read_mostly = {
.name = "nf_log_ipv4",
.type = NF_LOG_TYPE_LOG,
.logfn = nf_log_ip_packet,
.me = THIS_MODULE,
};
static int __net_init nf_log_ipv4_net_init(struct net *net)
{
return nf_log_set(net, NFPROTO_IPV4, &nf_ip_logger);
}
static void __net_exit nf_log_ipv4_net_exit(struct net *net)
{
nf_log_unset(net, &nf_ip_logger);
}
static struct pernet_operations nf_log_ipv4_net_ops = {
.init = nf_log_ipv4_net_init,
.exit = nf_log_ipv4_net_exit,
};
static int __init nf_log_ipv4_init(void)
{
int ret;
ret = register_pernet_subsys(&nf_log_ipv4_net_ops);
if (ret < 0)
return ret;
ret = nf_log_register(NFPROTO_IPV4, &nf_ip_logger);
if (ret < 0) {
pr_err("failed to register logger\n");
goto err1;
}
return 0;
err1:
unregister_pernet_subsys(&nf_log_ipv4_net_ops);
return ret;
}
static void __exit nf_log_ipv4_exit(void)
{
unregister_pernet_subsys(&nf_log_ipv4_net_ops);
nf_log_unregister(&nf_ip_logger);
}
module_init(nf_log_ipv4_init);
module_exit(nf_log_ipv4_exit);
MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
MODULE_DESCRIPTION("Netfilter IPv4 packet logging");
MODULE_LICENSE("GPL");
MODULE_ALIAS_NF_LOGGER(AF_INET, 0);
+634
View File
@@ -0,0 +1,634 @@
/*
* H.323 extension for NAT alteration.
*
* Copyright (c) 2006 Jing Min Zhao <zhaojingmin@users.sourceforge.net>
* Copyright (c) 2006-2012 Patrick McHardy <kaber@trash.net>
*
* This source code is licensed under General Public License version 2.
*
* Based on the 'brute force' H.323 NAT module by
* Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
*/
#include <linux/module.h>
#include <linux/tcp.h>
#include <net/tcp.h>
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_helper.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_expect.h>
#include <linux/netfilter/nf_conntrack_h323.h>
/****************************************************************************/
static int set_addr(struct sk_buff *skb, unsigned int protoff,
unsigned char **data, int dataoff,
unsigned int addroff, __be32 ip, __be16 port)
{
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
struct {
__be32 ip;
__be16 port;
} __attribute__ ((__packed__)) buf;
const struct tcphdr *th;
struct tcphdr _tcph;
buf.ip = ip;
buf.port = port;
addroff += dataoff;
if (ip_hdr(skb)->protocol == IPPROTO_TCP) {
if (!nf_nat_mangle_tcp_packet(skb, ct, ctinfo,
protoff, addroff, sizeof(buf),
(char *) &buf, sizeof(buf))) {
net_notice_ratelimited("nf_nat_h323: nf_nat_mangle_tcp_packet error\n");
return -1;
}
/* Relocate data pointer */
th = skb_header_pointer(skb, ip_hdrlen(skb),
sizeof(_tcph), &_tcph);
if (th == NULL)
return -1;
*data = skb->data + ip_hdrlen(skb) + th->doff * 4 + dataoff;
} else {
if (!nf_nat_mangle_udp_packet(skb, ct, ctinfo,
protoff, addroff, sizeof(buf),
(char *) &buf, sizeof(buf))) {
net_notice_ratelimited("nf_nat_h323: nf_nat_mangle_udp_packet error\n");
return -1;
}
/* nf_nat_mangle_udp_packet uses skb_make_writable() to copy
* or pull everything in a linear buffer, so we can safely
* use the skb pointers now */
*data = skb->data + ip_hdrlen(skb) + sizeof(struct udphdr);
}
return 0;
}
/****************************************************************************/
static int set_h225_addr(struct sk_buff *skb, unsigned int protoff,
unsigned char **data, int dataoff,
TransportAddress *taddr,
union nf_inet_addr *addr, __be16 port)
{
return set_addr(skb, protoff, data, dataoff, taddr->ipAddress.ip,
addr->ip, port);
}
/****************************************************************************/
static int set_h245_addr(struct sk_buff *skb, unsigned protoff,
unsigned char **data, int dataoff,
H245_TransportAddress *taddr,
union nf_inet_addr *addr, __be16 port)
{
return set_addr(skb, protoff, data, dataoff,
taddr->unicastAddress.iPAddress.network,
addr->ip, port);
}
/****************************************************************************/
static int set_sig_addr(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff, unsigned char **data,
TransportAddress *taddr, int count)
{
const struct nf_ct_h323_master *info = nfct_help_data(ct);
int dir = CTINFO2DIR(ctinfo);
int i;
__be16 port;
union nf_inet_addr addr;
for (i = 0; i < count; i++) {
if (get_h225_addr(ct, *data, &taddr[i], &addr, &port)) {
if (addr.ip == ct->tuplehash[dir].tuple.src.u3.ip &&
port == info->sig_port[dir]) {
/* GW->GK */
/* Fix for Gnomemeeting */
if (i > 0 &&
get_h225_addr(ct, *data, &taddr[0],
&addr, &port) &&
(ntohl(addr.ip) & 0xff000000) == 0x7f000000)
i = 0;
pr_debug("nf_nat_ras: set signal address %pI4:%hu->%pI4:%hu\n",
&addr.ip, port,
&ct->tuplehash[!dir].tuple.dst.u3.ip,
info->sig_port[!dir]);
return set_h225_addr(skb, protoff, data, 0,
&taddr[i],
&ct->tuplehash[!dir].
tuple.dst.u3,
info->sig_port[!dir]);
} else if (addr.ip == ct->tuplehash[dir].tuple.dst.u3.ip &&
port == info->sig_port[dir]) {
/* GK->GW */
pr_debug("nf_nat_ras: set signal address %pI4:%hu->%pI4:%hu\n",
&addr.ip, port,
&ct->tuplehash[!dir].tuple.src.u3.ip,
info->sig_port[!dir]);
return set_h225_addr(skb, protoff, data, 0,
&taddr[i],
&ct->tuplehash[!dir].
tuple.src.u3,
info->sig_port[!dir]);
}
}
}
return 0;
}
/****************************************************************************/
static int set_ras_addr(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff, unsigned char **data,
TransportAddress *taddr, int count)
{
int dir = CTINFO2DIR(ctinfo);
int i;
__be16 port;
union nf_inet_addr addr;
for (i = 0; i < count; i++) {
if (get_h225_addr(ct, *data, &taddr[i], &addr, &port) &&
addr.ip == ct->tuplehash[dir].tuple.src.u3.ip &&
port == ct->tuplehash[dir].tuple.src.u.udp.port) {
pr_debug("nf_nat_ras: set rasAddress %pI4:%hu->%pI4:%hu\n",
&addr.ip, ntohs(port),
&ct->tuplehash[!dir].tuple.dst.u3.ip,
ntohs(ct->tuplehash[!dir].tuple.dst.u.udp.port));
return set_h225_addr(skb, protoff, data, 0, &taddr[i],
&ct->tuplehash[!dir].tuple.dst.u3,
ct->tuplehash[!dir].tuple.
dst.u.udp.port);
}
}
return 0;
}
/****************************************************************************/
static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff, unsigned char **data, int dataoff,
H245_TransportAddress *taddr,
__be16 port, __be16 rtp_port,
struct nf_conntrack_expect *rtp_exp,
struct nf_conntrack_expect *rtcp_exp)
{
struct nf_ct_h323_master *info = nfct_help_data(ct);
int dir = CTINFO2DIR(ctinfo);
int i;
u_int16_t nated_port;
/* Set expectations for NAT */
rtp_exp->saved_proto.udp.port = rtp_exp->tuple.dst.u.udp.port;
rtp_exp->expectfn = nf_nat_follow_master;
rtp_exp->dir = !dir;
rtcp_exp->saved_proto.udp.port = rtcp_exp->tuple.dst.u.udp.port;
rtcp_exp->expectfn = nf_nat_follow_master;
rtcp_exp->dir = !dir;
/* Lookup existing expects */
for (i = 0; i < H323_RTP_CHANNEL_MAX; i++) {
if (info->rtp_port[i][dir] == rtp_port) {
/* Expected */
/* Use allocated ports first. This will refresh
* the expects */
rtp_exp->tuple.dst.u.udp.port = info->rtp_port[i][dir];
rtcp_exp->tuple.dst.u.udp.port =
htons(ntohs(info->rtp_port[i][dir]) + 1);
break;
} else if (info->rtp_port[i][dir] == 0) {
/* Not expected */
break;
}
}
/* Run out of expectations */
if (i >= H323_RTP_CHANNEL_MAX) {
net_notice_ratelimited("nf_nat_h323: out of expectations\n");
return 0;
}
/* Try to get a pair of ports. */
for (nated_port = ntohs(rtp_exp->tuple.dst.u.udp.port);
nated_port != 0; nated_port += 2) {
int ret;
rtp_exp->tuple.dst.u.udp.port = htons(nated_port);
ret = nf_ct_expect_related(rtp_exp);
if (ret == 0) {
rtcp_exp->tuple.dst.u.udp.port =
htons(nated_port + 1);
ret = nf_ct_expect_related(rtcp_exp);
if (ret == 0)
break;
else if (ret == -EBUSY) {
nf_ct_unexpect_related(rtp_exp);
continue;
} else if (ret < 0) {
nf_ct_unexpect_related(rtp_exp);
nated_port = 0;
break;
}
} else if (ret != -EBUSY) {
nated_port = 0;
break;
}
}
if (nated_port == 0) { /* No port available */
net_notice_ratelimited("nf_nat_h323: out of RTP ports\n");
return 0;
}
/* Modify signal */
if (set_h245_addr(skb, protoff, data, dataoff, taddr,
&ct->tuplehash[!dir].tuple.dst.u3,
htons((port & htons(1)) ? nated_port + 1 :
nated_port))) {
nf_ct_unexpect_related(rtp_exp);
nf_ct_unexpect_related(rtcp_exp);
return -1;
}
/* Save ports */
info->rtp_port[i][dir] = rtp_port;
info->rtp_port[i][!dir] = htons(nated_port);
/* Success */
pr_debug("nf_nat_h323: expect RTP %pI4:%hu->%pI4:%hu\n",
&rtp_exp->tuple.src.u3.ip,
ntohs(rtp_exp->tuple.src.u.udp.port),
&rtp_exp->tuple.dst.u3.ip,
ntohs(rtp_exp->tuple.dst.u.udp.port));
pr_debug("nf_nat_h323: expect RTCP %pI4:%hu->%pI4:%hu\n",
&rtcp_exp->tuple.src.u3.ip,
ntohs(rtcp_exp->tuple.src.u.udp.port),
&rtcp_exp->tuple.dst.u3.ip,
ntohs(rtcp_exp->tuple.dst.u.udp.port));
return 0;
}
/****************************************************************************/
static int nat_t120(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff, unsigned char **data, int dataoff,
H245_TransportAddress *taddr, __be16 port,
struct nf_conntrack_expect *exp)
{
int dir = CTINFO2DIR(ctinfo);
u_int16_t nated_port = ntohs(port);
/* Set expectations for NAT */
exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port;
exp->expectfn = nf_nat_follow_master;
exp->dir = !dir;
/* Try to get same port: if not, try to change it. */
for (; nated_port != 0; nated_port++) {
int ret;
exp->tuple.dst.u.tcp.port = htons(nated_port);
ret = nf_ct_expect_related(exp);
if (ret == 0)
break;
else if (ret != -EBUSY) {
nated_port = 0;
break;
}
}
if (nated_port == 0) { /* No port available */
net_notice_ratelimited("nf_nat_h323: out of TCP ports\n");
return 0;
}
/* Modify signal */
if (set_h245_addr(skb, protoff, data, dataoff, taddr,
&ct->tuplehash[!dir].tuple.dst.u3,
htons(nated_port)) < 0) {
nf_ct_unexpect_related(exp);
return -1;
}
pr_debug("nf_nat_h323: expect T.120 %pI4:%hu->%pI4:%hu\n",
&exp->tuple.src.u3.ip,
ntohs(exp->tuple.src.u.tcp.port),
&exp->tuple.dst.u3.ip,
ntohs(exp->tuple.dst.u.tcp.port));
return 0;
}
/****************************************************************************/
static int nat_h245(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff, unsigned char **data, int dataoff,
TransportAddress *taddr, __be16 port,
struct nf_conntrack_expect *exp)
{
struct nf_ct_h323_master *info = nfct_help_data(ct);
int dir = CTINFO2DIR(ctinfo);
u_int16_t nated_port = ntohs(port);
/* Set expectations for NAT */
exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port;
exp->expectfn = nf_nat_follow_master;
exp->dir = !dir;
/* Check existing expects */
if (info->sig_port[dir] == port)
nated_port = ntohs(info->sig_port[!dir]);
/* Try to get same port: if not, try to change it. */
for (; nated_port != 0; nated_port++) {
int ret;
exp->tuple.dst.u.tcp.port = htons(nated_port);
ret = nf_ct_expect_related(exp);
if (ret == 0)
break;
else if (ret != -EBUSY) {
nated_port = 0;
break;
}
}
if (nated_port == 0) { /* No port available */
net_notice_ratelimited("nf_nat_q931: out of TCP ports\n");
return 0;
}
/* Modify signal */
if (set_h225_addr(skb, protoff, data, dataoff, taddr,
&ct->tuplehash[!dir].tuple.dst.u3,
htons(nated_port))) {
nf_ct_unexpect_related(exp);
return -1;
}
/* Save ports */
info->sig_port[dir] = port;
info->sig_port[!dir] = htons(nated_port);
pr_debug("nf_nat_q931: expect H.245 %pI4:%hu->%pI4:%hu\n",
&exp->tuple.src.u3.ip,
ntohs(exp->tuple.src.u.tcp.port),
&exp->tuple.dst.u3.ip,
ntohs(exp->tuple.dst.u.tcp.port));
return 0;
}
/****************************************************************************
* This conntrack expect function replaces nf_conntrack_q931_expect()
* which was set by nf_conntrack_h323.c.
****************************************************************************/
static void ip_nat_q931_expect(struct nf_conn *new,
struct nf_conntrack_expect *this)
{
struct nf_nat_range2 range;
if (this->tuple.src.u3.ip != 0) { /* Only accept calls from GK */
nf_nat_follow_master(new, this);
return;
}
/* This must be a fresh one. */
BUG_ON(new->status & IPS_NAT_DONE_MASK);
/* Change src to where master sends to */
range.flags = NF_NAT_RANGE_MAP_IPS;
range.min_addr = range.max_addr =
new->tuplehash[!this->dir].tuple.src.u3;
nf_nat_setup_info(new, &range, NF_NAT_MANIP_SRC);
/* For DST manip, map port here to where it's expected. */
range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED);
range.min_proto = range.max_proto = this->saved_proto;
range.min_addr = range.max_addr =
new->master->tuplehash[!this->dir].tuple.src.u3;
nf_nat_setup_info(new, &range, NF_NAT_MANIP_DST);
}
/****************************************************************************/
static int nat_q931(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff, unsigned char **data,
TransportAddress *taddr, int idx,
__be16 port, struct nf_conntrack_expect *exp)
{
struct nf_ct_h323_master *info = nfct_help_data(ct);
int dir = CTINFO2DIR(ctinfo);
u_int16_t nated_port = ntohs(port);
union nf_inet_addr addr;
/* Set expectations for NAT */
exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port;
exp->expectfn = ip_nat_q931_expect;
exp->dir = !dir;
/* Check existing expects */
if (info->sig_port[dir] == port)
nated_port = ntohs(info->sig_port[!dir]);
/* Try to get same port: if not, try to change it. */
for (; nated_port != 0; nated_port++) {
int ret;
exp->tuple.dst.u.tcp.port = htons(nated_port);
ret = nf_ct_expect_related(exp);
if (ret == 0)
break;
else if (ret != -EBUSY) {
nated_port = 0;
break;
}
}
if (nated_port == 0) { /* No port available */
net_notice_ratelimited("nf_nat_ras: out of TCP ports\n");
return 0;
}
/* Modify signal */
if (set_h225_addr(skb, protoff, data, 0, &taddr[idx],
&ct->tuplehash[!dir].tuple.dst.u3,
htons(nated_port))) {
nf_ct_unexpect_related(exp);
return -1;
}
/* Save ports */
info->sig_port[dir] = port;
info->sig_port[!dir] = htons(nated_port);
/* Fix for Gnomemeeting */
if (idx > 0 &&
get_h225_addr(ct, *data, &taddr[0], &addr, &port) &&
(ntohl(addr.ip) & 0xff000000) == 0x7f000000) {
if (set_h225_addr(skb, protoff, data, 0, &taddr[0],
&ct->tuplehash[!dir].tuple.dst.u3,
info->sig_port[!dir])) {
nf_ct_unexpect_related(exp);
return -1;
}
}
/* Success */
pr_debug("nf_nat_ras: expect Q.931 %pI4:%hu->%pI4:%hu\n",
&exp->tuple.src.u3.ip,
ntohs(exp->tuple.src.u.tcp.port),
&exp->tuple.dst.u3.ip,
ntohs(exp->tuple.dst.u.tcp.port));
return 0;
}
/****************************************************************************/
static void ip_nat_callforwarding_expect(struct nf_conn *new,
struct nf_conntrack_expect *this)
{
struct nf_nat_range2 range;
/* This must be a fresh one. */
BUG_ON(new->status & IPS_NAT_DONE_MASK);
/* Change src to where master sends to */
range.flags = NF_NAT_RANGE_MAP_IPS;
range.min_addr = range.max_addr =
new->tuplehash[!this->dir].tuple.src.u3;
nf_nat_setup_info(new, &range, NF_NAT_MANIP_SRC);
/* For DST manip, map port here to where it's expected. */
range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED);
range.min_proto = range.max_proto = this->saved_proto;
range.min_addr = range.max_addr = this->saved_addr;
nf_nat_setup_info(new, &range, NF_NAT_MANIP_DST);
}
/****************************************************************************/
static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
unsigned char **data, int dataoff,
TransportAddress *taddr, __be16 port,
struct nf_conntrack_expect *exp)
{
int dir = CTINFO2DIR(ctinfo);
u_int16_t nated_port;
/* Set expectations for NAT */
exp->saved_addr = exp->tuple.dst.u3;
exp->tuple.dst.u3.ip = ct->tuplehash[!dir].tuple.dst.u3.ip;
exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port;
exp->expectfn = ip_nat_callforwarding_expect;
exp->dir = !dir;
/* Try to get same port: if not, try to change it. */
for (nated_port = ntohs(port); nated_port != 0; nated_port++) {
int ret;
exp->tuple.dst.u.tcp.port = htons(nated_port);
ret = nf_ct_expect_related(exp);
if (ret == 0)
break;
else if (ret != -EBUSY) {
nated_port = 0;
break;
}
}
if (nated_port == 0) { /* No port available */
net_notice_ratelimited("nf_nat_q931: out of TCP ports\n");
return 0;
}
/* Modify signal */
if (set_h225_addr(skb, protoff, data, dataoff, taddr,
&ct->tuplehash[!dir].tuple.dst.u3,
htons(nated_port))) {
nf_ct_unexpect_related(exp);
return -1;
}
/* Success */
pr_debug("nf_nat_q931: expect Call Forwarding %pI4:%hu->%pI4:%hu\n",
&exp->tuple.src.u3.ip,
ntohs(exp->tuple.src.u.tcp.port),
&exp->tuple.dst.u3.ip,
ntohs(exp->tuple.dst.u.tcp.port));
return 0;
}
static struct nf_ct_helper_expectfn q931_nat = {
.name = "Q.931",
.expectfn = ip_nat_q931_expect,
};
static struct nf_ct_helper_expectfn callforwarding_nat = {
.name = "callforwarding",
.expectfn = ip_nat_callforwarding_expect,
};
/****************************************************************************/
static int __init init(void)
{
BUG_ON(set_h245_addr_hook != NULL);
BUG_ON(set_h225_addr_hook != NULL);
BUG_ON(set_sig_addr_hook != NULL);
BUG_ON(set_ras_addr_hook != NULL);
BUG_ON(nat_rtp_rtcp_hook != NULL);
BUG_ON(nat_t120_hook != NULL);
BUG_ON(nat_h245_hook != NULL);
BUG_ON(nat_callforwarding_hook != NULL);
BUG_ON(nat_q931_hook != NULL);
RCU_INIT_POINTER(set_h245_addr_hook, set_h245_addr);
