diff options
41 files changed, 7534 insertions, 41 deletions
@@ -3,6 +3,7 @@ OP_TMPL_DIR := templates-op BUILD_DIR := build DATA_DIR := data SHIM_DIR := src/shim +XDP_DIR := src/xdp CC := gcc LIBS := -lzmq CFLAGS := @@ -96,8 +97,12 @@ component_versions: $(BUILD_DIR) $(obj) vyshim: $(MAKE) -C $(SHIM_DIR) +.PHONY: vyxdp +vyxdp: + $(MAKE) -C $(XDP_DIR) + .PHONY: all -all: clean interface_definitions op_mode_definitions component_versions vyshim +all: clean interface_definitions op_mode_definitions component_versions vyshim vyxdp .PHONY: clean clean: @@ -105,6 +110,7 @@ clean: rm -rf $(TMPL_DIR) rm -rf $(OP_TMPL_DIR) $(MAKE) -C $(SHIM_DIR) clean + $(MAKE) -C $(XDP_DIR) clean .PHONY: test test: diff --git a/data/templates/frr/bfd.frr.tmpl b/data/templates/frr/bfd.frr.tmpl index 95a29e06a..9e5ad3379 100644 --- a/data/templates/frr/bfd.frr.tmpl +++ b/data/templates/frr/bfd.frr.tmpl @@ -2,15 +2,21 @@ bfd {% for peer in old_peers %} no peer {{ peer.remote }}{% if peer.multihop %} multihop{% endif %}{% if peer.src_addr %} local-address {{ peer.src_addr }}{% endif %}{% if peer.src_if %} interface {{ peer.src_if }}{% endif %} + {% endfor %} ! {% for peer in new_peers %} peer {{ peer.remote }}{% if peer.multihop %} multihop{% endif %}{% if peer.src_addr %} local-address {{ peer.src_addr }}{% endif %}{% if peer.src_if %} interface {{ peer.src_if }}{% endif %} + detect-multiplier {{ peer.multiplier }} receive-interval {{ peer.rx_interval }} transmit-interval {{ peer.tx_interval }} - {% if peer.echo_mode %}echo-mode{% endif %} - {% if peer.echo_interval != '' %}echo-interval {{ peer.echo_interval }}{% endif %} +{% if peer.echo_mode %} + echo-mode +{% endif %} +{% if peer.echo_interval != '' %} + echo-interval {{ peer.echo_interval }} +{% endif %} {% if not peer.shutdown %}no {% endif %}shutdown {% endfor %} ! diff --git a/debian/control b/debian/control index 89c7beb8a..724367952 100644 --- a/debian/control +++ b/debian/control @@ -5,6 +5,12 @@ Maintainer: VyOS Package Maintainers <maintainers@vyos.net> Build-Depends: debhelper (>= 9), fakeroot, + gcc-multilib [amd64], + clang [amd64], + llvm [amd64], + libelf-dev (>= 0.2) [amd64], + libpcap-dev [amd64], + build-essential, libvyosconfig0 (>= 0.0.7), libzmq3-dev, python3, diff --git a/debian/rules b/debian/rules index a0cc7a99b..ab0df7201 100755 --- a/debian/rules +++ b/debian/rules @@ -78,6 +78,11 @@ override_dh_auto_install: mkdir -p $(DIR)/$(VYOS_DATA_DIR) cp -r data/* $(DIR)/$(VYOS_DATA_DIR) + # Install XDP plugins + mkdir -p $(DIR)/$(VYOS_DATA_DIR)/xdp + cp -r src/xdp/xdp_prog_kern.o $(DIR)/$(VYOS_DATA_DIR)/xdp + find src/xdp -perm /a+x -exec cp {} $(DIR)/$(VYOS_SBIN_DIR) \; + # Install etc configuration files mkdir -p $(DIR)/etc cp -r src/etc/* $(DIR)/etc diff --git a/debian/vyos-1x.install b/debian/vyos-1x.install index e69d85b66..bfc30f7e6 100644 --- a/debian/vyos-1x.install +++ b/debian/vyos-1x.install @@ -8,7 +8,7 @@ etc/udev etc/vyos lib/ opt/ -usr/sbin/vyshim +usr/sbin usr/bin/initial-setup usr/bin/vyos-config-file-query usr/bin/vyos-config-to-commands diff --git a/interface-definitions/interfaces-ethernet.xml.in b/interface-definitions/interfaces-ethernet.xml.in index 0337c629b..8bd9b7010 100644 --- a/interface-definitions/interfaces-ethernet.xml.in +++ b/interface-definitions/interfaces-ethernet.xml.in @@ -165,6 +165,12 @@ <constraintErrorMessage>Must be either 'on' or 'off'</constraintErrorMessage> </properties> </leafNode> + <leafNode name="xdp"> + <properties> + <help>Enable eXpress Data Path</help> + <valueless/> + </properties> + </leafNode> </children> </node> <leafNode name="speed"> diff --git a/interface-definitions/protocols-mpls.xml.in b/interface-definitions/protocols-mpls.xml.in index 3ac248e79..645b264bb 100644 --- a/interface-definitions/protocols-mpls.xml.in +++ b/interface-definitions/protocols-mpls.xml.in @@ -16,7 +16,7 @@ <children> <leafNode name="router-id"> <properties> - <help>Label Distribution Protocol (LDP) router ID</help> + <help>Label Distribution Protocol router ID</help> <valueHelp> <format>ipv4</format> <description>LDP IPv4 ID</description> @@ -28,7 +28,7 @@ </leafNode> <node name="allocation"> <properties> - <help>Forwarding equivalence class (FEC) allocation from local routes</help> + <help>Forwarding equivalence class allocation from local routes</help> </properties> <children> <node name="ipv4"> @@ -334,7 +334,7 @@ </node> <node name="parameters"> <properties> - <help>Label Distribution Protocol (LDP) miscellaneous parameters</help> + <help>Label Distribution Protocol miscellaneous parameters</help> </properties> <children> <leafNode name="cisco-interop-tlv"> @@ -369,7 +369,7 @@ </leafNode> <node name="export-filter"> <properties> - <help>Forwarding equivalence class (FEC) export filter</help> + <help>Forwarding equivalence class export filter</help> </properties> <children> <leafNode name="filter-access-list"> @@ -413,7 +413,7 @@ </leafNode> <node name="export-filter"> <properties> - <help>Forwarding equivalence class (FEC) export filter</help> + <help>Forwarding equivalence class export filter</help> </properties> <children> <leafNode name="filter-access-list6"> @@ -458,7 +458,7 @@ <children> <node name="import-filter"> <properties> - <help>Forwarding equivalence class (FEC) import filter</help> + <help>Forwarding equivalence class import filter</help> </properties> <children> <leafNode name="filter-access-list"> @@ -496,7 +496,7 @@ <children> <node name="import-filter"> <properties> - <help>Forwarding equivalence class (FEC) import filter</help> + <help>Forwarding equivalence class import filter</help> </properties> <children> <leafNode name="filter-access-list6"> @@ -542,7 +542,7 @@ </node> <node name="parameters"> <properties> - <help>Multiprotocol Label Switching (MPLS) miscellaneous parameters</help> + <help>Multiprotocol Label Switching miscellaneous parameters</help> </properties> <children> <leafNode name="no-propagate-ttl"> diff --git a/op-mode-definitions/show-mpls.xml b/op-mode-definitions/show-mpls.xml index 3f160b6dc..833ac98eb 100644 --- a/op-mode-definitions/show-mpls.xml +++ b/op-mode-definitions/show-mpls.xml @@ -1,4 +1,4 @@ -<?xml version="1.0"?> +<?xml version="1.0" encoding="UTF-8"?> <interfaceDefinition> <node name="show"> <children> @@ -17,33 +17,186 @@ <help>Label Information Base</help> </properties> <command>/usr/bin/vtysh -c "show mpls ldp binding"</command> + <children> + <node name="detail"> + <properties> + <help>Show detailed information</help> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp binding detail"</command> + </node> + <tagNode name="neighbor"> + <properties> + <help>Display labels from LDP neighbor</help> + <completionHelp> + <list><x.x.x.x> <h:h:h:h:h:h:h:h></list> + <script>/usr/bin/vtysh -c "show mpls ldp neighbor" | awk '{print $2}' | egrep -v "ID"</script> + </completionHelp> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp binding neighbor $6"</command> + <children> + <leafNode name="detail"> + <properties> + <help>Show detailed information</help> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp binding neighbor $6 detail"</command> + </leafNode> + <tagNode name="local-label"> + <properties> + <help>Match locally assigned label value</help> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp binding neighbor $6 local-label $8"</command> + </tagNode> + <tagNode name="remote-label"> + <properties> + <help>Match remotely assigned label value</help> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp binding neighbor $6 remote-label $8"</command> + </tagNode> + </children> + </tagNode> + <tagNode name="local-label"> + <properties> + <help>Match locally assigned label value</help> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp binding local-label $6"</command> + <children> + <leafNode name="detail"> + <properties> + <help>Show detailed information</help> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp binding local-label $6 detail"</command> + </leafNode> + <tagNode name="neighbor"> + <properties> + <help>Match LDP neighbor</help> + <completionHelp> + <list><x.x.x.x> <h:h:h:h:h:h:h:h></list> + <script>/usr/bin/vtysh -c "show mpls ldp neighbor" | awk '{print $2}' | egrep -v "ID"</script> + </completionHelp> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp binding local-label $6 neighbor $8"</command> + </tagNode> + <tagNode name="remote-label"> + <properties> + <help>Match remotely assigned label value</help> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp binding local-label $6 remote-label $8"</command> + </tagNode> + </children> + </tagNode> + <tagNode name="remote-label"> + <properties> + <help>Match remotely assigned label value</help> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp binding remote-label $6"</command> + <children> + <leafNode name="detail"> + <properties> + <help>Show detailed information</help> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp binding remote-label $6 detail"</command> + </leafNode> + <tagNode name="neighbor"> + <properties> + <help>Match LDP neighbor</help> + <completionHelp> + <list><x.x.x.x> <h:h:h:h:h:h:h:h></list> + <script>/usr/bin/vtysh -c "show mpls ldp neighbor" | awk '{print $2}' | egrep -v "ID"</script> + </completionHelp> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp binding remote-label $6 neighbor $8"</command> + </tagNode> + <tagNode name="local-label"> + <properties> + <help>Match locally assigned label value</help> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp binding remote-label $6 local-label $8"</command> + </tagNode> + </children> + </tagNode> + </children> </node> + <tagNode name="binding"> + <properties> + <help>LDP forwarding equivalence class</help> + <completionHelp> + <list><x.x.x.x/x> <h:h:h:h:h:h:h:h/h></list> + </completionHelp> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp binding $5"</command> + <children> + <leafNode name="detail"> + <properties> + <help>Show detailed information</help> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp binding $5 detail"</command> + </leafNode> + </children> + </tagNode> <node name="discovery"> <properties> <help>Discovery hello information</help> </properties> <command>/usr/bin/vtysh -c "show mpls ldp discovery"</command> + <children> + <leafNode name="detail"> + <properties> + <help>Show detailed information</help> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp discovery detail"</command> + </leafNode> + </children> </node> - <node name="interface"> + <node name="interface"> <properties> <help>LDP interface information</help> </properties> <command>/usr/bin/vtysh -c "show mpls ldp interface"</command> </node> <node name="neighbor"> - <properties> - <help>LDP neighbor information</help> - </properties> - <command>/usr/bin/vtysh -c "show mpls ldp neighbor"</command> + <properties> + <help>LDP neighbor information</help> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp neighbor"</command> <children> - <node name="detail"> - <properties> - <help>Show neighbor detail</help> - </properties> - <command>/usr/bin/vtysh -c "show mpls ldp neighbor detail"</command> - </node> - </children> + <leafNode name="detail"> + <properties> + <help>Show detailed information</help> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp neighbor detail"</command> + </leafNode> + <leafNode name="capabilities"> + <properties> + <help>Show neighbor capability information</help> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp neighbor capabilities"</command> + </leafNode> + </children> </node> + <tagNode name="neighbor"> + <properties> + <help>LDP neighbor</help> + <completionHelp> + <list><x.x.x.x> <h:h:h:h:h:h:h:h></list> + <script>/usr/bin/vtysh -c "show mpls ldp neighbor" | awk '{print $2}' | egrep -v "ID"</script> + </completionHelp> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp neighbor $5"</command> + <children> + <leafNode name="detail"> + <properties> + <help>Show detailed information</help> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp neighbor $5 detail"</command> + </leafNode> + <leafNode name="capabilities"> + <properties> + <help>Show neighbor capability information</help> + </properties> + <command>/usr/bin/vtysh -c "show mpls ldp neighbor $5 capabilities"</command> + </leafNode> + </children> + </tagNode> </children> </node> <node name="pseudowire"> diff --git a/python/vyos/ifconfig/ethernet.py b/python/vyos/ifconfig/ethernet.py index 12d1ec265..b2dd54587 100644 --- a/python/vyos/ifconfig/ethernet.py +++ b/python/vyos/ifconfig/ethernet.py @@ -44,34 +44,34 @@ class EthernetIf(Interface): @staticmethod def feature(ifname, option, value): - run(f'/sbin/ethtool -K {ifname} {option} {value}','ifconfig') + run(f'ethtool -K {ifname} {option} {value}','ifconfig') return False _command_set = {**Interface._command_set, **{ 'gro': { 'validate': lambda v: assert_list(v, ['on', 'off']), 'possible': lambda i, v: EthernetIf.feature(i, 'gro', v), - # 'shellcmd': '/sbin/ethtool -K {ifname} gro {value}', + # 'shellcmd': 'ethtool -K {ifname} gro {value}', }, 'gso': { 'validate': lambda v: assert_list(v, ['on', 'off']), 'possible': lambda i, v: EthernetIf.feature(i, 'gso', v), - # 'shellcmd': '/sbin/ethtool -K {ifname} gso {value}', + # 'shellcmd': 'ethtool -K {ifname} gso {value}', }, 'sg': { 'validate': lambda v: assert_list(v, ['on', 'off']), 'possible': lambda i, v: EthernetIf.feature(i, 'sg', v), - # 'shellcmd': '/sbin/ethtool -K {ifname} sg {value}', + # 'shellcmd': 'ethtool -K {ifname} sg {value}', }, 'tso': { 'validate': lambda v: assert_list(v, ['on', 'off']), 'possible': lambda i, v: EthernetIf.feature(i, 'tso', v), - # 'shellcmd': '/sbin/ethtool -K {ifname} tso {value}', + # 'shellcmd': 'ethtool -K {ifname} tso {value}', }, 'ufo': { 'validate': lambda v: assert_list(v, ['on', 'off']), 'possible': lambda i, v: EthernetIf.feature(i, 'ufo', v), - # 'shellcmd': '/sbin/ethtool -K {ifname} ufo {value}', + # 'shellcmd': 'ethtool -K {ifname} ufo {value}', }, }} @@ -86,8 +86,8 @@ class EthernetIf(Interface): >>> i.get_driver_name() 'vmxnet3' """ - sysfs_file = '/sys/class/net/{}/device/driver/module'.format( - self.config['ifname']) + ifname = self.config['ifname'] + sysfs_file = f'/sys/class/net/{ifname}/device/driver/module' if os.path.exists(sysfs_file): link = os.readlink(sysfs_file) return os.path.basename(link) @@ -116,7 +116,7 @@ class EthernetIf(Interface): return # Get current flow control settings: - cmd = f'/sbin/ethtool --show-pause {ifname}' + cmd = f'ethtool --show-pause {ifname}' output, code = self._popen(cmd) if code == 76: # the interface does not support it @@ -142,7 +142,7 @@ class EthernetIf(Interface): # Assemble command executed on system. Unfortunately there is no way # to change this setting via sysfs - cmd = f'/sbin/ethtool --pause {ifname} autoneg {enable} tx {enable} rx {enable}' + cmd = f'ethtool --pause {ifname} autoneg {enable} tx {enable} rx {enable}' output, code = self._popen(cmd) if code: print(f'could not set flowcontrol for {ifname}') @@ -173,7 +173,8 @@ class EthernetIf(Interface): return # Get current speed and duplex settings: - cmd = '/sbin/ethtool {0}'.format(self.config['ifname']) + ifname = self.config['ifname'] + cmd = f'ethtool {ifname}' tmp = self._cmd(cmd) if re.search("\tAuto-negotiation: on", tmp): @@ -198,12 +199,11 @@ class EthernetIf(Interface): # bail out early as nothing is to change return - cmd = '/sbin/ethtool -s {}'.format(self.config['ifname']) + cmd = f'ethtool -s {ifname}' if speed == 'auto' or duplex == 'auto': cmd += ' autoneg on' else: - cmd += ' speed {} duplex {} autoneg off'.format(speed, duplex) - + cmd += f' speed {speed} duplex {duplex} autoneg off' return self._cmd(cmd) def set_gro(self, state): @@ -251,6 +251,21 @@ class EthernetIf(Interface): """ return self.set_interface('ufo', state) + def set_xdp(self, enabled): + """ + """ + ifname = self.config['ifname'] + cmd = f'xdp_loader -d {ifname} -U --auto-mode' + if enabled: + # Using 'xdp' will automatically decide if the driver supports + # 'xdpdrv' or only 'xdpgeneric'. A user later sees which driver is + # actually in use by calling 'ip a' or 'show interfaces ethernet' + cmd = f'xdp_loader -d {ifname} --auto-mode -F --progsec xdp_router ' \ + f'--filename /usr/share/vyos/xdp/xdp_prog_kern.o && ' \ + f'xdp_prog_user -d {ifname}' + + return self._cmd(cmd) + def set_ring_buffer(self, b_type, b_size): """ Example: @@ -258,13 +273,14 @@ class EthernetIf(Interface): >>> i = EthernetIf('eth0') >>> i.set_ring_buffer('rx', '4096') """ - cmd = '/sbin/ethtool -G {0} {1} {2}'.format(self.config['ifname'], b_type, b_size) + ifname = self.config['ifname'] + cmd = f'ethtool -G {ifname} {b_type} {b_size}' output, code = self._popen(cmd) # ethtool error codes: # 80 - value already setted # 81 - does not possible to set value if code and code != 80: - print('could not set {0} ring-buffer for {1}'.format(b_type, self.config['ifname'])) + print(f'could not set "{b_type}" ring-buffer for {ifname}') return output @@ -306,6 +322,10 @@ class EthernetIf(Interface): value = tmp if (tmp != None) else 'off' self.set_ufo(value) + # UDP fragmentation offloading + tmp = dict_search('offload_options.xdp', config) + self.set_xdp(tmp != None) # enable or disable + # Set physical interface speed and duplex if {'speed', 'duplex'} <= set(config): speed = config.get('speed') diff --git a/src/xdp/.gitignore b/src/xdp/.gitignore new file mode 100644 index 000000000..2c931cf47 --- /dev/null +++ b/src/xdp/.gitignore @@ -0,0 +1,5 @@ +*.o +*.ll +xdp_loader +xdp_prog_user +xdp_stats diff --git a/src/xdp/Makefile b/src/xdp/Makefile new file mode 100644 index 000000000..0b5a6eaa0 --- /dev/null +++ b/src/xdp/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) + +XDP_TARGETS := xdp_prog_kern +USER_TARGETS := xdp_prog_user + +COMMON_DIR = common + +COPY_LOADER := xdp_loader +COPY_STATS := xdp_stats +EXTRA_DEPS := $(COMMON_DIR)/parsing_helpers.h + +include $(COMMON_DIR)/common.mk diff --git a/src/xdp/common/Makefile b/src/xdp/common/Makefile new file mode 100644 index 000000000..2502027e9 --- /dev/null +++ b/src/xdp/common/Makefile @@ -0,0 +1,23 @@ +# SPDX-License-Identifier: (GPL-2.0) +CC := gcc + +all: common_params.o common_user_bpf_xdp.o common_libbpf.o + +CFLAGS := -g -Wall + +CFLAGS += -I../include/ +# TODO: Do we need to make libbpf from this make file too? + +common_params.o: common_params.c common_params.h + $(CC) $(CFLAGS) -c -o $@ $< + +common_user_bpf_xdp.o: common_user_bpf_xdp.c common_user_bpf_xdp.h + $(CC) $(CFLAGS) -c -o $@ $< + +common_libbpf.o: common_libbpf.c common_libbpf.h + $(CC) $(CFLAGS) -c -o $@ $< + +.PHONY: clean + +clean: + rm -f *.o diff --git a/src/xdp/common/README.org b/src/xdp/common/README.org new file mode 100644 index 000000000..561fdbced --- /dev/null +++ b/src/xdp/common/README.org @@ -0,0 +1,8 @@ +# -*- fill-column: 76; -*- +#+TITLE: Common files +#+OPTIONS: ^:nil + +This directory contains code that is common between the different +assignments. This reduce code duplication in each tutorial assignment, and +allow us to hideaway code that is irrelevant or have been seen/introduced in +earlier assignments. diff --git a/src/xdp/common/common.mk b/src/xdp/common/common.mk new file mode 100644 index 000000000..89aac68ef --- /dev/null +++ b/src/xdp/common/common.mk @@ -0,0 +1,103 @@ +# Common Makefile parts for BPF-building with libbpf +# -------------------------------------------------- +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +# +# This file should be included from your Makefile like: +# COMMON_DIR = ../common/ +# include $(COMMON_DIR)/common.mk +# +# It is expected that you define the variables: +# XDP_TARGETS and USER_TARGETS +# as a space-separated list +# +LLC ?= llc +CLANG ?= clang +CC ?= gcc + +XDP_C = ${XDP_TARGETS:=.c} +XDP_OBJ = ${XDP_C:.c=.o} +USER_C := ${USER_TARGETS:=.c} +USER_OBJ := ${USER_C:.c=.o} + +# Expect this is defined by including Makefile, but define if not +COMMON_DIR ?= ../common/ + +COPY_LOADER ?= +LOADER_DIR ?= $(COMMON_DIR)/../utils + +# Extend if including Makefile already added some +COMMON_OBJS += $(COMMON_DIR)/common_params.o $(COMMON_DIR)/common_user_bpf_xdp.o + +# Create expansions for dependencies +COMMON_H := ${COMMON_OBJS:.o=.h} + +EXTRA_DEPS += + +# BPF-prog kern and userspace shares struct via header file: +KERN_USER_H ?= $(wildcard common_kern_user.h) + +CFLAGS ?= -g -I../include/ +BPF_CFLAGS ?= -I../include/ + +LIBS = -l:libbpf.a -lelf -lz $(USER_LIBS) + +all: llvm-check $(USER_TARGETS) $(XDP_OBJ) $(COPY_LOADER) $(COPY_STATS) + +.PHONY: clean $(CLANG) $(LLC) + +clean: + $(MAKE) -C $(COMMON_DIR) clean + rm -f $(USER_TARGETS) $(XDP_OBJ) $(USER_OBJ) $(COPY_LOADER) $(COPY_STATS) + rm -f *.ll + rm -f *~ + +ifdef COPY_LOADER +$(COPY_LOADER): $(LOADER_DIR)/${COPY_LOADER:=.c} $(COMMON_H) + make -C $(LOADER_DIR) $(COPY_LOADER) + cp $(LOADER_DIR)/$(COPY_LOADER) $(COPY_LOADER) +endif + +ifdef COPY_STATS +$(COPY_STATS): $(LOADER_DIR)/${COPY_STATS:=.c} $(COMMON_H) + make -C $(LOADER_DIR) $(COPY_STATS) + cp $(LOADER_DIR)/$(COPY_STATS) $(COPY_STATS) +# Needing xdp_stats imply depending on header files: +EXTRA_DEPS += $(COMMON_DIR)/xdp_stats_kern.h $(COMMON_DIR)/xdp_stats_kern_user.h +endif + +# For build dependency on this file, if it gets updated +COMMON_MK = $(COMMON_DIR)/common.mk + +llvm-check: $(CLANG) $(LLC) + @for TOOL in $^ ; do \ + if [ ! $$(command -v $${TOOL} 2>/dev/null) ]; then \ + echo "*** ERROR: Cannot find tool $${TOOL}" ;\ + exit 1; \ + else true; fi; \ + done + +# Create dependency: detect if C-file change and touch H-file, to trigger +# target $(COMMON_OBJS) +$(COMMON_H): %.h: %.c + touch $@ + +# Detect if any of common obj changed and create dependency on .h-files +$(COMMON_OBJS): %.o: %.h + make -C $(COMMON_DIR) + +$(USER_TARGETS): %: %.c Makefile $(COMMON_MK) $(COMMON_OBJS) $(KERN_USER_H) $(EXTRA_DEPS) + $(CC) -Wall $(CFLAGS) $(LDFLAGS) -o $@ $(COMMON_OBJS) \ + $< $(LIBS) + +$(XDP_OBJ): %.o: %.c Makefile $(COMMON_MK) $(KERN_USER_H) $(EXTRA_DEPS) + $(CLANG) -S \ + -target bpf \ + -D __BPF_TRACING__ \ + $(BPF_CFLAGS) \ + -Wall \ + -Wno-unused-value \ + -Wno-pointer-sign \ + -Wno-compare-distinct-pointer-types \ + -Werror \ + -O2 -emit-llvm -c -g -o ${@:.o=.ll} $< + $(LLC) -march=bpf -filetype=obj -o $@ ${@:.o=.ll} diff --git a/src/xdp/common/common_defines.h b/src/xdp/common/common_defines.h new file mode 100644 index 000000000..2986d2d67 --- /dev/null +++ b/src/xdp/common/common_defines.h @@ -0,0 +1,38 @@ +#ifndef __COMMON_DEFINES_H +#define __COMMON_DEFINES_H + +#include <net/if.h> +#include <linux/types.h> +#include <stdbool.h> + +struct config { + __u32 xdp_flags; + int ifindex; + char *ifname; + char ifname_buf[IF_NAMESIZE]; + int redirect_ifindex; + char *redirect_ifname; + char redirect_ifname_buf[IF_NAMESIZE]; + bool do_unload; + bool reuse_maps; + char pin_dir[512]; + char filename[512]; + char progsec[32]; + char src_mac[18]; + char dest_mac[18]; + __u16 xsk_bind_flags; + int xsk_if_queue; + bool xsk_poll_mode; +}; + +/* Defined in common_params.o */ +extern int verbose; + +/* Exit return codes */ +#define EXIT_OK 0 /* == EXIT_SUCCESS (stdlib.h) man exit(3) */ +#define EXIT_FAIL 1 /* == EXIT_FAILURE (stdlib.h) man exit(3) */ +#define EXIT_FAIL_OPTION 2 +#define EXIT_FAIL_XDP 30 +#define EXIT_FAIL_BPF 40 + +#endif /* __COMMON_DEFINES_H */ diff --git a/src/xdp/common/common_libbpf.c b/src/xdp/common/common_libbpf.c new file mode 100644 index 000000000..5788ecd9e --- /dev/null +++ b/src/xdp/common/common_libbpf.c @@ -0,0 +1,162 @@ +/* Common function that with time should be moved to libbpf */ + +#include <errno.h> +#include <string.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include "common_libbpf.h" + +/* From: include/linux/err.h */ +#define MAX_ERRNO 4095 +#define IS_ERR_VALUE(x) ((x) >= (unsigned long)-MAX_ERRNO) +static inline bool IS_ERR_OR_NULL(const void *ptr) +{ + return (!ptr) || IS_ERR_VALUE((unsigned long)ptr); +} + +#define pr_warning printf + +/* As close as possible to libbpf bpf_prog_load_xattr(), with the + * difference of handling pinned maps. + */ +int bpf_prog_load_xattr_maps(const struct bpf_prog_load_attr_maps *attr, + struct bpf_object **pobj, int *prog_fd) +{ + struct bpf_object_open_attr open_attr = { + .file = attr->file, + .prog_type = attr->prog_type, + }; + struct bpf_program *prog, *first_prog = NULL; + enum bpf_attach_type expected_attach_type; + enum bpf_prog_type prog_type; + struct bpf_object *obj; + struct bpf_map *map; + int err; + int i; + + if (!attr) + return -EINVAL; + if (!attr->file) + return -EINVAL; + + + obj = bpf_object__open_xattr(&open_attr); + if (IS_ERR_OR_NULL(obj)) + return -ENOENT; + + bpf_object__for_each_program(prog, obj) { + /* + * If type is not specified, try to guess it based on + * section name. + */ + prog_type = attr->prog_type; + // Was: prog->prog_ifindex = attr->ifindex; + bpf_program__set_ifindex(prog, attr->ifindex); + + expected_attach_type = attr->expected_attach_type; +#if 0 /* Use internal libbpf variables */ + if (prog_type == BPF_PROG_TYPE_UNSPEC) { + err = bpf_program__identify_section(prog, &prog_type, + &expected_attach_type); + if (err < 0) { + bpf_object__close(obj); + return -EINVAL; + } + } +#endif + + bpf_program__set_type(prog, prog_type); + bpf_program__set_expected_attach_type(prog, + expected_attach_type); + + if (!first_prog) + first_prog = prog; + } + + /* Reset attr->pinned_maps.map_fd to identify successful file load */ + for (i = 0; i < attr->nr_pinned_maps; i++) + attr->pinned_maps[i].map_fd = -1; + + bpf_map__for_each(map, obj) { + const char* mapname = bpf_map__name(map); + + if (!bpf_map__is_offload_neutral(map)) + bpf_map__set_ifindex(map, attr->ifindex); + /* Was: map->map_ifindex = attr->ifindex; */ + + for (i = 0; i < attr->nr_pinned_maps; i++) { + struct bpf_pinned_map *pin_map = &attr->pinned_maps[i]; + int fd; + + if (strcmp(mapname, pin_map->name) != 0) + continue; + + /* Matched, try opening pinned file */ + fd = bpf_obj_get(pin_map->filename); + if (fd > 0) { + /* Use FD from pinned map as replacement */ + bpf_map__reuse_fd(map, fd); + /* TODO: Might want to set internal map "name" + * if opened pinned map didn't, to allow + * bpf_object__find_map_fd_by_name() to work. + */ + pin_map->map_fd = fd; + continue; + } + /* Could not open pinned filename map, then this prog + * should then pin the map, BUT this can only happen + * after bpf_object__load(). + */ + } + } + + if (!first_prog) { + pr_warning("object file doesn't contain bpf program\n"); + bpf_object__close(obj); + return -ENOENT; + } + + err = bpf_object__load(obj); + if (err) { + bpf_object__close(obj); + return -EINVAL; + } + + /* Pin the maps that were not loaded via pinned filename */ + bpf_map__for_each(map, obj) { + const char* mapname = bpf_map__name(map); + + for (i = 0; i < attr->nr_pinned_maps; i++) { + struct bpf_pinned_map *pin_map = &attr->pinned_maps[i]; + int err; + + if (strcmp(mapname, pin_map->name) != 0) + continue; + + /* Matched, check if map is already loaded */ + if (pin_map->map_fd != -1) + continue; + + /* Needs to be pinned */ + err = bpf_map__pin(map, pin_map->filename); + if (err) + continue; + pin_map->map_fd = bpf_map__fd(map); + } + } + + /* Help user if requested map name that doesn't exist */ + for (i = 0; i < attr->nr_pinned_maps; i++) { + struct bpf_pinned_map *pin_map = &attr->pinned_maps[i]; + + if (pin_map->map_fd < 0) + pr_warning("%s() requested mapname:%s not seen\n", + __func__, pin_map->name); + } + + *pobj = obj; + *prog_fd = bpf_program__fd(first_prog); + return 0; +} diff --git a/src/xdp/common/common_libbpf.h b/src/xdp/common/common_libbpf.h new file mode 100644 index 000000000..4754bd8ca --- /dev/null +++ b/src/xdp/common/common_libbpf.h @@ -0,0 +1,24 @@ +/* Common function that with time should be moved to libbpf */ +#ifndef __COMMON_LIBBPF_H +#define __COMMON_LIBBPF_H + +struct bpf_pinned_map { + const char *name; + const char *filename; + int map_fd; +}; + +/* bpf_prog_load_attr extended */ +struct bpf_prog_load_attr_maps { + const char *file; + enum bpf_prog_type prog_type; + enum bpf_attach_type expected_attach_type; + int ifindex; + int nr_pinned_maps; + struct bpf_pinned_map *pinned_maps; +}; + +int bpf_prog_load_xattr_maps(const struct bpf_prog_load_attr_maps *attr, + struct bpf_object **pobj, int *prog_fd); + +#endif /* __COMMON_LIBBPF_H */ diff --git a/src/xdp/common/common_params.c b/src/xdp/common/common_params.c new file mode 100644 index 000000000..642d56d92 --- /dev/null +++ b/src/xdp/common/common_params.c @@ -0,0 +1,197 @@ +#include <stddef.h> +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <stdbool.h> +#include <getopt.h> +#include <errno.h> + +#include <net/if.h> +#include <linux/if_link.h> /* XDP_FLAGS_* depend on kernel-headers installed */ +#include <linux/if_xdp.h> + +#include "common_params.h" + +int verbose = 1; + +#define BUFSIZE 30 + +void _print_options(const struct option_wrapper *long_options, bool required) +{ + int i, pos; + char buf[BUFSIZE]; + + for (i = 0; long_options[i].option.name != 0; i++) { + if (long_options[i].required != required) + continue; + + if (long_options[i].option.val > 64) /* ord('A') = 65 */ + printf(" -%c,", long_options[i].option.val); + else + printf(" "); + pos = snprintf(buf, BUFSIZE, " --%s", long_options[i].option.name); + if (long_options[i].metavar) + snprintf(&buf[pos], BUFSIZE-pos, " %s", long_options[i].metavar); + printf("%-22s", buf); + printf(" %s", long_options[i].help); + printf("\n"); + } +} + +void usage(const char *prog_name, const char *doc, + const struct option_wrapper *long_options, bool full) +{ + printf("Usage: %s [options]\n", prog_name); + + if (!full) { + printf("Use --help (or -h) to see full option list.