mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-25 02:09:42 +00:00
![Daniel Borkmann](/assets/img/avatar_default.png)
Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_<tag>, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
449 lines
14 KiB
Text
449 lines
14 KiB
Text
#
|
|
# Network configuration
|
|
#
|
|
|
|
menuconfig NET
|
|
bool "Networking support"
|
|
select NLATTR
|
|
select GENERIC_NET_UTILS
|
|
select BPF
|
|
---help---
|
|
Unless you really know what you are doing, you should say Y here.
|
|
The reason is that some programs need kernel networking support even
|
|
when running on a stand-alone machine that isn't connected to any
|
|
other computer.
|
|
|
|
If you are upgrading from an older kernel, you
|
|
should consider updating your networking tools too because changes
|
|
in the kernel and the tools often go hand in hand. The tools are
|
|
contained in the package net-tools, the location and version number
|
|
of which are given in <file:Documentation/Changes>.
|
|
|
|
For a general introduction to Linux networking, it is highly
|
|
recommended to read the NET-HOWTO, available from
|
|
<http://www.tldp.org/docs.html#howto>.
|
|
|
|
if NET
|
|
|
|
config WANT_COMPAT_NETLINK_MESSAGES
|
|
bool
|
|
help
|
|
This option can be selected by other options that need compat
|
|
netlink messages.
|
|
|
|
config COMPAT_NETLINK_MESSAGES
|
|
def_bool y
|
|
depends on COMPAT
|
|
depends on WEXT_CORE || WANT_COMPAT_NETLINK_MESSAGES
|
|
help
|
|
This option makes it possible to send different netlink messages
|
|
to tasks depending on whether the task is a compat task or not. To
|
|
achieve this, you need to set skb_shinfo(skb)->frag_list to the
|
|
compat skb before sending the skb, the netlink code will sort out
|
|
which message to actually pass to the task.
|
|
|
|
Newly written code should NEVER need this option but do
|
|
compat-independent messages instead!
|
|
|
|
config NET_INGRESS
|
|
bool
|
|
|
|
config NET_EGRESS
|
|
bool
|
|
|
|
menu "Networking options"
|
|
|
|
source "net/packet/Kconfig"
|
|
source "net/unix/Kconfig"
|
|
source "net/xfrm/Kconfig"
|
|
source "net/iucv/Kconfig"
|
|
source "net/smc/Kconfig"
|
|
|
|
config INET
|
|
bool "TCP/IP networking"
|
|
select CRYPTO
|
|
select CRYPTO_AES
|
|
---help---
|
|
These are the protocols used on the Internet and on most local
|
|
Ethernets. It is highly recommended to say Y here (this will enlarge
|
|
your kernel by about 400 KB), since some programs (e.g. the X window
|
|
system) use TCP/IP even if your machine is not connected to any
|
|
other computer. You will get the so-called loopback device which
|
|
allows you to ping yourself (great fun, that!).
|
|
|
|
For an excellent introduction to Linux networking, please read the
|
|
Linux Networking HOWTO, available from
|
|
<http://www.tldp.org/docs.html#howto>.
|
|
|
|
If you say Y here and also to "/proc file system support" and
|
|
"Sysctl support" below, you can change various aspects of the
|
|
behavior of the TCP/IP code by writing to the (virtual) files in
|
|
/proc/sys/net/ipv4/*; the options are explained in the file
|
|
<file:Documentation/networking/ip-sysctl.txt>.
|
|
|
|
Short answer: say Y.
|
|
|
|
if INET
|
|
source "net/ipv4/Kconfig"
|
|
source "net/ipv6/Kconfig"
|
|
source "net/netlabel/Kconfig"
|
|
|
|
endif # if INET
|
|
|
|
config NETWORK_SECMARK
|
|
bool "Security Marking"
|
|
help
|
|
This enables security marking of network packets, similar
|
|
to nfmark, but designated for security purposes.
|
|
If you are unsure how to answer this question, answer N.
|
|
|
|
config NET_PTP_CLASSIFY
|
|
def_bool n
|
|
|
|
config NETWORK_PHY_TIMESTAMPING
|
|
bool "Timestamping in PHY devices"
|
|
select NET_PTP_CLASSIFY
|
|
help
|
|
This allows timestamping of network packets by PHYs with
|
|
hardware timestamping capabilities. This option adds some
|
|
overhead in the transmit and receive paths.
|
|
|
|
If you are unsure how to answer this question, answer N.