RCU_INIT_POINTER(set_h225_addr_hook, set_h225_addr);
RCU_INIT_POINTER(set_sig_addr_hook, set_sig_addr);
RCU_INIT_POINTER(set_ras_addr_hook, set_ras_addr);
RCU_INIT_POINTER(nat_rtp_rtcp_hook, nat_rtp_rtcp);
RCU_INIT_POINTER(nat_t120_hook, nat_t120);
RCU_INIT_POINTER(nat_h245_hook, nat_h245);
RCU_INIT_POINTER(nat_callforwarding_hook, nat_callforwarding);
RCU_INIT_POINTER(nat_q931_hook, nat_q931);
nf_ct_helper_expectfn_register(&q931_nat);
nf_ct_helper_expectfn_register(&callforwarding_nat);
return 0;
}
/****************************************************************************/
static void __exit fini(void)
{
RCU_INIT_POINTER(set_h245_addr_hook, NULL);
RCU_INIT_POINTER(set_h225_addr_hook, NULL);
RCU_INIT_POINTER(set_sig_addr_hook, NULL);
RCU_INIT_POINTER(set_ras_addr_hook, NULL);
RCU_INIT_POINTER(nat_rtp_rtcp_hook, NULL);
RCU_INIT_POINTER(nat_t120_hook, NULL);
RCU_INIT_POINTER(nat_h245_hook, NULL);
RCU_INIT_POINTER(nat_callforwarding_hook, NULL);
RCU_INIT_POINTER(nat_q931_hook, NULL);
nf_ct_helper_expectfn_unregister(&q931_nat);
nf_ct_helper_expectfn_unregister(&callforwarding_nat);
synchronize_rcu();
}
/****************************************************************************/
module_init(init);
module_exit(fini);
MODULE_AUTHOR("Jing Min Zhao <zhaojingmin@users.sourceforge.net>");
MODULE_DESCRIPTION("H.323 NAT helper");
MODULE_LICENSE("GPL");
MODULE_ALIAS("ip_nat_h323");
+421
View File
@@ -0,0 +1,421 @@
/*
* (C) 1999-2001 Paul `Rusty' Russell
* (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
* (C) 2011 Patrick McHardy <kaber@trash.net>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/types.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/ip.h>
#include <linux/icmp.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>
#include <net/secure_seq.h>
#include <net/checksum.h>
#include <net/route.h>
#include <net/ip.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_nat_l3proto.h>
#include <net/netfilter/nf_nat_l4proto.h>
static const struct nf_nat_l3proto nf_nat_l3proto_ipv4;
#ifdef CONFIG_XFRM
static void nf_nat_ipv4_decode_session(struct sk_buff *skb,
const struct nf_conn *ct,
enum ip_conntrack_dir dir,
unsigned long statusbit,
struct flowi *fl)
{
const struct nf_conntrack_tuple *t = &ct->tuplehash[dir].tuple;
struct flowi4 *fl4 = &fl->u.ip4;
if (ct->status & statusbit) {
fl4->daddr = t->dst.u3.ip;
if (t->dst.protonum == IPPROTO_TCP ||
t->dst.protonum == IPPROTO_UDP ||
t->dst.protonum == IPPROTO_UDPLITE ||
t->dst.protonum == IPPROTO_DCCP ||
t->dst.protonum == IPPROTO_SCTP)
fl4->fl4_dport = t->dst.u.all;
}
statusbit ^= IPS_NAT_MASK;
if (ct->status & statusbit) {
fl4->saddr = t->src.u3.ip;
if (t->dst.protonum == IPPROTO_TCP ||
t->dst.protonum == IPPROTO_UDP ||
t->dst.protonum == IPPROTO_UDPLITE ||
t->dst.protonum == IPPROTO_DCCP ||
t->dst.protonum == IPPROTO_SCTP)
fl4->fl4_sport = t->src.u.all;
}
}
#endif /* CONFIG_XFRM */
static bool nf_nat_ipv4_in_range(const struct nf_conntrack_tuple *t,
const struct nf_nat_range2 *range)
{
return ntohl(t->src.u3.ip) >= ntohl(range->min_addr.ip) &&
ntohl(t->src.u3.ip) <= ntohl(range->max_addr.ip);
}
static u32 nf_nat_ipv4_secure_port(const struct nf_conntrack_tuple *t,
__be16 dport)
{
return secure_ipv4_port_ephemeral(t->src.u3.ip, t->dst.u3.ip, dport);
}
static bool nf_nat_ipv4_manip_pkt(struct sk_buff *skb,
unsigned int iphdroff,
const struct nf_nat_l4proto *l4proto,
const struct nf_conntrack_tuple *target,
enum nf_nat_manip_type maniptype)
{
struct iphdr *iph;
unsigned int hdroff;
if (!skb_make_writable(skb, iphdroff + sizeof(*iph)))
return false;
iph = (void *)skb->data + iphdroff;
hdroff = iphdroff + iph->ihl * 4;
if (!l4proto->manip_pkt(skb, &nf_nat_l3proto_ipv4, iphdroff, hdroff,
target, maniptype))
return false;
iph = (void *)skb->data + iphdroff;
if (maniptype == NF_NAT_MANIP_SRC) {
csum_replace4(&iph->check, iph->saddr, target->src.u3.ip);
iph->saddr = target->src.u3.ip;
} else {
csum_replace4(&iph->check, iph->daddr, target->dst.u3.ip);
iph->daddr = target->dst.u3.ip;
}
return true;
}
static void nf_nat_ipv4_csum_update(struct sk_buff *skb,
unsigned int iphdroff, __sum16 *check,
const struct nf_conntrack_tuple *t,
enum nf_nat_manip_type maniptype)
{
struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff);
__be32 oldip, newip;
if (maniptype == NF_NAT_MANIP_SRC) {
oldip = iph->saddr;
newip = t->src.u3.ip;
} else {
oldip = iph->daddr;
newip = t->dst.u3.ip;
}
inet_proto_csum_replace4(check, skb, oldip, newip, true);
}
static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb,
u8 proto, void *data, __sum16 *check,
int datalen, int oldlen)
{
if (skb->ip_summed != CHECKSUM_PARTIAL) {
const struct iphdr *iph = ip_hdr(skb);
skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) +
ip_hdrlen(skb);
skb->csum_offset = (void *)check - data;
*check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, datalen,
proto, 0);
} else
inet_proto_csum_replace2(check, skb,
htons(oldlen), htons(datalen), true);
}
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
static int nf_nat_ipv4_nlattr_to_range(struct nlattr *tb[],
struct nf_nat_range2 *range)
{
if (tb[CTA_NAT_V4_MINIP]) {
range->min_addr.ip = nla_get_be32(tb[CTA_NAT_V4_MINIP]);
range->flags |= NF_NAT_RANGE_MAP_IPS;
}
if (tb[CTA_NAT_V4_MAXIP])
range->max_addr.ip = nla_get_be32(tb[CTA_NAT_V4_MAXIP]);
else
range->max_addr.ip = range->min_addr.ip;
return 0;
}
#endif
static const struct nf_nat_l3proto nf_nat_l3proto_ipv4 = {
.l3proto = NFPROTO_IPV4,
.in_range = nf_nat_ipv4_in_range,
.secure_port = nf_nat_ipv4_secure_port,
.manip_pkt = nf_nat_ipv4_manip_pkt,
.csum_update = nf_nat_ipv4_csum_update,
.csum_recalc = nf_nat_ipv4_csum_recalc,
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.nlattr_to_range = nf_nat_ipv4_nlattr_to_range,
#endif
#ifdef CONFIG_XFRM
.decode_session = nf_nat_ipv4_decode_session,
#endif
};
int nf_nat_icmp_reply_translation(struct sk_buff *skb,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int hooknum)
{
struct {
struct icmphdr icmp;
struct iphdr ip;
} *inside;
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
enum nf_nat_manip_type manip = HOOK2MANIP(hooknum);
unsigned int hdrlen = ip_hdrlen(skb);
const struct nf_nat_l4proto *l4proto;
struct nf_conntrack_tuple target;
unsigned long statusbit;
WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY);
if (!skb_make_writable(skb, hdrlen + sizeof(*inside)))
return 0;
if (nf_ip_checksum(skb, hooknum, hdrlen, 0))
return 0;
inside = (void *)skb->data + hdrlen;
if (inside->icmp.type == ICMP_REDIRECT) {
if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK)
return 0;
if (ct->status & IPS_NAT_MASK)
return 0;
}
if (manip == NF_NAT_MANIP_SRC)
statusbit = IPS_SRC_NAT;
else
statusbit = IPS_DST_NAT;
/* Invert if this is reply direction */
if (dir == IP_CT_DIR_REPLY)
statusbit ^= IPS_NAT_MASK;
if (!(ct->status & statusbit))
return 1;
l4proto = __nf_nat_l4proto_find(NFPROTO_IPV4, inside->ip.protocol);
if (!nf_nat_ipv4_manip_pkt(skb, hdrlen + sizeof(inside->icmp),
l4proto, &ct->tuplehash[!dir].tuple, !manip))
return 0;
if (skb->ip_summed != CHECKSUM_PARTIAL) {
/* Reloading "inside" here since manip_pkt may reallocate */
inside = (void *)skb->data + hdrlen;
inside->icmp.checksum = 0;
inside->icmp.checksum =
csum_fold(skb_checksum(skb, hdrlen,
skb->len - hdrlen, 0));
}
/* Change outer to look like the reply to an incoming packet */
nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple);
l4proto = __nf_nat_l4proto_find(NFPROTO_IPV4, 0);
if (!nf_nat_ipv4_manip_pkt(skb, 0, l4proto, &target, manip))
return 0;
return 1;
}
EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation);
unsigned int
nf_nat_ipv4_fn(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
ct = nf_ct_get(skb, &ctinfo);
if (!ct)
return NF_ACCEPT;
if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) {
if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
state->hook))
return NF_DROP;
else
return NF_ACCEPT;
}
}
return nf_nat_inet_fn(priv, skb, state);
}
EXPORT_SYMBOL_GPL(nf_nat_ipv4_fn);
static unsigned int
nf_nat_ipv4_in(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
unsigned int ret;
__be32 daddr = ip_hdr(skb)->daddr;
ret = nf_nat_ipv4_fn(priv, skb, state);
if (ret != NF_DROP && ret != NF_STOLEN &&
daddr != ip_hdr(skb)->daddr)
skb_dst_drop(skb);
return ret;
}
static unsigned int
nf_nat_ipv4_out(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
#ifdef CONFIG_XFRM
const struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
int err;
#endif
unsigned int ret;
ret = nf_nat_ipv4_fn(priv, skb, state);
#ifdef CONFIG_XFRM
if (ret != NF_DROP && ret != NF_STOLEN &&
!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
(ct = nf_ct_get(skb, &ctinfo)) != NULL) {
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
if ((ct->tuplehash[dir].tuple.src.u3.ip !=
ct->tuplehash[!dir].tuple.dst.u3.ip) ||
(ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
ct->tuplehash[dir].tuple.src.u.all !=
ct->tuplehash[!dir].tuple.dst.u.all)) {
err = nf_xfrm_me_harder(state->net, skb, AF_INET);
if (err < 0)
ret = NF_DROP_ERR(err);
}
}
#endif
return ret;
}
static unsigned int
nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
const struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
unsigned int ret;
int err;
ret = nf_nat_ipv4_fn(priv, skb, state);
if (ret != NF_DROP && ret != NF_STOLEN &&
(ct = nf_ct_get(skb, &ctinfo)) != NULL) {
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
if (ct->tuplehash[dir].tuple.dst.u3.ip !=
ct->tuplehash[!dir].tuple.src.u3.ip) {
err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
if (err < 0)
ret = NF_DROP_ERR(err);
}
#ifdef CONFIG_XFRM
else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
ct->tuplehash[dir].tuple.dst.u.all !=
ct->tuplehash[!dir].tuple.src.u.all) {
err = nf_xfrm_me_harder(state->net, skb, AF_INET);
if (err < 0)
ret = NF_DROP_ERR(err);
}
#endif
}
return ret;
}
static const struct nf_hook_ops nf_nat_ipv4_ops[] = {
/* Before packet filtering, change destination */
{
.hook = nf_nat_ipv4_in,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_PRE_ROUTING,
.priority = NF_IP_PRI_NAT_DST,
},
/* After packet filtering, change source */
{
.hook = nf_nat_ipv4_out,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_POST_ROUTING,
.priority = NF_IP_PRI_NAT_SRC,
},
/* Before packet filtering, change destination */
{
.hook = nf_nat_ipv4_local_fn,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_LOCAL_OUT,
.priority = NF_IP_PRI_NAT_DST,
},
/* After packet filtering, change source */
{
.hook = nf_nat_ipv4_fn,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_LOCAL_IN,
.priority = NF_IP_PRI_NAT_SRC,
},
};
int nf_nat_l3proto_ipv4_register_fn(struct net *net, const struct nf_hook_ops *ops)
{
return nf_nat_register_fn(net, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops));
}
EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv4_register_fn);
void nf_nat_l3proto_ipv4_unregister_fn(struct net *net, const struct nf_hook_ops *ops)
{
nf_nat_unregister_fn(net, ops, ARRAY_SIZE(nf_nat_ipv4_ops));
}
EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv4_unregister_fn);
static int __init nf_nat_l3proto_ipv4_init(void)
{
int err;
err = nf_nat_l4proto_register(NFPROTO_IPV4, &nf_nat_l4proto_icmp);
if (err < 0)
goto err1;
err = nf_nat_l3proto_register(&nf_nat_l3proto_ipv4);
if (err < 0)
goto err2;
return err;
err2:
nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_icmp);
err1:
return err;
}
static void __exit nf_nat_l3proto_ipv4_exit(void)
{
nf_nat_l3proto_unregister(&nf_nat_l3proto_ipv4);
nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_icmp);
}
MODULE_LICENSE("GPL");
MODULE_ALIAS("nf-nat-" __stringify(AF_INET));
module_init(nf_nat_l3proto_ipv4_init);
module_exit(nf_nat_l3proto_ipv4_exit);
+196
View File
@@ -0,0 +1,196 @@
/* (C) 1999-2001 Paul `Rusty' Russell
* (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/types.h>
#include <linux/atomic.h>
#include <linux/inetdevice.h>
#include <linux/ip.h>
#include <linux/timer.h>
#include <linux/netfilter.h>
#include <net/protocol.h>
#include <net/ip.h>
#include <net/checksum.h>
#include <net/route.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter/x_tables.h>
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/ipv4/nf_nat_masquerade.h>
unsigned int
nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
const struct nf_nat_range2 *range,
const struct net_device *out)
{
struct nf_conn *ct;
struct nf_conn_nat *nat;
enum ip_conntrack_info ctinfo;
struct nf_nat_range2 newrange;
const struct rtable *rt;
__be32 newsrc, nh;
WARN_ON(hooknum != NF_INET_POST_ROUTING);
ct = nf_ct_get(skb, &ctinfo);
WARN_ON(!(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
ctinfo == IP_CT_RELATED_REPLY)));
/* Source address is 0.0.0.0 - locally generated packet that is
* probably not supposed to be masqueraded.
*/
if (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip == 0)
return NF_ACCEPT;
rt = skb_rtable(skb);
nh = rt_nexthop(rt, ip_hdr(skb)->daddr);
newsrc = inet_select_addr(out, nh, RT_SCOPE_UNIVERSE);
if (!newsrc) {
pr_info("%s ate my IP address\n", out->name);
return NF_DROP;
}
nat = nf_ct_nat_ext_add(ct);
if (nat)
nat->masq_index = out->ifindex;
/* Transfer from original range. */
memset(&newrange.min_addr, 0, sizeof(newrange.min_addr));
memset(&newrange.max_addr, 0, sizeof(newrange.max_addr));
newrange.flags = range->flags | NF_NAT_RANGE_MAP_IPS;
newrange.min_addr.ip = newsrc;
newrange.max_addr.ip = newsrc;
newrange.min_proto = range->min_proto;
newrange.max_proto = range->max_proto;
/* Hand modified range to generic setup. */
return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);
}
EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4);
static int device_cmp(struct nf_conn *i, void *ifindex)
{
const struct nf_conn_nat *nat = nfct_nat(i);
if (!nat)
return 0;
if (nf_ct_l3num(i) != NFPROTO_IPV4)
return 0;
return nat->masq_index == (int)(long)ifindex;
}
static int masq_device_event(struct notifier_block *this,
unsigned long event,
void *ptr)
{
const struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net *net = dev_net(dev);
if (event == NETDEV_DOWN) {
/* Device was downed. Search entire table for
* conntracks which were associated with that device,
* and forget them.
*/
WARN_ON(dev->ifindex == 0);
nf_ct_iterate_cleanup_net(net, device_cmp,
(void *)(long)dev->ifindex, 0, 0);
}
return NOTIFY_DONE;
}
static int inet_cmp(struct nf_conn *ct, void *ptr)
{
struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
struct net_device *dev = ifa->ifa_dev->dev;
struct nf_conntrack_tuple *tuple;
if (!device_cmp(ct, (void *)(long)dev->ifindex))
return 0;
tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple;
return ifa->ifa_address == tuple->dst.u3.ip;
}
static int masq_inet_event(struct notifier_block *this,
unsigned long event,
void *ptr)
{
struct in_device *idev = ((struct in_ifaddr *)ptr)->ifa_dev;
struct net *net = dev_net(idev->dev);
/* The masq_dev_notifier will catch the case of the device going
* down. So if the inetdev is dead and being destroyed we have
* no work to do. Otherwise this is an individual address removal
* and we have to perform the flush.
*/
if (idev->dead)
return NOTIFY_DONE;
if (event == NETDEV_DOWN)
nf_ct_iterate_cleanup_net(net, inet_cmp, ptr, 0, 0);
return NOTIFY_DONE;
}
static struct notifier_block masq_dev_notifier = {
.notifier_call = masq_device_event,
};
static struct notifier_block masq_inet_notifier = {
.notifier_call = masq_inet_event,
};
static int masq_refcnt;
static DEFINE_MUTEX(masq_mutex);
int nf_nat_masquerade_ipv4_register_notifier(void)
{
int ret = 0;
mutex_lock(&masq_mutex);
/* check if the notifier was already set */
if (++masq_refcnt > 1)
goto out_unlock;
/* Register for device down reports */
ret = register_netdevice_notifier(&masq_dev_notifier);
if (ret)
goto err_dec;
/* Register IP address change reports */
ret = register_inetaddr_notifier(&masq_inet_notifier);
if (ret)
goto err_unregister;
mutex_unlock(&masq_mutex);
return ret;
err_unregister:
unregister_netdevice_notifier(&masq_dev_notifier);
err_dec:
masq_refcnt--;
out_unlock:
mutex_unlock(&masq_mutex);
return ret;
}
EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_register_notifier);
void nf_nat_masquerade_ipv4_unregister_notifier(void)
{
mutex_lock(&masq_mutex);
/* check if the notifier still has clients */
if (--masq_refcnt > 0)
goto out_unlock;
unregister_netdevice_notifier(&masq_dev_notifier);
unregister_inetaddr_notifier(&masq_inet_notifier);
out_unlock:
mutex_unlock(&masq_mutex);
}
EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_unregister_notifier);
+325
View File
@@ -0,0 +1,325 @@
/*
* nf_nat_pptp.c
*
* NAT support for PPTP (Point to Point Tunneling Protocol).
* PPTP is a a protocol for creating virtual private networks.
* It is a specification defined by Microsoft and some vendors
* working with Microsoft. PPTP is built on top of a modified
* version of the Internet Generic Routing Encapsulation Protocol.