\n"); + return; + } + + printf("\nDOCUMENTATION:\n %s\n", doc); + printf("Required options:\n"); + _print_options(long_options, true); + printf("\n"); + printf("Other options:\n"); + _print_options(long_options, false); + printf("\n"); +} + +int option_wrappers_to_options(const struct option_wrapper *wrapper, + struct option **options) +{ + int i, num; + struct option *new_options; + for (i = 0; wrapper[i].option.name != 0; i++) {} + num = i; + + new_options = malloc(sizeof(struct option) * num); + if (!new_options) + return -1; + for (i = 0; i < num; i++) { + memcpy(&new_options[i], &wrapper[i], sizeof(struct option)); + } + + *options = new_options; + return 0; +} + +void parse_cmdline_args(int argc, char **argv, + const struct option_wrapper *options_wrapper, + struct config *cfg, const char *doc) +{ + struct option *long_options; + bool full_help = false; + int longindex = 0; + char *dest; + int opt; + + if (option_wrappers_to_options(options_wrapper, &long_options)) { + fprintf(stderr, "Unable to malloc()\n"); + exit(EXIT_FAIL_OPTION); + } + + /* Parse commands line args */ + while ((opt = getopt_long(argc, argv, "hd:r:L:R:ASNFUMQ:czpq", + long_options, &longindex)) != -1) { + switch (opt) { + case 'd': + if (strlen(optarg) >= IF_NAMESIZE) { + fprintf(stderr, "ERR: --dev name too long\n"); + goto error; + } + cfg->ifname = (char *)&cfg->ifname_buf; + strncpy(cfg->ifname, optarg, IF_NAMESIZE); + cfg->ifindex = if_nametoindex(cfg->ifname); + if (cfg->ifindex == 0) { + fprintf(stderr, + "ERR: --dev name unknown err(%d):%s\n", + errno, strerror(errno)); + goto error; + } + break; + case 'r': + if (strlen(optarg) >= IF_NAMESIZE) { + fprintf(stderr, "ERR: --redirect-dev name too long\n"); + goto error; + } + cfg->redirect_ifname = (char *)&cfg->redirect_ifname_buf; + strncpy(cfg->redirect_ifname, optarg, IF_NAMESIZE); + cfg->redirect_ifindex = if_nametoindex(cfg->redirect_ifname); + if (cfg->redirect_ifindex == 0) { + fprintf(stderr, + "ERR: --redirect-dev name unknown err(%d):%s\n", + errno, strerror(errno)); + goto error; + } + break; + case 'A': + cfg->xdp_flags &= ~XDP_FLAGS_MODES; /* Clear flags */ + break; + case 'S': + cfg->xdp_flags &= ~XDP_FLAGS_MODES; /* Clear flags */ + cfg->xdp_flags |= XDP_FLAGS_SKB_MODE; /* Set flag */ + cfg->xsk_bind_flags &= XDP_ZEROCOPY; + cfg->xsk_bind_flags |= XDP_COPY; + break; + case 'N': + cfg->xdp_flags &= ~XDP_FLAGS_MODES; /* Clear flags */ + cfg->xdp_flags |= XDP_FLAGS_DRV_MODE; /* Set flag */ + break; + case 3: /* --offload-mode */ + cfg->xdp_flags &= ~XDP_FLAGS_MODES; /* Clear flags */ + cfg->xdp_flags |= XDP_FLAGS_HW_MODE; /* Set flag */ + break; + case 'F': + cfg->xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; + case 'M': + cfg->reuse_maps = true; + break; + case 'U': + cfg->do_unload = true; + break; + case 'p': + cfg->xsk_poll_mode = true; + break; + case 'q': + verbose = false; + break; + case 'Q': + cfg->xsk_if_queue = atoi(optarg); + break; + case 1: /* --filename */ + dest = (char *)&cfg->filename; + strncpy(dest, optarg, sizeof(cfg->filename)); + break; + case 2: /* --progsec */ + dest = (char *)&cfg->progsec; + strncpy(dest, optarg, sizeof(cfg->progsec)); + break; + case 'L': /* --src-mac */ + dest = (char *)&cfg->src_mac; + strncpy(dest, optarg, sizeof(cfg->src_mac)); + break; + case 'R': /* --dest-mac */ + dest = (char *)&cfg->dest_mac; + strncpy(dest, optarg, sizeof(cfg->dest_mac)); + case 'c': + cfg->xsk_bind_flags &= XDP_ZEROCOPY; + cfg->xsk_bind_flags |= XDP_COPY; + break; + case 'z': + cfg->xsk_bind_flags &= XDP_COPY; + cfg->xsk_bind_flags |= XDP_ZEROCOPY; + break; + case 'h': + full_help = true; + /* fall-through */ + error: + default: + usage(argv[0], doc, options_wrapper, full_help); + free(long_options); + exit(EXIT_FAIL_OPTION); + } + } + free(long_options); +} diff --git a/src/xdp/common/common_params.h b/src/xdp/common/common_params.h new file mode 100644 index 000000000..6f64c82e3 --- /dev/null +++ b/src/xdp/common/common_params.h @@ -0,0 +1,22 @@ +/* This common_user.h is used by userspace programs */ +#ifndef __COMMON_PARAMS_H +#define __COMMON_PARAMS_H + +#include <getopt.h> +#include "common_defines.h" + +struct option_wrapper { + struct option option; + char *help; + char *metavar; + bool required; +}; + +void usage(const char *prog_name, const char *doc, + const struct option_wrapper *long_options, bool full); + +void parse_cmdline_args(int argc, char **argv, + const struct option_wrapper *long_options, + struct config *cfg, const char *doc); + +#endif /* __COMMON_PARAMS_H */ diff --git a/src/xdp/common/common_user_bpf_xdp.c b/src/xdp/common/common_user_bpf_xdp.c new file mode 100644 index 000000000..e7ef77174 --- /dev/null +++ b/src/xdp/common/common_user_bpf_xdp.c @@ -0,0 +1,380 @@ +#include <bpf/libbpf.h> /* bpf_get_link_xdp_id + bpf_set_link_xdp_id */ +#include <string.h> /* strerror */ +#include <net/if.h> /* IF_NAMESIZE */ +#include <stdlib.h> /* exit(3) */ +#include <errno.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include <linux/if_link.h> /* Need XDP flags */ +#include <linux/err.h> + +#include "common_defines.h" + +#ifndef PATH_MAX +#define PATH_MAX 4096 +#endif + +int xdp_link_attach(int ifindex, __u32 xdp_flags, int prog_fd) +{ + int err; + + /* libbpf provide the XDP net_device link-level hook attach helper */ + err = bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags); + if (err == -EEXIST && !(xdp_flags & XDP_FLAGS_UPDATE_IF_NOEXIST)) { + /* Force mode didn't work, probably because a program of the + * opposite type is loaded. Let's unload that and try loading + * again. + */ + + __u32 old_flags = xdp_flags; + + xdp_flags &= ~XDP_FLAGS_MODES; + xdp_flags |= (old_flags & XDP_FLAGS_SKB_MODE) ? XDP_FLAGS_DRV_MODE : XDP_FLAGS_SKB_MODE; + err = bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + if (!err) + err = bpf_set_link_xdp_fd(ifindex, prog_fd, old_flags); + } + if (err < 0) { + fprintf(stderr, "ERR: " + "ifindex(%d) link set xdp fd failed (%d): %s\n", + ifindex, -err, strerror(-err)); + + switch (-err) { + case EBUSY: + case EEXIST: + fprintf(stderr, "Hint: XDP already loaded on device" + " use --force to swap/replace\n"); + break; + case EOPNOTSUPP: + fprintf(stderr, "Hint: Native-XDP not supported" + " use --skb-mode or --auto-mode\n"); + break; + default: + break; + } + return EXIT_FAIL_XDP; + } + + return EXIT_OK; +} + +int xdp_link_detach(int ifindex, __u32 xdp_flags, __u32 expected_prog_id) +{ + __u32 curr_prog_id; + int err; + + err = bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags); + if (err) { + fprintf(stderr, "ERR: get link xdp id failed (err=%d): %s\n", + -err, strerror(-err)); + return EXIT_FAIL_XDP; + } + + if (!curr_prog_id) { + if (verbose) + printf("INFO: %s() no curr XDP prog on ifindex:%d\n", + __func__, ifindex); + return EXIT_OK; + } + + if (expected_prog_id && curr_prog_id != expected_prog_id) { + fprintf(stderr, "ERR: %s() " + "expected prog ID(%d) no match(%d), not removing\n", + __func__, expected_prog_id, curr_prog_id); + return EXIT_FAIL; + } + + if ((err = bpf_set_link_xdp_fd(ifindex, -1, xdp_flags)) < 0) { + fprintf(stderr, "ERR: %s() link set xdp failed (err=%d): %s\n", + __func__, err, strerror(-err)); + return EXIT_FAIL_XDP; + } + + if (verbose) + printf("INFO: %s() removed XDP prog ID:%d on ifindex:%d\n", + __func__, curr_prog_id, ifindex); + + return EXIT_OK; +} + +struct bpf_object *load_bpf_object_file(const char *filename, int ifindex) +{ + int first_prog_fd = -1; + struct bpf_object *obj; + int err; + + /* This struct allow us to set ifindex, this features is used for + * hardware offloading XDP programs (note this sets libbpf + * bpf_program->prog_ifindex and foreach bpf_map->map_ifindex). + */ + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_XDP, + .ifindex = ifindex, + }; + prog_load_attr.file = filename; + + /* Use libbpf for extracting BPF byte-code from BPF-ELF object, and + * loading this into the kernel via bpf-syscall + */ + err = bpf_prog_load_xattr(&prog_load_attr, &obj, &first_prog_fd); + if (err) { + fprintf(stderr, "ERR: loading BPF-OBJ file(%s) (%d): %s\n", + filename, err, strerror(-err)); + return NULL; + } + + /* Notice how a pointer to a libbpf bpf_object is returned */ + return obj; +} + +static struct bpf_object *open_bpf_object(const char *file, int ifindex) +{ + int err; + struct bpf_object *obj; + struct bpf_map *map; + struct bpf_program *prog, *first_prog = NULL; + + struct bpf_object_open_attr open_attr = { + .file = file, + .prog_type = BPF_PROG_TYPE_XDP, + }; + + obj = bpf_object__open_xattr(&open_attr); + if (IS_ERR_OR_NULL(obj)) { + err = -PTR_ERR(obj); + fprintf(stderr, "ERR: opening BPF-OBJ file(%s) (%d): %s\n", + file, err, strerror(-err)); + return NULL; + } + + bpf_object__for_each_program(prog, obj) { + bpf_program__set_type(prog, BPF_PROG_TYPE_XDP); + bpf_program__set_ifindex(prog, ifindex); + if (!first_prog) + first_prog = prog; + } + + bpf_object__for_each_map(map, obj) { + if (!bpf_map__is_offload_neutral(map)) + bpf_map__set_ifindex(map, ifindex); + } + + if (!first_prog) { + fprintf(stderr, "ERR: file %s contains no programs\n", file); + return NULL; + } + + return obj; +} + +static int reuse_maps(struct bpf_object *obj, const char *path) +{ + struct bpf_map *map; + + if (!obj) + return -ENOENT; + + if (!path) + return -EINVAL; + + bpf_object__for_each_map(map, obj) { + int len, err; + int pinned_map_fd; + char buf[PATH_MAX]; + + len = snprintf(buf, PATH_MAX, "%s/%s", path, bpf_map__name(map)); + if (len < 0) { + return -EINVAL; + } else if (len >= PATH_MAX) { + return -ENAMETOOLONG; + } + + pinned_map_fd = bpf_obj_get(buf); + if (pinned_map_fd < 0) + return pinned_map_fd; + + err = bpf_map__reuse_fd(map, pinned_map_fd); + if (err) + return err; + } + + return 0; +} + +struct bpf_object *load_bpf_object_file_reuse_maps(const char *file, + int ifindex, + const char *pin_dir) +{ + int err; + struct bpf_object *obj; + + obj = open_bpf_object(file, ifindex); + if (!obj) { + fprintf(stderr, "ERR: failed to open object %s\n", file); + return NULL; + } + + err = reuse_maps(obj, pin_dir); + if (err) { + fprintf(stderr, "ERR: failed to reuse maps for object %s, pin_dir=%s\n", + file, pin_dir); + return NULL; + } + + err = bpf_object__load(obj); + if (err) { + fprintf(stderr, "ERR: loading BPF-OBJ file(%s) (%d): %s\n", + file, err, strerror(-err)); + return NULL; + } + + return obj; +} + +struct bpf_object *load_bpf_and_xdp_attach(struct config *cfg) +{ + struct bpf_program *bpf_prog; + struct bpf_object *bpf_obj; + int offload_ifindex = 0; + int prog_fd = -1; + int err; + + /* If flags indicate hardware offload, supply ifindex */ + if (cfg->xdp_flags & XDP_FLAGS_HW_MODE) + offload_ifindex = cfg->ifindex; + + /* Load the BPF-ELF object file and get back libbpf bpf_object */ + if (cfg->reuse_maps) + bpf_obj = load_bpf_object_file_reuse_maps(cfg->filename, + offload_ifindex, + cfg->pin_dir); + else + bpf_obj = load_bpf_object_file(cfg->filename, offload_ifindex); + if (!bpf_obj) { + fprintf(stderr, "ERR: loading file: %s\n", cfg->filename); + exit(EXIT_FAIL_BPF); + } + /* At this point: All XDP/BPF programs from the cfg->filename have been + * loaded into the kernel, and evaluated by the verifier. Only one of + * these gets attached to XDP hook, the others will get freed once this + * process exit. + */ + + if (cfg->progsec[0]) + /* Find a matching BPF prog section name */ + bpf_prog = bpf_object__find_program_by_title(bpf_obj, cfg->progsec); + else + /* Find the first program */ + bpf_prog = bpf_program__next(NULL, bpf_obj); + + if (!bpf_prog) { + fprintf(stderr, "ERR: couldn't find a program in ELF section '%s'\n", cfg->progsec); + exit(EXIT_FAIL_BPF); + } + + strncpy(cfg->progsec, bpf_program__title(bpf_prog, false), sizeof(cfg->progsec)); + + prog_fd = bpf_program__fd(bpf_prog); + if (prog_fd <= 0) { + fprintf(stderr, "ERR: bpf_program__fd failed\n"); + exit(EXIT_FAIL_BPF); + } + + /* At this point: BPF-progs are (only) loaded by the kernel, and prog_fd + * is our select file-descriptor handle. Next step is attaching this FD + * to a kernel hook point, in this case XDP net_device link-level hook. + */ + err = xdp_link_attach(cfg->ifindex, cfg->xdp_flags, prog_fd); + if (err) + exit(err); + + return bpf_obj; +} + +#define XDP_UNKNOWN XDP_REDIRECT + 1 +#ifndef XDP_ACTION_MAX +#define XDP_ACTION_MAX (XDP_UNKNOWN + 1) +#endif + +static const char *xdp_action_names[XDP_ACTION_MAX] = { + [XDP_ABORTED] = "XDP_ABORTED", + [XDP_DROP] = "XDP_DROP", + [XDP_PASS] = "XDP_PASS", + [XDP_TX] = "XDP_TX", + [XDP_REDIRECT] = "XDP_REDIRECT", + [XDP_UNKNOWN] = "XDP_UNKNOWN", +}; + +const char *action2str(__u32 action) +{ + if (action < XDP_ACTION_MAX) + return xdp_action_names[action]; + return NULL; +} + +int check_map_fd_info(const struct bpf_map_info *info, + const struct bpf_map_info *exp) +{ + if (exp->key_size && exp->key_size != info->key_size) { + fprintf(stderr, "ERR: %s() " + "Map key size(%d) mismatch expected size(%d)\n", + __func__, info->key_size, exp->key_size); + return EXIT_FAIL; + } + if (exp->value_size && exp->value_size != info->value_size) { + fprintf(stderr, "ERR: %s() " + "Map value size(%d) mismatch expected size(%d)\n", + __func__, info->value_size, exp->value_size); + return EXIT_FAIL; + } + if (exp->max_entries && exp->max_entries != info->max_entries) { + fprintf(stderr, "ERR: %s() " + "Map max_entries(%d) mismatch expected size(%d)\n", + __func__, info->max_entries, exp->max_entries); + return EXIT_FAIL; + } + if (exp->type && exp->type != info->type) { + fprintf(stderr, "ERR: %s() " + "Map type(%d) mismatch expected type(%d)\n", + __func__, info->type, exp->type); + return EXIT_FAIL; + } + + return 0; +} + +int open_bpf_map_file(const char *pin_dir, + const char *mapname, + struct bpf_map_info *info) +{ + char filename[PATH_MAX]; + int err, len, fd; + __u32 info_len = sizeof(*info); + + len = snprintf(filename, PATH_MAX, "%s/%s", pin_dir, mapname); + if (len < 0) { + fprintf(stderr, "ERR: constructing full mapname path\n"); + return -1; + } + + fd = bpf_obj_get(filename); + if (fd < 0) { + fprintf(stderr, + "WARN: Failed to open bpf map file:%s err(%d):%s\n", + filename, errno, strerror(errno)); + return fd; + } + + if (info) { + err = bpf_obj_get_info_by_fd(fd, info, &info_len); + if (err) { + fprintf(stderr, "ERR: %s() can't get info - %s\n", + __func__, strerror(errno)); + return EXIT_FAIL_BPF; + } + } + + return fd; +} diff --git a/src/xdp/common/common_user_bpf_xdp.h b/src/xdp/common/common_user_bpf_xdp.h new file mode 100644 index 000000000..4f8aa51d4 --- /dev/null +++ b/src/xdp/common/common_user_bpf_xdp.h @@ -0,0 +1,20 @@ +/* Common BPF/XDP functions used by userspace side programs */ +#ifndef __COMMON_USER_BPF_XDP_H +#define __COMMON_USER_BPF_XDP_H + +int xdp_link_attach(int ifindex, __u32 xdp_flags, int prog_fd); +int xdp_link_detach(int ifindex, __u32 xdp_flags, __u32 expected_prog_id); + +struct bpf_object *load_bpf_object_file(const char *filename, int ifindex); +struct bpf_object *load_bpf_and_xdp_attach(struct config *cfg); + +const char *action2str(__u32 action); + +int check_map_fd_info(const struct bpf_map_info *info, + const struct bpf_map_info *exp); + +int open_bpf_map_file(const char *pin_dir, + const char *mapname, + struct bpf_map_info *info); + +#endif /* __COMMON_USER_BPF_XDP_H */ diff --git a/src/xdp/common/parsing_helpers.h b/src/xdp/common/parsing_helpers.h new file mode 100644 index 000000000..c0837e88f --- /dev/null +++ b/src/xdp/common/parsing_helpers.h @@ -0,0 +1,244 @@ +/* SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-2-clause) */ +/* + * This file contains parsing functions that are used in the packetXX XDP + * programs. The functions are marked as __always_inline, and fully defined in + * this header file to be included in the BPF program. + * + * Each helper parses a packet header, including doing bounds checking, and + * returns the type of its contents if successful, and -1 otherwise. + * + * For Ethernet and IP headers, the content type is the type of the payload + * (h_proto for Ethernet, nexthdr for IPv6), for ICMP it is the ICMP type field. + * All return values are in host byte order. + * + * The versions of the functions included here are slightly expanded versions of + * the functions in the packet01 lesson. For instance, the Ethernet header + * parsing has support for parsing VLAN tags. + */ + +#ifndef __PARSING_HELPERS_H +#define __PARSING_HELPERS_H + +#include <stddef.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/icmp.h> +#include <linux/icmpv6.h> +#include <linux/udp.h> +#include <linux/tcp.h> + +/* Header cursor to keep track of current parsing position */ +struct hdr_cursor { + void *pos; +}; + +/* + * struct vlan_hdr - vlan header + * @h_vlan_TCI: priority and VLAN ID + * @h_vlan_encapsulated_proto: packet type ID or len + */ +struct vlan_hdr { + __be16 h_vlan_TCI; + __be16 h_vlan_encapsulated_proto; +}; + +/* + * Struct icmphdr_common represents the common part of the icmphdr and icmp6hdr + * structures. + */ +struct icmphdr_common { + __u8 type; + __u8 code; + __sum16 cksum; +}; + +/* Allow users of header file to redefine VLAN max depth */ +#ifndef VLAN_MAX_DEPTH +#define VLAN_MAX_DEPTH 4 +#endif + +static __always_inline int proto_is_vlan(__u16 h_proto) +{ + return !!(h_proto == bpf_htons(ETH_P_8021Q) || + h_proto == bpf_htons(ETH_P_8021AD)); +} + +/* Notice, parse_ethhdr() will skip VLAN tags, by advancing nh->pos and returns + * next header EtherType, BUT the ethhdr pointer supplied still points to the + * Ethernet header. Thus, caller can look at eth->h_proto to see if this was a + * VLAN tagged packet. + */ +static __always_inline int parse_ethhdr(struct hdr_cursor *nh, void *data_end, + struct ethhdr **ethhdr) +{ + struct ethhdr *eth = nh->pos; + int hdrsize = sizeof(*eth); + struct vlan_hdr *vlh; + __u16 h_proto; + int i; + + /* Byte-count bounds check; check if current pointer + size of header + * is after data_end. + */ + if (nh->pos + hdrsize > data_end) + return -1; + + nh->pos += hdrsize; + *ethhdr = eth; + vlh = nh->pos; + h_proto = eth->h_proto; + + /* Use loop unrolling to avoid the verifier restriction on loops; + * support up to VLAN_MAX_DEPTH layers of VLAN encapsulation. + */ + #pragma unroll + for (i = 0; i < VLAN_MAX_DEPTH; i++) { + if (!proto_is_vlan(h_proto)) + break; + + if (vlh + 1 > data_end) + break; + + h_proto = vlh->h_vlan_encapsulated_proto; + vlh++; + } + + nh->pos = vlh; + return h_proto; /* network-byte-order */ +} + +static __always_inline int parse_ip6hdr(struct hdr_cursor *nh, + void *data_end, + struct ipv6hdr **ip6hdr) +{ + struct ipv6hdr *ip6h = nh->pos; + + /* Pointer-arithmetic bounds check; pointer +1 points to after end of + * thing being pointed to. We will be using this style in the remainder + * of the tutorial. + */ + if (ip6h + 1 > data_end) + return -1; + + nh->pos = ip6h + 1; + *ip6hdr = ip6h; + + return ip6h->nexthdr; +} + +static __always_inline int parse_iphdr(struct hdr_cursor *nh, + void *data_end, + struct iphdr **iphdr) +{ + struct iphdr *iph = nh->pos; + int hdrsize; + + if (iph + 1 > data_end) + return -1; + + hdrsize = iph->ihl * 4; + + /* Variable-length IPv4 header, need to use byte-based arithmetic */ + if (nh->pos + hdrsize > data_end) + return -1; + + nh->pos += hdrsize; + *iphdr = iph; + + return iph->protocol; +} + +static __always_inline int parse_icmp6hdr(struct hdr_cursor *nh, + void *data_end, + struct icmp6hdr **icmp6hdr) +{ + struct icmp6hdr *icmp6h = nh->pos; + + if (icmp6h + 1 > data_end) + return -1; + + nh->pos = icmp6h + 1; + *icmp6hdr = icmp6h; + + return icmp6h->icmp6_type; +} + +static __always_inline int parse_icmphdr(struct hdr_cursor *nh, + void *data_end, + struct icmphdr **icmphdr) +{ + struct icmphdr *icmph = nh->pos; + + if (icmph + 1 > data_end) + return -1; + + nh->pos = icmph + 1; + *icmphdr = icmph; + + return icmph->type; +} + +static __always_inline int parse_icmphdr_common(struct hdr_cursor *nh, + void *data_end, + struct icmphdr_common **icmphdr) +{ + struct icmphdr_common *h = nh->pos; + + if (h + 1 > data_end) + return -1; + + nh->pos = h + 1; + *icmphdr = h; + + return h->type; +} + +/* + * parse_udphdr: parse the udp header and return the length of the udp payload + */ +static __always_inline int parse_udphdr(struct hdr_cursor *nh, + void *data_end, + struct udphdr **udphdr) +{ + int len; + struct udphdr *h = nh->pos; + + if (h + 1 > data_end) + return -1; + + nh->pos = h + 1; + *udphdr = h; + + len = bpf_ntohs(h->len) - sizeof(struct udphdr); + if (len < 0) + return -1; + + return len; +} + +/* + * parse_tcphdr: parse and return the length of the tcp header + */ +static __always_inline int parse_tcphdr(struct hdr_cursor *nh, + void *data_end, + struct tcphdr **tcphdr) +{ + int len; + struct tcphdr *h = nh->pos; + + if (h + 1 > data_end) + return -1; + + len = h->doff * 4; + if ((void *) h + len > data_end) + return -1; + + nh->pos = h + 1; + *tcphdr = h; + + return len; +} + +#endif /* __PARSING_HELPERS_H */ diff --git a/src/xdp/common/rewrite_helpers.h b/src/xdp/common/rewrite_helpers.h new file mode 100644 index 000000000..a5d3e671d --- /dev/null +++ b/src/xdp/common/rewrite_helpers.h @@ -0,0 +1,144 @@ +/* SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-2-clause) */ +/* + * This file contains functions that are used in the packetXX XDP programs to + * manipulate on packets data. The functions are marked as __always_inline, and + * fully defined in this header file to be included in the BPF program. + */ + +#ifndef __REWRITE_HELPERS_H +#define __REWRITE_HELPERS_H + +#include <linux/bpf.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/if_ether.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +/* Pops the outermost VLAN tag off the packet. Returns the popped VLAN ID on + * success or negative errno on failure. + */ +static __always_inline int vlan_tag_pop(struct xdp_md *ctx, struct ethhdr *eth) +{ + void *data_end = (void *)(long)ctx->data_end; + struct ethhdr eth_cpy; + struct vlan_hdr *vlh; + __be16 h_proto; + int vlid; + + if (!proto_is_vlan(eth->h_proto)) + return -1; + + /* Careful with the parenthesis here */ + vlh = (void *)(eth + 1); + + /* Still need to do bounds checking */ + if (vlh + 1 > data_end) + return -1; + + /* Save vlan ID for returning, h_proto for updating Ethernet header */ + vlid = bpf_ntohs(vlh->h_vlan_TCI); + h_proto = vlh->h_vlan_encapsulated_proto; + + /* Make a copy of the outer Ethernet header before we cut it off */ + __builtin_memcpy(ð_cpy, eth, sizeof(eth_cpy)); + + /* Actually adjust the head pointer */ + if (bpf_xdp_adjust_head(ctx, (int)sizeof(*vlh))) + return -1; + + /* Need to re-evaluate data *and* data_end and do new bounds checking + * after adjusting head + */ + eth = (void *)(long)ctx->data; + data_end = (void *)(long)ctx->data_end; + if (eth + 1 > data_end) + return -1; + + /* Copy back the old Ethernet header and update the proto type */ + __builtin_memcpy(eth, ð_cpy, sizeof(*eth)); + eth->h_proto = h_proto; + + return vlid; +} + +/* Pushes a new VLAN tag after the Ethernet header. Returns 0 on success, + * -1 on failure. + */ +static __always_inline int vlan_tag_push(struct xdp_md *ctx, + struct ethhdr *eth, int vlid) +{ + void *data_end = (void *)(long)ctx->data_end; + struct ethhdr eth_cpy; + struct vlan_hdr *vlh; + + /* First copy the original Ethernet header */ + __builtin_memcpy(ð_cpy, eth, sizeof(eth_cpy)); + + /* Then add space in front of the packet */ + if (bpf_xdp_adjust_head(ctx, 0 - (int)sizeof(*vlh))) + return -1; + + /* Need to re-evaluate data_end and data after head adjustment, and + * bounds check, even though we know there is enough space (as we + * increased it). + */ + data_end = (void *)(long)ctx->data_end; + eth = (void *)(long)ctx->data; + + if (eth + 1 > data_end) + return -1; + + /* Copy back Ethernet header in the right place, populate VLAN tag with + * ID and proto, and set outer Ethernet header to VLAN type. + */ + __builtin_memcpy(eth, ð_cpy, sizeof(*eth)); + + vlh = (void *)(eth + 1); + + if (vlh + 1 > data_end) + return -1; + + vlh->h_vlan_TCI = bpf_htons(vlid); + vlh->h_vlan_encapsulated_proto = eth->h_proto; + + eth->h_proto = bpf_htons(ETH_P_8021Q); + return 0; +} + +/* + * Swaps destination and source MAC addresses inside an Ethernet header + */ +static __always_inline void swap_src_dst_mac(struct ethhdr *eth) +{ + __u8 h_tmp[ETH_ALEN]; + + __builtin_memcpy(h_tmp, eth->h_source, ETH_ALEN); + __builtin_memcpy(eth->h_source, eth->h_dest, ETH_ALEN); + __builtin_memcpy(eth->h_dest, h_tmp, ETH_ALEN); +} + +/* + * Swaps destination and source IPv6 addresses inside an IPv6 header + */ +static __always_inline void swap_src_dst_ipv6(struct ipv6hdr *ipv6) +{ + struct in6_addr tmp = ipv6->saddr; + + ipv6->saddr = ipv6->daddr; + ipv6->daddr = tmp; +} + +/* + * Swaps destination and source IPv4 addresses inside an IPv4 header + */ +static __always_inline void swap_src_dst_ipv4(struct iphdr *iphdr) +{ + __be32 tmp = iphdr->saddr; + + iphdr->saddr = iphdr->daddr; + iphdr->daddr = tmp; +} + +#endif /* __REWRITE_HELPERS_H */ diff --git a/src/xdp/common/xdp_stats_kern.h b/src/xdp/common/xdp_stats_kern.h new file mode 100644 index 000000000..4e08551a0 --- /dev/null +++ b/src/xdp/common/xdp_stats_kern.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Used *ONLY* by BPF-prog running kernel side. */ +#ifndef __XDP_STATS_KERN_H +#define __XDP_STATS_KERN_H + +/* Data record type 'struct datarec' is defined in common/xdp_stats_kern_user.h, + * programs using this header must first include that file. + */ +#ifndef __XDP_STATS_KERN_USER_H +#warning "You forgot to #include <../common/xdp_stats_kern_user.h>" +#include <../common/xdp_stats_kern_user.h> +#endif + +/* Keeps stats per (enum) xdp_action */ +struct bpf_map_def SEC("maps") xdp_stats_map = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct datarec), + .max_entries = XDP_ACTION_MAX, +}; + +static __always_inline +__u32 xdp_stats_record_action(struct xdp_md *ctx, __u32 action) +{ + if (action >= XDP_ACTION_MAX) + return XDP_ABORTED; + + /* Lookup in kernel BPF-side return pointer to actual data record */ + struct datarec *rec = bpf_map_lookup_elem(&xdp_stats_map, &action); + if (!rec) + return XDP_ABORTED; + + /* BPF_MAP_TYPE_PERCPU_ARRAY returns a data record specific to current + * CPU and XDP hooks runs under Softirq, which makes it safe to update + * without atomic operations. + */ + rec->rx_packets++; + rec->rx_bytes += (ctx->data_end - ctx->data); + + return action; +} + +#endif /* __XDP_STATS_KERN_H */ diff --git a/src/xdp/common/xdp_stats_kern_user.h b/src/xdp/common/xdp_stats_kern_user.h new file mode 100644 index 000000000..d7b8d05e6 --- /dev/null +++ b/src/xdp/common/xdp_stats_kern_user.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Used by BPF-prog kernel side BPF-progs and userspace programs, + * for sharing xdp_stats common struct and DEFINEs. + */ +#ifndef __XDP_STATS_KERN_USER_H +#define __XDP_STATS_KERN_USER_H + +/* This is the data record stored in the map */ +struct datarec { + __u64 rx_packets; + __u64 rx_bytes; +}; + +#ifndef XDP_ACTION_MAX +#define XDP_ACTION_MAX (XDP_REDIRECT + 1) +#endif + +#endif /* __XDP_STATS_KERN_USER_H */ diff --git a/src/xdp/include/bpf_endian.h b/src/xdp/include/bpf_endian.h new file mode 100644 index 000000000..2b0ede3d5 --- /dev/null +++ b/src/xdp/include/bpf_endian.