Project import
diff --git a/iproute2/Android.mk b/iproute2/Android.mk
new file mode 100644
index 0000000..5053e7d
--- /dev/null
+++ b/iproute2/Android.mk
@@ -0,0 +1 @@
+include $(call all-subdir-makefiles)
diff --git a/iproute2/COPYING b/iproute2/COPYING
new file mode 100644
index 0000000..3912109
--- /dev/null
+++ b/iproute2/COPYING
@@ -0,0 +1,340 @@
+ GNU GENERAL PUBLIC LICENSE
+ Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.
+ 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+ Preamble
+
+ The licenses for most software are designed to take away your
+freedom to share and change it. By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users. This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it. (Some other Free Software Foundation software is covered by
+the GNU Library General Public License instead.) You can apply it to
+your programs, too.
+
+ When we speak of free software, we are referring to freedom, not
+price. Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+ To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+ For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have. You must make sure that they, too, receive or can get the
+source code. And you must show them these terms so they know their
+rights.
+
+ We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+ Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software. If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+ Finally, any free program is threatened constantly by software
+patents. We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary. To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+ The precise terms and conditions for copying, distribution and
+modification follow.
+
+ GNU GENERAL PUBLIC LICENSE
+ TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+ 0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License. The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language. (Hereinafter, translation is included without limitation in
+the term "modification".) Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope. The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+ 1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+ 2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+ a) You must cause the modified files to carry prominent notices
+ stating that you changed the files and the date of any change.
+
+ b) You must cause any work that you distribute or publish, that in
+ whole or in part contains or is derived from the Program or any
+ part thereof, to be licensed as a whole at no charge to all third
+ parties under the terms of this License.
+
+ c) If the modified program normally reads commands interactively
+ when run, you must cause it, when started running for such
+ interactive use in the most ordinary way, to print or display an
+ announcement including an appropriate copyright notice and a
+ notice that there is no warranty (or else, saying that you provide
+ a warranty) and that users may redistribute the program under
+ these conditions, and telling the user how to view a copy of this
+ License. (Exception: if the Program itself is interactive but
+ does not normally print such an announcement, your work based on
+ the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole. If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works. But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+ 3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+ a) Accompany it with the complete corresponding machine-readable
+ source code, which must be distributed under the terms of Sections
+ 1 and 2 above on a medium customarily used for software interchange; or,
+
+ b) Accompany it with a written offer, valid for at least three
+ years, to give any third party, for a charge no more than your
+ cost of physically performing source distribution, a complete
+ machine-readable copy of the corresponding source code, to be
+ distributed under the terms of Sections 1 and 2 above on a medium
+ customarily used for software interchange; or,
+
+ c) Accompany it with the information you received as to the offer
+ to distribute corresponding source code. (This alternative is
+ allowed only for noncommercial distribution and only if you
+ received the program in object code or executable form with such
+ an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it. For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable. However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+ 4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License. Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+ 5. You are not required to accept this License, since you have not
+signed it. However, nothing else grants you permission to modify or
+distribute the Program or its derivative works. These actions are
+prohibited by law if you do not accept this License. Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+ 6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions. You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+ 7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License. If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all. For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices. Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+ 8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded. In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+ 9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time. Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number. If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation. If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+ 10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission. For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this. Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+ NO WARRANTY
+
+ 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+ 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+ END OF TERMS AND CONDITIONS
+
+ How to Apply These Terms to Your New Programs
+
+ If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+ To do so, attach the following notices to the program. It is safest
+to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+ <one line to give the program's name and a brief idea of what it does.>
+ Copyright (C) <year> <name of author>
+
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 2 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+ Gnomovision version 69, Copyright (C) year name of author
+ Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+ This is free software, and you are welcome to redistribute it
+ under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License. Of course, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary. Here is a sample; alter the names:
+
+ Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+ `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+ <signature of Ty Coon>, 1 April 1989
+ Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs. If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library. If this is what you want to do, use the GNU Library General
+Public License instead of this License.
diff --git a/iproute2/CleanSpec.mk b/iproute2/CleanSpec.mk
new file mode 100644
index 0000000..b84e1b6
--- /dev/null
+++ b/iproute2/CleanSpec.mk
@@ -0,0 +1,49 @@
+# Copyright (C) 2007 The Android Open Source Project
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+# If you don't need to do a full clean build but would like to touch
+# a file or delete some intermediate files, add a clean step to the end
+# of the list. These steps will only be run once, if they haven't been
+# run before.
+#
+# E.g.:
+# $(call add-clean-step, touch -c external/sqlite/sqlite3.h)
+# $(call add-clean-step, rm -rf $(PRODUCT_OUT)/obj/STATIC_LIBRARIES/libz_intermediates)
+#
+# Always use "touch -c" and "rm -f" or "rm -rf" to gracefully deal with
+# files that are missing or have been moved.
+#
+# Use $(PRODUCT_OUT) to get to the "out/target/product/blah/" directory.
+# Use $(OUT_DIR) to refer to the "out" directory.
+#
+# If you need to re-do something that's already mentioned, just copy
+# the command and add it to the bottom of the list. E.g., if a change
+# that you made last week required touching a file and a change you
+# made today requires touching the same file, just copy the old
+# touch step and add it to the end of the list.
+#
+# ************************************************
+# NEWER CLEAN STEPS MUST BE AT THE END OF THE LIST
+# ************************************************
+
+# For example:
+#$(call add-clean-step, rm -rf $(OUT_DIR)/target/common/obj/APPS/AndroidTests_intermediates)
+#$(call add-clean-step, rm -rf $(OUT_DIR)/target/common/obj/JAVA_LIBRARIES/core_intermediates)
+#$(call add-clean-step, find $(OUT_DIR) -type f -name "IGTalkSession*" -print0 | xargs -0 rm -f)
+#$(call add-clean-step, rm -rf $(PRODUCT_OUT)/data/*)
+
+# ************************************************
+# NEWER CLEAN STEPS MUST BE AT THE END OF THE LIST
+# ************************************************
diff --git a/iproute2/MODULE_LICENSE_GPL b/iproute2/MODULE_LICENSE_GPL
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/iproute2/MODULE_LICENSE_GPL
diff --git a/iproute2/Makefile b/iproute2/Makefile
new file mode 100644
index 0000000..67176be
--- /dev/null
+++ b/iproute2/Makefile
@@ -0,0 +1,88 @@
+PREFIX?=/usr
+LIBDIR?=$(PREFIX)/lib
+SBINDIR?=/sbin
+CONFDIR?=/etc/iproute2
+DATADIR?=$(PREFIX)/share
+DOCDIR?=$(DATADIR)/doc/iproute2
+MANDIR?=$(DATADIR)/man
+ARPDDIR?=/var/lib/arpd
+KERNEL_INCLUDE?=/usr/include
+
+# Path to db_185.h include
+DBM_INCLUDE:=$(DESTDIR)/usr/include
+
+SHARED_LIBS = y
+
+DEFINES= -DRESOLVE_HOSTNAMES -DLIBDIR=\"$(LIBDIR)\"
+ifneq ($(SHARED_LIBS),y)
+DEFINES+= -DNO_SHARED_LIBS
+endif
+
+DEFINES+=-DCONFDIR=\"$(CONFDIR)\"
+
+#options for decnet
+ADDLIB+=dnet_ntop.o dnet_pton.o
+
+#options for ipx
+ADDLIB+=ipx_ntop.o ipx_pton.o
+
+#options for mpls
+ADDLIB+=mpls_ntop.o mpls_pton.o
+
+CC = gcc
+HOSTCC = gcc
+DEFINES += -D_GNU_SOURCE
+# Turn on transparent support for LFS
+DEFINES += -D_FILE_OFFSET_BITS=64 -D_LARGEFILE_SOURCE -D_LARGEFILE64_SOURCE
+CCOPTS = -O2
+WFLAGS := -Wall -Wstrict-prototypes -Wmissing-prototypes
+WFLAGS += -Wmissing-declarations -Wold-style-definition -Wformat=2
+
+CFLAGS := $(WFLAGS) $(CCOPTS) -I../include $(DEFINES) $(CFLAGS)
+YACCFLAGS = -d -t -v
+
+SUBDIRS=lib ip tc bridge misc netem genl tipc man
+
+LIBNETLINK=../lib/libnetlink.a ../lib/libutil.a
+LDLIBS += $(LIBNETLINK)
+
+all: Config
+ @set -e; \
+ for i in $(SUBDIRS); \
+ do $(MAKE) $(MFLAGS) -C $$i; done
+
+Config:
+ sh configure $(KERNEL_INCLUDE)
+
+install: all
+ install -m 0755 -d $(DESTDIR)$(SBINDIR)
+ install -m 0755 -d $(DESTDIR)$(CONFDIR)
+ install -m 0755 -d $(DESTDIR)$(ARPDDIR)
+ install -m 0755 -d $(DESTDIR)$(DOCDIR)/examples
+ install -m 0755 -d $(DESTDIR)$(DOCDIR)/examples/diffserv
+ install -m 0644 README.iproute2+tc $(shell find examples -maxdepth 1 -type f) \
+ $(DESTDIR)$(DOCDIR)/examples
+ install -m 0644 $(shell find examples/diffserv -maxdepth 1 -type f) \
+ $(DESTDIR)$(DOCDIR)/examples/diffserv
+ @for i in $(SUBDIRS) doc; do $(MAKE) -C $$i install; done
+ install -m 0644 $(shell find etc/iproute2 -maxdepth 1 -type f) $(DESTDIR)$(CONFDIR)
+
+snapshot:
+ echo "static const char SNAPSHOT[] = \""`date +%y%m%d`"\";" \
+ > include/SNAPSHOT.h
+
+clean:
+ @for i in $(SUBDIRS) doc; \
+ do $(MAKE) $(MFLAGS) -C $$i clean; done
+
+clobber:
+ touch Config
+ $(MAKE) $(MFLAGS) clean
+ rm -f Config cscope.*
+
+distclean: clobber
+
+cscope:
+ cscope -b -q -R -Iinclude -sip -slib -smisc -snetem -stc
+
+.EXPORT_ALL_VARIABLES:
diff --git a/iproute2/NOTICE b/iproute2/NOTICE
new file mode 100644
index 0000000..3912109
--- /dev/null
+++ b/iproute2/NOTICE
@@ -0,0 +1,340 @@
+ GNU GENERAL PUBLIC LICENSE
+ Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.
+ 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+ Preamble
+
+ The licenses for most software are designed to take away your
+freedom to share and change it. By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users. This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it. (Some other Free Software Foundation software is covered by
+the GNU Library General Public License instead.) You can apply it to
+your programs, too.
+
+ When we speak of free software, we are referring to freedom, not
+price. Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+ To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+ For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have. You must make sure that they, too, receive or can get the
+source code. And you must show them these terms so they know their
+rights.
+
+ We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+ Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software. If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+ Finally, any free program is threatened constantly by software
+patents. We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary. To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+ The precise terms and conditions for copying, distribution and
+modification follow.
+
+ GNU GENERAL PUBLIC LICENSE
+ TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+ 0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License. The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language. (Hereinafter, translation is included without limitation in
+the term "modification".) Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope. The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+ 1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+ 2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+ a) You must cause the modified files to carry prominent notices
+ stating that you changed the files and the date of any change.
+
+ b) You must cause any work that you distribute or publish, that in
+ whole or in part contains or is derived from the Program or any
+ part thereof, to be licensed as a whole at no charge to all third
+ parties under the terms of this License.
+
+ c) If the modified program normally reads commands interactively
+ when run, you must cause it, when started running for such
+ interactive use in the most ordinary way, to print or display an
+ announcement including an appropriate copyright notice and a
+ notice that there is no warranty (or else, saying that you provide
+ a warranty) and that users may redistribute the program under
+ these conditions, and telling the user how to view a copy of this
+ License. (Exception: if the Program itself is interactive but
+ does not normally print such an announcement, your work based on
+ the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole. If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works. But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+ 3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+ a) Accompany it with the complete corresponding machine-readable
+ source code, which must be distributed under the terms of Sections
+ 1 and 2 above on a medium customarily used for software interchange; or,
+
+ b) Accompany it with a written offer, valid for at least three
+ years, to give any third party, for a charge no more than your
+ cost of physically performing source distribution, a complete
+ machine-readable copy of the corresponding source code, to be
+ distributed under the terms of Sections 1 and 2 above on a medium
+ customarily used for software interchange; or,
+
+ c) Accompany it with the information you received as to the offer
+ to distribute corresponding source code. (This alternative is
+ allowed only for noncommercial distribution and only if you
+ received the program in object code or executable form with such
+ an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it. For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable. However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+ 4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License. Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+ 5. You are not required to accept this License, since you have not
+signed it. However, nothing else grants you permission to modify or
+distribute the Program or its derivative works. These actions are
+prohibited by law if you do not accept this License. Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+ 6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions. You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+ 7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License. If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all. For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices. Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+ 8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded. In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+ 9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time. Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number. If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation. If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+ 10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission. For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this. Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+ NO WARRANTY
+
+ 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+ 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+ END OF TERMS AND CONDITIONS
+
+ How to Apply These Terms to Your New Programs
+
+ If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+ To do so, attach the following notices to the program. It is safest
+to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+ <one line to give the program's name and a brief idea of what it does.>
+ Copyright (C) <year> <name of author>
+
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 2 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+ Gnomovision version 69, Copyright (C) year name of author
+ Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+ This is free software, and you are welcome to redistribute it
+ under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License. Of course, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary. Here is a sample; alter the names:
+
+ Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+ `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+ <signature of Ty Coon>, 1 April 1989
+ Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs. If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library. If this is what you want to do, use the GNU Library General
+Public License instead of this License.
diff --git a/iproute2/README b/iproute2/README
new file mode 100644
index 0000000..c7a5118
--- /dev/null
+++ b/iproute2/README
@@ -0,0 +1,43 @@
+This is a set of utilities for Linux networking.
+
+Information:
+ http://www.linuxfoundation.org/collaborate/workgroups/networking/iproute2
+
+Download:
+ http://www.kernel.org/pub/linux/utils/net/iproute2/
+
+Repository:
+ git://git.kernel.org/pub/scm/linux/kernel/git/shemminger/iproute2.git
+
+How to compile this.
+--------------------
+1. libdbm
+
+arpd needs to have the db4 development libraries. For Debian
+users this is the package with a name like libdb4.x-dev.
+DBM_INCLUDE points to the directory with db_185.h which
+is the include file used by arpd to get to the old format Berkeley
+database routines. Often this is in the db-devel package.
+
+2. make
+
+The makefile will automatically build a Config file which
+contains whether or not ATM is available, etc.
+
+3. To make documentation, cd to doc/ directory , then
+ look at start of Makefile and set correct values for
+ PAGESIZE=a4 , ie: a4 , letter ... (string)
+ PAGESPERPAGE=2 , ie: 1 , 2 ... (numeric)
+ and make there. It assumes, that latex, dvips and psnup
+ are in your path.
+
+4. This package includes matching sanitized kernel headers because
+ the build environment may not have up to date versions. See Makefile
+ if you have special requirements and need to point at different
+ kernel include files.
+
+Stephen Hemminger
+stephen@networkplumber.org
+
+Alexey Kuznetsov
+kuznet@ms2.inr.ac.ru
diff --git a/iproute2/README.decnet b/iproute2/README.decnet
new file mode 100644
index 0000000..4300f90
--- /dev/null
+++ b/iproute2/README.decnet
@@ -0,0 +1,33 @@
+
+Here are a few quick points about DECnet support...
+
+ o iproute2 is the tool of choice for configuring the DECnet support for
+ Linux. For many features, it is the only tool which can be used to
+ configure them.
+
+ o No name resolution is available as yet, all addresses must be
+ entered numerically.
+
+ o Remember to set the hardware address of the interface using:
+
+ ip link set ethX address xx:xx:xx:xx:xx:xx
+ (where xx:xx:xx:xx:xx:xx is the MAC address for your DECnet node
+ address)
+
+ if your Ethernet card won't listen to more than one unicast
+ mac address at once. If the Linux DECnet stack doesn't talk to
+ any other DECnet nodes, then check this with tcpdump and if its
+ a problem, change the mac address (but do this _before_ starting
+ any other network protocol on the interface)
+
+ o Whilst you can use ip addr add to add more than one DECnet address to an
+ interface, don't expect addresses which are not the same as the
+ kernels node address to work properly with 2.4 kernels. This should
+ be fine with 2.6 kernels as the routing code has been extensively
+ modified and improved.
+
+ o The DECnet support is currently self contained. It does not depend on
+ the libdnet library.
+
+Steve Whitehouse <steve@chygwyn.com>
+
diff --git a/iproute2/README.devel b/iproute2/README.devel
new file mode 100644
index 0000000..9b7d11e
--- /dev/null
+++ b/iproute2/README.devel
@@ -0,0 +1,15 @@
+Iproute2 development is closely tied to Linux kernel networking
+development. Most new features require a kernel and a utility component.
+
+Please submit both to the Linux networking mailing list
+ <netdev@vger.kernel.org>
+
+The current source is in the git repository:
+ git://git.kernel.org/pub/scm/linux/kernel/git/shemminger/iproute2.git
+
+The master branch contains the source corresponding to the current
+code in the mainline Linux kernel (ie follows Linus). The net-next
+branch is a temporary branch that tracks the code intended for the
+next release; it corresponds with networking development branch in
+the kernel.
+
diff --git a/iproute2/README.distribution b/iproute2/README.distribution
new file mode 100644
index 0000000..4e2e8ea
--- /dev/null
+++ b/iproute2/README.distribution
@@ -0,0 +1,95 @@
+I. About the distribution tables
+
+The table used for "synthesizing" the distribution is essentially a scaled,
+translated, inverse to the cumulative distribution function.
+
+Here's how to think about it: Let F() be the cumulative distribution
+function for a probability distribution X. We'll assume we've scaled
+things so that X has mean 0 and standard deviation 1, though that's not
+so important here. Then:
+
+ F(x) = P(X <= x) = \int_{-inf}^x f
+
+where f is the probability density function.
+
+F is monotonically increasing, so has an inverse function G, with range
+0 to 1. Here, G(t) = the x such that P(X <= x) = t. (In general, G may
+have singularities if X has point masses, i.e., points x such that
+P(X = x) > 0.)
+
+Now we create a tabular representation of G as follows: Choose some table
+size N, and for the ith entry, put in G(i/N). Let's call this table T.
+
+The claim now is, I can create a (discrete) random variable Y whose
+distribution has the same approximate "shape" as X, simply by letting
+Y = T(U), where U is a discrete uniform random variable with range 1 to N.
+To see this, it's enough to show that Y's cumulative distribution function,
+(let's call it H), is a discrete approximation to F. But
+
+ H(x) = P(Y <= x)
+ = (# of entries in T <= x) / N -- as Y chosen uniformly from T
+ = i/N, where i is the largest integer such that G(i/N) <= x
+ = i/N, where i is the largest integer such that i/N <= F(x)
+ -- since G and F are inverse functions (and F is
+ increasing)
+ = floor(N*F(x))/N
+
+as desired.
+
+II. How to create distribution tables (in theory)
+
+How can we create this table in practice? In some cases, F may have a
+simple expression which allows evaluating its inverse directly. The
+Pareto distribution is one example of this. In other cases, and
+especially for matching an experimentally observed distribution, it's
+easiest simply to create a table for F and "invert" it. Here, we give
+a concrete example, namely how the new "experimental" distribution was
+created.
+
+1. Collect enough data points to characterize the distribution. Here, I
+collected 25,000 "ping" roundtrip times to a "distant" point (time.nist.gov).
+That's far more data than is really necessary, but it was fairly painless to
+collect it, so...
+
+2. Normalize the data so that it has mean 0 and standard deviation 1.
+
+3. Determine the cumulative distribution. The code I wrote creates a table
+covering the range -10 to +10, with granularity .00005. Obviously, this
+is absurdly over-precise, but since it's a one-time only computation, I
+figured it hardly mattered.
+
+4. Invert the table: for each table entry F(x) = y, make the y*TABLESIZE
+(here, 4096) entry be x*TABLEFACTOR (here, 8192). This creates a table
+for the ("normalized") inverse of size TABLESIZE, covering its domain 0
+to 1 with granularity 1/TABLESIZE. Note that even with the granularity
+used in creating the table for F, it's possible not all the entries in
+the table for G will be filled in. So, make a pass through the
+inverse's table, filling in any missing entries by linear interpolation.
+
+III. How to create distribution tables (in practice)
+
+If you want to do all this yourself, I've provided several tools to help:
+
+1. maketable does the steps 2-4 above, and then generates the appropriate
+header file. So if you have your own time distribution, you can generate
+the header simply by:
+
+ maketable < time.values > header.h
+
+2. As explained in the other README file, the somewhat sleazy way I have
+of generating correlated values needs correction. You can generate your
+own correction tables by compiling makesigtable and makemutable with
+your header file. Check the Makefile to see how this is done.
+
+3. Warning: maketable, makesigtable and especially makemutable do
+enormous amounts of floating point arithmetic. Don't try running
+these on an old 486. (NIST Net itself will run fine on such a
+system, since in operation, it just needs to do a few simple integral
+calculations. But getting there takes some work.)
+
+4. The tables produced are all normalized for mean 0 and standard
+deviation 1. How do you know what values to use for real? Here, I've
+provided a simple "stats" utility. Give it a series of floating point
+values, and it will return their mean (mu), standard deviation (sigma),
+and correlation coefficient (rho). You can then plug these values
+directly into NIST Net.
diff --git a/iproute2/README.iproute2+tc b/iproute2/README.iproute2+tc
new file mode 100644
index 0000000..2a5638d
--- /dev/null
+++ b/iproute2/README.iproute2+tc
@@ -0,0 +1,123 @@
+iproute2+tc*
+
+It's the first release of Linux traffic control engine.
+
+
+NOTES.
+* csz scheduler is inoperational at the moment, and probably
+ never will be repaired but replaced with h-pfq scheduler.
+* To use "fw" classifier you will need ipfwchains patch.
+* No manual available. Ask me, if you have problems (only try to guess
+ answer yourself at first 8)).
+
+
+Micro-manual how to start it the first time
+-------------------------------------------
+
+A. Attach CBQ to eth1:
+
+tc qdisc add dev eth1 root handle 1: cbq bandwidth 10Mbit allot 1514 cell 8 \
+avpkt 1000 mpu 64
+
+B. Add root class:
+
+tc class add dev eth1 parent 1:0 classid 1:1 cbq bandwidth 10Mbit rate 10Mbit \
+allot 1514 cell 8 weight 1Mbit prio 8 maxburst 20 avpkt 1000
+
+C. Add default interactive class:
+
+tc class add dev eth1 parent 1:1 classid 1:2 cbq bandwidth 10Mbit rate 1Mbit \
+allot 1514 cell 8 weight 100Kbit prio 3 maxburst 20 avpkt 1000 split 1:0 \
+defmap c0
+
+D. Add default class:
+
+tc class add dev eth1 parent 1:1 classid 1:3 cbq bandwidth 10Mbit rate 8Mbit \
+allot 1514 cell 8 weight 800Kbit prio 7 maxburst 20 avpkt 1000 split 1:0 \
+defmap 3f
+
+etc. etc. etc. Well, it is enough to start 8) The rest can be guessed 8)
+Look also at more elaborated example, ready to start rsvpd,
+in rsvp/cbqinit.eth1.
+
+
+Terminology and advices about setting CBQ parameters may be found in Sally Floyd
+papers.
+
+
+Pairs X:Y are class handles, X:0 are qdisc handles.
+weight should be proportional to rate for leaf classes
+(I choosed it ten times less, but it is not necessary)
+
+defmap is bitmap of logical priorities served by this class.
+
+E. Another qdiscs are simpler. F.e. let's join TBF on class 1:2
+
+tc qdisc add dev eth1 parent 1:2 tbf rate 64Kbit buffer 5Kb/8 limit 10Kb
+
+F. Look at all that we created:
+
+tc qdisc ls dev eth1
+tc class ls dev eth1
+
+G. Install "route" classifier on root of cbq and map destination from realm
+1 to class 1:2
+
+tc filter add dev eth1 parent 1:0 protocol ip prio 100 route to 1 classid 1:2
+
+H. Assign routes to 10.11.12.0/24 to realm 1
+
+ip route add 10.11.12.0/24 dev eth1 via whatever realm 1
+
+etc. The same thing can be made with rules.
+I still did not test ipchains, but they should work too.
+
+
+Setup and code example of BPF classifier and action can be found under
+examples/bpf/, which should explain everything for getting started.
+
+
+Setup of rsvp and u32 classifiers is more hairy.
+If you read RSVP specs, you will understand how rsvp classifier
+works easily. What's about u32... That's example:
+
+
+#! /bin/sh
+
+TC=/home/root/tc
+
+# Setup classifier root on eth1 root (it is cbq)
+$TC filter add dev eth1 parent 1:0 prio 5 protocol ip u32
+
+# Create hash table of 256 slots with ID 1:
+$TC filter add dev eth1 parent 1:0 prio 5 handle 1: u32 divisor 256
+
+# Add to 6th slot of hash table rule to select tcp/telnet to 193.233.7.75
+# direct it to class 1:4 and prescribe to fall to best effort,
+# if traffic violate TBF (32kbit,5K)
+$TC filter add dev eth1 parent 1:0 prio 5 u32 ht 1:6: \
+ match ip dst 193.233.7.75 \
+ match tcp dst 0x17 0xffff \
+ flowid 1:4 \
+ police rate 32kbit buffer 5kb/8 mpu 64 mtu 1514 index 1
+
+# Add to 1th slot of hash table rule to select icmp to 193.233.7.75
+# direct it to class 1:4 and prescribe to fall to best effort,
+# if traffic violate TBF (10kbit,5K)
+$TC filter add dev eth1 parent 1:0 prio 5 u32 ht 1:: \
+ sample ip protocol 1 0xff \
+ match ip dst 193.233.7.75 \
+ flowid 1:4 \
+ police rate 10kbit buffer 5kb/8 mpu 64 mtu 1514 index 2
+
+# Lookup hash table, if it is not fragmented frame
+# Use protocol as hash key
+$TC filter add dev eth1 parent 1:0 prio 5 handle ::1 u32 ht 800:: \
+ match ip nofrag \
+ offset mask 0x0F00 shift 6 \
+ hashkey mask 0x00ff0000 at 8 \
+ link 1:
+
+
+Alexey Kuznetsov
+kuznet@ms2.inr.ac.ru
diff --git a/iproute2/README.lnstat b/iproute2/README.lnstat
new file mode 100644
index 0000000..057925f
--- /dev/null
+++ b/iproute2/README.lnstat
@@ -0,0 +1,81 @@
+lnstat - linux networking statistics
+(C) 2004 Harald Welte <laforge@gnumonks.org
+======================================================================
+
+This tool is a generalized and more feature-complete replacement for the old
+'rtstat' program.
+
+In addition to routing cache statistics, it supports any kind of statistics
+the linux kernel exports via a file in /proc/net/stat. In a stock 2.6.9
+kernel, this is
+ per-protocol neighbour cache statistics
+ (ipv4, ipv6, atm, decnet)
+ routing cache statistics
+ (ipv4)
+ connection tracking statistics
+ (ipv4)
+
+Please note that lnstat will adopt to any additional statistics that might be
+added to the kernel at some later point
+
+I personally always like examples more than any reference documentation, so I
+list the following examples. If somebody wants to do a manpage, feel free
+to send me a patch :)
+
+EXAMPLES:
+
+In order to get a list of supported statistics files, you can run
+
+ lnstat -d
+
+It will display something like
+
+/proc/net/stat/arp_cache:
+ 1: entries
+ 2: allocs
+ 3: destroys
+[...]
+/proc/net/stat/rt_cache:
+ 1: entries
+ 2: in_hit
+ 3: in_slow_tot
+
+You can now select the files/keys you are interested by something like
+
+ lnstat -k arp_cache:entries,rt_cache:in_hit,arp_cache:destroys
+
+arp_cach|rt_cache|arp_cach|
+ entries| in_hit|destroys|
+ 6| 6| 0|
+ 6| 0| 0|
+ 6| 2| 0|
+
+
+You can specify the interval (e.g. 10 seconds) by:
+
+ lnstat -i 10
+
+You can specify to only use one particular statistics file:
+
+ lnstat -f ip_conntrack
+
+You can specify individual field widths
+
+ lnstat -k arp_cache:entries,rt_cache:entries -w 20,8
+
+You can specify not to print a header at all
+
+ lnstat -s 0
+
+You can specify to print a header only at start of the program
+
+ lnstat -s 1
+
+You can specify to print a header at start and every 20 lines:
+
+ lnstat -s 20
+
+You can specify the number of samples you want to take (e.g. 5):
+
+ lnstat -c 5
+
diff --git a/iproute2/bridge/Makefile b/iproute2/bridge/Makefile
new file mode 100644
index 0000000..9800753
--- /dev/null
+++ b/iproute2/bridge/Makefile
@@ -0,0 +1,18 @@
+BROBJ = bridge.o fdb.o monitor.o link.o mdb.o vlan.o
+
+include ../Config
+
+ifeq ($(IP_CONFIG_SETNS),y)
+ CFLAGS += -DHAVE_SETNS
+endif
+
+all: bridge
+
+bridge: $(BROBJ) $(LIBNETLINK)
+
+install: all
+ install -m 0755 bridge $(DESTDIR)$(SBINDIR)
+
+clean:
+ rm -f $(BROBJ) bridge
+
diff --git a/iproute2/bridge/br_common.h b/iproute2/bridge/br_common.h
new file mode 100644
index 0000000..169a162
--- /dev/null
+++ b/iproute2/bridge/br_common.h
@@ -0,0 +1,20 @@
+extern int print_linkinfo(const struct sockaddr_nl *who,
+ struct nlmsghdr *n,
+ void *arg);
+extern int print_fdb(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg);
+extern int print_mdb(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg);
+
+extern int do_fdb(int argc, char **argv);
+extern int do_mdb(int argc, char **argv);
+extern int do_monitor(int argc, char **argv);
+extern int do_vlan(int argc, char **argv);
+extern int do_link(int argc, char **argv);
+
+extern int preferred_family;
+extern int show_stats;
+extern int show_details;
+extern int timestamp;
+extern int compress_vlans;
+extern struct rtnl_handle rth;
diff --git a/iproute2/bridge/bridge.c b/iproute2/bridge/bridge.c
new file mode 100644
index 0000000..72f153f
--- /dev/null
+++ b/iproute2/bridge/bridge.c
@@ -0,0 +1,204 @@
+/*
+ * Get/set/delete bridge with netlink
+ *
+ * Authors: Stephen Hemminger <shemminger@vyatta.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/socket.h>
+#include <string.h>
+#include <errno.h>
+
+#include "SNAPSHOT.h"
+#include "utils.h"
+#include "br_common.h"
+#include "namespace.h"
+
+struct rtnl_handle rth = { .fd = -1 };
+int preferred_family = AF_UNSPEC;
+int resolve_hosts;
+int oneline;
+int show_stats;
+int show_details;
+int compress_vlans;
+int timestamp;
+char *batch_file;
+int force;
+const char *_SL_;
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr,
+"Usage: bridge [ OPTIONS ] OBJECT { COMMAND | help }\n"
+" bridge [ -force ] -batch filename\n"
+"where OBJECT := { link | fdb | mdb | vlan | monitor }\n"
+" OPTIONS := { -V[ersion] | -s[tatistics] | -d[etails] |\n"
+" -o[neline] | -t[imestamp] | -n[etns] name |\n"
+" -c[ompressvlans] }\n");
+ exit(-1);
+}
+
+static int do_help(int argc, char **argv)
+{
+ usage();
+}
+
+
+static const struct cmd {
+ const char *cmd;
+ int (*func)(int argc, char **argv);
+} cmds[] = {
+ { "link", do_link },
+ { "fdb", do_fdb },
+ { "mdb", do_mdb },
+ { "vlan", do_vlan },
+ { "monitor", do_monitor },
+ { "help", do_help },
+ { 0 }
+};
+
+static int do_cmd(const char *argv0, int argc, char **argv)
+{
+ const struct cmd *c;
+
+ for (c = cmds; c->cmd; ++c) {
+ if (matches(argv0, c->cmd) == 0)
+ return c->func(argc-1, argv+1);
+ }
+
+ fprintf(stderr,
+ "Object \"%s\" is unknown, try \"bridge help\".\n", argv0);
+ return -1;
+}
+
+static int batch(const char *name)
+{
+ char *line = NULL;
+ size_t len = 0;
+ int ret = EXIT_SUCCESS;
+
+ if (name && strcmp(name, "-") != 0) {
+ if (freopen(name, "r", stdin) == NULL) {
+ fprintf(stderr,
+ "Cannot open file \"%s\" for reading: %s\n",
+ name, strerror(errno));
+ return EXIT_FAILURE;
+ }
+ }
+
+ if (rtnl_open(&rth, 0) < 0) {
+ fprintf(stderr, "Cannot open rtnetlink\n");
+ return EXIT_FAILURE;
+ }
+
+ cmdlineno = 0;
+ while (getcmdline(&line, &len, stdin) != -1) {
+ char *largv[100];
+ int largc;
+
+ largc = makeargs(line, largv, 100);
+ if (largc == 0)
+ continue; /* blank line */
+
+ if (do_cmd(largv[0], largc, largv)) {
+ fprintf(stderr, "Command failed %s:%d\n",
+ name, cmdlineno);
+ ret = EXIT_FAILURE;
+ if (!force)
+ break;
+ }
+ }
+ if (line)
+ free(line);
+
+ rtnl_close(&rth);
+ return ret;
+}
+
+int
+main(int argc, char **argv)
+{
+ while (argc > 1) {
+ const char *opt = argv[1];
+
+ if (strcmp(opt, "--") == 0) {
+ argc--; argv++;
+ break;
+ }
+ if (opt[0] != '-')
+ break;
+ if (opt[1] == '-')
+ opt++;
+
+ if (matches(opt, "-help") == 0) {
+ usage();
+ } else if (matches(opt, "-Version") == 0) {
+ printf("bridge utility, 0.0\n");
+ exit(0);
+ } else if (matches(opt, "-stats") == 0 ||
+ matches(opt, "-statistics") == 0) {
+ ++show_stats;
+ } else if (matches(opt, "-details") == 0) {
+ ++show_details;
+ } else if (matches(opt, "-oneline") == 0) {
+ ++oneline;
+ } else if (matches(opt, "-timestamp") == 0) {
+ ++timestamp;
+ } else if (matches(opt, "-family") == 0) {
+ argc--;
+ argv++;
+ if (argc <= 1)
+ usage();
+ if (strcmp(argv[1], "inet") == 0)
+ preferred_family = AF_INET;
+ else if (strcmp(argv[1], "inet6") == 0)
+ preferred_family = AF_INET6;
+ else if (strcmp(argv[1], "help") == 0)
+ usage();
+ else
+ invarg("invalid protocol family", argv[1]);
+ } else if (strcmp(opt, "-4") == 0) {
+ preferred_family = AF_INET;
+ } else if (strcmp(opt, "-6") == 0) {
+ preferred_family = AF_INET6;
+ } else if (matches(opt, "-netns") == 0) {
+ NEXT_ARG();
+ if (netns_switch(argv[1]))
+ exit(-1);
+ } else if (matches(opt, "-compressvlans") == 0) {
+ ++compress_vlans;
+ } else if (matches(opt, "-force") == 0) {
+ ++force;
+ } else if (matches(opt, "-batch") == 0) {
+ argc--;
+ argv++;
+ if (argc <= 1)
+ usage();
+ batch_file = argv[1];
+ } else {
+ fprintf(stderr,
+ "Option \"%s\" is unknown, try \"bridge help\".\n",
+ opt);
+ exit(-1);
+ }
+ argc--; argv++;
+ }
+
+ _SL_ = oneline ? "\\" : "\n";
+
+ if (batch_file)
+ return batch(batch_file);
+
+ if (rtnl_open(&rth, 0) < 0)
+ exit(1);
+
+ if (argc > 1)
+ return do_cmd(argv[1], argc-1, argv+1);
+
+ rtnl_close(&rth);
+ usage();
+}
diff --git a/iproute2/bridge/fdb.c b/iproute2/bridge/fdb.c
new file mode 100644
index 0000000..4d10925
--- /dev/null
+++ b/iproute2/bridge/fdb.c
@@ -0,0 +1,400 @@
+/*
+ * Get/set/delete fdb table with netlink
+ *
+ * TODO: merge/replace this with ip neighbour
+ *
+ * Authors: Stephen Hemminger <shemminger@vyatta.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <netdb.h>
+#include <time.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <net/if.h>
+#include <netinet/in.h>
+#include <linux/if_bridge.h>
+#include <linux/if_ether.h>
+#include <linux/neighbour.h>
+#include <string.h>
+#include <limits.h>
+
+#include "libnetlink.h"
+#include "br_common.h"
+#include "rt_names.h"
+#include "utils.h"
+
+static unsigned int filter_index;
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: bridge fdb { add | append | del | replace } ADDR dev DEV\n"
+ " [ self ] [ master ] [ use ] [ router ]\n"
+ " [ local | temp ] [ dst IPADDR ] [ vlan VID ]\n"
+ " [ port PORT] [ vni VNI ] [ via DEV ]\n");
+ fprintf(stderr, " bridge fdb [ show [ br BRDEV ] [ brport DEV ] ]\n");
+ exit(-1);
+}
+
+static const char *state_n2a(unsigned s)
+{
+ static char buf[32];
+
+ if (s & NUD_PERMANENT)
+ return "permanent";
+
+ if (s & NUD_NOARP)
+ return "static";
+
+ if (s & NUD_STALE)
+ return "stale";
+
+ if (s & NUD_REACHABLE)
+ return "";
+
+ sprintf(buf, "state=%#x", s);
+ return buf;
+}
+
+int print_fdb(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = arg;
+ struct ndmsg *r = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr * tb[NDA_MAX+1];
+
+ if (n->nlmsg_type != RTM_NEWNEIGH && n->nlmsg_type != RTM_DELNEIGH) {
+ fprintf(stderr, "Not RTM_NEWNEIGH: %08x %08x %08x\n",
+ n->nlmsg_len, n->nlmsg_type, n->nlmsg_flags);
+
+ return 0;
+ }
+
+ len -= NLMSG_LENGTH(sizeof(*r));
+ if (len < 0) {
+ fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+ return -1;
+ }
+
+ if (r->ndm_family != AF_BRIDGE)
+ return 0;
+
+ if (filter_index && filter_index != r->ndm_ifindex)
+ return 0;
+
+ parse_rtattr(tb, NDA_MAX, NDA_RTA(r),
+ n->nlmsg_len - NLMSG_LENGTH(sizeof(*r)));
+
+ if (n->nlmsg_type == RTM_DELNEIGH)
+ fprintf(fp, "Deleted ");
+
+ if (tb[NDA_LLADDR]) {
+ SPRINT_BUF(b1);
+ fprintf(fp, "%s ",
+ ll_addr_n2a(RTA_DATA(tb[NDA_LLADDR]),
+ RTA_PAYLOAD(tb[NDA_LLADDR]),
+ ll_index_to_type(r->ndm_ifindex),
+ b1, sizeof(b1)));
+ }
+
+ if (!filter_index && r->ndm_ifindex)
+ fprintf(fp, "dev %s ", ll_index_to_name(r->ndm_ifindex));
+
+ if (tb[NDA_DST]) {
+ SPRINT_BUF(abuf);
+ int family = AF_INET;
+
+ if (RTA_PAYLOAD(tb[NDA_DST]) == sizeof(struct in6_addr))
+ family = AF_INET6;
+
+ fprintf(fp, "dst %s ",
+ format_host(family,
+ RTA_PAYLOAD(tb[NDA_DST]),
+ RTA_DATA(tb[NDA_DST]),
+ abuf, sizeof(abuf)));
+ }
+
+ if (tb[NDA_VLAN]) {
+ __u16 vid = rta_getattr_u16(tb[NDA_VLAN]);
+ fprintf(fp, "vlan %hu ", vid);
+ }
+
+ if (tb[NDA_PORT])
+ fprintf(fp, "port %d ", ntohs(rta_getattr_u16(tb[NDA_PORT])));
+ if (tb[NDA_VNI])
+ fprintf(fp, "vni %d ", rta_getattr_u32(tb[NDA_VNI]));
+ if (tb[NDA_IFINDEX]) {
+ unsigned int ifindex = rta_getattr_u32(tb[NDA_IFINDEX]);
+
+ if (ifindex) {
+ char ifname[IF_NAMESIZE];
+
+ if (!tb[NDA_LINK_NETNSID] &&
+ if_indextoname(ifindex, ifname))
+ fprintf(fp, "via %s ", ifname);
+ else
+ fprintf(fp, "via ifindex %u ", ifindex);
+ }
+ }
+ if (tb[NDA_LINK_NETNSID])
+ fprintf(fp, "link-netnsid %d ",
+ rta_getattr_u32(tb[NDA_LINK_NETNSID]));
+
+ if (show_stats && tb[NDA_CACHEINFO]) {
+ struct nda_cacheinfo *ci = RTA_DATA(tb[NDA_CACHEINFO]);
+ int hz = get_user_hz();
+
+ fprintf(fp, "used %d/%d ", ci->ndm_used/hz,
+ ci->ndm_updated/hz);
+ }
+ if (r->ndm_flags & NTF_SELF)
+ fprintf(fp, "self ");
+ if (tb[NDA_MASTER])
+ fprintf(fp, "master %s ",
+ ll_index_to_name(rta_getattr_u32(tb[NDA_MASTER])));
+ else if (r->ndm_flags & NTF_MASTER)
+ fprintf(fp, "master ");
+ if (r->ndm_flags & NTF_ROUTER)
+ fprintf(fp, "router ");
+ if (r->ndm_flags & NTF_EXT_LEARNED)
+ fprintf(fp, "offload ");
+
+ fprintf(fp, "%s\n", state_n2a(r->ndm_state));
+ fflush(fp);
+
+ return 0;
+}
+
+static int fdb_show(int argc, char **argv)
+{
+ struct {
+ struct nlmsghdr n;
+ struct ifinfomsg ifm;
+ char buf[256];
+ } req;
+
+ char *filter_dev = NULL;
+ char *br = NULL;
+ int msg_size = sizeof(struct ifinfomsg);
+
+ memset(&req, 0, sizeof(req));
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+ req.ifm.ifi_family = PF_BRIDGE;
+
+ while (argc > 0) {
+ if ((strcmp(*argv, "brport") == 0) || strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ filter_dev = *argv;
+ } else if (strcmp(*argv, "br") == 0) {
+ NEXT_ARG();
+ br = *argv;
+ } else {
+ if (matches(*argv, "help") == 0)
+ usage();
+ }
+ argc--; argv++;
+ }
+
+ if (br) {
+ int br_ifindex = ll_name_to_index(br);
+ if (br_ifindex == 0) {
+ fprintf(stderr, "Cannot find bridge device \"%s\"\n", br);
+ return -1;
+ }
+ addattr32(&req.n, sizeof(req), IFLA_MASTER, br_ifindex);
+ msg_size += RTA_LENGTH(4);
+ }
+
+ /*we'll keep around filter_dev for older kernels */
+ if (filter_dev) {
+ filter_index = if_nametoindex(filter_dev);
+ if (filter_index == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n",
+ filter_dev);
+ return -1;
+ }
+ req.ifm.ifi_index = filter_index;
+ }
+
+ if (rtnl_dump_request(&rth, RTM_GETNEIGH, &req.ifm, msg_size) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+
+ if (rtnl_dump_filter(&rth, print_fdb, stdout) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ exit(1);
+ }
+
+ return 0;
+}
+
+static int fdb_modify(int cmd, int flags, int argc, char **argv)
+{
+ struct {
+ struct nlmsghdr n;
+ struct ndmsg ndm;
+ char buf[256];
+ } req;
+ char *addr = NULL;
+ char *d = NULL;
+ char abuf[ETH_ALEN];
+ int dst_ok = 0;
+ inet_prefix dst;
+ unsigned long port = 0;
+ unsigned long vni = ~0;
+ unsigned int via = 0;
+ char *endptr;
+ short vid = -1;
+
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ndmsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST|flags;
+ req.n.nlmsg_type = cmd;
+ req.ndm.ndm_family = PF_BRIDGE;
+ req.ndm.ndm_state = NUD_NOARP;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ d = *argv;
+ } else if (strcmp(*argv, "dst") == 0) {
+ NEXT_ARG();
+ if (dst_ok)
+ duparg2("dst", *argv);
+ get_addr(&dst, *argv, preferred_family);
+ dst_ok = 1;
+ } else if (strcmp(*argv, "port") == 0) {
+
+ NEXT_ARG();
+ port = strtoul(*argv, &endptr, 0);
+ if (endptr && *endptr) {
+ struct servent *pse;
+
+ pse = getservbyname(*argv, "udp");
+ if (!pse)
+ invarg("invalid port\n", *argv);
+ port = ntohs(pse->s_port);
+ } else if (port > 0xffff)
+ invarg("invalid port\n", *argv);
+ } else if (strcmp(*argv, "vni") == 0) {
+ NEXT_ARG();
+ vni = strtoul(*argv, &endptr, 0);
+ if ((endptr && *endptr) ||
+ (vni >> 24) || vni == ULONG_MAX)
+ invarg("invalid VNI\n", *argv);
+ } else if (strcmp(*argv, "via") == 0) {
+ NEXT_ARG();
+ via = if_nametoindex(*argv);
+ if (via == 0)
+ invarg("invalid device\n", *argv);
+ } else if (strcmp(*argv, "self") == 0) {
+ req.ndm.ndm_flags |= NTF_SELF;
+ } else if (matches(*argv, "master") == 0) {
+ req.ndm.ndm_flags |= NTF_MASTER;
+ } else if (matches(*argv, "router") == 0) {
+ req.ndm.ndm_flags |= NTF_ROUTER;
+ } else if (matches(*argv, "local") == 0||
+ matches(*argv, "permanent") == 0) {
+ req.ndm.ndm_state |= NUD_PERMANENT;
+ } else if (matches(*argv, "temp") == 0) {
+ req.ndm.ndm_state |= NUD_REACHABLE;
+ } else if (matches(*argv, "vlan") == 0) {
+ if (vid >= 0)
+ duparg2("vlan", *argv);
+ NEXT_ARG();
+ vid = atoi(*argv);
+ } else if (matches(*argv, "use") == 0) {
+ req.ndm.ndm_flags |= NTF_USE;
+ } else {
+ if (strcmp(*argv, "to") == 0) {
+ NEXT_ARG();
+ }
+ if (matches(*argv, "help") == 0)
+ usage();
+ if (addr)
+ duparg2("to", *argv);
+ addr = *argv;
+ }
+ argc--; argv++;
+ }
+
+ if (d == NULL || addr == NULL) {
+ fprintf(stderr, "Device and address are required arguments.\n");
+ return -1;
+ }
+
+ /* Assume self */
+ if (!(req.ndm.ndm_flags&(NTF_SELF|NTF_MASTER)))
+ req.ndm.ndm_flags |= NTF_SELF;
+
+ /* Assume permanent */
+ if (!(req.ndm.ndm_state&(NUD_PERMANENT|NUD_REACHABLE)))
+ req.ndm.ndm_state |= NUD_PERMANENT;
+
+ if (sscanf(addr, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx",
+ abuf, abuf+1, abuf+2,
+ abuf+3, abuf+4, abuf+5) != 6) {
+ fprintf(stderr, "Invalid mac address %s\n", addr);
+ return -1;
+ }
+
+ addattr_l(&req.n, sizeof(req), NDA_LLADDR, abuf, ETH_ALEN);
+ if (dst_ok)
+ addattr_l(&req.n, sizeof(req), NDA_DST, &dst.data, dst.bytelen);
+
+ if (vid >= 0)
+ addattr16(&req.n, sizeof(req), NDA_VLAN, vid);
+
+ if (port) {
+ unsigned short dport;
+
+ dport = htons((unsigned short)port);
+ addattr16(&req.n, sizeof(req), NDA_PORT, dport);
+ }
+ if (vni != ~0)
+ addattr32(&req.n, sizeof(req), NDA_VNI, vni);
+ if (via)
+ addattr32(&req.n, sizeof(req), NDA_IFINDEX, via);
+
+ req.ndm.ndm_ifindex = ll_name_to_index(d);
+ if (req.ndm.ndm_ifindex == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", d);
+ return -1;
+ }
+
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ return -1;
+
+ return 0;
+}
+
+int do_fdb(int argc, char **argv)
+{
+ ll_init_map(&rth);
+
+ if (argc > 0) {
+ if (matches(*argv, "add") == 0)
+ return fdb_modify(RTM_NEWNEIGH, NLM_F_CREATE|NLM_F_EXCL, argc-1, argv+1);
+ if (matches(*argv, "append") == 0)
+ return fdb_modify(RTM_NEWNEIGH, NLM_F_CREATE|NLM_F_APPEND, argc-1, argv+1);
+ if (matches(*argv, "replace") == 0)
+ return fdb_modify(RTM_NEWNEIGH, NLM_F_CREATE|NLM_F_REPLACE, argc-1, argv+1);
+ if (matches(*argv, "delete") == 0)
+ return fdb_modify(RTM_DELNEIGH, 0, argc-1, argv+1);
+ if (matches(*argv, "show") == 0 ||
+ matches(*argv, "lst") == 0 ||
+ matches(*argv, "list") == 0)
+ return fdb_show(argc-1, argv+1);
+ if (matches(*argv, "help") == 0)
+ usage();
+ } else
+ return fdb_show(0, NULL);
+
+ fprintf(stderr, "Command \"%s\" is unknown, try \"bridge fdb help\".\n", *argv);
+ exit(-1);
+}
diff --git a/iproute2/bridge/link.c b/iproute2/bridge/link.c
new file mode 100644
index 0000000..a9b1262
--- /dev/null
+++ b/iproute2/bridge/link.c
@@ -0,0 +1,476 @@
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <time.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <netinet/in.h>
+#include <linux/if.h>
+#include <linux/if_bridge.h>
+#include <string.h>
+#include <stdbool.h>
+
+#include "libnetlink.h"
+#include "utils.h"
+#include "br_common.h"
+
+static unsigned int filter_index;
+
+static const char *port_states[] = {
+ [BR_STATE_DISABLED] = "disabled",
+ [BR_STATE_LISTENING] = "listening",
+ [BR_STATE_LEARNING] = "learning",
+ [BR_STATE_FORWARDING] = "forwarding",
+ [BR_STATE_BLOCKING] = "blocking",
+};
+
+extern char *if_indextoname (unsigned int __ifindex, char *__ifname);
+
+static void print_link_flags(FILE *fp, unsigned flags)
+{
+ fprintf(fp, "<");
+ if (flags & IFF_UP && !(flags & IFF_RUNNING))
+ fprintf(fp, "NO-CARRIER%s", flags ? "," : "");
+ flags &= ~IFF_RUNNING;
+#define _PF(f) if (flags&IFF_##f) { \
+ flags &= ~IFF_##f ; \
+ fprintf(fp, #f "%s", flags ? "," : ""); }
+ _PF(LOOPBACK);
+ _PF(BROADCAST);
+ _PF(POINTOPOINT);
+ _PF(MULTICAST);
+ _PF(NOARP);
+ _PF(ALLMULTI);
+ _PF(PROMISC);
+ _PF(MASTER);
+ _PF(SLAVE);
+ _PF(DEBUG);
+ _PF(DYNAMIC);
+ _PF(AUTOMEDIA);
+ _PF(PORTSEL);
+ _PF(NOTRAILERS);
+ _PF(UP);
+ _PF(LOWER_UP);
+ _PF(DORMANT);
+ _PF(ECHO);
+#undef _PF
+ if (flags)
+ fprintf(fp, "%x", flags);
+ fprintf(fp, "> ");
+}
+
+static const char *oper_states[] = {
+ "UNKNOWN", "NOTPRESENT", "DOWN", "LOWERLAYERDOWN",
+ "TESTING", "DORMANT", "UP"
+};
+
+static const char *hw_mode[] = {"VEB", "VEPA"};
+
+static void print_operstate(FILE *f, __u8 state)
+{
+ if (state >= sizeof(oper_states)/sizeof(oper_states[0]))
+ fprintf(f, "state %#x ", state);
+ else
+ fprintf(f, "state %s ", oper_states[state]);
+}
+
+static void print_portstate(FILE *f, __u8 state)
+{
+ if (state <= BR_STATE_BLOCKING)
+ fprintf(f, "state %s ", port_states[state]);
+ else
+ fprintf(f, "state (%d) ", state);
+}
+
+static void print_onoff(FILE *f, char *flag, __u8 val)
+{
+ fprintf(f, "%s %s ", flag, val ? "on" : "off");
+}
+
+static void print_hwmode(FILE *f, __u16 mode)
+{
+ if (mode >= sizeof(hw_mode)/sizeof(hw_mode[0]))
+ fprintf(f, "hwmode %#hx ", mode);
+ else
+ fprintf(f, "hwmode %s ", hw_mode[mode]);
+}
+
+int print_linkinfo(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = arg;
+ int len = n->nlmsg_len;
+ struct ifinfomsg *ifi = NLMSG_DATA(n);
+ struct rtattr * tb[IFLA_MAX+1];
+ char b1[IFNAMSIZ];
+
+ len -= NLMSG_LENGTH(sizeof(*ifi));
+ if (len < 0) {
+ fprintf(stderr, "Message too short!\n");
+ return -1;
+ }
+
+ if (!(ifi->ifi_family == AF_BRIDGE || ifi->ifi_family == AF_UNSPEC))
+ return 0;
+
+ if (filter_index && filter_index != ifi->ifi_index)
+ return 0;
+
+ parse_rtattr_flags(tb, IFLA_MAX, IFLA_RTA(ifi), len, NLA_F_NESTED);
+
+ if (tb[IFLA_IFNAME] == NULL) {
+ fprintf(stderr, "BUG: nil ifname\n");
+ return -1;
+ }
+
+ if (n->nlmsg_type == RTM_DELLINK)
+ fprintf(fp, "Deleted ");
+
+ fprintf(fp, "%d: %s ", ifi->ifi_index,
+ tb[IFLA_IFNAME] ? rta_getattr_str(tb[IFLA_IFNAME]) : "<nil>");
+
+ if (tb[IFLA_OPERSTATE])
+ print_operstate(fp, rta_getattr_u8(tb[IFLA_OPERSTATE]));
+
+ if (tb[IFLA_LINK]) {
+ SPRINT_BUF(b1);
+ int iflink = rta_getattr_u32(tb[IFLA_LINK]);
+ if (iflink == 0)
+ fprintf(fp, "@NONE: ");
+ else
+ fprintf(fp, "@%s: ",
+ if_indextoname(iflink, b1));
+ } else
+ fprintf(fp, ": ");
+
+ print_link_flags(fp, ifi->ifi_flags);
+
+ if (tb[IFLA_MTU])
+ fprintf(fp, "mtu %u ", rta_getattr_u32(tb[IFLA_MTU]));
+
+ if (tb[IFLA_MASTER])
+ fprintf(fp, "master %s ",
+ if_indextoname(rta_getattr_u32(tb[IFLA_MASTER]), b1));
+
+ if (tb[IFLA_PROTINFO]) {
+ if (tb[IFLA_PROTINFO]->rta_type & NLA_F_NESTED) {
+ struct rtattr *prtb[IFLA_BRPORT_MAX+1];
+
+ parse_rtattr_nested(prtb, IFLA_BRPORT_MAX,
+ tb[IFLA_PROTINFO]);
+
+ if (prtb[IFLA_BRPORT_STATE])
+ print_portstate(fp,
+ rta_getattr_u8(prtb[IFLA_BRPORT_STATE]));
+ if (prtb[IFLA_BRPORT_PRIORITY])
+ fprintf(fp, "priority %hu ",
+ rta_getattr_u16(prtb[IFLA_BRPORT_PRIORITY]));
+ if (prtb[IFLA_BRPORT_COST])
+ fprintf(fp, "cost %u ",
+ rta_getattr_u32(prtb[IFLA_BRPORT_COST]));
+
+ if (show_details) {
+ fprintf(fp, "%s ", _SL_);
+
+ if (prtb[IFLA_BRPORT_MODE])
+ print_onoff(fp, "hairpin",
+ rta_getattr_u8(prtb[IFLA_BRPORT_MODE]));
+ if (prtb[IFLA_BRPORT_GUARD])
+ print_onoff(fp, "guard",
+ rta_getattr_u8(prtb[IFLA_BRPORT_GUARD]));
+ if (prtb[IFLA_BRPORT_PROTECT])
+ print_onoff(fp, "root_block",
+ rta_getattr_u8(prtb[IFLA_BRPORT_PROTECT]));
+ if (prtb[IFLA_BRPORT_FAST_LEAVE])
+ print_onoff(fp, "fastleave",
+ rta_getattr_u8(prtb[IFLA_BRPORT_FAST_LEAVE]));
+ if (prtb[IFLA_BRPORT_LEARNING])
+ print_onoff(fp, "learning",
+ rta_getattr_u8(prtb[IFLA_BRPORT_LEARNING]));
+ if (prtb[IFLA_BRPORT_LEARNING_SYNC])
+ print_onoff(fp, "learning_sync",
+ rta_getattr_u8(prtb[IFLA_BRPORT_LEARNING_SYNC]));
+ if (prtb[IFLA_BRPORT_UNICAST_FLOOD])
+ print_onoff(fp, "flood",
+ rta_getattr_u8(prtb[IFLA_BRPORT_UNICAST_FLOOD]));
+ }
+ } else
+ print_portstate(fp, rta_getattr_u8(tb[IFLA_PROTINFO]));
+ }
+
+ if (tb[IFLA_AF_SPEC]) {
+ /* This is reported by HW devices that have some bridging
+ * capabilities.