* GRE is defined in RFC 1701 and RFC 1702. Documentation of
* PPTP can be found in RFC 2637
*
* (C) 2000-2005 by Harald Welte <laforge@gnumonks.org>
*
* Development of this code funded by Astaro AG (http://www.astaro.com/)
*
* (C) 2006-2012 Patrick McHardy <kaber@trash.net>
*
* TODO: - NAT to a unique tuple, not to TCP source port
* (needs netfilter tuple reservation)
*/
#include <linux/module.h>
#include <linux/tcp.h>
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_helper.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_expect.h>
#include <net/netfilter/nf_conntrack_zones.h>
#include <linux/netfilter/nf_conntrack_proto_gre.h>
#include <linux/netfilter/nf_conntrack_pptp.h>
#define NF_NAT_PPTP_VERSION "3.0"
#define REQ_CID(req, off) (*(__be16 *)((char *)(req) + (off)))
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Harald Welte <laforge@gnumonks.org>");
MODULE_DESCRIPTION("Netfilter NAT helper module for PPTP");
MODULE_ALIAS("ip_nat_pptp");
static void pptp_nat_expected(struct nf_conn *ct,
struct nf_conntrack_expect *exp)
{
struct net *net = nf_ct_net(ct);
const struct nf_conn *master = ct->master;
struct nf_conntrack_expect *other_exp;
struct nf_conntrack_tuple t = {};
const struct nf_ct_pptp_master *ct_pptp_info;
const struct nf_nat_pptp *nat_pptp_info;
struct nf_nat_range2 range;
struct nf_conn_nat *nat;
nat = nf_ct_nat_ext_add(ct);
if (WARN_ON_ONCE(!nat))
return;
nat_pptp_info = &nat->help.nat_pptp_info;
ct_pptp_info = nfct_help_data(master);
/* And here goes the grand finale of corrosion... */
if (exp->dir == IP_CT_DIR_ORIGINAL) {
pr_debug("we are PNS->PAC\n");
/* therefore, build tuple for PAC->PNS */
t.src.l3num = AF_INET;
t.src.u3.ip = master->tuplehash[!exp->dir].tuple.src.u3.ip;
t.src.u.gre.key = ct_pptp_info->pac_call_id;
t.dst.u3.ip = master->tuplehash[!exp->dir].tuple.dst.u3.ip;
t.dst.u.gre.key = ct_pptp_info->pns_call_id;
t.dst.protonum = IPPROTO_GRE;
} else {
pr_debug("we are PAC->PNS\n");
/* build tuple for PNS->PAC */
t.src.l3num = AF_INET;
t.src.u3.ip = master->tuplehash[!exp->dir].tuple.src.u3.ip;
t.src.u.gre.key = nat_pptp_info->pns_call_id;
t.dst.u3.ip = master->tuplehash[!exp->dir].tuple.dst.u3.ip;
t.dst.u.gre.key = nat_pptp_info->pac_call_id;
t.dst.protonum = IPPROTO_GRE;
}
pr_debug("trying to unexpect other dir: ");
nf_ct_dump_tuple_ip(&t);
other_exp = nf_ct_expect_find_get(net, nf_ct_zone(ct), &t);
if (other_exp) {
nf_ct_unexpect_related(other_exp);
nf_ct_expect_put(other_exp);
pr_debug("success\n");
} else {
pr_debug("not found!\n");
}
/* This must be a fresh one. */
BUG_ON(ct->status & IPS_NAT_DONE_MASK);
/* Change src to where master sends to */
range.flags = NF_NAT_RANGE_MAP_IPS;
range.min_addr = range.max_addr
= ct->master->tuplehash[!exp->dir].tuple.dst.u3;
if (exp->dir == IP_CT_DIR_ORIGINAL) {
range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
range.min_proto = range.max_proto = exp->saved_proto;
}
nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC);
/* For DST manip, map port here to where it's expected. */
range.flags = NF_NAT_RANGE_MAP_IPS;
range.min_addr = range.max_addr
= ct->master->tuplehash[!exp->dir].tuple.src.u3;
if (exp->dir == IP_CT_DIR_REPLY) {
range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
range.min_proto = range.max_proto = exp->saved_proto;
}
nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST);
}
/* outbound packets == from PNS to PAC */
static int
pptp_outbound_pkt(struct sk_buff *skb,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
struct PptpControlHeader *ctlh,
union pptp_ctrl_union *pptpReq)
{
struct nf_ct_pptp_master *ct_pptp_info;
struct nf_conn_nat *nat = nfct_nat(ct);
struct nf_nat_pptp *nat_pptp_info;
u_int16_t msg;
__be16 new_callid;
unsigned int cid_off;
if (WARN_ON_ONCE(!nat))
return NF_DROP;
nat_pptp_info = &nat->help.nat_pptp_info;
ct_pptp_info = nfct_help_data(ct);
new_callid = ct_pptp_info->pns_call_id;
switch (msg = ntohs(ctlh->messageType)) {
case PPTP_OUT_CALL_REQUEST:
cid_off = offsetof(union pptp_ctrl_union, ocreq.callID);
/* FIXME: ideally we would want to reserve a call ID
* here. current netfilter NAT core is not able to do
* this :( For now we use TCP source port. This breaks
* multiple calls within one control session */
/* save original call ID in nat_info */
nat_pptp_info->pns_call_id = ct_pptp_info->pns_call_id;
/* don't use tcph->source since we are at a DSTmanip
* hook (e.g. PREROUTING) and pkt is not mangled yet */
new_callid = ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u.tcp.port;
/* save new call ID in ct info */
ct_pptp_info->pns_call_id = new_callid;
break;
case PPTP_IN_CALL_REPLY:
cid_off = offsetof(union pptp_ctrl_union, icack.callID);
break;
case PPTP_CALL_CLEAR_REQUEST:
cid_off = offsetof(union pptp_ctrl_union, clrreq.callID);
break;
default:
pr_debug("unknown outbound packet 0x%04x:%s\n", msg,
pptp_msg_name(msg));
/* fall through */
case PPTP_SET_LINK_INFO:
/* only need to NAT in case PAC is behind NAT box */
case PPTP_START_SESSION_REQUEST:
case PPTP_START_SESSION_REPLY:
case PPTP_STOP_SESSION_REQUEST:
case PPTP_STOP_SESSION_REPLY:
case PPTP_ECHO_REQUEST:
case PPTP_ECHO_REPLY:
/* no need to alter packet */
return NF_ACCEPT;
}
/* only OUT_CALL_REQUEST, IN_CALL_REPLY, CALL_CLEAR_REQUEST pass
* down to here */
pr_debug("altering call id from 0x%04x to 0x%04x\n",
ntohs(REQ_CID(pptpReq, cid_off)), ntohs(new_callid));
/* mangle packet */
if (!nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff,
cid_off + sizeof(struct pptp_pkt_hdr) +
sizeof(struct PptpControlHeader),
sizeof(new_callid), (char *)&new_callid,
sizeof(new_callid)))
return NF_DROP;
return NF_ACCEPT;
}
static void
pptp_exp_gre(struct nf_conntrack_expect *expect_orig,
struct nf_conntrack_expect *expect_reply)
{
const struct nf_conn *ct = expect_orig->master;
struct nf_conn_nat *nat = nfct_nat(ct);
struct nf_ct_pptp_master *ct_pptp_info;
struct nf_nat_pptp *nat_pptp_info;
if (WARN_ON_ONCE(!nat))
return;
nat_pptp_info = &nat->help.nat_pptp_info;
ct_pptp_info = nfct_help_data(ct);
/* save original PAC call ID in nat_info */
nat_pptp_info->pac_call_id = ct_pptp_info->pac_call_id;
/* alter expectation for PNS->PAC direction */
expect_orig->saved_proto.gre.key = ct_pptp_info->pns_call_id;
expect_orig->tuple.src.u.gre.key = nat_pptp_info->pns_call_id;
expect_orig->tuple.dst.u.gre.key = ct_pptp_info->pac_call_id;
expect_orig->dir = IP_CT_DIR_ORIGINAL;
/* alter expectation for PAC->PNS direction */
expect_reply->saved_proto.gre.key = nat_pptp_info->pns_call_id;
expect_reply->tuple.src.u.gre.key = nat_pptp_info->pac_call_id;
expect_reply->tuple.dst.u.gre.key = ct_pptp_info->pns_call_id;
expect_reply->dir = IP_CT_DIR_REPLY;
}
/* inbound packets == from PAC to PNS */
static int
pptp_inbound_pkt(struct sk_buff *skb,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
struct PptpControlHeader *ctlh,
union pptp_ctrl_union *pptpReq)
{
const struct nf_nat_pptp *nat_pptp_info;
struct nf_conn_nat *nat = nfct_nat(ct);
u_int16_t msg;
__be16 new_pcid;
unsigned int pcid_off;
if (WARN_ON_ONCE(!nat))
return NF_DROP;
nat_pptp_info = &nat->help.nat_pptp_info;
new_pcid = nat_pptp_info->pns_call_id;
switch (msg = ntohs(ctlh->messageType)) {
case PPTP_OUT_CALL_REPLY:
pcid_off = offsetof(union pptp_ctrl_union, ocack.peersCallID);
break;
case PPTP_IN_CALL_CONNECT:
pcid_off = offsetof(union pptp_ctrl_union, iccon.peersCallID);
break;
case PPTP_IN_CALL_REQUEST:
/* only need to nat in case PAC is behind NAT box */
return NF_ACCEPT;
case PPTP_WAN_ERROR_NOTIFY:
pcid_off = offsetof(union pptp_ctrl_union, wanerr.peersCallID);
break;
case PPTP_CALL_DISCONNECT_NOTIFY:
pcid_off = offsetof(union pptp_ctrl_union, disc.callID);
break;
case PPTP_SET_LINK_INFO:
pcid_off = offsetof(union pptp_ctrl_union, setlink.peersCallID);
break;
default:
pr_debug("unknown inbound packet %s\n", pptp_msg_name(msg));
/* fall through */
case PPTP_START_SESSION_REQUEST:
case PPTP_START_SESSION_REPLY:
case PPTP_STOP_SESSION_REQUEST:
case PPTP_STOP_SESSION_REPLY:
case PPTP_ECHO_REQUEST:
case PPTP_ECHO_REPLY:
/* no need to alter packet */
return NF_ACCEPT;
}
/* only OUT_CALL_REPLY, IN_CALL_CONNECT, IN_CALL_REQUEST,
* WAN_ERROR_NOTIFY, CALL_DISCONNECT_NOTIFY pass down here */
/* mangle packet */
pr_debug("altering peer call id from 0x%04x to 0x%04x\n",
ntohs(REQ_CID(pptpReq, pcid_off)), ntohs(new_pcid));
if (!nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff,
pcid_off + sizeof(struct pptp_pkt_hdr) +
sizeof(struct PptpControlHeader),
sizeof(new_pcid), (char *)&new_pcid,
sizeof(new_pcid)))
return NF_DROP;
return NF_ACCEPT;
}
static int __init nf_nat_helper_pptp_init(void)
{
nf_nat_need_gre();
BUG_ON(nf_nat_pptp_hook_outbound != NULL);
RCU_INIT_POINTER(nf_nat_pptp_hook_outbound, pptp_outbound_pkt);
BUG_ON(nf_nat_pptp_hook_inbound != NULL);
RCU_INIT_POINTER(nf_nat_pptp_hook_inbound, pptp_inbound_pkt);
BUG_ON(nf_nat_pptp_hook_exp_gre != NULL);
RCU_INIT_POINTER(nf_nat_pptp_hook_exp_gre, pptp_exp_gre);
BUG_ON(nf_nat_pptp_hook_expectfn != NULL);
RCU_INIT_POINTER(nf_nat_pptp_hook_expectfn, pptp_nat_expected);
return 0;
}
static void __exit nf_nat_helper_pptp_fini(void)
{
RCU_INIT_POINTER(nf_nat_pptp_hook_expectfn, NULL);
RCU_INIT_POINTER(nf_nat_pptp_hook_exp_gre, NULL);
RCU_INIT_POINTER(nf_nat_pptp_hook_inbound, NULL);
RCU_INIT_POINTER(nf_nat_pptp_hook_outbound, NULL);
synchronize_rcu();
}
module_init(nf_nat_helper_pptp_init);
module_exit(nf_nat_helper_pptp_fini);
+150
View File
@@ -0,0 +1,150 @@
/*
* nf_nat_proto_gre.c
*
* NAT protocol helper module for GRE.
*
* GRE is a generic encapsulation protocol, which is generally not very
* suited for NAT, as it has no protocol-specific part as port numbers.
*
* It has an optional key field, which may help us distinguishing two
* connections between the same two hosts.
*
* GRE is defined in RFC 1701 and RFC 1702, as well as RFC 2784
*
* PPTP is built on top of a modified version of GRE, and has a mandatory
* field called "CallID", which serves us for the same purpose as the key
* field in plain GRE.
*
* Documentation about PPTP can be found in RFC 2637
*
* (C) 2000-2005 by Harald Welte <laforge@gnumonks.org>
*
* Development of this code funded by Astaro AG (http://www.astaro.com/)
*
* (C) 2006-2012 Patrick McHardy <kaber@trash.net>
*
*/
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/ip.h>
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_l4proto.h>
#include <linux/netfilter/nf_conntrack_proto_gre.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Harald Welte <laforge@gnumonks.org>");
MODULE_DESCRIPTION("Netfilter NAT protocol helper module for GRE");
/* generate unique tuple ... */
static void
gre_unique_tuple(const struct nf_nat_l3proto *l3proto,
struct nf_conntrack_tuple *tuple,
const struct nf_nat_range2 *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
static u_int16_t key;
__be16 *keyptr;
unsigned int min, i, range_size;
/* If there is no master conntrack we are not PPTP,
do not change tuples */
if (!ct->master)
return;
if (maniptype == NF_NAT_MANIP_SRC)
keyptr = &tuple->src.u.gre.key;
else
keyptr = &tuple->dst.u.gre.key;
if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) {
pr_debug("%p: NATing GRE PPTP\n", ct);
min = 1;
range_size = 0xffff;
} else {
min = ntohs(range->min_proto.gre.key);
range_size = ntohs(range->max_proto.gre.key) - min + 1;
}
pr_debug("min = %u, range_size = %u\n", min, range_size);
for (i = 0; ; ++key) {
*keyptr = htons(min + key % range_size);
if (++i == range_size || !nf_nat_used_tuple(tuple, ct))
return;
}
pr_debug("%p: no NAT mapping\n", ct);
return;
}
/* manipulate a GRE packet according to maniptype */
static bool
gre_manip_pkt(struct sk_buff *skb,
const struct nf_nat_l3proto *l3proto,
unsigned int iphdroff, unsigned int hdroff,
const struct nf_conntrack_tuple *tuple,
enum nf_nat_manip_type maniptype)
{
const struct gre_base_hdr *greh;
struct pptp_gre_header *pgreh;
/* pgreh includes two optional 32bit fields which are not required
* to be there. That's where the magic '8' comes from */
if (!skb_make_writable(skb, hdroff + sizeof(*pgreh) - 8))
return false;
greh = (void *)skb->data + hdroff;
pgreh = (struct pptp_gre_header *)greh;
/* we only have destination manip of a packet, since 'source key'
* is not present in the packet itself */
if (maniptype != NF_NAT_MANIP_DST)
return true;
switch (greh->flags & GRE_VERSION) {
case GRE_VERSION_0:
/* We do not currently NAT any GREv0 packets.
* Try to behave like "nf_nat_proto_unknown" */
break;
case GRE_VERSION_1:
pr_debug("call_id -> 0x%04x\n", ntohs(tuple->dst.u.gre.key));
pgreh->call_id = tuple->dst.u.gre.key;
break;
default:
pr_debug("can't nat unknown GRE version\n");
return false;
}
return true;
}
static const struct nf_nat_l4proto gre = {
.l4proto = IPPROTO_GRE,
.manip_pkt = gre_manip_pkt,
.in_range = nf_nat_l4proto_in_range,
.unique_tuple = gre_unique_tuple,
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.nlattr_to_range = nf_nat_l4proto_nlattr_to_range,
#endif
};
static int __init nf_nat_proto_gre_init(void)
{
return nf_nat_l4proto_register(NFPROTO_IPV4, &gre);
}
static void __exit nf_nat_proto_gre_fini(void)
{
nf_nat_l4proto_unregister(NFPROTO_IPV4, &gre);
}
module_init(nf_nat_proto_gre_init);
module_exit(nf_nat_proto_gre_fini);
void nf_nat_need_gre(void)
{
return;
}
EXPORT_SYMBOL_GPL(nf_nat_need_gre);
+83
View File
@@ -0,0 +1,83 @@
/* (C) 1999-2001 Paul `Rusty' Russell
* (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/types.h>
#include <linux/init.h>
#include <linux/export.h>
#include <linux/ip.h>
#include <linux/icmp.h>
#include <linux/netfilter.h>
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_nat_l4proto.h>
static bool
icmp_in_range(const struct nf_conntrack_tuple *tuple,
enum nf_nat_manip_type maniptype,
const union nf_conntrack_man_proto *min,
const union nf_conntrack_man_proto *max)
{
return ntohs(tuple->src.u.icmp.id) >= ntohs(min->icmp.id) &&
ntohs(tuple->src.u.icmp.id) <= ntohs(max->icmp.id);
}
static void
icmp_unique_tuple(const struct nf_nat_l3proto *l3proto,
struct nf_conntrack_tuple *tuple,
const struct nf_nat_range2 *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
static u_int16_t id;
unsigned int range_size;
unsigned int i;
range_size = ntohs(range->max_proto.icmp.id) -
ntohs(range->min_proto.icmp.id) + 1;
/* If no range specified... */
if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED))
range_size = 0xFFFF;
for (i = 0; ; ++id) {
tuple->src.u.icmp.id = htons(ntohs(range->min_proto.icmp.id) +
(id % range_size));
if (++i == range_size || !nf_nat_used_tuple(tuple, ct))
return;
}
return;
}
static bool
icmp_manip_pkt(struct sk_buff *skb,
const struct nf_nat_l3proto *l3proto,
unsigned int iphdroff, unsigned int hdroff,
const struct nf_conntrack_tuple *tuple,
enum nf_nat_manip_type maniptype)
{
struct icmphdr *hdr;
if (!skb_make_writable(skb, hdroff + sizeof(*hdr)))
return false;
hdr = (struct icmphdr *)(skb->data + hdroff);
inet_proto_csum_replace2(&hdr->checksum, skb,
hdr->un.echo.id, tuple->src.u.icmp.id, false);
hdr->un.echo.id = tuple->src.u.icmp.id;
return true;
}
const struct nf_nat_l4proto nf_nat_l4proto_icmp = {
.l4proto = IPPROTO_ICMP,
.manip_pkt = icmp_manip_pkt,
.in_range = icmp_in_range,
.unique_tuple = icmp_unique_tuple,
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.nlattr_to_range = nf_nat_l4proto_nlattr_to_range,
#endif
};
+177
View File
@@ -0,0 +1,177 @@
Message ::=
SEQUENCE {
version
INTEGER ({snmp_version}),
community
OCTET STRING,
pdu
PDUs
}
ObjectName ::=
OBJECT IDENTIFIER
ObjectSyntax ::=
CHOICE {
simple
SimpleSyntax,
application-wide
ApplicationSyntax
}
SimpleSyntax ::=
CHOICE {
integer-value
INTEGER,
string-value
OCTET STRING,
objectID-value
OBJECT IDENTIFIER
}
ApplicationSyntax ::=
CHOICE {
ipAddress-value
IpAddress,
counter-value
Counter32,
timeticks-value
TimeTicks,
arbitrary-value
Opaque,
big-counter-value
Counter64,
unsigned-integer-value
Unsigned32
}
IpAddress ::=
[APPLICATION 0]
IMPLICIT OCTET STRING OPTIONAL ({snmp_helper})
Counter32 ::=
[APPLICATION 1]
IMPLICIT INTEGER OPTIONAL
Unsigned32 ::=
[APPLICATION 2]
IMPLICIT INTEGER OPTIONAL
Gauge32 ::= Unsigned32 OPTIONAL
TimeTicks ::=
[APPLICATION 3]
IMPLICIT INTEGER OPTIONAL
Opaque ::=
[APPLICATION 4]
IMPLICIT OCTET STRING OPTIONAL
Counter64 ::=
[APPLICATION 6]
IMPLICIT INTEGER OPTIONAL
PDUs ::=
CHOICE {
get-request
GetRequest-PDU,
get-next-request
GetNextRequest-PDU,
get-bulk-request
GetBulkRequest-PDU,
response
Response-PDU,
set-request
SetRequest-PDU,
inform-request
InformRequest-PDU,
snmpV2-trap
SNMPv2-Trap-PDU,
report
Report-PDU
}
GetRequest-PDU ::=
[0] IMPLICIT PDU OPTIONAL
GetNextRequest-PDU ::=
[1] IMPLICIT PDU OPTIONAL
Response-PDU ::=
[2] IMPLICIT PDU OPTIONAL
SetRequest-PDU ::=
[3] IMPLICIT PDU OPTIONAL
-- [4] is obsolete
GetBulkRequest-PDU ::=
[5] IMPLICIT PDU OPTIONAL
InformRequest-PDU ::=
[6] IMPLICIT PDU OPTIONAL
SNMPv2-Trap-PDU ::=
[7] IMPLICIT PDU OPTIONAL
Report-PDU ::=
[8] IMPLICIT PDU OPTIONAL
PDU ::=
SEQUENCE {
request-id
INTEGER,
error-status
INTEGER,
error-index
INTEGER,
variable-bindings
VarBindList
}
VarBind ::=
SEQUENCE {
name
ObjectName,
CHOICE {
value
ObjectSyntax,
unSpecified
NULL,
noSuchObject
[0] IMPLICIT NULL,
noSuchInstance
[1] IMPLICIT NULL,
endOfMibView
[2] IMPLICIT NULL
}
}
VarBindList ::= SEQUENCE OF VarBind
+240
View File
@@ -0,0 +1,240 @@
/*
* nf_nat_snmp_basic.c
*
* Basic SNMP Application Layer Gateway
*
* This IP NAT module is intended for use with SNMP network
* discovery and monitoring applications where target networks use
* conflicting private address realms.
*
* Static NAT is used to remap the networks from the view of the network
* management system at the IP layer, and this module remaps some application
* layer addresses to match.
*
* The simplest form of ALG is performed, where only tagged IP addresses
* are modified. The module does not need to be MIB aware and only scans
* messages at the ASN.1/BER level.
*
* Currently, only SNMPv1 and SNMPv2 are supported.
*
* More information on ALG and associated issues can be found in
* RFC 2962
*
* The ASB.1/BER parsing code is derived from the gxsnmp package by Gregory
* McLean & Jochen Friedrich, stripped down for use in the kernel.
*
* Copyright (c) 2000 RP Internet (www.rpi.net.au).
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
* You should have received a copy of the GNU General Public License
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*
* Author: James Morris <jmorris@intercode.com.au>
*
* Copyright (c) 2006-2010 Patrick McHardy <kaber@trash.net>
*/
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/udp.h>
#include <net/checksum.h>
#include <net/udp.h>
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_conntrack_expect.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <linux/netfilter/nf_conntrack_snmp.h>
#include "nf_nat_snmp_basic.asn1.h"
MODULE_LICENSE("GPL");
MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>");
MODULE_DESCRIPTION("Basic SNMP Application Layer Gateway");
MODULE_ALIAS("ip_nat_snmp_basic");
#define SNMP_PORT 161
#define SNMP_TRAP_PORT 162
static DEFINE_SPINLOCK(snmp_lock);
struct snmp_ctx {
unsigned char *begin;
__sum16 *check;
__be32 from;
__be32 to;
};
static void fast_csum(struct snmp_ctx *ctx, unsigned char offset)
{
unsigned char s[12] = {0,};
int size;
if (offset & 1) {
memcpy(&s[1], &ctx->from, 4);
memcpy(&s[7], &ctx->to, 4);
s[0] = ~0;
s[1] = ~s[1];
s[2] = ~s[2];
s[3] = ~s[3];
s[4] = ~s[4];
s[5] = ~0;
size = 12;
} else {
memcpy(&s[0], &ctx->from, 4);
memcpy(&s[4], &ctx->to, 4);
s[0] = ~s[0];
s[1] = ~s[1];
s[2] = ~s[2];
s[3] = ~s[3];
size = 8;
}
*ctx->check = csum_fold(csum_partial(s, size,
~csum_unfold(*ctx->check)));
}
int snmp_version(void *context, size_t hdrlen, unsigned char tag,
const void *data, size_t datalen)
{
if (datalen != 1)
return -EINVAL;
if (*(unsigned char *)data > 1)
return -ENOTSUPP;
return 1;
}
int snmp_helper(void *context, size_t hdrlen, unsigned char tag,
const void *data, size_t datalen)
{
struct snmp_ctx *ctx = (struct snmp_ctx *)context;
__be32 *pdata;
if (datalen != 4)
return -EINVAL;
pdata = (__be32 *)data;
if (*pdata == ctx->from) {
pr_debug("%s: %pI4 to %pI4\n", __func__,
(void *)&ctx->from, (void *)&ctx->to);
if (*ctx->check)
fast_csum(ctx, (unsigned char *)data - ctx->begin);
*pdata = ctx->to;
}
return 1;
}
static int snmp_translate(struct nf_conn *ct, int dir, struct sk_buff *skb)
{
struct iphdr *iph = ip_hdr(skb);
struct udphdr *udph = (struct udphdr *)((__be32 *)iph + iph->ihl);
u16 datalen = ntohs(udph->len) - sizeof(struct udphdr);
char *data = (unsigned char *)udph + sizeof(struct udphdr);
struct snmp_ctx ctx;
int ret;
if (dir == IP_CT_DIR_ORIGINAL) {
ctx.from = ct->tuplehash[dir].tuple.src.u3.ip;
ctx.to = ct->tuplehash[!dir].tuple.dst.u3.ip;
} else {
ctx.from = ct->tuplehash[!dir].tuple.src.u3.ip;
ctx.to = ct->tuplehash[dir].tuple.dst.u3.ip;
}
if (ctx.from == ctx.to)
return NF_ACCEPT;
ctx.begin = (unsigned char *)udph + sizeof(struct udphdr);
ctx.check = &udph->check;
ret = asn1_ber_decoder(&nf_nat_snmp_basic_decoder, &ctx, data, datalen);
if (ret < 0) {
nf_ct_helper_log(skb, ct, "parser failed\n");
return NF_DROP;
}
return NF_ACCEPT;
}
/* We don't actually set up expectations, just adjust internal IP
* addresses if this is being NATted
*/
static int help(struct sk_buff *skb, unsigned int protoff,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo)
{
int dir = CTINFO2DIR(ctinfo);
unsigned int ret;
const struct iphdr *iph = ip_hdr(skb);
const struct udphdr *udph = (struct udphdr *)((__be32 *)iph + iph->ihl);
/* SNMP replies and originating SNMP traps get mangled */
if (udph->source == htons(SNMP_PORT) && dir != IP_CT_DIR_REPLY)
return NF_ACCEPT;
if (udph->dest == htons(SNMP_TRAP_PORT) && dir != IP_CT_DIR_ORIGINAL)
return NF_ACCEPT;
/* No NAT? */
if (!(ct->status & IPS_NAT_MASK))
return NF_ACCEPT;
/* Make sure the packet length is ok. So far, we were only guaranteed
* to have a valid length IP header plus 8 bytes, which means we have
* enough room for a UDP header. Just verify the UDP length field so we
* can mess around with the payload.