|
|
|
|
menuconfig NETFILTER
|
|
bool "Network packet filtering framework (Netfilter)"
|
|
---help---
|
|
Netfilter is a framework for filtering and mangling network packets
|
|
that pass through your Linux box.
|
|
|
|
The most common use of packet filtering is to run your Linux box as
|
|
a firewall protecting a local network from the Internet. The type of
|
|
firewall provided by this kernel support is called a "packet
|
|
filter", which means that it can reject individual network packets
|
|
based on type, source, destination etc. The other kind of firewall,
|
|
a "proxy-based" one, is more secure but more intrusive and more
|
|
bothersome to set up; it inspects the network traffic much more
|
|
closely, modifies it and has knowledge about the higher level
|
|
protocols, which a packet filter lacks. Moreover, proxy-based
|
|
firewalls often require changes to the programs running on the local
|
|
clients. Proxy-based firewalls don't need support by the kernel, but
|
|
they are often combined with a packet filter, which only works if
|
|
you say Y here.
|
|
|
|
You should also say Y here if you intend to use your Linux box as
|
|
the gateway to the Internet for a local network of machines without
|
|
globally valid IP addresses. This is called "masquerading": if one
|
|
of the computers on your local network wants to send something to
|
|
the outside, your box can "masquerade" as that computer, i.e. it
|
|
forwards the traffic to the intended outside destination, but
|
|
modifies the packets to make it look like they came from the
|
|
firewall box itself. It works both ways: if the outside host
|
|
replies, the Linux box will silently forward the traffic to the
|
|
correct local computer. This way, the computers on your local net
|
|
are completely invisible to the outside world, even though they can
|
|
reach the outside and can receive replies. It is even possible to
|
|
run globally visible servers from within a masqueraded local network
|
|
using a mechanism called portforwarding. Masquerading is also often
|
|
called NAT (Network Address Translation).
|
|
|
|
Another use of Netfilter is in transparent proxying: if a machine on
|
|
the local network tries to connect to an outside host, your Linux
|
|
box can transparently forward the traffic to a local server,
|
|
typically a caching proxy server.
|
|
|
|
Yet another use of Netfilter is building a bridging firewall. Using
|
|
a bridge with Network packet filtering enabled makes iptables "see"
|
|
the bridged traffic. For filtering on the lower network and Ethernet
|
|
protocols over the bridge, use ebtables (under bridge netfilter
|
|
configuration).
|
|
|
|
Various modules exist for netfilter which replace the previous
|
|
masquerading (ipmasqadm), packet filtering (ipchains), transparent
|
|
proxying, and portforwarding mechanisms. Please see
|
|
<file:Documentation/Changes> under "iptables" for the location of
|
|
these packages.
|
|
|
|
if NETFILTER
|
|
|
|
config NETFILTER_DEBUG
|
|
bool "Network packet filtering debugging"
|
|
depends on NETFILTER
|
|
help
|
|
You can say Y here if you want to get additional messages useful in
|
|
debugging the netfilter code.
|
|
|
|
config NETFILTER_ADVANCED
|
|
bool "Advanced netfilter configuration"
|
|
depends on NETFILTER
|
|
default y
|
|
help
|
|
If you say Y here you can select between all the netfilter modules.
|
|
If you say N the more unusual ones will not be shown and the
|
|
basic ones needed by most people will default to 'M'.
|
|
|
|
If unsure, say Y.
|
|
|
|
config BRIDGE_NETFILTER
|
|
tristate "Bridged IP/ARP packets filtering"
|
|
depends on BRIDGE
|
|
depends on NETFILTER && INET
|
|
depends on NETFILTER_ADVANCED
|
|
default m
|
|
---help---
|
|
Enabling this option will let arptables resp. iptables see bridged
|
|
ARP resp. IP traffic. If you want a bridging firewall, you probably
|
|
want this option enabled.
|
|
Enabling or disabling this option doesn't enable or disable
|
|
ebtables.
|
|
|
|
If unsure, say N.