+ */
+ struct rtattr *aftb[IFLA_BRIDGE_MAX+1];
+
+ parse_rtattr_nested(aftb, IFLA_BRIDGE_MAX, tb[IFLA_AF_SPEC]);
+
+ if (aftb[IFLA_BRIDGE_MODE])
+ print_hwmode(fp, rta_getattr_u16(aftb[IFLA_BRIDGE_MODE]));
+ }
+
+ fprintf(fp, "\n");
+ fflush(fp);
+ return 0;
+}
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: bridge link set dev DEV [ cost COST ] [ priority PRIO ] [ state STATE ]\n");
+ fprintf(stderr, " [ guard {on | off} ]\n");
+ fprintf(stderr, " [ hairpin {on | off} ] \n");
+ fprintf(stderr, " [ fastleave {on | off} ]\n");
+ fprintf(stderr, " [ root_block {on | off} ]\n");
+ fprintf(stderr, " [ learning {on | off} ]\n");
+ fprintf(stderr, " [ learning_sync {on | off} ]\n");
+ fprintf(stderr, " [ flood {on | off} ]\n");
+ fprintf(stderr, " [ hwmode {vepa | veb} ]\n");
+ fprintf(stderr, " [ self ] [ master ]\n");
+ fprintf(stderr, " bridge link show [dev DEV]\n");
+ exit(-1);
+}
+
+static bool on_off(char *arg, __s8 *attr, char *val)
+{
+ if (strcmp(val, "on") == 0)
+ *attr = 1;
+ else if (strcmp(val, "off") == 0)
+ *attr = 0;
+ else {
+ fprintf(stderr,
+ "Error: argument of \"%s\" must be \"on\" or \"off\"\n",
+ arg);
+ return false;
+ }
+
+ return true;
+}
+
+static int brlink_modify(int argc, char **argv)
+{
+ struct {
+ struct nlmsghdr n;
+ struct ifinfomsg ifm;
+ char buf[512];
+ } req;
+ char *d = NULL;
+ __s8 learning = -1;
+ __s8 learning_sync = -1;
+ __s8 flood = -1;
+ __s8 hairpin = -1;
+ __s8 bpdu_guard = -1;
+ __s8 fast_leave = -1;
+ __s8 root_block = -1;
+ __u32 cost = 0;
+ __s16 priority = -1;
+ __s8 state = -1;
+ __s16 mode = -1;
+ __u16 flags = 0;
+ struct rtattr *nest;
+
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = RTM_SETLINK;
+ req.ifm.ifi_family = PF_BRIDGE;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ d = *argv;
+ } else if (strcmp(*argv, "guard") == 0) {
+ NEXT_ARG();
+ if (!on_off("guard", &bpdu_guard, *argv))
+ return -1;
+ } else if (strcmp(*argv, "hairpin") == 0) {
+ NEXT_ARG();
+ if (!on_off("hairping", &hairpin, *argv))
+ return -1;
+ } else if (strcmp(*argv, "fastleave") == 0) {
+ NEXT_ARG();
+ if (!on_off("fastleave", &fast_leave, *argv))
+ return -1;
+ } else if (strcmp(*argv, "root_block") == 0) {
+ NEXT_ARG();
+ if (!on_off("root_block", &root_block, *argv))
+ return -1;
+ } else if (strcmp(*argv, "learning") == 0) {
+ NEXT_ARG();
+ if (!on_off("learning", &learning, *argv))
+ return -1;
+ } else if (strcmp(*argv, "learning_sync") == 0) {
+ NEXT_ARG();
+ if (!on_off("learning_sync", &learning_sync, *argv))
+ return -1;
+ } else if (strcmp(*argv, "flood") == 0) {
+ NEXT_ARG();
+ if (!on_off("flood", &flood, *argv))
+ return -1;
+ } else if (strcmp(*argv, "cost") == 0) {
+ NEXT_ARG();
+ cost = atoi(*argv);
+ } else if (strcmp(*argv, "priority") == 0) {
+ NEXT_ARG();
+ priority = atoi(*argv);
+ } else if (strcmp(*argv, "state") == 0) {
+ NEXT_ARG();
+ char *endptr;
+ size_t nstates = sizeof(port_states) / sizeof(*port_states);
+ state = strtol(*argv, &endptr, 10);
+ if (!(**argv != '\0' && *endptr == '\0')) {
+ for (state = 0; state < nstates; state++)
+ if (strcmp(port_states[state], *argv) == 0)
+ break;
+ if (state == nstates) {
+ fprintf(stderr,
+ "Error: invalid STP port state\n");
+ return -1;
+ }
+ }
+ } else if (strcmp(*argv, "hwmode") == 0) {
+ NEXT_ARG();
+ flags = BRIDGE_FLAGS_SELF;
+ if (strcmp(*argv, "vepa") == 0)
+ mode = BRIDGE_MODE_VEPA;
+ else if (strcmp(*argv, "veb") == 0)
+ mode = BRIDGE_MODE_VEB;
+ else {
+ fprintf(stderr,
+ "Mode argument must be \"vepa\" or "
+ "\"veb\".\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "self") == 0) {
+ flags |= BRIDGE_FLAGS_SELF;
+ } else if (strcmp(*argv, "master") == 0) {
+ flags |= BRIDGE_FLAGS_MASTER;
+ } else {
+ usage();
+ }
+ argc--; argv++;
+ }
+ if (d == NULL) {
+ fprintf(stderr, "Device is a required argument.\n");
+ return -1;
+ }
+
+
+ req.ifm.ifi_index = ll_name_to_index(d);
+ if (req.ifm.ifi_index == 0) {
+ fprintf(stderr, "Cannot find bridge device \"%s\"\n", d);
+ return -1;
+ }
+
+ /* Nested PROTINFO attribute. Contains: port flags, cost, priority and
+ * state.
+ */
+ nest = addattr_nest(&req.n, sizeof(req),
+ IFLA_PROTINFO | NLA_F_NESTED);
+ /* Flags first */
+ if (bpdu_guard >= 0)
+ addattr8(&req.n, sizeof(req), IFLA_BRPORT_GUARD, bpdu_guard);
+ if (hairpin >= 0)
+ addattr8(&req.n, sizeof(req), IFLA_BRPORT_MODE, hairpin);
+ if (fast_leave >= 0)
+ addattr8(&req.n, sizeof(req), IFLA_BRPORT_FAST_LEAVE,
+ fast_leave);
+ if (root_block >= 0)
+ addattr8(&req.n, sizeof(req), IFLA_BRPORT_PROTECT, root_block);
+ if (flood >= 0)
+ addattr8(&req.n, sizeof(req), IFLA_BRPORT_UNICAST_FLOOD, flood);
+ if (learning >= 0)
+ addattr8(&req.n, sizeof(req), IFLA_BRPORT_LEARNING, learning);
+ if (learning_sync >= 0)
+ addattr8(&req.n, sizeof(req), IFLA_BRPORT_LEARNING_SYNC,
+ learning_sync);
+
+ if (cost > 0)
+ addattr32(&req.n, sizeof(req), IFLA_BRPORT_COST, cost);
+
+ if (priority >= 0)
+ addattr16(&req.n, sizeof(req), IFLA_BRPORT_PRIORITY, priority);
+
+ if (state >= 0)
+ addattr8(&req.n, sizeof(req), IFLA_BRPORT_STATE, state);
+
+ addattr_nest_end(&req.n, nest);
+
+ /* IFLA_AF_SPEC nested attribute. Contains IFLA_BRIDGE_FLAGS that
+ * designates master or self operation and IFLA_BRIDGE_MODE
+ * for hw 'vepa' or 'veb' operation modes. The hwmodes are
+ * only valid in 'self' mode on some devices so far.
+ */
+ if (mode >= 0 || flags > 0) {
+ nest = addattr_nest(&req.n, sizeof(req), IFLA_AF_SPEC);
+
+ if (flags > 0)
+ addattr16(&req.n, sizeof(req), IFLA_BRIDGE_FLAGS, flags);
+
+ if (mode >= 0)
+ addattr16(&req.n, sizeof(req), IFLA_BRIDGE_MODE, mode);
+
+ addattr_nest_end(&req.n, nest);
+ }
+
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ return -1;
+
+ return 0;
+}
+
+static int brlink_show(int argc, char **argv)
+{
+ char *filter_dev = NULL;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ if (filter_dev)
+ duparg("dev", *argv);
+ filter_dev = *argv;
+ }
+ argc--; argv++;
+ }
+
+ if (filter_dev) {
+ if ((filter_index = ll_name_to_index(filter_dev)) == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n",
+ filter_dev);
+ return -1;
+ }
+ }
+
+ if (rtnl_wilddump_request(&rth, PF_BRIDGE, RTM_GETLINK) < 0) {
+ perror("Cannon send dump request");
+ exit(1);
+ }
+
+ if (rtnl_dump_filter(&rth, print_linkinfo, stdout) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ exit(1);
+ }
+ return 0;
+}
+
+int do_link(int argc, char **argv)
+{
+ ll_init_map(&rth);
+ if (argc > 0) {
+ if (matches(*argv, "set") == 0 ||
+ matches(*argv, "change") == 0)
+ return brlink_modify(argc-1, argv+1);
+ if (matches(*argv, "show") == 0 ||
+ matches(*argv, "lst") == 0 ||
+ matches(*argv, "list") == 0)
+ return brlink_show(argc-1, argv+1);
+ if (matches(*argv, "help") == 0)
+ usage();
+ } else
+ return brlink_show(0, NULL);
+
+ fprintf(stderr, "Command \"%s\" is unknown, try \"bridge link help\".\n", *argv);
+ exit(-1);
+}
diff --git a/iproute2/bridge/mdb.c b/iproute2/bridge/mdb.c
new file mode 100644
index 0000000..24c4903
--- /dev/null
+++ b/iproute2/bridge/mdb.c
@@ -0,0 +1,279 @@
+/*
+ * Get mdb table with netlink
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <net/if.h>
+#include <netinet/in.h>
+#include <linux/if_bridge.h>
+#include <linux/if_ether.h>
+#include <string.h>
+#include <arpa/inet.h>
+
+#include "libnetlink.h"
+#include "br_common.h"
+#include "rt_names.h"
+#include "utils.h"
+
+#ifndef MDBA_RTA
+#define MDBA_RTA(r) \
+ ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct br_port_msg))))
+#endif
+
+static unsigned int filter_index;
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: bridge mdb { add | del } dev DEV port PORT grp GROUP [permanent | temp] [vid VID]\n");
+ fprintf(stderr, " bridge mdb {show} [ dev DEV ]\n");
+ exit(-1);
+}
+
+static void br_print_router_ports(FILE *f, struct rtattr *attr)
+{
+ uint32_t *port_ifindex;
+ struct rtattr *i;
+ int rem;
+
+ rem = RTA_PAYLOAD(attr);
+ for (i = RTA_DATA(attr); RTA_OK(i, rem); i = RTA_NEXT(i, rem)) {
+ port_ifindex = RTA_DATA(i);
+ fprintf(f, "%s ", ll_index_to_name(*port_ifindex));
+ }
+
+ fprintf(f, "\n");
+}
+
+static void print_mdb_entry(FILE *f, int ifindex, struct br_mdb_entry *e,
+ struct nlmsghdr *n)
+{
+ SPRINT_BUF(abuf);
+ const void *src;
+ int af;
+
+ af = e->addr.proto == htons(ETH_P_IP) ? AF_INET : AF_INET6;
+ src = af == AF_INET ? (const void *)&e->addr.u.ip4 :
+ (const void *)&e->addr.u.ip6;
+ if (n->nlmsg_type == RTM_DELMDB)
+ fprintf(f, "Deleted ");
+ fprintf(f, "dev %s port %s grp %s %s", ll_index_to_name(ifindex),
+ ll_index_to_name(e->ifindex),
+ inet_ntop(af, src, abuf, sizeof(abuf)),
+ (e->state & MDB_PERMANENT) ? "permanent" : "temp");
+ if (e->vid)
+ fprintf(f, " vid %hu", e->vid);
+ fprintf(f, "\n");
+}
+
+static void br_print_mdb_entry(FILE *f, int ifindex, struct rtattr *attr,
+ struct nlmsghdr *n)
+{
+ struct rtattr *i;
+ int rem;
+ struct br_mdb_entry *e;
+
+ rem = RTA_PAYLOAD(attr);
+ for (i = RTA_DATA(attr); RTA_OK(i, rem); i = RTA_NEXT(i, rem)) {
+ e = RTA_DATA(i);
+ print_mdb_entry(f, ifindex, e, n);
+ }
+}
+
+int print_mdb(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = arg;
+ struct br_port_msg *r = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr *tb[MDBA_MAX+1], *i;
+
+ if (n->nlmsg_type != RTM_GETMDB && n->nlmsg_type != RTM_NEWMDB && n->nlmsg_type != RTM_DELMDB) {
+ fprintf(stderr, "Not RTM_GETMDB, RTM_NEWMDB or RTM_DELMDB: %08x %08x %08x\n",
+ n->nlmsg_len, n->nlmsg_type, n->nlmsg_flags);
+
+ return 0;
+ }
+
+ len -= NLMSG_LENGTH(sizeof(*r));
+ if (len < 0) {
+ fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+ return -1;
+ }
+
+ if (filter_index && filter_index != r->ifindex)
+ return 0;
+
+ parse_rtattr(tb, MDBA_MAX, MDBA_RTA(r), n->nlmsg_len - NLMSG_LENGTH(sizeof(*r)));
+
+ if (tb[MDBA_MDB]) {
+ int rem = RTA_PAYLOAD(tb[MDBA_MDB]);
+
+ for (i = RTA_DATA(tb[MDBA_MDB]); RTA_OK(i, rem); i = RTA_NEXT(i, rem))
+ br_print_mdb_entry(fp, r->ifindex, i, n);
+ }
+
+ if (tb[MDBA_ROUTER]) {
+ if (n->nlmsg_type == RTM_GETMDB) {
+ if (show_details) {
+ fprintf(fp, "router ports on %s: ",
+ ll_index_to_name(r->ifindex));
+ br_print_router_ports(fp, tb[MDBA_ROUTER]);
+ }
+ } else {
+ uint32_t *port_ifindex;
+
+ i = RTA_DATA(tb[MDBA_ROUTER]);
+ port_ifindex = RTA_DATA(i);
+ if (n->nlmsg_type == RTM_DELMDB)
+ fprintf(fp, "Deleted ");
+ fprintf(fp, "router port dev %s master %s\n",
+ ll_index_to_name(*port_ifindex),
+ ll_index_to_name(r->ifindex));
+ }
+ }
+
+ fflush(fp);
+
+ return 0;
+}
+
+static int mdb_show(int argc, char **argv)
+{
+ char *filter_dev = NULL;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ if (filter_dev)
+ duparg("dev", *argv);
+ filter_dev = *argv;
+ }
+ argc--; argv++;
+ }
+
+ if (filter_dev) {
+ filter_index = if_nametoindex(filter_dev);
+ if (filter_index == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n",
+ filter_dev);
+ return -1;
+ }
+ }
+
+ if (rtnl_wilddump_request(&rth, PF_BRIDGE, RTM_GETMDB) < 0) {
+ perror("Cannot send dump request");
+ return -1;
+ }
+
+ if (rtnl_dump_filter(&rth, print_mdb, stdout) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ return -1;
+ }
+
+ return 0;
+}
+
+static int mdb_modify(int cmd, int flags, int argc, char **argv)
+{
+ struct {
+ struct nlmsghdr n;
+ struct br_port_msg bpm;
+ char buf[1024];
+ } req;
+ struct br_mdb_entry entry;
+ char *d = NULL, *p = NULL, *grp = NULL;
+ short vid = 0;
+
+ memset(&req, 0, sizeof(req));
+ memset(&entry, 0, sizeof(entry));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct br_port_msg));
+ req.n.nlmsg_flags = NLM_F_REQUEST|flags;
+ req.n.nlmsg_type = cmd;
+ req.bpm.family = PF_BRIDGE;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ d = *argv;
+ } else if (strcmp(*argv, "grp") == 0) {
+ NEXT_ARG();
+ grp = *argv;
+ } else if (strcmp(*argv, "port") == 0) {
+ NEXT_ARG();
+ p = *argv;
+ } else if (strcmp(*argv, "permanent") == 0) {
+ if (cmd == RTM_NEWMDB)
+ entry.state |= MDB_PERMANENT;
+ } else if (strcmp(*argv, "temp") == 0) {
+ ;/* nothing */
+ } else if (strcmp(*argv, "vid") == 0) {
+ NEXT_ARG();
+ vid = atoi(*argv);
+ } else {
+ if (matches(*argv, "help") == 0)
+ usage();
+ }
+ argc--; argv++;
+ }
+
+ if (d == NULL || grp == NULL || p == NULL) {
+ fprintf(stderr, "Device, group address and port name are required arguments.\n");
+ return -1;
+ }
+
+ req.bpm.ifindex = ll_name_to_index(d);
+ if (req.bpm.ifindex == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", d);
+ return -1;
+ }
+
+ entry.ifindex = ll_name_to_index(p);
+ if (entry.ifindex == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", p);
+ return -1;
+ }
+
+ if (!inet_pton(AF_INET, grp, &entry.addr.u.ip4)) {
+ if (!inet_pton(AF_INET6, grp, &entry.addr.u.ip6)) {
+ fprintf(stderr, "Invalid address \"%s\"\n", grp);
+ return -1;
+ } else
+ entry.addr.proto = htons(ETH_P_IPV6);
+ } else
+ entry.addr.proto = htons(ETH_P_IP);
+
+ entry.vid = vid;
+ addattr_l(&req.n, sizeof(req), MDBA_SET_ENTRY, &entry, sizeof(entry));
+
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ return -1;
+
+ return 0;
+}
+
+int do_mdb(int argc, char **argv)
+{
+ ll_init_map(&rth);
+
+ if (argc > 0) {
+ if (matches(*argv, "add") == 0)
+ return mdb_modify(RTM_NEWMDB, NLM_F_CREATE|NLM_F_EXCL, argc-1, argv+1);
+ if (matches(*argv, "delete") == 0)
+ return mdb_modify(RTM_DELMDB, 0, argc-1, argv+1);
+
+ if (matches(*argv, "show") == 0 ||
+ matches(*argv, "lst") == 0 ||
+ matches(*argv, "list") == 0)
+ return mdb_show(argc-1, argv+1);
+ if (matches(*argv, "help") == 0)
+ usage();
+ } else
+ return mdb_show(0, NULL);
+
+ fprintf(stderr, "Command \"%s\" is unknown, try \"bridge mdb help\".\n", *argv);
+ exit(-1);
+}
diff --git a/iproute2/bridge/monitor.c b/iproute2/bridge/monitor.c
new file mode 100644
index 0000000..d8341ec
--- /dev/null
+++ b/iproute2/bridge/monitor.c
@@ -0,0 +1,144 @@
+/*
+ * brmonitor.c "bridge monitor"
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Stephen Hemminger <shemminger@vyatta.com>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <time.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <net/if.h>
+#include <netinet/in.h>
+#include <linux/if_bridge.h>
+#include <linux/neighbour.h>
+#include <string.h>
+
+#include "utils.h"
+#include "br_common.h"
+
+
+static void usage(void) __attribute__((noreturn));
+int prefix_banner;
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: bridge monitor [file | link | fdb | mdb | all]\n");
+ exit(-1);
+}
+
+static int accept_msg(const struct sockaddr_nl *who,
+ struct rtnl_ctrl_data *ctrl,
+ struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = arg;
+
+ if (timestamp)
+ print_timestamp(fp);
+
+ switch (n->nlmsg_type) {
+ case RTM_NEWLINK:
+ case RTM_DELLINK:
+ if (prefix_banner)
+ fprintf(fp, "[LINK]");
+
+ return print_linkinfo(who, n, arg);
+
+ case RTM_NEWNEIGH:
+ case RTM_DELNEIGH:
+ if (prefix_banner)
+ fprintf(fp, "[NEIGH]");
+ return print_fdb(who, n, arg);
+
+ case RTM_NEWMDB:
+ case RTM_DELMDB:
+ if (prefix_banner)
+ fprintf(fp, "[MDB]");
+ return print_mdb(who, n, arg);
+
+ case NLMSG_TSTAMP:
+ print_nlmsg_timestamp(fp, n);
+ return 0;
+
+ default:
+ return 0;
+ }
+}
+
+int do_monitor(int argc, char **argv)
+{
+ char *file = NULL;
+ unsigned groups = ~RTMGRP_TC;
+ int llink=0;
+ int lneigh=0;
+ int lmdb=0;
+
+ rtnl_close(&rth);
+
+ while (argc > 0) {
+ if (matches(*argv, "file") == 0) {
+ NEXT_ARG();
+ file = *argv;
+ } else if (matches(*argv, "link") == 0) {
+ llink=1;
+ groups = 0;
+ } else if (matches(*argv, "fdb") == 0) {
+ lneigh = 1;
+ groups = 0;
+ } else if (matches(*argv, "mdb") == 0) {
+ lmdb = 1;
+ groups = 0;
+ } else if (strcmp(*argv, "all") == 0) {
+ groups = ~RTMGRP_TC;
+ prefix_banner=1;
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ } else {
+ fprintf(stderr, "Argument \"%s\" is unknown, try \"bridge monitor help\".\n", *argv);
+ exit(-1);
+ }
+ argc--; argv++;
+ }
+
+ if (llink)
+ groups |= nl_mgrp(RTNLGRP_LINK);
+
+ if (lneigh) {
+ groups |= nl_mgrp(RTNLGRP_NEIGH);
+ }
+
+ if (lmdb) {
+ groups |= nl_mgrp(RTNLGRP_MDB);
+ }
+
+ if (file) {
+ FILE *fp;
+ int err;
+ fp = fopen(file, "r");
+ if (fp == NULL) {
+ perror("Cannot fopen");
+ exit(-1);
+ }
+ err = rtnl_from_file(fp, accept_msg, stdout);
+ fclose(fp);
+ return err;
+ }
+
+ if (rtnl_open(&rth, groups) < 0)
+ exit(1);
+ ll_init_map(&rth);
+
+ if (rtnl_listen(&rth, accept_msg, stdout) < 0)
+ exit(2);
+
+ return 0;
+}
+
diff --git a/iproute2/bridge/vlan.c b/iproute2/bridge/vlan.c
new file mode 100644
index 0000000..ac2f523
--- /dev/null
+++ b/iproute2/bridge/vlan.c
@@ -0,0 +1,263 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <net/if.h>
+#include <netinet/in.h>
+#include <linux/if_bridge.h>
+#include <linux/if_ether.h>
+#include <string.h>
+
+#include "libnetlink.h"
+#include "br_common.h"
+#include "utils.h"
+
+static unsigned int filter_index;
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: bridge vlan { add | del } vid VLAN_ID dev DEV [ pvid] [ untagged ]\n");
+ fprintf(stderr, " [ self ] [ master ]\n");
+ fprintf(stderr, " bridge vlan { show } [ dev DEV ]\n");
+ exit(-1);
+}
+
+static int vlan_modify(int cmd, int argc, char **argv)
+{
+ struct {
+ struct nlmsghdr n;
+ struct ifinfomsg ifm;
+ char buf[1024];
+ } req;
+ char *d = NULL;
+ short vid = -1;
+ short vid_end = -1;
+ struct rtattr *afspec;
+ struct bridge_vlan_info vinfo;
+ unsigned short flags = 0;
+
+ memset(&vinfo, 0, sizeof(vinfo));
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = cmd;
+ req.ifm.ifi_family = PF_BRIDGE;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ d = *argv;
+ } else if (strcmp(*argv, "vid") == 0) {
+ char *p;
+ NEXT_ARG();
+ p = strchr(*argv, '-');
+ if (p) {
+ *p = '\0';
+ p++;
+ vid = atoi(*argv);
+ vid_end = atoi(p);
+ vinfo.flags |= BRIDGE_VLAN_INFO_RANGE_BEGIN;
+ } else {
+ vid = atoi(*argv);
+ }
+ } else if (strcmp(*argv, "self") == 0) {
+ flags |= BRIDGE_FLAGS_SELF;
+ } else if (strcmp(*argv, "master") == 0) {
+ flags |= BRIDGE_FLAGS_MASTER;
+ } else if (strcmp(*argv, "pvid") == 0) {
+ vinfo.flags |= BRIDGE_VLAN_INFO_PVID;
+ } else if (strcmp(*argv, "untagged") == 0) {
+ vinfo.flags |= BRIDGE_VLAN_INFO_UNTAGGED;
+ } else {
+ if (matches(*argv, "help") == 0) {
+ NEXT_ARG();
+ }
+ }
+ argc--; argv++;
+ }
+
+ if (d == NULL || vid == -1) {
+ fprintf(stderr, "Device and VLAN ID are required arguments.\n");
+ return -1;
+ }
+
+ req.ifm.ifi_index = ll_name_to_index(d);
+ if (req.ifm.ifi_index == 0) {
+ fprintf(stderr, "Cannot find bridge device \"%s\"\n", d);
+ return -1;
+ }
+
+ if (vid >= 4096) {
+ fprintf(stderr, "Invalid VLAN ID \"%hu\"\n", vid);
+ return -1;
+ }
+
+ if (vinfo.flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) {
+ if (vid_end == -1 || vid_end >= 4096 || vid >= vid_end) {
+ fprintf(stderr, "Invalid VLAN range \"%hu-%hu\"\n",
+ vid, vid_end);
+ return -1;
+ }
+ if (vinfo.flags & BRIDGE_VLAN_INFO_PVID) {
+ fprintf(stderr,
+ "pvid cannot be configured for a vlan range\n");
+ return -1;
+ }
+ }
+
+ afspec = addattr_nest(&req.n, sizeof(req), IFLA_AF_SPEC);
+
+ if (flags)
+ addattr16(&req.n, sizeof(req), IFLA_BRIDGE_FLAGS, flags);
+
+ vinfo.vid = vid;
+ if (vid_end != -1) {
+ /* send vlan range start */
+ addattr_l(&req.n, sizeof(req), IFLA_BRIDGE_VLAN_INFO, &vinfo,
+ sizeof(vinfo));
+ vinfo.flags &= ~BRIDGE_VLAN_INFO_RANGE_BEGIN;
+
+ /* Now send the vlan range end */
+ vinfo.flags |= BRIDGE_VLAN_INFO_RANGE_END;
+ vinfo.vid = vid_end;
+ addattr_l(&req.n, sizeof(req), IFLA_BRIDGE_VLAN_INFO, &vinfo,
+ sizeof(vinfo));
+ } else {
+ addattr_l(&req.n, sizeof(req), IFLA_BRIDGE_VLAN_INFO, &vinfo,
+ sizeof(vinfo));
+ }
+
+ addattr_nest_end(&req.n, afspec);
+
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ return -1;
+
+ return 0;
+}
+
+static int print_vlan(const struct sockaddr_nl *who,
+ struct nlmsghdr *n,
+ void *arg)
+{
+ FILE *fp = arg;
+ struct ifinfomsg *ifm = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr * tb[IFLA_MAX+1];
+
+ if (n->nlmsg_type != RTM_NEWLINK) {
+ fprintf(stderr, "Not RTM_NEWLINK: %08x %08x %08x\n",
+ n->nlmsg_len, n->nlmsg_type, n->nlmsg_flags);
+ return 0;
+ }
+
+ len -= NLMSG_LENGTH(sizeof(*ifm));
+ if (len < 0) {
+ fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+ return -1;
+ }
+
+ if (ifm->ifi_family != AF_BRIDGE)
+ return 0;
+
+ if (filter_index && filter_index != ifm->ifi_index)
+ return 0;
+
+ parse_rtattr(tb, IFLA_MAX, IFLA_RTA(ifm), len);
+
+ /* if AF_SPEC isn't there, vlan table is not preset for this port */
+ if (!tb[IFLA_AF_SPEC]) {
+ fprintf(fp, "%s\tNone\n", ll_index_to_name(ifm->ifi_index));
+ return 0;
+ } else {
+ struct rtattr *i, *list = tb[IFLA_AF_SPEC];
+ int rem = RTA_PAYLOAD(list);
+
+ fprintf(fp, "%s", ll_index_to_name(ifm->ifi_index));
+ for (i = RTA_DATA(list); RTA_OK(i, rem); i = RTA_NEXT(i, rem)) {
+ struct bridge_vlan_info *vinfo;
+
+ if (i->rta_type != IFLA_BRIDGE_VLAN_INFO)
+ continue;
+
+ vinfo = RTA_DATA(i);
+ if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_END)
+ fprintf(fp, "-%hu", vinfo->vid);
+ else
+ fprintf(fp, "\t %hu", vinfo->vid);
+ if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN)
+ continue;
+ if (vinfo->flags & BRIDGE_VLAN_INFO_PVID)
+ fprintf(fp, " PVID");
+ if (vinfo->flags & BRIDGE_VLAN_INFO_UNTAGGED)
+ fprintf(fp, " Egress Untagged");
+ fprintf(fp, "\n");
+ }
+ }
+ fprintf(fp, "\n");
+ fflush(fp);
+ return 0;
+}
+
+static int vlan_show(int argc, char **argv)
+{
+ char *filter_dev = NULL;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ if (filter_dev)
+ duparg("dev", *argv);
+ filter_dev = *argv;
+ }
+ argc--; argv++;
+ }
+
+ if (filter_dev) {
+ if ((filter_index = if_nametoindex(filter_dev)) == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n",
+ filter_dev);
+ return -1;
+ }
+ }
+
+ if (rtnl_wilddump_req_filter(&rth, PF_BRIDGE, RTM_GETLINK,
+ (compress_vlans ?
+ RTEXT_FILTER_BRVLAN_COMPRESSED :
+ RTEXT_FILTER_BRVLAN)) < 0) {
+ perror("Cannont send dump request");
+ exit(1);
+ }
+
+ printf("port\tvlan ids\n");
+ if (rtnl_dump_filter(&rth, print_vlan, stdout) < 0) {
+ fprintf(stderr, "Dump ternminated\n");
+ exit(1);
+ }
+
+ return 0;
+}
+
+
+int do_vlan(int argc, char **argv)
+{
+ ll_init_map(&rth);
+
+ if (argc > 0) {
+ if (matches(*argv, "add") == 0)
+ return vlan_modify(RTM_SETLINK, argc-1, argv+1);
+ if (matches(*argv, "delete") == 0)
+ return vlan_modify(RTM_DELLINK, argc-1, argv+1);
+ if (matches(*argv, "show") == 0 ||
+ matches(*argv, "lst") == 0 ||
+ matches(*argv, "list") == 0)
+ return vlan_show(argc-1, argv+1);
+ if (matches(*argv, "help") == 0)
+ usage();
+ } else
+ return vlan_show(0, NULL);
+
+ fprintf(stderr, "Command \"%s\" is unknown, try \"bridge fdb help\".\n", *argv);
+ exit(-1);
+}
diff --git a/iproute2/configure b/iproute2/configure
new file mode 100755
index 0000000..d2540b0
--- /dev/null
+++ b/iproute2/configure
@@ -0,0 +1,359 @@
+#! /bin/bash
+# This is not an autoconf generated configure
+#
+INCLUDE=${1:-"$PWD/include"}
+
+# Make a temp directory in build tree.