*/
if (ntohs(udph->len) != skb->len - (iph->ihl << 2)) {
nf_ct_helper_log(skb, ct, "dropping malformed packet\n");
return NF_DROP;
}
if (!skb_make_writable(skb, skb->len)) {
nf_ct_helper_log(skb, ct, "cannot mangle packet");
return NF_DROP;
}
spin_lock_bh(&snmp_lock);
ret = snmp_translate(ct, dir, skb);
spin_unlock_bh(&snmp_lock);
return ret;
}
static const struct nf_conntrack_expect_policy snmp_exp_policy = {
.max_expected = 0,
.timeout = 180,
};
static struct nf_conntrack_helper snmp_trap_helper __read_mostly = {
.me = THIS_MODULE,
.help = help,
.expect_policy = &snmp_exp_policy,
.name = "snmp_trap",
.tuple.src.l3num = AF_INET,
.tuple.src.u.udp.port = cpu_to_be16(SNMP_TRAP_PORT),
.tuple.dst.protonum = IPPROTO_UDP,
};
static int __init nf_nat_snmp_basic_init(void)
{
BUG_ON(nf_nat_snmp_hook != NULL);
RCU_INIT_POINTER(nf_nat_snmp_hook, help);
return nf_conntrack_helper_register(&snmp_trap_helper);
}
static void __exit nf_nat_snmp_basic_fini(void)
{
RCU_INIT_POINTER(nf_nat_snmp_hook, NULL);
synchronize_rcu();
nf_conntrack_helper_unregister(&snmp_trap_helper);
}
module_init(nf_nat_snmp_basic_init);
module_exit(nf_nat_snmp_basic_fini);
+194
View File
@@ -0,0 +1,194 @@
/* (C) 1999-2001 Paul `Rusty' Russell
* (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/module.h>
#include <net/ip.h>
#include <net/tcp.h>
#include <net/route.h>
#include <net/dst.h>
#include <net/netfilter/ipv4/nf_reject.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_bridge.h>
const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb,
struct tcphdr *_oth, int hook)
{
const struct tcphdr *oth;
/* IP header checks: fragment. */
if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
return NULL;
if (ip_hdr(oldskb)->protocol != IPPROTO_TCP)
return NULL;
oth = skb_header_pointer(oldskb, ip_hdrlen(oldskb),
sizeof(struct tcphdr), _oth);
if (oth == NULL)
return NULL;
/* No RST for RST. */
if (oth->rst)
return NULL;
/* Check checksum */
if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP))
return NULL;
return oth;
}
EXPORT_SYMBOL_GPL(nf_reject_ip_tcphdr_get);
struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb,
const struct sk_buff *oldskb,
__u8 protocol, int ttl)
{
struct iphdr *niph, *oiph = ip_hdr(oldskb);
skb_reset_network_header(nskb);
niph = skb_put(nskb, sizeof(struct iphdr));
niph->version = 4;
niph->ihl = sizeof(struct iphdr) / 4;
niph->tos = 0;
niph->id = 0;
niph->frag_off = htons(IP_DF);
niph->protocol = protocol;
niph->check = 0;
niph->saddr = oiph->daddr;
niph->daddr = oiph->saddr;
niph->ttl = ttl;
nskb->protocol = htons(ETH_P_IP);
return niph;
}
EXPORT_SYMBOL_GPL(nf_reject_iphdr_put);
void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb,
const struct tcphdr *oth)
{
struct iphdr *niph = ip_hdr(nskb);
struct tcphdr *tcph;
skb_reset_transport_header(nskb);
tcph = skb_put_zero(nskb, sizeof(struct tcphdr));
tcph->source = oth->dest;
tcph->dest = oth->source;
tcph->doff = sizeof(struct tcphdr) / 4;
if (oth->ack) {
tcph->seq = oth->ack_seq;
} else {
tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin +
oldskb->len - ip_hdrlen(oldskb) -
(oth->doff << 2));
tcph->ack = 1;
}
tcph->rst = 1;
tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), niph->saddr,
niph->daddr, 0);
nskb->ip_summed = CHECKSUM_PARTIAL;
nskb->csum_start = (unsigned char *)tcph - nskb->head;
nskb->csum_offset = offsetof(struct tcphdr, check);
}
EXPORT_SYMBOL_GPL(nf_reject_ip_tcphdr_put);
/* Send RST reply */
void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
{
struct sk_buff *nskb;
struct iphdr *niph;
const struct tcphdr *oth;
struct tcphdr _oth;
oth = nf_reject_ip_tcphdr_get(oldskb, &_oth, hook);
if (!oth)
return;
if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
return;
nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
LL_MAX_HEADER, GFP_ATOMIC);
if (!nskb)
return;
/* ip_route_me_harder expects skb->dst to be set */
skb_dst_set_noref(nskb, skb_dst(oldskb));
nskb->mark = IP4_REPLY_MARK(net, oldskb->mark);
skb_reserve(nskb, LL_MAX_HEADER);
niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP,
ip4_dst_hoplimit(skb_dst(nskb)));
nf_reject_ip_tcphdr_put(nskb, oldskb, oth);
if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC))
goto free_nskb;
niph = ip_hdr(nskb);
/* "Never happens" */
if (nskb->len > dst_mtu(skb_dst(nskb)))
goto free_nskb;
nf_ct_attach(nskb, oldskb);
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
/* If we use ip_local_out for bridged traffic, the MAC source on
* the RST will be ours, instead of the destination's. This confuses
* some routers/firewalls, and they drop the packet. So we need to
* build the eth header using the original destination's MAC as the
* source, and send the RST packet directly.
*/
if (oldskb->nf_bridge) {
struct ethhdr *oeth = eth_hdr(oldskb);
nskb->dev = nf_bridge_get_physindev(oldskb);
niph->tot_len = htons(nskb->len);
ip_send_check(niph);
if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
oeth->h_source, oeth->h_dest, nskb->len) < 0)
goto free_nskb;
dev_queue_xmit(nskb);
} else
#endif
ip_local_out(net, nskb->sk, nskb);
return;
free_nskb:
kfree_skb(nskb);
}
EXPORT_SYMBOL_GPL(nf_send_reset);
void nf_send_unreach(struct sk_buff *skb_in, int code, int hook)
{
struct iphdr *iph = ip_hdr(skb_in);
u8 proto;
if (iph->frag_off & htons(IP_OFFSET))
return;
if (skb_csum_unnecessary(skb_in)) {
icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0);
return;
}
if (iph->protocol == IPPROTO_TCP || iph->protocol == IPPROTO_UDP)
proto = iph->protocol;
else
proto = 0;
if (nf_ip_checksum(skb_in, hook, ip_hdrlen(skb_in), proto) == 0)
icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0);
}
EXPORT_SYMBOL_GPL(nf_send_unreach);
MODULE_LICENSE("GPL");
+165
View File
@@ -0,0 +1,165 @@
/*
* Copyright (C) 2007-2008 BalaBit IT Ltd.
* Author: Krisztian Kovacs
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/skbuff.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/icmp.h>
#include <net/sock.h>
#include <net/inet_sock.h>
#include <net/netfilter/nf_socket.h>
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
#include <net/netfilter/nf_conntrack.h>
#endif
static int
extract_icmp4_fields(const struct sk_buff *skb, u8 *protocol,
__be32 *raddr, __be32 *laddr,
__be16 *rport, __be16 *lport)
{
unsigned int outside_hdrlen = ip_hdrlen(skb);
struct iphdr *inside_iph, _inside_iph;
struct icmphdr *icmph, _icmph;
__be16 *ports, _ports[2];
icmph = skb_header_pointer(skb, outside_hdrlen,
sizeof(_icmph), &_icmph);
if (icmph == NULL)
return 1;
switch (icmph->type) {
case ICMP_DEST_UNREACH:
case ICMP_SOURCE_QUENCH:
case ICMP_REDIRECT:
case ICMP_TIME_EXCEEDED:
case ICMP_PARAMETERPROB:
break;
default:
return 1;
}
inside_iph = skb_header_pointer(skb, outside_hdrlen +
sizeof(struct icmphdr),
sizeof(_inside_iph), &_inside_iph);
if (inside_iph == NULL)
return 1;
if (inside_iph->protocol != IPPROTO_TCP &&
inside_iph->protocol != IPPROTO_UDP)
return 1;
ports = skb_header_pointer(skb, outside_hdrlen +
sizeof(struct icmphdr) +
(inside_iph->ihl << 2),
sizeof(_ports), &_ports);
if (ports == NULL)
return 1;
/* the inside IP packet is the one quoted from our side, thus
* its saddr is the local address */
*protocol = inside_iph->protocol;
*laddr = inside_iph->saddr;
*lport = ports[0];
*raddr = inside_iph->daddr;
*rport = ports[1];
return 0;
}
static struct sock *
nf_socket_get_sock_v4(struct net *net, struct sk_buff *skb, const int doff,
const u8 protocol,
const __be32 saddr, const __be32 daddr,
const __be16 sport, const __be16 dport,
const struct net_device *in)
{
switch (protocol) {
case IPPROTO_TCP:
return inet_lookup(net, &tcp_hashinfo, skb, doff,
saddr, sport, daddr, dport,
in->ifindex);
case IPPROTO_UDP:
return udp4_lib_lookup(net, saddr, sport, daddr, dport,
in->ifindex);
}
return NULL;
}
struct sock *nf_sk_lookup_slow_v4(struct net *net, const struct sk_buff *skb,
const struct net_device *indev)
{
__be32 uninitialized_var(daddr), uninitialized_var(saddr);
__be16 uninitialized_var(dport), uninitialized_var(sport);
const struct iphdr *iph = ip_hdr(skb);
struct sk_buff *data_skb = NULL;
u8 uninitialized_var(protocol);
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
enum ip_conntrack_info ctinfo;
struct nf_conn const *ct;
#endif
int doff = 0;
if (iph->protocol == IPPROTO_UDP || iph->protocol == IPPROTO_TCP) {
struct tcphdr _hdr;
struct udphdr *hp;
hp = skb_header_pointer(skb, ip_hdrlen(skb),
iph->protocol == IPPROTO_UDP ?
sizeof(*hp) : sizeof(_hdr), &_hdr);
if (hp == NULL)
return NULL;
protocol = iph->protocol;
saddr = iph->saddr;
sport = hp->source;
daddr = iph->daddr;
dport = hp->dest;
data_skb = (struct sk_buff *)skb;
doff = iph->protocol == IPPROTO_TCP ?
ip_hdrlen(skb) + __tcp_hdrlen((struct tcphdr *)hp) :
ip_hdrlen(skb) + sizeof(*hp);
} else if (iph->protocol == IPPROTO_ICMP) {
if (extract_icmp4_fields(skb, &protocol, &saddr, &daddr,
&sport, &dport))
return NULL;
} else {
return NULL;
}
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
/* Do the lookup with the original socket address in
* case this is a reply packet of an established
* SNAT-ted connection.
*/
ct = nf_ct_get(skb, &ctinfo);
if (ct &&
((iph->protocol != IPPROTO_ICMP &&
ctinfo == IP_CT_ESTABLISHED_REPLY) ||
(iph->protocol == IPPROTO_ICMP &&
ctinfo == IP_CT_RELATED_REPLY)) &&
(ct->status & IPS_SRC_NAT_DONE)) {
daddr = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip;
dport = (iph->protocol == IPPROTO_TCP) ?
ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port :
ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port;
}
#endif
return nf_socket_get_sock_v4(net, data_skb, doff, protocol, saddr,
daddr, sport, dport, indev);
}
EXPORT_SYMBOL_GPL(nf_sk_lookup_slow_v4);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Krisztian Kovacs, Balazs Scheidler");
MODULE_DESCRIPTION("Netfilter IPv4 socket lookup infrastructure");
+153
View File
@@ -0,0 +1,153 @@
/*
* Copyright (C) 2007-2008 BalaBit IT Ltd.
* Author: Krisztian Kovacs
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
*/
#include <net/netfilter/nf_tproxy.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/inet_sock.h>
#include <linux/ip.h>
#include <net/checksum.h>
#include <net/udp.h>
#include <net/tcp.h>
#include <linux/inetdevice.h>
struct sock *
nf_tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb,
__be32 laddr, __be16 lport, struct sock *sk)
{
const struct iphdr *iph = ip_hdr(skb);
struct tcphdr _hdr, *hp;
hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr);
if (hp == NULL) {
inet_twsk_put(inet_twsk(sk));
return NULL;
}
if (hp->syn && !hp->rst && !hp->ack && !hp->fin) {
/* SYN to a TIME_WAIT socket, we'd rather redirect it
* to a listener socket if there's one */
struct sock *sk2;
sk2 = nf_tproxy_get_sock_v4(net, skb, iph->protocol,
iph->saddr, laddr ? laddr : iph->daddr,
hp->source, lport ? lport : hp->dest,
skb->dev, NF_TPROXY_LOOKUP_LISTENER);
if (sk2) {
inet_twsk_deschedule_put(inet_twsk(sk));
sk = sk2;
}
}
return sk;
}
EXPORT_SYMBOL_GPL(nf_tproxy_handle_time_wait4);
__be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr)
{
struct in_device *indev;
__be32 laddr;
if (user_laddr)
return user_laddr;
laddr = 0;
indev = __in_dev_get_rcu(skb->dev);
for_primary_ifa(indev) {
laddr = ifa->ifa_local;
break;
} endfor_ifa(indev);
return laddr ? laddr : daddr;
}
EXPORT_SYMBOL_GPL(nf_tproxy_laddr4);
struct sock *
nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb,
const u8 protocol,
const __be32 saddr, const __be32 daddr,
const __be16 sport, const __be16 dport,
const struct net_device *in,
const enum nf_tproxy_lookup_t lookup_type)
{
struct sock *sk;
switch (protocol) {
case IPPROTO_TCP: {
struct tcphdr _hdr, *hp;
hp = skb_header_pointer(skb, ip_hdrlen(skb),
sizeof(struct tcphdr), &_hdr);
if (hp == NULL)
return NULL;
switch (lookup_type) {
case NF_TPROXY_LOOKUP_LISTENER:
sk = inet_lookup_listener(net, &tcp_hashinfo, skb,
ip_hdrlen(skb) +
__tcp_hdrlen(hp),
saddr, sport,
daddr, dport,
in->ifindex, 0);
if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
sk = NULL;
/* NOTE: we return listeners even if bound to
* 0.0.0.0, those are filtered out in
* xt_socket, since xt_TPROXY needs 0 bound
* listeners too
*/
break;
case NF_TPROXY_LOOKUP_ESTABLISHED:
sk = inet_lookup_established(net, &tcp_hashinfo,
saddr, sport, daddr, dport,
in->ifindex);
break;
default:
BUG();
}
break;
}
case IPPROTO_UDP:
sk = udp4_lib_lookup(net, saddr, sport, daddr, dport,
in->ifindex);
if (sk) {
int connected = (sk->sk_state == TCP_ESTABLISHED);
int wildcard = (inet_sk(sk)->inet_rcv_saddr == 0);
/* NOTE: we return listeners even if bound to
* 0.0.0.0, those are filtered out in
* xt_socket, since xt_TPROXY needs 0 bound
* listeners too
*/
if ((lookup_type == NF_TPROXY_LOOKUP_ESTABLISHED &&
(!connected || wildcard)) ||
(lookup_type == NF_TPROXY_LOOKUP_LISTENER && connected)) {
sock_put(sk);
sk = NULL;
}
}
break;
default:
WARN_ON(1);
sk = NULL;
}
pr_debug("tproxy socket lookup: proto %u %08x:%u -> %08x:%u, lookup type: %d, sock %p\n",
protocol, ntohl(saddr), ntohs(sport), ntohl(daddr), ntohs(dport), lookup_type, sk);
return sk;
}
EXPORT_SYMBOL_GPL(nf_tproxy_get_sock_v4);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Balazs Scheidler, Krisztian Kovacs");
MODULE_DESCRIPTION("Netfilter IPv4 transparent proxy support");
+87
View File
@@ -0,0 +1,87 @@
/*
* Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
* Copyright (c) 2012 Pablo Neira Ayuso <pablo@netfilter.org>
* Copyright (c) 2012 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* Development of this code funded by Astaro AG (http://www.astaro.com/)
*/
#include <linux/module.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/skbuff.h>
#include <linux/ip.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter/nf_tables.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables_ipv4.h>
#include <net/netfilter/nf_nat_l3proto.h>
#include <net/ip.h>
static unsigned int nft_nat_do_chain(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
struct nft_pktinfo pkt;
nft_set_pktinfo(&pkt, skb, state);
nft_set_pktinfo_ipv4(&pkt, skb);
return nft_do_chain(&pkt, priv);
}
static int nft_nat_ipv4_reg(struct net *net, const struct nf_hook_ops *ops)
{
return nf_nat_l3proto_ipv4_register_fn(net, ops);
}
static void nft_nat_ipv4_unreg(struct net *net, const struct nf_hook_ops *ops)
{
nf_nat_l3proto_ipv4_unregister_fn(net, ops);
}
static const struct nft_chain_type nft_chain_nat_ipv4 = {
.name = "nat",
.type = NFT_CHAIN_T_NAT,
.family = NFPROTO_IPV4,
.owner = THIS_MODULE,
.hook_mask = (1 << NF_INET_PRE_ROUTING) |
(1 << NF_INET_POST_ROUTING) |
(1 << NF_INET_LOCAL_OUT) |
(1 << NF_INET_LOCAL_IN),
.hooks = {
[NF_INET_PRE_ROUTING] = nft_nat_do_chain,
[NF_INET_POST_ROUTING] = nft_nat_do_chain,
[NF_INET_LOCAL_OUT] = nft_nat_do_chain,
[NF_INET_LOCAL_IN] = nft_nat_do_chain,
},
.ops_register = nft_nat_ipv4_reg,
.ops_unregister = nft_nat_ipv4_unreg,
};
static int __init nft_chain_nat_init(void)
{
nft_register_chain_type(&nft_chain_nat_ipv4);
return 0;
}
static void __exit nft_chain_nat_exit(void)
{
nft_unregister_chain_type(&nft_chain_nat_ipv4);
}
module_init(nft_chain_nat_init);
module_exit(nft_chain_nat_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
MODULE_ALIAS_NFT_CHAIN(AF_INET, "nat");
+89
View File
@@ -0,0 +1,89 @@
/*
* Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
* Copyright (c) 2012 Pablo Neira Ayuso <pablo@netfilter.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/module.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/skbuff.h>
#include <linux/netlink.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables_ipv4.h>
#include <net/route.h>
#include <net/ip.h>
static unsigned int nf_route_table_hook(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
unsigned int ret;
struct nft_pktinfo pkt;
u32 mark;
__be32 saddr, daddr;
u_int8_t tos;
const struct iphdr *iph;
int err;
nft_set_pktinfo(&pkt, skb, state);
nft_set_pktinfo_ipv4(&pkt, skb);
mark = skb->mark;
iph = ip_hdr(skb);
saddr = iph->saddr;
daddr = iph->daddr;
tos = iph->tos;
ret = nft_do_chain(&pkt, priv);
if (ret != NF_DROP && ret != NF_STOLEN) {
iph = ip_hdr(skb);
if (iph->saddr != saddr ||
iph->daddr != daddr ||
skb->mark != mark ||
iph->tos != tos) {
err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
if (err < 0)
ret = NF_DROP_ERR(err);
}
}
return ret;
}
static const struct nft_chain_type nft_chain_route_ipv4 = {
.name = "route",
.type = NFT_CHAIN_T_ROUTE,
.family = NFPROTO_IPV4,
.owner = THIS_MODULE,
.hook_mask = (1 << NF_INET_LOCAL_OUT),
.hooks = {
[NF_INET_LOCAL_OUT] = nf_route_table_hook,
},
};
static int __init nft_chain_route_init(void)
{
nft_register_chain_type(&nft_chain_route_ipv4);
return 0;
}
static void __exit nft_chain_route_exit(void)
{
nft_unregister_chain_type(&nft_chain_route_ipv4);
}
module_init(nft_chain_route_init);
module_exit(nft_chain_route_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
MODULE_ALIAS_NFT_CHAIN(AF_INET, "route");
+112
View File
@@ -0,0 +1,112 @@
/*
* Copyright (c) 2015 Pablo Neira Ayuso <pablo@netfilter.org>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published by
* the Free Software Foundation.