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copied from $(LINUX)/tools/testing/selftests/bpf/bpf_endian.h */ +#ifndef __BPF_ENDIAN__ +#define __BPF_ENDIAN__ + +#include <linux/swab.h> + +/* LLVM's BPF target selects the endianness of the CPU + * it compiles on, or the user specifies (bpfel/bpfeb), + * respectively. The used __BYTE_ORDER__ is defined by + * the compiler, we cannot rely on __BYTE_ORDER from + * libc headers, since it doesn't reflect the actual + * requested byte order. + * + * Note, LLVM's BPF target has different __builtin_bswapX() + * semantics. It does map to BPF_ALU | BPF_END | BPF_TO_BE + * in bpfel and bpfeb case, which means below, that we map + * to cpu_to_be16(). We could use it unconditionally in BPF + * case, but better not rely on it, so that this header here + * can be used from application and BPF program side, which + * use different targets. + */ +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +# define __bpf_ntohs(x)__builtin_bswap16(x) +# define __bpf_htons(x)__builtin_bswap16(x) +# define __bpf_constant_ntohs(x)___constant_swab16(x) +# define __bpf_constant_htons(x)___constant_swab16(x) +# define __bpf_ntohl(x)__builtin_bswap32(x) +# define __bpf_htonl(x)__builtin_bswap32(x) +# define __bpf_constant_ntohl(x)___constant_swab32(x) +# define __bpf_constant_htonl(x)___constant_swab32(x) +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ +# define __bpf_ntohs(x)(x) +# define __bpf_htons(x)(x) +# define __bpf_constant_ntohs(x)(x) +# define __bpf_constant_htons(x)(x) +# define __bpf_ntohl(x)(x) +# define __bpf_htonl(x)(x) +# define __bpf_constant_ntohl(x)(x) +# define __bpf_constant_htonl(x)(x) +#else +# error "Fix your compiler's __BYTE_ORDER__?!" +#endif + +#define bpf_htons(x)\ + (__builtin_constant_p(x) ?\ + __bpf_constant_htons(x) : __bpf_htons(x)) +#define bpf_ntohs(x)\ + (__builtin_constant_p(x) ?\ + __bpf_constant_ntohs(x) : __bpf_ntohs(x)) +#define bpf_htonl(x)\ + (__builtin_constant_p(x) ?\ + __bpf_constant_htonl(x) : __bpf_htonl(x)) +#define bpf_ntohl(x)\ + (__builtin_constant_p(x) ?\ + __bpf_constant_ntohl(x) : __bpf_ntohl(x)) + +#endif /* __BPF_ENDIAN__ */ diff --git a/src/xdp/include/bpf_legacy.h b/src/xdp/include/bpf_legacy.h new file mode 100644 index 000000000..8dfa168cd --- /dev/null +++ b/src/xdp/include/bpf_legacy.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __BPF_LEGACY__ +#define __BPF_LEGACY__ + +/* + * legacy bpf_map_def with extra fields supported only by bpf_load(), do not + * use outside of samples/bpf + */ +struct bpf_map_def_legacy { + unsigned int type; + unsigned int key_size; + unsigned int value_size; + unsigned int max_entries; + unsigned int map_flags; + unsigned int inner_map_idx; + unsigned int numa_node; +}; + +#define BPF_ANNOTATE_KV_PAIR(name, type_key, type_val) \ + struct ____btf_map_##name { \ + type_key key; \ + type_val value; \ + }; \ + struct ____btf_map_##name \ + __attribute__ ((section(".maps." #name), used)) \ + ____btf_map_##name = { } + +/* llvm builtin functions that eBPF C program may use to + * emit BPF_LD_ABS and BPF_LD_IND instructions + */ +unsigned long long load_byte(void *skb, + unsigned long long off) asm("llvm.bpf.load.byte"); +unsigned long long load_half(void *skb, + unsigned long long off) asm("llvm.bpf.load.half"); +unsigned long long load_word(void *skb, + unsigned long long off) asm("llvm.bpf.load.word"); + +#endif diff --git a/src/xdp/include/bpf_util.h b/src/xdp/include/bpf_util.h new file mode 100644 index 000000000..e74b33e9d --- /dev/null +++ b/src/xdp/include/bpf_util.h @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copied from $(LINUX)/tools/testing/selftests/bpf/bpf_util.h */ +#ifndef __BPF_UTIL__ +#define __BPF_UTIL__ + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> + +static inline unsigned int bpf_num_possible_cpus(void) +{ + static const char *fcpu = "/sys/devices/system/cpu/possible"; + unsigned int start, end, possible_cpus = 0; + char buff[128]; + FILE *fp; + int n; + + fp = fopen(fcpu, "r"); + if (!fp) { + printf("Failed to open %s: '%s'!\n", fcpu, strerror(errno)); + exit(1); + } + + while (fgets(buff, sizeof(buff), fp)) { + n = sscanf(buff, "%u-%u", &start, &end); + if (n == 0) { + printf("Failed to retrieve # possible CPUs!\n"); + exit(1); + } else if (n == 1) { + end = start; + } + possible_cpus = start == 0 ? end + 1 : 0; + break; + } + fclose(fp); + + return possible_cpus; +} + +#define __bpf_percpu_val_align __attribute__((__aligned__(8))) + +#define BPF_DECLARE_PERCPU(type, name) \ + struct { type v; /* padding */ } __bpf_percpu_val_align \ + name[bpf_num_possible_cpus()] +#define bpf_percpu(name, cpu) name[(cpu)].v + +#ifndef ARRAY_SIZE +# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +#ifndef sizeof_field +#define sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER)) +#endif + +#ifndef offsetofend +#define offsetofend(TYPE, MEMBER) \ + (offsetof(TYPE, MEMBER) + sizeof_field(TYPE, MEMBER)) +#endif + +#endif /* __BPF_UTIL__ */ diff --git a/src/xdp/include/jhash.h b/src/xdp/include/jhash.h new file mode 100644 index 000000000..b81a0d0eb --- /dev/null +++ b/src/xdp/include/jhash.h @@ -0,0 +1,172 @@ +#ifndef _LINUX_JHASH_H +#define _LINUX_JHASH_H + +/* Copied from $(LINUX)/include/linux/jhash.h (kernel 4.18) */ + +/* jhash.h: Jenkins hash support. + * + * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net) + * + * http://burtleburtle.net/bob/hash/ + * + * These are the credits from Bob's sources: + * + * lookup3.c, by Bob Jenkins, May 2006, Public Domain. + * + * These are functions for producing 32-bit hashes for hash table lookup. + * hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() + * are externally useful functions. Routines to test the hash are included + * if SELF_TEST is defined. You can use this free for any purpose. It's in + * the public domain. It has no warranty. + * + * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@blackhole.kfki.hu) + */ + +static inline __u32 rol32(__u32 word, unsigned int shift) +{ + return (word << shift) | (word >> ((-shift) & 31)); +} + +/* copy paste of jhash from kernel sources (include/linux/jhash.h) to make sure + * LLVM can compile it into valid sequence of BPF instructions + */ +#define __jhash_mix(a, b, c) \ +{ \ + a -= c; a ^= rol32(c, 4); c += b; \ + b -= a; b ^= rol32(a, 6); a += c; \ + c -= b; c ^= rol32(b, 8); b += a; \ + a -= c; a ^= rol32(c, 16); c += b; \ + b -= a; b ^= rol32(a, 19); a += c; \ + c -= b; c ^= rol32(b, 4); b += a; \ +} + +#define __jhash_final(a, b, c) \ +{ \ + c ^= b; c -= rol32(b, 14); \ + a ^= c; a -= rol32(c, 11); \ + b ^= a; b -= rol32(a, 25); \ + c ^= b; c -= rol32(b, 16); \ + a ^= c; a -= rol32(c, 4); \ + b ^= a; b -= rol32(a, 14); \ + c ^= b; c -= rol32(b, 24); \ +} + +#define JHASH_INITVAL 0xdeadbeef + +typedef unsigned int u32; + +/* jhash - hash an arbitrary key + * @k: sequence of bytes as key + * @length: the length of the key + * @initval: the previous hash, or an arbitray value + * + * The generic version, hashes an arbitrary sequence of bytes. + * No alignment or length assumptions are made about the input key. + * + * Returns the hash value of the key. The result depends on endianness. + */ +static inline u32 jhash(const void *key, u32 length, u32 initval) +{ + u32 a, b, c; + const unsigned char *k = key; + + /* Set up the internal state */ + a = b = c = JHASH_INITVAL + length + initval; + + /* All but the last block: affect some 32 bits of (a,b,c) */ + while (length > 12) { + a += *(u32 *)(k); + b += *(u32 *)(k + 4); + c += *(u32 *)(k + 8); + __jhash_mix(a, b, c); + length -= 12; + k += 12; + } + /* Last block: affect all 32 bits of (c) */ + switch (length) { + case 12: c += (u32)k[11]<<24; /* fall through */ + case 11: c += (u32)k[10]<<16; /* fall through */ + case 10: c += (u32)k[9]<<8; /* fall through */ + case 9: c += k[8]; /* fall through */ + case 8: b += (u32)k[7]<<24; /* fall through */ + case 7: b += (u32)k[6]<<16; /* fall through */ + case 6: b += (u32)k[5]<<8; /* fall through */ + case 5: b += k[4]; /* fall through */ + case 4: a += (u32)k[3]<<24; /* fall through */ + case 3: a += (u32)k[2]<<16; /* fall through */ + case 2: a += (u32)k[1]<<8; /* fall through */ + case 1: a += k[0]; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } + + return c; +} + +/* jhash2 - hash an array of u32's + * @k: the key which must be an array of u32's + * @length: the number of u32's in the key + * @initval: the previous hash, or an arbitray value + * + * Returns the hash value of the key. + */ +static inline u32 jhash2(const u32 *k, u32 length, u32 initval) +{ + u32 a, b, c; + + /* Set up the internal state */ + a = b = c = JHASH_INITVAL + (length<<2) + initval; + + /* Handle most of the key */ + while (length > 3) { + a += k[0]; + b += k[1]; + c += k[2]; + __jhash_mix(a, b, c); + length -= 3; + k += 3; + } + + /* Handle the last 3 u32's */ + switch (length) { + case 3: c += k[2]; /* fall through */ + case 2: b += k[1]; /* fall through */ + case 1: a += k[0]; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } + + return c; +} + + +/* __jhash_nwords - hash exactly 3, 2 or 1 word(s) */ +static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) +{ + a += initval; + b += initval; + c += initval; + + __jhash_final(a, b, c); + + return c; +} + +static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval) +{ + return __jhash_nwords(a, b, c, initval + JHASH_INITVAL + (3 << 2)); +} + +static inline u32 jhash_2words(u32 a, u32 b, u32 initval) +{ + return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); +} + +static inline u32 jhash_1word(u32 a, u32 initval) +{ + return __jhash_nwords(a, 0, 0, initval + JHASH_INITVAL + (1 << 2)); +} + +#endif /* _LINUX_JHASH_H */ diff --git a/src/xdp/include/linux/bpf.h b/src/xdp/include/linux/bpf.h new file mode 100644 index 000000000..161a93809 --- /dev/null +++ b/src/xdp/include/linux/bpf.h @@ -0,0 +1,3278 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * + * 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. + */ +#ifndef _UAPI__LINUX_BPF_H__ +#define _UAPI__LINUX_BPF_H__ + +#include <linux/types.h> +#include <linux/bpf_common.h> + +/* Extended instruction set based on top of classic BPF */ + +/* instruction classes */ +#define BPF_JMP32 0x06 /* jmp mode in word width */ +#define BPF_ALU64 0x07 /* alu mode in double word width */ + +/* ld/ldx fields */ +#define BPF_DW 0x18 /* double word (64-bit) */ +#define BPF_XADD 0xc0 /* exclusive add */ + +/* alu/jmp fields */ +#define BPF_MOV 0xb0 /* mov reg to reg */ +#define BPF_ARSH 0xc0 /* sign extending arithmetic shift right */ + +/* change endianness of a register */ +#define BPF_END 0xd0 /* flags for endianness conversion: */ +#define BPF_TO_LE 0x00 /* convert to little-endian */ +#define BPF_TO_BE 0x08 /* convert to big-endian */ +#define BPF_FROM_LE BPF_TO_LE +#define BPF_FROM_BE BPF_TO_BE + +/* jmp encodings */ +#define BPF_JNE 0x50 /* jump != */ +#define BPF_JLT 0xa0 /* LT is unsigned, '<' */ +#define BPF_JLE 0xb0 /* LE is unsigned, '<=' */ +#define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */ +#define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */ +#define BPF_JSLT 0xc0 /* SLT is signed, '<' */ +#define BPF_JSLE 0xd0 /* SLE is signed, '<=' */ +#define BPF_CALL 0x80 /* function call */ +#define BPF_EXIT 0x90 /* function return */ + +/* Register numbers */ +enum { + BPF_REG_0 = 0, + BPF_REG_1, + BPF_REG_2, + BPF_REG_3, + BPF_REG_4, + BPF_REG_5, + BPF_REG_6, + BPF_REG_7, + BPF_REG_8, + BPF_REG_9, + BPF_REG_10, + __MAX_BPF_REG, +}; + +/* BPF has 10 general purpose 64-bit registers and stack frame. */ +#define MAX_BPF_REG __MAX_BPF_REG + +struct bpf_insn { + __u8 code; /* opcode */ + __u8 dst_reg:4; /* dest register */ + __u8 src_reg:4; /* source register */ + __s16 off; /* signed offset */ + __s32 imm; /* signed immediate constant */ +}; + +/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */ +struct bpf_lpm_trie_key { + __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */ + __u8 data[0]; /* Arbitrary size */ +}; + +struct bpf_cgroup_storage_key { + __u64 cgroup_inode_id; /* cgroup inode id */ + __u32 attach_type; /* program attach type */ +}; + +/* BPF syscall commands, see bpf(2) man-page for details. */ +enum bpf_cmd { + BPF_MAP_CREATE, + BPF_MAP_LOOKUP_ELEM, + BPF_MAP_UPDATE_ELEM, + BPF_MAP_DELETE_ELEM, + BPF_MAP_GET_NEXT_KEY, + BPF_PROG_LOAD, + BPF_OBJ_PIN, + BPF_OBJ_GET, + BPF_PROG_ATTACH, + BPF_PROG_DETACH, + BPF_PROG_TEST_RUN, + BPF_PROG_GET_NEXT_ID, + BPF_MAP_GET_NEXT_ID, + BPF_PROG_GET_FD_BY_ID, + BPF_MAP_GET_FD_BY_ID, + BPF_OBJ_GET_INFO_BY_FD, + BPF_PROG_QUERY, + BPF_RAW_TRACEPOINT_OPEN, + BPF_BTF_LOAD, + BPF_BTF_GET_FD_BY_ID, + BPF_TASK_FD_QUERY, + BPF_MAP_LOOKUP_AND_DELETE_ELEM, +}; + +enum bpf_map_type { + BPF_MAP_TYPE_UNSPEC, + BPF_MAP_TYPE_HASH, + BPF_MAP_TYPE_ARRAY, + BPF_MAP_TYPE_PROG_ARRAY, + BPF_MAP_TYPE_PERF_EVENT_ARRAY, + BPF_MAP_TYPE_PERCPU_HASH, + BPF_MAP_TYPE_PERCPU_ARRAY, + BPF_MAP_TYPE_STACK_TRACE, + BPF_MAP_TYPE_CGROUP_ARRAY, + BPF_MAP_TYPE_LRU_HASH, + BPF_MAP_TYPE_LRU_PERCPU_HASH, + BPF_MAP_TYPE_LPM_TRIE, + BPF_MAP_TYPE_ARRAY_OF_MAPS, + BPF_MAP_TYPE_HASH_OF_MAPS, + BPF_MAP_TYPE_DEVMAP, + BPF_MAP_TYPE_SOCKMAP, + BPF_MAP_TYPE_CPUMAP, + BPF_MAP_TYPE_XSKMAP, + BPF_MAP_TYPE_SOCKHASH, + BPF_MAP_TYPE_CGROUP_STORAGE, + BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, + BPF_MAP_TYPE_QUEUE, + BPF_MAP_TYPE_STACK, +}; + +/* Note that tracing related programs such as + * BPF_PROG_TYPE_{KPROBE,TRACEPOINT,PERF_EVENT,RAW_TRACEPOINT} + * are not subject to a stable API since kernel internal data + * structures can change from release to release and may + * therefore break existing tracing BPF programs. Tracing BPF + * programs correspond to /a/ specific kernel which is to be + * analyzed, and not /a/ specific kernel /and/ all future ones. + */ +enum bpf_prog_type { + BPF_PROG_TYPE_UNSPEC, + BPF_PROG_TYPE_SOCKET_FILTER, + BPF_PROG_TYPE_KPROBE, + BPF_PROG_TYPE_SCHED_CLS, + BPF_PROG_TYPE_SCHED_ACT, + BPF_PROG_TYPE_TRACEPOINT, + BPF_PROG_TYPE_XDP, + BPF_PROG_TYPE_PERF_EVENT, + BPF_PROG_TYPE_CGROUP_SKB, + BPF_PROG_TYPE_CGROUP_SOCK, + BPF_PROG_TYPE_LWT_IN, + BPF_PROG_TYPE_LWT_OUT, + BPF_PROG_TYPE_LWT_XMIT, + BPF_PROG_TYPE_SOCK_OPS, + BPF_PROG_TYPE_SK_SKB, + BPF_PROG_TYPE_CGROUP_DEVICE, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_RAW_TRACEPOINT, + BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_PROG_TYPE_LWT_SEG6LOCAL, + BPF_PROG_TYPE_LIRC_MODE2, + BPF_PROG_TYPE_SK_REUSEPORT, + BPF_PROG_TYPE_FLOW_DISSECTOR, +}; + +enum bpf_attach_type { + BPF_CGROUP_INET_INGRESS, + BPF_CGROUP_INET_EGRESS, + BPF_CGROUP_INET_SOCK_CREATE, + BPF_CGROUP_SOCK_OPS, + BPF_SK_SKB_STREAM_PARSER, + BPF_SK_SKB_STREAM_VERDICT, + BPF_CGROUP_DEVICE, + BPF_SK_MSG_VERDICT, + BPF_CGROUP_INET4_BIND, + BPF_CGROUP_INET6_BIND, + BPF_CGROUP_INET4_CONNECT, + BPF_CGROUP_INET6_CONNECT, + BPF_CGROUP_INET4_POST_BIND, + BPF_CGROUP_INET6_POST_BIND, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + BPF_LIRC_MODE2, + BPF_FLOW_DISSECTOR, + __MAX_BPF_ATTACH_TYPE +}; + +#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE + +/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command + * + * NONE(default): No further bpf programs allowed in the subtree. + * + * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, + * the program in this cgroup yields to sub-cgroup program. + * + * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, + * that cgroup program gets run in addition to the program in this cgroup. + * + * Only one program is allowed to be attached to a cgroup with + * NONE or BPF_F_ALLOW_OVERRIDE flag. + * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will + * release old program and attach the new one. Attach flags has to match. + * + * Multiple programs are allowed to be attached to a cgroup with + * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order + * (those that were attached first, run first) + * The programs of sub-cgroup are executed first, then programs of + * this cgroup and then programs of parent cgroup. + * When children program makes decision (like picking TCP CA or sock bind) + * parent program has a chance to override it. + * + * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups. + * A cgroup with NONE doesn't allow any programs in sub-cgroups. + * Ex1: + * cgrp1 (MULTI progs A, B) -> + * cgrp2 (OVERRIDE prog C) -> + * cgrp3 (MULTI prog D) -> + * cgrp4 (OVERRIDE prog E) -> + * cgrp5 (NONE prog F) + * the event in cgrp5 triggers execution of F,D,A,B in that order. + * if prog F is detached, the execution is E,D,A,B + * if prog F and D are detached, the execution is E,A,B + * if prog F, E and D are detached, the execution is C,A,B + * + * All eligible programs are executed regardless of return code from + * earlier programs. + */ +#define BPF_F_ALLOW_OVERRIDE (1U << 0) +#define BPF_F_ALLOW_MULTI (1U << 1) + +/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the + * verifier will perform strict alignment checking as if the kernel + * has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set, + * and NET_IP_ALIGN defined to 2. + */ +#define BPF_F_STRICT_ALIGNMENT (1U << 0) + +/* If BPF_F_ANY_ALIGNMENT is used in BPF_PROF_LOAD command, the + * verifier will allow any alignment whatsoever. On platforms + * with strict alignment requirements for loads ands stores (such + * as sparc and mips) the verifier validates that all loads and + * stores provably follow this requirement. This flag turns that + * checking and enforcement off. + * + * It is mostly used for testing when we want to validate the + * context and memory access aspects of the verifier, but because + * of an unaligned access the alignment check would trigger before + * the one we are interested in. + */ +#define BPF_F_ANY_ALIGNMENT (1U << 1) + +/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */ +#define BPF_PSEUDO_MAP_FD 1 + +/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative + * offset to another bpf function + */ +#define BPF_PSEUDO_CALL 1 + +/* flags for BPF_MAP_UPDATE_ELEM command */ +#define BPF_ANY 0 /* create new element or update existing */ +#define BPF_NOEXIST 1 /* create new element if it didn't exist */ +#define BPF_EXIST 2 /* update existing element */ +#define BPF_F_LOCK 4 /* spin_lock-ed map_lookup/map_update */ + +/* flags for BPF_MAP_CREATE command */ +#define BPF_F_NO_PREALLOC (1U << 0) +/* Instead of having one common LRU list in the + * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list + * which can scale and perform better. + * Note, the LRU nodes (including free nodes) cannot be moved + * across different LRU lists. + */ +#define BPF_F_NO_COMMON_LRU (1U << 1) +/* Specify numa node during map creation */ +#define BPF_F_NUMA_NODE (1U << 2) + +#define BPF_OBJ_NAME_LEN 16U + +/* Flags for accessing BPF object */ +#define BPF_F_RDONLY (1U << 3) +#define BPF_F_WRONLY (1U << 4) + +/* Flag for stack_map, store build_id+offset instead of pointer */ +#define BPF_F_STACK_BUILD_ID (1U << 5) + +/* Zero-initialize hash function seed. This should only be used for testing. */ +#define BPF_F_ZERO_SEED (1U << 6) + +/* flags for BPF_PROG_QUERY */ +#define BPF_F_QUERY_EFFECTIVE (1U << 0) + +enum bpf_stack_build_id_status { + /* user space need an empty entry to identify end of a trace */ + BPF_STACK_BUILD_ID_EMPTY = 0, + /* with valid build_id and offset */ + BPF_STACK_BUILD_ID_VALID = 1, + /* couldn't get build_id, fallback to ip */ + BPF_STACK_BUILD_ID_IP = 2, +}; + +#define BPF_BUILD_ID_SIZE 20 +struct bpf_stack_build_id { + __s32 status; + unsigned char build_id[BPF_BUILD_ID_SIZE]; + union { + __u64 offset; + __u64 ip; + }; +}; + +union bpf_attr { + struct { /* anonymous struct used by BPF_MAP_CREATE command */ + __u32 map_type; /* one of enum bpf_map_type */ + __u32 key_size; /* size of key in bytes */ + __u32 value_size; /* size of value in bytes */ + __u32 max_entries; /* max number of entries in a map */ + __u32 map_flags; /* BPF_MAP_CREATE related + * flags defined above. + */ + __u32 inner_map_fd; /* fd pointing to the inner map */ + __u32 numa_node; /* numa node (effective only if + * BPF_F_NUMA_NODE is set). + */ + char map_name[BPF_OBJ_NAME_LEN]; + __u32 map_ifindex; /* ifindex of netdev to create on */ + __u32 btf_fd; /* fd pointing to a BTF type data */ + __u32 btf_key_type_id; /* BTF type_id of the key */ + __u32 btf_value_type_id; /* BTF type_id of the value */ + }; + + struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ + __u32 map_fd; + __aligned_u64 key; + union { + __aligned_u64 value; + __aligned_u64 next_key; + }; + __u64 flags; + }; + + struct { /* anonymous struct used by BPF_PROG_LOAD command */ + __u32 prog_type; /* one of enum bpf_prog_type */ + __u32 insn_cnt; + __aligned_u64 insns; + __aligned_u64 license; + __u32 log_level; /* verbosity level of verifier */ + __u32 log_size; /* size of user buffer */ + __aligned_u64 log_buf; /* user supplied buffer */ + __u32 kern_version; /* not used */ + __u32 prog_flags; + char prog_name[BPF_OBJ_NAME_LEN]; + __u32 prog_ifindex; /* ifindex of netdev to prep for */ + /* For some prog types expected attach type must be known at + * load time to verify attach type specific parts of prog + * (context accesses, allowed helpers, etc). + */ + __u32 expected_attach_type; + __u32 prog_btf_fd; /* fd pointing to BTF type data */ + __u32 func_info_rec_size; /* userspace bpf_func_info size */ + __aligned_u64 func_info; /* func info */ + __u32 func_info_cnt; /* number of bpf_func_info records */ + __u32 line_info_rec_size; /* userspace bpf_line_info size */ + __aligned_u64 line_info; /* line info */ + __u32 line_info_cnt; /* number of bpf_line_info records */ + }; + + struct { /* anonymous struct used by BPF_OBJ_* commands */ + __aligned_u64 pathname; + __u32 bpf_fd; + __u32 file_flags; + }; + + struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ + __u32 target_fd; /* container object to attach to */ + __u32 attach_bpf_fd; /* eBPF program to attach */ + __u32 attach_type; + __u32 attach_flags; + }; + + struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */ + __u32 prog_fd; + __u32 retval; + __u32 data_size_in; /* input: len of data_in */ + __u32 data_size_out; /* input/output: len of data_out + * returns ENOSPC if data_out + * is too small. + */ + __aligned_u64 data_in; + __aligned_u64 data_out; + __u32 repeat; + __u32 duration; + } test; + + struct { /* anonymous struct used by BPF_*_GET_*_ID */ + union { + __u32 start_id; + __u32 prog_id; + __u32 map_id; + __u32 btf_id; + }; + __u32 next_id; + __u32 open_flags; + }; + + struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */ + __u32 bpf_fd; + __u32 info_len; + __aligned_u64 info; + } info; + + struct { /* anonymous struct used by BPF_PROG_QUERY command */ + __u32 target_fd; /* container object to query */ + __u32 attach_type; + __u32 query_flags; + __u32 attach_flags; + __aligned_u64 prog_ids; + __u32 prog_cnt; + } query; + + struct { + __u64 name; + __u32 prog_fd; + } raw_tracepoint; + + struct { /* anonymous struct for BPF_BTF_LOAD */ + __aligned_u64 btf; + __aligned_u64 btf_log_buf; + __u32 btf_size; + __u32 btf_log_size; + __u32 btf_log_level; + }; + + struct { + __u32 pid; /* input: pid */ + __u32 fd; /* input: fd */ + __u32 flags; /* input: flags */ + __u32 buf_len; /* input/output: buf len */ + __aligned_u64 buf; /* input/output: + * tp_name for tracepoint + * symbol for kprobe + * filename for uprobe + */ + __u32 prog_id; /* output: prod_id */ + __u32 fd_type; /* output: BPF_FD_TYPE_* */ + __u64 probe_offset; /* output: probe_offset */ + __u64 probe_addr; /* output: probe_addr */ + } task_fd_query; +} __attribute__((aligned(8))); + +/* The description below is an attempt at providing documentation to eBPF + * developers about the multiple available eBPF helper functions. It can be + * parsed and used to produce a manual page. The workflow is the following, + * and requires the rst2man utility: + * + * $ ./scripts/bpf_helpers_doc.py \ + * --filename include/uapi/linux/bpf.h > /tmp/bpf-helpers.rst + * $ rst2man /tmp/bpf-helpers.rst > /tmp/bpf-helpers.7 + * $ man /tmp/bpf-helpers.7 + * + * Note that in order to produce this external documentation, some RST + * formatting is used in the descriptions to get "bold" and "italics" in + * manual pages. Also note that the few trailing white spaces are + * intentional, removing them would break paragraphs for rst2man. + * + * Start of BPF helper function descriptions: + * + * void *bpf_map_lookup_elem(struct bpf_map *map, const void *key) + * Description + * Perform a lookup in *map* for an entry associated to *key*. + * Return + * Map value associated to *key*, or **NULL** if no entry was + * found. + * + * int bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags) + * Description + * Add or update the value of the entry associated to *key* in + * *map* with *value*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * Flag value **BPF_NOEXIST** cannot be used for maps of types + * **BPF_MAP_TYPE_ARRAY** or **BPF_MAP_TYPE_PERCPU_ARRAY** (all + * elements always exist), the helper would return an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_delete_elem(struct bpf_map *map, const void *key) + * Description + * Delete entry with *key* from *map*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read(void *dst, u32 size, const void *src) + * Description + * For tracing programs, safely attempt to read *size* bytes from + * address *src* and store the data in *dst*. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_ktime_get_ns(void) + * Description + * Return the time elapsed since system boot, in nanoseconds. + * Return + * Current *ktime*. + * + * int bpf_trace_printk(const char *fmt, u32 fmt_size, ...) + * Description + * This helper is a "printk()-like" facility for debugging. It + * prints a message defined by format *fmt* (of size *fmt_size*) + * to file *\/sys/kernel/debug/tracing/trace* from DebugFS, if + * available. It can take up to three additional **u64** + * arguments (as an eBPF helpers, the total number of arguments is + * limited to five). + * + * Each time the helper is called, it appends a line to the trace. + * The format of the trace is customizable, and the exact output + * one will get depends on the options set in + * *\/sys/kernel/debug/tracing/trace_options* (see also the + * *README* file under the same directory). However, it usually + * defaults to something like: + * + * :: + * + * telnet-470 [001] .N.. 419421.045894: 0x00000001: <formatted msg> + * + * In the above: + * + * * ``telnet`` is the name of the current task. + * * ``470`` is the PID of the current task. + * * ``001`` is the CPU number on which the task is + * running. + * * In ``.N..``, each character refers to a set of + * options (whether irqs are enabled, scheduling + * options, whether hard/softirqs are running, level of + * preempt_disabled respectively). **N** means that + * **TIF_NEED_RESCHED** and **PREEMPT_NEED_RESCHED** + * are set. + * * ``419421.045894`` is a timestamp. + * * ``0x00000001`` is a fake value used by BPF for the + * instruction pointer register. + * * ``<formatted msg>`` is the message formatted with + * *fmt*. + * + * The conversion specifiers supported by *fmt* are similar, but + * more limited than for printk(). They are **%d**, **%i**, + * **%u**, **%x**, **%ld**, **%li**, **%lu**, **%lx**, **%lld**, + * **%lli**, **%llu**, **%llx**, **%p**, **%s**. No modifier (size + * of field, padding with zeroes, etc.) is available, and the + * helper will return **-EINVAL** (but print nothing) if it + * encounters an unknown specifier. + * + * Also, note that **bpf_trace_printk**\ () is slow, and should + * only be used for debugging purposes. For this reason, a notice + * bloc (spanning several lines) is printed to kernel logs and + * states that the helper should not be used "for production use" + * the first time this helper is used (or more precisely, when + * **trace_printk**\ () buffers are allocated). For passing values + * to user space, perf events should be preferred. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. + * + * u32 bpf_get_prandom_u32(void) + * Description + * Get a pseudo-random number. + * + * From a security point of view, this helper uses its own + * pseudo-random internal state, and cannot be used to infer the + * seed of other random functions in the kernel. However, it is + * essential to note that the generator used by the helper is not + * cryptographically secure. + * Return + * A random 32-bit unsigned value. + * + * u32 bpf_get_smp_processor_id(void) + * Description + * Get the SMP (symmetric multiprocessing) processor id. Note that + * all programs run with preemption disabled, which means that the + * SMP processor id is stable during all the execution of the + * program. + * Return + * The SMP id of the processor running the program. + * + * int bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) + * Description + * Store *len* bytes from address *from* into the packet + * associated to *skb*, at *offset*. *flags* are a combination of + * **BPF_F_RECOMPUTE_CSUM** (automatically recompute the + * checksum for the packet after storing the bytes) and + * **BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\ + * **->swhash** and *skb*\ **->l4hash** to 0). + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_l3_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 size) + * Description + * Recompute the layer 3 (e.g. IP) checksum for the packet + * associated to *skb*. Computation is incremental, so the helper + * must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored in *size*. + * Alternatively, it is possible to store the difference between + * the previous and the new values of the header field in *to*, by + * setting *from* and *size* to 0. For both methods, *offset* + * indicates the location of the IP checksum within the packet. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_l4_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 flags) + * Description + * Recompute the layer 4 (e.g. TCP, UDP or ICMP) checksum for the + * packet associated to *skb*. Computation is incremental, so the + * helper must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored on the lowest + * four bits of *flags*. Alternatively, it is possible to store + * the difference between the previous and the new values of the + * header field in *to*, by setting *from* and the four lowest + * bits of *flags* to 0. For both methods, *offset* indicates the + * location of the IP checksum within the packet. In addition to + * the size of the field, *flags* can be added (bitwise OR) actual + * flags. With **BPF_F_MARK_MANGLED_0**, a null checksum is left + * untouched (unless **BPF_F_MARK_ENFORCE** is added as well), and + * for updates resulting in a null checksum the value is set to + * **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates + * the checksum is to be computed against a pseudo-header. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_tail_call(void *ctx, struct bpf_map *prog_array_map, u32 index) + * Description + * This special helper is used to trigger a "tail call", or in + * other words, to jump into another eBPF program. The same stack + * frame is used (but values on stack and in registers for the + * caller are not accessible to the callee). This mechanism allows + * for program chaining, either for raising the maximum number of + * available eBPF instructions, or to execute given programs in + * conditional blocks. For security reasons, there is an upper + * limit to the number of successive tail calls that can be + * performed. + * + * Upon call of this helper, the program attempts to jump into a + * program referenced at index *index* in *prog_array_map*, a + * special map of type **BPF_MAP_TYPE_PROG_ARRAY**, and passes + * *ctx*, a pointer to the context. + * + * If the call succeeds, the kernel immediately runs the first + * instruction of the new program. This is not a function call, + * and it never returns to the previous program. If the call + * fails, then the helper has no effect, and the caller continues + * to run its subsequent instructions. A call can fail if the + * destination program for the jump does not exist (i.e. *index* + * is superior to the number of entries in *prog_array_map*), or + * if the maximum number of tail calls has been reached for this + * chain of programs. This limit is defined in the kernel by the + * macro **MAX_TAIL_CALL_CNT** (not accessible to user space), + * which is currently set to 32. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_clone_redirect(struct sk_buff *skb, u32 ifindex, u64 flags) + * Description + * Clone and redirect the packet associated to *skb* to another + * net device of index *ifindex*. Both ingress and egress + * interfaces can be used for redirection. The **BPF_F_INGRESS** + * value in *flags* is used to make the distinction (ingress path + * is selected if the flag is present, egress path otherwise). + * This is the only flag supported for now. + * + * In comparison with **bpf_redirect**\ () helper, + * **bpf_clone_redirect**\ () has the associated cost of + * duplicating the packet buffer, but this can be executed out of + * the eBPF program. Conversely, **bpf_redirect**\ () is more + * efficient, but it is handled through an action code where the + * redirection happens only after the eBPF program has returned. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_get_current_pid_tgid(void) + * Return + * A 64-bit integer containing the current tgid and pid, and + * created as such: + * *current_task*\ **->tgid << 32 \|** + * *current_task*\ **->pid**. + * + * u64 bpf_get_current_uid_gid(void) + * Return + * A 64-bit integer containing the current GID and UID, and + * created as such: *current_gid* **<< 32 \|** *current_uid*. + * + * int bpf_get_current_comm(char *buf, u32 size_of_buf) + * Description + * Copy the **comm** attribute of the current task into *buf* of + * *size_of_buf*. The **comm** attribute contains the name of + * the executable (excluding the path) for the current task. The + * *size_of_buf* must be strictly positive. On success, the + * helper makes sure that the *buf* is NUL-terminated. On failure, + * it is filled with zeroes. + * Return + * 0 on success, or a negative error in case of failure. + * + * u32 bpf_get_cgroup_classid(struct sk_buff *skb) + * Description + * Retrieve the classid for the current task, i.e. for the net_cls + * cgroup to which *skb* belongs. + * + * This helper can be used on TC egress path, but not on ingress. + * + * The net_cls cgroup provides an interface to tag network packets + * based on a user-provided identifier for all traffic coming from + * the tasks belonging to the related cgroup. See also the related + * kernel documentation, available from the Linux sources in file + * *Documentation/cgroup-v1/net_cls.txt*. + * + * The Linux kernel has two versions for cgroups: there are + * cgroups v1 and cgroups v2. Both are available to users, who can + * use a mixture of them, but note that the net_cls cgroup is for + * cgroup v1 only. This makes it incompatible with BPF programs + * run on cgroups, which is a cgroup-v2-only feature (a socket can + * only hold data for one version of cgroups at a time). + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_CGROUP_NET_CLASSID** configuration option set to + * "**y**" or to "**m**". + * Return + * The classid, or 0 for the default unconfigured classid. + * + * int bpf_skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) + * Description + * Push a *vlan_tci* (VLAN tag control information) of protocol + * *vlan_proto* to the packet associated to *skb*, then update + * the checksum. Note that if *vlan_proto* is different from + * **ETH_P_8021Q** and **ETH_P_8021AD**, it is considered to + * be **ETH_P_8021Q**. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_vlan_pop(struct sk_buff *skb) + * Description + * Pop a VLAN header from the packet associated to *skb*. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_get_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * Description + * Get tunnel metadata. This helper takes a pointer *key* to an + * empty **struct bpf_tunnel_key** of **size**, that will be + * filled with tunnel metadata for the packet associated to *skb*. + * The *flags* can be set to **BPF_F_TUNINFO_IPV6**, which + * indicates that the tunnel is based on IPv6 protocol instead of + * IPv4. + * + * The **struct bpf_tunnel_key** is an object that generalizes the + * principal parameters used by various tunneling protocols into a + * single struct. This way, it can be used to easily make a + * decision based on the contents of the encapsulation header, + * "summarized" in this struct. In particular, it holds the IP + * address of the remote end (IPv4 or IPv6, depending on the case) + * in *key*\ **->remote_ipv4** or *key*\ **->remote_ipv6**. Also, + * this struct exposes the *key*\ **->tunnel_id**, which is + * generally mapped to a VNI (Virtual Network Identifier), making + * it programmable together with the **bpf_skb_set_tunnel_key**\ + * () helper. + * + * Let's imagine that the following code is part of a program + * attached to the TC ingress interface, on one end of a GRE + * tunnel, and is supposed to filter out all messages coming from + * remote ends with IPv4 address other than 10.0.0.1: + * + * :: + * + * int ret; + * struct bpf_tunnel_key key = {}; + * + * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + * if (ret < 0) + * return TC_ACT_SHOT; // drop packet + * + * if (key.remote_ipv4 != 0x0a000001) + * return TC_ACT_SHOT; // drop packet + * + * return TC_ACT_OK; // accept packet + * + * This interface can also be used with all encapsulation devices + * that can operate in "collect metadata" mode: instead of having + * one network device per specific configuration, the "collect + * metadata" mode only requires a single device where the + * configuration can be extracted from this helper. + * + * This can be used together with various tunnels such as VXLan, + * Geneve, GRE or IP in IP (IPIP). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_set_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * Description + * Populate tunnel metadata for packet associated to *skb.* The + * tunnel metadata is set to the contents of *key*, of *size*. The + * *flags* can be set to a combination of the following values: + * + * **BPF_F_TUNINFO_IPV6** + * Indicate that the tunnel is based on IPv6 protocol + * instead of IPv4. + * **BPF_F_ZERO_CSUM_TX** + * For IPv4 packets, add a flag to tunnel metadata + * indicating that checksum computation should be skipped + * and checksum set to zeroes. + * **BPF_F_DONT_FRAGMENT** + * Add a flag to tunnel metadata indicating that the + * packet should not be fragmented. + * **BPF_F_SEQ_NUMBER** + * Add a flag to tunnel metadata indicating that a + * sequence number should be added to tunnel header before + * sending the packet. This flag was added for GRE + * encapsulation, but might be used with other protocols + * as well in the future. + * + * Here is a typical usage on the transmit path: + * + * :: + * + * struct bpf_tunnel_key key; + * populate key ... + * bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0); + * bpf_clone_redirect(skb, vxlan_dev_ifindex, 0); + * + * See also the description of the **bpf_skb_get_tunnel_key**\ () + * helper for additional information. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_perf_event_read(struct bpf_map *map, u64 flags) + * Description + * Read the value of a perf event counter. This helper relies on a + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of + * the perf event counter is selected when *map* is updated with + * perf event file descriptors. The *map* is an array whose size + * is the number of available CPUs, and each cell contains a value + * relative to one CPU. The value to retrieve is indicated by + * *flags*, that contains the index of the CPU to look up, masked + * with **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * Note that before Linux 4.13, only hardware perf event can be + * retrieved. + * + * Also, be aware that the newer helper + * **bpf_perf_event_read_value**\ () is recommended over + * **bpf_perf_event_read**\ () in general. The latter has some ABI + * quirks where error and counter value are used as a return code + * (which is wrong to do since ranges may overlap). This issue is + * fixed with **bpf_perf_event_read_value**\ (), which at the same + * time provides more features over the **bpf_perf_event_read**\ + * () interface. Please refer to the description of + * **bpf_perf_event_read_value**\ () for details. + * Return + * The value of the perf event counter read from the map, or a + * negative error code in case of failure. + * + * int bpf_redirect(u32 ifindex, u64 flags) + * Description + * Redirect the packet to another net device of index *ifindex*. + * This helper is somewhat similar to **bpf_clone_redirect**\ + * (), except that the packet is not cloned, which provides + * increased performance. + * + * Except for XDP, both ingress and egress interfaces can be used + * for redirection. The **BPF_F_INGRESS** value in *flags* is used + * to make the distinction (ingress path is selected if the flag + * is present, egress path otherwise). Currently, XDP only + * supports redirection to the egress interface, and accepts no + * flag at all. + * + * The same effect can be attained with the more generic + * **bpf_redirect_map**\ (), which requires specific maps to be + * used but offers better performance. + * Return + * For XDP, the helper returns **XDP_REDIRECT** on success or + * **XDP_ABORTED** on error. For other program types, the values + * are **TC_ACT_REDIRECT** on success or **TC_ACT_SHOT** on + * error. + * + * u32 bpf_get_route_realm(struct sk_buff *skb) + * Description + * Retrieve the realm or the route, that is to say the + * **tclassid** field of the destination for the *skb*. The + * indentifier retrieved is a user-provided tag, similar to the + * one used with the net_cls cgroup (see description for + * **bpf_get_cgroup_classid**\ () helper), but here this tag is + * held by a route (a destination entry), not by a task. + * + * Retrieving this identifier works with the clsact TC egress hook + * (see also **tc-bpf(8)**), or alternatively on conventional + * classful egress qdiscs, but not on TC ingress path. In case of + * clsact TC egress hook, this has the advantage that, internally, + * the destination entry has not been dropped yet in the transmit + * path. Therefore, the destination entry does not need to be + * artificially held via **netif_keep_dst**\ () for a classful + * qdisc until the *skb* is freed. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_IP_ROUTE_CLASSID** configuration option. + * Return + * The realm of the route for the packet associated to *skb*, or 0 + * if none was found. + * + * int bpf_perf_event_output(struct pt_reg *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * Description + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * The context of the program *ctx* needs also be passed to the + * helper. + * + * On user space, a program willing to read the values needs to + * call **perf_event_open**\ () on the perf event (either for + * one or for all CPUs) and to store the file descriptor into the + * *map*. This must be done before the eBPF program can send data + * into it. An example is available in file + * *samples/bpf/trace_output_user.c* in the Linux kernel source + * tree (the eBPF program counterpart is in + * *samples/bpf/trace_output_kern.c*). + * + * **bpf_perf_event_output**\ () achieves better performance + * than **bpf_trace_printk**\ () for sharing data with user + * space, and is much better suitable for streaming data from eBPF + * programs. + * + * Note that this helper is not restricted to tracing use cases + * and can be used with programs attached to TC or XDP as well, + * where it allows for passing data to user space listeners. Data + * can be: + * + * * Only custom structs, + * * Only the packet payload, or + * * A combination of both. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len) + * Description + * This helper was provided as an easy way to load data from a + * packet. It can be used to load *len* bytes from *offset* from + * the packet associated to *skb*, into the buffer pointed by + * *to*. + * + * Since Linux 4.7, usage of this helper has mostly been replaced + * by "direct packet access", enabling packet data to be + * manipulated with *skb*\ **->data** and *skb*\ **->data_end** + * pointing respectively to the first byte of packet data and to + * the byte after the last byte of packet data. However, it + * remains useful if one wishes to read large quantities of data + * at once from a packet into the eBPF stack. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_get_stackid(struct pt_reg *ctx, struct bpf_map *map, u64 flags) + * Description + * Walk a user or a kernel stack and return its id. To achieve + * this, the helper needs *ctx*, which is a pointer to the context + * on which the tracing program is executed, and a pointer to a + * *map* of type **BPF_MAP_TYPE_STACK_TRACE**. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * a combination of the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_FAST_STACK_CMP** + * Compare stacks by hash only. + * **BPF_F_REUSE_STACKID** + * If two different stacks hash into the same *stackid*, + * discard the old one. + * + * The stack id retrieved is a 32 bit long integer handle which + * can be further combined with other data (including other stack + * ids) and used as a key into maps. This can be useful for + * generating a variety of graphs (such as flame graphs or off-cpu + * graphs). + * + * For walking a stack, this helper is an improvement over + * **bpf_probe_read**\ (), which can be used with unrolled loops + * but is not efficient and consumes a lot of eBPF instructions. + * Instead, **bpf_get_stackid**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack=<new value> + * Return + * The positive or null stack id on success, or a negative error + * in case of failure. + * + * s64 bpf_csum_diff(__be32 *from, u32 from_size, __be32 *to, u32 to_size, __wsum seed) + * Description + * Compute a checksum difference, from the raw buffer pointed by + * *from*, of length *from_size* (that must be a multiple of 4), + * towards the raw buffer pointed by *to*, of size *to_size* + * (same remark). An optional *seed* can be added to the value + * (this can be cascaded, the seed may come from a previous call + * to the helper). + * + * This is flexible enough to be used in several ways: + * + * * With *from_size* == 0, *to_size* > 0 and *seed* set to + * checksum, it can be used when pushing new data. + * * With *from_size* > 0, *to_size* == 0 and *seed* set to + * checksum, it can be used when removing data from a packet. + * * With *from_size* > 0, *to_size* > 0 and *seed* set to 0, it + * can be used to compute a diff. Note that *from_size* and + * *to_size* do not need to be equal. + * + * This helper can be used in combination with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ (), to + * which one can feed in the difference computed with + * **bpf_csum_diff**\ (). + * Return + * The checksum result, or a negative error code in case of + * failure. + * + * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size) + * Description + * Retrieve tunnel options metadata for the packet associated to + * *skb*, and store the raw tunnel option data to the buffer *opt* + * of *size*. + * + * This helper can be used with encapsulation devices that can + * operate in "collect metadata" mode (please refer to the related + * note in the description of **bpf_skb_get_tunnel_key**\ () for + * more details). A particular example where this can be used is + * in combination with the Geneve encapsulation protocol, where it + * allows for pushing (with **bpf_skb_get_tunnel_opt**\ () helper) + * and retrieving arbitrary TLVs (Type-Length-Value headers) from + * the eBPF program. This allows for full customization of these + * headers. + * Return + * The size of the option data retrieved. + * + * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size) + * Description + * Set tunnel options metadata for the packet associated to *skb* + * to the option data contained in the raw buffer *opt* of *size*. + * + * See also the description of the **bpf_skb_get_tunnel_opt**\ () + * helper for additional information. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_change_proto(struct sk_buff *skb, __be16 proto, u64 flags) + * Description + * Change the protocol of the *skb* to *proto*. Currently + * supported are transition from IPv4 to IPv6, and from IPv6 to + * IPv4. The helper takes care of the groundwork for the + * transition, including resizing the socket buffer. The eBPF + * program is expected to fill the new headers, if any, via + * **skb_store_bytes**\ () and to recompute the checksums with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ + * (). The main case for this helper is to perform NAT64 + * operations out of an eBPF program. + * + * Internally, the GSO type is marked as dodgy so that headers are + * checked and segments are recalculated by the GSO/GRO engine. + * The size for GSO target is adapted as well. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_change_type(struct sk_buff *skb, u32 type) + * Description + * Change the packet type for the packet associated to *skb*. This + * comes down to setting *skb*\ **->pkt_type** to *type*, except + * the eBPF program does not have a write access to *skb*\ + * **->pkt_type** beside this helper. Using a helper here allows + * for graceful handling of errors. + * + * The major use case is to change incoming *skb*s to + * **PACKET_HOST** in a programmatic way instead of having to + * recirculate via **redirect**\ (..., **BPF_F_INGRESS**), for + * example. + * + * Note that *type* only allows certain values. At this time, they + * are: + * + * **PACKET_HOST** + * Packet is for us. + * **PACKET_BROADCAST** + * Send packet to all. + * **PACKET_MULTICAST** + * Send packet to group. + * **PACKET_OTHERHOST** + * Send packet to someone else. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_under_cgroup(struct sk_buff *skb, struct bpf_map *map, u32 index) + * Description + * Check whether *skb* is a descendant of the cgroup2 held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * Return + * The return value depends on the result of the test, and can be: + * + * * 0, if the *skb* failed the cgroup2 descendant test. + * * 1, if the *skb* succeeded the cgroup2 descendant test. + * * A negative error code, if an error occurred. + * + * u32 bpf_get_hash_recalc(struct sk_buff *skb) + * Description + * Retrieve the hash of the packet, *skb*\ **->hash**. If it is + * not set, in particular if the hash was cleared due to mangling, + * recompute this hash. Later accesses to the hash can be done + * directly with *skb*\ **->hash**. + * + * Calling **bpf_set_hash_invalid**\ (), changing a packet + * prototype with **bpf_skb_change_proto**\ (), or calling + * **bpf_skb_store_bytes**\ () with the + * **BPF_F_INVALIDATE_HASH** are actions susceptible to clear + * the hash and to trigger a new computation for the next call to + * **bpf_get_hash_recalc**\ (). + * Return + * The 32-bit hash. + * + * u64 bpf_get_current_task(void) + * Return + * A pointer to the current task struct. + * + * int bpf_probe_write_user(void *dst, const void *src, u32 len) + * Description + * Attempt in a safe way to write *len* bytes from the buffer + * *src* to *dst* in memory. It only works for threads that are in + * user context, and *dst* must be a valid user space address. + * + * This helper should not be used to implement any kind of + * security mechanism because of TOC-TOU attacks, but rather to + * debug, divert, and manipulate execution of semi-cooperative + * processes. + * + * Keep in mind that this feature is meant for experiments, and it + * has a risk of crashing the system and running programs. + * Therefore, when an eBPF program using this helper is attached, + * a warning including PID and process name is printed to kernel + * logs. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_current_task_under_cgroup(struct bpf_map *map, u32 index) + * Description + * Check whether the probe is being run is the context of a given + * subset of the cgroup2 hierarchy. The cgroup2 to test is held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * Return + * The return value depends on the result of the test, and can be: + * + * * 0, if the *skb* task belongs to the cgroup2. + * * 1, if the *skb* task does not belong to the cgroup2. + * * A negative error code, if an error occurred. + * + * int bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) + * Description + * Resize (trim or grow) the packet associated to *skb* to the + * new *len*. The *flags* are reserved for future usage, and must + * be left at zero. + * + * The basic idea is that the helper performs the needed work to + * change the size of the packet, then the eBPF program rewrites + * the rest via helpers like **bpf_skb_store_bytes**\ (), + * **bpf_l3_csum_replace**\ (), **bpf_l3_csum_replace**\ () + * and others. This helper is a slow path utility intended for + * replies with control messages. And because it is targeted for + * slow path, the helper itself can afford to be slow: it + * implicitly linearizes, unclones and drops offloads from the + * *skb*. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_pull_data(struct sk_buff *skb, u32 len) + * Description + * Pull in non-linear data in case the *skb* is non-linear and not + * all of *len* are part of the linear section. Make *len* bytes + * from *skb* readable and writable. If a zero value is passed for + * *len*, then the whole length of the *skb* is pulled. + * + * This helper is only needed for reading and writing with direct + * packet access. + * + * For direct packet access, testing that offsets to access + * are within packet boundaries (test on *skb*\ **->data_end**) is + * susceptible to fail if offsets are invalid, or if the requested + * data is in non-linear parts of the *skb*. On failure the + * program can just bail out, or in the case of a non-linear + * buffer, use a helper to make the data available. The + * **bpf_skb_load_bytes**\ () helper is a first solution to access + * the data. Another one consists in using **bpf_skb_pull_data** + * to pull in once the non-linear parts, then retesting and + * eventually access the data. + * + * At the same time, this also makes sure the *skb* is uncloned, + * which is a necessary condition for direct write. As this needs + * to be an invariant for the write part only, the verifier + * detects writes and adds a prologue that is calling + * **bpf_skb_pull_data()** to effectively unclone the *skb* from + * the very beginning in case it is indeed cloned. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * s64 bpf_csum_update(struct sk_buff *skb, __wsum csum) + * Description + * Add the checksum *csum* into *skb*\ **->csum** in case the + * driver has supplied a checksum for the entire packet into that + * field. Return an error otherwise. This helper is intended to be + * used in combination with **bpf_csum_diff**\ (), in particular + * when the checksum needs to be updated after data has been + * written into the packet through direct packet access. + * Return + * The checksum on success, or a negative error code in case of + * failure. + * + * void bpf_set_hash_invalid(struct sk_buff *skb) + * Description + * Invalidate the current *skb*\ **->hash**. It can be used after + * mangling on headers through direct packet access, in order to + * indicate that the hash is outdated and to trigger a + * recalculation the next time the kernel tries to access this + * hash or when the **bpf_get_hash_recalc**\ () helper is called. + * + * int bpf_get_numa_node_id(void) + * Description + * Return the id of the current NUMA node. The primary use case + * for this helper is the selection of sockets for the local NUMA + * node, when the program is attached to sockets using the + * **SO_ATTACH_REUSEPORT_EBPF** option (see also **socket(7)**), + * but the helper is also available to other eBPF program types, + * similarly to **bpf_get_smp_processor_id**\ (). + * Return + * The id of current NUMA node. + * + * int bpf_skb_change_head(struct sk_buff *skb, u32 len, u64 flags) + * Description + * Grows headroom of packet associated to *skb* and adjusts the + * offset of the MAC header accordingly, adding *len* bytes of + * space. It automatically extends and reallocates memory as + * required. + * + * This helper can be used on a layer 3 *skb* to push a MAC header + * for redirection into a layer 2 device. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_head(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust (move) *xdp_md*\ **->data** by *delta* bytes. Note that + * it is possible to use a negative value for *delta*. This helper + * can be used to prepare the packet for pushing or popping + * headers. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr) + * Description + * Copy a NUL terminated string from an unsafe address + * *unsafe_ptr* to *dst*. The *size* should include the + * terminating NUL byte. In case the string length is smaller than + * *size*, the target is not padded with further NUL bytes. If the + * string length is larger than *size*, just *size*-1 bytes are + * copied and the last byte is set to NUL. + * + * On success, the length of the copied string is returned. This + * makes this helper useful in tracing programs for reading + * strings, and more importantly to get its length at runtime. See + * the following snippet: + * + * :: + * + * SEC("kprobe/sys_open") + * void bpf_sys_open(struct pt_regs *ctx) + * { + * char buf[PATHLEN]; // PATHLEN is defined to 256 + * int res = bpf_probe_read_str(buf, sizeof(buf), + * ctx->di); + * + * // Consume buf, for example push it to + * // userspace via bpf_perf_event_output(); we + * // can use res (the string length) as event + * // size, after checking its boundaries. + * } + * + * In comparison, using **bpf_probe_read()** helper here instead + * to read the string would require to estimate the length at + * compile time, and would often result in copying more memory + * than necessary. + * + * Another useful use case is when parsing individual process + * arguments or individual environment variables navigating + * *current*\ **->mm->arg_start** and *current*\ + * **->mm->env_start**: using this helper and the return value, + * one can quickly iterate at the right offset of the memory area. + * Return + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. + * + * u64 bpf_get_socket_cookie(struct sk_buff *skb) + * Description + * If the **struct sk_buff** pointed by *skb* has a known socket, + * retrieve the cookie (generated by the kernel) of this socket. + * If no cookie has been set yet, generate a new cookie. Once + * generated, the socket cookie remains stable for the life of the + * socket. This helper can be useful for monitoring per socket + * networking traffic statistics as it provides a unique socket + * identifier per namespace. + * Return + * A 8-byte long non-decreasing number on success, or 0 if the + * socket field is missing inside *skb*. + * + * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx) + * Description + * Equivalent to bpf_get_socket_cookie() helper that accepts + * *skb*, but gets socket from **struct bpf_sock_addr** context. + * Return + * A 8-byte long non-decreasing number. + * + * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx) + * Description + * Equivalent to bpf_get_socket_cookie() helper that accepts + * *skb*, but gets socket from **struct bpf_sock_ops** context. + * Return + * A 8-byte long non-decreasing number. + * + * u32 bpf_get_socket_uid(struct sk_buff *skb) + * Return + * The owner UID of the socket associated to *skb*. If the socket + * is **NULL**, or if it is not a full socket (i.e. if it is a + * time-wait or a request socket instead), **overflowuid** value + * is returned (note that **overflowuid** might also be the actual + * UID value for the socket). + * + * u32 bpf_set_hash(struct sk_buff *skb, u32 hash) + * Description + * Set the full hash for *skb* (set the field *skb*\ **->hash**) + * to value *hash*. + * Return + * 0 + * + * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen) + * Description + * Emulate a call to **setsockopt()** on the socket associated to + * *bpf_socket*, which must be a full socket. The *level* at + * which the option resides and the name *optname* of the option + * must be specified, see **setsockopt(2)** for more information. + * The option value of length *optlen* is pointed by *optval*. + * + * This helper actually implements a subset of **setsockopt()**. + * It supports the following *level*\ s: + * + * * **SOL_SOCKET**, which supports the following *optname*\ s: + * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, + * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**. + * * **IPPROTO_TCP**, which supports the following *optname*\ s: + * **TCP_CONGESTION**, **TCP_BPF_IW**, + * **TCP_BPF_SNDCWND_CLAMP**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags) + * Description + * Grow or shrink the room for data in the packet associated to + * *skb* by *len_diff*, and according to the selected *mode*. + * + * There are two supported modes at this time: + * + * * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer + * (room space is added or removed below the layer 2 header). + * + * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer + * (room space is added or removed below the layer 3 header). + * + * The following flags are supported at this time: + * + * * **BPF_F_ADJ_ROOM_FIXED_GSO**: Do not adjust gso_size. + * Adjusting mss in this way is not allowed for datagrams. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 **: + * * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 **: + * Any new space is reserved to hold a tunnel header. + * Configure skb offsets and other fields accordingly. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L4_GRE **: + * * **BPF_F_ADJ_ROOM_ENCAP_L4_UDP **: + * Use with ENCAP_L3 flags to further specify the tunnel type. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * Description + * Redirect the packet to the endpoint referenced by *map* at + * index *key*. Depending on its type, this *map* can contain + * references to net devices (for forwarding packets through other + * ports), or to CPUs (for redirecting XDP frames to another CPU; + * but this is only implemented for native XDP (with driver + * support) as of this writing). + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * When used to redirect packets to net devices, this helper + * provides a high performance increase over **bpf_redirect**\ (). + * This is due to various implementation details of the underlying + * mechanisms, one of which is the fact that **bpf_redirect_map**\ + * () tries to send packet as a "bulk" to the device. + * Return + * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error. + * + * int bpf_sk_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * Description + * Redirect the packet to the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) + * Description + * Add an entry to, or update a *map* referencing sockets. The + * *skops* is used as a new value for the entry associated to + * *key*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * If the *map* has eBPF programs (parser and verdict), those will + * be inherited by the socket being added. If the socket is + * already attached to eBPF programs, this results in an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_meta(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust the address pointed by *xdp_md*\ **->data_meta** by + * *delta* (which can be positive or negative). Note that this + * operation modifies the address stored in *xdp_md*\ **->data**, + * so the latter must be loaded only after the helper has been + * called. + * + * The use of *xdp_md*\ **->data_meta** is optional and programs + * are not required to use it. The rationale is that when the + * packet is processed with XDP (e.g. as DoS filter), it is + * possible to push further meta data along with it before passing + * to the stack, and to give the guarantee that an ingress eBPF + * program attached as a TC classifier on the same device can pick + * this up for further post-processing. Since TC works with socket + * buffers, it remains possible to set from XDP the **mark** or + * **priority** pointers, or other pointers for the socket buffer. + * Having this scratch space generic and programmable allows for + * more flexibility as the user is free to store whatever meta + * data they need. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_perf_event_read_value(struct bpf_map *map, u64 flags, struct bpf_perf_event_value *buf, u32 buf_size) + * Description + * Read the value of a perf event counter, and store it into *buf* + * of size *buf_size*. This helper relies on a *map* of type + * **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of the perf event + * counter is selected when *map* is updated with perf event file + * descriptors. The *map* is an array whose size is the number of + * available CPUs, and each cell contains a value relative to one + * CPU. The value to retrieve is indicated by *flags*, that + * contains the index of the CPU to look up, masked with + * **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * This helper behaves in a way close to + * **bpf_perf_event_read**\ () helper, save that instead of + * just returning the value observed, it fills the *buf* + * structure. This allows for additional data to be retrieved: in + * particular, the enabled and running times (in *buf*\ + * **->enabled** and *buf*\ **->running**, respectively) are + * copied. In general, **bpf_perf_event_read_value**\ () is + * recommended over **bpf_perf_event_read**\ (), which has some + * ABI issues and provides fewer functionalities. + * + * These values are interesting, because hardware PMU (Performance + * Monitoring Unit) counters are limited resources. When there are + * more PMU based perf events opened than available counters, + * kernel will multiplex these events so each event gets certain + * percentage (but not all) of the PMU time. In case that + * multiplexing happens, the number of samples or counter value + * will not reflect the case compared to when no multiplexing + * occurs. This makes comparison between different runs difficult. + * Typically, the counter value should be normalized before + * comparing to other experiments. The usual normalization is done + * as follows. + * + * :: + * + * normalized_counter = counter * t_enabled / t_running + * + * Where t_enabled is the time enabled for event and t_running is + * the time running for event since last normalization. The + * enabled and running times are accumulated since the perf event + * open. To achieve scaling factor between two invocations of an + * eBPF program, users can can use CPU id as the key (which is + * typical for perf array usage model) to remember the previous + * value and do the calculation inside the eBPF program. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) + * Description + * For en eBPF program attached to a perf event, retrieve the + * value of the event counter associated to *ctx* and store it in + * the structure pointed by *buf* and of size *buf_size*. Enabled + * and running times are also stored in the structure (see + * description of helper **bpf_perf_event_read_value**\ () for + * more details). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen) + * Description + * Emulate a call to **getsockopt()** on the socket associated to + * *bpf_socket*, which must be a full socket. The *level* at + * which the option resides and the name *optname* of the option + * must be specified, see **getsockopt(2)** for more information. + * The retrieved value is stored in the structure pointed by + * *opval* and of length *optlen*. + * + * This helper actually implements a subset of **getsockopt()**. + * It supports the following *level*\ s: + * + * * **IPPROTO_TCP**, which supports *optname* + * **TCP_CONGESTION**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_override_return(struct pt_reg *regs, u64 rc) + * Description + * Used for error injection, this helper uses kprobes to override + * the return value of the probed function, and to set it to *rc*. + * The first argument is the context *regs* on which the kprobe + * works. + * + * This helper works by setting setting the PC (program counter) + * to an override function which is run in place of the original + * probed function. This means the probed function is not run at + * all. The replacement function just returns with the required + * value. + * + * This helper has security implications, and thus is subject to + * restrictions. It is only available if the kernel was compiled + * with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration + * option, and in this case it only works on functions tagged with + * **ALLOW_ERROR_INJECTION** in the kernel code. + * + * Also, the helper is only available for the architectures having + * the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing, + * x86 architecture is the only one to support this feature. + * Return + * 0 + * + * int bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *bpf_sock, int argval) + * Description + * Attempt to set the value of the **bpf_sock_ops_cb_flags** field + * for the full TCP socket associated to *bpf_sock_ops* to + * *argval*. + * + * The primary use of this field is to determine if there should + * be calls to eBPF programs of type + * **BPF_PROG_TYPE_SOCK_OPS** at various points in the TCP + * code. A program of the same type can change its value, per + * connection and as necessary, when the connection is + * established. This field is directly accessible for reading, but + * this helper must be used for updates in order to return an + * error if an eBPF program tries to set a callback that is not + * supported in the current kernel. + * + * The supported callback values that *argval* can combine are: + * + * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out) + * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission) + * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change) + * + * Here are some examples of where one could call such eBPF + * program: + * + * * When RTO fires. + * * When a packet is retransmitted. + * * When the connection terminates. + * * When a packet is sent. + * * When a packet is received. + * Return + * Code **-EINVAL** if the socket is not a full TCP socket; + * otherwise, a positive number containing the bits that could not + * be set is returned (which comes down to 0 if all bits were set + * as required). + * + * int bpf_msg_redirect_map(struct sk_msg_buff *msg, struct bpf_map *map, u32 key, u64 flags) + * Description + * This helper is used in programs implementing policies at the + * socket level. If the message *msg* is allowed to pass (i.e. if + * the verdict eBPF program returns **SK_PASS**), redirect it to + * the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_msg_apply_bytes(struct sk_msg_buff *msg, u32 bytes) + * Description + * For socket policies, apply the verdict of the eBPF program to + * the next *bytes* (number of bytes) of message *msg*. + * + * For example, this helper can be used in the following cases: + * + * * A single **sendmsg**\ () or **sendfile**\ () system call + * contains multiple logical messages that the eBPF program is + * supposed to read and for which it should apply a verdict. + * * An eBPF program only cares to read the first *bytes* of a + * *msg*. If the message has a large payload, then setting up + * and calling the eBPF program repeatedly for all bytes, even + * though the verdict is already known, would create unnecessary + * overhead. + * + * When called from within an eBPF program, the helper sets a + * counter internal to the BPF infrastructure, that is used to + * apply the last verdict to the next *bytes*. If *bytes* is + * smaller than the current data being processed from a + * **sendmsg**\ () or **sendfile**\ () system call, the first + * *bytes* will be sent and the eBPF program will be re-run with + * the pointer for start of data pointing to byte number *bytes* + * **+ 1**. If *bytes* is larger than the current data being + * processed, then the eBPF verdict will be applied to multiple + * **sendmsg**\ () or **sendfile**\ () calls until *bytes* are + * consumed. + * + * Note that if a socket closes with the internal counter holding + * a non-zero value, this is not a problem because data is not + * being buffered for *bytes* and is sent as it is received. + * Return + * 0 + * + * int bpf_msg_cork_bytes(struct sk_msg_buff *msg, u32 bytes) + * Description + * For socket policies, prevent the execution of the verdict eBPF + * program for message *msg* until *bytes* (byte number) have been + * accumulated. + * + * This can be used when one needs a specific number of bytes + * before a verdict can be assigned, even if the data spans + * multiple **sendmsg**\ () or **sendfile**\ () calls. The extreme + * case would be a user calling **sendmsg**\ () repeatedly with + * 1-byte long message segments. Obviously, this is bad for + * performance, but it is still valid. If the eBPF program needs + * *bytes* bytes to validate a header, this helper can be used to + * prevent the eBPF program to be called again until *bytes* have + * been accumulated. + * Return + * 0 + * + * int bpf_msg_pull_data(struct sk_msg_buff *msg, u32 start, u32 end, u64 flags) + * Description + * For socket policies, pull in non-linear data from user space + * for *msg* and set pointers *msg*\ **->data** and *msg*\ + * **->data_end** to *start* and *end* bytes offsets into *msg*, + * respectively. + * + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it can only parse data that the (**data**, **data_end**) + * pointers have already consumed. For **sendmsg**\ () hooks this + * is likely the first scatterlist element. But for calls relying + * on the **sendpage** handler (e.g. **sendfile**\ ()) this will + * be the range (**0**, **0**) because the data is shared with + * user space and by default the objective is to avoid allowing + * user space to modify data while (or after) eBPF verdict is + * being decided. This helper can be used to pull in data and to + * set the start and end pointer to given values. Data will be + * copied if necessary (i.e. if data was not linear and if start + * and end pointers do not point to the same chunk). + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_bind(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len) + * Description + * Bind the socket associated to *ctx* to the address pointed by + * *addr*, of length *addr_len*. This allows for making outgoing + * connection from the desired IP address, which can be useful for + * example when all processes inside a cgroup should use one + * single IP address on a host that has multiple IP configured. + * + * This helper works for IPv4 and IPv6, TCP and UDP sockets. The + * domain (*addr*\ **->sa_family**) must be **AF_INET** (or + * **AF_INET6**). Looking for a free port to bind to can be + * expensive, therefore binding to port is not permitted by the + * helper: *addr*\ **->sin_port** (or **sin6_port**, respectively) + * must be set to zero. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is + * only possible to shrink the packet as of this writing, + * therefore *delta* must be a negative integer. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_get_xfrm_state(struct sk_buff *skb, u32 index, struct bpf_xfrm_state *xfrm_state, u32 size, u64 flags) + * Description + * Retrieve the XFRM state (IP transform framework, see also + * **ip-xfrm(8)**) at *index* in XFRM "security path" for *skb*. + * + * The retrieved value is stored in the **struct bpf_xfrm_state** + * pointed by *xfrm_state* and of length *size*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_XFRM** configuration option. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_get_stack(struct pt_regs *regs, void *buf, u32 size, u64 flags) + * Description + * Return a user or a kernel stack in bpf program provided buffer. + * To achieve this, the helper needs *ctx*, which is a pointer + * to the context on which the tracing program is executed. + * To store the stacktrace, the bpf program provides *buf* with + * a nonnegative *size*. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_USER_BUILD_ID** + * Collect buildid+offset instead of ips for user stack, + * only valid if **BPF_F_USER_STACK** is also specified. + * + * **bpf_get_stack**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject + * to sufficient large buffer size. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack=<new value> + * Return + * A non-negative value equal to or less than *size* on success, + * or a negative error in case of failure. + * + * int bpf_skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header) + * Description + * This helper is similar to **bpf_skb_load_bytes**\ () in that + * it provides an easy way to load *len* bytes from *offset* + * from the packet associated to *skb*, into the buffer pointed + * by *to*. The difference to **bpf_skb_load_bytes**\ () is that + * a fifth argument *start_header* exists in order to select a + * base offset to start from. *start_header* can be one of: + * + * **BPF_HDR_START_MAC** + * Base offset to load data from is *skb*'s mac header. + * **BPF_HDR_START_NET** + * Base offset to load data from is *skb*'s network header. + * + * In general, "direct packet access" is the preferred method to + * access packet data, however, this helper is in particular useful + * in socket filters where *skb*\ **->data** does not always point + * to the start of the mac header and where "direct packet access" + * is not available. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_fib_lookup(void *ctx, struct bpf_fib_lookup *params, int plen, u32 flags) + * Description + * Do FIB lookup in kernel tables using parameters in *params*. + * If lookup is successful and result shows packet is to be + * forwarded, the neighbor tables are searched for the nexthop. + * If successful (ie., FIB lookup shows forwarding and nexthop + * is resolved), the nexthop address is returned in ipv4_dst + * or ipv6_dst based on family, smac is set to mac address of + * egress device, dmac is set to nexthop mac address, rt_metric + * is set to metric from route (IPv4/IPv6 only), and ifindex + * is set to the device index of the nexthop from the FIB lookup. + * + * *plen* argument is the size of the passed in struct. + * *flags* argument can be a combination of one or more of the + * following values: + * + * **BPF_FIB_LOOKUP_DIRECT** + * Do a direct table lookup vs full lookup using FIB + * rules. + * **BPF_FIB_LOOKUP_OUTPUT** + * Perform lookup from an egress perspective (default is + * ingress). + * + * *ctx* is either **struct xdp_md** for XDP programs or + * **struct sk_buff** tc cls_act programs. + * Return + * * < 0 if any input argument is invalid + * * 0 on success (packet is forwarded, nexthop neighbor exists) + * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the + * packet is not forwarded or needs assist from full stack + * + * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags) + * Description + * Add an entry to, or update a sockhash *map* referencing sockets. + * The *skops* is used as a new value for the entry associated to + * *key*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * If the *map* has eBPF programs (parser and verdict), those will + * be inherited by the socket being added. If the socket is + * already attached to eBPF programs, this results in an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_msg_redirect_hash(struct sk_msg_buff *msg, struct bpf_map *map, void *key, u64 flags) + * Description + * This helper is used in programs implementing policies at the + * socket level. If the message *msg* is allowed to pass (i.e. if + * the verdict eBPF program returns **SK_PASS**), redirect it to + * the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_sk_redirect_hash(struct sk_buff *skb, struct bpf_map *map, void *key, u64 flags) + * Description + * This helper is used in programs implementing policies at the + * skb socket level. If the sk_buff *skb* is allowed to pass (i.e. + * if the verdeict eBPF program returns **SK_PASS**), redirect it + * to the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_lwt_push_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len) + * Description + * Encapsulate the packet associated to *skb* within a Layer 3 + * protocol header. This header is provided in the buffer at + * address *hdr*, with *len* its size in bytes. *type* indicates + * the protocol of the header and can be one of: + * + * **BPF_LWT_ENCAP_SEG6** + * IPv6 encapsulation with Segment Routing Header + * (**struct ipv6_sr_hdr**). *hdr* only contains the SRH, + * the IPv6 header is computed by the kernel. + * **BPF_LWT_ENCAP_SEG6_INLINE** + * Only works if *skb* contains an IPv6 packet. Insert a + * Segment Routing Header (**struct ipv6_sr_hdr**) inside + * the IPv6 header. + * **BPF_LWT_ENCAP_IP** + * IP encapsulation (GRE/GUE/IPIP/etc). The outer header + * must be IPv4 or IPv6, followed by zero or more + * additional headers, up to LWT_BPF_MAX_HEADROOM total + * bytes in all prepended headers. Please note that + * if skb_is_gso(skb) is true, no more than two headers + * can be prepended, and the inner header, if present, + * should be either GRE or UDP/GUE. + * + * BPF_LWT_ENCAP_SEG6*** types can be called by bpf programs of + * type BPF_PROG_TYPE_LWT_IN; BPF_LWT_ENCAP_IP type can be called + * by bpf programs of types BPF_PROG_TYPE_LWT_IN and + * BPF_PROG_TYPE_LWT_XMIT. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_lwt_seg6_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len) + * Description + * Store *len* bytes from address *from* into the packet + * associated to *skb*, at *offset*. Only the flags, tag and TLVs + * inside the outermost IPv6 Segment Routing Header can be + * modified through this helper. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_lwt_seg6_adjust_srh(struct sk_buff *skb, u32 offset, s32 delta) + * Description + * Adjust the size allocated to TLVs in the outermost IPv6 + * Segment Routing Header contained in the packet associated to + * *skb*, at position *offset* by *delta* bytes. Only offsets + * after the segments are accepted. *delta* can be as well + * positive (growing) as negative (shrinking). + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_lwt_seg6_action(struct sk_buff *skb, u32 action, void *param, u32 param_len) + * Description + * Apply an IPv6 Segment Routing action of type *action* to the + * packet associated to *skb*. Each action takes a parameter + * contained at address *param*, and of length *param_len* bytes. + * *action* can be one of: + * + * **SEG6_LOCAL_ACTION_END_X** + * End.X action: Endpoint with Layer-3 cross-connect. + * Type of *param*: **struct in6_addr**. + * **SEG6_LOCAL_ACTION_END_T** + * End.T action: Endpoint with specific IPv6 table lookup. + * Type of *param*: **int**. + * **SEG6_LOCAL_ACTION_END_B6** + * End.B6 action: Endpoint bound to an SRv6 policy. + * Type of param: **struct ipv6_sr_hdr**. + * **SEG6_LOCAL_ACTION_END_B6_ENCAP** + * End.B6.Encap action: Endpoint bound to an SRv6 + * encapsulation policy. + * Type of param: **struct ipv6_sr_hdr**. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_rc_repeat(void *ctx) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded repeat key message. This delays + * the generation of a key up event for previously generated + * key down event. + * + * Some IR protocols like NEC have a special IR message for + * repeating last button, for when a button is held down. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * Return + * 0 + * + * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded key press with *scancode*, + * *toggle* value in the given *protocol*. The scancode will be + * translated to a keycode using the rc keymap, and reported as + * an input key down event. After a period a key up event is + * generated. This period can be extended by calling either + * **bpf_rc_keydown**\ () again with the same values, or calling + * **bpf_rc_repeat**\ (). + * + * Some protocols include a toggle bit, in case the button was + * released and pressed again between consecutive scancodes. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * The *protocol* is the decoded protocol number (see + * **enum rc_proto** for some predefined values). + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * Return + * 0 + * + * u64 bpf_skb_cgroup_id(struct sk_buff *skb) + * Description + * Return the cgroup v2 id of the socket associated with the *skb*. + * This is roughly similar to the **bpf_get_cgroup_classid**\ () + * helper for cgroup v1 by providing a tag resp. identifier that + * can be matched on or used for map lookups e.g. to implement + * policy. The cgroup v2 id of a given path in the hierarchy is + * exposed in user space through the f_handle API in order to get + * to the same 64-bit id. + * + * This helper can be used on TC egress path, but not on ingress, + * and is available only if the kernel was compiled with the + * **CONFIG_SOCK_CGROUP_DATA** configuration option. + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * u64 bpf_get_current_cgroup_id(void) + * Return + * A 64-bit integer containing the current cgroup id based + * on the cgroup within which the current task is running. + * + * void *bpf_get_local_storage(void *map, u64 flags) + * Description + * Get the pointer to the local storage area. + * The type and the size of the local storage is defined + * by the *map* argument. + * The *flags* meaning is specific for each map type, + * and has to be 0 for cgroup local storage. + * + * Depending on the BPF program type, a local storage area + * can be shared between multiple instances of the BPF program, + * running simultaneously. + * + * A user should care about the synchronization by himself. + * For example, by using the **BPF_STX_XADD** instruction to alter + * the shared data. + * Return + * A pointer to the local storage area. + * + * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags) + * Description + * Select a **SO_REUSEPORT** socket from a + * **BPF_MAP_TYPE_REUSEPORT_ARRAY** *map*. + * It checks the selected socket is matching the incoming + * request in the socket buffer. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level) + * Description + * Return id of cgroup v2 that is ancestor of cgroup associated + * with the *skb* at the *ancestor_level*. The root cgroup is at + * *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with *skb*, then return value will be same as that + * of **bpf_skb_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with *skb*. + * + * The format of returned id and helper limitations are same as in + * **bpf_skb_cgroup_id**\ (). + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is a negative signed 32-bit integer, then the + * socket lookup table in the netns associated with the *ctx* will + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For socket hooks, this is the netns of the socket. + * If *netns* is any other signed 32-bit value greater than or + * equal to zero then it specifies the ID of the netns relative to + * the netns associated with the *ctx*. *netns* values beyond the + * range of 32-bit integers are reserved for future use. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from **reuse->socks**\ [] using the hash of the tuple. + * + * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for UDP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is a negative signed 32-bit integer, then the + * socket lookup table in the netns associated with the *ctx* will + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For socket hooks, this is the netns of the socket. + * If *netns* is any other signed 32-bit value greater than or + * equal to zero then it specifies the ID of the netns relative to + * the netns associated with the *ctx*. *netns* values beyond the + * range of 32-bit integers are reserved for future use. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from **reuse->socks**\ [] using the hash of the tuple. + * + * int bpf_sk_release(struct bpf_sock *sock) + * Description + * Release the reference held by *sock*. *sock* must be a + * non-**NULL** pointer that was returned from + * **bpf_sk_lookup_xxx**\ (). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) + * Description + * Push an element *value* in *map*. *flags* is one of: + * + * **BPF_EXIST** + * If the queue/stack is full, the oldest element is + * removed to make room for this. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_pop_elem(struct bpf_map *map, void *value) + * Description + * Pop an element from *map*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_peek_elem(struct bpf_map *map, void *value) + * Description + * Get an element from *map* without removing it. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_msg_push_data(struct sk_buff *skb, u32 start, u32 len, u64 flags) + * Description + * For socket policies, insert *len* bytes into *msg* at offset + * *start*. + * + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it may want to insert metadata or options into the *msg*. + * This can later be read and used by any of the lower layer BPF + * hooks. + * + * This helper may fail if under memory pressure (a malloc + * fails) in these cases BPF programs will get an appropriate + * error and BPF programs will need to handle them. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 pop, u64 flags) + * Description + * Will remove *pop* bytes from a *msg* starting at byte *start*. + * This may result in **ENOMEM** errors under certain situations if + * an allocation and copy are required due to a full ring buffer. + * However, the helper will try to avoid doing the allocation + * if possible. Other errors can occur if input parameters are + * invalid either due to *start* byte not being valid part of *msg* + * payload and/or *pop* value being to large. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_rc_pointer_rel(void *ctx, s32 rel_x, s32 rel_y) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded pointer movement. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * Return + * 0 + * + * int bpf_spin_lock(struct bpf_spin_lock *lock) + * Description + * Acquire a spinlock represented by the pointer *lock*, which is + * stored as part of a value of a map. Taking the lock allows to + * safely update the rest of the fields in that value. The + * spinlock can (and must) later be released with a call to + * **bpf_spin_unlock**\ (\ *lock*\ ). + * + * Spinlocks in BPF programs come with a number of restrictions + * and constraints: + * + * * **bpf_spin_lock** objects are only allowed inside maps of + * types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this + * list could be extended in the future). + * * BTF description of the map is mandatory. + * * The BPF program can take ONE lock at a time, since taking two + * or more could cause dead locks. + * * Only one **struct bpf_spin_lock** is allowed per map element. + * * When the lock is taken, calls (either BPF to BPF or helpers) + * are not allowed. + * * The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not + * allowed inside a spinlock-ed region. + * * The BPF program MUST call **bpf_spin_unlock**\ () to release + * the lock, on all execution paths, before it returns. + * * The BPF program can access **struct bpf_spin_lock** only via + * the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ () + * helpers. Loading or storing data into the **struct + * bpf_spin_lock** *lock*\ **;** field of a map is not allowed. + * * To use the **bpf_spin_lock**\ () helper, the BTF description + * of the map value must be a struct and have **struct + * bpf_spin_lock** *anyname*\ **;** field at the top level. + * Nested lock inside another struct is not allowed. + * * The **struct bpf_spin_lock** *lock* field in a map value must + * be aligned on a multiple of 4 bytes in that value. + * * Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy + * the **bpf_spin_lock** field to user space. + * * Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from + * a BPF program, do not update the **bpf_spin_lock** field. + * * **bpf_spin_lock** cannot be on the stack or inside a + * networking packet (it can only be inside of a map values). + * * **bpf_spin_lock** is available to root only. + * * Tracing programs and socket filter programs cannot use + * **bpf_spin_lock**\ () due to insufficient preemption checks + * (but this may change in the future). + * * **bpf_spin_lock** is not allowed in inner maps of map-in-map. + * Return + * 0 + * + * int bpf_spin_unlock(struct bpf_spin_lock *lock) + * Description + * Release the *lock* previously locked by a call to + * **bpf_spin_lock**\ (\ *lock*\ ). + * Return + * 0 + * + * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk) + * Description + * This helper gets a **struct bpf_sock** pointer such + * that all the fields in this **bpf_sock** can be accessed. + * Return + * A **struct bpf_sock** pointer on success, or **NULL** in + * case of failure. + * + * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk) + * Description + * This helper gets a **struct bpf_tcp_sock** pointer from a + * **struct bpf_sock** pointer. + * Return + * A **struct bpf_tcp_sock** pointer on success, or **NULL** in + * case of failure. + * + * int bpf_skb_ecn_set_ce(struct sk_buf *skb) + * Description + * Set ECN (Explicit Congestion Notification) field of IP header + * to **CE** (Congestion Encountered) if current value is **ECT** + * (ECN Capable Transport). Otherwise, do nothing. Works with IPv6 + * and IPv4. + * Return + * 1 if the **CE** flag is set (either by the current helper call + * or because it was already present), 0 if it is not set. + * + * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk) + * Description + * Return a **struct bpf_sock** pointer in **TCP_LISTEN** state. + * **bpf_sk_release**\ () is unnecessary and not allowed. + * Return + * A **struct bpf_sock** pointer on success, or **NULL** in + * case of failure. + * + * struct bpf_sock *bpf_skc_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * This function is identical to bpf_sk_lookup_tcp, except that it + * also returns timewait or request sockets. Use bpf_sk_fullsock + * or bpf_tcp_socket to access the full structure. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from **reuse->socks**\ [] using the hash of the tuple. + * + * int bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * Description + * Check whether iph and th contain a valid SYN cookie ACK for + * the listening socket in sk. + * + * iph points to the start of the IPv4 or IPv6 header, while + * iph_len contains sizeof(struct iphdr) or sizeof(struct ip6hdr). + * + * th points to the start of the TCP header, while th_len contains + * sizeof(struct tcphdr). + * + * Return + * 0 if iph and th are a valid SYN cookie ACK, or a negative error + * otherwise. + */ +#define __BPF_FUNC_MAPPER(FN) \ + FN(unspec), \ + FN(map_lookup_elem), \ + FN(map_update_elem), \ + FN(map_delete_elem), \ + FN(probe_read), \ + FN(ktime_get_ns), \ + FN(trace_printk), \ + FN(get_prandom_u32), \ + FN(get_smp_processor_id), \ + FN(skb_store_bytes), \ + FN(l3_csum_replace), \ + FN(l4_csum_replace), \ + FN(tail_call), \ + FN(clone_redirect), \ + FN(get_current_pid_tgid), \ + FN(get_current_uid_gid), \ + FN(get_current_comm), \ + FN(get_cgroup_classid), \ + FN(skb_vlan_push), \ + FN(skb_vlan_pop), \ + FN(skb_get_tunnel_key), \ + FN(skb_set_tunnel_key), \ + FN(perf_event_read), \ + FN(redirect), \ + FN(get_route_realm), \ + FN(perf_event_output), \ + FN(skb_load_bytes), \ + FN(get_stackid), \ + FN(csum_diff), \ + FN(skb_get_tunnel_opt), \ + FN(skb_set_tunnel_opt), \ + FN(skb_change_proto), \ + FN(skb_change_type), \ + FN(skb_under_cgroup), \ + FN(get_hash_recalc), \ + FN(get_current_task), \ + FN(probe_write_user), \ + FN(current_task_under_cgroup), \ + FN(skb_change_tail), \ + FN(skb_pull_data), \ + FN(csum_update), \ + FN(set_hash_invalid), \ + FN(get_numa_node_id), \ + FN(skb_change_head), \ + FN(xdp_adjust_head), \ + FN(probe_read_str), \ + FN(get_socket_cookie), \ + FN(get_socket_uid), \ + FN(set_hash), \ + FN(setsockopt), \ + FN(skb_adjust_room), \ + FN(redirect_map), \ + FN(sk_redirect_map), \ + FN(sock_map_update), \ + FN(xdp_adjust_meta), \ + FN(perf_event_read_value), \ + FN(perf_prog_read_value), \ + FN(getsockopt), \ + FN(override_return), \ + FN(sock_ops_cb_flags_set), \ + FN(msg_redirect_map), \ + FN(msg_apply_bytes), \ + FN(msg_cork_bytes), \ + FN(msg_pull_data), \ + FN(bind), \ + FN(xdp_adjust_tail), \ + FN(skb_get_xfrm_state), \ + FN(get_stack), \ + FN(skb_load_bytes_relative), \ + FN(fib_lookup), \ + FN(sock_hash_update), \ + FN(msg_redirect_hash), \ + FN(sk_redirect_hash), \ + FN(lwt_push_encap), \ + FN(lwt_seg6_store_bytes), \ + FN(lwt_seg6_adjust_srh), \ + FN(lwt_seg6_action), \ + FN(rc_repeat), \ + FN(rc_keydown), \ + FN(skb_cgroup_id), \ + FN(get_current_cgroup_id), \ + FN(get_local_storage), \ + FN(sk_select_reuseport), \ + FN(skb_ancestor_cgroup_id), \ + FN(sk_lookup_tcp), \ + FN(sk_lookup_udp), \ + FN(sk_release), \ + FN(map_push_elem), \ + FN(map_pop_elem), \ + FN(map_peek_elem), \ + FN(msg_push_data), \ + FN(msg_pop_data), \ + FN(rc_pointer_rel), \ + FN(spin_lock), \ + FN(spin_unlock), \ + FN(sk_fullsock), \ + FN(tcp_sock), \ + FN(skb_ecn_set_ce), \ + FN(get_listener_sock), \ + FN(skc_lookup_tcp), \ + FN(tcp_check_syncookie), + +/* integer value in 'imm' field of BPF_CALL instruction selects which helper + * function eBPF program intends to call + */ +#define __BPF_ENUM_FN(x) BPF_FUNC_ ## x +enum bpf_func_id { + __BPF_FUNC_MAPPER(__BPF_ENUM_FN) + __BPF_FUNC_MAX_ID, +}; +#undef __BPF_ENUM_FN + +/* All flags used by eBPF helper functions, placed here. */ + +/* BPF_FUNC_skb_store_bytes flags. */ +#define BPF_F_RECOMPUTE_CSUM (1ULL << 0) +#define BPF_F_INVALIDATE_HASH (1ULL << 1) + +/* BPF_FUNC_l3_csum_replace and BPF_FUNC_l4_csum_replace flags. + * First 4 bits are for passing the header field size. + */ +#define BPF_F_HDR_FIELD_MASK 0xfULL + +/* BPF_FUNC_l4_csum_replace flags. */ +#define BPF_F_PSEUDO_HDR (1ULL << 4) +#define BPF_F_MARK_MANGLED_0 (1ULL << 5) +#define BPF_F_MARK_ENFORCE (1ULL << 6) + +/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */ +#define BPF_F_INGRESS (1ULL << 0) + +/* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ +#define BPF_F_TUNINFO_IPV6 (1ULL << 0) + +/* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */ +#define BPF_F_SKIP_FIELD_MASK 0xffULL +#define BPF_F_USER_STACK (1ULL << 8) +/* flags used by BPF_FUNC_get_stackid only. */ +#define BPF_F_FAST_STACK_CMP (1ULL << 9) +#define BPF_F_REUSE_STACKID (1ULL << 10) +/* flags used by BPF_FUNC_get_stack only. */ +#define BPF_F_USER_BUILD_ID (1ULL << 11) + +/* BPF_FUNC_skb_set_tunnel_key flags. */ +#define BPF_F_ZERO_CSUM_TX (1ULL << 1) +#define BPF_F_DONT_FRAGMENT (1ULL << 2) +#define BPF_F_SEQ_NUMBER (1ULL << 3) + +/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and + * BPF_FUNC_perf_event_read_value flags. + */ +#define BPF_F_INDEX_MASK 0xffffffffULL +#define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK +/* BPF_FUNC_perf_event_output for sk_buff input context. */ +#define BPF_F_CTXLEN_MASK (0xfffffULL << 32) + +/* Current network namespace */ +#define BPF_F_CURRENT_NETNS (-1L) + +/* BPF_FUNC_skb_adjust_room flags. */ +#define BPF_F_ADJ_ROOM_FIXED_GSO (1ULL << 0) + +#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 (1ULL << 1) +#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 (1ULL << 2) +#define BPF_F_ADJ_ROOM_ENCAP_L4_GRE (1ULL << 3) +#define BPF_F_ADJ_ROOM_ENCAP_L4_UDP (1ULL << 4) + +/* Mode for BPF_FUNC_skb_adjust_room helper. */ +enum bpf_adj_room_mode { + BPF_ADJ_ROOM_NET, + BPF_ADJ_ROOM_MAC, +}; + +/* Mode for BPF_FUNC_skb_load_bytes_relative helper. */ +enum bpf_hdr_start_off { + BPF_HDR_START_MAC, + BPF_HDR_START_NET, +}; + +/* Encapsulation type for BPF_FUNC_lwt_push_encap helper. */ +enum bpf_lwt_encap_mode { + BPF_LWT_ENCAP_SEG6, + BPF_LWT_ENCAP_SEG6_INLINE, + BPF_LWT_ENCAP_IP, +}; + +#define __bpf_md_ptr(type, name) \ +union { \ + type name; \ + __u64 :64; \ +} __attribute__((aligned(8))) + +/* user accessible mirror of in-kernel sk_buff. + * new fields can only be added to the end of this structure + */ +struct __sk_buff { + __u32 len; + __u32 pkt_type; + __u32 mark; + __u32 queue_mapping; + __u32 protocol; + __u32 vlan_present; + __u32 vlan_tci; + __u32 vlan_proto; + __u32 priority; + __u32 ingress_ifindex; + __u32 ifindex; + __u32 tc_index; + __u32 cb[5]; + __u32 hash; + __u32 tc_classid; + __u32 data; + __u32 data_end; + __u32 napi_id; + + /* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */ + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ + /* ... here. */ + + __u32 data_meta; + __bpf_md_ptr(struct bpf_flow_keys *, flow_keys); + __u64 tstamp; + __u32 wire_len; + __u32 gso_segs; + __bpf_md_ptr(struct bpf_sock *, sk); +}; + +struct bpf_tunnel_key { + __u32 tunnel_id; + union { + __u32 remote_ipv4; + __u32 remote_ipv6[4]; + }; + __u8 tunnel_tos; + __u8 tunnel_ttl; + __u16 tunnel_ext; /* Padding, future use. */ + __u32 tunnel_label; +}; + +/* user accessible mirror of in-kernel xfrm_state. + * new fields can only be added to the end of this structure + */ +struct bpf_xfrm_state { + __u32 reqid; + __u32 spi; /* Stored in network byte order */ + __u16 family; + __u16 ext; /* Padding, future use. */ + union { + __u32 remote_ipv4; /* Stored in network byte order */ + __u32 remote_ipv6[4]; /* Stored in network byte order */ + }; +}; + +/* Generic BPF return codes which all BPF program types may support. + * The values are binary compatible with their TC_ACT_* counter-part to + * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT + * programs. + * + * XDP is handled seprately, see XDP_*. + */ +enum bpf_ret_code { + BPF_OK = 0, + /* 1 reserved */ + BPF_DROP = 2, + /* 3-6 reserved */ + BPF_REDIRECT = 7, + /* >127 are reserved for prog type specific return codes. + * + * BPF_LWT_REROUTE: used by BPF_PROG_TYPE_LWT_IN and + * BPF_PROG_TYPE_LWT_XMIT to indicate that skb had been + * changed and should be routed based on its new L3 header. + * (This is an L3 redirect, as opposed to L2 redirect + * represented by BPF_REDIRECT above). + */ + BPF_LWT_REROUTE = 128, +}; + +struct bpf_sock { + __u32 bound_dev_if; + __u32 family; + __u32 type; + __u32 protocol; + __u32 mark; + __u32 priority; + /* IP address also allows 1 and 2 bytes access */ + __u32 src_ip4; + __u32 src_ip6[4]; + __u32 src_port; /* host byte order */ + __u32 dst_port; /* network byte order */ + __u32 dst_ip4; + __u32 dst_ip6[4]; + __u32 state; +}; + +struct bpf_tcp_sock { + __u32 snd_cwnd; /* Sending congestion window */ + __u32 srtt_us; /* smoothed round trip time << 3 in usecs */ + __u32 rtt_min; + __u32 snd_ssthresh; /* Slow start size threshold */ + __u32 rcv_nxt; /* What we want to receive next */ + __u32 snd_nxt; /* Next sequence we send */ + __u32 snd_una; /* First byte we want an ack for */ + __u32 mss_cache; /* Cached effective mss, not including SACKS */ + __u32 ecn_flags; /* ECN status bits. */ + __u32 rate_delivered; /* saved rate sample: packets delivered */ + __u32 rate_interval_us; /* saved rate sample: time elapsed */ + __u32 packets_out; /* Packets which are "in flight" */ + __u32 retrans_out; /* Retransmitted packets out */ + __u32 total_retrans; /* Total retransmits for entire connection */ + __u32 segs_in; /* RFC4898 tcpEStatsPerfSegsIn + * total number of segments in. + */ + __u32 data_segs_in; /* RFC4898 tcpEStatsPerfDataSegsIn + * total number of data segments in. + */ + __u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut + * The total number of segments sent. + */ + __u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut + * total number of data segments sent. + */ + __u32 lost_out; /* Lost packets */ + __u32 sacked_out; /* SACK'd packets */ + __u64 bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived + * sum(delta(rcv_nxt)), or how many bytes + * were acked. + */ + __u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked + * sum(delta(snd_una)), or how many bytes + * were acked. + */ +}; + +struct bpf_sock_tuple { + union { + struct { + __be32 saddr; + __be32 daddr; + __be16 sport; + __be16 dport; + } ipv4; + struct { + __be32 saddr[4]; + __be32 daddr[4]; + __be16 sport; + __be16 dport; + } ipv6; + }; +}; + +#define XDP_PACKET_HEADROOM 256 + +/* User return codes for XDP prog type. + * A valid XDP program must return one of these defined values. All other + * return codes are reserved for future use. Unknown return codes will + * result in packet drops and a warning via bpf_warn_invalid_xdp_action(). + */ +enum xdp_action { + XDP_ABORTED = 0, + XDP_DROP, + XDP_PASS, + XDP_TX, + XDP_REDIRECT, +}; + +/* user accessible metadata for XDP packet hook + * new fields must be added to the end of this structure + */ +struct xdp_md { + __u32 data; + __u32 data_end; + __u32 data_meta; + /* Below access go through struct xdp_rxq_info */ + __u32 ingress_ifindex; /* rxq->dev->ifindex */ + __u32 rx_queue_index; /* rxq->queue_index */ +}; + +enum sk_action { + SK_DROP = 0, + SK_PASS, +}; + +/* user accessible metadata for SK_MSG packet hook, new fields must + * be added to the end of this structure + */ +struct sk_msg_md { + __bpf_md_ptr(void *, data); + __bpf_md_ptr(void *, data_end); + + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ + __u32 size; /* Total size of sk_msg */ +}; + +struct sk_reuseport_md { + /* + * Start of directly accessible data. It begins from + * the tcp/udp header. + */ + __bpf_md_ptr(void *, data); + /* End of directly accessible data */ + __bpf_md_ptr(void *, data_end); + /* + * Total length of packet (starting from the tcp/udp header). + * Note that the directly accessible bytes (data_end - data) + * could be less than this "len". Those bytes could be + * indirectly read by a helper "bpf_skb_load_bytes()". + */ + __u32 len; + /* + * Eth protocol in the mac header (network byte order). e.g. + * ETH_P_IP(0x0800) and ETH_P_IPV6(0x86DD) + */ + __u32 eth_protocol; + __u32 ip_protocol; /* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */ + __u32 bind_inany; /* Is sock bound to an INANY address? */ + __u32 hash; /* A hash of the packet 4 tuples */ +}; + +#define BPF_TAG_SIZE 8 + +struct bpf_prog_info { + __u32 type; + __u32 id; + __u8 tag[BPF_TAG_SIZE]; + __u32 jited_prog_len; + __u32 xlated_prog_len; + __aligned_u64 jited_prog_insns; + __aligned_u64 xlated_prog_insns; + __u64 load_time; /* ns since boottime */ + __u32 created_by_uid; + __u32 nr_map_ids; + __aligned_u64 map_ids; + char name[BPF_OBJ_NAME_LEN]; + __u32 ifindex; + __u32 gpl_compatible:1; + __u64 netns_dev; + __u64 netns_ino; + __u32 nr_jited_ksyms; + __u32 nr_jited_func_lens; + __aligned_u64 jited_ksyms; + __aligned_u64 jited_func_lens; + __u32 btf_id; + __u32 func_info_rec_size; + __aligned_u64 func_info; + __u32 nr_func_info; + __u32 nr_line_info; + __aligned_u64 line_info; + __aligned_u64 jited_line_info; + __u32 nr_jited_line_info; + __u32 line_info_rec_size; + __u32 jited_line_info_rec_size; + __u32 nr_prog_tags; + __aligned_u64 prog_tags; + __u64 run_time_ns; + __u64 run_cnt; +} __attribute__((aligned(8))); + +struct bpf_map_info { + __u32 type; + __u32 id; + __u32 key_size; + __u32 value_size; + __u32 max_entries; + __u32 map_flags; + char name[BPF_OBJ_NAME_LEN]; + __u32 ifindex; + __u32 :32; + __u64 netns_dev; + __u64 netns_ino; + __u32 btf_id; + __u32 btf_key_type_id; + __u32 btf_value_type_id; +} __attribute__((aligned(8))); + +struct bpf_btf_info { + __aligned_u64 btf; + __u32 btf_size; + __u32 id; +} __attribute__((aligned(8))); + +/* User bpf_sock_addr struct to access socket fields and sockaddr struct passed + * by user and intended to be used by socket (e.g. to bind to, depends on + * attach attach type). + */ +struct bpf_sock_addr { + __u32 user_family; /* Allows 4-byte read, but no write. */ + __u32 user_ip4; /* Allows 1,2,4-byte read and 4-byte write. + * Stored in network byte order. + */ + __u32 user_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. + * Stored in network byte order. + */ + __u32 user_port; /* Allows 4-byte read and write. + * Stored in network byte order + */ + __u32 family; /* Allows 4-byte read, but no write */ + __u32 type; /* Allows 4-byte read, but no write */ + __u32 protocol; /* Allows 4-byte read, but no write */ + __u32 msg_src_ip4; /* Allows 1,2,4-byte read an 4-byte write. + * Stored in network byte order. + */ + __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. + * Stored in network byte order. + */ +}; + +/* User bpf_sock_ops struct to access socket values and specify request ops + * and their replies. + * Some of this fields are in network (bigendian) byte order and may need + * to be converted before use (bpf_ntohl() defined in samples/bpf/bpf_endian.h). + * New fields can only be added at the end of this structure + */ +struct bpf_sock_ops { + __u32 op; + union { + __u32 args[4]; /* Optionally passed to bpf program */ + __u32 reply; /* Returned by bpf program */ + __u32 replylong[4]; /* Optionally returned by bpf prog */ + }; + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ + __u32 is_fullsock; /* Some TCP fields are only valid if + * there is a full socket. If not, the + * fields read as zero. + */ + __u32 snd_cwnd; + __u32 srtt_us; /* Averaged RTT << 3 in usecs */ + __u32 bpf_sock_ops_cb_flags; /* flags defined in uapi/linux/tcp.h */ + __u32 state; + __u32 rtt_min; + __u32 snd_ssthresh; + __u32 rcv_nxt; + __u32 snd_nxt; + __u32 snd_una; + __u32 mss_cache; + __u32 ecn_flags; + __u32 rate_delivered; + __u32 rate_interval_us; + __u32 packets_out; + __u32 retrans_out; + __u32 total_retrans; + __u32 segs_in; + __u32 data_segs_in; + __u32 segs_out; + __u32 data_segs_out; + __u32 lost_out; + __u32 sacked_out; + __u32 sk_txhash; + __u64 bytes_received; + __u64 bytes_acked; +}; + +/* Definitions for bpf_sock_ops_cb_flags */ +#define BPF_SOCK_OPS_RTO_CB_FLAG (1<<0) +#define BPF_SOCK_OPS_RETRANS_CB_FLAG (1<<1) +#define BPF_SOCK_OPS_STATE_CB_FLAG (1<<2) +#define BPF_SOCK_OPS_ALL_CB_FLAGS 0x7 /* Mask of all currently + * supported cb flags + */ + +/* List of known BPF sock_ops operators. + * New entries can only be added at the end + */ +enum { + BPF_SOCK_OPS_VOID, + BPF_SOCK_OPS_TIMEOUT_INIT, /* Should return SYN-RTO value to use or + * -1 if default value should be used + */ + BPF_SOCK_OPS_RWND_INIT, /* Should return initial advertized + * window (in packets) or -1 if default + * value should be used + */ + BPF_SOCK_OPS_TCP_CONNECT_CB, /* Calls BPF program right before an + * active connection is initialized + */ + BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB, /* Calls BPF program when an + * active connection is + * established + */ + BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, /* Calls BPF program when a + * passive connection is + * established + */ + BPF_SOCK_OPS_NEEDS_ECN, /* If connection's congestion control + * needs ECN + */ + BPF_SOCK_OPS_BASE_RTT, /* Get base RTT. The correct value is + * based on the path and may be + * dependent on the congestion control + * algorithm. In general it indicates + * a congestion threshold. RTTs above + * this indicate congestion + */ + BPF_SOCK_OPS_RTO_CB, /* Called when an RTO has triggered. + * Arg1: value of icsk_retransmits + * Arg2: value of icsk_rto + * Arg3: whether RTO has expired + */ + BPF_SOCK_OPS_RETRANS_CB, /* Called when skb is retransmitted. + * Arg1: sequence number of 1st byte + * Arg2: # segments + * Arg3: return value of + * tcp_transmit_skb (0 => success) + */ + BPF_SOCK_OPS_STATE_CB, /* Called when TCP changes state. + * Arg1: old_state + * Arg2: new_state + */ + BPF_SOCK_OPS_TCP_LISTEN_CB, /* Called on listen(2), right after + * socket transition to LISTEN state. + */ +}; + +/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect + * changes between the TCP and BPF versions. Ideally this should never happen. + * If it does, we need to add code to convert them before calling + * the BPF sock_ops function. + */ +enum { + BPF_TCP_ESTABLISHED = 1, + BPF_TCP_SYN_SENT, + BPF_TCP_SYN_RECV, + BPF_TCP_FIN_WAIT1, + BPF_TCP_FIN_WAIT2, + BPF_TCP_TIME_WAIT, + BPF_TCP_CLOSE, + BPF_TCP_CLOSE_WAIT, + BPF_TCP_LAST_ACK, + BPF_TCP_LISTEN, + BPF_TCP_CLOSING, /* Now a valid state */ + BPF_TCP_NEW_SYN_RECV, + + BPF_TCP_MAX_STATES /* Leave at the end! */ +}; + +#define TCP_BPF_IW 1001 /* Set TCP initial congestion window */ +#define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */ + +struct bpf_perf_event_value { + __u64 counter; + __u64 enabled; + __u64 running; +}; + +#define BPF_DEVCG_ACC_MKNOD (1ULL << 0) +#define BPF_DEVCG_ACC_READ (1ULL << 1) +#define BPF_DEVCG_ACC_WRITE (1ULL << 2) + +#define BPF_DEVCG_DEV_BLOCK (1ULL << 0) +#define BPF_DEVCG_DEV_CHAR (1ULL << 1) + +struct bpf_cgroup_dev_ctx { + /* access_type encoded as (BPF_DEVCG_ACC_* << 16) | BPF_DEVCG_DEV_* */ + __u32 access_type; + __u32 major; + __u32 minor; +}; + +struct bpf_raw_tracepoint_args { + __u64 args[0]; +}; + +/* DIRECT: Skip the FIB rules and go to FIB table associated with device + * OUTPUT: Do lookup from egress perspective; default is ingress + */ +#define BPF_FIB_LOOKUP_DIRECT BIT(0) +#define BPF_FIB_LOOKUP_OUTPUT BIT(1) + +enum { + BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */ + BPF_FIB_LKUP_RET_BLACKHOLE, /* dest is blackholed; can be dropped */ + BPF_FIB_LKUP_RET_UNREACHABLE, /* dest is unreachable; can be dropped */ + BPF_FIB_LKUP_RET_PROHIBIT, /* dest not allowed; can be dropped */ + BPF_FIB_LKUP_RET_NOT_FWDED, /* packet is not forwarded */ + BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */ + BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */ + BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */ + BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */ +}; + +struct bpf_fib_lookup { + /* input: network family for lookup (AF_INET, AF_INET6) + * output: network family of egress nexthop + */ + __u8 family; + + /* set if lookup is to consider L4 data - e.g., FIB rules */ + __u8 l4_protocol; + __be16 sport; + __be16 dport; + + /* total length of packet from network header - used for MTU check */ + __u16 tot_len; + + /* input: L3 device index for lookup + * output: device index from FIB lookup + */ + __u32 ifindex; + + union { + /* inputs to lookup */ + __u8 tos; /* AF_INET */ + __be32 flowinfo; /* AF_INET6, flow_label + priority */ + + /* output: metric of fib result (IPv4/IPv6 only) */ + __u32 rt_metric; + }; + + union { + __be32 ipv4_src; + __u32 ipv6_src[4]; /* in6_addr; network order */ + }; + + /* input to bpf_fib_lookup, ipv{4,6}_dst is destination address in + * network header. output: bpf_fib_lookup sets to gateway address + * if FIB lookup returns gateway route + */ + union { + __be32 ipv4_dst; + __u32 ipv6_dst[4]; /* in6_addr; network order */ + }; + + /* output */ + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + __u8 smac[6]; /* ETH_ALEN */ + __u8 dmac[6]; /* ETH_ALEN */ +}; + +enum bpf_task_fd_type { + BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */ + BPF_FD_TYPE_TRACEPOINT, /* tp name */ + BPF_FD_TYPE_KPROBE, /* (symbol + offset) or addr */ + BPF_FD_TYPE_KRETPROBE, /* (symbol + offset) or addr */ + BPF_FD_TYPE_UPROBE, /* filename + offset */ + BPF_FD_TYPE_URETPROBE, /* filename + offset */ +}; + +struct bpf_flow_keys { + __u16 nhoff; + __u16 thoff; + __u16 addr_proto; /* ETH_P_* of valid addrs */ + __u8 is_frag; + __u8 is_first_frag; + __u8 is_encap; + __u8 ip_proto; + __be16 n_proto; + __be16 sport; + __be16 dport; + union { + struct { + __be32 ipv4_src; + __be32 ipv4_dst; + }; + struct { + __u32 ipv6_src[4]; /* in6_addr; network order */ + __u32 ipv6_dst[4]; /* in6_addr; network order */ + }; + }; +}; + +struct bpf_func_info { + __u32 insn_off; + __u32 type_id; +}; + +#define BPF_LINE_INFO_LINE_NUM(line_col) ((line_col) >> 10) +#define BPF_LINE_INFO_LINE_COL(line_col) ((line_col) & 0x3ff) + +struct bpf_line_info { + __u32 insn_off; + __u32 file_name_off; + __u32 line_off; + __u32 line_col; +}; + +struct bpf_spin_lock { + __u32 val; +}; +#endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/src/xdp/include/linux/err.h b/src/xdp/include/linux/err.h new file mode 100644 index 000000000..a3db4cf5e --- /dev/null +++ b/src/xdp/include/linux/err.