+TMPDIR=$(mktemp -d config.XXXXXX)
+trap 'status=$?; rm -rf $TMPDIR; exit $status' EXIT HUP INT QUIT TERM
+
+check_prog()
+{
+ echo -n "$2"
+ command -v $1 >/dev/null 2>&1 && (echo "$3:=y" >> Config; echo "yes") || (echo "no"; return 1)
+}
+
+check_docs()
+{
+ if check_prog latex " latex: " HAVE_LATEX; then
+ check_prog pdflatex " pdflatex: " HAVE_PDFLATEX || echo " WARNING: no PDF docs can be built from LaTeX files"
+ check_prog sgml2latex " sgml2latex: " HAVE_SGML2LATEX || echo " WARNING: no LaTeX files can be build from SGML files"
+ else
+ echo " WARNING: no docs can be built from LaTeX files"
+ fi
+
+ check_prog sgml2html " sgml2html: " HAVE_SGML2HTML || echo " WARNING: no HTML docs can be built from SGML"
+}
+
+check_toolchain()
+{
+ : ${PKG_CONFIG:=pkg-config}
+ : ${AR=ar}
+ : ${CC=gcc}
+ echo "PKG_CONFIG:=${PKG_CONFIG}" >>Config
+ echo "AR:=${AR}" >>Config
+ echo "CC:=${CC}" >>Config
+}
+
+check_atm()
+{
+ cat >$TMPDIR/atmtest.c <<EOF
+#include <atm.h>
+int main(int argc, char **argv) {
+ struct atm_qos qos;
+ (void) text2qos("aal5,ubr:sdu=9180,rx:none",&qos,0);
+ return 0;
+}
+EOF
+
+ $CC -I$INCLUDE -o $TMPDIR/atmtest $TMPDIR/atmtest.c -latm >/dev/null 2>&1
+ if [ $? -eq 0 ]
+ then
+ echo "TC_CONFIG_ATM:=y" >>Config
+ echo yes
+ else
+ echo no
+ fi
+ rm -f $TMPDIR/atmtest.c $TMPDIR/atmtest
+}
+
+check_xt()
+{
+ #check if we have xtables from iptables >= 1.4.5.
+ cat >$TMPDIR/ipttest.c <<EOF
+#include <xtables.h>
+#include <linux/netfilter.h>
+static struct xtables_globals test_globals = {
+ .option_offset = 0,
+ .program_name = "tc-ipt",
+ .program_version = XTABLES_VERSION,
+ .orig_opts = NULL,
+ .opts = NULL,
+ .exit_err = NULL,
+};
+
+int main(int argc, char **argv)
+{
+ xtables_init_all(&test_globals, NFPROTO_IPV4);
+ return 0;
+}
+EOF
+
+ if $CC -I$INCLUDE $IPTC -o $TMPDIR/ipttest $TMPDIR/ipttest.c $IPTL \
+ $(${PKG_CONFIG} xtables --cflags --libs) -ldl >/dev/null 2>&1
+ then
+ echo "TC_CONFIG_XT:=y" >>Config
+ echo "using xtables"
+ fi
+ rm -f $TMPDIR/ipttest.c $TMPDIR/ipttest
+}
+
+check_xt_old()
+{
+ # bail if previous XT checks has already succeded.
+ if grep -q TC_CONFIG_XT Config
+ then
+ return
+ fi
+
+ #check if we dont need our internal header ..
+ cat >$TMPDIR/ipttest.c <<EOF
+#include <xtables.h>
+char *lib_dir;
+unsigned int global_option_offset = 0;
+const char *program_version = XTABLES_VERSION;
+const char *program_name = "tc-ipt";
+struct afinfo afinfo = {
+ .libprefix = "libxt_",
+};
+
+void exit_error(enum exittype status, const char *msg, ...)
+{
+}
+
+int main(int argc, char **argv) {
+
+ return 0;
+}
+
+EOF
+
+ $CC -I$INCLUDE $IPTC -o $TMPDIR/ipttest $TMPDIR/ipttest.c $IPTL -ldl >/dev/null 2>&1
+ if [ $? -eq 0 ]
+ then
+ echo "TC_CONFIG_XT_OLD:=y" >>Config
+ echo "using old xtables (no need for xt-internal.h)"
+ fi
+ rm -f $TMPDIR/ipttest.c $TMPDIR/ipttest
+}
+
+check_xt_old_internal_h()
+{
+ # bail if previous XT checks has already succeded.
+ if grep -q TC_CONFIG_XT Config
+ then
+ return
+ fi
+
+ #check if we need our own internal.h
+ cat >$TMPDIR/ipttest.c <<EOF
+#include <xtables.h>
+#include "xt-internal.h"
+char *lib_dir;
+unsigned int global_option_offset = 0;
+const char *program_version = XTABLES_VERSION;
+const char *program_name = "tc-ipt";
+struct afinfo afinfo = {
+ .libprefix = "libxt_",
+};
+
+void exit_error(enum exittype status, const char *msg, ...)
+{
+}
+
+int main(int argc, char **argv) {
+
+ return 0;
+}
+
+EOF
+ $CC -I$INCLUDE $IPTC -o $TMPDIR/ipttest $TMPDIR/ipttest.c $IPTL -ldl >/dev/null 2>&1
+
+ if [ $? -eq 0 ]
+ then
+ echo "using old xtables with xt-internal.h"
+ echo "TC_CONFIG_XT_OLD_H:=y" >>Config
+ fi
+ rm -f $TMPDIR/ipttest.c $TMPDIR/ipttest
+}
+
+check_ipt()
+{
+ if ! grep TC_CONFIG_XT Config > /dev/null
+ then
+ echo "using iptables"
+ fi
+}
+
+check_ipt_lib_dir()
+{
+ IPT_LIB_DIR=$(${PKG_CONFIG} --variable=xtlibdir xtables)
+ if [ -n "$IPT_LIB_DIR" ]; then
+ echo $IPT_LIB_DIR
+ echo "IPT_LIB_DIR:=$IPT_LIB_DIR" >> Config
+ return
+ fi
+
+ for dir in /lib /usr/lib /usr/local/lib
+ do
+ for file in $dir/{xtables,iptables}/lib*t_*so ; do
+ if [ -f $file ]; then
+ echo ${file%/*}
+ echo "IPT_LIB_DIR:=${file%/*}" >> Config
+ return
+ fi
+ done
+ done
+ echo "not found!"
+}
+
+check_setns()
+{
+ cat >$TMPDIR/setnstest.c <<EOF
+#include <sched.h>
+int main(int argc, char **argv)
+{
+ (void)setns(0,0);
+ return 0;
+}
+EOF
+ $CC -I$INCLUDE -o $TMPDIR/setnstest $TMPDIR/setnstest.c >/dev/null 2>&1
+ if [ $? -eq 0 ]
+ then
+ echo "IP_CONFIG_SETNS:=y" >>Config
+ echo "yes"
+ else
+ echo "no"
+ fi
+ rm -f $TMPDIR/setnstest.c $TMPDIR/setnstest
+}
+
+check_ipset()
+{
+ cat >$TMPDIR/ipsettest.c <<EOF
+#include <linux/netfilter/ipset/ip_set.h>
+#ifndef IP_SET_INVALID
+#define IPSET_DIM_MAX 3
+typedef unsigned short ip_set_id_t;
+#endif
+#include <linux/netfilter/xt_set.h>
+
+struct xt_set_info info;
+#if IPSET_PROTOCOL == 6
+int main(void)
+{
+ return IPSET_MAXNAMELEN;
+}
+#else
+#error unknown ipset version
+#endif
+EOF
+
+ if $CC -I$INCLUDE -o $TMPDIR/ipsettest $TMPDIR/ipsettest.c >/dev/null 2>&1
+ then
+ echo "TC_CONFIG_IPSET:=y" >>Config
+ echo "yes"
+ else
+ echo "no"
+ fi
+ rm -f $TMPDIR/ipsettest.c $TMPDIR/ipsettest
+}
+
+check_elf()
+{
+ cat >$TMPDIR/elftest.c <<EOF
+#include <libelf.h>
+#include <gelf.h>
+int main(void)
+{
+ Elf_Scn *scn;
+ GElf_Shdr shdr;
+ return elf_version(EV_CURRENT);
+}
+EOF
+
+ if $CC -I$INCLUDE -o $TMPDIR/elftest $TMPDIR/elftest.c -lelf >/dev/null 2>&1
+ then
+ echo "TC_CONFIG_ELF:=y" >>Config
+ echo "yes"
+ else
+ echo "no"
+ fi
+ rm -f $TMPDIR/elftest.c $TMPDIR/elftest
+}
+
+check_selinux()
+# SELinux is a compile time option in the ss utility
+{
+ if ${PKG_CONFIG} libselinux --exists
+ then
+ echo "HAVE_SELINUX:=y" >>Config
+ echo "yes"
+ else
+ echo "no"
+ fi
+}
+
+check_mnl()
+{
+ if ${PKG_CONFIG} libmnl --exists
+ then
+ echo "HAVE_MNL:=y" >>Config
+ echo "yes"
+ else
+ echo "no"
+ fi
+}
+
+check_berkeley_db()
+{
+ cat >$TMPDIR/dbtest.c <<EOF
+#include <fcntl.h>
+#include <stdlib.h>
+#include <db_185.h>
+int main(int argc, char **argv) {
+ dbopen("/tmp/xxx_test_db.db", O_CREAT|O_RDWR, 0644, DB_HASH, NULL);
+ return 0;
+}
+EOF
+ $CC -I$INCLUDE -o $TMPDIR/dbtest $TMPDIR/dbtest.c -ldb >/dev/null 2>&1
+ if [ $? -eq 0 ]
+ then
+ echo "HAVE_BERKELEY_DB:=y" >>Config
+ echo "yes"
+ else
+ echo "no"
+ fi
+ rm -f $TMPDIR/dbtest.c $TMPDIR/dbtest
+}
+
+echo "# Generated config based on" $INCLUDE >Config
+check_toolchain
+
+echo "TC schedulers"
+
+echo -n " ATM "
+check_atm
+
+echo -n " IPT "
+check_xt
+check_xt_old
+check_xt_old_internal_h
+check_ipt
+
+echo -n " IPSET "
+check_ipset
+
+echo
+echo -n "iptables modules directory: "
+check_ipt_lib_dir
+
+echo -n "libc has setns: "
+check_setns
+
+echo -n "SELinux support: "
+check_selinux
+
+echo -n "ELF support: "
+check_elf
+
+echo -n "libmnl support: "
+check_mnl
+
+echo -n "Berkeley DB: "
+check_berkeley_db
+
+echo
+echo -n "docs:"
+check_docs
+echo
diff --git a/iproute2/doc/Makefile b/iproute2/doc/Makefile
new file mode 100644
index 0000000..e9c0ff7
--- /dev/null
+++ b/iproute2/doc/Makefile
@@ -0,0 +1,73 @@
+PSFILES=ip-cref.ps ip-tunnels.ps api-ip6-flowlabels.ps ss.ps nstat.ps arpd.ps rtstat.ps
+# tc-cref.ps
+# api-rtnl.tex api-pmtudisc.tex api-news.tex
+# iki-netdev.ps iki-neighdst.ps
+
+
+LATEX=latex
+DVIPS=dvips
+SGML2DVI=sgml2latex
+SGML2HTML=sgml2html -s 0
+LPR=lpr -Zsduplex
+SHELL=bash
+PAGESIZE=a4
+PAGESPERPAGE=2
+
+HTMLFILES=$(subst .sgml,.html,$(shell echo *.sgml))
+DVIFILES=$(subst .ps,.dvi,$(PSFILES))
+PDFFILES=$(subst .ps,.pdf,$(PSFILES))
+
+
+all: pstwocol
+
+pstwocol: $(PSFILES)
+
+html: $(HTMLFILES)
+
+dvi: $(DVIFILES)
+
+pdf: $(PDFFILES)
+
+print: $(PSFILES)
+ $(LPR) $(PSFILES)
+
+%.tex: %.sgml
+ $(SGML2DVI) --output=tex $<
+
+%.dvi: %.sgml
+ $(SGML2DVI) --output=dvi $<
+
+%.dvi: %.tex
+ @set -e; pass=2; echo "Running LaTeX $<"; \
+ while [ `$(LATEX) $< </dev/null 2>&1 | \
+ grep -c '^\(LaTeX Warning: Label(s) may\|No file \|! Emergency stop\)'` -ge 1 ]; do \
+ if [ $$pass -gt 3 ]; then \
+ echo "Seems, something is wrong. Try by hands." ; exit 1 ; \
+ fi; \
+ echo "Re-running LaTeX $<, $${pass}d pass"; pass=$$[$$pass + 1]; \
+ done
+
+%.pdf: %.tex
+ @set -e; pass=2; echo "Running pdfLaTeX $<"; \
+ while [ `pdflatex $< </dev/null 2>&1 | \
+ grep -c '^\(LaTeX Warning: Label(s) may\|No file \|! Emergency stop\)'` -ge 1 ]; do \
+ if [ $$pass -gt 3 ]; then \
+ echo "Seems, something is wrong. Try by hands." ; exit 1 ; \
+ fi; \
+ echo "Re-running pdfLaTeX $<, $${pass}d pass"; pass=$$[$$pass + 1]; \
+ done
+#%.pdf: %.ps
+# ps2pdf $<
+
+%.ps: %.dvi
+ $(DVIPS) $< -o $@
+
+%.html: %.sgml
+ $(SGML2HTML) $<
+
+install:
+ install -m 0644 $(shell echo *.tex) $(DESTDIR)$(DOCDIR)
+ install -m 0644 $(shell echo *.sgml) $(DESTDIR)$(DOCDIR)
+
+clean:
+ rm -f *.aux *.log *.toc $(PSFILES) $(DVIFILES) *.html *.pdf
diff --git a/iproute2/doc/Plan b/iproute2/doc/Plan
new file mode 100644
index 0000000..55f478e
--- /dev/null
+++ b/iproute2/doc/Plan
@@ -0,0 +1,16 @@
+Partially finished work.
+
+1. User Reference manuals.
+1.1 IP Command reference (ip-cref.tex, published)
+1.2 TC Command reference (tc-cref.tex)
+1.3 IP tunnels (ip-tunnels.tex, published)
+
+2. Linux-2.2 Networking API
+2.1 RTNETLINK (api-rtnl.tex)
+2.2 Path MTU Discovery (api-pmtudisc.tex)
+2.3 IPv6 Flow Labels (api-ip6-flowlabels.tex, published)
+2.4 Miscellaneous extensions (api-misc.tex)
+
+3. Linux-2.2 Networking Intra-Kernel Interfaces
+3.1 NetDev --- Networking Devices and netdev... (iki-netdev.tex)
+3.2 Neighbour cache and destination cache. (iki-neighdst.tex)
diff --git a/iproute2/doc/SNAPSHOT.tex b/iproute2/doc/SNAPSHOT.tex
new file mode 100644
index 0000000..7ed0298
--- /dev/null
+++ b/iproute2/doc/SNAPSHOT.tex
@@ -0,0 +1 @@
+\def\Draft{020116}
diff --git a/iproute2/doc/actions/actions-general b/iproute2/doc/actions/actions-general
new file mode 100644
index 0000000..70f7cd6
--- /dev/null
+++ b/iproute2/doc/actions/actions-general
@@ -0,0 +1,257 @@
+
+This documented is slightly dated but should give you idea of how things
+work.
+
+What is it?
+-----------
+
+An extension to the filtering/classification architecture of Linux Traffic
+Control.
+Up to 2.6.8 the only action that could be "attached" to a filter was policing.
+i.e you could say something like:
+
+-----
+tc filter add dev lo parent ffff: protocol ip prio 10 u32 match ip src \
+127.0.0.1/32 flowid 1:1 police mtu 4000 rate 1500kbit burst 90k
+-----
+
+which implies "if a packet is seen on the ingress of the lo device with
+a source IP address of 127.0.0.1/32 we give it a classification id of 1:1 and
+we execute a policing action which rate limits its bandwidth utilization
+to 1.5Mbps".
+
+The new extensions allow for more than just policing actions to be added.
+They are also fully backward compatible. If you have a kernel that doesnt
+understand them, then the effect is null i.e if you have a newer tc
+but older kernel, the actions are not installed. Likewise if you
+have a newer kernel but older tc, obviously the tc will use current
+syntax which will work fine. Of course to get the required effect you need
+both newer tc and kernel. If you are reading this you have the
+right tc ;->
+
+A side effect is that we can now get stateless firewalling to work with tc.
+Essentially this is now an alternative to iptables.
+I wont go into details of my dislike for iptables at times, but
+scalability is one of the main issues; however, if you need stateful
+classification - use netfilter (for now).
+
+This stuff works on both ingress and egress qdiscs.
+
+Features
+--------
+
+1) new additional syntax and actions enabled. Note old syntax is still valid.
+
+Essentially this is still the same syntax as tc with a new construct
+"action". The syntax is of the form:
+tc filter add <DEVICE> parent 1:0 protocol ip prio 10 <Filter description>
+flowid 1:1 action <ACTION description>*
+
+You can have as many actions as you want (within sensible reasoning).
+
+In the past the only real action was the policer; i.e you could do something
+along the lines of:
+tc filter add dev lo parent ffff: protocol ip prio 10 u32 \
+match ip src 127.0.0.1/32 flowid 1:1 \
+police mtu 4000 rate 1500kbit burst 90k
+
+Although you can still use the same syntax, now you can say:
+
+tc filter add dev lo parent 1:0 protocol ip prio 10 u32 \
+match ip src 127.0.0.1/32 flowid 1:1 \
+action police mtu 4000 rate 1500kbit burst 90k
+
+" generic Actions" (gact) at the moment are:
+{ drop, pass, reclassify, continue}
+(If you have others, no listed here give me a reason and we will add them)
++drop says to drop the packet
++pass and ok (are equivalent) says to accept it
++reclassify requests for reclassification of the packet
++continue requests for next lookup to match
+
+2)In order to take advantage of some of the targets written by the
+iptables people, a classifier can have a packet being massaged by an
+iptable target. I have only tested with mangler targets up to now.
+(infact anything that is not in the mangling table is disabled right now)
+
+In terms of hooks:
+*ingress is mapped to pre-routing hook
+*egress is mapped to post-routing hook
+I dont see much value in the other hooks, if you see it and email me good
+reasons, the addition is trivial.
+
+Example syntax for iptables targets usage becomes:
+tc filter add ..... u32 <u32 syntax> action ipt -j <iptables target syntax>
+
+example:
+tc filter add dev lo parent ffff: protocol ip prio 8 u32 \
+match ip dst 127.0.0.8/32 flowid 1:12 \
+action ipt -j mark --set-mark 2
+
+NOTE: flowid 1:12 is parsed flowid 0x1:0x12. Make sure if you want flowid
+decimal 12, then use flowid 1:c.
+
+3) A feature i call pipe
+The motivation is derived from Unix pipe mechanism but applied to packets.
+Essentially take a matching packet and pass it through
+action1 | action2 | action3 etc.
+You could do something similar to this with the tc policer and the "continue"
+operator but this rather restricts it to just the policer and requires
+multiple rules (and lookups, hence quiet inefficient);
+
+as an example -- and please note that this is just an example _not_ The
+Word Youve Been Waiting For (yes i have had problems giving examples
+which ended becoming dogma in documents and people modifying them a little
+to look clever);
+
+i selected the metering rates to be small so that i can show better how
+things work.
+
+The script below does the following:
+- an incoming packet from 10.0.0.21 is first given a firewall mark of 1.
+
+- It is then metered to make sure it does not exceed its allocated rate of
+1Kbps. If it doesnt exceed rate, this is where we terminate action execution.
+
+- If it does exceed its rate, its "color" changes to a mark of 2 and it is
+then passed through a second meter.
+
+-The second meter is shared across all flows on that device [i am suprised
+that this seems to be not a well know feature of the policer; Bert was telling
+me that someone was writing a qdisc just to do sharing across multiple devices;
+it must be the summer heat again; weve had someone doing that every year around
+summer -- the key to sharing is to use a operator "index" in your policer
+rules (example "index 20"). All your rules have to use the same index to
+share.]
+
+-If the second meter is exceeded the color of the flow changes further to 3.
+
+-We then pass the packet to another meter which is shared across all devices
+in the system. If this meter is exceeded we drop the packet.
+
+Note the mark can be used further up the system to do things like policy
+or more interesting things on the egress.
+
+------------------ cut here -------------------------------
+#
+# Add an ingress qdisc on eth0
+tc qdisc add dev eth0 ingress
+#
+#if you see an incoming packet from 10.0.0.21
+tc filter add dev eth0 parent ffff: protocol ip prio 1 \
+u32 match ip src 10.0.0.21/32 flowid 1:15 \
+#
+# first give it a mark of 1
+action ipt -j mark --set-mark 1 index 2 \
+#
+# then pass it through a policer which allows 1kbps; if the flow
+# doesnt exceed that rate, this is where we stop, if it exceeds we
+# pipe the packet to the next action
+action police rate 1kbit burst 9k pipe \
+#
+# which marks the packet fwmark as 2 and pipes
+action ipt -j mark --set-mark 2 \
+#
+# next attempt to borrow b/width from a meter
+# used across all flows incoming on eth0("index 30")
+# and if that is exceeded we pipe to the next action
+action police index 30 mtu 5000 rate 1kbit burst 10k pipe \
+# mark it as fwmark 3 if exceeded
+action ipt -j mark --set-mark 3 \
+# and then attempt to borrow from a meter used by all devices in the
+# system. Should this be exceeded, drop the packet on the floor.
+action police index 20 mtu 5000 rate 1kbit burst 90k drop
+---------------------------------
+
+Now lets see the actions installed with
+"tc filter show parent ffff: dev eth0"
+
+-------- output -----------
+jroot# tc filter show parent ffff: dev eth0
+filter protocol ip pref 1 u32
+filter protocol ip pref 1 u32 fh 800: ht divisor 1
+filter protocol ip pref 1 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:15
+
+ action order 1: tablename: mangle hook: NF_IP_PRE_ROUTING
+ target MARK set 0x1 index 2
+
+ action order 2: police 1 action pipe rate 1Kbit burst 9Kb mtu 2Kb
+
+ action order 3: tablename: mangle hook: NF_IP_PRE_ROUTING
+ target MARK set 0x2 index 1
+
+ action order 4: police 30 action pipe rate 1Kbit burst 10Kb mtu 5000b
+
+ action order 5: tablename: mangle hook: NF_IP_PRE_ROUTING
+ target MARK set 0x3 index 3
+
+ action order 6: police 20 action drop rate 1Kbit burst 90Kb mtu 5000b
+
+ match 0a000015/ffffffff at 12
+-------------------------------
+
+Note the ordering of the actions is based on the order in which we entered
+them. In the future i will add explicit priorities.
+
+Now lets run a ping -f from 10.0.0.21 to this host; stop the ping after
+you see a few lines of dots
+
+----
+[root@jzny hadi]# ping -f 10.0.0.22
+PING 10.0.0.22 (10.0.0.22): 56 data bytes
+....................................................................................................................................................................................................................................................................................................................................................................................................................................................
+--- 10.0.0.22 ping statistics ---
+2248 packets transmitted, 1811 packets received, 19% packet loss
+round-trip min/avg/max = 0.7/9.3/20.1 ms
+-----------------------------
+
+Now lets take a look at the stats with "tc -s filter show parent ffff: dev eth0"
+
+--------------
+jroot# tc -s filter show parent ffff: dev eth0
+filter protocol ip pref 1 u32
+filter protocol ip pref 1 u32 fh 800: ht divisor 1
+filter protocol ip pref 1 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:1
+5
+
+ action order 1: tablename: mangle hook: NF_IP_PRE_ROUTING
+ target MARK set 0x1 index 2
+ Sent 188832 bytes 2248 pkts (dropped 0, overlimits 0)
+
+ action order 2: police 1 action pipe rate 1Kbit burst 9Kb mtu 2Kb
+ Sent 188832 bytes 2248 pkts (dropped 0, overlimits 2122)
+
+ action order 3: tablename: mangle hook: NF_IP_PRE_ROUTING
+ target MARK set 0x2 index 1
+ Sent 178248 bytes 2122 pkts (dropped 0, overlimits 0)
+
+ action order 4: police 30 action pipe rate 1Kbit burst 10Kb mtu 5000b
+ Sent 178248 bytes 2122 pkts (dropped 0, overlimits 1945)
+
+ action order 5: tablename: mangle hook: NF_IP_PRE_ROUTING
+ target MARK set 0x3 index 3
+ Sent 163380 bytes 1945 pkts (dropped 0, overlimits 0)
+
+ action order 6: police 20 action drop rate 1Kbit burst 90Kb mtu 5000b
+ Sent 163380 bytes 1945 pkts (dropped 0, overlimits 437)
+
+ match 0a000015/ffffffff at 12
+-------------------------------
+
+Neat, eh?
+
+
+Wanna write an action module?
+------------------------------
+Its easy. Either look at the code or send me email. I will document at
+some point; will also accept documentation.
+
+TODO
+----
+
+Lotsa goodies/features coming. Requests also being accepted.
+At the moment the focus has been on getting the architecture in place.
+Expect new things in the spurious time i have to work on this
+(particularly around end of year when i have typically get time off
+from work).
+
diff --git a/iproute2/doc/actions/gact-usage b/iproute2/doc/actions/gact-usage
new file mode 100644
index 0000000..de1308d
--- /dev/null
+++ b/iproute2/doc/actions/gact-usage
@@ -0,0 +1,79 @@
+
+gact <ACTION> [RAND] [INDEX]
+
+Where:
+ ACTION := reclassify | drop | continue | pass | ok
+ RAND := random <RANDTYPE> <ACTION> <VAL>
+ RANDTYPE := netrand | determ
+ VAL : = value not exceeding 10000
+ INDEX := index value used
+
+ACTION semantics
+- pass and ok are equivalent to accept
+- continue allows to restart classification lookup
+- drop drops packets
+- reclassify implies continue classification where we left off
+
+randomization
+--------------
+
+At the moment there are only two algorithms. One is deterministic
+and the other uses internal kernel netrand.
+
+Examples:
+
+Rules can be installed on both ingress and egress - this shows ingress
+only
+
+tc qdisc add dev eth0 ingress
+
+# example 1
+tc filter add dev eth0 parent ffff: protocol ip prio 6 u32 match ip src \
+10.0.0.9/32 flowid 1:16 action drop
+
+ping -c 20 10.0.0.9
+
+--
+filter u32
+filter u32 fh 800: ht divisor 1
+filter u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:16 (rule hit 32 success 20)
+ match 0a000009/ffffffff at 12 (success 20 )
+ action order 1: gact action drop
+ random type none pass val 0
+ index 1 ref 1 bind 1 installed 59 sec used 35 sec
+ Sent 1680 bytes 20 pkts (dropped 20, overlimits 0 )
+
+----
+
+# example 2
+#allow 1 out 10 randomly using the netrand generator
+tc filter add dev eth0 parent ffff: protocol ip prio 6 u32 match ip src \
+10.0.0.9/32 flowid 1:16 action drop random netrand ok 10
+
+ping -c 20 10.0.0.9
+
+----
+filter protocol ip pref 6 u32 filter protocol ip pref 6 u32 fh 800: ht divisor 1filter protocol ip pref 6 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:16 (rule hit 20 success 20)
+ match 0a000009/ffffffff at 12 (success 20 )
+ action order 1: gact action drop
+ random type netrand pass val 10
+ index 5 ref 1 bind 1 installed 49 sec used 25 sec
+ Sent 1680 bytes 20 pkts (dropped 16, overlimits 0 )
+
+--------
+#alternative: deterministically accept every second packet
+tc filter add dev eth0 parent ffff: protocol ip prio 6 u32 match ip src \
+10.0.0.9/32 flowid 1:16 action drop random determ ok 2
+
+ping -c 20 10.0.0.9
+
+tc -s filter show parent ffff: dev eth0
+-----
+filter protocol ip pref 6 u32 filter protocol ip pref 6 u32 fh 800: ht divisor 1filter protocol ip pref 6 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:16 (rule hit 20 success 20)
+ match 0a000009/ffffffff at 12 (success 20 )
+ action order 1: gact action drop
+ random type determ pass val 2
+ index 4 ref 1 bind 1 installed 118 sec used 82 sec
+ Sent 1680 bytes 20 pkts (dropped 10, overlimits 0 )
+-----
+
diff --git a/iproute2/doc/actions/ifb-README b/iproute2/doc/actions/ifb-README
new file mode 100644
index 0000000..3d01179
--- /dev/null
+++ b/iproute2/doc/actions/ifb-README
@@ -0,0 +1,125 @@
+
+IFB is intended to replace IMQ.
+Advantage over current IMQ; cleaner in particular in in SMP;
+with a _lot_ less code.
+
+Known IMQ/IFB USES
+------------------
+
+As far as i know the reasons listed below is why people use IMQ.
+It would be nice to know of anything else that i missed.
+
+1) qdiscs/policies that are per device as opposed to system wide.
+IFB allows for sharing.
+
+2) Allows for queueing incoming traffic for shaping instead of
+dropping. I am not aware of any study that shows policing is
+worse than shaping in achieving the end goal of rate control.
+I would be interested if anyone is experimenting.
+
+3) Very interesting use: if you are serving p2p you may wanna give
+preference to your own localy originated traffic (when responses come back)
+vs someone using your system to do bittorent. So QoSing based on state
+comes in as the solution. What people did to achive this was stick
+the IMQ somewhere prelocal hook.
+I think this is a pretty neat feature to have in Linux in general.
+(i.e not just for IMQ).
+But i wont go back to putting netfilter hooks in the device to satisfy
+this. I also dont think its worth it hacking ifb some more to be
+aware of say L3 info and play ip rule tricks to achieve this.
+--> Instead the plan is to have a contrack related action. This action will
+selectively either query/create contrack state on incoming packets.
+Packets could then be redirected to ifb based on what happens -> eg
+on incoming packets; if we find they are of known state we could send to
+a different queue than one which didnt have existing state. This
+all however is dependent on whatever rules the admin enters.
+
+At the moment this 3rd function does not exist yet. I have decided that
+instead of sitting on the patch for another year, to release it and then
+if theres pressure i will add this feature.
+
+An example, to provide functionality that most people use IMQ for below:
+
+--------
+export TC="/sbin/tc"
+
+$TC qdisc add dev ifb0 root handle 1: prio
+$TC qdisc add dev ifb0 parent 1:1 handle 10: sfq
+$TC qdisc add dev ifb0 parent 1:2 handle 20: tbf rate 20kbit buffer 1600 limit 3000
+$TC qdisc add dev ifb0 parent 1:3 handle 30: sfq
+$TC filter add dev ifb0 protocol ip pref 1 parent 1: handle 1 fw classid 1:1
+$TC filter add dev ifb0 protocol ip pref 2 parent 1: handle 2 fw classid 1:2
+
+ifconfig ifb0 up
+
+$TC qdisc add dev eth0 ingress
+
+# redirect all IP packets arriving in eth0 to ifb0
+# use mark 1 --> puts them onto class 1:1
+$TC filter add dev eth0 parent ffff: protocol ip prio 10 u32 \
+match u32 0 0 flowid 1:1 \
+action ipt -j MARK --set-mark 1 \
+action mirred egress redirect dev ifb0
+
+--------
+
+
+Run A Little test:
+
+from another machine ping so that you have packets going into the box:
+-----
+[root@jzny action-tests]# ping 10.22
+PING 10.22 (10.0.0.22): 56 data bytes
+64 bytes from 10.0.0.22: icmp_seq=0 ttl=64 time=2.8 ms
+64 bytes from 10.0.0.22: icmp_seq=1 ttl=64 time=0.6 ms
+64 bytes from 10.0.0.22: icmp_seq=2 ttl=64 time=0.6 ms
+
+--- 10.22 ping statistics ---
+3 packets transmitted, 3 packets received, 0% packet loss
+round-trip min/avg/max = 0.6/1.3/2.8 ms
+[root@jzny action-tests]#
+-----
+Now look at some stats:
+
+---
+[root@jmandrake]:~# $TC -s filter show parent ffff: dev eth0
+filter protocol ip pref 10 u32
+filter protocol ip pref 10 u32 fh 800: ht divisor 1
+filter protocol ip pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:1
+ match 00000000/00000000 at 0
+ action order 1: tablename: mangle hook: NF_IP_PRE_ROUTING
+ target MARK set 0x1
+ index 1 ref 1 bind 1 installed 4195sec used 27sec
+ Sent 252 bytes 3 pkts (dropped 0, overlimits 0)
+
+ action order 2: mirred (Egress Redirect to device ifb0) stolen
+ index 1 ref 1 bind 1 installed 165 sec used 27 sec
+ Sent 252 bytes 3 pkts (dropped 0, overlimits 0)
+
+[root@jmandrake]:~# $TC -s qdisc
+qdisc sfq 30: dev ifb0 limit 128p quantum 1514b
+ Sent 0 bytes 0 pkts (dropped 0, overlimits 0)
+qdisc tbf 20: dev ifb0 rate 20Kbit burst 1575b lat 2147.5s
+ Sent 210 bytes 3 pkts (dropped 0, overlimits 0)
+qdisc sfq 10: dev ifb0 limit 128p quantum 1514b
+ Sent 294 bytes 3 pkts (dropped 0, overlimits 0)
+qdisc prio 1: dev ifb0 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1
+ Sent 504 bytes 6 pkts (dropped 0, overlimits 0)
+qdisc ingress ffff: dev eth0 ----------------
+ Sent 308 bytes 5 pkts (dropped 0, overlimits 0)
+
+[root@jmandrake]:~# ifconfig ifb0
+ifb0 Link encap:Ethernet HWaddr 00:00:00:00:00:00
+ inet6 addr: fe80::200:ff:fe00:0/64 Scope:Link
+ UP BROADCAST RUNNING NOARP MTU:1500 Metric:1
+ RX packets:6 errors:0 dropped:3 overruns:0 frame:0
+ TX packets:3 errors:0 dropped:0 overruns:0 carrier:0
+ collisions:0 txqueuelen:32
+ RX bytes:504 (504.0 b) TX bytes:252 (252.0 b)
+-----
+
+You send it any packet not originating from the actions it will drop them.
+[In this case the three dropped packets were ipv6 ndisc].
+
+cheers,
+jamal
diff --git a/iproute2/doc/actions/mirred-usage b/iproute2/doc/actions/mirred-usage
new file mode 100644
index 0000000..2622c43
--- /dev/null
+++ b/iproute2/doc/actions/mirred-usage
@@ -0,0 +1,164 @@
+
+Very funky action. I do plan to add to a few more things to it
+This is the basic stuff. Idea borrowed from the way ethernet switches
+mirror and redirect packets. The main difference with say a vannila
+ethernet switch is that you can use u32 classifier to select a
+flow to be mirrored. High end switches typically can select based
+on more than just a port (eg a 5 tuple classifier). They may also be
+capable of redirecting.
+
+Usage:
+
+mirred <DIRECTION> <ACTION> [index INDEX] <dev DEVICENAME>
+where:
+DIRECTION := <ingress | egress>
+ACTION := <mirror | redirect>
+INDEX is the specific policy instance id
+DEVICENAME is the devicename
+
+Direction:
+- Ingress is not supported at the moment. It will be in the
+future as well as mirror/redirecting to a socket.
+
+Action:
+- Mirror takes a copy of the packet and sends it to specified
+dev ("port" in ethernet switch/bridging terminology)
+- redirect
+steals the packet and redirects to specified destination dev.
+
+What NOT to do if you dont want your machine to crash:
+------------------------------------------------------
+
+Do not create loops!
+Loops are not hard to create in the egress qdiscs.
+
+Here are simple rules to follow if you dont want to get
+hurt:
+A) Do not have the same packet go to same netdevice twice
+in a single graph of policies. Your machine will just hang!
+This is design intent _not a bug_ to teach you some lessons.
+
+In the future if there are easy ways to do this in the kernel
+without affecting other packets not interested in this feature
+I will add them. At the moment that is not clear.
+
+Some examples of bad things NOT to do:
+1) redirecting eth0 to eth0
+2) eth0->eth1-> eth0
+3) eth0->lo-> eth1-> eth0
+
+B) Do not redirect from one IFB device to another.
+Remember that IFB is a very specialized case of packet redirecting
+device. Instead of redirecting it puts packets at the exact spot
+on the stack it found them from.
+Redirecting from ifbX->ifbY will actually not crash your machine but your
+packets will all be dropped (this is much simpler to detect
+and resolve and is only affecting users of ifb as opposed to the
+whole stack).
+
+In the case of A) the problem has to do with a recursive contention
+for the devices queue lock and in the second case for the transmit lock.
+
+Some examples:
+-------------
+
+1) Mirror all packets arriving on eth0 to be sent out on eth1.
+You may have a sniffer or some accounting box hooked up on eth1.
+
+---
+tc qdisc add dev eth0 ingress
+tc filter add dev eth0 parent ffff: protocol ip prio 10 u32 \
+match u32 0 0 flowid 1:2 action mirred egress mirror dev eth1
+---
+
+If you replace "mirror" with "redirect" then not a copy but rather
+the original packet is sent to eth1.
+
+2) Host A is hooked up to us on eth0
+
+# redirect all packets arriving on ingress of lo to eth0
+---
+tc qdisc add dev lo ingress
+tc filter add dev lo parent ffff: protocol ip prio 10 u32 \
+match u32 0 0 flowid 1:2 action mirred egress redirect dev eth0
+---
+
+On host A start a tcpdump on interface connecting to us.
+
+on our host ping -c 2 127.0.0.1
+
+Ping would fail since all packets are heading out eth0
+tcpudmp on host A would show them
+
+if you substitute the redirect with mirror above as in:
+tc filter add dev lo parent ffff: protocol ip prio 10 u32 \
+match u32 0 0 flowid 1:2 action mirred egress mirror dev eth0
+
+Then you should see the packets on both host A and the local
+stack (i.e ping would work).
+
+3) Even more funky example:
+
+#
+#allow 1 out 10 packets on ingress of lo to randomly make it to the
+# host A (Randomness uses the netrand generator)
+#
+---
+tc filter add dev lo parent ffff: protocol ip prio 10 u32 \
+match u32 0 0 flowid 1:2 \
+action drop random determ ok 10\
+action mirred egress mirror dev eth0
+---
+
+4)
+# for packets from 10.0.0.9 going out on eth0 (could be local
+# IP or something # we are forwarding) -
+# if exceeding a 100Kbps rate, then redirect to eth1
+#
+
+---
+tc qdisc add dev eth0 handle 1:0 root prio
+tc filter add dev eth0 parent 1:0 protocol ip prio 6 u32 \
+match ip src 10.0.0.9/32 flowid 1:16 \
+action police rate 100kbit burst 90k ok \
+action mirred egress mirror dev eth1
+---
+
+A more interesting example is when you mirror flows to a dummy device
+so you could tcpdump them (dummy by defaults drops all packets it sees).
+This is a very useful debug feature.
+
+Lets say you are policing packets from alias 192.168.200.200/32
+you dont want those to exceed 100kbps going out.
+
+---
+tc qdisc add dev eth0 handle 1:0 root prio
+tc filter add dev eth0 parent 1: protocol ip prio 10 u32 \
+match ip src 192.168.200.200/32 flowid 1:2 \
+action police rate 100kbit burst 90k drop
+---
+
+If you run tcpdump on eth0 you will see all packets going out
+with src 192.168.200.200/32 dropped or not (since tcpdump shows
+all packets being egressed).
+Extend the rule a little to see only the packets making it out.
+
+---
+tc qdisc add dev eth0 handle 1:0 root prio
+tc filter add dev eth0 parent 1: protocol ip prio 10 u32 \
+match ip src 192.168.200.200/32 flowid 1:2 \
+action police rate 10kbit burst 90k drop \
+action mirred egress mirror dev dummy0
+---
+
+Now fire tcpdump on dummy0 to see only those packets ..
+tcpdump -n -i dummy0 -x -e -t
+
+Essentially a good debugging/logging interface (sort of like
+BSDs speacialized log device does without needing one).
+
+If you replace mirror with redirect, those packets will be
+blackholed and will never make it out.
+
+cheers,
+jamal
diff --git a/iproute2/doc/api-ip6-flowlabels.tex b/iproute2/doc/api-ip6-flowlabels.tex
new file mode 100644
index 0000000..aa34e94
--- /dev/null
+++ b/iproute2/doc/api-ip6-flowlabels.tex
@@ -0,0 +1,429 @@
+\documentstyle[12pt,twoside]{article}
+\def\TITLE{IPv6 Flow Labels}
+\input preamble
+\begin{center}
+\Large\bf IPv6 Flow Labels in Linux-2.2.
+\end{center}
+
+
+\begin{center}
+{ \large Alexey~N.~Kuznetsov } \\
+\em Institute for Nuclear Research, Moscow \\
+\verb|kuznet@ms2.inr.ac.ru| \\
+\rm April 11, 1999
+\end{center}
+
+\vspace{5mm}
+
+\tableofcontents
+
+\section{Introduction.}
+
+Every IPv6 packet carries 28 bits of flow information. RFC2460 splits
+these bits to two fields: 8 bits of traffic class (or DS field, if you
+prefer this term) and 20 bits of flow label. Currently there exist
+no well-defined API to manage IPv6 flow information. In this document
+I describe an attempt to design the API for Linux-2.2 IPv6 stack.
+
+\vskip 1mm
+
+The API must solve the following tasks:
+
+\begin{enumerate}
+
+\item To allow user to set traffic class bits.
+
+\item To allow user to read traffic class bits of received packets.
+This feature is not so useful as the first one, however it will be
+necessary f.e.\ to implement ECN [RFC2481] for datagram oriented services
+or to implement receiver side of SRP or another end-to-end protocol
+using traffic class bits.
+
+\item To assign flow labels to packets sent by user.
+
+\item To get flow labels of received packets. I do not know
+any applications of this feature, but it is possible that receiver will
+want to use flow labels to distinguish sub-flows.
+
+\item To allocate flow labels in the way, compliant to RFC2460. Namely:
+
+\begin{itemize}
+\item
+Flow labels must be uniformly distributed (pseudo-)random numbers,
+so that any subset of 20 bits can be used as hash key.
+
+\item
+Flows with coinciding source address and flow label must have identical
+destination address and not-fragmentable extensions headers (i.e.\
+hop by hop options and all the headers up to and including routing header,
+if it is present.)
+
+\begin{NB}
+There is a hole in specs: some hop-by-hop options can be
+defined only on per-packet base (f.e.\ jumbo payload option).
+Essentially, it means that such options cannot present in packets
+with flow labels.
+\end{NB}
+\begin{NB}
+NB notes here and below reflect only my personal opinion,
+they should be read with smile or should not be read at all :-).
+\end{NB}
+
+
+\item
+Flow labels have finite lifetime and source is not allowed to reuse
+flow label for another flow within the maximal lifetime has expired,
+so that intermediate nodes will be able to invalidate flow state before
+the label is taken over by another flow.
+Flow state, including lifetime, is propagated along datagram path
+by some application specific methods
+(f.e.\ in RSVP PATH messages or in some hop-by-hop option).
+
+
+\end{itemize}
+
+\end{enumerate}
+
+\section{Sending/receiving flow information.}
+
+\paragraph{Discussion.}
+\addcontentsline{toc}{subsection}{Discussion}
+It was proposed (Where? I do not remember any explicit statement)
+to solve the first four tasks using
+\verb|sin6_flowinfo| field added to \verb|struct| \verb|sockaddr_in6|
+(see RFC2553).
+
+\begin{NB}
+ This method is difficult to consider as reasonable, because it
+ puts additional overhead to all the services, despite of only
+ very small subset of them (none, to be more exact) really use it.
+ It contradicts both to IETF spirit and the letter. Before RFC2553
+ one justification existed, IPv6 address alignment left 4 byte
+ hole in \verb|sockaddr_in6| in any case. Now it has no justification.
+\end{NB}
+
+We have two problems with this method. The first one is common for all OSes:
+if \verb|recvmsg()| initializes \verb|sin6_flowinfo| to flow info
+of received packet, we loose one very important property of BSD socket API,
+namely, we are not allowed to use received address for reply directly
+and have to mangle it, even if we are not interested in flowinfo subtleties.
+
+\begin{NB}
+ RFC2553 adds new requirement: to clear \verb|sin6_flowinfo|.
+ Certainly, it is not solution but rather attempt to force applications
+ to make unnecessary work. Well, as usually, one mistake in design
+ is followed by attempts to patch the hole and more mistakes...