*/
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/netlink.h>
#include <linux/netfilter.h>
#include <linux/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables.h>
#include <net/netfilter/ipv4/nf_dup_ipv4.h>
struct nft_dup_ipv4 {
enum nft_registers sreg_addr:8;
enum nft_registers sreg_dev:8;
};
static void nft_dup_ipv4_eval(const struct nft_expr *expr,
struct nft_regs *regs,
const struct nft_pktinfo *pkt)
{
struct nft_dup_ipv4 *priv = nft_expr_priv(expr);
struct in_addr gw = {
.s_addr = (__force __be32)regs->data[priv->sreg_addr],
};
int oif = priv->sreg_dev ? regs->data[priv->sreg_dev] : -1;
nf_dup_ipv4(nft_net(pkt), pkt->skb, nft_hook(pkt), &gw, oif);
}
static int nft_dup_ipv4_init(const struct nft_ctx *ctx,
const struct nft_expr *expr,
const struct nlattr * const tb[])
{
struct nft_dup_ipv4 *priv = nft_expr_priv(expr);
int err;
if (tb[NFTA_DUP_SREG_ADDR] == NULL)
return -EINVAL;
priv->sreg_addr = nft_parse_register(tb[NFTA_DUP_SREG_ADDR]);
err = nft_validate_register_load(priv->sreg_addr, sizeof(struct in_addr));
if (err < 0)
return err;
if (tb[NFTA_DUP_SREG_DEV] != NULL) {
priv->sreg_dev = nft_parse_register(tb[NFTA_DUP_SREG_DEV]);
return nft_validate_register_load(priv->sreg_dev, sizeof(int));
}
return 0;
}
static int nft_dup_ipv4_dump(struct sk_buff *skb, const struct nft_expr *expr)
{
struct nft_dup_ipv4 *priv = nft_expr_priv(expr);
if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr))
goto nla_put_failure;
if (priv->sreg_dev &&
nft_dump_register(skb, NFTA_DUP_SREG_DEV, priv->sreg_dev))
goto nla_put_failure;
return 0;
nla_put_failure:
return -1;
}
static struct nft_expr_type nft_dup_ipv4_type;
static const struct nft_expr_ops nft_dup_ipv4_ops = {
.type = &nft_dup_ipv4_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_dup_ipv4)),
.eval = nft_dup_ipv4_eval,
.init = nft_dup_ipv4_init,
.dump = nft_dup_ipv4_dump,
};
static const struct nla_policy nft_dup_ipv4_policy[NFTA_DUP_MAX + 1] = {
[NFTA_DUP_SREG_ADDR] = { .type = NLA_U32 },
[NFTA_DUP_SREG_DEV] = { .type = NLA_U32 },
};
static struct nft_expr_type nft_dup_ipv4_type __read_mostly = {
.family = NFPROTO_IPV4,
.name = "dup",
.ops = &nft_dup_ipv4_ops,
.policy = nft_dup_ipv4_policy,
.maxattr = NFTA_DUP_MAX,
.owner = THIS_MODULE,
};
static int __init nft_dup_ipv4_module_init(void)
{
return nft_register_expr(&nft_dup_ipv4_type);
}
static void __exit nft_dup_ipv4_module_exit(void)
{
nft_unregister_expr(&nft_dup_ipv4_type);
}
module_init(nft_dup_ipv4_module_init);
module_exit(nft_dup_ipv4_module_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "dup");
+248
View File
@@ -0,0 +1,248 @@
/*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/netlink.h>
#include <linux/netfilter.h>
#include <linux/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables_core.h>
#include <net/netfilter/nf_tables.h>
#include <net/netfilter/nft_fib.h>
#include <net/ip_fib.h>
#include <net/route.h>
/* don't try to find route from mcast/bcast/zeronet */
static __be32 get_saddr(__be32 addr)
{
if (ipv4_is_multicast(addr) || ipv4_is_lbcast(addr) ||
ipv4_is_zeronet(addr))
return 0;
return addr;
}
#define DSCP_BITS 0xfc
void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs,
const struct nft_pktinfo *pkt)
{
const struct nft_fib *priv = nft_expr_priv(expr);
int noff = skb_network_offset(pkt->skb);
u32 *dst = &regs->data[priv->dreg];
const struct net_device *dev = NULL;
struct iphdr *iph, _iph;
__be32 addr;
if (priv->flags & NFTA_FIB_F_IIF)
dev = nft_in(pkt);
else if (priv->flags & NFTA_FIB_F_OIF)
dev = nft_out(pkt);
iph = skb_header_pointer(pkt->skb, noff, sizeof(_iph), &_iph);
if (!iph) {
regs->verdict.code = NFT_BREAK;
return;
}
if (priv->flags & NFTA_FIB_F_DADDR)
addr = iph->daddr;
else
addr = iph->saddr;
*dst = inet_dev_addr_type(nft_net(pkt), dev, addr);
}
EXPORT_SYMBOL_GPL(nft_fib4_eval_type);
static int get_ifindex(const struct net_device *dev)
{
return dev ? dev->ifindex : 0;
}
void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
const struct nft_pktinfo *pkt)
{
const struct nft_fib *priv = nft_expr_priv(expr);
int noff = skb_network_offset(pkt->skb);
u32 *dest = &regs->data[priv->dreg];
struct iphdr *iph, _iph;
struct fib_result res;
struct flowi4 fl4 = {
.flowi4_scope = RT_SCOPE_UNIVERSE,
.flowi4_iif = LOOPBACK_IFINDEX,
};
const struct net_device *oif;
struct net_device *found;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
int i;
#endif
/*
* Do not set flowi4_oif, it restricts results (for example, asking
* for oif 3 will get RTN_UNICAST result even if the daddr exits
* on another interface.
*
* Search results for the desired outinterface instead.
*/
if (priv->flags & NFTA_FIB_F_OIF)
oif = nft_out(pkt);
else if (priv->flags & NFTA_FIB_F_IIF)
oif = nft_in(pkt);
else
oif = NULL;
if (nft_hook(pkt) == NF_INET_PRE_ROUTING &&
nft_fib_is_loopback(pkt->skb, nft_in(pkt))) {
nft_fib_store_result(dest, priv, pkt,
nft_in(pkt)->ifindex);
return;
}
iph = skb_header_pointer(pkt->skb, noff, sizeof(_iph), &_iph);
if (!iph) {
regs->verdict.code = NFT_BREAK;
return;
}
if (ipv4_is_zeronet(iph->saddr)) {
if (ipv4_is_lbcast(iph->daddr) ||
ipv4_is_local_multicast(iph->daddr)) {
nft_fib_store_result(dest, priv, pkt,
get_ifindex(pkt->skb->dev));
return;
}
}
if (priv->flags & NFTA_FIB_F_MARK)
fl4.flowi4_mark = pkt->skb->mark;
fl4.flowi4_tos = iph->tos & DSCP_BITS;
if (priv->flags & NFTA_FIB_F_DADDR) {
fl4.daddr = iph->daddr;
fl4.saddr = get_saddr(iph->saddr);
} else {
fl4.daddr = iph->saddr;
fl4.saddr = get_saddr(iph->daddr);
}
*dest = 0;
if (fib_lookup(nft_net(pkt), &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE))
return;
switch (res.type) {
case RTN_UNICAST:
break;
case RTN_LOCAL: /* Should not see RTN_LOCAL here */
return;
default:
break;
}
if (!oif) {
found = FIB_RES_DEV(res);
goto ok;
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
for (i = 0; i < res.fi->fib_nhs; i++) {
struct fib_nh *nh = &res.fi->fib_nh[i];
if (nh->nh_dev == oif) {
found = nh->nh_dev;
goto ok;
}
}
return;
#else
found = FIB_RES_DEV(res);
if (found != oif)
return;
#endif
ok:
switch (priv->result) {
case NFT_FIB_RESULT_OIF:
*dest = found->ifindex;
break;
case NFT_FIB_RESULT_OIFNAME:
strncpy((char *)dest, found->name, IFNAMSIZ);
break;
default:
WARN_ON_ONCE(1);
break;
}
}
EXPORT_SYMBOL_GPL(nft_fib4_eval);
static struct nft_expr_type nft_fib4_type;
static const struct nft_expr_ops nft_fib4_type_ops = {
.type = &nft_fib4_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_fib)),
.eval = nft_fib4_eval_type,
.init = nft_fib_init,
.dump = nft_fib_dump,
.validate = nft_fib_validate,
};
static const struct nft_expr_ops nft_fib4_ops = {
.type = &nft_fib4_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_fib)),
.eval = nft_fib4_eval,
.init = nft_fib_init,
.dump = nft_fib_dump,
.validate = nft_fib_validate,
};
static const struct nft_expr_ops *
nft_fib4_select_ops(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
enum nft_fib_result result;
if (!tb[NFTA_FIB_RESULT])
return ERR_PTR(-EINVAL);
result = ntohl(nla_get_be32(tb[NFTA_FIB_RESULT]));
switch (result) {
case NFT_FIB_RESULT_OIF:
return &nft_fib4_ops;
case NFT_FIB_RESULT_OIFNAME:
return &nft_fib4_ops;
case NFT_FIB_RESULT_ADDRTYPE:
return &nft_fib4_type_ops;
default:
return ERR_PTR(-EOPNOTSUPP);
}
}
static struct nft_expr_type nft_fib4_type __read_mostly = {
.name = "fib",
.select_ops = nft_fib4_select_ops,
.policy = nft_fib_policy,
.maxattr = NFTA_FIB_MAX,
.family = NFPROTO_IPV4,
.owner = THIS_MODULE,
};
static int __init nft_fib4_module_init(void)
{
return nft_register_expr(&nft_fib4_type);
}
static void __exit nft_fib4_module_exit(void)
{
nft_unregister_expr(&nft_fib4_type);
}
module_init(nft_fib4_module_init);
module_exit(nft_fib4_module_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
MODULE_ALIAS_NFT_AF_EXPR(2, "fib");
+90
View File
@@ -0,0 +1,90 @@
/*
* Copyright (c) 2014 Arturo Borrero Gonzalez <arturo@debian.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/netlink.h>
#include <linux/netfilter.h>
#include <linux/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables.h>
#include <net/netfilter/nft_masq.h>
#include <net/netfilter/ipv4/nf_nat_masquerade.h>
static void nft_masq_ipv4_eval(const struct nft_expr *expr,
struct nft_regs *regs,
const struct nft_pktinfo *pkt)
{
struct nft_masq *priv = nft_expr_priv(expr);
struct nf_nat_range2 range;
memset(&range, 0, sizeof(range));
range.flags = priv->flags;
if (priv->sreg_proto_min) {
range.min_proto.all = (__force __be16)nft_reg_load16(
&regs->data[priv->sreg_proto_min]);
range.max_proto.all = (__force __be16)nft_reg_load16(
&regs->data[priv->sreg_proto_max]);
}
regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, nft_hook(pkt),
&range, nft_out(pkt));
}
static void
nft_masq_ipv4_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
{
nf_ct_netns_put(ctx->net, NFPROTO_IPV4);
}
static struct nft_expr_type nft_masq_ipv4_type;
static const struct nft_expr_ops nft_masq_ipv4_ops = {
.type = &nft_masq_ipv4_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_masq)),
.eval = nft_masq_ipv4_eval,
.init = nft_masq_init,
.destroy = nft_masq_ipv4_destroy,
.dump = nft_masq_dump,
.validate = nft_masq_validate,
};
static struct nft_expr_type nft_masq_ipv4_type __read_mostly = {
.family = NFPROTO_IPV4,
.name = "masq",
.ops = &nft_masq_ipv4_ops,
.policy = nft_masq_policy,
.maxattr = NFTA_MASQ_MAX,
.owner = THIS_MODULE,
};
static int __init nft_masq_ipv4_module_init(void)
{
int ret;
ret = nft_register_expr(&nft_masq_ipv4_type);
if (ret < 0)
return ret;
ret = nf_nat_masquerade_ipv4_register_notifier();
if (ret)
nft_unregister_expr(&nft_masq_ipv4_type);
return ret;
}
static void __exit nft_masq_ipv4_module_exit(void)
{
nft_unregister_expr(&nft_masq_ipv4_type);
nf_nat_masquerade_ipv4_unregister_notifier();
}
module_init(nft_masq_ipv4_module_init);
module_exit(nft_masq_ipv4_module_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org");
MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "masq");
+82
View File
@@ -0,0 +1,82 @@
/*
* Copyright (c) 2014 Arturo Borrero Gonzalez <arturo@debian.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/netlink.h>
#include <linux/netfilter.h>
#include <linux/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables.h>
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_redirect.h>
#include <net/netfilter/nft_redir.h>
static void nft_redir_ipv4_eval(const struct nft_expr *expr,
struct nft_regs *regs,
const struct nft_pktinfo *pkt)
{
struct nft_redir *priv = nft_expr_priv(expr);
struct nf_nat_ipv4_multi_range_compat mr;
memset(&mr, 0, sizeof(mr));
if (priv->sreg_proto_min) {
mr.range[0].min.all = (__force __be16)nft_reg_load16(
&regs->data[priv->sreg_proto_min]);
mr.range[0].max.all = (__force __be16)nft_reg_load16(
&regs->data[priv->sreg_proto_max]);
mr.range[0].flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
}
mr.range[0].flags |= priv->flags;
regs->verdict.code = nf_nat_redirect_ipv4(pkt->skb, &mr, nft_hook(pkt));
}
static void
nft_redir_ipv4_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
{
nf_ct_netns_put(ctx->net, NFPROTO_IPV4);
}
static struct nft_expr_type nft_redir_ipv4_type;
static const struct nft_expr_ops nft_redir_ipv4_ops = {
.type = &nft_redir_ipv4_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_redir)),
.eval = nft_redir_ipv4_eval,
.init = nft_redir_init,
.destroy = nft_redir_ipv4_destroy,
.dump = nft_redir_dump,
.validate = nft_redir_validate,
};
static struct nft_expr_type nft_redir_ipv4_type __read_mostly = {
.family = NFPROTO_IPV4,
.name = "redir",
.ops = &nft_redir_ipv4_ops,
.policy = nft_redir_policy,
.maxattr = NFTA_REDIR_MAX,
.owner = THIS_MODULE,
};
static int __init nft_redir_ipv4_module_init(void)
{
return nft_register_expr(&nft_redir_ipv4_type);
}
static void __exit nft_redir_ipv4_module_exit(void)
{
nft_unregister_expr(&nft_redir_ipv4_type);
}
module_init(nft_redir_ipv4_module_init);
module_exit(nft_redir_ipv4_module_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>");
MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "redir");
+76
View File
@@ -0,0 +1,76 @@
/*
* Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
* Copyright (c) 2013 Eric Leblond <eric@regit.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* Development of this code funded by Astaro AG (http://www.astaro.com/)
*/
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/netlink.h>
#include <linux/netfilter.h>
#include <linux/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables.h>
#include <net/netfilter/ipv4/nf_reject.h>
#include <net/netfilter/nft_reject.h>
static void nft_reject_ipv4_eval(const struct nft_expr *expr,
struct nft_regs *regs,
const struct nft_pktinfo *pkt)
{
struct nft_reject *priv = nft_expr_priv(expr);
switch (priv->type) {
case NFT_REJECT_ICMP_UNREACH:
nf_send_unreach(pkt->skb, priv->icmp_code, nft_hook(pkt));
break;
case NFT_REJECT_TCP_RST:
nf_send_reset(nft_net(pkt), pkt->skb, nft_hook(pkt));
break;
default:
break;
}
regs->verdict.code = NF_DROP;
}
static struct nft_expr_type nft_reject_ipv4_type;
static const struct nft_expr_ops nft_reject_ipv4_ops = {
.type = &nft_reject_ipv4_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_reject)),
.eval = nft_reject_ipv4_eval,
.init = nft_reject_init,
.dump = nft_reject_dump,
.validate = nft_reject_validate,
};
static struct nft_expr_type nft_reject_ipv4_type __read_mostly = {
.family = NFPROTO_IPV4,
.name = "reject",
.ops = &nft_reject_ipv4_ops,
.policy = nft_reject_policy,
.maxattr = NFTA_REJECT_MAX,
.owner = THIS_MODULE,
};
static int __init nft_reject_ipv4_module_init(void)
{
return nft_register_expr(&nft_reject_ipv4_type);
}
static void __exit nft_reject_ipv4_module_exit(void)
{
nft_unregister_expr(&nft_reject_ipv4_type);
}
module_init(nft_reject_ipv4_module_init);
module_exit(nft_reject_ipv4_module_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "reject");
+32
View File
@@ -0,0 +1,32 @@
#include <linux/netlink.h>
#include <linux/rtnetlink.h>
#include <linux/types.h>
#include <net/net_namespace.h>
#include <net/netlink.h>
#include <linux/in6.h>
#include <net/ip.h>
int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family,
struct netlink_ext_ack *extack)
{
*ip_proto = nla_get_u8(attr);
switch (*ip_proto) {
case IPPROTO_TCP:
case IPPROTO_UDP:
return 0;
case IPPROTO_ICMP:
if (family != AF_INET)
break;
return 0;
#if IS_ENABLED(CONFIG_IPV6)
case IPPROTO_ICMPV6:
if (family != AF_INET6)
break;
return 0;
#endif
}
NL_SET_ERR_MSG(extack, "Unsupported ip proto");
return -EOPNOTSUPP;
}
EXPORT_SYMBOL_GPL(rtm_getroute_parse_ip_proto);
+1190
View File
File diff suppressed because it is too large. Load diff
+528
View File
@@ -0,0 +1,528 @@
/*
* 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.
*
* This file implements the various access functions for the
* PROC file system. It is mainly used for debugging and
* statistics.
*
* Authors: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Gerald J. Heim, <heim@peanuts.informatik.uni-tuebingen.de>
* Fred Baumgarten, <dc6iq@insu1.etec.uni-karlsruhe.de>
* Erik Schoenfelder, <schoenfr@ibr.cs.tu-bs.de>
*
* Fixes:
* Alan Cox : UDP sockets show the rxqueue/txqueue
* using hint flag for the netinfo.
* Pauline Middelink : identd support
* Alan Cox : Make /proc safer.
* Erik Schoenfelder : /proc/net/snmp
* Alan Cox : Handle dead sockets properly.
* Gerhard Koerting : Show both timers
* Alan Cox : Allow inode to be NULL (kernel socket)
* Andi Kleen : Add support for open_requests and
* split functions for more readibility.