|
|
|
|
source "net/netfilter/Kconfig"
|
|
source "net/ipv4/netfilter/Kconfig"
|
|
source "net/ipv6/netfilter/Kconfig"
|
|
source "net/decnet/netfilter/Kconfig"
|
|
source "net/bridge/netfilter/Kconfig"
|
|
|
|
endif
|
|
|
|
source "net/dccp/Kconfig"
|
|
source "net/sctp/Kconfig"
|
|
source "net/rds/Kconfig"
|
|
source "net/tipc/Kconfig"
|
|
source "net/atm/Kconfig"
|
|
source "net/l2tp/Kconfig"
|
|
source "net/802/Kconfig"
|
|
source "net/bridge/Kconfig"
|
|
source "net/dsa/Kconfig"
|
|
source "net/8021q/Kconfig"
|
|
source "net/decnet/Kconfig"
|
|
source "net/llc/Kconfig"
|
|
source "net/ipx/Kconfig"
|
|
source "drivers/net/appletalk/Kconfig"
|
|
source "net/x25/Kconfig"
|
|
source "net/lapb/Kconfig"
|
|
source "net/phonet/Kconfig"
|
|
source "net/6lowpan/Kconfig"
|
|
source "net/ieee802154/Kconfig"
|
|
source "net/mac802154/Kconfig"
|
|
source "net/sched/Kconfig"
|
|
source "net/dcb/Kconfig"
|
|
source "net/dns_resolver/Kconfig"
|
|
source "net/batman-adv/Kconfig"
|
|
source "net/openvswitch/Kconfig"
|
|
source "net/vmw_vsock/Kconfig"
|
|
source "net/netlink/Kconfig"
|
|
source "net/mpls/Kconfig"
|
|
source "net/hsr/Kconfig"
|
|
source "net/switchdev/Kconfig"
|
|
source "net/l3mdev/Kconfig"
|
|
source "net/qrtr/Kconfig"
|
|
source "net/ncsi/Kconfig"
|
|
|
|
config RPS
|
|
bool
|
|
depends on SMP && SYSFS
|
|
default y
|
|
|
|
config RFS_ACCEL
|
|
bool
|
|
depends on RPS
|
|
select CPU_RMAP
|
|
default y
|
|
|
|
config XPS
|
|
bool
|
|
depends on SMP
|
|
default y
|
|
|
|
config HWBM
|
|
bool
|
|
|
|
config CGROUP_NET_PRIO
|
|
bool "Network priority cgroup"
|
|
depends on CGROUPS
|
|
select SOCK_CGROUP_DATA
|
|
---help---
|
|
Cgroup subsystem for use in assigning processes to network priorities on
|
|
a per-interface basis.
|
|
|
|
config CGROUP_NET_CLASSID
|
|
bool "Network classid cgroup"
|
|
depends on CGROUPS
|
|
select SOCK_CGROUP_DATA
|
|
---help---
|
|
Cgroup subsystem for use as general purpose socket classid marker that is
|
|
being used in cls_cgroup and for netfilter matching.
|
|
|
|
config NET_RX_BUSY_POLL
|
|
bool
|
|
default y
|
|
|
|
config BQL
|
|
bool
|
|
depends on SYSFS
|
|
select DQL
|
|
default y
|
|
|
|
config BPF_JIT
|
|
bool "enable BPF Just In Time compiler"
|
|
depends on HAVE_CBPF_JIT || HAVE_EBPF_JIT
|
|
depends on MODULES
|
|
---help---
|
|
Berkeley Packet Filter filtering capabilities are normally handled
|
|
by an interpreter. This option allows kernel to generate a native
|
|
code when filter is loaded in memory. This should speedup
|
|
packet sniffing (libpcap/tcpdump).
|
|
|
|
Note, admin should enable this feature changing:
|
|
/proc/sys/net/core/bpf_jit_enable
|
|
/proc/sys/net/core/bpf_jit_harden (optional)
|
|
/proc/sys/net/core/bpf_jit_kallsyms (optional)
|
|
|
|
config NET_FLOW_LIMIT
|
|
bool
|
|
depends on RPS
|
|
default y
|
|
---help---
|
|
The network stack has to drop packets when a receive processing CPU's
|
|
backlog reaches netdev_max_backlog. If a few out of many active flows
|
|
generate the vast majority of load, drop their traffic earlier to
|
|
maintain capacity for the other flows. This feature provides servers
|
|
with many clients some protection against DoS by a single (spoofed)
|
|
flow that greatly exceeds average workload.
|
|
|
|
menu "Network testing"
|
|
|
|
config NET_PKTGEN
|
|
tristate "Packet Generator (USE WITH CAUTION)"
|
|
depends on INET && PROC_FS
|
|
---help---
|
|
This module will inject preconfigured packets, at a configurable
|
|
rate, out of a given interface. It is used for network interface
|
|
stress testing and performance analysis. If you don't understand
|
|
what was just said, you don't need it: say N.
|
|
|
|
Documentation on how to use the packet generator can be found
|
|
at <file:Documentation/networking/pktgen.txt>.