+\end{NB}
+
+Another problem is Linux specific. Historically Linux IPv6 did not
+initialize \verb|sin6_flowinfo| at all, so that, if kernel does not
+support flow labels, this field is not zero, but a random number.
+Some applications also did not take care about it.
+
+\begin{NB}
+Following RFC2553 such applications can be considered as broken,
+but I still think that they are right: clearing all the address
+before filling known fields is robust but stupid solution.
+Useless wasting CPU cycles and
+memory bandwidth is not a good idea. Such patches are acceptable
+as temporary hacks, but not as standard of the future.
+\end{NB}
+
+
+\paragraph{Implementation.}
+\addcontentsline{toc}{subsection}{Implementation}
+By default Linux IPv6 does not read \verb|sin6_flowinfo| field
+assuming that common applications are not obliged to initialize it
+and are permitted to consider it as pure alignment padding.
+In order to tell kernel that application
+is aware of this field, it is necessary to set socket option
+\verb|IPV6_FLOWINFO_SEND|.
+
+\begin{verbatim}
+ int on = 1;
+ setsockopt(sock, SOL_IPV6, IPV6_FLOWINFO_SEND,
+ (void*)&on, sizeof(on));
+\end{verbatim}
+
+Linux kernel never fills \verb|sin6_flowinfo| field, when passing
+message to user space, though the kernels which support flow labels
+initialize it to zero. If user wants to get received flowinfo, he
+will set option \verb|IPV6_FLOWINFO| and after this he will receive
+flowinfo as ancillary data object of type \verb|IPV6_FLOWINFO|
+(cf.\ RFC2292).
+
+\begin{verbatim}
+ int on = 1;
+ setsockopt(sock, SOL_IPV6, IPV6_FLOWINFO, (void*)&on, sizeof(on));
+\end{verbatim}
+
+Flowinfo received and latched by a connected TCP socket also may be fetched
+with \verb|getsockopt()| \verb|IPV6_PKTOPTIONS| together with
+another optional information.
+
+Besides that, in the spirit of RFC2292 the option \verb|IPV6_FLOWINFO|
+may be used as alternative way to send flowinfo with \verb|sendmsg()| or
+to latch it with \verb|IPV6_PKTOPTIONS|.
+
+\paragraph{Note about IPv6 options and destination address.}
+\addcontentsline{toc}{subsection}{IPv6 options and destination address}
+If \verb|sin6_flowinfo| does contain not zero flow label,
+destination address in \verb|sin6_addr| and non-fragmentable
+extension headers are ignored. Instead, kernel uses the values
+cached at flow setup (see below). However, for connected sockets
+kernel prefers the values set at connection time.
+
+\paragraph{Example.}
+\addcontentsline{toc}{subsection}{Example}
+After setting socket option \verb|IPV6_FLOWINFO|
+flowlabel and DS field are received as ancillary data object
+of type \verb|IPV6_FLOWINFO| and level \verb|SOL_IPV6|.
+In the cases when it is convenient to use \verb|recvfrom(2)|,
+it is possible to replace library variant with your own one,
+sort of:
+
+\begin{verbatim}
+#include <sys/socket.h>
+#include <netinet/in6.h>
+
+size_t recvfrom(int fd, char *buf, size_t len, int flags,
+ struct sockaddr *addr, int *addrlen)
+{
+ size_t cc;
+ char cbuf[128];
+ struct cmsghdr *c;
+ struct iovec iov = { buf, len };
+ struct msghdr msg = { addr, *addrlen,
+ &iov, 1,
+ cbuf, sizeof(cbuf),
+ 0 };
+
+ cc = recvmsg(fd, &msg, flags);
+ if (cc < 0)
+ return cc;
+ ((struct sockaddr_in6*)addr)->sin6_flowinfo = 0;
+ *addrlen = msg.msg_namelen;
+ for (c=CMSG_FIRSTHDR(&msg); c; c = CMSG_NEXTHDR(&msg, c)) {
+ if (c->cmsg_level != SOL_IPV6 ||
+ c->cmsg_type != IPV6_FLOWINFO)
+ continue;
+ ((struct sockaddr_in6*)addr)->sin6_flowinfo = *(__u32*)CMSG_DATA(c);
+ }
+ return cc;
+}
+\end{verbatim}
+
+
+
+\section{Flow label management.}
+
+\paragraph{Discussion.}
+\addcontentsline{toc}{subsection}{Discussion}
+Requirements of RFC2460 are pretty tough. Particularly, lifetimes
+longer than boot time require to store allocated labels at stable
+storage, so that the full implementation necessarily includes user space flow
+label manager. There are at least three different approaches:
+
+\begin{enumerate}
+\item {\bf ``Cooperative''. } We could leave flow label allocation wholly
+to user space. When user needs label he requests manager directly. The approach
+is valid, but as any ``cooperative'' approach it suffers of security problems.
+
+\begin{NB}
+One idea is to disallow not privileged user to allocate flow
+labels, but instead to pass the socket to manager via \verb|SCM_RIGHTS|
+control message, so that it will allocate label and assign it to socket
+itself. Hmm... the idea is interesting.
+\end{NB}
+
+\item {\bf ``Indirect''.} Kernel redirects requests to user level daemon
+and does not install label until the daemon acknowledged the request.
+The approach is the most promising, it is especially pleasant to recognize
+parallel with IPsec API [RFC2367,Craig]. Actually, it may share API with
+IPsec.
+
+\item {\bf ``Stupid''.} To allocate labels in kernel space. It is the simplest
+method, but it suffers of two serious flaws: the first,
+we cannot lease labels with lifetimes longer than boot time, the second,
+it is sensitive to DoS attacks. Kernel have to remember all the obsolete
+labels until their expiration and malicious user may fastly eat all the
+flow label space.
+
+\end{enumerate}
+
+Certainly, I choose the most ``stupid'' method. It is the cheapest one
+for implementor (i.e.\ me), and taking into account that flow labels
+still have no serious applications it is not useful to work on more
+advanced API, especially, taking into account that eventually we
+will get it for no fee together with IPsec.
+
+
+\paragraph{Implementation.}
+\addcontentsline{toc}{subsection}{Implementation}
+Socket option \verb|IPV6_FLOWLABEL_MGR| allows to
+request flow label manager to allocate new flow label, to reuse
+already allocated one or to delete old flow label.
+Its argument is \verb|struct| \verb|in6_flowlabel_req|:
+
+\begin{verbatim}
+struct in6_flowlabel_req
+{
+ struct in6_addr flr_dst;
+ __u32 flr_label;
+ __u8 flr_action;
+ __u8 flr_share;
+ __u16 flr_flags;
+ __u16 flr_expires;
+ __u16 flr_linger;
+ __u32 __flr_reserved;
+ /* Options in format of IPV6_PKTOPTIONS */
+};
+\end{verbatim}
+
+\begin{itemize}
+
+\item \verb|dst| is IPv6 destination address associated with the label.
+
+\item \verb|label| is flow label value in network byte order. If it is zero,
+kernel will allocate new pseudo-random number. Otherwise, kernel will try
+to lease flow label ordered by user. In this case, it is user task to provide
+necessary flow label randomness.
+
+\item \verb|action| is requested operation. Currently, only three operations
+are defined:
+
+\begin{verbatim}
+#define IPV6_FL_A_GET 0 /* Get flow label */
+#define IPV6_FL_A_PUT 1 /* Release flow label */
+#define IPV6_FL_A_RENEW 2 /* Update expire time */
+\end{verbatim}
+
+\item \verb|flags| are optional modifiers. Currently
+only \verb|IPV6_FL_A_GET| has modifiers:
+
+\begin{verbatim}
+#define IPV6_FL_F_CREATE 1 /* Allowed to create new label */
+#define IPV6_FL_F_EXCL 2 /* Do not create new label */
+\end{verbatim}
+
+
+\item \verb|share| defines who is allowed to reuse the same flow label.
+
+\begin{verbatim}
+#define IPV6_FL_S_NONE 0 /* Not defined */
+#define IPV6_FL_S_EXCL 1 /* Label is private */
+#define IPV6_FL_S_PROCESS 2 /* May be reused by this process */
+#define IPV6_FL_S_USER 3 /* May be reused by this user */
+#define IPV6_FL_S_ANY 255 /* Anyone may reuse it */
+\end{verbatim}
+
+\item \verb|linger| is time in seconds. After the last user releases flow
+label, it will not be reused with different destination and options at least
+during this time. If \verb|share| is not \verb|IPV6_FL_S_EXCL| the label
+still can be shared by another sockets. Current implementation does not allow
+unprivileged user to set linger longer than 60 sec.
+
+\item \verb|expires| is time in seconds. Flow label will be kept at least
+for this time, but it will not be destroyed before user released it explicitly
+or closed all the sockets using it. Current implementation does not allow
+unprivileged user to set timeout longer than 60 sec. Proviledged applications
+MAY set longer lifetimes, but in this case they MUST save allocated
+labels at stable storage and restore them back after reboot before the first
+application allocates new flow.
+
+\end{itemize}
+
+This structure is followed by optional extension headers associated
+with this flow label in format of \verb|IPV6_PKTOPTIONS|. Only
+\verb|IPV6_HOPOPTS|, \verb|IPV6_RTHDR| and, if \verb|IPV6_RTHDR| presents,
+\verb|IPV6_DSTOPTS| are allowed.
+
+\paragraph{Example.}
+\addcontentsline{toc}{subsection}{Example}
+ The function \verb|get_flow_label| allocates
+private flow label.
+
+\begin{verbatim}
+int get_flow_label(int fd, struct sockaddr_in6 *dst, __u32 fl)
+{
+ int on = 1;
+ struct in6_flowlabel_req freq;
+
+ memset(&freq, 0, sizeof(freq));
+ freq.flr_label = htonl(fl);
+ freq.flr_action = IPV6_FL_A_GET;
+ freq.flr_flags = IPV6_FL_F_CREATE | IPV6_FL_F_EXCL;
+ freq.flr_share = IPV6_FL_S_EXCL;
+ memcpy(&freq.flr_dst, &dst->sin6_addr, 16);
+ if (setsockopt(fd, SOL_IPV6, IPV6_FLOWLABEL_MGR,
+ &freq, sizeof(freq)) == -1) {
+ perror ("can't lease flowlabel");
+ return -1;
+ }
+ dst->sin6_flowinfo |= freq.flr_label;
+
+ if (setsockopt(fd, SOL_IPV6, IPV6_FLOWINFO_SEND,
+ &on, sizeof(on)) == -1) {
+ perror ("can't send flowinfo");
+
+ freq.flr_action = IPV6_FL_A_PUT;
+ setsockopt(fd, SOL_IPV6, IPV6_FLOWLABEL_MGR,
+ &freq, sizeof(freq));
+ return -1;
+ }
+ return 0;
+}
+\end{verbatim}
+
+A bit more complicated example using routing header can be found
+in \verb|ping6| utility (\verb|iputils| package). Linux rsvpd backend
+contains an example of using operation \verb|IPV6_FL_A_RENEW|.
+
+\paragraph{Listing flow labels.}
+\addcontentsline{toc}{subsection}{Listing flow labels}
+List of currently allocated
+flow labels may be read from \verb|/proc/net/ip6_flowlabel|.
+
+\begin{verbatim}
+Label S Owner Users Linger Expires Dst Opt
+A1BE5 1 0 0 6 3 3ffe2400000000010a0020fffe71fb30 0
+\end{verbatim}
+
+\begin{itemize}
+\item \verb|Label| is hexadecimal flow label value.
+\item \verb|S| is sharing style.
+\item \verb|Owner| is ID of creator, it is zero, pid or uid, depending on
+ sharing style.
+\item \verb|Users| is number of applications using the label now.
+\item \verb|Linger| is \verb|linger| of this label in seconds.
+\item \verb|Expires| is time until expiration of the label in seconds. It may
+ be negative, if the label is in use.
+\item \verb|Dst| is IPv6 destination address.
+\item \verb|Opt| is length of options, associated with the label. Option
+ data are not accessible.
+\end{itemize}
+
+
+\paragraph{Flow labels and RSVP.}
+\addcontentsline{toc}{subsection}{Flow labels and RSVP}
+RSVP daemon supports IPv6 flow labels
+without any modifications to standard ISI RAPI. Sender must allocate
+flow label, fill corresponding sender template and submit it to local rsvp
+daemon. rsvpd will check the label and start to announce it in PATH
+messages. Rsvpd on sender node will renew the flow label, so that it will not
+be reused before path state expires and all the intermediate
+routers and receiver purge flow state.
+
+\verb|rtap| utility is modified to parse flow labels. F.e.\ if user allocated
+flow label \verb|0xA1234|, he may write:
+
+\begin{verbatim}
+RTAP> sender 3ffe:2400::1/FL0xA1234 <Tspec>
+\end{verbatim}
+
+Receiver makes reservation with command:
+\begin{verbatim}
+RTAP> reserve ff 3ffe:2400::1/FL0xA1234 <Flowspec>
+\end{verbatim}
+
+\end{document}
diff --git a/iproute2/doc/arpd.sgml b/iproute2/doc/arpd.sgml
new file mode 100644
index 0000000..0ab79c6
--- /dev/null
+++ b/iproute2/doc/arpd.sgml
@@ -0,0 +1,130 @@
+<!doctype linuxdoc system>
+
+<article>
+
+<title>ARPD Daemon
+<author>Alexey Kuznetsov, <tt/kuznet@ms2.inr.ac.ru/
+<date>some_negative_number, 20 Sep 2001
+<abstract>
+<tt/arpd/ is daemon collecting gratuitous ARP information, saving
+it on local disk and feeding it to kernel on demand to avoid
+redundant broadcasting due to limited size of kernel ARP cache.
+</abstract>
+
+
+<p><bf/Description/
+
+<p>The format of the command is:
+
+<tscreen><verb>
+ arpd OPTIONS [ INTERFACE [ INTERFACE ... ] ]
+</verb></tscreen>
+
+<p> <tt/OPTIONS/ are:
+
+<itemize>
+
+<item><tt/-l/ - dump <tt/arpd/ database to stdout and exit. Output consists
+of three columns: interface index, IP address and MAC address.
+Negative entries for dead hosts are also shown, in this case MAC address
+is replaced by word <tt/FAILED/ followed by colon and time when the fact
+that host is dead was proven the last time.
+
+<item><tt/-f FILE/ - read and load <tt/arpd/ database from <tt/FILE/
+in text format similar dumped by option <tt/-l/. Exit after load,
+probably listing resulting database, if option <tt/-l/ is also given.
+If <tt/FILE/ is <tt/-/, <tt/stdin/ is read to get ARP table.
+
+<item><tt/-b DATABASE/ - location of database file. Default location is
+<tt>/var/lib/arpd/arpd.db</tt>.
+
+<item><tt/-a NUMBER/ - <tt/arpd/ not only passively listens ARP on wire, but
+also send brodcast queries itself. <tt/NUMBER/ is number of such queries
+to make before destination is considered as dead. When <tt/arpd/ is started
+as kernel helper (i.e. with <tt/app_solicit/ enabled in <tt/sysctl/
+or even with option <tt/-k/) without this option and still did not learn enough
+information, you can observe 1 second gaps in service. Not fatal, but
+not good.
+
+<item><tt/-k/ - suppress sending broadcast queries by kernel. It takes
+sense together with option <tt/-a/.
+
+<item><tt/-n TIME/ - timeout of negative cache. When resolution fails <tt/arpd/
+suppresses further attempts to resolve for this period. It makes sense
+only together with option <tt/-k/. This timeout should not be too much
+longer than boot time of a typical host not supporting gratuitous ARP.
+Default value is 60 seconds.
+
+<item><tt/-R RATE/ - maximal steady rate of broadcasts sent by <tt/arpd/
+in packets per second. Default value is 1.
+
+<item><tt/-B NUMBER/ - number of broadcasts sent by <tt/arpd/ back to back.
+Default value is 3. Together with option <tt/-R/ this option allows
+to police broadcasting not to exceed <tt/B+R*T/ over any interval
+of time <tt/T/.
+
+</itemize>
+
+<p><tt/INTERFACE/ is name of networking inteface to watch.
+If no interfaces given, <tt/arpd/ monitors all the interfaces.
+In this case <tt/arpd/ does not adjust <tt/sysctl/ parameters,
+it is supposed user does this himself after <tt/arpd/ is started.
+
+
+<p> Signals
+
+<p> <tt/arpd/ exits gracefully syncing database and restoring adjusted
+<tt/sysctl/ parameters, when receives <tt/SIGINT/ or <tt/SIGTERM/.
+<tt/SIGHUP/ syncs database to disk. <tt/SIGUSR1/ sends some statistics
+to <tt/syslog/. Effect of another signals is undefined, they may corrupt
+database and leave <tt/sysctl/ parameters in an unpredictable state.
+
+<p> Note
+
+<p> In order to <tt/arpd/ be able to serve as ARP resolver, kernel must be
+compiled with the option <tt/CONFIG_ARPD/ and, in the case when interface list
+is not given on command line, variable <tt/app_solicit/
+on interfaces of interest should be set in <tt>/proc/sys/net/ipv4/neigh/*</tt>.
+If this is not made <tt/arpd/ still collects gratuitous ARP information
+in its database.
+
+<p> Examples
+
+<enum>
+<item> Start <tt/arpd/ to collect gratuitous ARP, but not messing
+with kernel functionality:
+
+<tscreen><verb>
+ arpd -b /var/tmp/arpd.db
+</verb></tscreen>
+
+<item> Look at result after some time:
+
+<tscreen><verb>
+ killall arpd
+ arpd -l -b /var/tmp/arpd.db
+</verb></tscreen>
+
+<item> To enable kernel helper, leaving leading role to kernel:
+
+<tscreen><verb>
+ arpd -b /var/tmp/arpd.db -a 1 eth0 eth1
+</verb></tscreen>
+
+<item> Completely replace kernel resolution on interfaces <tt/eth0/
+and <tt/eth1/. In this case kernel still does unicast probing to
+validate entries, but all the broadcast activity is suppressed
+and made under authority of <tt/arpd/:
+
+<tscreen><verb>
+ arpd -b /var/tmp/arpd.db -a 3 -k eth0 eth1
+</verb></tscreen>
+
+This is mode which <tt/arpd/ is supposed to work normally.
+It is not default just to prevent occasional enabling of too aggressive
+mode occasionally.
+
+</enum>
+
+</article>
+
diff --git a/iproute2/doc/do-psnup b/iproute2/doc/do-psnup
new file mode 100644
index 0000000..2dce848
--- /dev/null
+++ b/iproute2/doc/do-psnup
@@ -0,0 +1,16 @@
+#! /bin/bash
+# $1 = Temporary file . "string"
+# $2 = File to process . "string"
+# $3 = Page size . ie: a4 , letter ... "string"
+# $4 = Number of pages to fit on a single sheet . "numeric"
+
+if type psnup >&/dev/null; then
+ echo "psnup -$4 -p$3 $1 $2"
+ psnup -$4 -p$3 $1 $2
+elif type psmulti >&/dev/null; then
+ echo "psmulti $1 > $2"
+ psmulti $1 > $2
+else
+ echo "cp $1 $2"
+ cp $1 $2
+fi
diff --git a/iproute2/doc/ip-cref.tex b/iproute2/doc/ip-cref.tex
new file mode 100644
index 0000000..67094c9
--- /dev/null
+++ b/iproute2/doc/ip-cref.tex
@@ -0,0 +1,3449 @@
+\documentstyle[12pt,twoside]{article}
+\def\TITLE{IP Command Reference}
+\input preamble
+\begin{center}
+\Large\bf IP Command Reference.
+\end{center}
+
+
+\begin{center}
+{ \large Alexey~N.~Kuznetsov } \\
+\em Institute for Nuclear Research, Moscow \\
+\verb|kuznet@ms2.inr.ac.ru| \\
+\rm April 14, 1999
+\end{center}
+
+\vspace{5mm}
+
+\tableofcontents
+
+\newpage
+
+\section{About this document}
+
+This document presents a comprehensive description of the \verb|ip| utility
+from the \verb|iproute2| package. It is not a tutorial or user's guide.
+It is a {\em dictionary\/}, not explaining terms,
+but translating them into other terms, which may also be unknown to the reader.
+However, the document is self-contained and the reader, provided they have a
+basic networking background, will find enough information
+and examples to understand and configure Linux-2.2 IP and IPv6
+networking.
+
+This document is split into sections explaining \verb|ip| commands
+and options, decrypting \verb|ip| output and containing a few examples.
+More voluminous examples and some topics, which require more elaborate
+discussion, are in the appendix.
+
+The paragraphs beginning with NB contain side notes, warnings about
+bugs and design drawbacks. They may be skipped at the first reading.
+
+\section{{\tt ip} --- command syntax}
+
+The generic form of an \verb|ip| command is:
+\begin{verbatim}
+ip [ OPTIONS ] OBJECT [ COMMAND [ ARGUMENTS ]]
+\end{verbatim}
+where \verb|OPTIONS| is a set of optional modifiers affecting the
+general behaviour of the \verb|ip| utility or changing its output. All options
+begin with the character \verb|'-'| and may be used in either long or abbreviated
+forms. Currently, the following options are available:
+
+\begin{itemize}
+\item \verb|-V|, \verb|-Version|
+
+--- print the version of the \verb|ip| utility and exit.
+
+
+\item \verb|-s|, \verb|-stats|, \verb|-statistics|
+
+--- output more information. If the option
+appears twice or more, the amount of information increases.
+As a rule, the information is statistics or some time values.
+
+\item \verb|-d|, \verb|-details|
+
+--- output more detailed information.
+
+\item \verb|-f|, \verb|-family| followed by a protocol family
+identifier: \verb|inet|, \verb|inet6| or \verb|link|.
+
+--- enforce the protocol family to use. If the option is not present,
+the protocol family is guessed from other arguments. If the rest of the command
+line does not give enough information to guess the family, \verb|ip| falls back to the default
+one, usually \verb|inet| or \verb|any|. \verb|link| is a special family
+identifier meaning that no networking protocol is involved.
+
+\item \verb|-4|
+
+--- shortcut for \verb|-family inet|.
+
+\item \verb|-6|
+
+--- shortcut for \verb|-family inet6|.
+
+\item \verb|-0|
+
+--- shortcut for \verb|-family link|.
+
+
+\item \verb|-o|, \verb|-oneline|
+
+--- output each record on a single line, replacing line feeds
+with the \verb|'\'| character. This is convenient when you want to
+count records with \verb|wc| or to \verb|grep| the output. The trivial
+script \verb|rtpr| converts the output back into readable form.
+
+\item \verb|-r|, \verb|-resolve|
+
+--- use the system's name resolver to print DNS names instead of
+host addresses.
+
+\begin{NB}
+ Do not use this option when reporting bugs or asking for advice.
+\end{NB}
+\begin{NB}
+ \verb|ip| never uses DNS to resolve names to addresses.
+\end{NB}
+
+\item \verb|-b|, \verb|-batch FILE|
+
+--- read commands from provided file or standart input and invoke them.
+First failure will cause termination of \verb|ip|.
+In batch \verb|FILE| everything which begins with \verb|#| symbol is
+ignored and can be used for comments.
+\paragraph{Example:}
+\begin{verbatim}
+kuznet@kaiser $ cat /tmp/ip_batch.ip
+# This is a comment
+tuntap add mode tap tap1 # This is an another comment
+link set up dev tap1
+addr add 10.0.0.1/24 dev tap1
+kuznet@kaiser $ sudo ip -b /tmp/ip_batch.ip
+\end{verbatim}
+or from standart input:
+\begin{verbatim}
+kuznet@kaiser $ cat /tmp/ip_batch.ip | sudo ip -b -
+\end{verbatim}
+
+\item \verb|-force|
+
+--- don't terminate ip on errors in batch mode.
+If there were any errors during execution of the commands,
+the application return code will be non zero.
+
+\item \verb|-l|, \verb|-loops COUNT|
+
+--- specify maximum number of loops the 'ip addr flush' logic will attempt
+before giving up. The default is 10. Zero (0) means loop until all
+addresses are removed.
+
+\end{itemize}
+
+\verb|OBJECT| is the object to manage or to get information about.
+The object types currently understood by \verb|ip| are:
+
+\begin{itemize}
+\item \verb|link| --- network device
+\item \verb|address| --- protocol (IP or IPv6) address on a device
+\item \verb|neighbour| --- ARP or NDISC cache entry
+\item \verb|route| --- routing table entry
+\item \verb|rule| --- rule in routing policy database
+\item \verb|maddress| --- multicast address
+\item \verb|mroute| --- multicast routing cache entry
+\item \verb|tunnel| --- tunnel over IP
+\end{itemize}
+
+Again, the names of all objects may be written in full or
+abbreviated form, f.e.\ \verb|address| is abbreviated as \verb|addr|
+or just \verb|a|.
+
+\verb|COMMAND| specifies the action to perform on the object.
+The set of possible actions depends on the object type.
+As a rule, it is possible to \verb|add|, \verb|delete| and
+\verb|show| (or \verb|list|) objects, but some objects
+do not allow all of these operations or have some additional commands.
+The \verb|help| command is available for all objects. It prints
+out a list of available commands and argument syntax conventions.
+
+If no command is given, some default command is assumed.
+Usually it is \verb|list| or, if the objects of this class
+cannot be listed, \verb|help|.
+
+\verb|ARGUMENTS| is a list of arguments to the command.
+The arguments depend on the command and object. There are two types of arguments:
+{\em flags\/}, consisting of a single keyword, and {\em parameters\/},
+consisting of a keyword followed by a value. For convenience,
+each command has some {\em default parameter\/}
+which may be omitted. F.e.\ parameter \verb|dev| is the default
+for the {\tt ip link} command, so {\tt ip link ls eth0} is equivalent
+to {\tt ip link ls dev eth0}.
+In the command descriptions below such parameters
+are distinguished with the marker: ``(default)''.
+
+Almost all keywords may be abbreviated with several first (or even single)
+letters. The shortcuts are convenient when \verb|ip| is used interactively,
+but they are not recommended in scripts or when reporting bugs
+or asking for advice. ``Officially'' allowed abbreviations are listed
+in the document body.
+
+
+
+\section{{\tt ip} --- error messages}
+
+\verb|ip| may fail for one of the following reasons:
+
+\begin{itemize}
+\item
+A syntax error on the command line: an unknown keyword, incorrectly formatted
+IP address {\em et al\/}. In this case \verb|ip| prints an error message
+and exits. As a rule, the error message will contain information
+about the reason for the failure. Sometimes it also prints a help page.
+
+\item
+The arguments did not pass verification for self-consistency.
+
+\item
+\verb|ip| failed to compile a kernel request from the arguments
+because the user didn't give enough information.
+
+\item
+The kernel returned an error to some syscall. In this case \verb|ip|
+prints the error message, as it is output with \verb|perror(3)|,
+prefixed with a comment and a syscall identifier.
+
+\item
+The kernel returned an error to some RTNETLINK request.
+In this case \verb|ip| prints the error message, as it is output
+with \verb|perror(3)| prefixed with ``RTNETLINK answers:''.
+
+\end{itemize}
+
+All the operations are atomic, i.e.\
+if the \verb|ip| utility fails, it does not change anything
+in the system. One harmful exception is \verb|ip link| command
+(Sec.\ref{IP-LINK}, p.\pageref{IP-LINK}),
+which may change only some of the device parameters given
+on command line.
+
+It is difficult to list all the error messages (especially
+syntax errors). However, as a rule, their meaning is clear
+from the context of the command.
+
+The most common mistakes are:
+
+\begin{enumerate}
+\item Netlink is not configured in the kernel. The message is:
+\begin{verbatim}
+Cannot open netlink socket: Invalid value
+\end{verbatim}
+
+\item RTNETLINK is not configured in the kernel. In this case
+one of the following messages may be printed, depending on the command:
+\begin{verbatim}
+Cannot talk to rtnetlink: Connection refused
+Cannot send dump request: Connection refused
+\end{verbatim}
+
+\item The \verb|CONFIG_IP_MULTIPLE_TABLES| option was not selected
+when configuring the kernel. In this case any attempt to use the
+\verb|ip| \verb|rule| command will fail, f.e.
+\begin{verbatim}
+kuznet@kaiser $ ip rule list
+RTNETLINK error: Invalid argument
+dump terminated
+\end{verbatim}
+
+\end{enumerate}
+
+
+\section{{\tt ip link} --- network device configuration}
+\label{IP-LINK}
+
+\paragraph{Object:} A \verb|link| is a network device and the corresponding
+commands display and change the state of devices.
+
+\paragraph{Commands:} \verb|set| and \verb|show| (or \verb|list|).
+
+\subsection{{\tt ip link set} --- change device attributes}
+
+\paragraph{Abbreviations:} \verb|set|, \verb|s|.
+
+\paragraph{Arguments:}
+
+\begin{itemize}
+\item \verb|dev NAME| (default)
+
+--- \verb|NAME| specifies the network device on which to operate.
+
+\item \verb|up| and \verb|down|
+
+--- change the state of the device to \verb|UP| or \verb|DOWN|.
+
+\item \verb|arp on| or \verb|arp off|
+
+--- change the \verb|NOARP| flag on the device.
+
+\begin{NB}
+This operation is {\em not allowed\/} if the device is in state \verb|UP|.
+Though neither the \verb|ip| utility nor the kernel check for this condition.
+You can get unpredictable results changing this flag while the
+device is running.
+\end{NB}
+
+\item \verb|multicast on| or \verb|multicast off|
+
+--- change the \verb|MULTICAST| flag on the device.
+
+\item \verb|dynamic on| or \verb|dynamic off|
+
+--- change the \verb|DYNAMIC| flag on the device.
+
+\item \verb|name NAME|
+
+--- change the name of the device. This operation is not
+recommended if the device is running or has some addresses
+already configured.
+
+\item \verb|txqueuelen NUMBER| or \verb|txqlen NUMBER|
+
+--- change the transmit queue length of the device.
+
+\item \verb|mtu NUMBER|
+
+--- change the MTU of the device.
+
+\item \verb|address LLADDRESS|
+
+--- change the station address of the interface.
+
+\item \verb|broadcast LLADDRESS|, \verb|brd LLADDRESS| or \verb|peer LLADDRESS|
+
+--- change the link layer broadcast address or the peer address when
+the interface is \verb|POINTOPOINT|.
+
+\vskip 1mm
+\begin{NB}
+For most devices (f.e.\ for Ethernet) changing the link layer
+broadcast address will break networking.
+Do not use it, if you do not understand what this operation really does.
+\end{NB}
+
+\item \verb|netns PID|
+
+--- move the device to the network namespace associated with the process PID.
+
+\end{itemize}
+
+\vskip 1mm
+\begin{NB}
+The \verb|PROMISC| and \verb|ALLMULTI| flags are considered
+obsolete and should not be changed administratively, though
+the {\tt ip} utility will allow that.
+\end{NB}
+
+\paragraph{Warning:} If multiple parameter changes are requested,
+\verb|ip| aborts immediately after any of the changes have failed.
+This is the only case when \verb|ip| can move the system to
+an unpredictable state. The solution is to avoid changing
+several parameters with one {\tt ip link set} call.
+
+\paragraph{Examples:}
+\begin{itemize}
+\item \verb|ip link set dummy address 00:00:00:00:00:01|
+
+--- change the station address of the interface \verb|dummy|.
+
+\item \verb|ip link set dummy up|
+
+--- start the interface \verb|dummy|.
+
+\end{itemize}
+
+
+\subsection{{\tt ip link show} --- display device attributes}
+\label{IP-LINK-SHOW}
+
+\paragraph{Abbreviations:} \verb|show|, \verb|list|, \verb|lst|, \verb|sh|, \verb|ls|,
+\verb|l|.
+
+\paragraph{Arguments:}
+\begin{itemize}
+\item \verb|dev NAME| (default)
+
+--- \verb|NAME| specifies the network device to show.
+If this argument is omitted all devices are listed.
+
+\item \verb|up|
+
+--- only display running interfaces.
+
+\end{itemize}
+
+
+\paragraph{Output format:}
+
+\begin{verbatim}
+kuznet@alisa:~ $ ip link ls eth0
+3: eth0: <BROADCAST,MULTICAST,UP> mtu 1500 qdisc cbq qlen 100
+ link/ether 00:a0:cc:66:18:78 brd ff:ff:ff:ff:ff:ff
+kuznet@alisa:~ $ ip link ls sit0
+5: sit0@NONE: <NOARP,UP> mtu 1480 qdisc noqueue
+ link/sit 0.0.0.0 brd 0.0.0.0
+kuznet@alisa:~ $ ip link ls dummy
+2: dummy: <BROADCAST,NOARP> mtu 1500 qdisc noop
+ link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff
+kuznet@alisa:~ $
+\end{verbatim}
+
+
+The number before each colon is an {\em interface index\/} or {\em ifindex\/}.
+This number uniquely identifies the interface. This is followed by the {\em interface name\/}
+(\verb|eth0|, \verb|sit0| etc.). The interface name is also
+unique at every given moment. However, the interface may disappear from the
+list (f.e.\ when the corresponding driver module is unloaded) and another
+one with the same name may be created later. Besides that,
+the administrator may change the name of any device with
+\verb|ip| \verb|link| \verb|set| \verb|name|
+to make it more intelligible.
+
+The interface name may have another name or \verb|NONE| appended
+after the \verb|@| sign. This means that this device is bound to some other
+device,
+i.e.\ packets send through it are encapsulated and sent via the ``master''
+device. If the name is \verb|NONE|, the master is unknown.
+
+Then we see the interface {\em mtu\/} (``maximal transfer unit''). This determines
+the maximal size of data which can be sent as a single packet over this interface.
+
+{\em qdisc\/} (``queuing discipline'') shows the queuing algorithm used
+on the interface. Particularly, \verb|noqueue| means that this interface
+does not queue anything and \verb|noop| means that the interface is in blackhole
+mode i.e.\ all packets sent to it are immediately discarded.
+{\em qlen\/} is the default transmit queue length of the device measured
+in packets.
+
+The interface flags are summarized in the angle brackets.
+
+\begin{itemize}
+\item \verb|UP| --- the device is turned on. It is ready to accept
+packets for transmission and it may inject into the kernel packets received
+from other nodes on the network.
+
+\item \verb|LOOPBACK| --- the interface does not communicate with other
+hosts. All packets sent through it will be returned
+and nothing but bounced packets can be received.
+
+\item \verb|BROADCAST| --- the device has the facility to send packets
+to all hosts sharing the same link. A typical example is an Ethernet link.
+
+\item \verb|POINTOPOINT| --- the link has only two ends with one node
+attached to each end. All packets sent to this link will reach the peer
+and all packets received by us came from this single peer.
+
+If neither \verb|LOOPBACK| nor \verb|BROADCAST| nor \verb|POINTOPOINT|
+are set, the interface is assumed to be NMBA (Non-Broadcast Multi-Access).
+This is the most generic type of device and the most complicated one, because
+the host attached to a NBMA link has no means to send to anyone
+without additionally configured information.
+
+\item \verb|MULTICAST| --- is an advisory flag indicating that the interface
+is aware of multicasting i.e.\ sending packets to some subset of neighbouring
+nodes. Broadcasting is a particular case of multicasting, where the multicast
+group consists of all nodes on the link. It is important to emphasize
+that software {\em must not\/} interpret the absence of this flag as the inability
+to use multicasting on this interface. Any \verb|POINTOPOINT| and
+\verb|BROADCAST| link is multicasting by definition, because we have
+direct access to all the neighbours and, hence, to any part of them.
+Certainly, the use of high bandwidth multicast transfers is not recommended
+on broadcast-only links because of high expense, but it is not strictly
+prohibited.
+
+\item \verb|PROMISC| --- the device listens to and feeds to the kernel all
+traffic on the link even if it is not destined for us, not broadcasted
+and not destined for a multicast group of which we are member. Usually
+this mode exists only on broadcast links and is used by bridges and for network
+monitoring.
+
+\item \verb|ALLMULTI| --- the device receives all multicast packets
+wandering on the link. This mode is used by multicast routers.
+
+\item \verb|NOARP| --- this flag is different from the other ones. It has
+no invariant value and its interpretation depends on the network protocols
+involved. As a rule, it indicates that the device needs no address
+resolution and that the software or hardware knows how to deliver packets
+without any help from the protocol stacks.
+
+\item \verb|DYNAMIC| --- is an advisory flag indicating that the interface is
+dynamically created and destroyed.
+
+\item \verb|SLAVE| --- this interface is bonded to some other interfaces
+to share link capacities.
+
+\end{itemize}
+
+\vskip 1mm
+\begin{NB}
+There are other flags but they are either obsolete (\verb|NOTRAILERS|)
+or not implemented (\verb|DEBUG|) or specific to some devices
+(\verb|MASTER|, \verb|AUTOMEDIA| and \verb|PORTSEL|). We do not discuss
+them here.
+\end{NB}
+
+
+The second line contains information on the link layer addresses
+associated with the device. The first word (\verb|ether|, \verb|sit|)
+defines the interface hardware type. This type determines the format and semantics
+of the addresses and is logically part of the address.
+The default format of the station address and the broadcast address
+(or the peer address for pointopoint links) is a
+sequence of hexadecimal bytes separated by colons, but some link
+types may have their natural address format, f.e.\ addresses
+of tunnels over IP are printed as dotted-quad IP addresses.
+
+\vskip 1mm
+\begin{NB}
+ NBMA links have no well-defined broadcast or peer address,
+ however this field may contain useful information, f.e.\
+ about the address of broadcast relay or about the address of the ARP server.
+\end{NB}
+\begin{NB}
+Multicast addresses are not shown by this command, see
+\verb|ip maddr ls| in~Sec.\ref{IP-MADDR} (p.\pageref{IP-MADDR} of this
+document).
+\end{NB}
+
+
+\paragraph{Statistics:} With the \verb|-statistics| option, \verb|ip| also
+prints interface statistics:
+
+\begin{verbatim}
+kuznet@alisa:~ $ ip -s link ls eth0
+3: eth0: <BROADCAST,MULTICAST,UP> mtu 1500 qdisc cbq qlen 100
+ link/ether 00:a0:cc:66:18:78 brd ff:ff:ff:ff:ff:ff
+ RX: bytes packets errors dropped overrun mcast
+ 2449949362 2786187 0 0 0 0
+ TX: bytes packets errors dropped carrier collsns
+ 178558497 1783945 332 0 332 35172
+kuznet@alisa:~ $
+\end{verbatim}
+\verb|RX:| and \verb|TX:| lines summarize receiver and transmitter
+statistics. They contain:
+\begin{itemize}
+\item \verb|bytes| --- the total number of bytes received or transmitted
+on the interface. This number wraps when the maximal length of the data type
+natural for the architecture is exceeded, so continuous monitoring requires
+a user level daemon snapping it periodically.
+\item \verb|packets| --- the total number of packets received or transmitted
+on the interface.
+\item \verb|errors| --- the total number of receiver or transmitter errors.
+\item \verb|dropped| --- the total number of packets dropped due to lack
+of resources.
+\item \verb|overrun| --- the total number of receiver overruns resulting
+in dropped packets. As a rule, if the interface is overrun, it means
+serious problems in the kernel or that your machine is too slow
+for this interface.
+\item \verb|mcast| --- the total number of received multicast packets. This option
+is only supported by a few devices.
+\item \verb|carrier| --- total number of link media failures f.e.\ because
+of lost carrier.
+\item \verb|collsns| --- the total number of collision events
+on Ethernet-like media. This number may have a different sense on other
+link types.
+\item \verb|compressed| --- the total number of compressed packets. This is
+available only for links using VJ header compression.
+\end{itemize}
+
+
+If the \verb|-s| option is entered twice or more,
+\verb|ip| prints more detailed statistics on receiver
+and transmitter errors.
+
+\begin{verbatim}
+kuznet@alisa:~ $ ip -s -s link ls eth0
+3: eth0: <BROADCAST,MULTICAST,UP> mtu 1500 qdisc cbq qlen 100
+ link/ether 00:a0:cc:66:18:78 brd ff:ff:ff:ff:ff:ff
+ RX: bytes packets errors dropped overrun mcast
+ 2449949362 2786187 0 0 0 0
+ RX errors: length crc frame fifo missed
+ 0 0 0 0 0
+ TX: bytes packets errors dropped carrier collsns
+ 178558497 1783945 332 0 332 35172
+ TX errors: aborted fifo window heartbeat
+ 0 0 0 332
+kuznet@alisa:~ $
+\end{verbatim}
+These error names are pure Ethernetisms. Other devices
+may have non zero values in these fields but they may be
+interpreted differently.
+
+
+\section{{\tt ip address} --- protocol address management}
+
+\paragraph{Abbreviations:} \verb|address|, \verb|addr|, \verb|a|.
+
+\paragraph{Object:} The \verb|address| is a protocol (IP or IPv6) address attached
+to a network device. Each device must have at least one address
+to use the corresponding protocol. It is possible to have several
+different addresses attached to one device. These addresses are not
+discriminated, so that the term {\em alias\/} is not quite appropriate
+for them and we do not use it in this document.
+
+The \verb|ip addr| command displays addresses and their properties,
+adds new addresses and deletes old ones.
+
+\paragraph{Commands:} \verb|add|, \verb|delete|, \verb|flush| and \verb|show|
+(or \verb|list|).
+
+
+\subsection{{\tt ip address add} --- add a new protocol address}
+\label{IP-ADDR-ADD}
+
+\paragraph{Abbreviations:} \verb|add|, \verb|a|.
+
+\paragraph{Arguments:}
+
+\begin{itemize}
+\item \verb|dev NAME|
+
+\noindent--- the name of the device to add the address to.
+
+\item \verb|local ADDRESS| (default)
+
+--- the address of the interface. The format of the address depends
+on the protocol. It is a dotted quad for IP and a sequence of hexadecimal halfwords
+separated by colons for IPv6. The \verb|ADDRESS| may be followed by
+a slash and a decimal number which encodes the network prefix length.
+
+
+\item \verb|peer ADDRESS|
+
+--- the address of the remote endpoint for pointopoint interfaces.
+Again, the \verb|ADDRESS| may be followed by a slash and a decimal number,
+encoding the network prefix length. If a peer address is specified,
+the local address {\em cannot\/} have a prefix length. The network prefix is associated
+with the peer rather than with the local address.
+
+
+\item \verb|broadcast ADDRESS|
+
+--- the broadcast address on the interface.
+
+It is possible to use the special symbols \verb|'+'| and \verb|'-'|
+instead of the broadcast address. In this case, the broadcast address
+is derived by setting/resetting the host bits of the interface prefix.
+
+\vskip 1mm
+\begin{NB}
+Unlike \verb|ifconfig|, the \verb|ip| utility {\em does not\/} set any broadcast
+address unless explicitly requested.
+\end{NB}
+
+
+\item \verb|label NAME|
+
+--- Each address may be tagged with a label string.
+In order to preserve compatibility with Linux-2.0 net aliases,
+this string must coincide with the name of the device or must be prefixed
+with the device name followed by colon.
+
+
+\item \verb|scope SCOPE_VALUE|
+
+--- the scope of the area where this address is valid.
+The available scopes are listed in file \verb|/etc/iproute2/rt_scopes|.
+Predefined scope values are:
+
+ \begin{itemize}
+ \item \verb|global| --- the address is globally valid.
+ \item \verb|site| --- (IPv6 only) the address is site local,
+ i.e.\ it is valid inside this site.
+ \item \verb|link| --- the address is link local, i.e.\
+ it is valid only on this device.
+ \item \verb|host| --- the address is valid only inside this host.
+ \end{itemize}
+
+Appendix~\ref{ADDR-SEL} (p.\pageref{ADDR-SEL} of this document)
+contains more details on address scopes.
+
+\end{itemize}
+
+\paragraph{Examples:}
+\begin{itemize}
+\item \verb|ip addr add 127.0.0.1/8 dev lo brd + scope host|
+
+--- add the usual loopback address to the loopback device.
+
+\item \verb|ip addr add 10.0.0.1/24 brd + dev eth0 label eth0:Alias|
+
+--- add the address 10.0.0.1 with prefix length 24 (i.e.\ netmask
+\verb|255.255.255.0|), standard broadcast and label \verb|eth0:Alias|
+to the interface \verb|eth0|.
+\end{itemize}
+
+
+\subsection{{\tt ip address delete} --- delete a protocol address}
+
+\paragraph{Abbreviations:} \verb|delete|, \verb|del|, \verb|d|.
+
+\paragraph{Arguments:} coincide with the arguments of \verb|ip addr add|.
+The device name is a required argument. The rest are optional.
+If no arguments are given, the first address is deleted.