* Andi Kleen : Add support for /proc/net/netstat
* Arnaldo C. Melo : Convert to seq_file
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/types.h>
#include <net/net_namespace.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/udplite.h>
#include <linux/bottom_half.h>
#include <linux/inetdevice.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/export.h>
#include <net/sock.h>
#include <net/raw.h>
#define TCPUDP_MIB_MAX max_t(u32, UDP_MIB_MAX, TCP_MIB_MAX)
/*
* Report socket allocation statistics [mea@utu.fi]
*/
static int sockstat_seq_show(struct seq_file *seq, void *v)
{
struct net *net = seq->private;
int orphans, sockets;
orphans = percpu_counter_sum_positive(&tcp_orphan_count);
sockets = proto_sockets_allocated_sum_positive(&tcp_prot);
socket_seq_show(seq);
seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %ld\n",
sock_prot_inuse_get(net, &tcp_prot), orphans,
atomic_read(&net->ipv4.tcp_death_row.tw_count), sockets,
proto_memory_allocated(&tcp_prot));
seq_printf(seq, "UDP: inuse %d mem %ld\n",
sock_prot_inuse_get(net, &udp_prot),
proto_memory_allocated(&udp_prot));
seq_printf(seq, "UDPLITE: inuse %d\n",
sock_prot_inuse_get(net, &udplite_prot));
seq_printf(seq, "RAW: inuse %d\n",
sock_prot_inuse_get(net, &raw_prot));
seq_printf(seq, "FRAG: inuse %u memory %lu\n",
atomic_read(&net->ipv4.frags.rhashtable.nelems),
frag_mem_limit(&net->ipv4.frags));
return 0;
}
/* snmp items */
static const struct snmp_mib snmp4_ipstats_list[] = {
SNMP_MIB_ITEM("InReceives", IPSTATS_MIB_INPKTS),
SNMP_MIB_ITEM("InHdrErrors", IPSTATS_MIB_INHDRERRORS),
SNMP_MIB_ITEM("InAddrErrors", IPSTATS_MIB_INADDRERRORS),
SNMP_MIB_ITEM("ForwDatagrams", IPSTATS_MIB_OUTFORWDATAGRAMS),
SNMP_MIB_ITEM("InUnknownProtos", IPSTATS_MIB_INUNKNOWNPROTOS),
SNMP_MIB_ITEM("InDiscards", IPSTATS_MIB_INDISCARDS),
SNMP_MIB_ITEM("InDelivers", IPSTATS_MIB_INDELIVERS),
SNMP_MIB_ITEM("OutRequests", IPSTATS_MIB_OUTPKTS),
SNMP_MIB_ITEM("OutDiscards", IPSTATS_MIB_OUTDISCARDS),
SNMP_MIB_ITEM("OutNoRoutes", IPSTATS_MIB_OUTNOROUTES),
SNMP_MIB_ITEM("ReasmTimeout", IPSTATS_MIB_REASMTIMEOUT),
SNMP_MIB_ITEM("ReasmReqds", IPSTATS_MIB_REASMREQDS),
SNMP_MIB_ITEM("ReasmOKs", IPSTATS_MIB_REASMOKS),
SNMP_MIB_ITEM("ReasmFails", IPSTATS_MIB_REASMFAILS),
SNMP_MIB_ITEM("FragOKs", IPSTATS_MIB_FRAGOKS),
SNMP_MIB_ITEM("FragFails", IPSTATS_MIB_FRAGFAILS),
SNMP_MIB_ITEM("FragCreates", IPSTATS_MIB_FRAGCREATES),
SNMP_MIB_SENTINEL
};
/* Following items are displayed in /proc/net/netstat */
static const struct snmp_mib snmp4_ipextstats_list[] = {
SNMP_MIB_ITEM("InNoRoutes", IPSTATS_MIB_INNOROUTES),
SNMP_MIB_ITEM("InTruncatedPkts", IPSTATS_MIB_INTRUNCATEDPKTS),
SNMP_MIB_ITEM("InMcastPkts", IPSTATS_MIB_INMCASTPKTS),
SNMP_MIB_ITEM("OutMcastPkts", IPSTATS_MIB_OUTMCASTPKTS),
SNMP_MIB_ITEM("InBcastPkts", IPSTATS_MIB_INBCASTPKTS),
SNMP_MIB_ITEM("OutBcastPkts", IPSTATS_MIB_OUTBCASTPKTS),
SNMP_MIB_ITEM("InOctets", IPSTATS_MIB_INOCTETS),
SNMP_MIB_ITEM("OutOctets", IPSTATS_MIB_OUTOCTETS),
SNMP_MIB_ITEM("InMcastOctets", IPSTATS_MIB_INMCASTOCTETS),
SNMP_MIB_ITEM("OutMcastOctets", IPSTATS_MIB_OUTMCASTOCTETS),
SNMP_MIB_ITEM("InBcastOctets", IPSTATS_MIB_INBCASTOCTETS),
SNMP_MIB_ITEM("OutBcastOctets", IPSTATS_MIB_OUTBCASTOCTETS),
/* Non RFC4293 fields */
SNMP_MIB_ITEM("InCsumErrors", IPSTATS_MIB_CSUMERRORS),
SNMP_MIB_ITEM("InNoECTPkts", IPSTATS_MIB_NOECTPKTS),
SNMP_MIB_ITEM("InECT1Pkts", IPSTATS_MIB_ECT1PKTS),
SNMP_MIB_ITEM("InECT0Pkts", IPSTATS_MIB_ECT0PKTS),
SNMP_MIB_ITEM("InCEPkts", IPSTATS_MIB_CEPKTS),
SNMP_MIB_ITEM("ReasmOverlaps", IPSTATS_MIB_REASM_OVERLAPS),
SNMP_MIB_SENTINEL
};
static const struct {
const char *name;
int index;
} icmpmibmap[] = {
{ "DestUnreachs", ICMP_DEST_UNREACH },
{ "TimeExcds", ICMP_TIME_EXCEEDED },
{ "ParmProbs", ICMP_PARAMETERPROB },
{ "SrcQuenchs", ICMP_SOURCE_QUENCH },
{ "Redirects", ICMP_REDIRECT },
{ "Echos", ICMP_ECHO },
{ "EchoReps", ICMP_ECHOREPLY },
{ "Timestamps", ICMP_TIMESTAMP },
{ "TimestampReps", ICMP_TIMESTAMPREPLY },
{ "AddrMasks", ICMP_ADDRESS },
{ "AddrMaskReps", ICMP_ADDRESSREPLY },
{ NULL, 0 }
};
static const struct snmp_mib snmp4_tcp_list[] = {
SNMP_MIB_ITEM("RtoAlgorithm", TCP_MIB_RTOALGORITHM),
SNMP_MIB_ITEM("RtoMin", TCP_MIB_RTOMIN),
SNMP_MIB_ITEM("RtoMax", TCP_MIB_RTOMAX),
SNMP_MIB_ITEM("MaxConn", TCP_MIB_MAXCONN),
SNMP_MIB_ITEM("ActiveOpens", TCP_MIB_ACTIVEOPENS),
SNMP_MIB_ITEM("PassiveOpens", TCP_MIB_PASSIVEOPENS),
SNMP_MIB_ITEM("AttemptFails", TCP_MIB_ATTEMPTFAILS),
SNMP_MIB_ITEM("EstabResets", TCP_MIB_ESTABRESETS),
SNMP_MIB_ITEM("CurrEstab", TCP_MIB_CURRESTAB),
SNMP_MIB_ITEM("InSegs", TCP_MIB_INSEGS),
SNMP_MIB_ITEM("OutSegs", TCP_MIB_OUTSEGS),
SNMP_MIB_ITEM("RetransSegs", TCP_MIB_RETRANSSEGS),
SNMP_MIB_ITEM("InErrs", TCP_MIB_INERRS),
SNMP_MIB_ITEM("OutRsts", TCP_MIB_OUTRSTS),
SNMP_MIB_ITEM("InCsumErrors", TCP_MIB_CSUMERRORS),
SNMP_MIB_SENTINEL
};
static const struct snmp_mib snmp4_udp_list[] = {
SNMP_MIB_ITEM("InDatagrams", UDP_MIB_INDATAGRAMS),
SNMP_MIB_ITEM("NoPorts", UDP_MIB_NOPORTS),
SNMP_MIB_ITEM("InErrors", UDP_MIB_INERRORS),
SNMP_MIB_ITEM("OutDatagrams", UDP_MIB_OUTDATAGRAMS),
SNMP_MIB_ITEM("RcvbufErrors", UDP_MIB_RCVBUFERRORS),
SNMP_MIB_ITEM("SndbufErrors", UDP_MIB_SNDBUFERRORS),
SNMP_MIB_ITEM("InCsumErrors", UDP_MIB_CSUMERRORS),
SNMP_MIB_ITEM("IgnoredMulti", UDP_MIB_IGNOREDMULTI),
SNMP_MIB_SENTINEL
};
static const struct snmp_mib snmp4_net_list[] = {
SNMP_MIB_ITEM("SyncookiesSent", LINUX_MIB_SYNCOOKIESSENT),
SNMP_MIB_ITEM("SyncookiesRecv", LINUX_MIB_SYNCOOKIESRECV),
SNMP_MIB_ITEM("SyncookiesFailed", LINUX_MIB_SYNCOOKIESFAILED),
SNMP_MIB_ITEM("EmbryonicRsts", LINUX_MIB_EMBRYONICRSTS),
SNMP_MIB_ITEM("PruneCalled", LINUX_MIB_PRUNECALLED),
SNMP_MIB_ITEM("RcvPruned", LINUX_MIB_RCVPRUNED),
SNMP_MIB_ITEM("OfoPruned", LINUX_MIB_OFOPRUNED),
SNMP_MIB_ITEM("OutOfWindowIcmps", LINUX_MIB_OUTOFWINDOWICMPS),
SNMP_MIB_ITEM("LockDroppedIcmps", LINUX_MIB_LOCKDROPPEDICMPS),
SNMP_MIB_ITEM("ArpFilter", LINUX_MIB_ARPFILTER),
SNMP_MIB_ITEM("TW", LINUX_MIB_TIMEWAITED),
SNMP_MIB_ITEM("TWRecycled", LINUX_MIB_TIMEWAITRECYCLED),
SNMP_MIB_ITEM("TWKilled", LINUX_MIB_TIMEWAITKILLED),
SNMP_MIB_ITEM("PAWSActive", LINUX_MIB_PAWSACTIVEREJECTED),
SNMP_MIB_ITEM("PAWSEstab", LINUX_MIB_PAWSESTABREJECTED),
SNMP_MIB_ITEM("DelayedACKs", LINUX_MIB_DELAYEDACKS),
SNMP_MIB_ITEM("DelayedACKLocked", LINUX_MIB_DELAYEDACKLOCKED),
SNMP_MIB_ITEM("DelayedACKLost", LINUX_MIB_DELAYEDACKLOST),
SNMP_MIB_ITEM("ListenOverflows", LINUX_MIB_LISTENOVERFLOWS),
SNMP_MIB_ITEM("ListenDrops", LINUX_MIB_LISTENDROPS),
SNMP_MIB_ITEM("TCPHPHits", LINUX_MIB_TCPHPHITS),
SNMP_MIB_ITEM("TCPPureAcks", LINUX_MIB_TCPPUREACKS),
SNMP_MIB_ITEM("TCPHPAcks", LINUX_MIB_TCPHPACKS),
SNMP_MIB_ITEM("TCPRenoRecovery", LINUX_MIB_TCPRENORECOVERY),
SNMP_MIB_ITEM("TCPSackRecovery", LINUX_MIB_TCPSACKRECOVERY),
SNMP_MIB_ITEM("TCPSACKReneging", LINUX_MIB_TCPSACKRENEGING),
SNMP_MIB_ITEM("TCPSACKReorder", LINUX_MIB_TCPSACKREORDER),
SNMP_MIB_ITEM("TCPRenoReorder", LINUX_MIB_TCPRENOREORDER),
SNMP_MIB_ITEM("TCPTSReorder", LINUX_MIB_TCPTSREORDER),
SNMP_MIB_ITEM("TCPFullUndo", LINUX_MIB_TCPFULLUNDO),
SNMP_MIB_ITEM("TCPPartialUndo", LINUX_MIB_TCPPARTIALUNDO),
SNMP_MIB_ITEM("TCPDSACKUndo", LINUX_MIB_TCPDSACKUNDO),
SNMP_MIB_ITEM("TCPLossUndo", LINUX_MIB_TCPLOSSUNDO),
SNMP_MIB_ITEM("TCPLostRetransmit", LINUX_MIB_TCPLOSTRETRANSMIT),
SNMP_MIB_ITEM("TCPRenoFailures", LINUX_MIB_TCPRENOFAILURES),
SNMP_MIB_ITEM("TCPSackFailures", LINUX_MIB_TCPSACKFAILURES),
SNMP_MIB_ITEM("TCPLossFailures", LINUX_MIB_TCPLOSSFAILURES),
SNMP_MIB_ITEM("TCPFastRetrans", LINUX_MIB_TCPFASTRETRANS),
SNMP_MIB_ITEM("TCPSlowStartRetrans", LINUX_MIB_TCPSLOWSTARTRETRANS),
SNMP_MIB_ITEM("TCPTimeouts", LINUX_MIB_TCPTIMEOUTS),
SNMP_MIB_ITEM("TCPLossProbes", LINUX_MIB_TCPLOSSPROBES),
SNMP_MIB_ITEM("TCPLossProbeRecovery", LINUX_MIB_TCPLOSSPROBERECOVERY),
SNMP_MIB_ITEM("TCPRenoRecoveryFail", LINUX_MIB_TCPRENORECOVERYFAIL),
SNMP_MIB_ITEM("TCPSackRecoveryFail", LINUX_MIB_TCPSACKRECOVERYFAIL),
SNMP_MIB_ITEM("TCPRcvCollapsed", LINUX_MIB_TCPRCVCOLLAPSED),
SNMP_MIB_ITEM("TCPDSACKOldSent", LINUX_MIB_TCPDSACKOLDSENT),
SNMP_MIB_ITEM("TCPDSACKOfoSent", LINUX_MIB_TCPDSACKOFOSENT),
SNMP_MIB_ITEM("TCPDSACKRecv", LINUX_MIB_TCPDSACKRECV),
SNMP_MIB_ITEM("TCPDSACKOfoRecv", LINUX_MIB_TCPDSACKOFORECV),
SNMP_MIB_ITEM("TCPAbortOnData", LINUX_MIB_TCPABORTONDATA),
SNMP_MIB_ITEM("TCPAbortOnClose", LINUX_MIB_TCPABORTONCLOSE),
SNMP_MIB_ITEM("TCPAbortOnMemory", LINUX_MIB_TCPABORTONMEMORY),
SNMP_MIB_ITEM("TCPAbortOnTimeout", LINUX_MIB_TCPABORTONTIMEOUT),
SNMP_MIB_ITEM("TCPAbortOnLinger", LINUX_MIB_TCPABORTONLINGER),
SNMP_MIB_ITEM("TCPAbortFailed", LINUX_MIB_TCPABORTFAILED),
SNMP_MIB_ITEM("TCPMemoryPressures", LINUX_MIB_TCPMEMORYPRESSURES),
SNMP_MIB_ITEM("TCPMemoryPressuresChrono", LINUX_MIB_TCPMEMORYPRESSURESCHRONO),
SNMP_MIB_ITEM("TCPSACKDiscard", LINUX_MIB_TCPSACKDISCARD),
SNMP_MIB_ITEM("TCPDSACKIgnoredOld", LINUX_MIB_TCPDSACKIGNOREDOLD),
SNMP_MIB_ITEM("TCPDSACKIgnoredNoUndo", LINUX_MIB_TCPDSACKIGNOREDNOUNDO),
SNMP_MIB_ITEM("TCPSpuriousRTOs", LINUX_MIB_TCPSPURIOUSRTOS),
SNMP_MIB_ITEM("TCPMD5NotFound", LINUX_MIB_TCPMD5NOTFOUND),
SNMP_MIB_ITEM("TCPMD5Unexpected", LINUX_MIB_TCPMD5UNEXPECTED),
SNMP_MIB_ITEM("TCPMD5Failure", LINUX_MIB_TCPMD5FAILURE),
SNMP_MIB_ITEM("TCPSackShifted", LINUX_MIB_SACKSHIFTED),
SNMP_MIB_ITEM("TCPSackMerged", LINUX_MIB_SACKMERGED),
SNMP_MIB_ITEM("TCPSackShiftFallback", LINUX_MIB_SACKSHIFTFALLBACK),
SNMP_MIB_ITEM("TCPBacklogDrop", LINUX_MIB_TCPBACKLOGDROP),
SNMP_MIB_ITEM("PFMemallocDrop", LINUX_MIB_PFMEMALLOCDROP),
SNMP_MIB_ITEM("TCPMinTTLDrop", LINUX_MIB_TCPMINTTLDROP),
SNMP_MIB_ITEM("TCPDeferAcceptDrop", LINUX_MIB_TCPDEFERACCEPTDROP),
SNMP_MIB_ITEM("IPReversePathFilter", LINUX_MIB_IPRPFILTER),
SNMP_MIB_ITEM("TCPTimeWaitOverflow", LINUX_MIB_TCPTIMEWAITOVERFLOW),
SNMP_MIB_ITEM("TCPReqQFullDoCookies", LINUX_MIB_TCPREQQFULLDOCOOKIES),
SNMP_MIB_ITEM("TCPReqQFullDrop", LINUX_MIB_TCPREQQFULLDROP),
SNMP_MIB_ITEM("TCPRetransFail", LINUX_MIB_TCPRETRANSFAIL),
SNMP_MIB_ITEM("TCPRcvCoalesce", LINUX_MIB_TCPRCVCOALESCE),
SNMP_MIB_ITEM("TCPOFOQueue", LINUX_MIB_TCPOFOQUEUE),
SNMP_MIB_ITEM("TCPOFODrop", LINUX_MIB_TCPOFODROP),
SNMP_MIB_ITEM("TCPOFOMerge", LINUX_MIB_TCPOFOMERGE),
SNMP_MIB_ITEM("TCPChallengeACK", LINUX_MIB_TCPCHALLENGEACK),
SNMP_MIB_ITEM("TCPSYNChallenge", LINUX_MIB_TCPSYNCHALLENGE),
SNMP_MIB_ITEM("TCPFastOpenActive", LINUX_MIB_TCPFASTOPENACTIVE),
SNMP_MIB_ITEM("TCPFastOpenActiveFail", LINUX_MIB_TCPFASTOPENACTIVEFAIL),
SNMP_MIB_ITEM("TCPFastOpenPassive", LINUX_MIB_TCPFASTOPENPASSIVE),
SNMP_MIB_ITEM("TCPFastOpenPassiveFail", LINUX_MIB_TCPFASTOPENPASSIVEFAIL),
SNMP_MIB_ITEM("TCPFastOpenListenOverflow", LINUX_MIB_TCPFASTOPENLISTENOVERFLOW),
SNMP_MIB_ITEM("TCPFastOpenCookieReqd", LINUX_MIB_TCPFASTOPENCOOKIEREQD),
SNMP_MIB_ITEM("TCPFastOpenBlackhole", LINUX_MIB_TCPFASTOPENBLACKHOLE),
SNMP_MIB_ITEM("TCPSpuriousRtxHostQueues", LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES),
SNMP_MIB_ITEM("BusyPollRxPackets", LINUX_MIB_BUSYPOLLRXPACKETS),
SNMP_MIB_ITEM("TCPAutoCorking", LINUX_MIB_TCPAUTOCORKING),
SNMP_MIB_ITEM("TCPFromZeroWindowAdv", LINUX_MIB_TCPFROMZEROWINDOWADV),
SNMP_MIB_ITEM("TCPToZeroWindowAdv", LINUX_MIB_TCPTOZEROWINDOWADV),
SNMP_MIB_ITEM("TCPWantZeroWindowAdv", LINUX_MIB_TCPWANTZEROWINDOWADV),
SNMP_MIB_ITEM("TCPSynRetrans", LINUX_MIB_TCPSYNRETRANS),
SNMP_MIB_ITEM("TCPOrigDataSent", LINUX_MIB_TCPORIGDATASENT),
SNMP_MIB_ITEM("TCPHystartTrainDetect", LINUX_MIB_TCPHYSTARTTRAINDETECT),
SNMP_MIB_ITEM("TCPHystartTrainCwnd", LINUX_MIB_TCPHYSTARTTRAINCWND),
SNMP_MIB_ITEM("TCPHystartDelayDetect", LINUX_MIB_TCPHYSTARTDELAYDETECT),
SNMP_MIB_ITEM("TCPHystartDelayCwnd", LINUX_MIB_TCPHYSTARTDELAYCWND),
SNMP_MIB_ITEM("TCPACKSkippedSynRecv", LINUX_MIB_TCPACKSKIPPEDSYNRECV),
SNMP_MIB_ITEM("TCPACKSkippedPAWS", LINUX_MIB_TCPACKSKIPPEDPAWS),
SNMP_MIB_ITEM("TCPACKSkippedSeq", LINUX_MIB_TCPACKSKIPPEDSEQ),
SNMP_MIB_ITEM("TCPACKSkippedFinWait2", LINUX_MIB_TCPACKSKIPPEDFINWAIT2),
SNMP_MIB_ITEM("TCPACKSkippedTimeWait", LINUX_MIB_TCPACKSKIPPEDTIMEWAIT),
SNMP_MIB_ITEM("TCPACKSkippedChallenge", LINUX_MIB_TCPACKSKIPPEDCHALLENGE),
SNMP_MIB_ITEM("TCPWinProbe", LINUX_MIB_TCPWINPROBE),
SNMP_MIB_ITEM("TCPKeepAlive", LINUX_MIB_TCPKEEPALIVE),
SNMP_MIB_ITEM("TCPMTUPFail", LINUX_MIB_TCPMTUPFAIL),
SNMP_MIB_ITEM("TCPMTUPSuccess", LINUX_MIB_TCPMTUPSUCCESS),
SNMP_MIB_ITEM("TCPDelivered", LINUX_MIB_TCPDELIVERED),
SNMP_MIB_ITEM("TCPDeliveredCE", LINUX_MIB_TCPDELIVEREDCE),
SNMP_MIB_ITEM("TCPAckCompressed", LINUX_MIB_TCPACKCOMPRESSED),
SNMP_MIB_ITEM("TCPZeroWindowDrop", LINUX_MIB_TCPZEROWINDOWDROP),
SNMP_MIB_ITEM("TCPRcvQDrop", LINUX_MIB_TCPRCVQDROP),
SNMP_MIB_ITEM("TCPWqueueTooBig", LINUX_MIB_TCPWQUEUETOOBIG),
SNMP_MIB_SENTINEL
};
static void icmpmsg_put_line(struct seq_file *seq, unsigned long *vals,
unsigned short *type, int count)
{
int j;
if (count) {
seq_puts(seq, "\nIcmpMsg:");
for (j = 0; j < count; ++j)
seq_printf(seq, " %sType%u",
type[j] & 0x100 ? "Out" : "In",
type[j] & 0xff);
seq_puts(seq, "\nIcmpMsg:");
for (j = 0; j < count; ++j)
seq_printf(seq, " %lu", vals[j]);
}
}
static void icmpmsg_put(struct seq_file *seq)
{
#define PERLINE 16
int i, count;
unsigned short type[PERLINE];
unsigned long vals[PERLINE], val;
struct net *net = seq->private;
count = 0;
for (i = 0; i < ICMPMSG_MIB_MAX; i++) {
val = atomic_long_read(&net->mib.icmpmsg_statistics->mibs[i]);
if (val) {
type[count] = i;
vals[count++] = val;
}
if (count == PERLINE) {
icmpmsg_put_line(seq, vals, type, count);
count = 0;
}
}
icmpmsg_put_line(seq, vals, type, count);
#undef PERLINE
}
static void icmp_put(struct seq_file *seq)
{
int i;
struct net *net = seq->private;
atomic_long_t *ptr = net->mib.icmpmsg_statistics->mibs;
seq_puts(seq, "\nIcmp: InMsgs InErrors InCsumErrors");
for (i = 0; icmpmibmap[i].name; i++)
seq_printf(seq, " In%s", icmpmibmap[i].name);
seq_puts(seq, " OutMsgs OutErrors");
for (i = 0; icmpmibmap[i].name; i++)
seq_printf(seq, " Out%s", icmpmibmap[i].name);
seq_printf(seq, "\nIcmp: %lu %lu %lu",
snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_INMSGS),
snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_INERRORS),
snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_CSUMERRORS));
for (i = 0; icmpmibmap[i].name; i++)
seq_printf(seq, " %lu",
atomic_long_read(ptr + icmpmibmap[i].index));
seq_printf(seq, " %lu %lu",
snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_OUTMSGS),
snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_OUTERRORS));
for (i = 0; icmpmibmap[i].name; i++)
seq_printf(seq, " %lu",
atomic_long_read(ptr + (icmpmibmap[i].index | 0x100)));
}
/*
* Called from the PROCfs module. This outputs /proc/net/snmp.
*/
static int snmp_seq_show_ipstats(struct seq_file *seq, void *v)
{
struct net *net = seq->private;
u64 buff64[IPSTATS_MIB_MAX];
int i;
memset(buff64, 0, IPSTATS_MIB_MAX * sizeof(u64));
seq_puts(seq, "Ip: Forwarding DefaultTTL");
for (i = 0; snmp4_ipstats_list[i].name; i++)
seq_printf(seq, " %s", snmp4_ipstats_list[i].name);
seq_printf(seq, "\nIp: %d %d",
IPV4_DEVCONF_ALL(net, FORWARDING) ? 1 : 2,
net->ipv4.sysctl_ip_default_ttl);
BUILD_BUG_ON(offsetof(struct ipstats_mib, mibs) != 0);
snmp_get_cpu_field64_batch(buff64, snmp4_ipstats_list,
net->mib.ip_statistics,
offsetof(struct ipstats_mib, syncp));
for (i = 0; snmp4_ipstats_list[i].name; i++)
seq_printf(seq, " %llu", buff64[i]);
return 0;
}
static int snmp_seq_show_tcp_udp(struct seq_file *seq, void *v)
{
unsigned long buff[TCPUDP_MIB_MAX];
struct net *net = seq->private;
int i;
memset(buff, 0, TCPUDP_MIB_MAX * sizeof(unsigned long));
seq_puts(seq, "\nTcp:");
for (i = 0; snmp4_tcp_list[i].name; i++)
seq_printf(seq, " %s", snmp4_tcp_list[i].name);
seq_puts(seq, "\nTcp:");
snmp_get_cpu_field_batch(buff, snmp4_tcp_list,
net->mib.tcp_statistics);
for (i = 0; snmp4_tcp_list[i].name; i++) {
/* MaxConn field is signed, RFC 2012 */
if (snmp4_tcp_list[i].entry == TCP_MIB_MAXCONN)
seq_printf(seq, " %ld", buff[i]);
else
seq_printf(seq, " %lu", buff[i]);
}
memset(buff, 0, TCPUDP_MIB_MAX * sizeof(unsigned long));
snmp_get_cpu_field_batch(buff, snmp4_udp_list,
net->mib.udp_statistics);
seq_puts(seq, "\nUdp:");
for (i = 0; snmp4_udp_list[i].name; i++)
seq_printf(seq, " %s", snmp4_udp_list[i].name);
seq_puts(seq, "\nUdp:");
for (i = 0; snmp4_udp_list[i].name; i++)
seq_printf(seq, " %lu", buff[i]);
memset(buff, 0, TCPUDP_MIB_MAX * sizeof(unsigned long));
/* the UDP and UDP-Lite MIBs are the same */
seq_puts(seq, "\nUdpLite:");
snmp_get_cpu_field_batch(buff, snmp4_udp_list,
net->mib.udplite_statistics);
for (i = 0; snmp4_udp_list[i].name; i++)
seq_printf(seq, " %s", snmp4_udp_list[i].name);
seq_puts(seq, "\nUdpLite:");
for (i = 0; snmp4_udp_list[i].name; i++)
seq_printf(seq, " %lu", buff[i]);
seq_putc(seq, '\n');
return 0;
}
static int snmp_seq_show(struct seq_file *seq, void *v)
{
snmp_seq_show_ipstats(seq, v);
icmp_put(seq); /* RFC 2011 compatibility */
icmpmsg_put(seq);
snmp_seq_show_tcp_udp(seq, v);
return 0;
}
/*
* Output /proc/net/netstat
*/
static int netstat_seq_show(struct seq_file *seq, void *v)
{
int i;
struct net *net = seq->private;
seq_puts(seq, "TcpExt:");
for (i = 0; snmp4_net_list[i].name; i++)
seq_printf(seq, " %s", snmp4_net_list[i].name);
seq_puts(seq, "\nTcpExt:");
for (i = 0; snmp4_net_list[i].name; i++)
seq_printf(seq, " %lu",
snmp_fold_field(net->mib.net_statistics,
snmp4_net_list[i].entry));
seq_puts(seq, "\nIpExt:");
for (i = 0; snmp4_ipextstats_list[i].name; i++)
seq_printf(seq, " %s", snmp4_ipextstats_list[i].name);
seq_puts(seq, "\nIpExt:");
for (i = 0; snmp4_ipextstats_list[i].name; i++)
seq_printf(seq, " %llu",
snmp_fold_field64(net->mib.ip_statistics,
snmp4_ipextstats_list[i].entry,
offsetof(struct ipstats_mib, syncp)));
seq_putc(seq, '\n');
return 0;
}
static __net_init int ip_proc_init_net(struct net *net)
{
if (!proc_create_net_single("sockstat", 0444, net->proc_net,
sockstat_seq_show, NULL))
goto out_sockstat;
if (!proc_create_net_single("netstat", 0444, net->proc_net,
netstat_seq_show, NULL))
goto out_netstat;
if (!proc_create_net_single("snmp", 0444, net->proc_net, snmp_seq_show,
NULL))
goto out_snmp;
return 0;
out_snmp:
remove_proc_entry("netstat", net->proc_net);
out_netstat:
remove_proc_entry("sockstat", net->proc_net);
out_sockstat:
return -ENOMEM;
}
static __net_exit void ip_proc_exit_net(struct net *net)
{
remove_proc_entry("snmp", net->proc_net);
remove_proc_entry("netstat", net->proc_net);
remove_proc_entry("sockstat", net->proc_net);
}
static __net_initdata struct pernet_operations ip_proc_ops = {
.init = ip_proc_init_net,
.exit = ip_proc_exit_net,
};
int __init ip_misc_proc_init(void)
{
return register_pernet_subsys(&ip_proc_ops);
}
+79
View File
@@ -0,0 +1,79 @@
/*
* 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.