|
|
|
|
To compile this code as a module, choose M here: the
|
|
module will be called pktgen.
|
|
|
|
config NET_TCPPROBE
|
|
tristate "TCP connection probing"
|
|
depends on INET && PROC_FS && KPROBES
|
|
---help---
|
|
This module allows for capturing the changes to TCP connection
|
|
state in response to incoming packets. It is used for debugging
|
|
TCP congestion avoidance modules. If you don't understand
|
|
what was just said, you don't need it: say N.
|
|
|
|
Documentation on how to use TCP connection probing can be found
|
|
at:
|
|
|
|
http://www.linuxfoundation.org/collaborate/workgroups/networking/tcpprobe
|
|
|
|
To compile this code as a module, choose M here: the
|
|
module will be called tcp_probe.
|
|
|
|
config NET_DROP_MONITOR
|
|
tristate "Network packet drop alerting service"
|
|
depends on INET && TRACEPOINTS
|
|
---help---
|
|
This feature provides an alerting service to userspace in the
|
|
event that packets are discarded in the network stack. Alerts
|
|
are broadcast via netlink socket to any listening user space
|
|
process. If you don't need network drop alerts, or if you are ok
|
|
just checking the various proc files and other utilities for
|
|
drop statistics, say N here.
|
|
|
|
endmenu
|
|
|
|
endmenu
|
|
|
|
source "net/ax25/Kconfig"
|
|
source "net/can/Kconfig"
|
|
source "net/irda/Kconfig"
|
|
source "net/bluetooth/Kconfig"
|
|
source "net/rxrpc/Kconfig"
|
|
source "net/kcm/Kconfig"
|
|
source "net/strparser/Kconfig"
|
|
|
|
config FIB_RULES
|
|
bool
|
|
|
|
menuconfig WIRELESS
|
|
bool "Wireless"
|
|
depends on !S390
|
|
default y
|
|
|
|
if WIRELESS
|
|
|
|
source "net/wireless/Kconfig"
|
|
source "net/mac80211/Kconfig"
|
|
|
|
endif # WIRELESS
|
|
|
|
source "net/wimax/Kconfig"
|
|
|
|
source "net/rfkill/Kconfig"
|
|
source "net/9p/Kconfig"
|
|
source "net/caif/Kconfig"
|
|
source "net/ceph/Kconfig"
|
|
source "net/nfc/Kconfig"
|
|
source "net/psample/Kconfig"
|
|
source "net/ife/Kconfig"
|
|
|
|
config LWTUNNEL
|
|
bool "Network light weight tunnels"
|
|
---help---
|
|
This feature provides an infrastructure to support light weight
|
|
tunnels like mpls. There is no netdevice associated with a light
|
|
weight tunnel endpoint. Tunnel encapsulation parameters are stored
|
|
with light weight tunnel state associated with fib routes.
|
|
|
|
config LWTUNNEL_BPF
|
|
bool "Execute BPF program as route nexthop action"
|
|
depends on LWTUNNEL
|
|
default y if LWTUNNEL=y
|
|
---help---
|
|
Allows to run BPF programs as a nexthop action following a route
|
|
lookup for incoming and outgoing packets.
|
|
|
|
config DST_CACHE
|
|
bool
|
|
default n
|
|
|
|
config GRO_CELLS
|
|
bool
|
|
default n
|
|
|
|
config NET_DEVLINK
|
|
tristate "Network physical/parent device Netlink interface"
|
|
help
|
|
Network physical/parent device Netlink interface provides
|
|
infrastructure to support access to physical chip-wide config and
|
|
monitoring.
|
|
|
|
config MAY_USE_DEVLINK
|
|
tristate
|
|
default m if NET_DEVLINK=m
|
|
default y if NET_DEVLINK=y || NET_DEVLINK=n
|
|
help
|
|
Drivers using the devlink infrastructure should have a dependency
|
|
on MAY_USE_DEVLINK to ensure they do not cause link errors when
|
|
devlink is a loadable module and the driver using it is built-in.
|
|
|
|
endif # if NET
|
|
|
|
# Used by archs to tell that they support BPF JIT compiler plus which flavour.
|
|
# Only one of the two can be selected for a specific arch since eBPF JIT supersedes
|
|
# the cBPF JIT.
|
|
|
|
# Classic BPF JIT (cBPF)
|
|
config HAVE_CBPF_JIT
|
|
bool
|
|
|
|
# Extended BPF JIT (eBPF)
|
|
config HAVE_EBPF_JIT
|
|
bool
|