+
+\paragraph{Examples:}
+\begin{itemize}
+\item \verb|ip addr del 127.0.0.1/8 dev lo|
+
+--- deletes the loopback address from the loopback device.
+It would be best not to repeat this experiment.
+
+\item Disable IP on the interface \verb|eth0|:
+\begin{verbatim}
+ while ip -f inet addr del dev eth0; do
+ : nothing
+ done
+\end{verbatim}
+Another method to disable IP on an interface using {\tt ip addr flush}
+may be found in sec.\ref{IP-ADDR-FLUSH}, p.\pageref{IP-ADDR-FLUSH}.
+
+\end{itemize}
+
+
+\subsection{{\tt ip address show} --- display protocol addresses}
+
+\paragraph{Abbreviations:} \verb|show|, \verb|list|, \verb|lst|, \verb|sh|, \verb|ls|,
+\verb|l|.
+
+\paragraph{Arguments:}
+
+\begin{itemize}
+\item \verb|dev NAME| (default)
+
+--- the name of the device.
+
+\item \verb|scope SCOPE_VAL|
+
+--- only list addresses with this scope.
+
+\item \verb|to PREFIX|
+
+--- only list addresses matching this prefix.
+
+\item \verb|label PATTERN|
+
+--- only list addresses with labels matching the \verb|PATTERN|.
+\verb|PATTERN| is a usual shell style pattern.
+
+
+\item \verb|dynamic| and \verb|permanent|
+
+--- (IPv6 only) only list addresses installed due to stateless
+address configuration or only list permanent (not dynamic) addresses.
+
+\item \verb|tentative|
+
+--- (IPv6 only) only list addresses which did not pass duplicate
+address detection.
+
+\item \verb|deprecated|
+
+--- (IPv6 only) only list deprecated addresses.
+
+
+\item \verb|primary| and \verb|secondary|
+
+--- only list primary (or secondary) addresses.
+
+\end{itemize}
+
+
+\paragraph{Output format:}
+
+\begin{verbatim}
+kuznet@alisa:~ $ ip addr ls eth0
+3: eth0: <BROADCAST,MULTICAST,UP> mtu 1500 qdisc cbq qlen 100
+ link/ether 00:a0:cc:66:18:78 brd ff:ff:ff:ff:ff:ff
+ inet 193.233.7.90/24 brd 193.233.7.255 scope global eth0
+ inet6 3ffe:2400:0:1:2a0:ccff:fe66:1878/64 scope global dynamic
+ valid_lft forever preferred_lft 604746sec
+ inet6 fe80::2a0:ccff:fe66:1878/10 scope link
+kuznet@alisa:~ $
+\end{verbatim}
+
+The first two lines coincide with the output of \verb|ip link ls|.
+It is natural to interpret link layer addresses
+as addresses of the protocol family \verb|AF_PACKET|.
+
+Then the list of IP and IPv6 addresses follows, accompanied by
+additional address attributes: scope value (see Sec.\ref{IP-ADDR-ADD},
+p.\pageref{IP-ADDR-ADD} above), flags and the address label.
+
+Address flags are set by the kernel and cannot be changed
+administratively. Currently, the following flags are defined:
+
+\begin{enumerate}
+\item \verb|secondary|
+
+--- the address is not used when selecting the default source address
+of outgoing packets (Cf.\ Appendix~\ref{ADDR-SEL}, p.\pageref{ADDR-SEL}.).
+An IP address becomes secondary if another address with the same
+prefix bits already exists. The first address is primary.
+It is the leader of the group of all secondary addresses. When the leader
+is deleted, all secondaries are purged too.
+There is a tweak in \verb|/proc/sys/net/ipv4/conf/<dev>/promote_secondaries|
+which activate secondaries promotion when a primary is deleted.
+To permanently enable this feature on all devices add
+\verb|net.ipv4.conf.all.promote_secondaries=1| to \verb|/etc/sysctl.conf|.
+This tweak is available in linux 2.6.15 and later.
+
+
+\item \verb|dynamic|
+
+--- the address was created due to stateless autoconfiguration~\cite{RFC-ADDRCONF}.
+In this case the output also contains information on times, when
+the address is still valid. After \verb|preferred_lft| expires the address is
+moved to the deprecated state. After \verb|valid_lft| expires the address
+is finally invalidated.
+
+\item \verb|deprecated|
+
+--- the address is deprecated, i.e.\ it is still valid, but cannot
+be used by newly created connections.
+
+\item \verb|tentative|
+
+--- the address is not used because duplicate address detection~\cite{RFC-ADDRCONF}
+is still not complete or failed.
+
+\end{enumerate}
+
+
+\subsection{{\tt ip address flush} --- flush protocol addresses}
+\label{IP-ADDR-FLUSH}
+
+\paragraph{Abbreviations:} \verb|flush|, \verb|f|.
+
+\paragraph{Description:}This command flushes the protocol addresses
+selected by some criteria.
+
+\paragraph{Arguments:} This command has the same arguments as \verb|show|.
+The difference is that it does not run when no arguments are given.
+
+\paragraph{Warning:} This command (and other \verb|flush| commands
+described below) is pretty dangerous. If you make a mistake, it will
+not forgive it, but will cruelly purge all the addresses.
+
+\paragraph{Statistics:} With the \verb|-statistics| option, the command
+becomes verbose. It prints out the number of deleted addresses and the number
+of rounds made to flush the address list. If this option is given
+twice, \verb|ip addr flush| also dumps all the deleted addresses
+in the format described in the previous subsection.
+
+\paragraph{Example:} Delete all the addresses from the private network
+10.0.0.0/8:
+\begin{verbatim}
+netadm@amber:~ # ip -s -s a f to 10/8
+2: dummy inet 10.7.7.7/16 brd 10.7.255.255 scope global dummy
+3: eth0 inet 10.10.7.7/16 brd 10.10.255.255 scope global eth0
+4: eth1 inet 10.8.7.7/16 brd 10.8.255.255 scope global eth1
+
+*** Round 1, deleting 3 addresses ***
+*** Flush is complete after 1 round ***
+netadm@amber:~ #
+\end{verbatim}
+Another instructive example is disabling IP on all the Ethernets:
+\begin{verbatim}
+netadm@amber:~ # ip -4 addr flush label "eth*"
+\end{verbatim}
+And the last example shows how to flush all the IPv6 addresses
+acquired by the host from stateless address autoconfiguration
+after you enabled forwarding or disabled autoconfiguration.
+\begin{verbatim}
+netadm@amber:~ # ip -6 addr flush dynamic
+\end{verbatim}
+
+
+
+\section{{\tt ip neighbour} --- neighbour/arp tables management}
+
+\paragraph{Abbreviations:} \verb|neighbour|, \verb|neighbor|, \verb|neigh|,
+\verb|n|.
+
+\paragraph{Object:} \verb|neighbour| objects establish bindings between protocol
+addresses and link layer addresses for hosts sharing the same link.
+Neighbour entries are organized into tables. The IPv4 neighbour table
+is known by another name --- the ARP table.
+
+The corresponding commands display neighbour bindings
+and their properties, add new neighbour entries and delete old ones.
+
+\paragraph{Commands:} \verb|add|, \verb|change|, \verb|replace|,
+\verb|delete|, \verb|flush| and \verb|show| (or \verb|list|).
+
+\paragraph{See also:} Appendix~\ref{PROXY-NEIGH}, p.\pageref{PROXY-NEIGH}
+describes how to manage proxy ARP/NDISC with the \verb|ip| utility.
+
+
+\subsection{{\tt ip neighbour add} --- add a new neighbour entry\\
+ {\tt ip neighbour change} --- change an existing entry\\
+ {\tt ip neighbour replace} --- add a new entry or change an existing one}
+
+\paragraph{Abbreviations:} \verb|add|, \verb|a|; \verb|change|, \verb|chg|;
+\verb|replace|, \verb|repl|.
+
+\paragraph{Description:} These commands create new neighbour records
+or update existing ones.
+
+\paragraph{Arguments:}
+
+\begin{itemize}
+\item \verb|to ADDRESS| (default)
+
+--- the protocol address of the neighbour. It is either an IPv4 or IPv6 address.
+
+\item \verb|dev NAME|
+
+--- the interface to which this neighbour is attached.
+
+
+\item \verb|lladdr LLADDRESS|
+
+--- the link layer address of the neighbour. \verb|LLADDRESS| can also be
+\verb|null|.
+
+\item \verb|nud NUD_STATE|
+
+--- the state of the neighbour entry. \verb|nud| is an abbreviation for ``Neighbour
+Unreachability Detection''. The state can take one of the following values:
+
+\begin{enumerate}
+\item \verb|permanent| --- the neighbour entry is valid forever and can be only be removed
+administratively.
+\item \verb|noarp| --- the neighbour entry is valid. No attempts to validate
+this entry will be made but it can be removed when its lifetime expires.
+\item \verb|reachable| --- the neighbour entry is valid until the reachability
+timeout expires.
+\item \verb|stale| --- the neighbour entry is valid but suspicious.
+This option to \verb|ip neigh| does not change the neighbour state if
+it was valid and the address is not changed by this command.
+\end{enumerate}
+
+\end{itemize}
+
+\paragraph{Examples:}
+\begin{itemize}
+\item \verb|ip neigh add 10.0.0.3 lladdr 0:0:0:0:0:1 dev eth0 nud perm|
+
+--- add a permanent ARP entry for the neighbour 10.0.0.3 on the device \verb|eth0|.
+
+\item \verb|ip neigh chg 10.0.0.3 dev eth0 nud reachable|
+
+--- change its state to \verb|reachable|.
+\end{itemize}
+
+
+\subsection{{\tt ip neighbour delete} --- delete a neighbour entry}
+
+\paragraph{Abbreviations:} \verb|delete|, \verb|del|, \verb|d|.
+
+\paragraph{Description:} This command invalidates a neighbour entry.
+
+\paragraph{Arguments:} The arguments are the same as with \verb|ip neigh add|,
+except that \verb|lladdr| and \verb|nud| are ignored.
+
+
+\paragraph{Example:}
+\begin{itemize}
+\item \verb|ip neigh del 10.0.0.3 dev eth0|
+
+--- invalidate an ARP entry for the neighbour 10.0.0.3 on the device \verb|eth0|.
+
+\end{itemize}
+
+\begin{NB}
+ The deleted neighbour entry will not disappear from the tables
+ immediately. If it is in use it cannot be deleted until the last
+ client releases it. Otherwise it will be destroyed during
+ the next garbage collection.
+\end{NB}
+
+
+\paragraph{Warning:} Attempts to delete or manually change
+a \verb|noarp| entry created by the kernel may result in unpredictable behaviour.
+Particularly, the kernel may try to resolve this address even
+on a \verb|NOARP| interface or if the address is multicast or broadcast.
+
+
+\subsection{{\tt ip neighbour show} --- list neighbour entries}
+
+\paragraph{Abbreviations:} \verb|show|, \verb|list|, \verb|sh|, \verb|ls|.
+
+\paragraph{Description:}This commands displays neighbour tables.
+
+\paragraph{Arguments:}
+
+\begin{itemize}
+
+\item \verb|to ADDRESS| (default)
+
+--- the prefix selecting the neighbours to list.
+
+\item \verb|dev NAME|
+
+--- only list the neighbours attached to this device.
+
+\item \verb|unused|
+
+--- only list neighbours which are not currently in use.
+
+\item \verb|nud NUD_STATE|
+
+--- only list neighbour entries in this state. \verb|NUD_STATE| takes
+values listed below or the special value \verb|all| which means all states.
+This option may occur more than once. If this option is absent, \verb|ip|
+lists all entries except for \verb|none| and \verb|noarp|.
+
+\end{itemize}
+
+
+\paragraph{Output format:}
+
+\begin{verbatim}
+kuznet@alisa:~ $ ip neigh ls
+:: dev lo lladdr 00:00:00:00:00:00 nud noarp
+fe80::200:cff:fe76:3f85 dev eth0 lladdr 00:00:0c:76:3f:85 router \
+ nud stale
+0.0.0.0 dev lo lladdr 00:00:00:00:00:00 nud noarp
+193.233.7.254 dev eth0 lladdr 00:00:0c:76:3f:85 nud reachable
+193.233.7.85 dev eth0 lladdr 00:e0:1e:63:39:00 nud stale
+kuznet@alisa:~ $
+\end{verbatim}
+
+The first word of each line is the protocol address of the neighbour.
+Then the device name follows. The rest of the line describes the contents of
+the neighbour entry identified by the pair (device, address).
+
+\verb|lladdr| is the link layer address of the neighbour.
+
+\verb|nud| is the state of the ``neighbour unreachability detection'' machine
+for this entry. The detailed description of the neighbour
+state machine can be found in~\cite{RFC-NDISC}. Here is the full list
+of the states with short descriptions:
+
+\begin{enumerate}
+\item\verb|none| --- the state of the neighbour is void.
+\item\verb|incomplete| --- the neighbour is in the process of resolution.
+\item\verb|reachable| --- the neighbour is valid and apparently reachable.
+\item\verb|stale| --- the neighbour is valid, but is probably already
+unreachable, so the kernel will try to check it at the first transmission.
+\item\verb|delay| --- a packet has been sent to the stale neighbour and the kernel is waiting
+for confirmation.
+\item\verb|probe| --- the delay timer expired but no confirmation was received.
+The kernel has started to probe the neighbour with ARP/NDISC messages.
+\item\verb|failed| --- resolution has failed.
+\item\verb|noarp| --- the neighbour is valid. No attempts to check the entry
+will be made.
+\item\verb|permanent| --- it is a \verb|noarp| entry, but only the administrator
+may remove the entry from the neighbour table.
+\end{enumerate}
+
+The link layer address is valid in all states except for \verb|none|,
+\verb|failed| and \verb|incomplete|.
+
+IPv6 neighbours can be marked with the additional flag \verb|router|
+which means that the neighbour introduced itself as an IPv6 router~\cite{RFC-NDISC}.
+
+\paragraph{Statistics:} The \verb|-statistics| option displays some usage
+statistics, f.e.\
+
+\begin{verbatim}
+kuznet@alisa:~ $ ip -s n ls 193.233.7.254
+193.233.7.254 dev eth0 lladdr 00:00:0c:76:3f:85 ref 5 used 12/13/20 \
+ nud reachable
+kuznet@alisa:~ $
+\end{verbatim}
+
+Here \verb|ref| is the number of users of this entry
+and \verb|used| is a triplet of time intervals in seconds
+separated by slashes. In this case they show that:
+
+\begin{enumerate}
+\item the entry was used 12 seconds ago.
+\item the entry was confirmed 13 seconds ago.
+\item the entry was updated 20 seconds ago.
+\end{enumerate}
+
+\subsection{{\tt ip neighbour flush} --- flush neighbour entries}
+
+\paragraph{Abbreviations:} \verb|flush|, \verb|f|.
+
+\paragraph{Description:}This command flushes neighbour tables, selecting
+entries to flush by some criteria.
+
+\paragraph{Arguments:} This command has the same arguments as \verb|show|.
+The differences are that it does not run when no arguments are given,
+and that the default neighbour states to be flushed do not include
+\verb|permanent| and \verb|noarp|.
+
+
+\paragraph{Statistics:} With the \verb|-statistics| option, the command
+becomes verbose. It prints out the number of deleted neighbours and the number
+of rounds made to flush the neighbour table. If the option is given
+twice, \verb|ip neigh flush| also dumps all the deleted neighbours
+in the format described in the previous subsection.
+
+\paragraph{Example:}
+\begin{verbatim}
+netadm@alisa:~ # ip -s -s n f 193.233.7.254
+193.233.7.254 dev eth0 lladdr 00:00:0c:76:3f:85 ref 5 used 12/13/20 \
+ nud reachable
+
+*** Round 1, deleting 1 entries ***
+*** Flush is complete after 1 round ***
+netadm@alisa:~ #
+\end{verbatim}
+
+
+\section{{\tt ip route} --- routing table management}
+\label{IP-ROUTE}
+
+\paragraph{Abbreviations:} \verb|route|, \verb|ro|, \verb|r|.
+
+\paragraph{Object:} \verb|route| entries in the kernel routing tables keep
+information about paths to other networked nodes.
+
+Each route entry has a {\em key\/} consisting of a {\em prefix\/}
+(i.e.\ a pair containing a network address and the length of its mask) and,
+optionally, the TOS value. An IP packet matches the route if the highest
+bits of its destination address are equal to the route prefix at least
+up to the prefix length and if the TOS of the route is zero or equal to
+the TOS of the packet.
+
+If several routes match the packet, the following pruning rules
+are used to select the best one (see~\cite{RFC1812}):
+\begin{enumerate}
+\item The longest matching prefix is selected. All shorter ones
+are dropped.
+
+\item If the TOS of some route with the longest prefix is equal to the TOS
+of the packet, the routes with different TOS are dropped.
+
+If no exact TOS match was found and routes with TOS=0 exist,
+the rest of routes are pruned.
+
+Otherwise, the route lookup fails.
+
+\item If several routes remain after the previous steps, then
+the routes with the best preference values are selected.
+
+\item If we still have several routes, then the {\em first\/} of them
+is selected.
+
+\begin{NB}
+ Note the ambiguity of the last step. Unfortunately, Linux
+ historically allows such a bizarre situation. The sense of the
+word ``first'' depends on the order of route additions and it is practically
+impossible to maintain a bundle of such routes in this order.
+\end{NB}
+
+For simplicity we will limit ourselves to the case where such a situation
+is impossible and routes are uniquely identified by the triplet
+\{prefix, tos, preference\}. Actually, it is impossible to create
+non-unique routes with \verb|ip| commands described in this section.
+
+One useful exception to this rule is the default route on non-forwarding
+hosts. It is ``officially'' allowed to have several fallback routes
+when several routers are present on directly connected networks.
+In this case, Linux-2.2 makes ``dead gateway detection''~\cite{RFC1122}
+controlled by neighbour unreachability detection and by advice
+from transport protocols to select a working router, so the order
+of the routes is not essential. However, in this case,
+fiddling with default routes manually is not recommended. Use the Router Discovery
+protocol (see Appendix~\ref{EXAMPLE-SETUP}, p.\pageref{EXAMPLE-SETUP})
+instead. Actually, Linux-2.2 IPv6 does not give user level applications
+any access to default routes.
+\end{enumerate}
+
+Certainly, the steps above are not performed exactly
+in this sequence. Instead, the routing table in the kernel is kept
+in some data structure to achieve the final result
+with minimal cost. However, not depending on a particular
+routing algorithm implemented in the kernel, we can summarize
+the statements above as: a route is identified by the triplet
+\{prefix, tos, preference\}. This {\em key\/} lets us locate
+the route in the routing table.
+
+\paragraph{Route attributes:} Each route key refers to a routing
+information record containing
+the data required to deliver IP packets (f.e.\ output device and
+next hop router) and some optional attributes (f.e. the path MTU or
+the preferred source address when communicating with this destination).
+These attributes are described in the following subsection.
+
+\paragraph{Route types:} \label{IP-ROUTE-TYPES}
+It is important that the set
+of required and optional attributes depend on the route {\em type\/}.
+The most important route type
+is \verb|unicast|. It describes real paths to other hosts.
+As a rule, common routing tables contain only such routes. However,
+there are other types of routes with different semantics. The
+full list of types understood by Linux-2.2 is:
+\begin{itemize}
+\item \verb|unicast| --- the route entry describes real paths to the
+destinations covered by the route prefix.
+\item \verb|unreachable| --- these destinations are unreachable. Packets
+are discarded and the ICMP message {\em host unreachable\/} is generated.
+The local senders get an \verb|EHOSTUNREACH| error.
+\item \verb|blackhole| --- these destinations are unreachable. Packets
+are discarded silently. The local senders get an \verb|EINVAL| error.
+\item \verb|prohibit| --- these destinations are unreachable. Packets
+are discarded and the ICMP message {\em communication administratively
+prohibited\/} is generated. The local senders get an \verb|EACCES| error.
+\item \verb|local| --- the destinations are assigned to this
+host. The packets are looped back and delivered locally.
+\item \verb|broadcast| --- the destinations are broadcast addresses.
+The packets are sent as link broadcasts.
+\item \verb|throw| --- a special control route used together with policy
+rules (see sec.\ref{IP-RULE}, p.\pageref{IP-RULE}). If such a route is selected, lookup
+in this table is terminated pretending that no route was found.
+Without policy routing it is equivalent to the absence of the route in the routing
+table. The packets are dropped and the ICMP message {\em net unreachable\/}
+is generated. The local senders get an \verb|ENETUNREACH| error.
+\item \verb|nat| --- a special NAT route. Destinations covered by the prefix
+are considered to be dummy (or external) addresses which require translation
+to real (or internal) ones before forwarding. The addresses to translate to
+are selected with the attribute \verb|via|. More about NAT is
+in Appendix~\ref{ROUTE-NAT}, p.\pageref{ROUTE-NAT}.
+\item \verb|anycast| --- ({\em not implemented\/}) the destinations are
+{\em anycast\/} addresses assigned to this host. They are mainly equivalent
+to \verb|local| with one difference: such addresses are invalid when used
+as the source address of any packet.
+\item \verb|multicast| --- a special type used for multicast routing.
+It is not present in normal routing tables.
+\end{itemize}
+
+\paragraph{Route tables:} Linux-2.2 can pack routes into several routing
+tables identified by a number in the range from 1 to 255 or by
+name from the file \verb|/etc/iproute2/rt_tables|. By default all normal
+routes are inserted into the \verb|main| table (ID 254) and the kernel only uses
+this table when calculating routes.
+
+Actually, one other table always exists, which is invisible but
+even more important. It is the \verb|local| table (ID 255). This table
+consists of routes for local and broadcast addresses. The kernel maintains
+this table automatically and the administrator usually need not modify it
+or even look at it.
+
+The multiple routing tables enter the game when {\em policy routing\/}
+is used. See sec.\ref{IP-RULE}, p.\pageref{IP-RULE}.
+In this case, the table identifier effectively becomes
+one more parameter, which should be added to the triplet
+\{prefix, tos, preference\} to uniquely identify the route.
+
+
+\subsection{{\tt ip route add} --- add a new route\\
+ {\tt ip route change} --- change a route\\
+ {\tt ip route replace} --- change a route or add a new one}
+\label{IP-ROUTE-ADD}
+
+\paragraph{Abbreviations:} \verb|add|, \verb|a|; \verb|change|, \verb|chg|;
+ \verb|replace|, \verb|repl|.
+
+
+\paragraph{Arguments:}
+\begin{itemize}
+\item \verb|to PREFIX| or \verb|to TYPE PREFIX| (default)
+
+--- the destination prefix of the route. If \verb|TYPE| is omitted,
+\verb|ip| assumes type \verb|unicast|. Other values of \verb|TYPE|
+are listed above. \verb|PREFIX| is an IP or IPv6 address optionally followed
+by a slash and the prefix length. If the length of the prefix is missing,
+\verb|ip| assumes a full-length host route. There is also a special
+\verb|PREFIX| --- \verb|default| --- which is equivalent to IP \verb|0/0| or
+to IPv6 \verb|::/0|.
+
+\item \verb|tos TOS| or \verb|dsfield TOS|
+
+--- the Type Of Service (TOS) key. This key has no associated mask and
+the longest match is understood as: First, compare the TOS
+of the route and of the packet. If they are not equal, then the packet
+may still match a route with a zero TOS. \verb|TOS| is either an 8 bit hexadecimal
+number or an identifier from {\tt /etc/iproute2/rt\_dsfield}.
+
+
+\item \verb|metric NUMBER| or \verb|preference NUMBER|
+
+--- the preference value of the route. \verb|NUMBER| is an arbitrary 32bit number.
+
+\item \verb|table TABLEID|
+
+--- the table to add this route to.
+\verb|TABLEID| may be a number or a string from the file
+\verb|/etc/iproute2/rt_tables|. If this parameter is omitted,
+\verb|ip| assumes the \verb|main| table, with the exception of
+\verb|local|, \verb|broadcast| and \verb|nat| routes, which are
+put into the \verb|local| table by default.
+
+\item \verb|dev NAME|
+
+--- the output device name.
+
+\item \verb|via ADDRESS|
+
+--- the address of the nexthop router. Actually, the sense of this field depends
+on the route type. For normal \verb|unicast| routes it is either the true nexthop
+router or, if it is a direct route installed in BSD compatibility mode,
+it can be a local address of the interface.
+For NAT routes it is the first address of the block of translated IP destinations.
+
+\item \verb|src ADDRESS|
+
+--- the source address to prefer when sending to the destinations
+covered by the route prefix.
+
+\item \verb|realm REALMID|
+
+--- the realm to which this route is assigned.
+\verb|REALMID| may be a number or a string from the file
+\verb|/etc/iproute2/rt_realms|. Sec.\ref{RT-REALMS} (p.\pageref{RT-REALMS})
+contains more information on realms.
+
+\item \verb|mtu MTU| or \verb|mtu lock MTU|
+
+--- the MTU along the path to the destination. If the modifier \verb|lock| is
+not used, the MTU may be updated by the kernel due to Path MTU Discovery.
+If the modifier \verb|lock| is used, no path MTU discovery will be tried,
+all packets will be sent without the DF bit in IPv4 case
+or fragmented to MTU for IPv6.
+
+\item \verb|window NUMBER|
+
+--- the maximal window for TCP to advertise to these destinations,
+measured in bytes. It limits maximal data bursts that our TCP
+peers are allowed to send to us.
+
+\item \verb|rtt NUMBER|
+
+--- the initial RTT (``Round Trip Time'') estimate.
+
+
+\item \verb|rttvar NUMBER|
+
+--- \threeonly the initial RTT variance estimate.
+
+
+\item \verb|ssthresh NUMBER|
+
+--- \threeonly an estimate for the initial slow start threshold.
+
+
+\item \verb|cwnd NUMBER|
+
+--- \threeonly the clamp for congestion window. It is ignored if the \verb|lock|
+ flag is not used.
+
+
+\item \verb|advmss NUMBER|
+
+--- \threeonly the MSS (``Maximal Segment Size'') to advertise to these
+ destinations when establishing TCP connections. If it is not given,
+ Linux uses a default value calculated from the first hop device MTU.
+
+\begin{NB}
+ If the path to these destination is asymmetric, this guess may be wrong.
+\end{NB}
+
+\item \verb|reordering NUMBER|
+
+--- \threeonly Maximal reordering on the path to this destination.
+ If it is not given, Linux uses the value selected with \verb|sysctl|
+ variable \verb|net/ipv4/tcp_reordering|.
+
+\item \verb|hoplimit NUMBER|
+
+--- [2.5.74+ only] Maximum number of hops on the path to this destination.
+ The default is the value selected with the \verb|sysctl| variable
+ \verb|net/ipv4/ip_default_ttl|.
+
+\item \verb|initcwnd NUMBER|
+--- [2.5.70+ only] Initial congestion window size for connections to
+ this destination. Actual window size is this value multiplied by the
+ MSS (``Maximal Segment Size'') for same connection. The default is
+ zero, meaning to use the values specified in~\cite{RFC2414}.
+
++\item \verb|initrwnd NUMBER|
+
++--- [2.6.33+ only] Initial receive window size for connections to
++ this destination. The actual window size is this value multiplied
++ by the MSS (''Maximal Segment Size'') of the connection. The default
++ value is zero, meaning to use Slow Start value.
+
+\item \verb|nexthop NEXTHOP|
+
+--- the nexthop of a multipath route. \verb|NEXTHOP| is a complex value
+with its own syntax similar to the top level argument lists:
+\begin{itemize}
+\item \verb|via ADDRESS| is the nexthop router.
+\item \verb|dev NAME| is the output device.
+\item \verb|weight NUMBER| is a weight for this element of a multipath
+route reflecting its relative bandwidth or quality.
+\end{itemize}
+
+\item \verb|scope SCOPE_VAL|
+
+--- the scope of the destinations covered by the route prefix.
+\verb|SCOPE_VAL| may be a number or a string from the file
+\verb|/etc/iproute2/rt_scopes|.
+If this parameter is omitted,
+\verb|ip| assumes scope \verb|global| for all gatewayed \verb|unicast|
+routes, scope \verb|link| for direct \verb|unicast| and \verb|broadcast| routes
+and scope \verb|host| for \verb|local| routes.
+
+\item \verb|protocol RTPROTO|
+
+--- the routing protocol identifier of this route.
+\verb|RTPROTO| may be a number or a string from the file
+\verb|/etc/iproute2/rt_protos|. If the routing protocol ID is
+not given, \verb|ip| assumes protocol \verb|boot| (i.e.\
+it assumes the route was added by someone who doesn't
+understand what they are doing). Several protocol values have a fixed interpretation.
+Namely:
+\begin{itemize}
+\item \verb|redirect| --- the route was installed due to an ICMP redirect.
+\item \verb|kernel| --- the route was installed by the kernel during
+autoconfiguration.
+\item \verb|boot| --- the route was installed during the bootup sequence.
+If a routing daemon starts, it will purge all of them.
+\item \verb|static| --- the route was installed by the administrator
+to override dynamic routing. Routing daemon will respect them
+and, probably, even advertise them to its peers.
+\item \verb|ra| --- the route was installed by Router Discovery protocol.
+\end{itemize}
+The rest of the values are not reserved and the administrator is free
+to assign (or not to assign) protocol tags. At least, routing
+daemons should take care of setting some unique protocol values,
+f.e.\ as they are assigned in \verb|rtnetlink.h| or in \verb|rt_protos|
+database.
+
+
+\item \verb|onlink|
+
+--- pretend that the nexthop is directly attached to this link,
+even if it does not match any interface prefix. One application of this
+option may be found in~\cite{IP-TUNNELS}.
+
+\item \verb|pref PREF|
+
+--- the IPv6 route preference.
+\verb|PREF| PREF is a string specifying the route preference as defined in
+RFC4191 for Router Discovery messages. Namely:
+\begin{itemize}
+\item \verb|low| --- the route has a lowest priority.
+\item \verb|medium| --- the route has a default priority.
+\item \verb|high| --- the route has a highest priority.
+\end{itemize}
+
+\end{itemize}
+
+
+\begin{NB}
+ Actually there are more commands: \verb|prepend| does the same
+ thing as classic \verb|route add|, i.e.\ adds a route, even if another
+ route to the same destination exists. Its opposite case is \verb|append|,
+ which adds the route to the end of the list. Avoid these
+ features.
+\end{NB}
+\begin{NB}
+ More sad news, IPv6 only understands the \verb|append| command correctly.
+ All the others are translated into \verb|append| commands. Certainly,
+ this will change in the future.
+\end{NB}
+
+\paragraph{Examples:}
+\begin{itemize}
+\item add a plain route to network 10.0.0/24 via gateway 193.233.7.65
+\begin{verbatim}
+ ip route add 10.0.0/24 via 193.233.7.65
+\end{verbatim}
+\item change it to a direct route via the \verb|dummy| device
+\begin{verbatim}
+ ip ro chg 10.0.0/24 dev dummy
+\end{verbatim}
+\item add a default multipath route splitting the load between \verb|ppp0|
+and \verb|ppp1|
+\begin{verbatim}
+ ip route add default scope global nexthop dev ppp0 \
+ nexthop dev ppp1
+\end{verbatim}
+Note the scope value. It is not necessary but it informs the kernel
+that this route is gatewayed rather than direct. Actually, if you
+know the addresses of remote endpoints it would be better to use the
+\verb|via| parameter.
+\item announce that the address 192.203.80.144 is not a real one, but
+should be translated to 193.233.7.83 before forwarding
+\begin{verbatim}
+ ip route add nat 192.203.80.144 via 193.233.7.83
+\end{verbatim}
+Backward translation is setup with policy rules described
+in the following section (sec.\ref{IP-RULE}, p.\pageref{IP-RULE}).
+\end{itemize}
+
+\subsection{{\tt ip route delete} --- delete a route}
+
+\paragraph{Abbreviations:} \verb|delete|, \verb|del|, \verb|d|.
+
+\paragraph{Arguments:} \verb|ip route del| has the same arguments as
+\verb|ip route add|, but their semantics are a bit different.
+
+Key values (\verb|to|, \verb|tos|, \verb|preference| and \verb|table|)
+select the route to delete. If optional attributes are present, \verb|ip|
+verifies that they coincide with the attributes of the route to delete.
+If no route with the given key and attributes was found, \verb|ip route del|
+fails.
+\begin{NB}
+Linux-2.0 had the option to delete a route selected only by prefix address,
+ignoring its length (i.e.\ netmask). This option no longer exists
+because it was ambiguous. However, look at {\tt ip route flush}
+(sec.\ref{IP-ROUTE-FLUSH}, p.\pageref{IP-ROUTE-FLUSH}) which
+provides similar and even richer functionality.
+\end{NB}
+
+\paragraph{Example:}
+\begin{itemize}
+\item delete the multipath route created by the command in previous subsection
+\begin{verbatim}
+ ip route del default scope global nexthop dev ppp0 \
+ nexthop dev ppp1
+\end{verbatim}
+\end{itemize}
+
+
+
+\subsection{{\tt ip route show} --- list routes}
+
+\paragraph{Abbreviations:} \verb|show|, \verb|list|, \verb|sh|, \verb|ls|, \verb|l|.
+
+\paragraph{Description:} the command displays the contents of the routing tables
+or the route(s) selected by some criteria.
+
+
+\paragraph{Arguments:}
+\begin{itemize}
+\item \verb|to SELECTOR| (default)
+
+--- only select routes from the given range of destinations. \verb|SELECTOR|
+consists of an optional modifier (\verb|root|, \verb|match| or \verb|exact|)
+and a prefix. \verb|root PREFIX| selects routes with prefixes not shorter
+than \verb|PREFIX|. F.e.\ \verb|root 0/0| selects the entire routing table.
+\verb|match PREFIX| selects routes with prefixes not longer than
+\verb|PREFIX|. F.e.\ \verb|match 10.0/16| selects \verb|10.0/16|,
+\verb|10/8| and \verb|0/0|, but it does not select \verb|10.1/16| and
+\verb|10.0.0/24|. And \verb|exact PREFIX| (or just \verb|PREFIX|)
+selects routes with this exact prefix. If neither of these options
+are present, \verb|ip| assumes \verb|root 0/0| i.e.\ it lists the entire table.
+
+
+\item \verb|tos TOS| or \verb|dsfield TOS|
+
+ --- only select routes with the given TOS.
+
+
+\item \verb|table TABLEID|
+
+ --- show the routes from this table(s). The default setting is to show
+\verb|table| \verb|main|. \verb|TABLEID| may either be the ID of a real table
+or one of the special values:
+ \begin{itemize}
+ \item \verb|all| --- list all of the tables.
+ \item \verb|cache| --- dump the routing cache.
+ \end{itemize}
+\begin{NB}
+ IPv6 has a single table. However, splitting it into \verb|main|, \verb|local|
+ and \verb|cache| is emulated by the \verb|ip| utility.
+\end{NB}
+
+\item \verb|cloned| or \verb|cached|
+
+--- list cloned routes i.e.\ routes which were dynamically forked from
+other routes because some route attribute (f.e.\ MTU) was updated.
+Actually, it is equivalent to \verb|table cache|.
+
+\item \verb|from SELECTOR|
+
+--- the same syntax as for \verb|to|, but it binds the source address range
+rather than destinations. Note that the \verb|from| option only works with
+cloned routes.
+
+\item \verb|protocol RTPROTO|
+
+--- only list routes of this protocol.
+
+
+\item \verb|scope SCOPE_VAL|
+
+--- only list routes with this scope.
+
+\item \verb|type TYPE|
+
+--- only list routes of this type.
+
+\item \verb|dev NAME|
+
+--- only list routes going via this device.
+
+\item \verb|via PREFIX|
+
+--- only list routes going via the nexthop routers selected by \verb|PREFIX|.
+
+\item \verb|src PREFIX|
+
+--- only list routes with preferred source addresses selected
+by \verb|PREFIX|.
+
+\item \verb|realm REALMID| or \verb|realms FROMREALM/TOREALM|
+
+--- only list routes with these realms.
+
+\end{itemize}
+
+\paragraph{Examples:} Let us count routes of protocol \verb|gated/bgp|
+on a router:
+\begin{verbatim}
+kuznet@amber:~ $ ip ro ls proto gated/bgp | wc
+ 1413 9891 79010
+kuznet@amber:~ $
+\end{verbatim}
+To count the size of the routing cache, we have to use the \verb|-o| option
+because cached attributes can take more than one line of output:
+\begin{verbatim}
+kuznet@amber:~ $ ip -o ro ls cloned | wc
+ 159 2543 18707
+kuznet@amber:~ $
+\end{verbatim}
+
+
+\paragraph{Output format:} The output of this command consists
+of per route records separated by line feeds.
+However, some records may consist
+of more than one line: particularly, this is the case when the route
+is cloned or you requested additional statistics. If the
+\verb|-o| option was given, then line feeds separating lines inside
+records are replaced with the backslash sign.
+
+The output has the same syntax as arguments given to {\tt ip route add},
+so that it can be understood easily. F.e.\
+\begin{verbatim}
+kuznet@amber:~ $ ip ro ls 193.233.7/24
+193.233.7.0/24 dev eth0 proto gated/conn scope link \
+ src 193.233.7.65 realms inr.ac
+kuznet@amber:~ $
+\end{verbatim}
+
+If you list cloned entries, the output contains other attributes which
+are evaluated during route calculation and updated during route
+lifetime. An example of the output is:
+\begin{verbatim}
+kuznet@amber:~ $ ip ro ls 193.233.7.82 tab cache
+193.233.7.82 from 193.233.7.82 dev eth0 src 193.233.7.65 \
+ realms inr.ac/inr.ac
+ cache <src-direct,redirect> mtu 1500 rtt 300 iif eth0
+193.233.7.82 dev eth0 src 193.233.7.65 realms inr.ac
+ cache mtu 1500 rtt 300
+kuznet@amber:~ $
+\end{verbatim}
+\begin{NB}
+ \label{NB-strange-route}
+ The route looks a bit strange, doesn't it? Did you notice that
+ it is a path from 193.233.7.82 back to 193.233.82? Well, you will
+ see in the section on \verb|ip route get| (p.\pageref{NB-nature-of-strangeness})
+ how it appeared.
+\end{NB}
+The second line, starting with the word \verb|cache|, shows
+additional attributes which normal routes do not possess.
+Cached flags are summarized in angle brackets:
+\begin{itemize}
+\item \verb|local| --- packets are delivered locally.
+It stands for loopback unicast routes, for broadcast routes
+and for multicast routes, if this host is a member of the corresponding
+group.
+
+\item \verb|reject| --- the path is bad. Any attempt to use it results
+in an error. See attribute \verb|error| below (p.\pageref{IP-ROUTE-GET-error}).
+
+\item \verb|mc| --- the destination is multicast.
+
+\item \verb|brd| --- the destination is broadcast.
+
+\item \verb|src-direct| --- the source is on a directly connected
+interface.
+
+\item \verb|redirected| --- the route was created by an ICMP Redirect.
+
+\item \verb|redirect| --- packets going via this route will
+trigger an ICMP redirect.
+
+\item \verb|fastroute| --- the route is eligible to be used for fastroute.
+
+\item \verb|equalize| --- make packet by packet randomization
+along this path.
+
+\item \verb|dst-nat| --- the destination address requires translation.
+
+\item \verb|src-nat| --- the source address requires translation.
+
+\item \verb|masq| --- the source address requires masquerading.
+This feature disappeared in linux-2.4.
+
+\item \verb|notify| --- ({\em not implemented}) change/deletion
+of this route will trigger RTNETLINK notification.
+\end{itemize}
+
+Then some optional attributes follow:
+\begin{itemize}
+\item \verb|error| --- on \verb|reject| routes it is error code
+returned to local senders when they try to use this route.
+These error codes are translated into ICMP error codes, sent to remote
+senders, according to the rules described above in the subsection
+devoted to route types (p.\pageref{IP-ROUTE-TYPES}).
+\label{IP-ROUTE-GET-error}
+
+\item \verb|expires| --- this entry will expire after this timeout.
+
+\item \verb|iif| --- the packets for this path are expected to arrive
+on this interface.
+\end{itemize}
+
+\paragraph{Statistics:} With the \verb|-statistics| option, more
+information about this route is shown:
+\begin{itemize}
+\item \verb|users| --- the number of users of this entry.
+\item \verb|age| --- shows when this route was last used.
+\item \verb|used| --- the number of lookups of this route since its creation.
+\end{itemize}
+
+\subsection{{\tt ip route save} -- save routing tables}
+\label{IP-ROUTE-SAVE}
+
+\paragraph{Description:} this command saves the contents of the routing
+tables or the route(s) selected by some criteria to standard output.
+
+\paragraph{Arguments:} \verb|ip route save| has the same arguments as
+\verb|ip route show|.
+
+\paragraph{Example:} This saves all the routes to the {\tt saved\_routes}
+file:
+\begin{verbatim}
+dan@caffeine:~ # ip route save > saved_routes
+\end{verbatim}
+
+\paragraph{Output format:} The format of the data stream provided by
+\verb|ip route save| is that of \verb|rtnetlink|. See
+\verb|rtnetlink(7)| for more information.
+
+\subsection{{\tt ip route restore} -- restore routing tables}
+\label{IP-ROUTE-RESTORE}
+
+\paragraph{Description:} this command restores the contents of the routing
+tables according to a data stream as provided by \verb|ip route save| via
+standard input. Note that any routes already in the table are left unchanged.
+Any routes in the input stream that already exist in the tables are ignored.
+
+\paragraph{Arguments:} This command takes no arguments.
+
+\paragraph{Example:} This restores all routes that were saved to the
+{\tt saved\_routes} file:
+
+\begin{verbatim}
+dan@caffeine:~ # ip route restore < saved_routes
+\end{verbatim}
+
+\subsection{{\tt ip route flush} --- flush routing tables}
+\label{IP-ROUTE-FLUSH}
+
+\paragraph{Abbreviations:} \verb|flush|, \verb|f|.
+
+\paragraph{Description:} this command flushes routes selected
+by some criteria.
+
+\paragraph{Arguments:} the arguments have the same syntax and semantics
+as the arguments of \verb|ip route show|, but routing tables are not
+listed but purged. The only difference is the default action: \verb|show|
+dumps all the IP main routing table but \verb|flush| prints the helper page.
+The reason for this difference does not require any explanation, does it?
+
+
+\paragraph{Statistics:} With the \verb|-statistics| option, the command
+becomes verbose. It prints out the number of deleted routes and the number
+of rounds made to flush the routing table. If the option is given
+twice, \verb|ip route flush| also dumps all the deleted routes
+in the format described in the previous subsection.
+
+\paragraph{Examples:} The first example flushes all the
+gatewayed routes from the main table (f.e.\ after a routing daemon crash).
+\begin{verbatim}
+netadm@amber:~ # ip -4 ro flush scope global type unicast
+\end{verbatim}
+This option deserves to be put into a scriptlet \verb|routef|.
+\begin{NB}
+This option was described in the \verb|route(8)| man page borrowed
+from BSD, but was never implemented in Linux.
+\end{NB}
+
+The second example flushes all IPv6 cloned routes:
+\begin{verbatim}
+netadm@amber:~ # ip -6 -s -s ro flush cache
+3ffe:2400::220:afff:fef4:c5d1 via 3ffe:2400::220:afff:fef4:c5d1 \
+ dev eth0 metric 0
+ cache used 2 age 12sec mtu 1500 rtt 300
+3ffe:2400::280:adff:feb7:8034 via 3ffe:2400::280:adff:feb7:8034 \
+ dev eth0 metric 0
+ cache used 2 age 15sec mtu 1500 rtt 300
+3ffe:2400::280:c8ff:fe59:5bcc via 3ffe:2400::280:c8ff:fe59:5bcc \
+ dev eth0 metric 0
+ cache users 1 used 1 age 23sec mtu 1500 rtt 300
+3ffe:2400:0:1:2a0:ccff:fe66:1878 via 3ffe:2400:0:1:2a0:ccff:fe66:1878 \
+ dev eth1 metric 0
+ cache used 2 age 20sec mtu 1500 rtt 300
+3ffe:2400:0:1:a00:20ff:fe71:fb30 via 3ffe:2400:0:1:a00:20ff:fe71:fb30 \
+ dev eth1 metric 0
+ cache used 2 age 33sec mtu 1500 rtt 300
+ff02::1 via ff02::1 dev eth1 metric 0
+ cache users 1 used 1 age 45sec mtu 1500 rtt 300
+
+*** Round 1, deleting 6 entries ***
+*** Flush is complete after 1 round ***
+netadm@amber:~ # ip -6 -s -s ro flush cache
+Nothing to flush.