*
* INET protocol dispatch tables.
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
*
* Fixes:
* Alan Cox : Ahah! udp icmp errors don't work because
* udp_err is never called!
* Alan Cox : Added new fields for init and ready for
* proper fragmentation (_NO_ 4K limits!)
* Richard Colella : Hang on hash collision
* Vince Laviano : Modified inet_del_protocol() to correctly
* maintain copy bit.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/cache.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/spinlock.h>
#include <net/protocol.h>
struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly;
const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly;
EXPORT_SYMBOL(inet_offloads);
int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol)
{
if (!prot->netns_ok) {
pr_err("Protocol %u is not namespace aware, cannot register.\n",
protocol);
return -EINVAL;
}
return !cmpxchg((const struct net_protocol **)&inet_protos[protocol],
NULL, prot) ? 0 : -1;
}
EXPORT_SYMBOL(inet_add_protocol);
int inet_add_offload(const struct net_offload *prot, unsigned char protocol)
{
return !cmpxchg((const struct net_offload **)&inet_offloads[protocol],
NULL, prot) ? 0 : -1;
}
EXPORT_SYMBOL(inet_add_offload);
int inet_del_protocol(const struct net_protocol *prot, unsigned char protocol)
{
int ret;
ret = (cmpxchg((const struct net_protocol **)&inet_protos[protocol],
prot, NULL) == prot) ? 0 : -1;
synchronize_net();
return ret;
}
EXPORT_SYMBOL(inet_del_protocol);
int inet_del_offload(const struct net_offload *prot, unsigned char protocol)
{
int ret;
ret = (cmpxchg((const struct net_offload **)&inet_offloads[protocol],
prot, NULL) == prot) ? 0 : -1;
synchronize_net();
return ret;
}
EXPORT_SYMBOL(inet_del_offload);
+1136
View File
File diff suppressed because it is too large. Load diff
+264
View File
@@ -0,0 +1,264 @@
#include <linux/module.h>
#include <linux/inet_diag.h>
#include <linux/sock_diag.h>
#include <net/inet_sock.h>
#include <net/raw.h>
#include <net/rawv6.h>
#ifdef pr_fmt
# undef pr_fmt
#endif
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
static struct raw_hashinfo *
raw_get_hashinfo(const struct inet_diag_req_v2 *r)
{
if (r->sdiag_family == AF_INET) {
return &raw_v4_hashinfo;
#if IS_ENABLED(CONFIG_IPV6)
} else if (r->sdiag_family == AF_INET6) {
return &raw_v6_hashinfo;
#endif
} else {
return ERR_PTR(-EINVAL);
}
}
/*
* Due to requirement of not breaking user API we can't simply
* rename @pad field in inet_diag_req_v2 structure, instead
* use helper to figure it out.
*/
static struct sock *raw_lookup(struct net *net, struct sock *from,
const struct inet_diag_req_v2 *req)
{
struct inet_diag_req_raw *r = (void *)req;
struct sock *sk = NULL;
if (r->sdiag_family == AF_INET)
sk = __raw_v4_lookup(net, from, r->sdiag_raw_protocol,
r->id.idiag_dst[0],
r->id.idiag_src[0],
r->id.idiag_if, 0);
#if IS_ENABLED(CONFIG_IPV6)
else
sk = __raw_v6_lookup(net, from, r->sdiag_raw_protocol,
(const struct in6_addr *)r->id.idiag_src,
(const struct in6_addr *)r->id.idiag_dst,
r->id.idiag_if, 0);
#endif
return sk;
}
static struct sock *raw_sock_get(struct net *net, const struct inet_diag_req_v2 *r)
{
struct raw_hashinfo *hashinfo = raw_get_hashinfo(r);
struct sock *sk = NULL, *s;
int slot;
if (IS_ERR(hashinfo))
return ERR_CAST(hashinfo);
read_lock(&hashinfo->lock);
for (slot = 0; slot < RAW_HTABLE_SIZE; slot++) {
sk_for_each(s, &hashinfo->ht[slot]) {
sk = raw_lookup(net, s, r);
if (sk) {
/*
* Grab it and keep until we fill
* diag meaage to be reported, so
* caller should call sock_put then.
* We can do that because we're keeping
* hashinfo->lock here.
*/
sock_hold(sk);
goto out_unlock;
}
}
}
out_unlock:
read_unlock(&hashinfo->lock);
return sk ? sk : ERR_PTR(-ENOENT);
}
static int raw_diag_dump_one(struct sk_buff *in_skb,
const struct nlmsghdr *nlh,
const struct inet_diag_req_v2 *r)
{
struct net *net = sock_net(in_skb->sk);
struct sk_buff *rep;
struct sock *sk;
int err;
sk = raw_sock_get(net, r);
if (IS_ERR(sk))
return PTR_ERR(sk);
rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) +
inet_diag_msg_attrs_size() +
nla_total_size(sizeof(struct inet_diag_meminfo)) + 64,
GFP_KERNEL);
if (!rep) {
sock_put(sk);
return -ENOMEM;
}
err = inet_sk_diag_fill(sk, NULL, rep, r,
sk_user_ns(NETLINK_CB(in_skb).sk),
NETLINK_CB(in_skb).portid,
nlh->nlmsg_seq, 0, nlh,
netlink_net_capable(in_skb, CAP_NET_ADMIN));
sock_put(sk);
if (err < 0) {
kfree_skb(rep);
return err;
}
err = netlink_unicast(net->diag_nlsk, rep,
NETLINK_CB(in_skb).portid,
MSG_DONTWAIT);
if (err > 0)
err = 0;
return err;
}
static int sk_diag_dump(struct sock *sk, struct sk_buff *skb,
struct netlink_callback *cb,
const struct inet_diag_req_v2 *r,
struct nlattr *bc, bool net_admin)
{
if (!inet_diag_bc_sk(bc, sk))
return 0;
return inet_sk_diag_fill(sk, NULL, skb, r,
sk_user_ns(NETLINK_CB(cb->skb).sk),
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
cb->nlh, net_admin);
}
static void raw_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
const struct inet_diag_req_v2 *r, struct nlattr *bc)
{
bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN);
struct raw_hashinfo *hashinfo = raw_get_hashinfo(r);
struct net *net = sock_net(skb->sk);
int num, s_num, slot, s_slot;
struct sock *sk = NULL;
if (IS_ERR(hashinfo))
return;
s_slot = cb->args[0];
num = s_num = cb->args[1];
read_lock(&hashinfo->lock);
for (slot = s_slot; slot < RAW_HTABLE_SIZE; s_num = 0, slot++) {
num = 0;
sk_for_each(sk, &hashinfo->ht[slot]) {
struct inet_sock *inet = inet_sk(sk);
if (!net_eq(sock_net(sk), net))
continue;
if (num < s_num)
goto next;
if (sk->sk_family != r->sdiag_family)
goto next;
if (r->id.idiag_sport != inet->inet_sport &&
r->id.idiag_sport)
goto next;
if (r->id.idiag_dport != inet->inet_dport &&
r->id.idiag_dport)
goto next;
if (sk_diag_dump(sk, skb, cb, r, bc, net_admin) < 0)
goto out_unlock;
next:
num++;
}
}
out_unlock:
read_unlock(&hashinfo->lock);
cb->args[0] = slot;
cb->args[1] = num;
}
static void raw_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
void *info)
{
r->idiag_rqueue = sk_rmem_alloc_get(sk);
r->idiag_wqueue = sk_wmem_alloc_get(sk);
}
#ifdef CONFIG_INET_DIAG_DESTROY
static int raw_diag_destroy(struct sk_buff *in_skb,
const struct inet_diag_req_v2 *r)
{
struct net *net = sock_net(in_skb->sk);
struct sock *sk;
int err;
sk = raw_sock_get(net, r);
if (IS_ERR(sk))
return PTR_ERR(sk);
err = sock_diag_destroy(sk, ECONNABORTED);
sock_put(sk);
return err;
}
#endif
static const struct inet_diag_handler raw_diag_handler = {
.dump = raw_diag_dump,
.dump_one = raw_diag_dump_one,
.idiag_get_info = raw_diag_get_info,
.idiag_type = IPPROTO_RAW,
.idiag_info_size = 0,
#ifdef CONFIG_INET_DIAG_DESTROY
.destroy = raw_diag_destroy,
#endif
};
static void __always_unused __check_inet_diag_req_raw(void)
{
/*
* Make sure the two structures are identical,
* except the @pad field.
*/
#define __offset_mismatch(m1, m2) \
(offsetof(struct inet_diag_req_v2, m1) != \
offsetof(struct inet_diag_req_raw, m2))
BUILD_BUG_ON(sizeof(struct inet_diag_req_v2) !=
sizeof(struct inet_diag_req_raw));
BUILD_BUG_ON(__offset_mismatch(sdiag_family, sdiag_family));
BUILD_BUG_ON(__offset_mismatch(sdiag_protocol, sdiag_protocol));
BUILD_BUG_ON(__offset_mismatch(idiag_ext, idiag_ext));
BUILD_BUG_ON(__offset_mismatch(pad, sdiag_raw_protocol));
BUILD_BUG_ON(__offset_mismatch(idiag_states, idiag_states));
BUILD_BUG_ON(__offset_mismatch(id, id));
#undef __offset_mismatch
}
static int __init raw_diag_init(void)
{
return inet_diag_register(&raw_diag_handler);
}
static void __exit raw_diag_exit(void)
{
inet_diag_unregister(&raw_diag_handler);
}
module_init(raw_diag_init);
module_exit(raw_diag_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-255 /* AF_INET - IPPROTO_RAW */);
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 10-255 /* AF_INET6 - IPPROTO_RAW */);
+3263
View File
File diff suppressed because it is too large. Load diff
+415
View File
@@ -0,0 +1,415 @@
/*
* Syncookies implementation for the Linux kernel
*
* Copyright (C) 1997 Andi Kleen
* Based on ideas by D.J.Bernstein and Eric Schenk.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/tcp.h>
#include <linux/slab.h>
#include <linux/random.h>
#include <linux/siphash.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <net/secure_seq.h>
#include <net/tcp.h>
#include <net/route.h>
static siphash_key_t syncookie_secret[2] __read_mostly;
#define COOKIEBITS 24 /* Upper bits store count */
#define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
/* TCP Timestamp: 6 lowest bits of timestamp sent in the cookie SYN-ACK
* stores TCP options:
*
* MSB LSB
* | 31 ... 6 | 5 | 4 | 3 2 1 0 |
* | Timestamp | ECN | SACK | WScale |
*
* When we receive a valid cookie-ACK, we look at the echoed tsval (if
* any) to figure out which TCP options we should use for the rebuilt
* connection.
*
* A WScale setting of '0xf' (which is an invalid scaling value)
* means that original syn did not include the TCP window scaling option.
*/
#define TS_OPT_WSCALE_MASK 0xf
#define TS_OPT_SACK BIT(4)
#define TS_OPT_ECN BIT(5)
/* There is no TS_OPT_TIMESTAMP:
* if ACK contains timestamp option, we already know it was
* requested/supported by the syn/synack exchange.
*/
#define TSBITS 6
#define TSMASK (((__u32)1 << TSBITS) - 1)
static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport,
u32 count, int c)
{
net_get_random_once(syncookie_secret, sizeof(syncookie_secret));
return siphash_4u32((__force u32)saddr, (__force u32)daddr,
(__force u32)sport << 16 | (__force u32)dport,
count, &syncookie_secret[c]);
}
/*
* when syncookies are in effect and tcp timestamps are enabled we encode
* tcp options in the lower bits of the timestamp value that will be
* sent in the syn-ack.
* Since subsequent timestamps use the normal tcp_time_stamp value, we
* must make sure that the resulting initial timestamp is <= tcp_time_stamp.
*/
u64 cookie_init_timestamp(struct request_sock *req)
{
struct inet_request_sock *ireq;
u32 ts, ts_now = tcp_time_stamp_raw();
u32 options = 0;
ireq = inet_rsk(req);
options = ireq->wscale_ok ? ireq->snd_wscale : TS_OPT_WSCALE_MASK;
if (ireq->sack_ok)
options |= TS_OPT_SACK;
if (ireq->ecn_ok)
options |= TS_OPT_ECN;
ts = ts_now & ~TSMASK;
ts |= options;
if (ts > ts_now) {
ts >>= TSBITS;
ts--;
ts <<= TSBITS;
ts |= options;
}
return (u64)ts * (USEC_PER_SEC / TCP_TS_HZ);
}
static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport,
__be16 dport, __u32 sseq, __u32 data)
{
/*
* Compute the secure sequence number.
* The output should be:
* HASH(sec1,saddr,sport,daddr,dport,sec1) + sseq + (count * 2^24)
* + (HASH(sec2,saddr,sport,daddr,dport,count,sec2) % 2^24).
* Where sseq is their sequence number and count increases every
* minute by 1.
* As an extra hack, we add a small "data" value that encodes the
* MSS into the second hash value.
*/
u32 count = tcp_cookie_time();
return (cookie_hash(saddr, daddr, sport, dport, 0, 0) +
sseq + (count << COOKIEBITS) +
((cookie_hash(saddr, daddr, sport, dport, count, 1) + data)
& COOKIEMASK));
}
/*
* This retrieves the small "data" value from the syncookie.
* If the syncookie is bad, the data returned will be out of
* range. This must be checked by the caller.
*
* The count value used to generate the cookie must be less than
* MAX_SYNCOOKIE_AGE minutes in the past.
* The return value (__u32)-1 if this test fails.
*/
static __u32 check_tcp_syn_cookie(__u32 cookie, __be32 saddr, __be32 daddr,
__be16 sport, __be16 dport, __u32 sseq)
{
u32 diff, count = tcp_cookie_time();
/* Strip away the layers from the cookie */
cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq;
/* Cookie is now reduced to (count * 2^24) ^ (hash % 2^24) */
diff = (count - (cookie >> COOKIEBITS)) & ((__u32) -1 >> COOKIEBITS);
if (diff >= MAX_SYNCOOKIE_AGE)
return (__u32)-1;
return (cookie -
cookie_hash(saddr, daddr, sport, dport, count - diff, 1))
& COOKIEMASK; /* Leaving the data behind */
}
/*
* MSS Values are chosen based on the 2011 paper
* 'An Analysis of TCP Maximum Segement Sizes' by S. Alcock and R. Nelson.
* Values ..
* .. lower than 536 are rare (< 0.2%)
* .. between 537 and 1299 account for less than < 1.5% of observed values
* .. in the 1300-1349 range account for about 15 to 20% of observed mss values
* .. exceeding 1460 are very rare (< 0.04%)
*
* 1460 is the single most frequently announced mss value (30 to 46% depending
* on monitor location). Table must be sorted.
*/
static __u16 const msstab[] = {
536,
1300,
1440, /* 1440, 1452: PPPoE */
1460,
};
/*
* Generate a syncookie. mssp points to the mss, which is returned
* rounded down to the value encoded in the cookie.
*/
u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th,
u16 *mssp)
{
int mssind;
const __u16 mss = *mssp;
for (mssind = ARRAY_SIZE(msstab) - 1; mssind ; mssind--)
if (mss >= msstab[mssind])
break;
*mssp = msstab[mssind];
return secure_tcp_syn_cookie(iph->saddr, iph->daddr,
th->source, th->dest, ntohl(th->seq),
mssind);
}
EXPORT_SYMBOL_GPL(__cookie_v4_init_sequence);
__u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mssp)
{
const struct iphdr *iph = ip_hdr(skb);
const struct tcphdr *th = tcp_hdr(skb);
return __cookie_v4_init_sequence(iph, th, mssp);
}
/*
* Check if a ack sequence number is a valid syncookie.
* Return the decoded mss if it is, or 0 if not.
*/
int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
u32 cookie)
{
__u32 seq = ntohl(th->seq) - 1;
__u32 mssind = check_tcp_syn_cookie(cookie, iph->saddr, iph->daddr,
th->source, th->dest, seq);
return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0;
}
EXPORT_SYMBOL_GPL(__cookie_v4_check);
struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst, u32 tsoff)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct sock *child;
bool own_req;
child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst,
NULL, &own_req);
if (child) {
refcount_set(&req->rsk_refcnt, 1);
tcp_sk(child)->tsoffset = tsoff;
sock_rps_save_rxhash(child, skb);
if (!inet_csk_reqsk_queue_add(sk, req, child)) {
bh_unlock_sock(child);
sock_put(child);
child = NULL;
reqsk_put(req);
}
} else {
reqsk_free(req);
}
return child;
}
EXPORT_SYMBOL(tcp_get_cookie_sock);
/*
* when syncookies are in effect and tcp timestamps are enabled we stored
* additional tcp options in the timestamp.
* This extracts these options from the timestamp echo.
*
* return false if we decode a tcp option that is disabled
* on the host.
*/
bool cookie_timestamp_decode(const struct net *net,
struct tcp_options_received *tcp_opt)
{
/* echoed timestamp, lowest bits contain options */
u32 options = tcp_opt->rcv_tsecr;
if (!tcp_opt->saw_tstamp) {
tcp_clear_options(tcp_opt);
return true;
}
if (!net->ipv4.sysctl_tcp_timestamps)
return false;
tcp_opt->sack_ok = (options & TS_OPT_SACK) ? TCP_SACK_SEEN : 0;
if (tcp_opt->sack_ok && !net->ipv4.sysctl_tcp_sack)
return false;
if ((options & TS_OPT_WSCALE_MASK) == TS_OPT_WSCALE_MASK)
return true; /* no window scaling */
tcp_opt->wscale_ok = 1;
tcp_opt->snd_wscale = options & TS_OPT_WSCALE_MASK;
return net->ipv4.sysctl_tcp_window_scaling != 0;
}
EXPORT_SYMBOL(cookie_timestamp_decode);
bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt,
const struct net *net, const struct dst_entry *dst)
{
bool ecn_ok = tcp_opt->rcv_tsecr & TS_OPT_ECN;
if (!ecn_ok)
return false;
if (net->ipv4.sysctl_tcp_ecn)
return true;
return dst_feature(dst, RTAX_FEATURE_ECN);
}
EXPORT_SYMBOL(cookie_ecn_ok);
/* On input, sk is a listener.
* Output is listener if incoming packet would not create a child
* NULL if memory could not be allocated.
*/
struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
{
struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
struct tcp_options_received tcp_opt;
struct inet_request_sock *ireq;
struct tcp_request_sock *treq;
struct tcp_sock *tp = tcp_sk(sk);
const struct tcphdr *th = tcp_hdr(skb);
__u32 cookie = ntohl(th->ack_seq) - 1;
struct sock *ret = sk;
struct request_sock *req;
int full_space, mss;
struct rtable *rt;
__u8 rcv_wscale;
struct flowi4 fl4;
u32 tsoff = 0;
if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst)
goto out;
if (tcp_synq_no_recent_overflow(sk))
goto out;
mss = __cookie_v4_check(ip_hdr(skb), th, cookie);
if (mss == 0) {
__NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESFAILED);
goto out;
}
__NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV);
/* check for timestamp cookie support */
memset(&tcp_opt, 0, sizeof(tcp_opt));
tcp_parse_options(sock_net(sk), skb, &tcp_opt, 0, NULL);
if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) {
tsoff = secure_tcp_ts_off(sock_net(sk),
ip_hdr(skb)->daddr,
ip_hdr(skb)->saddr);
tcp_opt.rcv_tsecr -= tsoff;
}
if (!cookie_timestamp_decode(sock_net(sk), &tcp_opt))
goto out;
ret = NULL;
req = inet_reqsk_alloc(&tcp_request_sock_ops, sk, false); /* for safety */
if (!req)
goto out;
ireq = inet_rsk(req);
treq = tcp_rsk(req);
treq->rcv_isn = ntohl(th->seq) - 1;
treq->snt_isn = cookie;
treq->ts_off = 0;
treq->txhash = net_tx_rndhash();
req->mss = mss;
ireq->ir_num = ntohs(th->dest);
ireq->ir_rmt_port = th->source;
sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
ireq->ir_mark = inet_request_mark(sk, skb);
ireq->snd_wscale = tcp_opt.snd_wscale;
ireq->sack_ok = tcp_opt.sack_ok;
ireq->wscale_ok = tcp_opt.wscale_ok;
ireq->tstamp_ok = tcp_opt.saw_tstamp;
req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
treq->snt_synack = 0;
treq->tfo_listener = false;
if (IS_ENABLED(CONFIG_SMC))
ireq->smc_ok = 0;
ireq->ir_iif = inet_request_bound_dev_if(sk, skb);
/* We throwed the options of the initial SYN away, so we hope
* the ACK carries the same options again (see RFC1122 4.2.3.8)
*/
RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(sock_net(sk), skb));
if (security_inet_conn_request(sk, skb, req)) {
reqsk_free(req);
goto out;
}
req->num_retrans = 0;
/*
* We need to lookup the route here to get at the correct
* window size. We should better make sure that the window size
* hasn't changed since we received the original syn, but I see
* no easy way to do this.