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +#ifndef __LINUX_ERR_H +#define __LINUX_ERR_H + +#include <linux/types.h> +#include <asm/errno.h> + +#define MAX_ERRNO 4095 + +#define IS_ERR_VALUE(x) ((x) >= (unsigned long)-MAX_ERRNO) + +static inline void * ERR_PTR(long error_) +{ + return (void *) error_; +} + +static inline long PTR_ERR(const void *ptr) +{ + return (long) ptr; +} + +static inline bool IS_ERR(const void *ptr) +{ + return IS_ERR_VALUE((unsigned long)ptr); +} + +static inline bool IS_ERR_OR_NULL(const void *ptr) +{ + return (!ptr) || IS_ERR_VALUE((unsigned long)ptr); +} + +#endif diff --git a/src/xdp/include/linux/if_link.h b/src/xdp/include/linux/if_link.h new file mode 100644 index 000000000..5b225ff63 --- /dev/null +++ b/src/xdp/include/linux/if_link.h @@ -0,0 +1,1025 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_IF_LINK_H +#define _UAPI_LINUX_IF_LINK_H + +#include <linux/types.h> +#include <linux/netlink.h> + +/* This struct should be in sync with struct rtnl_link_stats64 */ +struct rtnl_link_stats { + __u32 rx_packets; /* total packets received */ + __u32 tx_packets; /* total packets transmitted */ + __u32 rx_bytes; /* total bytes received */ + __u32 tx_bytes; /* total bytes transmitted */ + __u32 rx_errors; /* bad packets received */ + __u32 tx_errors; /* packet transmit problems */ + __u32 rx_dropped; /* no space in linux buffers */ + __u32 tx_dropped; /* no space available in linux */ + __u32 multicast; /* multicast packets received */ + __u32 collisions; + + /* detailed rx_errors: */ + __u32 rx_length_errors; + __u32 rx_over_errors; /* receiver ring buff overflow */ + __u32 rx_crc_errors; /* recved pkt with crc error */ + __u32 rx_frame_errors; /* recv'd frame alignment error */ + __u32 rx_fifo_errors; /* recv'r fifo overrun */ + __u32 rx_missed_errors; /* receiver missed packet */ + + /* detailed tx_errors */ + __u32 tx_aborted_errors; + __u32 tx_carrier_errors; + __u32 tx_fifo_errors; + __u32 tx_heartbeat_errors; + __u32 tx_window_errors; + + /* for cslip etc */ + __u32 rx_compressed; + __u32 tx_compressed; + + __u32 rx_nohandler; /* dropped, no handler found */ +}; + +/* The main device statistics structure */ +struct rtnl_link_stats64 { + __u64 rx_packets; /* total packets received */ + __u64 tx_packets; /* total packets transmitted */ + __u64 rx_bytes; /* total bytes received */ + __u64 tx_bytes; /* total bytes transmitted */ + __u64 rx_errors; /* bad packets received */ + __u64 tx_errors; /* packet transmit problems */ + __u64 rx_dropped; /* no space in linux buffers */ + __u64 tx_dropped; /* no space available in linux */ + __u64 multicast; /* multicast packets received */ + __u64 collisions; + + /* detailed rx_errors: */ + __u64 rx_length_errors; + __u64 rx_over_errors; /* receiver ring buff overflow */ + __u64 rx_crc_errors; /* recved pkt with crc error */ + __u64 rx_frame_errors; /* recv'd frame alignment error */ + __u64 rx_fifo_errors; /* recv'r fifo overrun */ + __u64 rx_missed_errors; /* receiver missed packet */ + + /* detailed tx_errors */ + __u64 tx_aborted_errors; + __u64 tx_carrier_errors; + __u64 tx_fifo_errors; + __u64 tx_heartbeat_errors; + __u64 tx_window_errors; + + /* for cslip etc */ + __u64 rx_compressed; + __u64 tx_compressed; + + __u64 rx_nohandler; /* dropped, no handler found */ +}; + +/* The struct should be in sync with struct ifmap */ +struct rtnl_link_ifmap { + __u64 mem_start; + __u64 mem_end; + __u64 base_addr; + __u16 irq; + __u8 dma; + __u8 port; +}; + +/* + * IFLA_AF_SPEC + * Contains nested attributes for address family specific attributes. + * Each address family may create a attribute with the address family + * number as type and create its own attribute structure in it. + * + * Example: + * [IFLA_AF_SPEC] = { + * [AF_INET] = { + * [IFLA_INET_CONF] = ..., + * }, + * [AF_INET6] = { + * [IFLA_INET6_FLAGS] = ..., + * [IFLA_INET6_CONF] = ..., + * } + * } + */ + +enum { + IFLA_UNSPEC, + IFLA_ADDRESS, + IFLA_BROADCAST, + IFLA_IFNAME, + IFLA_MTU, + IFLA_LINK, + IFLA_QDISC, + IFLA_STATS, + IFLA_COST, +#define IFLA_COST IFLA_COST + IFLA_PRIORITY, +#define IFLA_PRIORITY IFLA_PRIORITY + IFLA_MASTER, +#define IFLA_MASTER IFLA_MASTER + IFLA_WIRELESS, /* Wireless Extension event - see wireless.h */ +#define IFLA_WIRELESS IFLA_WIRELESS + IFLA_PROTINFO, /* Protocol specific information for a link */ +#define IFLA_PROTINFO IFLA_PROTINFO + IFLA_TXQLEN, +#define IFLA_TXQLEN IFLA_TXQLEN + IFLA_MAP, +#define IFLA_MAP IFLA_MAP + IFLA_WEIGHT, +#define IFLA_WEIGHT IFLA_WEIGHT + IFLA_OPERSTATE, + IFLA_LINKMODE, + IFLA_LINKINFO, +#define IFLA_LINKINFO IFLA_LINKINFO + IFLA_NET_NS_PID, + IFLA_IFALIAS, + IFLA_NUM_VF, /* Number of VFs if device is SR-IOV PF */ + IFLA_VFINFO_LIST, + IFLA_STATS64, + IFLA_VF_PORTS, + IFLA_PORT_SELF, + IFLA_AF_SPEC, + IFLA_GROUP, /* Group the device belongs to */ + IFLA_NET_NS_FD, + IFLA_EXT_MASK, /* Extended info mask, VFs, etc */ + IFLA_PROMISCUITY, /* Promiscuity count: > 0 means acts PROMISC */ +#define IFLA_PROMISCUITY IFLA_PROMISCUITY + IFLA_NUM_TX_QUEUES, + IFLA_NUM_RX_QUEUES, + IFLA_CARRIER, + IFLA_PHYS_PORT_ID, + IFLA_CARRIER_CHANGES, + IFLA_PHYS_SWITCH_ID, + IFLA_LINK_NETNSID, + IFLA_PHYS_PORT_NAME, + IFLA_PROTO_DOWN, + IFLA_GSO_MAX_SEGS, + IFLA_GSO_MAX_SIZE, + IFLA_PAD, + IFLA_XDP, + IFLA_EVENT, + IFLA_NEW_NETNSID, + IFLA_IF_NETNSID, + IFLA_TARGET_NETNSID = IFLA_IF_NETNSID, /* new alias */ + IFLA_CARRIER_UP_COUNT, + IFLA_CARRIER_DOWN_COUNT, + IFLA_NEW_IFINDEX, + IFLA_MIN_MTU, + IFLA_MAX_MTU, + __IFLA_MAX +}; + + +#define IFLA_MAX (__IFLA_MAX - 1) + +/* backwards compatibility for userspace */ +#ifndef __KERNEL__ +#define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg)))) +#define IFLA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifinfomsg)) +#endif + +enum { + IFLA_INET_UNSPEC, + IFLA_INET_CONF, + __IFLA_INET_MAX, +}; + +#define IFLA_INET_MAX (__IFLA_INET_MAX - 1) + +/* ifi_flags. + + IFF_* flags. + + The only change is: + IFF_LOOPBACK, IFF_BROADCAST and IFF_POINTOPOINT are + more not changeable by user. They describe link media + characteristics and set by device driver. + + Comments: + - Combination IFF_BROADCAST|IFF_POINTOPOINT is invalid + - If neither of these three flags are set; + the interface is NBMA. + + - IFF_MULTICAST does not mean anything special: + multicasts can be used on all not-NBMA links. + IFF_MULTICAST means that this media uses special encapsulation + for multicast frames. Apparently, all IFF_POINTOPOINT and + IFF_BROADCAST devices are able to use multicasts too. + */ + +/* IFLA_LINK. + For usual devices it is equal ifi_index. + If it is a "virtual interface" (f.e. tunnel), ifi_link + can point to real physical interface (f.e. for bandwidth calculations), + or maybe 0, what means, that real media is unknown (usual + for IPIP tunnels, when route to endpoint is allowed to change) + */ + +/* Subtype attributes for IFLA_PROTINFO */ +enum { + IFLA_INET6_UNSPEC, + IFLA_INET6_FLAGS, /* link flags */ + IFLA_INET6_CONF, /* sysctl parameters */ + IFLA_INET6_STATS, /* statistics */ + IFLA_INET6_MCAST, /* MC things. What of them? */ + IFLA_INET6_CACHEINFO, /* time values and max reasm size */ + IFLA_INET6_ICMP6STATS, /* statistics (icmpv6) */ + IFLA_INET6_TOKEN, /* device token */ + IFLA_INET6_ADDR_GEN_MODE, /* implicit address generator mode */ + __IFLA_INET6_MAX +}; + +#define IFLA_INET6_MAX (__IFLA_INET6_MAX - 1) + +enum in6_addr_gen_mode { + IN6_ADDR_GEN_MODE_EUI64, + IN6_ADDR_GEN_MODE_NONE, + IN6_ADDR_GEN_MODE_STABLE_PRIVACY, + IN6_ADDR_GEN_MODE_RANDOM, +}; + +/* Bridge section */ + +enum { + IFLA_BR_UNSPEC, + IFLA_BR_FORWARD_DELAY, + IFLA_BR_HELLO_TIME, + IFLA_BR_MAX_AGE, + IFLA_BR_AGEING_TIME, + IFLA_BR_STP_STATE, + IFLA_BR_PRIORITY, + IFLA_BR_VLAN_FILTERING, + IFLA_BR_VLAN_PROTOCOL, + IFLA_BR_GROUP_FWD_MASK, + IFLA_BR_ROOT_ID, + IFLA_BR_BRIDGE_ID, + IFLA_BR_ROOT_PORT, + IFLA_BR_ROOT_PATH_COST, + IFLA_BR_TOPOLOGY_CHANGE, + IFLA_BR_TOPOLOGY_CHANGE_DETECTED, + IFLA_BR_HELLO_TIMER, + IFLA_BR_TCN_TIMER, + IFLA_BR_TOPOLOGY_CHANGE_TIMER, + IFLA_BR_GC_TIMER, + IFLA_BR_GROUP_ADDR, + IFLA_BR_FDB_FLUSH, + IFLA_BR_MCAST_ROUTER, + IFLA_BR_MCAST_SNOOPING, + IFLA_BR_MCAST_QUERY_USE_IFADDR, + IFLA_BR_MCAST_QUERIER, + IFLA_BR_MCAST_HASH_ELASTICITY, + IFLA_BR_MCAST_HASH_MAX, + IFLA_BR_MCAST_LAST_MEMBER_CNT, + IFLA_BR_MCAST_STARTUP_QUERY_CNT, + IFLA_BR_MCAST_LAST_MEMBER_INTVL, + IFLA_BR_MCAST_MEMBERSHIP_INTVL, + IFLA_BR_MCAST_QUERIER_INTVL, + IFLA_BR_MCAST_QUERY_INTVL, + IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, + IFLA_BR_MCAST_STARTUP_QUERY_INTVL, + IFLA_BR_NF_CALL_IPTABLES, + IFLA_BR_NF_CALL_IP6TABLES, + IFLA_BR_NF_CALL_ARPTABLES, + IFLA_BR_VLAN_DEFAULT_PVID, + IFLA_BR_PAD, + IFLA_BR_VLAN_STATS_ENABLED, + IFLA_BR_MCAST_STATS_ENABLED, + IFLA_BR_MCAST_IGMP_VERSION, + IFLA_BR_MCAST_MLD_VERSION, + IFLA_BR_VLAN_STATS_PER_PORT, + IFLA_BR_MULTI_BOOLOPT, + __IFLA_BR_MAX, +}; + +#define IFLA_BR_MAX (__IFLA_BR_MAX - 1) + +struct ifla_bridge_id { + __u8 prio[2]; + __u8 addr[6]; /* ETH_ALEN */ +}; + +enum { + BRIDGE_MODE_UNSPEC, + BRIDGE_MODE_HAIRPIN, +}; + +enum { + IFLA_BRPORT_UNSPEC, + IFLA_BRPORT_STATE, /* Spanning tree state */ + IFLA_BRPORT_PRIORITY, /* " priority */ + IFLA_BRPORT_COST, /* " cost */ + IFLA_BRPORT_MODE, /* mode (hairpin) */ + IFLA_BRPORT_GUARD, /* bpdu guard */ + IFLA_BRPORT_PROTECT, /* root port protection */ + IFLA_BRPORT_FAST_LEAVE, /* multicast fast leave */ + IFLA_BRPORT_LEARNING, /* mac learning */ + IFLA_BRPORT_UNICAST_FLOOD, /* flood unicast traffic */ + IFLA_BRPORT_PROXYARP, /* proxy ARP */ + IFLA_BRPORT_LEARNING_SYNC, /* mac learning sync from device */ + IFLA_BRPORT_PROXYARP_WIFI, /* proxy ARP for Wi-Fi */ + IFLA_BRPORT_ROOT_ID, /* designated root */ + IFLA_BRPORT_BRIDGE_ID, /* designated bridge */ + IFLA_BRPORT_DESIGNATED_PORT, + IFLA_BRPORT_DESIGNATED_COST, + IFLA_BRPORT_ID, + IFLA_BRPORT_NO, + IFLA_BRPORT_TOPOLOGY_CHANGE_ACK, + IFLA_BRPORT_CONFIG_PENDING, + IFLA_BRPORT_MESSAGE_AGE_TIMER, + IFLA_BRPORT_FORWARD_DELAY_TIMER, + IFLA_BRPORT_HOLD_TIMER, + IFLA_BRPORT_FLUSH, + IFLA_BRPORT_MULTICAST_ROUTER, + IFLA_BRPORT_PAD, + IFLA_BRPORT_MCAST_FLOOD, + IFLA_BRPORT_MCAST_TO_UCAST, + IFLA_BRPORT_VLAN_TUNNEL, + IFLA_BRPORT_BCAST_FLOOD, + IFLA_BRPORT_GROUP_FWD_MASK, + IFLA_BRPORT_NEIGH_SUPPRESS, + IFLA_BRPORT_ISOLATED, + IFLA_BRPORT_BACKUP_PORT, + __IFLA_BRPORT_MAX +}; +#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) + +struct ifla_cacheinfo { + __u32 max_reasm_len; + __u32 tstamp; /* ipv6InterfaceTable updated timestamp */ + __u32 reachable_time; + __u32 retrans_time; +}; + +enum { + IFLA_INFO_UNSPEC, + IFLA_INFO_KIND, + IFLA_INFO_DATA, + IFLA_INFO_XSTATS, + IFLA_INFO_SLAVE_KIND, + IFLA_INFO_SLAVE_DATA, + __IFLA_INFO_MAX, +}; + +#define IFLA_INFO_MAX (__IFLA_INFO_MAX - 1) + +/* VLAN section */ + +enum { + IFLA_VLAN_UNSPEC, + IFLA_VLAN_ID, + IFLA_VLAN_FLAGS, + IFLA_VLAN_EGRESS_QOS, + IFLA_VLAN_INGRESS_QOS, + IFLA_VLAN_PROTOCOL, + __IFLA_VLAN_MAX, +}; + +#define IFLA_VLAN_MAX (__IFLA_VLAN_MAX - 1) + +struct ifla_vlan_flags { + __u32 flags; + __u32 mask; +}; + +enum { + IFLA_VLAN_QOS_UNSPEC, + IFLA_VLAN_QOS_MAPPING, + __IFLA_VLAN_QOS_MAX +}; + +#define IFLA_VLAN_QOS_MAX (__IFLA_VLAN_QOS_MAX - 1) + +struct ifla_vlan_qos_mapping { + __u32 from; + __u32 to; +}; + +/* MACVLAN section */ +enum { + IFLA_MACVLAN_UNSPEC, + IFLA_MACVLAN_MODE, + IFLA_MACVLAN_FLAGS, + IFLA_MACVLAN_MACADDR_MODE, + IFLA_MACVLAN_MACADDR, + IFLA_MACVLAN_MACADDR_DATA, + IFLA_MACVLAN_MACADDR_COUNT, + __IFLA_MACVLAN_MAX, +}; + +#define IFLA_MACVLAN_MAX (__IFLA_MACVLAN_MAX - 1) + +enum macvlan_mode { + MACVLAN_MODE_PRIVATE = 1, /* don't talk to other macvlans */ + MACVLAN_MODE_VEPA = 2, /* talk to other ports through ext bridge */ + MACVLAN_MODE_BRIDGE = 4, /* talk to bridge ports directly */ + MACVLAN_MODE_PASSTHRU = 8,/* take over the underlying device */ + MACVLAN_MODE_SOURCE = 16,/* use source MAC address list to assign */ +}; + +enum macvlan_macaddr_mode { + MACVLAN_MACADDR_ADD, + MACVLAN_MACADDR_DEL, + MACVLAN_MACADDR_FLUSH, + MACVLAN_MACADDR_SET, +}; + +#define MACVLAN_FLAG_NOPROMISC 1 + +/* VRF section */ +enum { + IFLA_VRF_UNSPEC, + IFLA_VRF_TABLE, + __IFLA_VRF_MAX +}; + +#define IFLA_VRF_MAX (__IFLA_VRF_MAX - 1) + +enum { + IFLA_VRF_PORT_UNSPEC, + IFLA_VRF_PORT_TABLE, + __IFLA_VRF_PORT_MAX +}; + +#define IFLA_VRF_PORT_MAX (__IFLA_VRF_PORT_MAX - 1) + +/* MACSEC section */ +enum { + IFLA_MACSEC_UNSPEC, + IFLA_MACSEC_SCI, + IFLA_MACSEC_PORT, + IFLA_MACSEC_ICV_LEN, + IFLA_MACSEC_CIPHER_SUITE, + IFLA_MACSEC_WINDOW, + IFLA_MACSEC_ENCODING_SA, + IFLA_MACSEC_ENCRYPT, + IFLA_MACSEC_PROTECT, + IFLA_MACSEC_INC_SCI, + IFLA_MACSEC_ES, + IFLA_MACSEC_SCB, + IFLA_MACSEC_REPLAY_PROTECT, + IFLA_MACSEC_VALIDATION, + IFLA_MACSEC_PAD, + __IFLA_MACSEC_MAX, +}; + +#define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1) + +/* XFRM section */ +enum { + IFLA_XFRM_UNSPEC, + IFLA_XFRM_LINK, + IFLA_XFRM_IF_ID, + __IFLA_XFRM_MAX +}; + +#define IFLA_XFRM_MAX (__IFLA_XFRM_MAX - 1) + +enum macsec_validation_type { + MACSEC_VALIDATE_DISABLED = 0, + MACSEC_VALIDATE_CHECK = 1, + MACSEC_VALIDATE_STRICT = 2, + __MACSEC_VALIDATE_END, + MACSEC_VALIDATE_MAX = __MACSEC_VALIDATE_END - 1, +}; + +/* IPVLAN section */ +enum { + IFLA_IPVLAN_UNSPEC, + IFLA_IPVLAN_MODE, + IFLA_IPVLAN_FLAGS, + __IFLA_IPVLAN_MAX +}; + +#define IFLA_IPVLAN_MAX (__IFLA_IPVLAN_MAX - 1) + +enum ipvlan_mode { + IPVLAN_MODE_L2 = 0, + IPVLAN_MODE_L3, + IPVLAN_MODE_L3S, + IPVLAN_MODE_MAX +}; + +#define IPVLAN_F_PRIVATE 0x01 +#define IPVLAN_F_VEPA 0x02 + +/* VXLAN section */ +enum { + IFLA_VXLAN_UNSPEC, + IFLA_VXLAN_ID, + IFLA_VXLAN_GROUP, /* group or remote address */ + IFLA_VXLAN_LINK, + IFLA_VXLAN_LOCAL, + IFLA_VXLAN_TTL, + IFLA_VXLAN_TOS, + IFLA_VXLAN_LEARNING, + IFLA_VXLAN_AGEING, + IFLA_VXLAN_LIMIT, + IFLA_VXLAN_PORT_RANGE, /* source port */ + IFLA_VXLAN_PROXY, + IFLA_VXLAN_RSC, + IFLA_VXLAN_L2MISS, + IFLA_VXLAN_L3MISS, + IFLA_VXLAN_PORT, /* destination port */ + IFLA_VXLAN_GROUP6, + IFLA_VXLAN_LOCAL6, + IFLA_VXLAN_UDP_CSUM, + IFLA_VXLAN_UDP_ZERO_CSUM6_TX, + IFLA_VXLAN_UDP_ZERO_CSUM6_RX, + IFLA_VXLAN_REMCSUM_TX, + IFLA_VXLAN_REMCSUM_RX, + IFLA_VXLAN_GBP, + IFLA_VXLAN_REMCSUM_NOPARTIAL, + IFLA_VXLAN_COLLECT_METADATA, + IFLA_VXLAN_LABEL, + IFLA_VXLAN_GPE, + IFLA_VXLAN_TTL_INHERIT, + IFLA_VXLAN_DF, + __IFLA_VXLAN_MAX +}; +#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) + +struct ifla_vxlan_port_range { + __be16 low; + __be16 high; +}; + +enum ifla_vxlan_df { + VXLAN_DF_UNSET = 0, + VXLAN_DF_SET, + VXLAN_DF_INHERIT, + __VXLAN_DF_END, + VXLAN_DF_MAX = __VXLAN_DF_END - 1, +}; + +/* GENEVE section */ +enum { + IFLA_GENEVE_UNSPEC, + IFLA_GENEVE_ID, + IFLA_GENEVE_REMOTE, + IFLA_GENEVE_TTL, + IFLA_GENEVE_TOS, + IFLA_GENEVE_PORT, /* destination port */ + IFLA_GENEVE_COLLECT_METADATA, + IFLA_GENEVE_REMOTE6, + IFLA_GENEVE_UDP_CSUM, + IFLA_GENEVE_UDP_ZERO_CSUM6_TX, + IFLA_GENEVE_UDP_ZERO_CSUM6_RX, + IFLA_GENEVE_LABEL, + IFLA_GENEVE_TTL_INHERIT, + IFLA_GENEVE_DF, + __IFLA_GENEVE_MAX +}; +#define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) + +enum ifla_geneve_df { + GENEVE_DF_UNSET = 0, + GENEVE_DF_SET, + GENEVE_DF_INHERIT, + __GENEVE_DF_END, + GENEVE_DF_MAX = __GENEVE_DF_END - 1, +}; + +/* PPP section */ +enum { + IFLA_PPP_UNSPEC, + IFLA_PPP_DEV_FD, + __IFLA_PPP_MAX +}; +#define IFLA_PPP_MAX (__IFLA_PPP_MAX - 1) + +/* GTP section */ + +enum ifla_gtp_role { + GTP_ROLE_GGSN = 0, + GTP_ROLE_SGSN, +}; + +enum { + IFLA_GTP_UNSPEC, + IFLA_GTP_FD0, + IFLA_GTP_FD1, + IFLA_GTP_PDP_HASHSIZE, + IFLA_GTP_ROLE, + __IFLA_GTP_MAX, +}; +#define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) + +/* Bonding section */ + +enum { + IFLA_BOND_UNSPEC, + IFLA_BOND_MODE, + IFLA_BOND_ACTIVE_SLAVE, + IFLA_BOND_MIIMON, + IFLA_BOND_UPDELAY, + IFLA_BOND_DOWNDELAY, + IFLA_BOND_USE_CARRIER, + IFLA_BOND_ARP_INTERVAL, + IFLA_BOND_ARP_IP_TARGET, + IFLA_BOND_ARP_VALIDATE, + IFLA_BOND_ARP_ALL_TARGETS, + IFLA_BOND_PRIMARY, + IFLA_BOND_PRIMARY_RESELECT, + IFLA_BOND_FAIL_OVER_MAC, + IFLA_BOND_XMIT_HASH_POLICY, + IFLA_BOND_RESEND_IGMP, + IFLA_BOND_NUM_PEER_NOTIF, + IFLA_BOND_ALL_SLAVES_ACTIVE, + IFLA_BOND_MIN_LINKS, + IFLA_BOND_LP_INTERVAL, + IFLA_BOND_PACKETS_PER_SLAVE, + IFLA_BOND_AD_LACP_RATE, + IFLA_BOND_AD_SELECT, + IFLA_BOND_AD_INFO, + IFLA_BOND_AD_ACTOR_SYS_PRIO, + IFLA_BOND_AD_USER_PORT_KEY, + IFLA_BOND_AD_ACTOR_SYSTEM, + IFLA_BOND_TLB_DYNAMIC_LB, + __IFLA_BOND_MAX, +}; + +#define IFLA_BOND_MAX (__IFLA_BOND_MAX - 1) + +enum { + IFLA_BOND_AD_INFO_UNSPEC, + IFLA_BOND_AD_INFO_AGGREGATOR, + IFLA_BOND_AD_INFO_NUM_PORTS, + IFLA_BOND_AD_INFO_ACTOR_KEY, + IFLA_BOND_AD_INFO_PARTNER_KEY, + IFLA_BOND_AD_INFO_PARTNER_MAC, + __IFLA_BOND_AD_INFO_MAX, +}; + +#define IFLA_BOND_AD_INFO_MAX (__IFLA_BOND_AD_INFO_MAX - 1) + +enum { + IFLA_BOND_SLAVE_UNSPEC, + IFLA_BOND_SLAVE_STATE, + IFLA_BOND_SLAVE_MII_STATUS, + IFLA_BOND_SLAVE_LINK_FAILURE_COUNT, + IFLA_BOND_SLAVE_PERM_HWADDR, + IFLA_BOND_SLAVE_QUEUE_ID, + IFLA_BOND_SLAVE_AD_AGGREGATOR_ID, + IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE, + IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE, + __IFLA_BOND_SLAVE_MAX, +}; + +#define IFLA_BOND_SLAVE_MAX (__IFLA_BOND_SLAVE_MAX - 1) + +/* SR-IOV virtual function management section */ + +enum { + IFLA_VF_INFO_UNSPEC, + IFLA_VF_INFO, + __IFLA_VF_INFO_MAX, +}; + +#define IFLA_VF_INFO_MAX (__IFLA_VF_INFO_MAX - 1) + +enum { + IFLA_VF_UNSPEC, + IFLA_VF_MAC, /* Hardware queue specific attributes */ + IFLA_VF_VLAN, /* VLAN ID and QoS */ + IFLA_VF_TX_RATE, /* Max TX Bandwidth Allocation */ + IFLA_VF_SPOOFCHK, /* Spoof Checking on/off switch */ + IFLA_VF_LINK_STATE, /* link state enable/disable/auto switch */ + IFLA_VF_RATE, /* Min and Max TX Bandwidth Allocation */ + IFLA_VF_RSS_QUERY_EN, /* RSS Redirection Table and Hash Key query + * on/off switch + */ + IFLA_VF_STATS, /* network device statistics */ + IFLA_VF_TRUST, /* Trust VF */ + IFLA_VF_IB_NODE_GUID, /* VF Infiniband node GUID */ + IFLA_VF_IB_PORT_GUID, /* VF Infiniband port GUID */ + IFLA_VF_VLAN_LIST, /* nested list of vlans, option for QinQ */ + __IFLA_VF_MAX, +}; + +#define IFLA_VF_MAX (__IFLA_VF_MAX - 1) + +struct ifla_vf_mac { + __u32 vf; + __u8 mac[32]; /* MAX_ADDR_LEN */ +}; + +struct ifla_vf_vlan { + __u32 vf; + __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */ + __u32 qos; +}; + +enum { + IFLA_VF_VLAN_INFO_UNSPEC, + IFLA_VF_VLAN_INFO, /* VLAN ID, QoS and VLAN protocol */ + __IFLA_VF_VLAN_INFO_MAX, +}; + +#define IFLA_VF_VLAN_INFO_MAX (__IFLA_VF_VLAN_INFO_MAX - 1) +#define MAX_VLAN_LIST_LEN 1 + +struct ifla_vf_vlan_info { + __u32 vf; + __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */ + __u32 qos; + __be16 vlan_proto; /* VLAN protocol either 802.1Q or 802.1ad */ +}; + +struct ifla_vf_tx_rate { + __u32 vf; + __u32 rate; /* Max TX bandwidth in Mbps, 0 disables throttling */ +}; + +struct ifla_vf_rate { + __u32 vf; + __u32 min_tx_rate; /* Min Bandwidth in Mbps */ + __u32 max_tx_rate; /* Max Bandwidth in Mbps */ +}; + +struct ifla_vf_spoofchk { + __u32 vf; + __u32 setting; +}; + +struct ifla_vf_guid { + __u32 vf; + __u64 guid; +}; + +enum { + IFLA_VF_LINK_STATE_AUTO, /* link state of the uplink */ + IFLA_VF_LINK_STATE_ENABLE, /* link always up */ + IFLA_VF_LINK_STATE_DISABLE, /* link always down */ + __IFLA_VF_LINK_STATE_MAX, +}; + +struct ifla_vf_link_state { + __u32 vf; + __u32 link_state; +}; + +struct ifla_vf_rss_query_en { + __u32 vf; + __u32 setting; +}; + +enum { + IFLA_VF_STATS_RX_PACKETS, + IFLA_VF_STATS_TX_PACKETS, + IFLA_VF_STATS_RX_BYTES, + IFLA_VF_STATS_TX_BYTES, + IFLA_VF_STATS_BROADCAST, + IFLA_VF_STATS_MULTICAST, + IFLA_VF_STATS_PAD, + IFLA_VF_STATS_RX_DROPPED, + IFLA_VF_STATS_TX_DROPPED, + __IFLA_VF_STATS_MAX, +}; + +#define IFLA_VF_STATS_MAX (__IFLA_VF_STATS_MAX - 1) + +struct ifla_vf_trust { + __u32 vf; + __u32 setting; +}; + +/* VF ports management section + * + * Nested layout of set/get msg is: + * + * [IFLA_NUM_VF] + * [IFLA_VF_PORTS] + * [IFLA_VF_PORT] + * [IFLA_PORT_*], ... + * [IFLA_VF_PORT] + * [IFLA_PORT_*], ... + * ... + * [IFLA_PORT_SELF] + * [IFLA_PORT_*], ... + */ + +enum { + IFLA_VF_PORT_UNSPEC, + IFLA_VF_PORT, /* nest */ + __IFLA_VF_PORT_MAX, +}; + +#define IFLA_VF_PORT_MAX (__IFLA_VF_PORT_MAX - 1) + +enum { + IFLA_PORT_UNSPEC, + IFLA_PORT_VF, /* __u32 */ + IFLA_PORT_PROFILE, /* string */ + IFLA_PORT_VSI_TYPE, /* 802.1Qbg (pre-)standard VDP */ + IFLA_PORT_INSTANCE_UUID, /* binary UUID */ + IFLA_PORT_HOST_UUID, /* binary UUID */ + IFLA_PORT_REQUEST, /* __u8 */ + IFLA_PORT_RESPONSE, /* __u16, output only */ + __IFLA_PORT_MAX, +}; + +#define IFLA_PORT_MAX (__IFLA_PORT_MAX - 1) + +#define PORT_PROFILE_MAX 40 +#define PORT_UUID_MAX 16 +#define PORT_SELF_VF -1 + +enum { + PORT_REQUEST_PREASSOCIATE = 0, + PORT_REQUEST_PREASSOCIATE_RR, + PORT_REQUEST_ASSOCIATE, + PORT_REQUEST_DISASSOCIATE, +}; + +enum { + PORT_VDP_RESPONSE_SUCCESS = 0, + PORT_VDP_RESPONSE_INVALID_FORMAT, + PORT_VDP_RESPONSE_INSUFFICIENT_RESOURCES, + PORT_VDP_RESPONSE_UNUSED_VTID, + PORT_VDP_RESPONSE_VTID_VIOLATION, + PORT_VDP_RESPONSE_VTID_VERSION_VIOALTION, + PORT_VDP_RESPONSE_OUT_OF_SYNC, + /* 0x08-0xFF reserved for future VDP use */ + PORT_PROFILE_RESPONSE_SUCCESS = 0x100, + PORT_PROFILE_RESPONSE_INPROGRESS, + PORT_PROFILE_RESPONSE_INVALID, + PORT_PROFILE_RESPONSE_BADSTATE, + PORT_PROFILE_RESPONSE_INSUFFICIENT_RESOURCES, + PORT_PROFILE_RESPONSE_ERROR, +}; + +struct ifla_port_vsi { + __u8 vsi_mgr_id; + __u8 vsi_type_id[3]; + __u8 vsi_type_version; + __u8 pad[3]; +}; + + +/* IPoIB section */ + +enum { + IFLA_IPOIB_UNSPEC, + IFLA_IPOIB_PKEY, + IFLA_IPOIB_MODE, + IFLA_IPOIB_UMCAST, + __IFLA_IPOIB_MAX +}; + +enum { + IPOIB_MODE_DATAGRAM = 0, /* using unreliable datagram QPs */ + IPOIB_MODE_CONNECTED = 1, /* using connected QPs */ +}; + +#define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1) + + +/* HSR section */ + +enum { + IFLA_HSR_UNSPEC, + IFLA_HSR_SLAVE1, + IFLA_HSR_SLAVE2, + IFLA_HSR_MULTICAST_SPEC, /* Last byte of supervision addr */ + IFLA_HSR_SUPERVISION_ADDR, /* Supervision frame multicast addr */ + IFLA_HSR_SEQ_NR, + IFLA_HSR_VERSION, /* HSR version */ + __IFLA_HSR_MAX, +}; + +#define IFLA_HSR_MAX (__IFLA_HSR_MAX - 1) + +/* STATS section */ + +struct if_stats_msg { + __u8 family; + __u8 pad1; + __u16 pad2; + __u32 ifindex; + __u32 filter_mask; +}; + +/* A stats attribute can be netdev specific or a global stat. + * For netdev stats, lets use the prefix IFLA_STATS_LINK_* + */ +enum { + IFLA_STATS_UNSPEC, /* also used as 64bit pad attribute */ + IFLA_STATS_LINK_64, + IFLA_STATS_LINK_XSTATS, + IFLA_STATS_LINK_XSTATS_SLAVE, + IFLA_STATS_LINK_OFFLOAD_XSTATS, + IFLA_STATS_AF_SPEC, + __IFLA_STATS_MAX, +}; + +#define IFLA_STATS_MAX (__IFLA_STATS_MAX - 1) + +#define IFLA_STATS_FILTER_BIT(ATTR) (1 << (ATTR - 1)) + +/* These are embedded into IFLA_STATS_LINK_XSTATS: + * [IFLA_STATS_LINK_XSTATS] + * -> [LINK_XSTATS_TYPE_xxx] + * -> [rtnl link type specific attributes] + */ +enum { + LINK_XSTATS_TYPE_UNSPEC, + LINK_XSTATS_TYPE_BRIDGE, + LINK_XSTATS_TYPE_BOND, + __LINK_XSTATS_TYPE_MAX +}; +#define LINK_XSTATS_TYPE_MAX (__LINK_XSTATS_TYPE_MAX - 1) + +/* These are stats embedded into IFLA_STATS_LINK_OFFLOAD_XSTATS */ +enum { + IFLA_OFFLOAD_XSTATS_UNSPEC, + IFLA_OFFLOAD_XSTATS_CPU_HIT, /* struct rtnl_link_stats64 */ + __IFLA_OFFLOAD_XSTATS_MAX +}; +#define IFLA_OFFLOAD_XSTATS_MAX (__IFLA_OFFLOAD_XSTATS_MAX - 1) + +/* XDP section */ + +#define XDP_FLAGS_UPDATE_IF_NOEXIST (1U << 0) +#define XDP_FLAGS_SKB_MODE (1U << 1) +#define XDP_FLAGS_DRV_MODE (1U << 2) +#define XDP_FLAGS_HW_MODE (1U << 3) +#define XDP_FLAGS_MODES (XDP_FLAGS_SKB_MODE | \ + XDP_FLAGS_DRV_MODE | \ + XDP_FLAGS_HW_MODE) +#define XDP_FLAGS_MASK (XDP_FLAGS_UPDATE_IF_NOEXIST | \ + XDP_FLAGS_MODES) + +/* These are stored into IFLA_XDP_ATTACHED on dump. */ +enum { + XDP_ATTACHED_NONE = 0, + XDP_ATTACHED_DRV, + XDP_ATTACHED_SKB, + XDP_ATTACHED_HW, + XDP_ATTACHED_MULTI, +}; + +enum { + IFLA_XDP_UNSPEC, + IFLA_XDP_FD, + IFLA_XDP_ATTACHED, + IFLA_XDP_FLAGS, + IFLA_XDP_PROG_ID, + IFLA_XDP_DRV_PROG_ID, + IFLA_XDP_SKB_PROG_ID, + IFLA_XDP_HW_PROG_ID, + __IFLA_XDP_MAX, +}; + +#define IFLA_XDP_MAX (__IFLA_XDP_MAX - 1) + +enum { + IFLA_EVENT_NONE, + IFLA_EVENT_REBOOT, /* internal reset / reboot */ + IFLA_EVENT_FEATURES, /* change in offload features */ + IFLA_EVENT_BONDING_FAILOVER, /* change in active slave */ + IFLA_EVENT_NOTIFY_PEERS, /* re-sent grat. arp/ndisc */ + IFLA_EVENT_IGMP_RESEND, /* re-sent IGMP JOIN */ + IFLA_EVENT_BONDING_OPTIONS, /* change in bonding options */ +}; + +/* tun section */ + +enum { + IFLA_TUN_UNSPEC, + IFLA_TUN_OWNER, + IFLA_TUN_GROUP, + IFLA_TUN_TYPE, + IFLA_TUN_PI, + IFLA_TUN_VNET_HDR, + IFLA_TUN_PERSIST, + IFLA_TUN_MULTI_QUEUE, + IFLA_TUN_NUM_QUEUES, + IFLA_TUN_NUM_DISABLED_QUEUES, + __IFLA_TUN_MAX, +}; + +#define IFLA_TUN_MAX (__IFLA_TUN_MAX - 1) + +/* rmnet section */ + +#define RMNET_FLAGS_INGRESS_DEAGGREGATION (1U << 0) +#define RMNET_FLAGS_INGRESS_MAP_COMMANDS (1U << 1) +#define RMNET_FLAGS_INGRESS_MAP_CKSUMV4 (1U << 2) +#define RMNET_FLAGS_EGRESS_MAP_CKSUMV4 (1U << 3) + +enum { + IFLA_RMNET_UNSPEC, + IFLA_RMNET_MUX_ID, + IFLA_RMNET_FLAGS, + __IFLA_RMNET_MAX, +}; + +#define IFLA_RMNET_MAX (__IFLA_RMNET_MAX - 1) + +struct ifla_rmnet_flags { + __u32 flags; + __u32 mask; +}; + +#endif /* _UAPI_LINUX_IF_LINK_H */ diff --git a/src/xdp/include/linux/if_xdp.h b/src/xdp/include/linux/if_xdp.h new file mode 100644 index 000000000..be328c593 --- /dev/null +++ b/src/xdp/include/linux/if_xdp.h @@ -0,0 +1,108 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * if_xdp: XDP socket user-space interface + * Copyright(c) 2018 Intel Corporation. + * + * Author(s): Björn Töpel <bjorn.topel@intel.com> + * Magnus Karlsson <magnus.karlsson@intel.com> + */ + +#ifndef _LINUX_IF_XDP_H +#define _LINUX_IF_XDP_H + +#include <linux/types.h> + +/* Options for the sxdp_flags field */ +#define XDP_SHARED_UMEM (1 << 0) +#define XDP_COPY (1 << 1) /* Force copy-mode */ +#define XDP_ZEROCOPY (1 << 2) /* Force zero-copy mode */ +/* If this option is set, the driver might go sleep and in that case + * the XDP_RING_NEED_WAKEUP flag in the fill and/or Tx rings will be + * set. If it is set, the application need to explicitly wake up the + * driver with a poll() (Rx and Tx) or sendto() (Tx only). If you are + * running the driver and the application on the same core, you should + * use this option so that the kernel will yield to the user space + * application. + */ +#define XDP_USE_NEED_WAKEUP (1 << 3) + +/* Flags for xsk_umem_config flags */ +#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0) + +struct sockaddr_xdp { + __u16 sxdp_family; + __u16 sxdp_flags; + __u32 sxdp_ifindex; + __u32 sxdp_queue_id; + __u32 sxdp_shared_umem_fd; +}; + +/* XDP_RING flags */ +#define XDP_RING_NEED_WAKEUP (1 << 0) + +struct xdp_ring_offset { + __u64 producer; + __u64 consumer; + __u64 desc; + __u64 flags; +}; + +struct xdp_mmap_offsets { + struct xdp_ring_offset rx; + struct xdp_ring_offset tx; + struct xdp_ring_offset fr; /* Fill */ + struct xdp_ring_offset cr; /* Completion */ +}; + +/* XDP socket options */ +#define XDP_MMAP_OFFSETS 1 +#define XDP_RX_RING 2 +#define XDP_TX_RING 3 +#define XDP_UMEM_REG 4 +#define XDP_UMEM_FILL_RING 5 +#define XDP_UMEM_COMPLETION_RING 6 +#define XDP_STATISTICS 7 +#define XDP_OPTIONS 8 + +struct xdp_umem_reg { + __u64 addr; /* Start of packet data area */ + __u64 len; /* Length of packet data area */ + __u32 chunk_size; + __u32 headroom; + __u32 flags; +}; + +struct xdp_statistics { + __u64 rx_dropped; /* Dropped for reasons other than invalid desc */ + __u64 rx_invalid_descs; /* Dropped due to invalid descriptor */ + __u64 tx_invalid_descs; /* Dropped due to invalid descriptor */ +}; + +struct xdp_options { + __u32 flags; +}; + +/* Flags for the flags field of struct xdp_options */ +#define XDP_OPTIONS_ZEROCOPY (1 << 0) + +/* Pgoff for mmaping the rings */ +#define XDP_PGOFF_RX_RING 0 +#define XDP_PGOFF_TX_RING 0x80000000 +#define XDP_UMEM_PGOFF_FILL_RING 0x100000000ULL +#define XDP_UMEM_PGOFF_COMPLETION_RING 0x180000000ULL + +/* Masks for unaligned chunks mode */ +#define XSK_UNALIGNED_BUF_OFFSET_SHIFT 48 +#define XSK_UNALIGNED_BUF_ADDR_MASK \ + ((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1) + +/* Rx/Tx descriptor */ +struct xdp_desc { + __u64 addr; + __u32 len; + __u32 options; +}; + +/* UMEM descriptor is __u64 */ + +#endif /* _LINUX_IF_XDP_H */ diff --git a/src/xdp/include/perf-sys.h b/src/xdp/include/perf-sys.h new file mode 100644 index 000000000..2fd16e482 --- /dev/null +++ b/src/xdp/include/perf-sys.