+netadm@amber:~ #
+\end{verbatim}
+
+The third example flushes BGP routing tables after a \verb|gated|
+death.
+\begin{verbatim}
+netadm@amber:~ # ip ro ls proto gated/bgp | wc
+ 1408 9856 78730
+netadm@amber:~ # ip -s ro f proto gated/bgp
+
+*** Round 1, deleting 1408 entries ***
+*** Flush is complete after 1 round ***
+netadm@amber:~ # ip ro f proto gated/bgp
+Nothing to flush.
+netadm@amber:~ # ip ro ls proto gated/bgp
+netadm@amber:~ #
+\end{verbatim}
+
+
+\subsection{{\tt ip route get} --- get a single route}
+\label{IP-ROUTE-GET}
+
+\paragraph{Abbreviations:} \verb|get|, \verb|g|.
+
+\paragraph{Description:} this command gets a single route to a destination
+and prints its contents exactly as the kernel sees it.
+
+\paragraph{Arguments:}
+\begin{itemize}
+\item \verb|to ADDRESS| (default)
+
+--- the destination address.
+
+\item \verb|from ADDRESS|
+
+--- the source address.
+
+\item \verb|tos TOS| or \verb|dsfield TOS|
+
+--- the Type Of Service.
+
+\item \verb|iif NAME|
+
+--- the device from which this packet is expected to arrive.
+
+\item \verb|oif NAME|
+
+--- force the output device on which this packet will be routed.
+
+\item \verb|connected|
+
+--- if no source address (option \verb|from|) was given, relookup
+the route with the source set to the preferred address received from the first lookup.
+If policy routing is used, it may be a different route.
+
+\end{itemize}
+
+Note that this operation is not equivalent to \verb|ip route show|.
+\verb|show| shows existing routes. \verb|get| resolves them and
+creates new clones if necessary. Essentially, \verb|get|
+is equivalent to sending a packet along this path.
+If the \verb|iif| argument is not given, the kernel creates a route
+to output packets towards the requested destination.
+This is equivalent to pinging the destination
+with a subsequent {\tt ip route ls cache}, however, no packets are
+actually sent. With the \verb|iif| argument, the kernel pretends
+that a packet arrived from this interface and searches for
+a path to forward the packet.
+
+\paragraph{Output format:} This command outputs routes in the same
+format as \verb|ip route ls|.
+
+\paragraph{Examples:}
+\begin{itemize}
+\item Find a route to output packets to 193.233.7.82:
+\begin{verbatim}
+kuznet@amber:~ $ ip route get 193.233.7.82
+193.233.7.82 dev eth0 src 193.233.7.65 realms inr.ac
+ cache mtu 1500 rtt 300
+kuznet@amber:~ $
+\end{verbatim}
+
+\item Find a route to forward packets arriving on \verb|eth0|
+from 193.233.7.82 and destined for 193.233.7.82:
+\begin{verbatim}
+kuznet@amber:~ $ ip r g 193.233.7.82 from 193.233.7.82 iif eth0
+193.233.7.82 from 193.233.7.82 dev eth0 src 193.233.7.65 \
+ realms inr.ac/inr.ac
+ cache <src-direct,redirect> mtu 1500 rtt 300 iif eth0
+kuznet@amber:~ $
+\end{verbatim}
+\begin{NB}
+ \label{NB-nature-of-strangeness}
+ This is the command that created the funny route from 193.233.7.82
+ looped back to 193.233.7.82 (cf.\ NB on~p.\pageref{NB-strange-route}).
+ Note the \verb|redirect| flag on it.
+\end{NB}
+
+\item Find a multicast route for packets arriving on \verb|eth0|
+from host 193.233.7.82 and destined for multicast group 224.2.127.254
+(it is assumed that a multicast routing daemon is running.
+In this case, it is \verb|pimd|)
+\begin{verbatim}
+kuznet@amber:~ $ ip r g 224.2.127.254 from 193.233.7.82 iif eth0
+multicast 224.2.127.254 from 193.233.7.82 dev lo \
+ src 193.233.7.65 realms inr.ac/cosmos
+ cache <mc> iif eth0 Oifs: eth1 pimreg
+kuznet@amber:~ $
+\end{verbatim}
+This route differs from the ones seen before. It contains a ``normal'' part
+and a ``multicast'' part. The normal part is used to deliver (or not to
+deliver) the packet to local IP listeners. In this case the router
+is not a member
+of this group, so that route has no \verb|local| flag and only
+forwards packets. The output device for such entries is always loopback.
+The multicast part consists of an additional \verb|Oifs:| list showing
+the output interfaces.
+\end{itemize}
+
+
+It is time for a more complicated example. Let us add an invalid
+gatewayed route for a destination which is really directly connected:
+\begin{verbatim}
+netadm@alisa:~ # ip route add 193.233.7.98 via 193.233.7.254
+netadm@alisa:~ # ip route get 193.233.7.98
+193.233.7.98 via 193.233.7.254 dev eth0 src 193.233.7.90
+ cache mtu 1500 rtt 3072
+netadm@alisa:~ #
+\end{verbatim}
+and probe it with ping:
+\begin{verbatim}
+netadm@alisa:~ # ping -n 193.233.7.98
+PING 193.233.7.98 (193.233.7.98) from 193.233.7.90 : 56 data bytes
+From 193.233.7.254: Redirect Host(New nexthop: 193.233.7.98)
+64 bytes from 193.233.7.98: icmp_seq=0 ttl=255 time=3.5 ms
+From 193.233.7.254: Redirect Host(New nexthop: 193.233.7.98)
+64 bytes from 193.233.7.98: icmp_seq=1 ttl=255 time=2.2 ms
+64 bytes from 193.233.7.98: icmp_seq=2 ttl=255 time=0.4 ms
+64 bytes from 193.233.7.98: icmp_seq=3 ttl=255 time=0.4 ms
+64 bytes from 193.233.7.98: icmp_seq=4 ttl=255 time=0.4 ms
+^C
+--- 193.233.7.98 ping statistics ---
+5 packets transmitted, 5 packets received, 0% packet loss
+round-trip min/avg/max = 0.4/1.3/3.5 ms
+netadm@alisa:~ #
+\end{verbatim}
+What happened? Router 193.233.7.254 understood that we have a much
+better path to the destination and sent us an ICMP redirect message.
+We may retry \verb|ip route get| to see what we have in the routing
+tables now:
+\begin{verbatim}
+netadm@alisa:~ # ip route get 193.233.7.98
+193.233.7.98 dev eth0 src 193.233.7.90
+ cache <redirected> mtu 1500 rtt 3072
+netadm@alisa:~ #
+\end{verbatim}
+
+
+
+\section{{\tt ip rule} --- routing policy database management}
+\label{IP-RULE}
+
+\paragraph{Abbreviations:} \verb|rule|, \verb|ru|.
+
+\paragraph{Object:} \verb|rule|s in the routing policy database control
+the route selection algorithm.
+
+Classic routing algorithms used in the Internet make routing decisions
+based only on the destination address of packets (and in theory,
+but not in practice, on the TOS field). The seminal review of classic
+routing algorithms and their modifications can be found in~\cite{RFC1812}.
+
+In some circumstances we want to route packets differently depending not only
+on destination addresses, but also on other packet fields: source address,
+IP protocol, transport protocol ports or even packet payload.
+This task is called ``policy routing''.
+
+\begin{NB}
+ ``policy routing'' $\neq$ ``routing policy''.
+
+\noindent ``policy routing'' $=$ ``cunning routing''.
+
+\noindent ``routing policy'' $=$ ``routing tactics'' or ``routing plan''.
+\end{NB}
+
+To solve this task, the conventional destination based routing table, ordered
+according to the longest match rule, is replaced with a ``routing policy
+database'' (or RPDB), which selects routes
+by executing some set of rules. The rules may have lots of keys of different
+natures and therefore they have no natural ordering, but one imposed
+by the administrator. Linux-2.2 RPDB is a linear list of rules
+ordered by numeric priority value.
+RPDB explicitly allows matching a few packet fields:
+
+\begin{itemize}
+\item packet source address.
+\item packet destination address.
+\item TOS.
+\item incoming interface (which is packet metadata, rather than a packet field).
+\end{itemize}
+
+Matching IP protocols and transport ports is also possible,
+indirectly, via \verb|ipchains|, by exploiting their ability
+to mark some classes of packets with \verb|fwmark|. Therefore,
+\verb|fwmark| is also included in the set of keys checked by rules.
+
+Each policy routing rule consists of a {\em selector\/} and an {\em action\/}
+predicate. The RPDB is scanned in the order of increasing priority. The selector
+of each rule is applied to \{source address, destination address, incoming
+interface, tos, fwmark\} and, if the selector matches the packet,
+the action is performed. The action predicate may return with success.
+In this case, it will either give a route or failure indication
+and the RPDB lookup is terminated. Otherwise, the RPDB program
+continues on the next rule.
+
+What is the action, semantically? The natural action is to select the
+nexthop and the output device. This is what
+Cisco IOS~\cite{IOS} does. Let us call it ``match \& set''.
+The Linux-2.2 approach is more flexible. The action includes
+lookups in destination-based routing tables and selecting
+a route from these tables according to the classic longest match algorithm.
+The ``match \& set'' approach is the simplest case of the Linux one. It is realized
+when a second level routing table contains a single default route.
+Recall that Linux-2.2 supports multiple tables
+managed with the \verb|ip route| command, described in the previous section.
+
+At startup time the kernel configures the default RPDB consisting of three
+rules:
+
+\begin{enumerate}
+\item Priority: 0, Selector: match anything, Action: lookup routing
+table \verb|local| (ID 255).
+The \verb|local| table is a special routing table containing
+high priority control routes for local and broadcast addresses.
+
+Rule 0 is special. It cannot be deleted or overridden.
+
+
+\item Priority: 32766, Selector: match anything, Action: lookup routing
+table \verb|main| (ID 254).
+The \verb|main| table is the normal routing table containing all non-policy
+routes. This rule may be deleted and/or overridden with other
+ones by the administrator.
+
+\item Priority: 32767, Selector: match anything, Action: lookup routing
+table \verb|default| (ID 253).
+The \verb|default| table is empty. It is reserved for some
+post-processing if no previous default rules selected the packet.
+This rule may also be deleted.
+
+\end{enumerate}
+
+Do not confuse routing tables with rules: rules point to routing tables,
+several rules may refer to one routing table and some routing tables
+may have no rules pointing to them. If the administrator deletes all the rules
+referring to a table, the table is not used, but it still exists
+and will disappear only after all the routes contained in it are deleted.
+
+
+\paragraph{Rule attributes:} Each RPDB entry has additional
+attributes. F.e.\ each rule has a pointer to some routing
+table. NAT and masquerading rules have an attribute to select new IP
+address to translate/masquerade. Besides that, rules have some
+optional attributes, which routes have, namely \verb|realms|.
+These values do not override those contained in the routing tables. They
+are only used if the route did not select any attributes.
+
+
+\paragraph{Rule types:} The RPDB may contain rules of the following
+types:
+\begin{itemize}
+\item \verb|unicast| --- the rule prescribes to return the route found
+in the routing table referenced by the rule.
+\item \verb|blackhole| --- the rule prescribes to silently drop the packet.
+\item \verb|unreachable| --- the rule prescribes to generate a ``Network
+is unreachable'' error.
+\item \verb|prohibit| --- the rule prescribes to generate
+``Communication is administratively prohibited'' error.
+\item \verb|nat| --- the rule prescribes to translate the source address
+of the IP packet into some other value. More about NAT is
+in Appendix~\ref{ROUTE-NAT}, p.\pageref{ROUTE-NAT}.
+\end{itemize}
+
+
+\paragraph{Commands:} \verb|add|, \verb|delete| and \verb|show|
+(or \verb|list|).
+
+\subsection{{\tt ip rule add} --- insert a new rule\\
+ {\tt ip rule delete} --- delete a rule}
+\label{IP-RULE-ADD}
+
+\paragraph{Abbreviations:} \verb|add|, \verb|a|; \verb|delete|, \verb|del|,
+ \verb|d|.
+
+\paragraph{Arguments:}
+
+\begin{itemize}
+\item \verb|type TYPE| (default)
+
+--- the type of this rule. The list of valid types was given in the previous
+subsection.
+
+\item \verb|from PREFIX|
+
+--- select the source prefix to match.
+
+\item \verb|to PREFIX|
+
+--- select the destination prefix to match.
+
+\item \verb|iif NAME|
+
+--- select the incoming device to match. If the interface is loopback,
+the rule only matches packets originating from this host. This means that you
+may create separate routing tables for forwarded and local packets and,
+hence, completely segregate them.
+
+\item \verb|tos TOS| or \verb|dsfield TOS|
+
+--- select the TOS value to match.
+
+\item \verb|fwmark MARK|
+
+--- select the \verb|fwmark| value to match.
+
+\item \verb|priority PREFERENCE|
+
+--- the priority of this rule. Each rule should have an explicitly
+set {\em unique\/} priority value.
+\begin{NB}
+ Really, for historical reasons \verb|ip rule add| does not require a
+ priority value and allows them to be non-unique.
+ If the user does not supplied a priority, it is selected by the kernel.
+ If the user creates a rule with a priority value that
+ already exists, the kernel does not reject the request. It adds
+ the new rule before all old rules of the same priority.
+
+ It is mistake in design, no more. And it will be fixed one day,
+ so do not rely on this feature. Use explicit priorities.
+\end{NB}
+
+
+\item \verb|table TABLEID|
+
+--- the routing table identifier to lookup if the rule selector matches.
+
+\item \verb|realms FROM/TO|
+
+--- Realms to select if the rule matched and the routing table lookup
+succeeded. Realm \verb|TO| is only used if the route did not select
+any realm.
+
+\item \verb|nat ADDRESS|
+
+--- The base of the IP address block to translate (for source addresses).
+The \verb|ADDRESS| may be either the start of the block of NAT addresses
+(selected by NAT routes) or in linux-2.2 a local host address (or even zero).
+In the last case the router does not translate the packets,
+but masquerades them to this address; this feature disappered in 2.4.
+More about NAT is in Appendix~\ref{ROUTE-NAT},
+p.\pageref{ROUTE-NAT}.
+
+\end{itemize}
+
+\paragraph{Warning:} Changes to the RPDB made with these commands
+do not become active immediately. It is assumed that after
+a script finishes a batch of updates, it flushes the routing cache
+with \verb|ip route flush cache|.
+
+\paragraph{Examples:}
+\begin{itemize}
+\item Route packets with source addresses from 192.203.80/24
+according to routing table \verb|inr.ruhep|:
+\begin{verbatim}
+ip ru add from 192.203.80.0/24 table inr.ruhep prio 220
+\end{verbatim}
+
+\item Translate packet source address 193.233.7.83 into 192.203.80.144
+and route it according to table \#1 (actually, it is \verb|inr.ruhep|):
+\begin{verbatim}
+ip ru add from 193.233.7.83 nat 192.203.80.144 table 1 prio 320
+\end{verbatim}
+
+\item Delete the unused default rule:
+\begin{verbatim}
+ip ru del prio 32767
+\end{verbatim}
+
+\end{itemize}
+
+
+
+\subsection{{\tt ip rule show} --- list rules}
+\label{IP-RULE-SHOW}
+
+\paragraph{Abbreviations:} \verb|show|, \verb|list|, \verb|sh|, \verb|ls|, \verb|l|.
+
+
+\paragraph{Arguments:} Good news, this is one command that has no arguments.
+
+\paragraph{Output format:}
+
+\begin{verbatim}
+kuznet@amber:~ $ ip ru ls
+0: from all lookup local
+200: from 192.203.80.0/24 to 193.233.7.0/24 lookup main
+210: from 192.203.80.0/24 to 192.203.80.0/24 lookup main
+220: from 192.203.80.0/24 lookup inr.ruhep realms inr.ruhep/radio-msu
+300: from 193.233.7.83 to 193.233.7.0/24 lookup main
+310: from 193.233.7.83 to 192.203.80.0/24 lookup main
+320: from 193.233.7.83 lookup inr.ruhep map-to 192.203.80.144
+32766: from all lookup main
+kuznet@amber:~ $
+\end{verbatim}
+
+In the first column is the rule priority value followed
+by a colon. Then the selectors follow. Each key is prefixed
+with the same keyword that was used to create the rule.
+
+The keyword \verb|lookup| is followed by a routing table identifier,
+as it is recorded in the file \verb|/etc/iproute2/rt_tables|.
+
+If the rule does NAT (f.e.\ rule \#320), it is shown by the keyword
+\verb|map-to| followed by the start of the block of addresses to map.
+
+The sense of this example is pretty simple. The prefixes
+192.203.80.0/24 and 193.233.7.0/24 form the internal network, but
+they are routed differently when the packets leave it.
+Besides that, the host 193.233.7.83 is translated into
+another prefix to look like 192.203.80.144 when talking
+to the outer world.
+
+\subsection{{\tt ip rule save} -- save rules tables}
+\label{IP-RULE-SAVE}
+
+\paragraph{Description:} this command saves the contents of the rules
+tables or the rule(s) selected by some criteria to standard output.
+
+\paragraph{Arguments:} \verb|ip rule save| has the same arguments as
+\verb|ip rule show|.
+
+\paragraph{Example:} This saves all the rules to the {\tt saved\_rules}
+file:
+\begin{verbatim}
+dan@caffeine:~ # ip rule save > saved_rules
+\end{verbatim}
+
+\paragraph{Output format:} The format of the data stream provided by
+\verb|ip rule save| is that of \verb|rtnetlink|. See
+\verb|rtnetlink(7)| for more information.
+
+\subsection{{\tt ip rule restore} -- restore rules tables}
+\label{IP-RULE-RESTORE}
+
+\paragraph{Description:} this command restores the contents of the rules
+tables according to a data stream as provided by \verb|ip rule save| via
+standard input. Note that any rules already in the table are left unchanged,
+and duplicates are not ignored.
+
+\paragraph{Arguments:} This command takes no arguments.
+
+\paragraph{Example:} This restores all rules that were saved to the
+{\tt saved\_rules} file:
+
+\begin{verbatim}
+dan@caffeine:~ # ip rule restore < saved_rules
+\end{verbatim}
+
+
+
+\section{{\tt ip maddress} --- multicast addresses management}
+\label{IP-MADDR}
+
+\paragraph{Object:} \verb|maddress| objects are multicast addresses.
+
+\paragraph{Commands:} \verb|add|, \verb|delete|, \verb|show| (or \verb|list|).
+
+\subsection{{\tt ip maddress show} --- list multicast addresses}
+
+\paragraph{Abbreviations:} \verb|show|, \verb|list|, \verb|sh|, \verb|ls|, \verb|l|.
+
+\paragraph{Arguments:}
+
+\begin{itemize}
+
+\item \verb|dev NAME| (default)
+
+--- the device name.
+
+\end{itemize}
+
+\paragraph{Output format:}
+
+\begin{verbatim}
+kuznet@alisa:~ $ ip maddr ls dummy
+2: dummy
+ link 33:33:00:00:00:01
+ link 01:00:5e:00:00:01
+ inet 224.0.0.1 users 2
+ inet6 ff02::1
+kuznet@alisa:~ $
+\end{verbatim}
+
+The first line of the output shows the interface index and its name.
+Then the multicast address list follows. Each line starts with the
+protocol identifier. The word \verb|link| denotes a link layer
+multicast addresses.
+
+If a multicast address has more than one user, the number
+of users is shown after the \verb|users| keyword.
+
+One additional feature not present in the example above
+is the \verb|static| flag, which indicates that the address was joined
+with \verb|ip maddr add|. See the following subsection.
+
+
+
+\subsection{{\tt ip maddress add} --- add a multicast address\\
+ {\tt ip maddress delete} --- delete a multicast address}
+
+\paragraph{Abbreviations:} \verb|add|, \verb|a|; \verb|delete|, \verb|del|, \verb|d|.
+
+\paragraph{Description:} these commands attach/detach
+a static link layer multicast address to listen on the interface.
+Note that it is impossible to join protocol multicast groups
+statically. This command only manages link layer addresses.
+
+
+\paragraph{Arguments:}
+
+\begin{itemize}
+\item \verb|address LLADDRESS| (default)
+
+--- the link layer multicast address.
+
+\item \verb|dev NAME|
+
+--- the device to join/leave this multicast address.
+
+\end{itemize}
+
+
+\paragraph{Example:} Let us continue with the example from the previous subsection.
+
+\begin{verbatim}
+netadm@alisa:~ # ip maddr add 33:33:00:00:00:01 dev dummy
+netadm@alisa:~ # ip -0 maddr ls dummy
+2: dummy
+ link 33:33:00:00:00:01 users 2 static
+ link 01:00:5e:00:00:01
+netadm@alisa:~ # ip maddr del 33:33:00:00:00:01 dev dummy
+\end{verbatim}
+
+\begin{NB}
+ Neither \verb|ip| nor the kernel check for multicast address validity.
+ Particularly, this means that you can try to load a unicast address
+ instead of a multicast address. Most drivers will ignore such addresses,
+ but several (f.e.\ Tulip) will intern it to their on-board filter.
+ The effects may be strange. Namely, the addresses become additional
+ local link addresses and, if you loaded the address of another host
+ to the router, wait for duplicated packets on the wire.
+ It is not a bug, but rather a hole in the API and intra-kernel interfaces.
+ This feature is really more useful for traffic monitoring, but using it
+ with Linux-2.2 you {\em have to\/} be sure that the host is not
+ a router and, especially, that it is not a transparent proxy or masquerading
+ agent.
+\end{NB}
+
+
+
+\section{{\tt ip mroute} --- multicast routing cache management}
+\label{IP-MROUTE}
+
+\paragraph{Abbreviations:} \verb|mroute|, \verb|mr|.
+
+\paragraph{Object:} \verb|mroute| objects are multicast routing cache
+entries created by a user level mrouting daemon
+(f.e.\ \verb|pimd| or \verb|mrouted|).
+
+Due to the limitations of the current interface to the multicast routing
+engine, it is impossible to change \verb|mroute| objects administratively,
+so we may only display them. This limitation will be removed
+in the future.
+
+\paragraph{Commands:} \verb|show| (or \verb|list|).
+
+
+\subsection{{\tt ip mroute show} --- list mroute cache entries}
+
+\paragraph{Abbreviations:} \verb|show|, \verb|list|, \verb|sh|, \verb|ls|, \verb|l|.
+
+\paragraph{Arguments:}
+
+\begin{itemize}
+\item \verb|to PREFIX| (default)
+
+--- the prefix selecting the destination multicast addresses to list.
+
+
+\item \verb|iif NAME|
+
+--- the interface on which multicast packets are received.
+
+
+\item \verb|from PREFIX|
+
+--- the prefix selecting the IP source addresses of the multicast route.
+
+
+\end{itemize}
+
+\paragraph{Output format:}
+
+\begin{verbatim}
+kuznet@amber:~ $ ip mroute ls
+(193.232.127.6, 224.0.1.39) Iif: unresolved
+(193.232.244.34, 224.0.1.40) Iif: unresolved
+(193.233.7.65, 224.66.66.66) Iif: eth0 Oifs: pimreg
+kuznet@amber:~ $
+\end{verbatim}
+
+Each line shows one (S,G) entry in the multicast routing cache,
+where S is the source address and G is the multicast group. \verb|Iif| is
+the interface on which multicast packets are expected to arrive.
+If the word \verb|unresolved| is there instead of the interface name,
+it means that the routing daemon still hasn't resolved this entry.
+The keyword \verb|oifs| is followed by a list of output interfaces, separated
+by spaces. If a multicast routing entry is created with non-trivial
+TTL scope, administrative distances are appended to the device names
+in the \verb|oifs| list.
+
+\paragraph{Statistics:} The \verb|-statistics| option also prints the
+number of packets and bytes forwarded along this route and
+the number of packets that arrived on the wrong interface, if this number is not zero.
+
+\begin{verbatim}
+kuznet@amber:~ $ ip -s mr ls 224.66/16
+(193.233.7.65, 224.66.66.66) Iif: eth0 Oifs: pimreg
+ 9383 packets, 300256 bytes
+kuznet@amber:~ $
+\end{verbatim}
+
+
+\section{{\tt ip tunnel} --- tunnel configuration}
+\label{IP-TUNNEL}
+
+\paragraph{Abbreviations:} \verb|tunnel|, \verb|tunl|.
+
+\paragraph{Object:} \verb|tunnel| objects are tunnels, encapsulating
+packets in IPv4 packets and then sending them over the IP infrastructure.
+
+\paragraph{Commands:} \verb|add|, \verb|delete|, \verb|change|, \verb|show|
+(or \verb|list|).
+
+\paragraph{See also:} A more informal discussion of tunneling
+over IP and the \verb|ip tunnel| command can be found in~\cite{IP-TUNNELS}.
+
+\subsection{{\tt ip tunnel add} --- add a new tunnel\\
+ {\tt ip tunnel change} --- change an existing tunnel\\
+ {\tt ip tunnel delete} --- destroy a tunnel}
+
+\paragraph{Abbreviations:} \verb|add|, \verb|a|; \verb|change|, \verb|chg|;
+\verb|delete|, \verb|del|, \verb|d|.
+
+
+\paragraph{Arguments:}
+
+\begin{itemize}
+
+\item \verb|name NAME| (default)
+
+--- select the tunnel device name.
+
+\item \verb|mode MODE|
+
+--- set the tunnel mode. Three modes are currently available:
+ \verb|ipip|, \verb|sit| and \verb|gre|.
+
+\item \verb|remote ADDRESS|
+
+--- set the remote endpoint of the tunnel.
+
+\item \verb|local ADDRESS|
+
+--- set the fixed local address for tunneled packets.
+It must be an address on another interface of this host.
+
+\item \verb|ttl N|
+
+--- set a fixed TTL \verb|N| on tunneled packets.
+ \verb|N| is a number in the range 1--255. 0 is a special value
+ meaning that packets inherit the TTL value.
+ The default value is: \verb|inherit|.
+
+\item \verb|tos T| or \verb|dsfield T|
+
+--- set a fixed TOS \verb|T| on tunneled packets.
+ The default value is: \verb|inherit|.
+
+
+
+\item \verb|dev NAME|
+
+--- bind the tunnel to the device \verb|NAME| so that
+ tunneled packets will only be routed via this device and will
+ not be able to escape to another device when the route to endpoint changes.
+
+\item \verb|nopmtudisc|
+
+--- disable Path MTU Discovery on this tunnel.
+ It is enabled by default. Note that a fixed ttl is incompatible
+ with this option: tunnelling with a fixed ttl always makes pmtu discovery.
+
+\item \verb|key K|, \verb|ikey K|, \verb|okey K|
+
+--- (only GRE tunnels) use keyed GRE with key \verb|K|. \verb|K| is
+ either a number or an IP address-like dotted quad.
+ The \verb|key| parameter sets the key to use in both directions.
+ The \verb|ikey| and \verb|okey| parameters set different keys for input and output.
+
+
+\item \verb|csum|, \verb|icsum|, \verb|ocsum|
+
+--- (only GRE tunnels) generate/require checksums for tunneled packets.
+ The \verb|ocsum| flag calculates checksums for outgoing packets.
+ The \verb|icsum| flag requires that all input packets have the correct
+ checksum. The \verb|csum| flag is equivalent to the combination
+ ``\verb|icsum| \verb|ocsum|''.
+
+\item \verb|seq|, \verb|iseq|, \verb|oseq|
+
+--- (only GRE tunnels) serialize packets.
+ The \verb|oseq| flag enables sequencing of outgoing packets.
+ The \verb|iseq| flag requires that all input packets are serialized.
+ The \verb|seq| flag is equivalent to the combination ``\verb|iseq| \verb|oseq|''.
+
+\begin{NB}
+ I think this option does not
+ work. At least, I did not test it, did not debug it and
+ do not even understand how it is supposed to work or for what
+ purpose Cisco planned to use it. Do not use it.
+\end{NB}
+
+
+\end{itemize}
+
+\paragraph{Example:} Create a pointopoint IPv6 tunnel with maximal TTL of 32.
+\begin{verbatim}
+netadm@amber:~ # ip tunl add Cisco mode sit remote 192.31.7.104 \
+ local 192.203.80.142 ttl 32
+\end{verbatim}
+
+\subsection{{\tt ip tunnel show} --- list tunnels}
+
+\paragraph{Abbreviations:} \verb|show|, \verb|list|, \verb|sh|, \verb|ls|, \verb|l|.
+
+
+\paragraph{Arguments:} None.
+
+\paragraph{Output format:}
+\begin{verbatim}
+kuznet@amber:~ $ ip tunl ls Cisco
+Cisco: ipv6/ip remote 192.31.7.104 local 192.203.80.142 ttl 32
+kuznet@amber:~ $
+\end{verbatim}
+The line starts with the tunnel device name followed by a colon.
+Then the tunnel mode follows. The parameters of the tunnel are listed
+with the same keywords that were used when creating the tunnel.
+
+\paragraph{Statistics:}
+
+\begin{verbatim}
+kuznet@amber:~ $ ip -s tunl ls Cisco
+Cisco: ipv6/ip remote 192.31.7.104 local 192.203.80.142 ttl 32
+RX: Packets Bytes Errors CsumErrs OutOfSeq Mcasts
+ 12566 1707516 0 0 0 0
+TX: Packets Bytes Errors DeadLoop NoRoute NoBufs
+ 13445 1879677 0 0 0 0
+kuznet@amber:~ $
+\end{verbatim}
+Essentially, these numbers are the same as the numbers
+printed with {\tt ip -s link show}
+(sec.\ref{IP-LINK-SHOW}, p.\pageref{IP-LINK-SHOW}) but the tags are different
+to reflect that they are tunnel specific.
+\begin{itemize}
+\item \verb|CsumErrs| --- the total number of packets dropped
+because of checksum failures for a GRE tunnel with checksumming enabled.
+\item \verb|OutOfSeq| --- the total number of packets dropped
+because they arrived out of sequence for a GRE tunnel with
+serialization enabled.
+\item \verb|Mcasts| --- the total number of multicast packets
+received on a broadcast GRE tunnel.
+\item \verb|DeadLoop| --- the total number of packets which were not
+transmitted because the tunnel is looped back to itself.
+\item \verb|NoRoute| --- the total number of packets which were not
+transmitted because there is no IP route to the remote endpoint.
+\item \verb|NoBufs| --- the total number of packets which were not
+transmitted because the kernel failed to allocate a buffer.
+\end{itemize}
+
+
+\section{{\tt ip monitor} and {\tt rtmon} --- state monitoring}
+\label{IP-MONITOR}
+
+The \verb|ip| utility can monitor the state of devices, addresses
+and routes continuously. This option has a slightly different format.
+Namely,
+the \verb|monitor| command is the first in the command line and then
+the object list follows:
+\begin{verbatim}
+ ip monitor [ file FILE ] [ all | OBJECT-LIST ] [ label ]
+\end{verbatim}
+\verb|OBJECT-LIST| is the list of object types that we want to
+monitor. It may contain \verb|link|, \verb|address| and \verb|route|.
+Specifying \verb|label| indicates that output lines should be labelled
+with the type of object being printed --- this happens by default if
+\verb|all| is specified. If no \verb|file| argument is given,
+\verb|ip| opens RTNETLINK, listens on it and dumps state changes in
+the format described in previous sections.
+
+If a file name is given, it does not listen on RTNETLINK,
+but opens the file containing RTNETLINK messages saved in binary format
+and dumps them. Such a history file can be generated with the
+\verb|rtmon| utility. This utility has a command line syntax similar to
+\verb|ip monitor|.
+Ideally, \verb|rtmon| should be started before
+the first network configuration command is issued. F.e.\ if
+you insert:
+\begin{verbatim}
+ rtmon file /var/log/rtmon.log
+\end{verbatim}
+in a startup script, you will be able to view the full history
+later.
+
+Certainly, it is possible to start \verb|rtmon| at any time.
+It prepends the history with the state snapshot dumped at the moment
+of starting.
+
+
+\section{Route realms and policy propagation, {\tt rtacct}}
+\label{RT-REALMS}
+
+On routers using OSPF ASE or, especially, the BGP protocol, routing
+tables may be huge. If we want to classify or to account for the packets
+per route, we will have to keep lots of information. Even worse, if we
+want to distinguish the packets not only by their destination, but
+also by their source, the task gets quadratic complexity and its solution
+is physically impossible.
+
+One approach to propagating the policy from routing protocols
+to the forwarding engine has been proposed in~\cite{IOS-BGP-PP}.
+Essentially, Cisco Policy Propagation via BGP is based on the fact
+that dedicated routers all have the RIB (Routing Information Base)
+close to the forwarding engine, so policy routing rules can
+check all the route attributes, including ASPATH information
+and community strings.
+
+The Linux architecture, splitting the RIB (maintained by a user level
+daemon) and the kernel based FIB (Forwarding Information Base),
+does not allow such a simple approach.
+
+It is to our fortune because there is another solution
+which allows even more flexible policy and richer semantics.
+
+Namely, routes can be clustered together in user space, based on their
+attributes. F.e.\ a BGP router knows route ASPATH, its community;
+an OSPF router knows the route tag or its area. The administrator, when adding
+routes manually, also knows their nature. Providing that the number of such
+aggregates (we call them {\em realms\/}) is low, the task of full
+classification both by source and destination becomes quite manageable.
+
+So each route may be assigned to a realm. It is assumed that
+this identification is made by a routing daemon, but static routes
+can also be handled manually with \verb|ip route| (see sec.\ref{IP-ROUTE},
+p.\pageref{IP-ROUTE}).
+\begin{NB}
+ There is a patch to \verb|gated|, allowing classification of routes
+ to realms with all the set of policy rules implemented in \verb|gated|:
+ by prefix, by ASPATH, by origin, by tag etc.
+\end{NB}
+
+To facilitate the construction (f.e.\ in case the routing
+daemon is not aware of realms), missing realms may be completed
+with routing policy rules, see sec.~\ref{IP-RULE}, p.\pageref{IP-RULE}.
+
+For each packet the kernel calculates a tuple of realms: source realm
+and destination realm, using the following algorithm:
+
+\begin{enumerate}
+\item If the route has a realm, the destination realm of the packet is set to it.
+\item If the rule has a source realm, the source realm of the packet is set to it.
+If the destination realm was not inherited from the route and the rule has a destination realm,
+it is also set.
+\item If at least one of the realms is still unknown, the kernel finds
+the reversed route to the source of the packet.
+\item If the source realm is still unknown, get it from the reversed route.
+\item If one of the realms is still unknown, swap the realms of reversed
+routes and apply step 2 again.
+\end{enumerate}
+
+After this procedure is completed we know what realm the packet
+arrived from and the realm where it is going to propagate to.
+If some of the realms are unknown, they are initialized to zero
+(or realm \verb|unknown|).
+
+The main application of realms is the TC \verb|route| classifier~\cite{TC-CREF},
+where they are used to help assign packets to traffic classes,
+to account, police and schedule them according to this
+classification.
+
+A much simpler but still very useful application is incoming packet
+accounting by realms. The kernel gathers a packet statistics summary
+which can be viewed with the \verb|rtacct| utility.
+\begin{verbatim}
+kuznet@amber:~ $ rtacct russia
+Realm BytesTo PktsTo BytesFrom PktsFrom
+russia 20576778 169176 47080168 153805
+kuznet@amber:~ $
+\end{verbatim}
+This shows that this router received 153805 packets from
+the realm \verb|russia| and forwarded 169176 packets to \verb|russia|.
+The realm \verb|russia| consists of routes with ASPATHs not leaving
+Russia.
+
+Note that locally originating packets are not accounted here,
+\verb|rtacct| shows incoming packets only. Using the \verb|route|
+classifier (see~\cite{TC-CREF}) you can get even more detailed
+accounting information about outgoing packets, optionally
+summarizing traffic not only by source or destination, but
+by any pair of source and destination realms.
+
+
+\begin{thebibliography}{99}
+\addcontentsline{toc}{section}{References}
+\bibitem{RFC-NDISC} T.~Narten, E.~Nordmark, W.~Simpson.
+``Neighbor Discovery for IP Version 6 (IPv6)'', RFC-2461.
+
+\bibitem{RFC-ADDRCONF} S.~Thomson, T.~Narten.
+``IPv6 Stateless Address Autoconfiguration'', RFC-2462.
+
+\bibitem{RFC1812} F.~Baker.
+``Requirements for IP Version 4 Routers'', RFC-1812.
+
+\bibitem{RFC1122} R.~T.~Braden.
+``Requirements for Internet hosts --- communication layers'', RFC-1122.
+
+\bibitem{IOS} ``Cisco IOS Release 12.0 Network Protocols
+Command Reference, Part 1'' and
+``Cisco IOS Release 12.0 Quality of Service Solutions
+Configuration Guide: Configuring Policy-Based Routing'',\\
+http://www.cisco.com/univercd/cc/td/doc/product/software/ios120.
+
+\bibitem{IP-TUNNELS} A.~N.~Kuznetsov.
+``Tunnels over IP in Linux-2.2'', \\
+In: {\tt ftp://ftp.inr.ac.ru/ip-routing/iproute2-current.tar.gz}.
+
+\bibitem{TC-CREF} A.~N.~Kuznetsov. ``TC Command Reference'',\\
+In: {\tt ftp://ftp.inr.ac.ru/ip-routing/iproute2-current.tar.gz}.
+
+\bibitem{IOS-BGP-PP} ``Cisco IOS Release 12.0 Quality of Service Solutions
+Configuration Guide: Configuring QoS Policy Propagation via
+Border Gateway Protocol'',\\
+http://www.cisco.com/univercd/cc/td/doc/product/software/ios120.
+
+\bibitem{RFC-DHCP} R.~Droms.
+``Dynamic Host Configuration Protocol.'', RFC-2131
+
+\bibitem{RFC2414} M.~Allman, S.~Floyd, C.~Partridge.
+``Increasing TCP's Initial Window'', RFC-2414.
+
+\end{thebibliography}
+
+
+
+
+\appendix
+\addcontentsline{toc}{section}{Appendix}
+
+\section{Source address selection}
+\label{ADDR-SEL}
+
+When a host creates an IP packet, it must select some source
+address. Correct source address selection is a critical procedure,
+because it gives the receiver the information needed to deliver a
+reply. If the source is selected incorrectly, in the best case,
+the backward path may appear different to the forward one which
+is harmful for performance. In the worst case, when the addresses
+are administratively scoped, the reply may be lost entirely.
+
+Linux-2.2 selects source addresses using the following algorithm:
+
+\begin{itemize}
+\item
+The application may select a source address explicitly with \verb|bind(2)|
+syscall or supplying it to \verb|sendmsg(2)| via the ancillary data object
+\verb|IP_PKTINFO|. In this case the kernel only checks the validity
+of the address and never tries to ``improve'' an incorrect user choice,
+generating an error instead.
+\begin{NB}
+ Never say ``Never''. The sysctl option \verb|ip_dynaddr| breaks
+ this axiom. It has been made deliberately with the purpose
+ of automatically reselecting the address on hosts with dynamic dial-out interfaces.
+ However, this hack {\em must not\/} be used on multihomed hosts
+ and especially on routers: it would break them.
+\end{NB}
+
+
+\item Otherwise, IP routing tables can contain an explicit source
+address hint for this destination. The hint is set with the \verb|src| parameter
+to the \verb|ip route| command, sec.\ref{IP-ROUTE}, p.\pageref{IP-ROUTE}.
+
+
+\item Otherwise, the kernel searches through the list of addresses
+attached to the interface through which the packets will be routed.
+The search strategies are different for IP and IPv6. Namely:
+
+\begin{itemize}
+\item IPv6 searches for the first valid, not deprecated address
+with the same scope as the destination.
+
+\item IP searches for the first valid address with a scope wider
+than the scope of the destination but it prefers addresses
+which fall to the same subnet as the nexthop of the route
+to the destination. Unlike IPv6, the scopes of IPv4 destinations
+are not encoded in their addresses but are supplied
+in routing tables instead (the \verb|scope| parameter to the \verb|ip route| command,
+sec.\ref{IP-ROUTE}, p.\pageref{IP-ROUTE}).
+
+\end{itemize}
+
+
+\item Otherwise, if the scope of the destination is \verb|link| or \verb|host|,
+the algorithm fails and returns a zero source address.
+
+\item Otherwise, all interfaces are scanned to search for an address
+with an appropriate scope. The loopback device \verb|lo| is always the first
+in the search list, so that if an address with global scope (not 127.0.0.1!)
+is configured on loopback, it is always preferred.
+
+\end{itemize}
+
+
+\section{Proxy ARP/NDISC}
+\label{PROXY-NEIGH}
+
+Routers may answer ARP/NDISC solicitations on behalf of other hosts.
+In Linux-2.2 proxy ARP on an interface may be enabled
+by setting the kernel \verb|sysctl| variable
+\verb|/proc/sys/net/ipv4/conf/<dev>/proxy_arp| to 1. After this, the router
+starts to answer ARP requests on the interface \verb|<dev>|, provided
+the route to the requested destination does {\em not\/} go back via the same
+device.
+
+The variable \verb|/proc/sys/net/ipv4/conf/all/proxy_arp| enables proxy
+ARP on all the IP devices.
+
+However, this approach fails in the case of IPv6 because the router
+must join the solicited node multicast address to listen for the corresponding
+NDISC queries. It means that proxy NDISC is possible only on a per destination
+basis.
+
+Logically, proxy ARP/NDISC is not a kernel task. It can easily be implemented
+in user space. However, similar functionality was present in BSD kernels
+and in Linux-2.0, so we have to preserve it at least to the extent that
+is standardized in BSD.
+\begin{NB}
+ Linux-2.0 ARP had a feature called {\em subnet\/} proxy ARP.
+ It is replaced with the sysctl flag in Linux-2.2.
+\end{NB}
+
+
+The \verb|ip| utility provides a way to manage proxy ARP/NDISC
+with the \verb|ip neigh| command, namely:
+\begin{verbatim}
+ ip neigh add proxy ADDRESS [ dev NAME ]
+\end{verbatim}
+adds a new proxy ARP/NDISC record and
+\begin{verbatim}
+ ip neigh del proxy ADDRESS [ dev NAME ]
+\end{verbatim}
+deletes it.
+
+If the name of the device is not given, the router will answer solicitations
+for address \verb|ADDRESS| on all devices, otherwise it will only serve
+the device \verb|NAME|. Even if the proxy entry is created with
+\verb|ip neigh|, the router {\em will not\/} answer a query if the route
+to the destination goes back via the interface from which the solicitation
+was received.
+
+It is important to emphasize that proxy entries have {\em no\/}
+parameters other than these (IP/IPv6 address and optional device).
+Particularly, the entry does not store any link layer address.
+It always advertises the station address of the interface
+on which it sends advertisements (i.e. it's own station address).
+
+\section{Route NAT status}
+\label{ROUTE-NAT}
+
+NAT (or ``Network Address Translation'') remaps some parts
+of the IP address space into other ones. Linux-2.2 route NAT is supposed
+to be used to facilitate policy routing by rewriting addresses
+to other routing domains or to help while renumbering sites
+to another prefix.
+
+\paragraph{What it is not:}
+It is necessary to emphasize that {\em it is not supposed\/}
+to be used to compress address space or to split load.
+This is not missing functionality but a design principle.
+Route NAT is {\em stateless\/}. It does not hold any state
+about translated sessions. This means that it handles any number
+of sessions flawlessly. But it also means that it is {\em static\/}.
+It cannot detect the moment when the last TCP client stops
+using an address. For the same reason, it will not help to split
+load between several servers.
+\begin{NB}
+It is a pretty commonly held belief that it is useful to split load between
+several servers with NAT. This is a mistake. All you get from this
+is the requirement that the router keep the state of all the TCP connections
+going via it. Well, if the router is so powerful, run apache on it. 8)
+\end{NB}
+
+The second feature: it does not touch packet payload,
+does not try to ``improve'' broken protocols by looking
+through its data and mangling it. It mangles IP addresses,
+only IP addresses and nothing but IP addresses.
+This also, is not missing any functionality.
+
+To resume: if you need to compress address space or keep
+active FTP clients happy, your choice is not route NAT but masquerading,
+port forwarding, NAPT etc.
+\begin{NB}
+By the way, you may also want to look at
+http://www.suse.com/\~mha/HyperNews/get/linux-ip-nat.html
+\end{NB}
+
+
+\paragraph{How it works.}
+Some part of the address space is reserved for dummy addresses
+which will look for all the world like some host addresses
+inside your network. No other hosts may use these addresses,
+however other routers may also be configured to translate them.