*/
flowi4_init_output(&fl4, ireq->ir_iif, ireq->ir_mark,
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
inet_sk_flowi_flags(sk),
opt->srr ? opt->faddr : ireq->ir_rmt_addr,
ireq->ir_loc_addr, th->source, th->dest, sk->sk_uid);
security_req_classify_flow(req, flowi4_to_flowi(&fl4));
rt = ip_route_output_key(sock_net(sk), &fl4);
if (IS_ERR(rt)) {
reqsk_free(req);
goto out;
}
/* Try to redo what tcp_v4_send_synack did. */
req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW);
/* limit the window selection if the user enforce a smaller rx buffer */
full_space = tcp_full_space(sk);
if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
(req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0))
req->rsk_window_clamp = full_space;
tcp_select_initial_window(sk, full_space, req->mss,
&req->rsk_rcv_wnd, &req->rsk_window_clamp,
ireq->wscale_ok, &rcv_wscale,
dst_metric(&rt->dst, RTAX_INITRWND));
ireq->rcv_wscale = rcv_wscale;
ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), &rt->dst);
ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst, tsoff);
/* ip_queue_xmit() depends on our flow being setup
* Normal sockets get it right from inet_csk_route_child_sock()
*/
if (ret)
inet_sk(ret)->cork.fl.u.ip4 = fl4;
out: return ret;
}
File diff suppressed because it is too large. Load diff
+3957
View File
File diff suppressed because it is too large. Load diff
+1118
View File
File diff suppressed because it is too large. Load diff
+227
View File
@@ -0,0 +1,227 @@
/*
* Binary Increase Congestion control for TCP
* Home page:
* http://netsrv.csc.ncsu.edu/twiki/bin/view/Main/BIC
* This is from the implementation of BICTCP in
* Lison-Xu, Kahaled Harfoush, and Injong Rhee.
* "Binary Increase Congestion Control for Fast, Long Distance
* Networks" in InfoComm 2004
* Available from:
* http://netsrv.csc.ncsu.edu/export/bitcp.pdf
*
* Unless BIC is enabled and congestion window is large
* this behaves the same as the original Reno.
*/
#include <linux/mm.h>
#include <linux/module.h>
#include <net/tcp.h>
#define BICTCP_BETA_SCALE 1024 /* Scale factor beta calculation
* max_cwnd = snd_cwnd * beta
*/
#define BICTCP_B 4 /*
* In binary search,
* go to point (max+min)/N
*/
static int fast_convergence = 1;
static int max_increment = 16;
static int low_window = 14;
static int beta = 819; /* = 819/1024 (BICTCP_BETA_SCALE) */
static int initial_ssthresh;
static int smooth_part = 20;
module_param(fast_convergence, int, 0644);
MODULE_PARM_DESC(fast_convergence, "turn on/off fast convergence");
module_param(max_increment, int, 0644);
MODULE_PARM_DESC(max_increment, "Limit on increment allowed during binary search");
module_param(low_window, int, 0644);
MODULE_PARM_DESC(low_window, "lower bound on congestion window (for TCP friendliness)");
module_param(beta, int, 0644);
MODULE_PARM_DESC(beta, "beta for multiplicative increase");
module_param(initial_ssthresh, int, 0644);
MODULE_PARM_DESC(initial_ssthresh, "initial value of slow start threshold");
module_param(smooth_part, int, 0644);
MODULE_PARM_DESC(smooth_part, "log(B/(B*Smin))/log(B/(B-1))+B, # of RTT from Wmax-B to Wmax");
/* BIC TCP Parameters */
struct bictcp {
u32 cnt; /* increase cwnd by 1 after ACKs */
u32 last_max_cwnd; /* last maximum snd_cwnd */
u32 last_cwnd; /* the last snd_cwnd */
u32 last_time; /* time when updated last_cwnd */
u32 epoch_start; /* beginning of an epoch */
#define ACK_RATIO_SHIFT 4
u32 delayed_ack; /* estimate the ratio of Packets/ACKs << 4 */
};
static inline void bictcp_reset(struct bictcp *ca)
{
ca->cnt = 0;
ca->last_max_cwnd = 0;
ca->last_cwnd = 0;
ca->last_time = 0;
ca->epoch_start = 0;
ca->delayed_ack = 2 << ACK_RATIO_SHIFT;
}
static void bictcp_init(struct sock *sk)
{
struct bictcp *ca = inet_csk_ca(sk);
bictcp_reset(ca);
if (initial_ssthresh)
tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
}
/*
* Compute congestion window to use.
*/
static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
{
if (ca->last_cwnd == cwnd &&
(s32)(tcp_jiffies32 - ca->last_time) <= HZ / 32)
return;
ca->last_cwnd = cwnd;
ca->last_time = tcp_jiffies32;
if (ca->epoch_start == 0) /* record the beginning of an epoch */
ca->epoch_start = tcp_jiffies32;
/* start off normal */
if (cwnd <= low_window) {
ca->cnt = cwnd;
return;
}
/* binary increase */
if (cwnd < ca->last_max_cwnd) {
__u32 dist = (ca->last_max_cwnd - cwnd)
/ BICTCP_B;
if (dist > max_increment)
/* linear increase */
ca->cnt = cwnd / max_increment;
else if (dist <= 1U)
/* binary search increase */
ca->cnt = (cwnd * smooth_part) / BICTCP_B;
else
/* binary search increase */
ca->cnt = cwnd / dist;
} else {
/* slow start AMD linear increase */
if (cwnd < ca->last_max_cwnd + BICTCP_B)
/* slow start */
ca->cnt = (cwnd * smooth_part) / BICTCP_B;
else if (cwnd < ca->last_max_cwnd + max_increment*(BICTCP_B-1))
/* slow start */
ca->cnt = (cwnd * (BICTCP_B-1))
/ (cwnd - ca->last_max_cwnd);
else
/* linear increase */
ca->cnt = cwnd / max_increment;
}
/* if in slow start or link utilization is very low */
if (ca->last_max_cwnd == 0) {
if (ca->cnt > 20) /* increase cwnd 5% per RTT */
ca->cnt = 20;
}
ca->cnt = (ca->cnt << ACK_RATIO_SHIFT) / ca->delayed_ack;
if (ca->cnt == 0) /* cannot be zero */
ca->cnt = 1;
}
static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
{
struct tcp_sock *tp = tcp_sk(sk);
struct bictcp *ca = inet_csk_ca(sk);
if (!tcp_is_cwnd_limited(sk))
return;
if (tcp_in_slow_start(tp))
tcp_slow_start(tp, acked);
else {
bictcp_update(ca, tp->snd_cwnd);
tcp_cong_avoid_ai(tp, ca->cnt, 1);
}
}
/*
* behave like Reno until low_window is reached,
* then increase congestion window slowly
*/
static u32 bictcp_recalc_ssthresh(struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
struct bictcp *ca = inet_csk_ca(sk);
ca->epoch_start = 0; /* end of epoch */
/* Wmax and fast convergence */
if (tp->snd_cwnd < ca->last_max_cwnd && fast_convergence)
ca->last_max_cwnd = (tp->snd_cwnd * (BICTCP_BETA_SCALE + beta))
/ (2 * BICTCP_BETA_SCALE);
else
ca->last_max_cwnd = tp->snd_cwnd;
if (tp->snd_cwnd <= low_window)
return max(tp->snd_cwnd >> 1U, 2U);
else
return max((tp->snd_cwnd * beta) / BICTCP_BETA_SCALE, 2U);
}
static void bictcp_state(struct sock *sk, u8 new_state)
{
if (new_state == TCP_CA_Loss)
bictcp_reset(inet_csk_ca(sk));
}
/* Track delayed acknowledgment ratio using sliding window
* ratio = (15*ratio + sample) / 16
*/
static void bictcp_acked(struct sock *sk, const struct ack_sample *sample)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
if (icsk->icsk_ca_state == TCP_CA_Open) {
struct bictcp *ca = inet_csk_ca(sk);
ca->delayed_ack += sample->pkts_acked -
(ca->delayed_ack >> ACK_RATIO_SHIFT);
}
}
static struct tcp_congestion_ops bictcp __read_mostly = {
.init = bictcp_init,
.ssthresh = bictcp_recalc_ssthresh,
.cong_avoid = bictcp_cong_avoid,
.set_state = bictcp_state,
.undo_cwnd = tcp_reno_undo_cwnd,
.pkts_acked = bictcp_acked,
.owner = THIS_MODULE,
.name = "bic",
};
static int __init bictcp_register(void)
{
BUILD_BUG_ON(sizeof(struct bictcp) > ICSK_CA_PRIV_SIZE);
return tcp_register_congestion_control(&bictcp);
}
static void __exit bictcp_unregister(void)
{
tcp_unregister_congestion_control(&bictcp);
}
module_init(bictcp_register);
module_exit(bictcp_unregister);
MODULE_AUTHOR("Stephen Hemminger");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("BIC TCP");
+425
View File
@@ -0,0 +1,425 @@
/*
* CAIA Delay-Gradient (CDG) congestion control
*
* This implementation is based on the paper:
* D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using
* delay gradients." In IFIP Networking, pages 328-341. Springer, 2011.
*
* Scavenger traffic (Less-than-Best-Effort) should disable coexistence
* heuristics using parameters use_shadow=0 and use_ineff=0.
*
* Parameters window, backoff_beta, and backoff_factor are crucial for
* throughput and delay. Future work is needed to determine better defaults,
* and to provide guidelines for use in different environments/contexts.
*
* Except for window, knobs are configured via /sys/module/tcp_cdg/parameters/.
* Parameter window is only configurable when loading tcp_cdg as a module.
*
* Notable differences from paper/FreeBSD:
* o Using Hybrid Slow start and Proportional Rate Reduction.
* o Add toggle for shadow window mechanism. Suggested by David Hayes.
* o Add toggle for non-congestion loss tolerance.
* o Scaling parameter G is changed to a backoff factor;
* conversion is given by: backoff_factor = 1000/(G * window).
* o Limit shadow window to 2 * cwnd, or to cwnd when application limited.
* o More accurate e^-x.
*/
#include <linux/kernel.h>
#include <linux/random.h>
#include <linux/module.h>
#include <linux/sched/clock.h>
#include <net/tcp.h>
#define HYSTART_ACK_TRAIN 1
#define HYSTART_DELAY 2
static int window __read_mostly = 8;
static unsigned int backoff_beta __read_mostly = 0.7071 * 1024; /* sqrt 0.5 */
static unsigned int backoff_factor __read_mostly = 42;
static unsigned int hystart_detect __read_mostly = 3;
static unsigned int use_ineff __read_mostly = 5;
static bool use_shadow __read_mostly = true;
static bool use_tolerance __read_mostly;
module_param(window, int, 0444);
MODULE_PARM_DESC(window, "gradient window size (power of two <= 256)");
module_param(backoff_beta, uint, 0644);
MODULE_PARM_DESC(backoff_beta, "backoff beta (0-1024)");
module_param(backoff_factor, uint, 0644);
MODULE_PARM_DESC(backoff_factor, "backoff probability scale factor");
module_param(hystart_detect, uint, 0644);
MODULE_PARM_DESC(hystart_detect, "use Hybrid Slow start "
"(0: disabled, 1: ACK train, 2: delay threshold, 3: both)");
module_param(use_ineff, uint, 0644);
MODULE_PARM_DESC(use_ineff, "use ineffectual backoff detection (threshold)");
module_param(use_shadow, bool, 0644);
MODULE_PARM_DESC(use_shadow, "use shadow window heuristic");
module_param(use_tolerance, bool, 0644);
MODULE_PARM_DESC(use_tolerance, "use loss tolerance heuristic");
struct cdg_minmax {
union {
struct {
s32 min;
s32 max;
};
u64 v64;
};
};
enum cdg_state {
CDG_UNKNOWN = 0,
CDG_NONFULL = 1,
CDG_FULL = 2,
CDG_BACKOFF = 3,
};
struct cdg {
struct cdg_minmax rtt;
struct cdg_minmax rtt_prev;
struct cdg_minmax *gradients;
struct cdg_minmax gsum;
bool gfilled;
u8 tail;
u8 state;
u8 delack;
u32 rtt_seq;
u32 shadow_wnd;
u16 backoff_cnt;
u16 sample_cnt;
s32 delay_min;
u32 last_ack;
u32 round_start;
};
/**
* nexp_u32 - negative base-e exponential
* @ux: x in units of micro
*
* Returns exp(ux * -1e-6) * U32_MAX.
*/
static u32 __pure nexp_u32(u32 ux)
{
static const u16 v[] = {
/* exp(-x)*65536-1 for x = 0, 0.000256, 0.000512, ... */
65535,
65518, 65501, 65468, 65401, 65267, 65001, 64470, 63422,
61378, 57484, 50423, 38795, 22965, 8047, 987, 14,
};
u32 msb = ux >> 8;
u32 res;
int i;
/* Cut off when ux >= 2^24 (actual result is <= 222/U32_MAX). */
if (msb > U16_MAX)
return 0;
/* Scale first eight bits linearly: */
res = U32_MAX - (ux & 0xff) * (U32_MAX / 1000000);
/* Obtain e^(x + y + ...) by computing e^x * e^y * ...: */
for (i = 1; msb; i++, msb >>= 1) {
u32 y = v[i & -(msb & 1)] + U32_C(1);
res = ((u64)res * y) >> 16;
}
return res;
}
/* Based on the HyStart algorithm (by Ha et al.) that is implemented in
* tcp_cubic. Differences/experimental changes:
* o Using Hayes' delayed ACK filter.
* o Using a usec clock for the ACK train.
* o Reset ACK train when application limited.
* o Invoked at any cwnd (i.e. also when cwnd < 16).
* o Invoked only when cwnd < ssthresh (i.e. not when cwnd == ssthresh).
*/
static void tcp_cdg_hystart_update(struct sock *sk)
{
struct cdg *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);
ca->delay_min = min_not_zero(ca->delay_min, ca->rtt.min);
if (ca->delay_min == 0)
return;
if (hystart_detect & HYSTART_ACK_TRAIN) {
u32 now_us = div_u64(local_clock(), NSEC_PER_USEC);
if (ca->last_ack == 0 || !tcp_is_cwnd_limited(sk)) {
ca->last_ack = now_us;
ca->round_start = now_us;
} else if (before(now_us, ca->last_ack + 3000)) {
u32 base_owd = max(ca->delay_min / 2U, 125U);
ca->last_ack = now_us;
if (after(now_us, ca->round_start + base_owd)) {
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPHYSTARTTRAINDETECT);
NET_ADD_STATS(sock_net(sk),
LINUX_MIB_TCPHYSTARTTRAINCWND,
tp->snd_cwnd);
tp->snd_ssthresh = tp->snd_cwnd;
return;
}
}
}
if (hystart_detect & HYSTART_DELAY) {
if (ca->sample_cnt < 8) {
ca->sample_cnt++;
} else {
s32 thresh = max(ca->delay_min + ca->delay_min / 8U,
125U);
if (ca->rtt.min > thresh) {
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPHYSTARTDELAYDETECT);
NET_ADD_STATS(sock_net(sk),
LINUX_MIB_TCPHYSTARTDELAYCWND,
tp->snd_cwnd);
tp->snd_ssthresh = tp->snd_cwnd;
}
}
}
}
static s32 tcp_cdg_grad(struct cdg *ca)
{
s32 gmin = ca->rtt.min - ca->rtt_prev.min;
s32 gmax = ca->rtt.max - ca->rtt_prev.max;
s32 grad;
if (ca->gradients) {
ca->gsum.min += gmin - ca->gradients[ca->tail].min;
ca->gsum.max += gmax - ca->gradients[ca->tail].max;
ca->gradients[ca->tail].min = gmin;
ca->gradients[ca->tail].max = gmax;
ca->tail = (ca->tail + 1) & (window - 1);
gmin = ca->gsum.min;
gmax = ca->gsum.max;
}
/* We keep sums to ignore gradients during cwnd reductions;
* the paper's smoothed gradients otherwise simplify to:
* (rtt_latest - rtt_oldest) / window.
*
* We also drop division by window here.
*/
grad = gmin > 0 ? gmin : gmax;
/* Extrapolate missing values in gradient window: */
if (!ca->gfilled) {
if (!ca->gradients && window > 1)
grad *= window; /* Memory allocation failed. */
else if (ca->tail == 0)
ca->gfilled = true;
else
grad = (grad * window) / (int)ca->tail;
}
/* Backoff was effectual: */
if (gmin <= -32 || gmax <= -32)
ca->backoff_cnt = 0;
if (use_tolerance) {
/* Reduce small variations to zero: */
gmin = DIV_ROUND_CLOSEST(gmin, 64);
gmax = DIV_ROUND_CLOSEST(gmax, 64);
if (gmin > 0 && gmax <= 0)
ca->state = CDG_FULL;
else if ((gmin > 0 && gmax > 0) || gmax < 0)
ca->state = CDG_NONFULL;
}
return grad;
}
static bool tcp_cdg_backoff(struct sock *sk, u32 grad)
{
struct cdg *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);
if (prandom_u32() <= nexp_u32(grad * backoff_factor))
return false;
if (use_ineff) {
ca->backoff_cnt++;
if (ca->backoff_cnt > use_ineff)
return false;
}
ca->shadow_wnd = max(ca->shadow_wnd, tp->snd_cwnd);
ca->state = CDG_BACKOFF;
tcp_enter_cwr(sk);
return true;
}
/* Not called in CWR or Recovery state. */
static void tcp_cdg_cong_avoid(struct sock *sk, u32 ack, u32 acked)
{
struct cdg *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);
u32 prior_snd_cwnd;
u32 incr;
if (tcp_in_slow_start(tp) && hystart_detect)
tcp_cdg_hystart_update(sk);
if (after(ack, ca->rtt_seq) && ca->rtt.v64) {
s32 grad = 0;
if (ca->rtt_prev.v64)
grad = tcp_cdg_grad(ca);
ca->rtt_seq = tp->snd_nxt;
ca->rtt_prev = ca->rtt;
ca->rtt.v64 = 0;
ca->last_ack = 0;
ca->sample_cnt = 0;
if (grad > 0 && tcp_cdg_backoff(sk, grad))
return;
}
if (!tcp_is_cwnd_limited(sk)) {
ca->shadow_wnd = min(ca->shadow_wnd, tp->snd_cwnd);
return;
}
prior_snd_cwnd = tp->snd_cwnd;
tcp_reno_cong_avoid(sk, ack, acked);
incr = tp->snd_cwnd - prior_snd_cwnd;
ca->shadow_wnd = max(ca->shadow_wnd, ca->shadow_wnd + incr);
}
static void tcp_cdg_acked(struct sock *sk, const struct ack_sample *sample)
{
struct cdg *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);
if (sample->rtt_us <= 0)
return;
/* A heuristic for filtering delayed ACKs, adapted from:
* D.A. Hayes. "Timing enhancements to the FreeBSD kernel to support
* delay and rate based TCP mechanisms." TR 100219A. CAIA, 2010.
*/
if (tp->sacked_out == 0) {
if (sample->pkts_acked == 1 && ca->delack) {
/* A delayed ACK is only used for the minimum if it is
* provenly lower than an existing non-zero minimum.
*/
ca->rtt.min = min(ca->rtt.min, sample->rtt_us);
ca->delack--;
return;
} else if (sample->pkts_acked > 1 && ca->delack < 5) {
ca->delack++;
}
}
ca->rtt.min = min_not_zero(ca->rtt.min, sample->rtt_us);
ca->rtt.max = max(ca->rtt.max, sample->rtt_us);
}
static u32 tcp_cdg_ssthresh(struct sock *sk)
{
struct cdg *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);
if (ca->state == CDG_BACKOFF)
return max(2U, (tp->snd_cwnd * min(1024U, backoff_beta)) >> 10);
if (ca->state == CDG_NONFULL && use_tolerance)
return tp->snd_cwnd;
ca->shadow_wnd = min(ca->shadow_wnd >> 1, tp->snd_cwnd);
if (use_shadow)
return max3(2U, ca->shadow_wnd, tp->snd_cwnd >> 1);
return max(2U, tp->snd_cwnd >> 1);
}
static void tcp_cdg_cwnd_event(struct sock *sk, const enum tcp_ca_event ev)
{
struct cdg *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct cdg_minmax *gradients;
switch (ev) {
case CA_EVENT_CWND_RESTART:
gradients = ca->gradients;
if (gradients)
memset(gradients, 0, window * sizeof(gradients[0]));
memset(ca, 0, sizeof(*ca));
ca->gradients = gradients;
ca->rtt_seq = tp->snd_nxt;
ca->shadow_wnd = tp->snd_cwnd;
break;
case CA_EVENT_COMPLETE_CWR:
ca->state = CDG_UNKNOWN;
ca->rtt_seq = tp->snd_nxt;
ca->rtt_prev = ca->rtt;
ca->rtt.v64 = 0;
break;
default:
break;
}
}
static void tcp_cdg_init(struct sock *sk)
{
struct cdg *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);
/* We silently fall back to window = 1 if allocation fails. */
if (window > 1)
ca->gradients = kcalloc(window, sizeof(ca->gradients[0]),
GFP_NOWAIT | __GFP_NOWARN);
ca->rtt_seq = tp->snd_nxt;
ca->shadow_wnd = tp->snd_cwnd;
}
static void tcp_cdg_release(struct sock *sk)
{
struct cdg *ca = inet_csk_ca(sk);
kfree(ca->gradients);
}
static struct tcp_congestion_ops tcp_cdg __read_mostly = {
.cong_avoid = tcp_cdg_cong_avoid,
.cwnd_event = tcp_cdg_cwnd_event,
.pkts_acked = tcp_cdg_acked,
.undo_cwnd = tcp_reno_undo_cwnd,
.ssthresh = tcp_cdg_ssthresh,
.release = tcp_cdg_release,
.init = tcp_cdg_init,
.owner = THIS_MODULE,
.name = "cdg",
};
static int __init tcp_cdg_register(void)
{
if (backoff_beta > 1024 || window < 1 || window > 256)
return -ERANGE;
if (!is_power_of_2(window))
return -EINVAL;
BUILD_BUG_ON(sizeof(struct cdg) > ICSK_CA_PRIV_SIZE);
tcp_register_congestion_control(&tcp_cdg);
return 0;
}
static void __exit tcp_cdg_unregister(void)
{
tcp_unregister_congestion_control(&tcp_cdg);
}
module_init(tcp_cdg_register);
module_exit(tcp_cdg_unregister);
MODULE_AUTHOR("Kenneth Klette Jonassen");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("TCP CDG");
Loaded 100 of 80519 files, more files were not shown because too many files have changed in this diff. Show more