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copied from $(LINUX)/tools/perf/perf-sys.h (kernel 4.18) */ +#ifndef _PERF_SYS_H +#define _PERF_SYS_H + +#include <unistd.h> +#include <sys/types.h> +#include <sys/syscall.h> +#include <linux/types.h> +#include <linux/perf_event.h> +/* + * remove the following headers to allow for userspace program compilation + * #include <linux/compiler.h> + * #include <asm/barrier.h> + */ +#ifdef __powerpc__ +#define CPUINFO_PROC {"cpu"} +#endif + +#ifdef __s390__ +#define CPUINFO_PROC {"vendor_id"} +#endif + +#ifdef __sh__ +#define CPUINFO_PROC {"cpu type"} +#endif + +#ifdef __hppa__ +#define CPUINFO_PROC {"cpu"} +#endif + +#ifdef __sparc__ +#define CPUINFO_PROC {"cpu"} +#endif + +#ifdef __alpha__ +#define CPUINFO_PROC {"cpu model"} +#endif + +#ifdef __arm__ +#define CPUINFO_PROC {"model name", "Processor"} +#endif + +#ifdef __mips__ +#define CPUINFO_PROC {"cpu model"} +#endif + +#ifdef __arc__ +#define CPUINFO_PROC {"Processor"} +#endif + +#ifdef __xtensa__ +#define CPUINFO_PROC {"core ID"} +#endif + +#ifndef CPUINFO_PROC +#define CPUINFO_PROC { "model name", } +#endif + +static inline int +sys_perf_event_open(struct perf_event_attr *attr, + pid_t pid, int cpu, int group_fd, + unsigned long flags) +{ + int fd; + + fd = syscall(__NR_perf_event_open, attr, pid, cpu, + group_fd, flags); + +#ifdef HAVE_ATTR_TEST + if (unlikely(test_attr__enabled)) + test_attr__open(attr, pid, cpu, fd, group_fd, flags); +#endif + return fd; +} + +#endif /* _PERF_SYS_H */ diff --git a/src/xdp/utils/Makefile b/src/xdp/utils/Makefile new file mode 100644 index 000000000..42d6e63e3 --- /dev/null +++ b/src/xdp/utils/Makefile @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) + +USER_TARGETS := xdp_stats xdp_loader + +LIBBPF_DIR = ../libbpf/src/ +COMMON_DIR = ../common/ + +# Extend with another COMMON_OBJS +COMMON_OBJS += $(COMMON_DIR)/common_libbpf.o + +include $(COMMON_DIR)/common.mk diff --git a/src/xdp/utils/xdp_loader b/src/xdp/utils/xdp_loader Binary files differnew file mode 100755 index 000000000..887a7788b --- /dev/null +++ b/src/xdp/utils/xdp_loader diff --git a/src/xdp/utils/xdp_loader.c b/src/xdp/utils/xdp_loader.c new file mode 100644 index 000000000..d3b05d0c0 --- /dev/null +++ b/src/xdp/utils/xdp_loader.c @@ -0,0 +1,165 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +static const char *__doc__ = "XDP loader\n" + " - Allows selecting BPF section --progsec name to XDP-attach to --dev\n"; + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <getopt.h> + +#include <locale.h> +#include <unistd.h> +#include <time.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include <net/if.h> +#include <linux/if_link.h> /* depend on kernel-headers installed */ + +#include "../common/common_params.h" +#include "../common/common_user_bpf_xdp.h" +#include "../common/common_libbpf.h" + +static const char *default_filename = "xdp_prog_kern.o"; + +static const struct option_wrapper long_options[] = { + + {{"help", no_argument, NULL, 'h' }, + "Show help", false}, + + {{"dev", required_argument, NULL, 'd' }, + "Operate on device <ifname>", "<ifname>", true}, + + {{"skb-mode", no_argument, NULL, 'S' }, + "Install XDP program in SKB (AKA generic) mode"}, + + {{"native-mode", no_argument, NULL, 'N' }, + "Install XDP program in native mode"}, + + {{"auto-mode", no_argument, NULL, 'A' }, + "Auto-detect SKB or native mode"}, + + {{"force", no_argument, NULL, 'F' }, + "Force install, replacing existing program on interface"}, + + {{"unload", no_argument, NULL, 'U' }, + "Unload XDP program instead of loading"}, + + {{"reuse-maps", no_argument, NULL, 'M' }, + "Reuse pinned maps"}, + + {{"quiet", no_argument, NULL, 'q' }, + "Quiet mode (no output)"}, + + {{"filename", required_argument, NULL, 1 }, + "Load program from <file>", "<file>"}, + + {{"progsec", required_argument, NULL, 2 }, + "Load program in <section> of the ELF file", "<section>"}, + + {{0, 0, NULL, 0 }, NULL, false} +}; + +#ifndef PATH_MAX +#define PATH_MAX 4096 +#endif + +const char *pin_basedir = "/sys/fs/bpf"; +const char *map_name = "xdp_stats_map"; + +/* Pinning maps under /sys/fs/bpf in subdir */ +int pin_maps_in_bpf_object(struct bpf_object *bpf_obj, struct config *cfg) +{ + char map_filename[PATH_MAX]; + int err, len; + + len = snprintf(map_filename, PATH_MAX, "%s/%s/%s", + pin_basedir, cfg->ifname, map_name); + if (len < 0) { + fprintf(stderr, "ERR: creating map_name\n"); + return EXIT_FAIL_OPTION; + } + + /* Existing/previous XDP prog might not have cleaned up */ + if (access(map_filename, F_OK ) != -1 ) { + if (verbose) + printf(" - Unpinning (remove) prev maps in %s/\n", + cfg->pin_dir); + + /* Basically calls unlink(3) on map_filename */ + err = bpf_object__unpin_maps(bpf_obj, cfg->pin_dir); + if (err) { + fprintf(stderr, "ERR: UNpinning maps in %s\n", cfg->pin_dir); + return EXIT_FAIL_BPF; + } + } + if (verbose) + printf(" - Pinning maps in %s/\n", cfg->pin_dir); + + /* This will pin all maps in our bpf_object */ + err = bpf_object__pin_maps(bpf_obj, cfg->pin_dir); + if (err) + return EXIT_FAIL_BPF; + + return 0; +} + +int main(int argc, char **argv) +{ + struct bpf_object *bpf_obj; + int err, len; + + struct config cfg = { + .xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE, + .ifindex = -1, + .do_unload = false, + }; + /* Set default BPF-ELF object file and BPF program name */ + strncpy(cfg.filename, default_filename, sizeof(cfg.filename)); + /* Cmdline options can change progsec */ + parse_cmdline_args(argc, argv, long_options, &cfg, __doc__); + + /* Required option */ + if (cfg.ifindex == -1) { + fprintf(stderr, "ERR: required option --dev missing\n\n"); + usage(argv[0], __doc__, long_options, (argc == 1)); + return EXIT_FAIL_OPTION; + } + if (cfg.do_unload) { + if (!cfg.reuse_maps) { + /* TODO: Miss unpin of maps on unload */ + } + return xdp_link_detach(cfg.ifindex, cfg.xdp_flags, 0); + } + + len = snprintf(cfg.pin_dir, PATH_MAX, "%s/%s", pin_basedir, cfg.ifname); + if (len < 0) { + fprintf(stderr, "ERR: creating pin dirname\n"); + return EXIT_FAIL_OPTION; + } + + + bpf_obj = load_bpf_and_xdp_attach(&cfg); + if (!bpf_obj) + return EXIT_FAIL_BPF; + + if (verbose) { + printf("Success: Loaded BPF-object(%s) and used section(%s)\n", + cfg.filename, cfg.progsec); + printf(" - XDP prog attached on device:%s(ifindex:%d)\n", + cfg.ifname, cfg.ifindex); + } + + /* Use the --dev name as subdir for exporting/pinning maps */ + if (!cfg.reuse_maps) { + err = pin_maps_in_bpf_object(bpf_obj, &cfg); + if (err) { + fprintf(stderr, "ERR: pinning maps\n"); + return err; + } + } + + return EXIT_OK; +} diff --git a/src/xdp/utils/xdp_stats b/src/xdp/utils/xdp_stats Binary files differnew file mode 100755 index 000000000..fafb10cd1 --- /dev/null +++ b/src/xdp/utils/xdp_stats diff --git a/src/xdp/utils/xdp_stats.c b/src/xdp/utils/xdp_stats.c new file mode 100644 index 000000000..5dbec8351 --- /dev/null +++ b/src/xdp/utils/xdp_stats.c @@ -0,0 +1,295 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +static const char *__doc__ = "XDP stats program\n" + " - Finding xdp_stats_map via --dev name info\n"; + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <getopt.h> + +#include <locale.h> +#include <unistd.h> +#include <time.h> + +#include <bpf/bpf.h> +/* Lesson#1: this prog does not need to #include <bpf/libbpf.h> as it only uses + * the simple bpf-syscall wrappers, defined in libbpf #include<bpf/bpf.h> + */ + +#include <net/if.h> +#include <linux/if_link.h> /* depend on kernel-headers installed */ + +#include "../common/common_params.h" +#include "../common/common_user_bpf_xdp.h" +#include "../common/xdp_stats_kern_user.h" + +#include "../include/bpf_util.h" /* bpf_num_possible_cpus */ + +static const struct option_wrapper long_options[] = { + {{"help", no_argument, NULL, 'h' }, + "Show help", false}, + + {{"dev", required_argument, NULL, 'd' }, + "Operate on device <ifname>", "<ifname>", true}, + + {{"quiet", no_argument, NULL, 'q' }, + "Quiet mode (no output)"}, + + {{0, 0, NULL, 0 }} +}; + +#define NANOSEC_PER_SEC 1000000000 /* 10^9 */ +static __u64 gettime(void) +{ + struct timespec t; + int res; + + res = clock_gettime(CLOCK_MONOTONIC, &t); + if (res < 0) { + fprintf(stderr, "Error with gettimeofday! (%i)\n", res); + exit(EXIT_FAIL); + } + return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec; +} + +struct record { + __u64 timestamp; + struct datarec total; /* defined in common_kern_user.h */ +}; + +struct stats_record { + struct record stats[XDP_ACTION_MAX]; +}; + +static double calc_period(struct record *r, struct record *p) +{ + double period_ = 0; + __u64 period = 0; + + period = r->timestamp - p->timestamp; + if (period > 0) + period_ = ((double) period / NANOSEC_PER_SEC); + + return period_; +} + +static void stats_print_header() +{ + /* Print stats "header" */ + printf("%-12s\n", "XDP-action"); +} + +static void stats_print(struct stats_record *stats_rec, + struct stats_record *stats_prev) +{ + struct record *rec, *prev; + __u64 packets, bytes; + double period; + double pps; /* packets per sec */ + double bps; /* bits per sec */ + int i; + + stats_print_header(); /* Print stats "header" */ + + /* Print for each XDP actions stats */ + for (i = 0; i < XDP_ACTION_MAX; i++) + { + char *fmt = "%-12s %'11lld pkts (%'10.0f pps)" + " %'11lld Kbytes (%'6.0f Mbits/s)" + " period:%f\n"; + const char *action = action2str(i); + + rec = &stats_rec->stats[i]; + prev = &stats_prev->stats[i]; + + period = calc_period(rec, prev); + if (period == 0) + return; + + packets = rec->total.rx_packets - prev->total.rx_packets; + pps = packets / period; + + bytes = rec->total.rx_bytes - prev->total.rx_bytes; + bps = (bytes * 8)/ period / 1000000; + + printf(fmt, action, rec->total.rx_packets, pps, + rec->total.rx_bytes / 1000 , bps, + period); + } + printf("\n"); +} + + +/* BPF_MAP_TYPE_ARRAY */ +void map_get_value_array(int fd, __u32 key, struct datarec *value) +{ + if ((bpf_map_lookup_elem(fd, &key, value)) != 0) { + fprintf(stderr, + "ERR: bpf_map_lookup_elem failed key:0x%X\n", key); + } +} + +/* BPF_MAP_TYPE_PERCPU_ARRAY */ +void map_get_value_percpu_array(int fd, __u32 key, struct datarec *value) +{ + /* For percpu maps, userspace gets a value per possible CPU */ + unsigned int nr_cpus = bpf_num_possible_cpus(); + struct datarec values[nr_cpus]; + __u64 sum_bytes = 0; + __u64 sum_pkts = 0; + int i; + + if ((bpf_map_lookup_elem(fd, &key, values)) != 0) { + fprintf(stderr, + "ERR: bpf_map_lookup_elem failed key:0x%X\n", key); + return; + } + + /* Sum values from each CPU */ + for (i = 0; i < nr_cpus; i++) { + sum_pkts += values[i].rx_packets; + sum_bytes += values[i].rx_bytes; + } + value->rx_packets = sum_pkts; + value->rx_bytes = sum_bytes; +} + +static bool map_collect(int fd, __u32 map_type, __u32 key, struct record *rec) +{ + struct datarec value; + + /* Get time as close as possible to reading map contents */ + rec->timestamp = gettime(); + + switch (map_type) { + case BPF_MAP_TYPE_ARRAY: + map_get_value_array(fd, key, &value); + break; + case BPF_MAP_TYPE_PERCPU_ARRAY: + map_get_value_percpu_array(fd, key, &value); + break; + default: + fprintf(stderr, "ERR: Unknown map_type(%u) cannot handle\n", + map_type); + return false; + break; + } + + rec->total.rx_packets = value.rx_packets; + rec->total.rx_bytes = value.rx_bytes; + return true; +} + +static void stats_collect(int map_fd, __u32 map_type, + struct stats_record *stats_rec) +{ + /* Collect all XDP actions stats */ + __u32 key; + + for (key = 0; key < XDP_ACTION_MAX; key++) { + map_collect(map_fd, map_type, key, &stats_rec->stats[key]); + } +} + +static int stats_poll(const char *pin_dir, int map_fd, __u32 id, + __u32 map_type, int interval) +{ + struct bpf_map_info info = {}; + struct stats_record prev, record = { 0 }; + + /* Trick to pretty printf with thousands separators use %' */ + setlocale(LC_NUMERIC, "en_US"); + + /* Get initial reading quickly */ + stats_collect(map_fd, map_type, &record); + usleep(1000000/4); + + while (1) { + prev = record; /* struct copy */ + + map_fd = open_bpf_map_file(pin_dir, "xdp_stats_map", &info); + if (map_fd < 0) { + return EXIT_FAIL_BPF; + } else if (id != info.id) { + printf("BPF map xdp_stats_map changed its ID, restarting\n"); + return 0; + } + + stats_collect(map_fd, map_type, &record); + stats_print(&record, &prev); + sleep(interval); + } + + return 0; +} + +#ifndef PATH_MAX +#define PATH_MAX 4096 +#endif + +const char *pin_basedir = "/sys/fs/bpf"; + +int main(int argc, char **argv) +{ + const struct bpf_map_info map_expect = { + .key_size = sizeof(__u32), + .value_size = sizeof(struct datarec), + .max_entries = XDP_ACTION_MAX, + }; + struct bpf_map_info info = { 0 }; + char pin_dir[PATH_MAX]; + int stats_map_fd; + int interval = 2; + int len, err; + + struct config cfg = { + .ifindex = -1, + .do_unload = false, + }; + + /* Cmdline options can change progsec */ + parse_cmdline_args(argc, argv, long_options, &cfg, __doc__); + + /* Required option */ + if (cfg.ifindex == -1) { + fprintf(stderr, "ERR: required option --dev missing\n\n"); + usage(argv[0], __doc__, long_options, (argc == 1)); + return EXIT_FAIL_OPTION; + } + + /* Use the --dev name as subdir for finding pinned maps */ + len = snprintf(pin_dir, PATH_MAX, "%s/%s", pin_basedir, cfg.ifname); + if (len < 0) { + fprintf(stderr, "ERR: creating pin dirname\n"); + return EXIT_FAIL_OPTION; + } + + for ( ;; ) { + stats_map_fd = open_bpf_map_file(pin_dir, "xdp_stats_map", &info); + if (stats_map_fd < 0) { + return EXIT_FAIL_BPF; + } + + /* check map info, e.g. datarec is expected size */ + err = check_map_fd_info(&info, &map_expect); + if (err) { + fprintf(stderr, "ERR: map via FD not compatible\n"); + return err; + } + if (verbose) { + printf("\nCollecting stats from BPF map\n"); + printf(" - BPF map (bpf_map_type:%d) id:%d name:%s" + " key_size:%d value_size:%d max_entries:%d\n", + info.type, info.id, info.name, + info.key_size, info.value_size, info.max_entries + ); + } + + err = stats_poll(pin_dir, stats_map_fd, info.id, info.type, interval); + if (err < 0) + return err; + } + + return EXIT_OK; +} diff --git a/src/xdp/xdp_prog_kern.c b/src/xdp/xdp_prog_kern.c new file mode 100644 index 000000000..a1eb395af --- /dev/null +++ b/src/xdp/xdp_prog_kern.c @@ -0,0 +1,343 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/bpf.h> +#include <linux/in.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +// The parsing helper functions from the packet01 lesson have moved here +#include "common/parsing_helpers.h" +#include "common/rewrite_helpers.h" + +/* Defines xdp_stats_map */ +#include "common/xdp_stats_kern_user.h" +#include "common/xdp_stats_kern.h" + +#ifndef memcpy +#define memcpy(dest, src, n) __builtin_memcpy((dest), (src), (n)) +#endif + +struct bpf_map_def SEC("maps") tx_port = { + .type = BPF_MAP_TYPE_DEVMAP, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 256, +}; + +struct bpf_map_def SEC("maps") redirect_params = { + .type = BPF_MAP_TYPE_HASH, + .key_size = ETH_ALEN, + .value_size = ETH_ALEN, + .max_entries = 1, +}; + +static __always_inline __u16 csum_fold_helper(__u32 csum) +{ + return ~((csum & 0xffff) + (csum >> 16)); +} + +/* + * The icmp_checksum_diff function takes pointers to old and new structures and + * the old checksum and returns the new checksum. It uses the bpf_csum_diff + * helper to compute the checksum difference. Note that the sizes passed to the + * bpf_csum_diff helper should be multiples of 4, as it operates on 32-bit + * words. + */ +static __always_inline __u16 icmp_checksum_diff( + __u16 seed, + struct icmphdr_common *icmphdr_new, + struct icmphdr_common *icmphdr_old) +{ + __u32 csum, size = sizeof(struct icmphdr_common); + + csum = bpf_csum_diff((__be32 *)icmphdr_old, size, (__be32 *)icmphdr_new, size, seed); + return csum_fold_helper(csum); +} + +/* Solution to packet03/assignment-1 */ +SEC("xdp_icmp_echo") +int xdp_icmp_echo_func(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct hdr_cursor nh; + struct ethhdr *eth; + int eth_type; + int ip_type; + int icmp_type; + struct iphdr *iphdr; + struct ipv6hdr *ipv6hdr; + __u16 echo_reply, old_csum; + struct icmphdr_common *icmphdr; + struct icmphdr_common icmphdr_old; + __u32 action = XDP_PASS; + + /* These keep track of the next header type and iterator pointer */ + nh.pos = data; + + /* Parse Ethernet and IP/IPv6 headers */ + eth_type = parse_ethhdr(&nh, data_end, ð); + if (eth_type == bpf_htons(ETH_P_IP)) { + ip_type = parse_iphdr(&nh, data_end, &iphdr); + if (ip_type != IPPROTO_ICMP) + goto out; + } else if (eth_type == bpf_htons(ETH_P_IPV6)) { + ip_type = parse_ip6hdr(&nh, data_end, &ipv6hdr); + if (ip_type != IPPROTO_ICMPV6) + goto out; + } else { + goto out; + } + + /* + * We are using a special parser here which returns a stucture + * containing the "protocol-independent" part of an ICMP or ICMPv6 + * header. For purposes of this Assignment we are not interested in + * the rest of the structure. + */ + icmp_type = parse_icmphdr_common(&nh, data_end, &icmphdr); + if (eth_type == bpf_htons(ETH_P_IP) && icmp_type == ICMP_ECHO) { + /* Swap IP source and destination */ + swap_src_dst_ipv4(iphdr); + echo_reply = ICMP_ECHOREPLY; + } else if (eth_type == bpf_htons(ETH_P_IPV6) + && icmp_type == ICMPV6_ECHO_REQUEST) { + /* Swap IPv6 source and destination */ + swap_src_dst_ipv6(ipv6hdr); + echo_reply = ICMPV6_ECHO_REPLY; + } else { + goto out; + } + + /* Swap Ethernet source and destination */ + swap_src_dst_mac(eth); + + + /* Patch the packet and update the checksum.*/ + old_csum = icmphdr->cksum; + icmphdr->cksum = 0; + icmphdr_old = *icmphdr; + icmphdr->type = echo_reply; + icmphdr->cksum = icmp_checksum_diff(~old_csum, icmphdr, &icmphdr_old); + + /* Another, less generic, but a bit more efficient way to update the + * checksum is listed below. As only one 16-bit word changed, the sum + * can be patched using this formula: sum' = ~(~sum + ~m0 + m1), where + * sum' is a new sum, sum is an old sum, m0 and m1 are the old and new + * 16-bit words, correspondingly. In the formula above the + operation + * is defined as the following function: + * + * static __always_inline __u16 csum16_add(__u16 csum, __u16 addend) + * { + * csum += addend; + * return csum + (csum < addend); + * } + * + * So an alternative code to update the checksum might look like this: + * + * __u16 m0 = * (__u16 *) icmphdr; + * icmphdr->type = echo_reply; + * __u16 m1 = * (__u16 *) icmphdr; + * icmphdr->checksum = ~(csum16_add(csum16_add(~icmphdr->checksum, ~m0), m1)); + */ + + action = XDP_TX; + +out: + return xdp_stats_record_action(ctx, action); +} + +/* Solution to packet03/assignment-2 */ +SEC("xdp_redirect") +int xdp_redirect_func(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct hdr_cursor nh; + struct ethhdr *eth; + int eth_type; + int action = XDP_PASS; + unsigned char dst[ETH_ALEN] = { /* TODO: put your values here */ }; + unsigned ifindex = 0/* TODO: put your values here */; + + /* These keep track of the next header type and iterator pointer */ + nh.pos = data; + + /* Parse Ethernet and IP/IPv6 headers */ + eth_type = parse_ethhdr(&nh, data_end, ð); + if (eth_type == -1) + goto out; + + /* Set a proper destination address */ + memcpy(eth->h_dest, dst, ETH_ALEN); + action = bpf_redirect(ifindex, 0); + +out: + return xdp_stats_record_action(ctx, action); +} + +/* Solution to packet03/assignment-3 */ +SEC("xdp_redirect_map") +int xdp_redirect_map_func(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct hdr_cursor nh; + struct ethhdr *eth; + int eth_type; + int action = XDP_PASS; + unsigned char *dst; + + /* These keep track of the next header type and iterator pointer */ + nh.pos = data; + + /* Parse Ethernet and IP/IPv6 headers */ + eth_type = parse_ethhdr(&nh, data_end, ð); + if (eth_type == -1) + goto out; + + /* Do we know where to redirect this packet? */ + dst = bpf_map_lookup_elem(&redirect_params, eth->h_source); + if (!dst) + goto out; + + /* Set a proper destination address */ + memcpy(eth->h_dest, dst, ETH_ALEN); + action = bpf_redirect_map(&tx_port, 0, 0); + +out: + return xdp_stats_record_action(ctx, action); +} + +#define AF_INET 2 +#define AF_INET6 10 +#define IPV6_FLOWINFO_MASK bpf_htonl(0x0FFFFFFF) + +/* from include/net/ip.h */ +static __always_inline int ip_decrease_ttl(struct iphdr *iph) +{ + __u32 check = iph->check; + check += bpf_htons(0x0100); + iph->check = (__u16)(check + (check >= 0xFFFF)); + return --iph->ttl; +} + +/* Solution to packet03/assignment-4 */ +/* xdp_router is the name of the xdp program */ +SEC("xdp_router") +int xdp_router_func(struct xdp_md *ctx) +{ + /* this is the packet context*/ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct bpf_fib_lookup fib_params = {}; + struct ethhdr *eth = data; + struct ipv6hdr *ip6h; + struct iphdr *iph; + __u16 h_proto; + __u64 nh_off; + int rc; + /* default action is to pass */ + int action = XDP_PASS; + + nh_off = sizeof(*eth); + if (data + nh_off > data_end) { + action = XDP_DROP; + goto out; + } + + /* determine if this is IP4 or IPv6 by looking at the Ethernet protocol field */ + h_proto = eth->h_proto; + if (h_proto == bpf_htons(ETH_P_IP)) { + /* IPv4 part of the code */ + iph = data + nh_off; + + if (iph + 1 > data_end) { + action = XDP_DROP; + goto out; + } + /* as a real router, we need to check the TTL to prevent never ending loops*/ + if (iph->ttl <= 1) + goto out; + + /* populate the fib_params fields to prepare for the lookup */ + fib_params.family = AF_INET; + fib_params.tos = iph->tos; + fib_params.l4_protocol = iph->protocol; + fib_params.sport = 0; + fib_params.dport = 0; + fib_params.tot_len = bpf_ntohs(iph->tot_len); + fib_params.ipv4_src = iph->saddr; + fib_params.ipv4_dst = iph->daddr; + } else if (h_proto == bpf_htons(ETH_P_IPV6)) { + /* IPv6 part of the code */ + struct in6_addr *src = (struct in6_addr *) fib_params.ipv6_src; + struct in6_addr *dst = (struct in6_addr *) fib_params.ipv6_dst; + + ip6h = data + nh_off; + if (ip6h + 1 > data_end) { + action = XDP_DROP; + goto out; + } + /* as a real router, we need to check the TTL to prevent never ending loops*/ + if (ip6h->hop_limit <= 1) + goto out; + + /* populate the fib_params fields to prepare for the lookup */ + fib_params.family = AF_INET6; + fib_params.flowinfo = *(__be32 *) ip6h & IPV6_FLOWINFO_MASK; + fib_params.l4_protocol = ip6h->nexthdr; + fib_params.sport = 0; + fib_params.dport = 0; + fib_params.tot_len = bpf_ntohs(ip6h->payload_len); + *src = ip6h->saddr; + *dst = ip6h->daddr; + } else { + goto out; + } + + fib_params.ifindex = ctx->ingress_ifindex; + + /* this is where the FIB lookup happens. If the lookup is successful */ + /* it will populate the fib_params.ifindex with the egress interface index */ + + rc = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), 0); + switch (rc) { + case BPF_FIB_LKUP_RET_SUCCESS: /* lookup successful */ + /* we are a router, so we need to decrease the ttl */ + if (h_proto == bpf_htons(ETH_P_IP)) + ip_decrease_ttl(iph); + else if (h_proto == bpf_htons(ETH_P_IPV6)) + ip6h->hop_limit--; + /* set the correct new source and destionation mac addresses */ + /* can be found in fib_params.dmac and fib_params.smac */ + memcpy(eth->h_dest, fib_params.dmac, ETH_ALEN); + memcpy(eth->h_source, fib_params.smac, ETH_ALEN); + /* and done, now we set the action to bpf_redirect_map with fib_params.ifindex which is the egress port as paramater */ + action = bpf_redirect_map(&tx_port, fib_params.ifindex, 0); + break; + case BPF_FIB_LKUP_RET_BLACKHOLE: /* dest is blackholed; can be dropped */ + case BPF_FIB_LKUP_RET_UNREACHABLE: /* dest is unreachable; can be dropped */ + case BPF_FIB_LKUP_RET_PROHIBIT: /* dest not allowed; can be dropped */ + action = XDP_DROP; + break; + case BPF_FIB_LKUP_RET_NOT_FWDED: /* packet is not forwarded */ + case BPF_FIB_LKUP_RET_FWD_DISABLED: /* fwding is not enabled on ingress */ + case BPF_FIB_LKUP_RET_UNSUPP_LWT: /* fwd requires encapsulation */ + case BPF_FIB_LKUP_RET_NO_NEIGH: /* no neighbor entry for nh */ + case BPF_FIB_LKUP_RET_FRAG_NEEDED: /* fragmentation required to fwd */ + /* PASS */ + break; + } + +out: + /* and done, update stats and return action */ + return xdp_stats_record_action(ctx, action); +} + +SEC("xdp_pass") +int xdp_pass_func(struct xdp_md *ctx) +{ + return xdp_stats_record_action(ctx, XDP_PASS); +} + +char _license[] SEC("license") = "GPL"; diff --git a/src/xdp/xdp_prog_user.c b/src/xdp/xdp_prog_user.c new file mode 100644 index 000000000..c47d2977d --- /dev/null +++ b/src/xdp/xdp_prog_user.c @@ -0,0 +1,182 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +static const char *__doc__ = "XDP redirect helper\n" + " - Allows to populate/query tx_port and redirect_params maps\n"; + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <getopt.h> +#include <stdbool.h> + +#include <locale.h> +#include <unistd.h> +#include <time.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include <net/if.h> +#include <linux/if_ether.h> +#include <linux/if_link.h> /* depend on kernel-headers installed */ + +#include "common/common_params.h" +#include "common/common_user_bpf_xdp.h" +#include "common/common_libbpf.h" + +#include "common/xdp_stats_kern_user.h" + +static const struct option_wrapper long_options[] = { + + {{"help", no_argument, NULL, 'h' }, + "Show help", false}, + + {{"dev", required_argument, NULL, 'd' }, + "Operate on device <ifname>", "<ifname>", true}, + + {{"redirect-dev", required_argument, NULL, 'r' }, + "Redirect to device <ifname>", "<ifname>", true}, + + {{"src-mac", required_argument, NULL, 'L' }, + "Source MAC address of <dev>", "<mac>", true }, + + {{"dest-mac", required_argument, NULL, 'R' }, + "Destination MAC address of <redirect-dev>", "<mac>", true }, + + {{"quiet", no_argument, NULL, 'q' }, + "Quiet mode (no output)"}, + + {{0, 0, NULL, 0 }, NULL, false} +}; + +static int parse_u8(char *str, unsigned char *x) +{ + unsigned long z; + + z = strtoul(str, 0, 16); + if (z > 0xff) + return -1; + + if (x) + *x = z; + + return 0; +} + +static int parse_mac(char *str, unsigned char mac[ETH_ALEN]) +{ + if (parse_u8(str, &mac[0]) < 0) + return -1; + if (parse_u8(str + 3, &mac[1]) < 0) + return -1; + if (parse_u8(str + 6, &mac[2]) < 0) + return -1; + if (parse_u8(str + 9, &mac[3]) < 0) + return -1; + if (parse_u8(str + 12, &mac[4]) < 0) + return -1; + if (parse_u8(str + 15, &mac[5]) < 0) + return -1; + + return 0; +} + +static int write_iface_params(int map_fd, unsigned char *src, unsigned char *dest) +{ + if (bpf_map_update_elem(map_fd, src, dest, 0) < 0) { + fprintf(stderr, + "WARN: Failed to update bpf map file: err(%d):%s\n", + errno, strerror(errno)); + return -1; + } + + printf("forward: %02x:%02x:%02x:%02x:%02x:%02x -> %02x:%02x:%02x:%02x:%02x:%02x\n", + src[0], src[1], src[2], src[3], src[4], src[5], + dest[0], dest[1], dest[2], dest[3], dest[4], dest[5] + ); + + return 0; +} + +#ifndef PATH_MAX +#define PATH_MAX 4096 +#endif + +const char *pin_basedir = "/sys/fs/bpf"; + +int main(int argc, char **argv) +{ + int i; + int len; + int map_fd; + bool redirect_map; + char pin_dir[PATH_MAX]; + unsigned char src[ETH_ALEN]; + unsigned char dest[ETH_ALEN]; + + struct config cfg = { + .ifindex = -1, + .redirect_ifindex = -1, + }; + + /* Cmdline options can change progsec */ + parse_cmdline_args(argc, argv, long_options, &cfg, __doc__); + + redirect_map = (cfg.ifindex > 0) && (cfg.redirect_ifindex > 0); + + if (cfg.redirect_ifindex > 0 && cfg.ifindex == -1) { + fprintf(stderr, "ERR: required option --dev missing\n\n"); + usage(argv[0], __doc__, long_options, (argc == 1)); + return EXIT_FAIL_OPTION; + } + + len = snprintf(pin_dir, PATH_MAX, "%s/%s", pin_basedir, cfg.ifname); + if (len < 0) { + fprintf(stderr, "ERR: creating pin dirname\n"); + return EXIT_FAIL_OPTION; + } + + if (parse_mac(cfg.src_mac, src) < 0) { + fprintf(stderr, "ERR: can't parse mac address %s\n", cfg.src_mac); + return EXIT_FAIL_OPTION; + } + + if (parse_mac(cfg.dest_mac, dest) < 0) { + fprintf(stderr, "ERR: can't parse mac address %s\n", cfg.dest_mac); + return EXIT_FAIL_OPTION; + } + + /* Open the tx_port map corresponding to the cfg.ifname interface */ + map_fd = open_bpf_map_file(pin_dir, "tx_port", NULL); + if (map_fd < 0) { + return EXIT_FAIL_BPF; + } + + printf("map dir: %s\n", pin_dir); + + if (redirect_map) { + /* setup a virtual port for the static redirect */ + i = 0; + bpf_map_update_elem(map_fd, &i, &cfg.redirect_ifindex, 0); + printf("redirect from ifnum=%d to ifnum=%d\n", cfg.ifindex, cfg.redirect_ifindex); + + /* Open the redirect_params map */ + map_fd = open_bpf_map_file(pin_dir, "redirect_params", NULL); + if (map_fd < 0) { + return EXIT_FAIL_BPF; + } + + /* Setup the mapping containing MAC addresses */ + if (write_iface_params(map_fd, src, dest) < 0) { + fprintf(stderr, "can't write iface params\n"); + return 1; + } + } else { + /* setup 1-1 mapping for the dynamic router */ + for (i = 1; i < 256; ++i) + bpf_map_update_elem(map_fd, &i, &i, 0); + } + + return EXIT_OK; +} |