+\begin{NB}
+A great advantage of route NAT is that it may be used not
+only in stub networks but in environments with arbitrarily complicated
+structure. It does not firewall, it {\em forwards.}
+\end{NB}
+These addresses are selected by the \verb|ip route| command
+(sec.\ref{IP-ROUTE-ADD}, p.\pageref{IP-ROUTE-ADD}). F.e.\
+\begin{verbatim}
+ ip route add nat 192.203.80.144 via 193.233.7.83
+\end{verbatim}
+states that the single address 192.203.80.144 is a dummy NAT address.
+For all the world it looks like a host address inside our network.
+For neighbouring hosts and routers it looks like the local address
+of the translating router. The router answers ARP for it, advertises
+this address as routed via it, {\em et al\/}. When the router
+receives a packet destined for 192.203.80.144, it replaces
+this address with 193.233.7.83 which is the address of some real
+host and forwards the packet. If you need to remap
+blocks of addresses, you may use a command like:
+\begin{verbatim}
+ ip route add nat 192.203.80.192/26 via 193.233.7.64
+\end{verbatim}
+This command will map a block of 63 addresses 192.203.80.192-255 to
+193.233.7.64-127.
+
+When an internal host (193.233.7.83 in the example above)
+sends something to the outer world and these packets are forwarded
+by our router, it should translate the source address 193.233.7.83
+into 192.203.80.144. This task is solved by setting a special
+policy rule (sec.\ref{IP-RULE-ADD}, p.\pageref{IP-RULE-ADD}):
+\begin{verbatim}
+ ip rule add prio 320 from 193.233.7.83 nat 192.203.80.144
+\end{verbatim}
+This rule says that the source address 193.233.7.83
+should be translated into 192.203.80.144 before forwarding.
+It is important that the address after the \verb|nat| keyword
+is some NAT address, declared by {\tt ip route add nat}.
+If it is just a random address the router will not map to it.
+\begin{NB}
+The exception is when the address is a local address of this
+router (or 0.0.0.0) and masquerading is configured in the linux-2.2
+kernel. In this case the router will masquerade the packets as this address.
+If 0.0.0.0 is selected, the result is equivalent to one
+obtained with firewalling rules. Otherwise, you have the way
+to order Linux to masquerade to this fixed address.
+NAT mechanism used in linux-2.4 is more flexible than
+masquerading, so that this feature has lost meaning and disabled.
+\end{NB}
+
+If the network has non-trivial internal structure, it is
+useful and even necessary to add rules disabling translation
+when a packet does not leave this network. Let us return to the
+example from sec.\ref{IP-RULE-SHOW} (p.\pageref{IP-RULE-SHOW}).
+\begin{verbatim}
+300: from 193.233.7.83 to 193.233.7.0/24 lookup main
+310: from 193.233.7.83 to 192.203.80.0/24 lookup main
+320: from 193.233.7.83 lookup inr.ruhep map-to 192.203.80.144
+\end{verbatim}
+This block of rules causes normal forwarding when
+packets from 193.233.7.83 do not leave networks 193.233.7/24
+and 192.203.80/24. Also, if the \verb|inr.ruhep| table does not
+contain a route to the destination (which means that the routing
+domain owning addresses from 192.203.80/24 is dead), no translation
+will occur. Otherwise, the packets are translated.
+
+\paragraph{How to only translate selected ports:}
+If you only want to translate selected ports (f.e.\ http)
+and leave the rest intact, you may use \verb|ipchains|
+to \verb|fwmark| a class of packets.
+Suppose you did and all the packets from 193.233.7.83
+destined for port 80 are marked with marker 0x1234 in input fwchain.
+In this case you may replace rule \#320 with:
+\begin{verbatim}
+320: from 193.233.7.83 fwmark 1234 lookup main map-to 192.203.80.144
+\end{verbatim}
+and translation will only be enabled for outgoing http requests.
+
+\section{Example: minimal host setup}
+\label{EXAMPLE-SETUP}
+
+The following script gives an example of a fault safe
+setup of IP (and IPv6, if it is compiled into the kernel)
+in the common case of a node attached to a single broadcast
+network. A more advanced script, which may be used both on multihomed
+hosts and on routers, is described in the following
+section.
+
+The utilities used in the script may be found in the
+directory ftp://ftp.inr.ac.ru/ip-routing/:
+\begin{enumerate}
+\item \verb|ip| --- package \verb|iproute2|.
+\item \verb|arping| --- package \verb|iputils|.
+\item \verb|rdisc| --- package \verb|iputils|.
+\end{enumerate}
+\begin{NB}
+It also refers to a DHCP client, \verb|dhcpcd|. I should refrain from
+recommending a good DHCP client to use. All that I can
+say is that ISC \verb|dhcp-2.0b1pl6| patched with the patch that
+can be found in the \verb|dhcp.bootp.rarp| subdirectory of
+the same ftp site {\em does\/} work,
+at least on Ethernet and Token Ring.
+\end{NB}
+
+\begin{verbatim}
+#! /bin/bash
+\end{verbatim}
+\begin{flushleft}
+\# {\bf Usage: \verb|ifone ADDRESS[/PREFIX-LENGTH] [DEVICE]|}\\
+\# {\bf Parameters:}\\
+\# \$1 --- Static IP address, optionally followed by prefix length.\\
+\# \$2 --- Device name. If it is missing, \verb|eth0| is asssumed.\\
+\# F.e. \verb|ifone 193.233.7.90|
+\end{flushleft}
+\begin{verbatim}
+dev=$2
+: ${dev:=eth0}
+ipaddr=
+\end{verbatim}
+\# Parse IP address, splitting prefix length.
+\begin{verbatim}
+if [ "$1" != "" ]; then
+ ipaddr=${1%/*}
+ if [ "$1" != "$ipaddr" ]; then
+ pfxlen=${1#*/}
+ fi
+ : ${pfxlen:=24}
+fi
+pfx="${ipaddr}/${pfxlen}"
+\end{verbatim}
+
+\begin{flushleft}
+\# {\bf Step 0} --- enable loopback.\\
+\#\\
+\# This step is necessary on any networked box before attempt\\
+\# to configure any other device.\\
+\end{flushleft}
+\begin{verbatim}
+ip link set up dev lo
+ip addr add 127.0.0.1/8 dev lo brd + scope host
+\end{verbatim}
+\begin{flushleft}
+\# IPv6 autoconfigure themself on loopback.\\
+\#\\
+\# If user gave loopback as device, we add the address as alias and exit.
+\end{flushleft}
+\begin{verbatim}
+if [ "$dev" = "lo" ]; then
+ if [ "$ipaddr" != "" -a "$ipaddr" != "127.0.0.1" ]; then
+ ip address add $ipaddr dev $dev
+ exit $?
+ fi
+ exit 0
+fi
+\end{verbatim}
+
+\noindent\# {\bf Step 1} --- enable device \verb|$dev|
+
+\begin{verbatim}
+if ! ip link set up dev $dev ; then
+ echo "Cannot enable interface $dev. Aborting." 1>&2
+ exit 1
+fi
+\end{verbatim}
+\begin{flushleft}
+\# The interface is \verb|UP|. IPv6 started stateless autoconfiguration itself,\\
+\# and its configuration finishes here. However,\\
+\# IP still needs some static preconfigured address.
+\end{flushleft}
+\begin{verbatim}
+if [ "$ipaddr" = "" ]; then
+ echo "No address for $dev is configured, trying DHCP..." 1>&2
+ dhcpcd
+ exit $?
+fi
+\end{verbatim}
+
+\begin{flushleft}
+\# {\bf Step 2} --- IP Duplicate Address Detection~\cite{RFC-DHCP}.\\
+\# Send two probes and wait for result for 3 seconds.\\
+\# If the interface opens slower f.e.\ due to long media detection,\\
+\# you want to increase the timeout.\\
+\end{flushleft}
+\begin{verbatim}
+if ! arping -q -c 2 -w 3 -D -I $dev $ipaddr ; then
+ echo "Address $ipaddr is busy, trying DHCP..." 1>&2
+ dhcpcd
+ exit $?
+fi
+\end{verbatim}
+\begin{flushleft}
+\# OK, the address is unique, we may add it on the interface.\\
+\#\\
+\# {\bf Step 3} --- Configure the address on the interface.
+\end{flushleft}
+
+\begin{verbatim}
+if ! ip address add $pfx brd + dev $dev; then
+ echo "Failed to add $pfx on $dev, trying DHCP..." 1>&2
+ dhcpcd
+ exit $?
+fi
+\end{verbatim}
+
+\noindent\# {\bf Step 4} --- Announce our presence on the link.
+\begin{verbatim}
+arping -A -c 1 -I $dev $ipaddr
+noarp=$?
+( sleep 2;
+ arping -U -c 1 -I $dev $ipaddr ) >& /dev/null </dev/null &
+\end{verbatim}
+
+\begin{flushleft}
+\# {\bf Step 5} (optional) --- Add some control routes.\\
+\#\\
+\# 1. Prohibit link local multicast addresses.\\
+\# 2. Prohibit link local (alias, limited) broadcast.\\
+\# 3. Add default multicast route.
+\end{flushleft}
+\begin{verbatim}
+ip route add unreachable 224.0.0.0/24
+ip route add unreachable 255.255.255.255
+if [ `ip link ls $dev | grep -c MULTICAST` -ge 1 ]; then
+ ip route add 224.0.0.0/4 dev $dev scope global
+fi
+\end{verbatim}
+
+\begin{flushleft}
+\# {\bf Step 6} --- Add fallback default route with huge metric.\\
+\# If a proxy ARP server is present on the interface, we will be\\
+\# able to talk to all the Internet without further configuration.\\
+\# It is not so cheap though and we still hope that this route\\
+\# will be overridden by more correct one by rdisc.\\
+\# Do not make this step if the device is not ARPable,\\
+\# because dead nexthop detection does not work on them.
+\end{flushleft}
+\begin{verbatim}
+if [ "$noarp" = "0" ]; then
+ ip ro add default dev $dev metric 30000 scope global
+fi
+\end{verbatim}
+
+\begin{flushleft}
+\# {\bf Step 7} --- Restart router discovery and exit.
+\end{flushleft}
+\begin{verbatim}
+killall -HUP rdisc || rdisc -fs
+exit 0
+\end{verbatim}
+
+
+\section{Example: {\protect\tt ifcfg} --- interface address management}
+\label{EXAMPLE-IFCFG}
+
+This is a simplistic script replacing one option of \verb|ifconfig|,
+namely, IP address management. It not only adds
+addresses, but also carries out Duplicate Address Detection~\cite{RFC-DHCP},
+sends unsolicited ARP to update the caches of other hosts sharing
+the interface, adds some control routes and restarts Router Discovery
+when it is necessary.
+
+I strongly recommend using it {\em instead\/} of \verb|ifconfig| both
+on hosts and on routers.
+
+\begin{verbatim}
+#! /bin/bash
+\end{verbatim}
+\begin{flushleft}
+\# {\bf Usage: \verb?ifcfg DEVICE[:ALIAS] [add|del] ADDRESS[/LENGTH] [PEER]?}\\
+\# {\bf Parameters:}\\
+\# ---Device name. It may have alias suffix, separated by colon.\\
+\# ---Command: add, delete or stop.\\
+\# ---IP address, optionally followed by prefix length.\\
+\# ---Optional peer address for pointopoint interfaces.\\
+\# F.e. \verb|ifcfg eth0 193.233.7.90/24|
+
+\noindent\# This function determines, whether it is router or host.\\
+\# It returns 0, if the host is apparently not router.
+\end{flushleft}
+\begin{verbatim}
+CheckForwarding () {
+ local sbase fwd
+ sbase=/proc/sys/net/ipv4/conf
+ fwd=0
+ if [ -d $sbase ]; then
+ for dir in $sbase/*/forwarding; do
+ fwd=$[$fwd + `cat $dir`]
+ done
+ else
+ fwd=2
+ fi
+ return $fwd
+}
+\end{verbatim}
+\begin{flushleft}
+\# This function restarts Router Discovery.\\
+\end{flushleft}
+\begin{verbatim}
+RestartRDISC () {
+ killall -HUP rdisc || rdisc -fs
+}
+\end{verbatim}
+\begin{flushleft}
+\# Calculate ABC "natural" mask length\\
+\# Arg: \$1 = dotquad address
+\end{flushleft}
+\begin{verbatim}
+ABCMaskLen () {
+ local class;
+ class=${1%%.*}
+ if [ $class -eq 0 -o $class -ge 224 ]; then return 0
+ elif [ $class -ge 192 ]; then return 24
+ elif [ $class -ge 128 ]; then return 16
+ else return 8 ; fi
+}
+\end{verbatim}
+
+
+\begin{flushleft}
+\# {\bf MAIN()}\\
+\#\\
+\# Strip alias suffix separated by colon.
+\end{flushleft}
+\begin{verbatim}
+label="label $1"
+ldev=$1
+dev=${1%:*}
+if [ "$dev" = "" -o "$1" = "help" ]; then
+ echo "Usage: ifcfg DEV [[add|del [ADDR[/LEN]] [PEER] | stop]" 1>&2
+ echo " add - add new address" 1>&2
+ echo " del - delete address" 1>&2
+ echo " stop - completely disable IP" 1>&2
+ exit 1
+fi
+shift
+
+CheckForwarding
+fwd=$?
+\end{verbatim}
+\begin{flushleft}
+\# Parse command. If it is ``stop'', flush and exit.
+\end{flushleft}
+\begin{verbatim}
+deleting=0
+case "$1" in
+add) shift ;;
+stop)
+ if [ "$ldev" != "$dev" ]; then
+ echo "Cannot stop alias $ldev" 1>&2
+ exit 1;
+ fi
+ ip -4 addr flush dev $dev $label || exit 1
+ if [ $fwd -eq 0 ]; then RestartRDISC; fi
+ exit 0 ;;
+del*)
+ deleting=1; shift ;;
+*)
+esac
+\end{verbatim}
+\begin{flushleft}
+\# Parse prefix, split prefix length, separated by slash.
+\end{flushleft}
+\begin{verbatim}
+ipaddr=
+pfxlen=
+if [ "$1" != "" ]; then
+ ipaddr=${1%/*}
+ if [ "$1" != "$ipaddr" ]; then
+ pfxlen=${1#*/}
+ fi
+ if [ "$ipaddr" = "" ]; then
+ echo "$1 is bad IP address." 1>&2
+ exit 1
+ fi
+fi
+shift
+\end{verbatim}
+\begin{flushleft}
+\# If peer address is present, prefix length is 32.\\
+\# Otherwise, if prefix length was not given, guess it.
+\end{flushleft}
+\begin{verbatim}
+peer=$1
+if [ "$peer" != "" ]; then
+ if [ "$pfxlen" != "" -a "$pfxlen" != "32" ]; then
+ echo "Peer address with non-trivial netmask." 1>&2
+ exit 1
+ fi
+ pfx="$ipaddr peer $peer"
+else
+ if [ "$pfxlen" = "" ]; then
+ ABCMaskLen $ipaddr
+ pfxlen=$?
+ fi
+ pfx="$ipaddr/$pfxlen"
+fi
+if [ "$ldev" = "$dev" -a "$ipaddr" != "" ]; then
+ label=
+fi
+\end{verbatim}
+\begin{flushleft}
+\# If deletion was requested, delete the address and restart RDISC
+\end{flushleft}
+\begin{verbatim}
+if [ $deleting -ne 0 ]; then
+ ip addr del $pfx dev $dev $label || exit 1
+ if [ $fwd -eq 0 ]; then RestartRDISC; fi
+ exit 0
+fi
+\end{verbatim}
+\begin{flushleft}
+\# Start interface initialization.\\
+\#\\
+\# {\bf Step 0} --- enable device \verb|$dev|
+\end{flushleft}
+\begin{verbatim}
+if ! ip link set up dev $dev ; then
+ echo "Error: cannot enable interface $dev." 1>&2
+ exit 1
+fi
+if [ "$ipaddr" = "" ]; then exit 0; fi
+\end{verbatim}
+\begin{flushleft}
+\# {\bf Step 1} --- IP Duplicate Address Detection~\cite{RFC-DHCP}.\\
+\# Send two probes and wait for result for 3 seconds.\\
+\# If the interface opens slower f.e.\ due to long media detection,\\
+\# you want to increase the timeout.\\
+\end{flushleft}
+\begin{verbatim}
+if ! arping -q -c 2 -w 3 -D -I $dev $ipaddr ; then
+ echo "Error: some host already uses address $ipaddr on $dev." 1>&2
+ exit 1
+fi
+\end{verbatim}
+\begin{flushleft}
+\# OK, the address is unique. We may add it to the interface.\\
+\#\\
+\# {\bf Step 2} --- Configure the address on the interface.
+\end{flushleft}
+\begin{verbatim}
+if ! ip address add $pfx brd + dev $dev $label; then
+ echo "Error: failed to add $pfx on $dev." 1>&2
+ exit 1
+fi
+\end{verbatim}
+\noindent\# {\bf Step 3} --- Announce our presence on the link
+\begin{verbatim}
+arping -q -A -c 1 -I $dev $ipaddr
+noarp=$?
+( sleep 2 ;
+ arping -q -U -c 1 -I $dev $ipaddr ) >& /dev/null </dev/null &
+\end{verbatim}
+\begin{flushleft}
+\# {\bf Step 4} (optional) --- Add some control routes.\\
+\#\\
+\# 1. Prohibit link local multicast addresses.\\
+\# 2. Prohibit link local (alias, limited) broadcast.\\
+\# 3. Add default multicast route.
+\end{flushleft}
+\begin{verbatim}
+ip route add unreachable 224.0.0.0/24 >& /dev/null
+ip route add unreachable 255.255.255.255 >& /dev/null
+if [ `ip link ls $dev | grep -c MULTICAST` -ge 1 ]; then
+ ip route add 224.0.0.0/4 dev $dev scope global >& /dev/null
+fi
+\end{verbatim}
+\begin{flushleft}
+\# {\bf Step 5} --- Add fallback default route with huge metric.\\
+\# If a proxy ARP server is present on the interface, we will be\\
+\# able to talk to all the Internet without further configuration.\\
+\# Do not make this step on router or if the device is not ARPable.\\
+\# because dead nexthop detection does not work on them.
+\end{flushleft}
+\begin{verbatim}
+if [ $fwd -eq 0 ]; then
+ if [ $noarp -eq 0 ]; then
+ ip ro append default dev $dev metric 30000 scope global
+ elif [ "$peer" != "" ]; then
+ if ping -q -c 2 -w 4 $peer ; then
+ ip ro append default via $peer dev $dev metric 30001
+ fi
+ fi
+ RestartRDISC
+fi
+
+exit 0
+\end{verbatim}
+\begin{flushleft}
+\# End of {\bf MAIN()}
+\end{flushleft}
+
+
+\end{document}
diff --git a/iproute2/doc/ip-tunnels.tex b/iproute2/doc/ip-tunnels.tex
new file mode 100644
index 0000000..0a8c930
--- /dev/null
+++ b/iproute2/doc/ip-tunnels.tex
@@ -0,0 +1,469 @@
+\documentstyle[12pt,twoside]{article}
+\def\TITLE{Tunnels over IP}
+\input preamble
+\begin{center}
+\Large\bf Tunnels over IP in Linux-2.2
+\end{center}
+
+
+\begin{center}
+{ \large Alexey~N.~Kuznetsov } \\
+\em Institute for Nuclear Research, Moscow \\
+\verb|kuznet@ms2.inr.ac.ru| \\
+\rm March 17, 1999
+\end{center}
+
+\vspace{5mm}
+
+\tableofcontents
+
+
+\section{Instead of introduction: micro-FAQ.}
+
+\begin{itemize}
+
+\item
+Q: In linux-2.0.36 I used:
+\begin{verbatim}
+ ifconfig tunl1 10.0.0.1 pointopoint 193.233.7.65
+\end{verbatim}
+to create tunnel. It does not work in 2.2.0!
+
+A: You are right, it does not work. The command written above is split to two commands.
+\begin{verbatim}
+ ip tunnel add MY-TUNNEL mode ipip remote 193.233.7.65
+\end{verbatim}
+will create tunnel device with name \verb|MY-TUNNEL|. Now you may configure
+it with:
+\begin{verbatim}
+ ifconfig MY-TUNNEL 10.0.0.1
+\end{verbatim}
+Certainly, if you prefer name \verb|tunl1| to \verb|MY-TUNNEL|,
+you still may use it.
+
+\item
+Q: In linux-2.0.36 I used:
+\begin{verbatim}
+ ifconfig tunl0 10.0.0.1
+ route add -net 10.0.0.0 gw 193.233.7.65 dev tunl0
+\end{verbatim}
+to tunnel net 10.0.0.0 via router 193.233.7.65. It does not
+work in 2.2.0! Moreover, \verb|route| prints a funny error sort of
+``network unreachable'' and after this I found a strange direct route
+to 10.0.0.0 via \verb|tunl0| in routing table.
+
+A: Yes, in 2.2 the rule that {\em normal} gateway must reside on directly
+connected network has not any exceptions. You may tell kernel, that
+this particular route is {\em abnormal}:
+\begin{verbatim}
+ ifconfig tunl0 10.0.0.1 netmask 255.255.255.255
+ ip route add 10.0.0.0/8 via 193.233.7.65 dev tunl0 onlink
+\end{verbatim}
+Note keyword \verb|onlink|, it is the magic key that orders kernel
+not to check for consistency of gateway address.
+Probably, after this explanation you have already guessed another method
+to cheat kernel:
+\begin{verbatim}
+ ifconfig tunl0 10.0.0.1 netmask 255.255.255.255
+ route add -host 193.233.7.65 dev tunl0
+ route add -net 10.0.0.0 netmask 255.0.0.0 gw 193.233.7.65
+ route del -host 193.233.7.65 dev tunl0
+\end{verbatim}
+Well, if you like such tricks, nobody may prohibit you to use them.
+Only do not forget
+that between \verb|route add| and \verb|route del| host 193.233.7.65 is
+unreachable.
+
+\item
+Q: In 2.0.36 I used to load \verb|tunnel| device module and \verb|ipip| module.
+I cannot find any \verb|tunnel| in 2.2!
+
+A: Linux-2.2 has single module \verb|ipip| for both directions of tunneling
+and for all IPIP tunnel devices.
+
+\item
+Q: \verb|traceroute| does not work over tunnel! Well, stop... It works,
+ only skips some number of hops.
+
+A: Yes. By default tunnel driver copies \verb|ttl| value from
+inner packet to outer one. It means that path traversed by tunneled
+packets to another endpoint is not hidden. If you dislike this, or if you
+are going to use some routing protocol expecting that packets
+with ttl 1 will reach peering host (f.e.\ RIP, OSPF or EBGP)
+and you are not afraid of
+tunnel loops, you may append option \verb|ttl 64|, when creating tunnel
+with \verb|ip tunnel add|.
+
+\item
+Q: ... Well, list of things, which 2.0 was able to do finishes.
+
+\end{itemize}
+
+\paragraph{Summary of differences between 2.2 and 2.0.}
+
+\begin{itemize}
+
+\item {\bf In 2.0} you could compile tunnel device into kernel
+ and got set of 4 devices \verb|tunl0| ... \verb|tunl3| or,
+ alternatively, compile it as module and load new module
+ for each new tunnel. Also, module \verb|ipip| was necessary
+ to receive tunneled packets.
+
+ {\bf 2.2} has {\em one\/} module \verb|ipip|. Loading it you get base
+ tunnel device \verb|tunl0| and another tunnels may be created with command
+ \verb|ip tunnel add|. These new devices may have arbitrary names.
+
+
+\item {\bf In 2.0} you set remote tunnel endpoint address with
+ the command \verb|ifconfig| ... \verb|pointopoint A|.
+
+ {\bf In 2.2} this command has the same semantics on all
+ the interfaces, namely it sets not tunnel endpoint,
+ but address of peering host, which is directly reachable
+ via this tunnel,
+ rather than via Internet. Actual tunnel endpoint address \verb|A|
+ should be set with \verb|ip tunnel add ... remote A|.
+
+\item {\bf In 2.0} you create tunnel routes with the command:
+\begin{verbatim}
+ route add -net 10.0.0.0 gw A dev tunl0
+\end{verbatim}
+
+ {\bf 2.2} interprets this command equally for all device
+ kinds and gateway is required to be directly reachable via this tunnel,
+ rather than via Internet. You still may use \verb|ip route add ... onlink|
+ to override this behaviour.
+
+\end{itemize}
+
+
+\section{Tunnel setup: basics}
+
+Standard Linux-2.2 kernel supports three flavor of tunnels,
+listed in the following table:
+\vspace{2mm}
+
+\begin{tabular}{lll}
+\vrule depth 0.8ex width 0pt\relax
+Mode & Description & Base device \\
+ipip & IP over IP & tunl0 \\
+sit & IPv6 over IP & sit0 \\
+gre & ANY over GRE over IP & gre0
+\end{tabular}
+
+\vspace{2mm}
+
+\noindent All the kinds of tunnels are created with one command:
+\begin{verbatim}
+ ip tunnel add <NAME> mode <MODE> [ local <S> ] [ remote <D> ]
+\end{verbatim}
+
+This command creates new tunnel device with name \verb|<NAME>|.
+The \verb|<NAME>| is an arbitrary string. Particularly,
+it may be even \verb|eth0|. The rest of parameters set
+different tunnel characteristics.
+
+\begin{itemize}
+
+\item
+\verb|mode <MODE>| sets tunnel mode. Three modes are available now
+ \verb|ipip|, \verb|sit| and \verb|gre|.
+
+\item
+\verb|remote <D>| sets remote endpoint of the tunnel to IP
+ address \verb|<D>|.
+\item
+\verb|local <S>| sets fixed local address for tunneled
+ packets. It must be an address on another interface of this host.
+
+\end{itemize}
+
+\let\thefootnote\oldthefootnote
+
+Both \verb|remote| and \verb|local| may be omitted. In this case we
+say that they are zero or wildcard. Two tunnels of one mode cannot
+have the same \verb|remote| and \verb|local|. Particularly it means
+that base device or fallback tunnel cannot be replicated.\footnote{
+This restriction is relaxed for keyed GRE tunnels.}
+
+Tunnels are divided to two classes: {\bf pointopoint} tunnels, which
+have some not wildcard \verb|remote| address and deliver all the packets
+to this destination, and {\bf NBMA} (i.e. Non-Broadcast Multi-Access) tunnels,
+which have no \verb|remote|. Particularly, base devices (f.e.\ \verb|tunl0|)
+are NBMA, because they have neither \verb|remote| nor
+\verb|local| addresses.
+
+
+After tunnel device is created you should configure it as you did
+it with another devices. Certainly, the configuration of tunnels has
+some features related to the fact that they work over existing Internet
+routing infrastructure and simultaneously create new virtual links,
+which changes this infrastructure. The danger that not enough careful
+tunnel setup will result in formation of tunnel loops,
+collapse of routing or flooding network with exponentially
+growing number of tunneled fragments is very real.
+
+
+Protocol setup on pointopoint tunnels does not differ of configuration
+of another devices. You should set a protocol address with \verb|ifconfig|
+and add routes with \verb|route| utility.
+
+NBMA tunnels are different. To route something via NBMA tunnel
+you have to explain to driver, where it should deliver packets to.
+The only way to make it is to create special routes with gateway
+address pointing to desired endpoint. F.e.\
+\begin{verbatim}
+ ip route add 10.0.0.0/24 via <A> dev tunl0 onlink
+\end{verbatim}
+It is important to use option \verb|onlink|, otherwise
+kernel will refuse request to create route via gateway not directly
+reachable over device \verb|tunl0|. With IPv6 the situation is much simpler:
+when you start device \verb|sit0|, it automatically configures itself
+with all IPv4 addresses mapped to IPv6 space, so that all IPv4
+Internet is {\em really reachable} via \verb|sit0|! Excellent, the command
+\begin{verbatim}
+ ip route add 3FFE::/16 via ::193.233.7.65 dev sit0
+\end{verbatim}
+will route \verb|3FFE::/16| via \verb|sit0|, sending all the packets
+destined to this prefix to 193.233.7.65.
+
+\section{Tunnel setup: options}
+
+Command \verb|ip tunnel add| has several additional options.
+\begin{itemize}
+
+\item \verb|ttl N| --- set fixed TTL \verb|N| on tunneled packets.
+ \verb|N| is number in the range 1--255. 0 is special value,
+ meaning that packets inherit TTL value.
+ Default value is: \verb|inherit|.
+
+\item \verb|tos T| --- set fixed tos \verb|T| on tunneled packets.
+ Default value is: \verb|inherit|.
+
+\item \verb|dev DEV| --- bind tunnel to device \verb|DEV|, so that
+ tunneled packets will be routed only via this device and will
+ not be able to escape to another device, when route to endpoint changes.
+
+\item \verb|nopmtudisc| --- disable Path MTU Discovery on this tunnel.
+ It is enabled by default. Note that fixed ttl is incompatible
+ with this option: tunnels with fixed ttl always make pmtu discovery.
+
+\end{itemize}
+
+\verb|ipip| and \verb|sit| tunnels have no more options. \verb|gre|
+tunnels are more complicated:
+
+\begin{itemize}
+
+\item \verb|key K| --- use keyed GRE with key \verb|K|. \verb|K| is
+ either number or IP address-like dotted quad.
+
+\item \verb|csum| --- checksum tunneled packets.
+
+\item \verb|seq| --- serialize packets.
+\begin{NB}
+ I think this option does not
+ work. At least, I did not test it, did not debug it and
+ even do not understand, how it is supposed to work and for what
+ purpose Cisco planned to use it.
+\end{NB}
+
+\end{itemize}
+
+
+Actually, these GRE options can be set separately for input and
+output directions by prefixing corresponding keywords with letter
+\verb|i| or \verb|o|. F.e.\ \verb|icsum| orders to accept only
+packets with correct checksum and \verb|ocsum| means, that
+our host will calculate and send checksum.
+
+Command \verb|ip tunnel add| is not the only operation,
+which can be made with tunnels. Certainly, you may get short help page
+with:
+\begin{verbatim}
+ ip tunnel help
+\end{verbatim}
+
+Besides that, you may view list of installed tunnels with the help of command:
+\begin{verbatim}
+ ip tunnel ls
+\end{verbatim}
+Also you may look at statistics:
+\begin{verbatim}
+ ip -s tunnel ls Cisco
+\end{verbatim}
+where \verb|Cisco| is name of tunnel device. Command
+\begin{verbatim}
+ ip tunnel del Cisco
+\end{verbatim}
+destroys tunnel \verb|Cisco|. And, finally,
+\begin{verbatim}
+ ip tunnel change Cisco mode sit local ME remote HE ttl 32
+\end{verbatim}
+changes its parameters.
+
+\section{Differences 2.2 and 2.0 tunnels revisited.}
+
+Now we can discuss more subtle differences between tunneling in 2.0
+and 2.2.
+
+\begin{itemize}
+
+\item In 2.0 all tunneled packets were received promiscuously
+as soon as you loaded module \verb|ipip|. 2.2 tries to select the best
+tunnel device and packet looks as received on this. F.e.\ if host
+received \verb|ipip| packet from host \verb|D| destined to our
+local address \verb|S|, kernel searches for matching tunnels
+in order:
+
+\begin{tabular}{ll}
+1 & \verb|remote| is \verb|D| and \verb|local| is \verb|S| \\
+2 & \verb|remote| is \verb|D| and \verb|local| is wildcard \\
+3 & \verb|remote| is wildcard and \verb|local| is \verb|S| \\
+4 & \verb|tunl0|
+\end{tabular}
+
+If tunnel exists, but it is not in \verb|UP| state, the tunnel is ignored.
+Note, that if \verb|tunl0| is \verb|UP| it receives all the IPIP packets,
+not acknowledged by more specific tunnels.
+Be careful, it means that without carefully installed firewall rules
+anyone on the Internet may inject to your network any packets with
+source addresses indistinguishable from local ones. It is not so bad idea
+to design tunnels in the way enforcing maximal route symmetry
+and to enable reversed path filter (\verb|rp_filter| sysctl option) on
+tunnel devices.
+
+\item In 2.2 you can monitor and debug tunnels with \verb|tcpdump|.
+F.e.\ \verb|tcpdump| \verb|-i Cisco| \verb|-nvv| will dump packets,
+which kernel output, via tunnel \verb|Cisco| and the packets received on it
+from kernel viewpoint.
+
+\end{itemize}
+
+
+\section{Linux and Cisco IOS tunnels.}
+
+Among another tunnels Cisco IOS supports IPIP and GRE.
+Essentially, Cisco setup is subset of options, available for Linux.
+Let us consider the simplest example:
+
+\begin{verbatim}
+interface Tunnel0
+ tunnel mode gre ip
+ tunnel source 10.10.14.1
+ tunnel destination 10.10.13.2
+\end{verbatim}
+
+
+This command set translates to:
+
+\begin{verbatim}
+ ip tunnel add Tunnel0 \
+ mode gre \
+ local 10.10.14.1 \
+ remote 10.10.13.2
+\end{verbatim}
+
+Any questions? No questions.
+
+\section{Interaction IPIP tunnels and DVMRP.}
+
+DVMRP exploits IPIP tunnels to route multicasts via Internet.
+\verb|mrouted| creates
+IPIP tunnels listed in its configuration file automatically.
+From kernel and user viewpoints there are no differences between
+tunnels, created in this way, and tunnels created by \verb|ip tunnel|.
+I.e.\ if \verb|mrouted| created some tunnel, it may be used to
+route unicast packets, provided appropriate routes are added.
+And vice versa, if administrator has already created a tunnel,
+it will be reused by \verb|mrouted|, if it requests DVMRP
+tunnel with the same local and remote addresses.
+
+Do not wonder, if your manually configured tunnel is
+destroyed, when mrouted exits.
+
+
+\section{Broadcast GRE ``tunnels''.}
+
+It is possible to set \verb|remote| for GRE tunnel to a multicast
+address. Such tunnel becomes {\bf broadcast} tunnel (though word
+tunnel is not quite appropriate in this case, it is rather virtual network).
+\begin{verbatim}
+ ip tunnel add Universe local 193.233.7.65 \
+ remote 224.66.66.66 ttl 16
+ ip addr add 10.0.0.1/16 dev Universe
+ ip link set Universe up
+\end{verbatim}
+This tunnel is true broadcast network and broadcast packets are
+sent to multicast group 224.66.66.66. By default such tunnel starts
+to resolve both IP and IPv6 addresses via ARP/NDISC, so that
+if multicast routing is supported in surrounding network, all GRE nodes
+will find one another automatically and will form virtual Ethernet-like
+broadcast network. If multicast routing does not work, it is unpleasant
+but not fatal flaw. The tunnel becomes NBMA rather than broadcast network.
+You may disable dynamic ARPing by:
+\begin{verbatim}
+ echo 0 > /proc/sys/net/ipv4/neigh/Universe/mcast_solicit
+\end{verbatim}
+and to add required information to ARP tables manually:
+\begin{verbatim}
+ ip neigh add 10.0.0.2 lladdr 128.6.190.2 dev Universe nud permanent
+\end{verbatim}
+In this case packets sent to 10.0.0.2 will be encapsulated in GRE
+and sent to 128.6.190.2. It is possible to facilitate address resolution
+using methods typical for another NBMA networks f.e.\ to start user
+level \verb|arpd| daemon, which will maintain database of hosts attached
+to GRE virtual network or ask for information
+dedicated ARP or NHRP server.
+
+
+Actually, such setup is the most natural for tunneling,
+it is really flexible, scalable and easily managable, so that
+it is strongly recommended to be used with GRE tunnels instead of ugly
+hack with NBMA mode and \verb|onlink| modifier. Unfortunately,
+by historical reasons broadcast mode is not supported by IPIP tunnels,
+but this probably will change in future.
+
+
+
+\section{Traffic control issues.}
+
+Tunnels are devices, hence all the power of Linux traffic control
+applies to them. The simplest (and the most useful in practice)
+example is limiting tunnel bandwidth. The following command:
+\begin{verbatim}
+ tc qdisc add dev tunl0 root tbf \
+ rate 128Kbit burst 4K limit 10K
+\end{verbatim}
+will limit tunneled traffic to 128Kbit with maximal burst size of 4K
+and queuing not more than 10K.
+
+However, you should remember, that tunnels are {\em virtual} devices
+implemented in software and true queue management is impossible for them
+just because they have no queues. Instead, it is better to create classes
+on real physical interfaces and to map tunneled packets to them.
+In general case of dynamic routing you should create such classes
+on all outgoing interfaces, or, alternatively,
+to use option \verb|dev DEV| to bind tunnel to a fixed physical device.
+In the last case packets will be routed only via specified device
+and you need to setup corresponding classes only on it.
+Though you have to pay for this convenience,
+if routing will change, your tunnel will fail.
+
+Suppose that CBQ class \verb|1:ABC| has been created on device \verb|eth0|
+specially for tunnel \verb|Cisco| with endpoints \verb|S| and \verb|D|.
+Now you can select IPIP packets with addresses \verb|S| and \verb|D|
+with some classifier and map them to class \verb|1:ABC|. F.e.\
+it is easy to make with \verb|rsvp| classifier:
+\begin{verbatim}
+ tc filter add dev eth0 pref 100 proto ip rsvp \
+ session D ipproto ipip filter S \
+ classid 1:ABC
+\end{verbatim}
+
+If you want to make more detailed classification of sub-flows
+transmitted via tunnel, you can build CBQ subtree,
+rooted at \verb|1:ABC| and attach to subroot set of rules parsing
+IPIP packets more deeply.
+
+\end{document}
diff --git a/iproute2/doc/nstat.sgml b/iproute2/doc/nstat.sgml
new file mode 100644
index 0000000..48cacc6
--- /dev/null
+++ b/iproute2/doc/nstat.sgml
@@ -0,0 +1,110 @@
+<!doctype linuxdoc system>
+
+<article>
+
+<title>NSTAT, IFSTAT and RTACCT Utilities
+<author>Alexey Kuznetsov, <tt/kuznet@ms2.inr.ac.ru/
+<date>some_negative_number, 20 Sep 2001
+<abstract>
+<tt/nstat/, <tt/ifstat/ and <tt/rtacct/ are simple tools helping
+to monitor kernel snmp counters and network interface statistics.
+</abstract>
+
+<p> These utilities are very similar, so that I describe
+them simultaneously, using name <tt/Xstat/ in the places which apply
+to all of them.
+
+<p>The format of the command is:
+
+<tscreen><verb>
+ Xstat [ OPTIONS ] [ PATTERN [ PATTERN ... ] ]
+</verb></tscreen>
+
+<p>
+<tt/PATTERN/ is shell style pattern, selecting identifier
+of SNMP variables or interfaces to show. Variable is displayed
+if one of patterns matches its name. If no patterns are given,
+<tt/Xstat/ assumes that user wants to see all the variables.
+
+<p> <tt/OPTIONS/ is list of single letter options, using common unix
+conventions.
+
+<itemize>
+<item><tt/-h/ - show help page
+<item><tt/-?/ - the same, of course
+<item><tt/-v/, <tt/-V/ - print version of <tt/Xstat/ and exit
+<item><tt/-z/ - dump zero counters too. By default they are not shown.
+<item><tt/-a/ - dump absolute values of counters. By default <tt/Xstat/
+ calculates increments since the previous use.
+<item><tt/-s/ - do not update history, so that the next time you will
+ see counters including values accumulated to the moment
+ of this measurement too.
+<item><tt/-n/ - do not display anything, only update history.
+<item><tt/-r/ - reset history.
+<item><tt/-d INTERVAL/ - <tt/Xstat/ is run in daemon mode collecting
+ statistics. <tt/INTERVAL/ is interval between measurements
+ in seconds.
+<item><tt/-t INTERVAL/ - time interval to average rates. Default value
+ is 60 seconds.
+<item><tt/-e/ - display extended information about errors (<tt/ifstat/ only).
+</itemize>
+
+<p>
+History is just dump saved in file <tt>/tmp/.Xstat.uUID</tt>
+or in file given by environment variables <tt/NSTAT_HISTORY/,
+<tt/IFSTAT_HISTORY/ and <tt/RTACCT_HISTORY/.
+Each time when you use <tt/Xstat/ values there are updated.
+If you use patterns, only the values which you _really_ see
+are updated. If you want to skip an unintersting period,
+use option <tt/-n/, or just output to <tt>/dev/null</tt>.
+
+<p>
+<tt/Xstat/ understands when history is invalidated by system reboot
+or source of information switched between different instances
+of daemonic <tt/Xstat/ and kernel SNMP tables and does not
+use invalid history.
+
+<p> Beware, <tt/Xstat/ will not produce sane output,
+when many processes use it simultaneously. If several processes
+under single user need this utility they should use environment
+variables to put their history in safe places
+or to use it with options <tt/-a -s/.
+
+<p>
+Well, that's all. The utility is very simple, but nevertheless
+very handy.
+
+<p> <bf/Output of XSTAT/
+<p> The first line of output is <tt/#/ followed by identifier
+of source of information, it may be word <tt/kernel/, when <tt/Xstat/
+gets information from kernel or some dotted decimal number followed
+by parameters, when it obtains information from running <tt/Xstat/ daemon.
+
+<p>In the case of <tt/nstat/ the rest of output consists of three columns:
+SNMP MIB identifier,
+its value (or increment since previous measurement) and average
+rate of increase of the counter per second. <tt/ifstat/ outputs
+interface name followed by pairs of counter and rate of its change.
+
+<p> <bf/Daemonic Xstat/
+<p> <tt/Xstat/ may be started as daemon by any user. This makes sense
+to avoid wrapped counters and to obtain reasonable long counters
+for large time. Also <tt/Xstat/ daemon calculates average rates.
+For the first goal sampling interval (option <tt/-d/) may be large enough,
+f.e. for gigabit rates byte counters overflow not more frequently than
+each 40 seconds and you may select interval of 20 seconds.
+From the other hand, when <tt/Xstat/ is used for estimating rates
+interval should be less than averaging period (option <tt/-t/), otherwise
+estimation loses in quality.
+
+Client <tt/Xstat/, before trying to get information from the kernel,
+contacts daemon started by this user, then it tries system wide
+daemon, which is supposed to be started by superuser. And only if
+none of them replied it gets information from kernel.
+
+<p> <bf/Environment/
+<p> <tt/NSTAT_HISTORY/ - name of history file for <tt/nstat/.
+<p> <tt/IFSTAT_HISTORY/ - name of history file for <tt/ifstat/.
+<p> <tt/RTACCT_HISTORY/ - name of history file for <tt/rtacct/.
+
+</article>
diff --git a/iproute2/doc/preamble.tex b/iproute2/doc/preamble.tex
new file mode 100644
index 0000000..80ca508
--- /dev/null
+++ b/iproute2/doc/preamble.tex
@@ -0,0 +1,26 @@
+\textwidth 6.0in
+\textheight 8.5in
+
+\input SNAPSHOT
+
+\pagestyle{myheadings}
+\markboth{\protect\TITLE}{}
+\markright{{\protect\sc iproute2-ss\Draft}}
+
+% To print it in compact form: both sides on one sheet (psnup -2)
+\evensidemargin=\oddsidemargin
+
+\newenvironment{NB}{\bgroup \vskip 1mm\leftskip 1cm \footnotesize \noindent NB.
+}{\par\egroup \vskip 1mm}
+
+\def\threeonly{[2.3.15+ only] }
+
+\begin{document}
+
+\makeatletter
+\renewcommand{\@oddhead}{{\protect\sc iproute2-ss\Draft} \hfill \protect\arabic{page}}
+\makeatother
+\let\oldthefootnote\thefootnote
+\def\thefootnote{}
+\footnotetext{Copyright \copyright~1999 A.N.Kuznetsov}
+
diff --git a/iproute2/doc/rtstat.sgml b/iproute2/doc/rtstat.sgml
new file mode 100644
index 0000000..07391c3
--- /dev/null
+++ b/iproute2/doc/rtstat.sgml
@@ -0,0 +1,52 @@
+<!doctype linuxdoc system>
+
+<article>
+
+<title>RTACCT Utility
+<author>Robert Olsson
+<date>some_negative_number, 20 Dec 2001
+
+<p>
+Here is some code for monitoring the route cache. For systems handling high
+network load, servers, routers, firewalls etc the route cache and its garbage
+collection is crucial. Linux has a solid implementation.
+
+<p>
+The kernel patch (not required since linux-2.4.7) adds statistics counters
+from route cache process into
+/proc/net/rt_cache_stat. A companion user mode program presents the statistics
+in a vmstat or iostat manner. The ratio between cache hits and misses gives
+the flow length.
+
+<p>
+Hopefully it can help understanding performance and DoS and other related
+issues.
+
+<p> An URL where newer versions of this utility can be (probably) found
+is ftp://robur.slu.se/pub/Linux/net-development/rt_cache_stat/
+
+
+<p><bf/Description/
+
+<p>The format of the command is:
+
+<tscreen><verb>
+ rtstat [ OPTIONS ]
+</verb></tscreen>
+
+<p> <tt/OPTIONS/ are:
+
+<itemize>
+
+<item><tt/-h/, <tt/-help/ - show help page and version of the utility.
+
+<item><tt/-i INTERVAL/ - interval between snapshots, default value is
+2 seconds.
+
+<item><tt/-s NUMBER/ - whether to print header line. 0 inhibits header line,
+1 prescribes to print it once and 2 (this is default setting) forces header
+line each 20 lines.
+
+</itemize>
+
+</article>
diff --git a/iproute2/doc/ss.sgml b/iproute2/doc/ss.sgml
new file mode 100644
index 0000000..3024b57
--- /dev/null
+++ b/iproute2/doc/ss.sgml
@@ -0,0 +1,525 @@
+<!doctype linuxdoc system>
+
+<article>
+
+<title>SS Utility: Quick Intro
+<author>Alexey Kuznetsov, <tt/kuznet@ms2.inr.ac.ru/
+<date>some_negative_number, 20 Sep 2001
+<abstract>
+<tt/ss/ is one another utility to investigate sockets.
+Functionally it is NOT better than <tt/netstat/ combined
+with some perl/awk scripts and though it is surely faster
+it is not enough to make it much better. :-)
+So, stop reading this now and do not waste your time.
+Well, certainly, it proposes some functionality, which current
+netstat is still not able to do, but surely will soon.
+</abstract>
+
+<sect>Why?
+
+<p> <tt>/proc</tt> interface is inadequate, unfortunately.
+When amount of sockets is enough large, <tt/netstat/ or even
+plain <tt>cat /proc/net/tcp/</tt> cause nothing but pains and curses.
+In linux-2.4 the desease became worse: even if amount
+of sockets is small reading <tt>/proc/net/tcp/</tt> is slow enough.
+
+This utility presents a new approach, which is supposed to scale
+well. I am not going to describe technical details here and
+will concentrate on description of the command.
+The only important thing to say is that it is not so bad idea
+to load module <tt/tcp_diag/, which can be found in directory
+<tt/Modules/ of <tt/iproute2/. If you do not make this <tt/ss/
+will work, but it falls back to <tt>/proc</tt> and becomes slow
+like <tt/netstat/, well, a bit faster yet (see section "Some numbers").
+
+<sect>Old news
+
+<p>
+In the simplest form <tt/ss/ is equivalent to netstat
+with some small deviations.
+
+<itemize>
+<item><tt/ss -t -a/ dumps all TCP sockets
+<item><tt/ss -u -a/ dumps all UDP sockets
+<item><tt/ss -w -a/ dumps all RAW sockets
+<item><tt/ss -x -a/ dumps all UNIX sockets
+</itemize>
+
+<p>
+Option <tt/-o/ shows TCP timers state.
+Option <tt/-e/ shows some extended information.
+Etc. etc. etc. Seems, all the options of netstat related to sockets
+are supported. Though not AX.25 and other bizarres. :-)
+If someone wants, he can make support for decnet and ipx.
+Some rudimentary support for them is already present in iproute2 libutils,
+and I will be glad to see these new members.
+
+<p>
+However, standard functionality is a bit different:
+
+<p>
+The first: without option <tt/-a/ sockets in states
+<tt/TIME-WAIT/ and <tt/SYN-RECV/ are skipped too.
+It is more reasonable default, I think.
+
+<p>
+The second: format of UNIX sockets is different. It coincides
+with tcp/udp. Though standard kernel still does not allow to
+see write/read queues and peer address of connected UNIX sockets,
+the patch doing this exists.
+
+<p>
+The third: default is to dump only TCP sockets, rather than all of the types.
+
+<p>
+The next: by default it does not resolve numeric host addresses (like <tt/ip/)!
+Resolving is enabled with option <tt/-r/. Service names, usually stored
+in local files, are resolved by default. Also, if service database
+does not contain references to a port, <tt/ss/ queries system
+<tt/rpcbind/. RPC services are prefixed with <tt/rpc./
+Resolution of services may be suppressed with option <tt/-n/.
+
+<p>
+It does not accept "long" options (I dislike them, sorry).
+So, address family is given with family identifier following
+option <tt/-f/ to be algined to iproute2 conventions.
+Mostly, it is to allow option parser to parse
+addresses correctly, but as side effect it really limits dumping
+to sockets supporting only given family. Option <tt/-A/ followed
+by list of socket tables to dump is also supported.
+Logically, id of socket table is different of _address_ family, which is
+another point of incompatibility. So, id is one of
+<tt/all/, <tt/tcp/, <tt/udp/,
+<tt/raw/, <tt/inet/, <tt/unix/, <tt/packet/, <tt/netlink/. See?
+Well, <tt/inet/ is just abbreviation for <tt/tcp|udp|raw/
+and it is not difficult to guess that <tt/packet/ allows
+to look at packet sockets. Actually, there are also some other abbreviations,
+f.e. <tt/unix_dgram/ selects only datagram UNIX sockets.
+
+<p>
+The next: well, I still do not know. :-)
+
+
+
+
+<sect>Time to talk about new functionality.
+
+<p>It is builtin filtering of socket lists.
+
+<sect1> Filtering by state.
+
+<p>
+<tt/ss/ allows to filter socket states, using keywords
+<tt/state/ and <tt/exclude/, followed by some state
+identifier.
+
+<p>
+State identifier are standard TCP state names (not listed,
+they are useless for you if you already do not know them)
+or abbreviations:
+
+<itemize>
+<item><tt/all/ - for all the states
+<item><tt/bucket/ - for TCP minisockets (<tt/TIME-WAIT|SYN-RECV/)
+<item><tt/big/ - all except for minisockets
+<item><tt/connected/ - not closed and not listening
+<item><tt/synchronized/ - connected and not <tt/SYN-SENT/
+</itemize>
+
+<p>
+ F.e. to dump all tcp sockets except <tt/SYN-RECV/:
+
+<tscreen><verb>
+ ss exclude SYN-RECV
+</verb></tscreen>
+
+<p>
+ If neither <tt/state/ nor <tt/exclude/ directives
+ are present,
+ state filter defaults to <tt/all/ with option <tt/-a/
+ or to <tt/all/,
+ excluding listening, syn-recv, time-wait and closed sockets.
+
+<sect1> Filtering by addresses and ports.
+
+<p>
+Option list may contain address/port filter.
+It is boolean expression which consists of boolean operation
+<tt/or/, <tt/and/, <tt/not/ and predicates.
+Actually, all the flavors of names for boolean operations are eaten:
+<tt/&/, <tt/&&/, <tt/|/, <tt/||/, <tt/!/, but do not forget
+about special sense given to these symbols by unix shells and escape
+them correctly, when used from command line.
+
+<p>
+Predicates may be of the folowing kinds:
+
+<itemize>
+<item>A. Address/port match, where address is checked against mask
+ and port is either wildcard or exact. It is one of:
+
+<tscreen><verb>
+ dst prefix:port
+ src prefix:port
+ src unix:STRING
+ src link:protocol:ifindex
+ src nl:channel:pid
+</verb></tscreen>
+
+ Both prefix and port may be absent or replaced with <tt/*/,
+ which means wildcard. UNIX socket use more powerful scheme
+ matching to socket names by shell wildcards. Also, prefixes
+ unix: and link: may be omitted, if address family is evident
+ from context (with option <tt/-x/ or with <tt/-f unix/
+ or with <tt/unix/ keyword)
+
+<p>
+ F.e.
+
+<tscreen><verb>
+ dst 10.0.0.1
+ dst 10.0.0.1:
+ dst 10.0.0.1/32:
+ dst 10.0.0.1:*
+</verb></tscreen>
+ are equivalent and mean socket connected to
+ any port on host 10.0.0.1
+
+<tscreen><verb>
+ dst 10.0.0.0/24:22
+</verb></tscreen>
+ sockets connected to port 22 on network
+ 10.0.0.0...255.
+
+<p>
+ Note that port separated of address with colon, which creates
+ troubles with IPv6 addresses. Generally, we interpret the last
+ colon as splitting port. To allow to give IPv6 addresses,
+ trick like used in IPv6 HTTP URLs may be used:
+
+<tscreen><verb>
+ dst [::1]
+</verb></tscreen>
+ are sockets connected to ::1 on any port
+
+<p>
+ Another way is <tt/dst ::1/128/. / helps to understand that
+ colon is part of IPv6 address.
+
+<p>
+ Now we can add another alias for <tt/dst 10.0.0.1/:
+ <tt/dst [10.0.0.1]/. :-)
+
+<p> Address may be a DNS name. In this case all the addresses are looked
+ up (in all the address families, if it is not limited by option <tt/-f/
+ or special address prefix <tt/inet:/, <tt/inet6/) and resulting
+ expression is <tt/or/ over all of them.
+
+<item> B. Port expressions:
+<tscreen><verb>
+ dport >= :1024
+ dport != :22
+ sport < :32000
+</verb></tscreen>
+ etc.
+
+ All the relations: <tt/</, <tt/>/, <tt/=/, <tt/>=/, <tt/=/, <tt/==/,
+ <tt/!=/, <tt/eq/, <tt/ge/, <tt/lt/, <tt/ne/...
+ Use variant which you like more, but not forget to escape special
+ characters when typing them in command line. :-)
+
+ Note that port number syntactically coincides to the case A!
+ You may even add an IP address, but it will not participate
+ incomparison, except for <tt/==/ and <tt/!=/, which are equivalent
+ to corresponding predicates of type A. F.e.
+<p>
+<tt/dst 10.0.0.1:22/
+ is equivalent to <tt/dport eq 10.0.0.1:22/
+ and
+ <tt/not dst 10.0.0.1:22/ is equivalent to
+ <tt/dport neq 10.0.0.1:22/
+
+<item>C. Keyword <tt/autobound/. It matches to sockets bound automatically
+ on local system.
+
+</itemize>
+
+
+<sect> Examples
+
+<p>
+<itemize>
+<item>1. List all the tcp sockets in state <tt/FIN-WAIT-1/ for our apache
+ to network 193.233.7/24 and look at their timers:
+
+<tscreen><verb>
+ ss -o state fin-wait-1 \( sport = :http or sport = :https \) \
+ dst 193.233.7/24
+</verb></tscreen>
+
+ Oops, forgot to say that missing logical operation is
+ equivalent to <tt/and/.
+
+<item> 2. Well, now look at the rest...
+
+<tscreen><verb>
+ ss -o excl fin-wait-1
+ ss state fin-wait-1 \( sport neq :http and sport neq :https \) \
+ or not dst 193.233.7/24
+</verb></tscreen>
+
+ Note that we have to do _two_ calls of ss to do this.
+ State match is always anded to address/port match.
+ The reason for this is purely technical: ss does fast skip of
+ not matching states before parsing addresses and I consider the
+ ability to skip fastly gobs of time-wait and syn-recv sockets
+ as more important than logical generality.
+
+<item> 3. So, let's look at all our sockets using autobound ports:
+
+<tscreen><verb>
+ ss -a -A all autobound
+</verb></tscreen>
+
+
+<item> 4. And eventually find all the local processes connected
+ to local X servers:
+
+<tscreen><verb>
+ ss -xp dst "/tmp/.X11-unix/*"
+</verb></tscreen>
+
+ Pardon, this does not work with current kernel, patching is required.
+ But we still can look at server side:
+
+<tscreen><verb>
+ ss -x src "/tmp/.X11-unix/*"
+</verb></tscreen>
+
+</itemize>
+
+
+<sect> Returning to ground: real manual
+
+<p>
+<sect1> Command arguments
+
+<p> General format of arguments to <tt/ss/ is:
+
+<tscreen><verb>
+ ss [ OPTIONS ] [ STATE-FILTER ] [ ADDRESS-FILTER ]
+</verb></tscreen>
+
+<sect2><tt/OPTIONS/
+<p> <tt/OPTIONS/ is list of single letter options, using common unix
+conventions.
+
+<itemize>
+<item><tt/-h/ - show help page
+<item><tt/-?/ - the same, of course
+<item><tt/-v/, <tt/-V/ - print version of <tt/ss/ and exit
+<item><tt/-s/ - print summary statistics. This option does not parse
+socket lists obtaining summary from various sources. It is useful
+when amount of sockets is so huge that parsing <tt>/proc/net/tcp</tt>
+is painful.
+<item><tt/-D FILE/ - do not display anything, just dump raw information
+about TCP sockets to <tt/FILE/ after applying filters. If <tt/FILE/ is <tt/-/
+<tt/stdout/ is used.
+<item><tt/-F FILE/ - read continuation of filter from <tt/FILE/.
+Each line of <tt/FILE/ is interpreted like single command line option.
+If <tt/FILE/ is <tt/-/ <tt/stdin/ is used.
+<item><tt/-r/ - try to resolve numeric address/ports
+<item><tt/-n/ - do not try to resolve ports
+<item><tt/-o/ - show some optional information, f.e. TCP timers
+<item><tt/-i/ - show some infomration specific to TCP (RTO, congestion
+window, slow start threshould etc.)
+<item><tt/-e/ - show even more optional information
+<item><tt/-m/ - show extended information on memory used by the socket.
+It is available only with <tt/tcp_diag/ enabled.
+<item><tt/-p/ - show list of processes owning the socket
+<item><tt/-f FAMILY/ - default address family used for parsing addresses.
+ Also this option limits listing to sockets supporting
+ given address family. Currently the following families
+ are supported: <tt/unix/, <tt/inet/, <tt/inet6/, <tt/link/,
+ <tt/netlink/.
+<item><tt/-4/ - alias for <tt/-f inet/
+<item><tt/-6/ - alias for <tt/-f inet6/
+<item><tt/-0/ - alias for <tt/-f link/
+<item><tt/-A LIST-OF-TABLES/ - list of socket tables to dump, separated
+ by commas. The following identifiers are understood:
+ <tt/all/, <tt/inet/, <tt/tcp/, <tt/udp/, <tt/raw/,
+ <tt/unix/, <tt/packet/, <tt/netlink/, <tt/unix_dgram/,
+ <tt/unix_stream/, <tt/packet_raw/, <tt/packet_dgram/.
+<item><tt/-x/ - alias for <tt/-A unix/
+<item><tt/-t/ - alias for <tt/-A tcp/
+<item><tt/-u/ - alias for <tt/-A udp/
+<item><tt/-w/ - alias for <tt/-A raw/
+<item><tt/-a/ - show sockets of all the states. By default sockets
+ in states <tt/LISTEN/, <tt/TIME-WAIT/, <tt/SYN_RECV/
+ and <tt/CLOSE/ are skipped.
+<item><tt/-l/ - show only sockets in state <tt/LISTEN/
+</itemize>
+
+<sect2><tt/STATE-FILTER/
+
+<p><tt/STATE-FILTER/ allows to construct arbitrary set of
+states to match. Its syntax is sequence of keywords <tt/state/
+and <tt/exclude/ followed by identifier of state.
+Available identifiers are:
+
+<p>
+<itemize>
+<item> All standard TCP states: <tt/established/, <tt/syn-sent/,
+<tt/syn-recv/, <tt/fin-wait-1/, <tt/fin-wait-2/, <tt/time-wait/,
+<tt/closed/, <tt/close-wait/, <tt/last-ack/, <tt/listen/ and <tt/closing/.
+
+<item><tt/all/ - for all the states
+<item><tt/connected/ - all the states except for <tt/listen/ and <tt/closed/
+<item><tt/synchronized/ - all the <tt/connected/ states except for
+<tt/syn-sent/
+<item><tt/bucket/ - states, which are maintained as minisockets, i.e.
+<tt/time-wait/ and <tt/syn-recv/.
+<item><tt/big/ - opposite to <tt/bucket/
+</itemize>
+
+<sect2><tt/ADDRESS_FILTER/
+
+<p><tt/ADDRESS_FILTER/ is boolean expression with operations <tt/and/, <tt/or/
+and <tt/not/, which can be abbreviated in C style f.e. as <tt/&/,
+<tt/&&/.
+
+<p>
+Predicates check socket addresses, both local and remote.
+There are the following kinds of predicates:
+
+<itemize>
+<item> <tt/dst ADDRESS_PATTERN/ - matches remote address and port
+<item> <tt/src ADDRESS_PATTERN/ - matches local address and port
+<item> <tt/dport RELOP PORT/ - compares remote port to a number
+<item> <tt/sport RELOP PORT/ - compares local port to a number
+<item> <tt/autobound/ - checks that socket is bound to an ephemeral
+ port
+</itemize>
+
+<p><tt/RELOP/ is some of <tt/<=/, <tt/>=/, <tt/==/ etc.
+To make this more convinient for use in unix shell, alphabetic
+FORTRAN-like notations <tt/le/, <tt/gt/ etc. are accepted as well.
+
+<p>The format and semantics of <tt/ADDRESS_PATTERN/ depends on address
+family.
+
+<itemize>
+<item><tt/inet/ - <tt/ADDRESS_PATTERN/ consists of IP prefix, optionally
+followed by colon and port. If prefix or port part is absent or replaced
+with <tt/*/, this means wildcard match.
+<item><tt/inet6/ - The same as <tt/inet/, only prefix refers to an IPv6
+address. Unlike <tt/inet/ colon becomes ambiguous, so that <tt/ss/ allows
+to use scheme, like used in URLs, where address is suppounded with
+<tt/[/ ... <tt/]/.
+<item><tt/unix/ - <tt/ADDRESS_PATTERN/ is shell-style wildcard.
+<item><tt/packet/ - format looks like <tt/inet/, only interface index
+stays instead of port and link layer protocol id instead of address.
+<item><tt/netlink/ - format looks like <tt/inet/, only socket pid
+stays instead of port and netlink channel instead of address.
+</itemize>
+
+<p><tt/PORT/ is syntactically <tt/ADDRESS_PATTERN/ with wildcard
+address part. Certainly, it is undefined for UNIX sockets.
+
+<sect1> Environment variables
+
+<p>
+<tt/ss/ allows to change source of information using various
+environment variables:
+
+<p>
+<itemize>
+<item> <tt/PROC_SLABINFO/ to override <tt>/proc/slabinfo</tt>
+<item> <tt/PROC_NET_TCP/ to override <tt>/proc/net/tcp</tt>
+<item> <tt/PROC_NET_UDP/ to override <tt>/proc/net/udp</tt>
+<item> etc.
+</itemize>
+
+<p>
+Variable <tt/PROC_ROOT/ allows to change root of all the <tt>/proc/</tt>
+hierarchy.
+
+<p>
+Variable <tt/TCPDIAG_FILE/ prescribes to open a file instead of
+requesting kernel to dump information about TCP sockets.
+
+
+<p> This option is used mainly to investigate bug reports,
+when dumps of files usually found in <tt>/proc/</tt> are recevied
+by e-mail.
+
+<sect1> Output format
+
+<p>Six columns. The first is <tt/Netid/, it denotes socket type and
+transport protocol, when it is ambiguous: <tt/tcp/, <tt/udp/, <tt/raw/,
+<tt/u_str/ is abbreviation for <tt/unix_stream/, <tt/u_dgr/ for UNIX
+datagram sockets, <tt/nl/ for netlink, <tt/p_raw/ and <tt/p_dgr/ for
+raw and datagram packet sockets. This column is optional, it will
+be hidden, if filter selects an unique netid.
+
+<p>
+The second column is <tt/State/. Socket state is displayed here.
+The names are standard TCP names, except for <tt/UNCONN/, which
+cannot happen for TCP, but normal for not connected sockets
+of another types. Again, this column can be hidden.
+
+<p>
+Then two columns (<tt/Recv-Q/ and <tt/Send-Q/) showing amount of data
+queued for receive and transmit.
+
+<p>
+And the last two columns display local address and port of the socket
+and its peer address, if the socket is connected.
+
+<p>
+If options <tt/-o/, <tt/-e/ or <tt/-p/ were given, options are
+displayed not in fixed positions but separated by spaces pairs:
+<tt/option:value/. If value is not a single number, it is presented
+as list of values, enclosed to <tt/(/ ... <tt/)/ and separated with
+commas. F.e.
+
+<tscreen><verb>
+ timer:(keepalive,111min,0)
+</verb></tscreen>
+is typical format for TCP timer (option <tt/-o/).
+
+<tscreen><verb>
+ users:((X,113,3))
+</verb></tscreen>
+is typical for list of users (option <tt/-p/).
+
+
+<sect>Some numbers
+
+<p>
+Well, let us use <tt/pidentd/ and a tool <tt/ibench/ to measure
+its performance. It is 30 requests per second here. Nothing to test,
+it is too slow. OK, let us patch pidentd with patch from directory
+Patches. After this it handles about 4300 requests per second
+and becomes handy tool to pollute socket tables with lots of timewait
+buckets.
+
+<p>
+So, each test starts from pollution tables with 30000 sockets
+and then doing full dump of the table piped to wc and measuring
+timings with time:
+
+<p>Results:
+
+<itemize>
+<item> <tt/netstat -at/ - 15.6 seconds
+<item> <tt/ss -atr/, but without <tt/tcp_diag/ - 5.4 seconds
+<item> <tt/ss -atr/ with <tt/tcp_diag/ - 0.47 seconds
+</itemize>
+
+No comments. Though one comment is necessary, most of time
+without <tt/tcp_diag/ is wasted inside kernel with completely
+blocked networking. More than 10 seconds, yes. <tt/tcp_diag/
+does the same work for 100 milliseconds of system time.
+
+</article>
diff --git a/iproute2/etc/iproute2/bpf_pinning b/iproute2/etc/iproute2/bpf_pinning
new file mode 100644
index 0000000..2b39c70
--- /dev/null
+++ b/iproute2/etc/iproute2/bpf_pinning
@@ -0,0 +1,6 @@
+#
+# subpath mappings from mount point for pinning
+#
+#3 tracing
+#4 foo/bar
+#5 tc/cls1
diff --git a/iproute2/etc/iproute2/ematch_map b/iproute2/etc/iproute2/ematch_map
new file mode 100644
index 0000000..1823983
--- /dev/null
+++ b/iproute2/etc/iproute2/ematch_map
@@ -0,0 +1,7 @@
+# lookup table for ematch kinds
+1 cmp
+2 nbyte
+3 u32
+4 meta
+7 canid
+8 ipset
diff --git a/iproute2/etc/iproute2/group b/iproute2/etc/iproute2/group
new file mode 100644
index 0000000..6f000b2
--- /dev/null
+++ b/iproute2/etc/iproute2/group
@@ -0,0 +1,2 @@
+# device group names
+0 default
diff --git a/iproute2/etc/iproute2/nl_protos b/iproute2/etc/iproute2/nl_protos
new file mode 100644
index 0000000..43418f3
--- /dev/null
+++ b/iproute2/etc/iproute2/nl_protos
@@ -0,0 +1,23 @@
+# Netlink protocol names mapping
+
+0 rtnl
+1 unused
+2 usersock
+3 fw
+4 tcpdiag
+5 nflog
+6 xfrm
+7 selinux
+8 iscsi
+9 audit
+10 fiblookup
+11 connector
+12 nft
+13 ip6fw
+14 dec-rt
+15 uevent
+16 genl
+18 scsi-trans
+19 ecryptfs
+20 rdma
+21 crypto
diff --git a/iproute2/etc/iproute2/rt_dsfield b/iproute2/etc/iproute2/rt_dsfield
new file mode 100644
index 0000000..1426d60
--- /dev/null
+++ b/iproute2/etc/iproute2/rt_dsfield
@@ -0,0 +1,26 @@
+# Differentiated field values
+# These include the DSCP and unused bits
+0x0 default
+# Newer RFC2597 values
+0x28 AF11
+0x30 AF12
+0x38 AF13
+0x48 AF21
+0x50 AF22
+0x58 AF23
+0x68 AF31
+0x70 AF32
+0x78 AF33
+0x88 AF41
+0x90 AF42
+0x98 AF43
+# Older values RFC2474
+0x20 CS1
+0x40 CS2
+0x60 CS3
+0x80 CS4
+0xA0 CS5
+0xC0 CS6
+0xE0 CS7
+# RFC 2598
+0xB8 EF
diff --git a/iproute2/etc/iproute2/rt_protos b/iproute2/etc/iproute2/rt_protos
new file mode 100644
index 0000000..82cf9c4
--- /dev/null
+++ b/iproute2/etc/iproute2/rt_protos
@@ -0,0 +1,31 @@
+#
+# Reserved protocols.
+#
+0 unspec
+1 redirect
+2 kernel
+3 boot
+4 static
+8 gated
+9 ra
+10 mrt
+11 zebra
+12 bird
+13 dnrouted
+14 xorp
+15 ntk
+16 dhcp
+42 babel
+
+#
+# Used by me for gated
+#
+254 gated/aggr
+253 gated/bgp
+252 gated/ospf
+251 gated/ospfase
+250 gated/rip
+249 gated/static
+248 gated/conn
+247 gated/inet
+246 gated/default
diff --git a/iproute2/etc/iproute2/rt_realms b/iproute2/etc/iproute2/rt_realms
new file mode 100644
index 0000000..eedd76d
--- /dev/null
+++ b/iproute2/etc/iproute2/rt_realms
@@ -0,0 +1,13 @@
+#
+# reserved values
+#
+0 cosmos
+#
+# local
+#
+#1 inr.ac
+#2 inr.ruhep
+#3 freenet
+#4 radio-msu
+#5 russia
+#6 internet
diff --git a/iproute2/etc/iproute2/rt_scopes b/iproute2/etc/iproute2/rt_scopes
new file mode 100644
index 0000000..8514bc1
--- /dev/null
+++ b/iproute2/etc/iproute2/rt_scopes
@@ -0,0 +1,11 @@
+#
+# reserved values
+#
+0 global
+255 nowhere
+254 host
+253 link
+#
+# pseudo-reserved
+#
+200 site
diff --git a/iproute2/etc/iproute2/rt_tables b/iproute2/etc/iproute2/rt_tables
new file mode 100644
index 0000000..541abfd
--- /dev/null
+++ b/iproute2/etc/iproute2/rt_tables
@@ -0,0 +1,11 @@
+#
+# reserved values
+#
+255 local
+254 main
+253 default
+0 unspec
+#
+# local
+#
+#1 inr.ruhep
diff --git a/iproute2/etc/iproute2/rt_tables.d/README b/iproute2/etc/iproute2/rt_tables.d/README
new file mode 100644
index 0000000..79386f8
--- /dev/null
+++ b/iproute2/etc/iproute2/rt_tables.d/README
@@ -0,0 +1,3 @@
+Each file in this directory is an rt_tables configuration file. iproute2
+commands scan this directory processing all files that end in '.conf'.
+
diff --git a/iproute2/examples/README.cbq b/iproute2/examples/README.cbq
new file mode 100644
index 0000000..38c1089
--- /dev/null
+++ b/iproute2/examples/README.cbq
@@ -0,0 +1,122 @@
+# CHANGES
+# -------
+# v0.3a2- fixed bug in "if" operator. Thanks kad@dgtu.donetsk.ua.
+# v0.3a- added TIME parameter. Example:
+# TIME=00:00-19:00;64Kbit/6Kbit
+# So, between 00:00 and 19:00 RATE will be 64Kbit.
+# Just start "cbq.init timecheck" periodically from cron (every 10
+# minutes for example).
+# !!! Anyway you MUST start "cbq.init start" for CBQ initialize.
+# v0.2 - Some cosmetique changes. Now it more compatible with
+# old bash version. Thanks to Stanislav V. Voronyi
+# <stas@cnti.uanet.kharkov.ua>.
+# v0.1 - First public release
+#
+# README
+# ------
+#
+# First of all - this is just a SIMPLE EXAMPLE of CBQ power.
+# Don't ask me "why" and "how" :)
+#
+# This is an example of using CBQ (Class Based Queueing) and policy-based
+# filter for building smart ethernet shapers. All CBQ parameters are
+# correct only for ETHERNET (eth0,1,2..) linux interfaces. It works for
+# ARCNET too (just set bandwidth parameter to 2Mbit). It was tested
+# on 2.1.125-2.1.129 linux kernels (KSI linux, Nostromo version) and
+# ip-route utility by A.Kuznetsov (iproute2-ss981101 version).
+# You can download ip-route from ftp://ftp.inr.ac.ru/ip-routing or
+# get iproute2*.rpm (compiled with glibc) from ftp.ksi-linux.com.
+#
+#
+# HOW IT WORKS
+#
+# Each shaper must be described by config file in $CBQ_PATH
+# (/etc/sysconfig/cbq/) directory - one config file for each CBQ shaper.
+#
+# Some words about config file name:
+# Each shaper has its personal ID - two byte HEX number. Really ID is
+# CBQ class.
+# So, filename looks like:
+#
+# cbq-1280.My_first_shaper
+# ^^^ ^^^ ^^^^^^^^^^^^^
+# | | |______ Shaper name - any word
+# | |___________________ ID (0000-FFFF), let ID looks like shaper's rate
+# |______________________ Filename must begin from "cbq-"
+#
+#
+# Config file describes shaper parameters and source[destination]
+# address[port].
+# For example let's prepare /etc/sysconfig/cbq/cbq-1280.My_first_shaper:
+#
+# ----------8<---------------------
+# DEVICE=eth0,10Mbit,1Mbit
+# RATE=128Kbit
+# WEIGHT=10Kbit
+# PRIO=5
+# RULE=192.168.1.0/24
+# ----------8<---------------------
+#
+# This is minimal configuration, where:
+# DEVICE: eth0 - device where we do control our traffic
+# 10Mbit - REAL ethernet card bandwidth
+# 1Mbit - "weight" of :1 class (parent for all shapers for eth0),
+# as a rule of thumb weight=batdwidth/10.
+# 100Mbit adapter's example: DEVICE=eth0,100Mbit,10Mbit
+# *** If you want to build more than one shaper per device it's
+# enough to describe bandwidth and weight once - cbq.init
+# is smart :) You can put only 'DEVICE=eth0' into cbq-*
+# config file for eth0.
+#
+# RATE: Shaper's speed - Kbit,Mbit or bps (bytes per second)
+#
+# WEIGHT: "weight" of shaper (CBQ class). Like for DEVICE - approx. RATE/10
+#
+# PRIO: shaper's priority from 1 to 8 where 1 is the highest one.
+# I do always use "5" for all my shapers.
+#
+# RULE: [source addr][:source port],[dest addr][:dest port]
+# Some examples:
+# RULE=10.1.1.0/24:80 - all traffic for network 10.1.1.0 to port 80
+# will be shaped.
+# RULE=10.2.2.5 - shaper works only for IP address 10.2.2.5
+# RULE=:25,10.2.2.128/25:5000 - all traffic from any address and port 25 to
+# address 10.2.2.128 - 10.2.2.255 and port 5000
+# will be shaped.
+# RULE=10.5.5.5:80, - shaper active only for traffic from port 80 of
+# address 10.5.5.5
+# Multiple RULE fields per one config file are allowed. For example:
+# RULE=10.1.1.2:80
+# RULE=10.1.1.2:25
+# RULE=10.1.1.2:110
+#
+# *** ATTENTION!!!
+# All shapers do work only for outgoing traffic!
+# So, if you want to build bidirectional shaper you must set it up for
+# both ethernet card. For example let's build shaper for our linux box like:
+#
+# --------- 192.168.1.1
+# BACKBONE -----eth0-| linux |-eth1------*[our client]
+# ---------
+#
+# Let all traffic from backbone to client will be shaped at 28Kbit and
+# traffic from client to backbone - at 128Kbit. We need two config files:
+#
+# ---8<-----/etc/sysconfig/cbq/cbq-28.client-out----
+# DEVICE=eth1,10Mbit,1Mbit
+# RATE=28Kbit
+# WEIGHT=2Kbit
+# PRIO=5
+# RULE=192.168.1.1
+# ---8<---------------------------------------------
+#
+# ---8<-----/etc/sysconfig/cbq/cbq-128.client-in----
+# DEVICE=eth0,10Mbit,1Mbit
+# RATE=128Kbit
+# WEIGHT=10Kbit
+# PRIO=5
+# RULE=192.168.1.1,
+# ---8<---------------------------------------------
+# ^pay attention to "," - this is source address!
+#
+# Enjoy.
diff --git a/iproute2/examples/SYN-DoS.rate.limit b/iproute2/examples/SYN-DoS.rate.limit
new file mode 100644
index 0000000..8766b67
--- /dev/null
+++ b/iproute2/examples/SYN-DoS.rate.limit
@@ -0,0 +1,49 @@
+#! /bin/sh -x
+#
+# sample script on using the ingress capabilities
+# this script shows how one can rate limit incoming SYNs
+# Useful for TCP-SYN attack protection. You can use
+# IPchains to have more powerful additions to the SYN (eg
+# in addition the subnet)
+#
+#path to various utilities;
+#change to reflect yours.
+#
+IPROUTE=/root/DS-6-beta/iproute2-990530-dsing
+TC=$IPROUTE/tc/tc
+IP=$IPROUTE/ip/ip
+IPCHAINS=/root/DS-6-beta/ipchains-1.3.9/ipchains
+INDEV=eth2
+#
+# tag all incoming SYN packets through $INDEV as mark value 1
+############################################################
+$IPCHAINS -A input -i $INDEV -y -m 1
+############################################################
+#
+# install the ingress qdisc on the ingress interface
+############################################################
+$TC qdisc add dev $INDEV handle ffff: ingress
+############################################################
+
+#
+#
+# SYN packets are 40 bytes (320 bits) so three SYNs equals
+# 960 bits (approximately 1kbit); so we rate limit below
+# the incoming SYNs to 3/sec (not very sueful really; but
+#serves to show the point - JHS
+############################################################
+$TC filter add dev $INDEV parent ffff: protocol ip prio 50 handle 1 fw \
+police rate 1kbit burst 40 mtu 9k drop flowid :1
+############################################################
+
+
+#
+echo "---- qdisc parameters Ingress ----------"
+$TC qdisc ls dev $INDEV
+echo "---- Class parameters Ingress ----------"
+$TC class ls dev $INDEV
+echo "---- filter parameters Ingress ----------"
+$TC filter ls dev $INDEV parent ffff:
+
+#deleting the ingress qdisc
+#$TC qdisc del $INDEV ingress
diff --git a/iproute2/examples/bpf/README b/iproute2/examples/bpf/README
new file mode 100644
index 0000000..4247257
--- /dev/null
+++ b/iproute2/examples/bpf/README
@@ -0,0 +1,13 @@
+eBPF toy code examples (running in kernel) to familiarize yourself
+with syntax and features:
+
+ - bpf_prog.c -> Classifier examples with using maps
+ - bpf_shared.c -> Ingress/egress map sharing example
+ - bpf_tailcall.c -> Using tail call chains
+ - bpf_cyclic.c -> Simple cycle as tail calls
+ - bpf_graft.c -> Demo on altering runtime behaviour
+
+User space code example:
+
+ - bpf_agent.c -> Counterpart to bpf_prog.c for user
+ space to transfer/read out map data
diff --git a/iproute2/examples/bpf/bpf_agent.c b/iproute2/examples/bpf/bpf_agent.c
new file mode 100644
index 0000000..f9b9ce3
--- /dev/null
+++ b/iproute2/examples/bpf/bpf_agent.c
@@ -0,0 +1,258 @@
+/*
+ * eBPF user space agent part
+ *
+ * Simple, _self-contained_ user space agent for the eBPF kernel
+ * ebpf_prog.c program, which gets all map fds passed from tc via unix
+ * domain socket in one transaction and can thus keep referencing
+ * them from user space in order to read out (or possibly modify)
+ * map data. Here, just as a minimal example to display counters.
+ *
+ * The agent only uses the bpf(2) syscall API to read or possibly
+ * write to eBPF maps, it doesn't need to be aware of the low-level
+ * bytecode parts and/or ELF parsing bits.
+ *
+ * ! For more details, see header comment in bpf_prog.c !
+ *
+ * gcc bpf_agent.c -o bpf_agent -Wall -O2
+ *
+ * For example, a more complex user space agent could run on each
+ * host, reading and writing into eBPF maps used by tc classifier
+ * and actions. It would thus allow for implementing a distributed
+ * tc architecture, for example, which would push down central
+ * policies into eBPF maps, and thus altering run-time behaviour.
+ *
+ * -- Happy eBPF hacking! ;)
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <stdint.h>
+#include <assert.h>
+
+#include <sys/un.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/socket.h>
+
+/* Just some misc macros as min(), offsetof(), etc. */
+#include "../../include/utils.h"
+/* Common code from fd passing. */
+#include "../../include/bpf_scm.h"
+/* Common, shared definitions with ebpf_prog.c */
+#include "bpf_shared.h"
+/* Mini syscall wrapper */
+#include "bpf_sys.h"
+
+static void bpf_dump_drops(int fd)
+{
+ int cpu, max;
+
+ max = sysconf(_SC_NPROCESSORS_ONLN);
+
+ printf(" `- number of drops:");
+ for (cpu = 0; cpu < max; cpu++) {
+ long drops;
+
+ assert(bpf_lookup_elem(fd, &cpu, &drops) == 0);
+ printf("\tcpu%d: %5ld", cpu, drops);
+ }
+ printf("\n");
+}
+
+static void bpf_dump_queue(int fd)
+{
+ /* Just for the same of the example. */
+ int max_queue = 4, i;
+
+ printf(" | nic queues:");
+ for (i = 0; i < max_queue; i++) {
+ struct count_queue cq;
+ int ret;
+
+ memset(&cq, 0, sizeof(cq));
+ ret = bpf_lookup_elem(fd, &i, &cq);
+ assert(ret == 0 || (ret < 0 && errno == ENOENT));
+
+ printf("\tq%d:[pkts: %ld, mis: %ld]",
+ i, cq.total, cq.mismatch);
+ }
+ printf("\n");
+}
+
+static void bpf_dump_proto(int fd)
+{
+ uint8_t protos[] = { IPPROTO_TCP, IPPROTO_UDP, IPPROTO_ICMP };
+ char *names[] = { "tcp", "udp", "icmp" };
+ int i;
+
+ printf(" ` protos:");
+ for (i = 0; i < ARRAY_SIZE(protos); i++) {
+ struct count_tuple ct;
+ int ret;
+
+ memset(&ct, 0, sizeof(ct));
+ ret = bpf_lookup_elem(fd, &protos[i], &ct);
+ assert(ret == 0 || (ret < 0 && errno == ENOENT));
+
+ printf("\t%s:[pkts: %ld, bytes: %ld]",
+ names[i], ct.packets, ct.bytes);
+ }
+ printf("\n");
+}
+
+static void bpf_dump_map_data(int *tfd)
+{
+ int i;
+
+ for (i = 0; i < 30; i++) {
+ const int period = 5;
+
+ printf("data, period: %dsec\n", period);
+
+ bpf_dump_drops(tfd[BPF_MAP_ID_DROPS]);
+ bpf_dump_queue(tfd[BPF_MAP_ID_QUEUE]);
+ bpf_dump_proto(tfd[BPF_MAP_ID_PROTO]);
+
+ sleep(period);
+ }
+}
+
+static void bpf_info_loop(int *fds, struct bpf_map_aux *aux)
+{
+ int i, tfd[BPF_MAP_ID_MAX];
+
+ printf("ver: %d\nobj: %s\ndev: %lu\nino: %lu\nmaps: %u\n",
+ aux->uds_ver, aux->obj_name, aux->obj_st.st_dev,
+ aux->obj_st.st_ino, aux->num_ent);
+
+ for (i = 0; i < aux->num_ent; i++) {
+ printf("map%d:\n", i);
+ printf(" `- fd: %u\n", fds[i]);
+ printf(" | serial: %u\n", aux->ent[i].id);
+ printf(" | type: %u\n", aux->ent[i].type);
+ printf(" | max elem: %u\n", aux->ent[i].max_elem);
+ printf(" | size key: %u\n", aux->ent[i].size_key);
+ printf(" ` size val: %u\n", aux->ent[i].size_value);
+
+ tfd[aux->ent[i].id] = fds[i];
+ }
+
+ bpf_dump_map_data(tfd);
+}
+
+static void bpf_map_get_from_env(int *tfd)
+{
+ char key[64], *val;
+ int i;
+
+ for (i = 0; i < BPF_MAP_ID_MAX; i++) {
+ memset(key, 0, sizeof(key));
+ snprintf(key, sizeof(key), "BPF_MAP%d", i);
+
+ val = getenv(key);
+ assert(val != NULL);
+
+ tfd[i] = atoi(val);
+ }
+}
+
+static int bpf_map_set_recv(int fd, int *fds, struct bpf_map_aux *aux,
+ unsigned int entries)
+{
+ struct bpf_map_set_msg msg;
+ int *cmsg_buf, min_fd, i;
+ char *amsg_buf, *mmsg_buf;
+
+ cmsg_buf = bpf_map_set_init(&msg, NULL, 0);
+ amsg_buf = (char *)msg.aux.ent;
+ mmsg_buf = (char *)&msg.aux;
+
+ for (i = 0; i < entries; i += min_fd) {
+ struct cmsghdr *cmsg;
+ int ret;
+
+ min_fd = min(BPF_SCM_MAX_FDS * 1U, entries - i);
+
+ bpf_map_set_init_single(&msg, min_fd);
+
+ ret = recvmsg(fd, &msg.hdr, 0);
+ if (ret <= 0)
+ return ret ? : -1;
+
+ cmsg = CMSG_FIRSTHDR(&msg.hdr);
+ if (!cmsg || cmsg->cmsg_type != SCM_RIGHTS)
+ return -EINVAL;
+ if (msg.hdr.msg_flags & MSG_CTRUNC)
+ return -EIO;
+
+ min_fd = (cmsg->cmsg_len - sizeof(*cmsg)) / sizeof(fd);
+ if (min_fd > entries || min_fd <= 0)
+ return -1;
+
+ memcpy(&fds[i], cmsg_buf, sizeof(fds[0]) * min_fd);
+ memcpy(&aux->ent[i], amsg_buf, sizeof(aux->ent[0]) * min_fd);
+ memcpy(aux, mmsg_buf, offsetof(struct bpf_map_aux, ent));
+
+ if (i + min_fd == aux->num_ent)
+ break;
+ }
+
+ return 0;
+}
+
+int main(int argc, char **argv)
+{
+ int fds[BPF_SCM_MAX_FDS];
+ struct bpf_map_aux aux;
+ struct sockaddr_un addr;
+ int fd, ret, i;
+
+ /* When arguments are being passed, we take it as a path
+ * to a Unix domain socket, otherwise we grab the fds
+ * from the environment to demonstrate both possibilities.
+ */
+ if (argc == 1) {
+ int tfd[BPF_MAP_ID_MAX];
+
+ bpf_map_get_from_env(tfd);
+ bpf_dump_map_data(tfd);
+
+ return 0;
+ }
+
+ fd = socket(AF_UNIX, SOCK_DGRAM, 0);
+ if (fd < 0) {
+ fprintf(stderr, "Cannot open socket: %s\n",
+ strerror(errno));
+ exit(1);
+ }
+
+ memset(&addr, 0, sizeof(addr));
+ addr.sun_family = AF_UNIX;
+ strncpy(addr.sun_path, argv[argc - 1], sizeof(addr.sun_path));
+
+ ret = bind(fd, (struct sockaddr *)&addr, sizeof(addr));
+ if (ret < 0) {
+ fprintf(stderr, "Cannot bind to socket: %s\n",
+ strerror(errno));
+ exit(1);
+ }
+
+ memset(fds, 0, sizeof(fds));
+ memset(&aux, 0, sizeof(aux));
+
+ ret = bpf_map_set_recv(fd, fds, &aux, BPF_SCM_MAX_FDS);
+ if (ret >= 0)
+ bpf_info_loop(fds, &aux);
+
+ for (i = 0; i < aux.num_ent; i++)
+ close(fds[i]);
+
+ close(fd);
+ return 0;
+}
diff --git a/iproute2/examples/bpf/bpf_cyclic.c b/iproute2/examples/bpf/bpf_cyclic.c
new file mode 100644
index 0000000..c66cbec
--- /dev/null
+++ b/iproute2/examples/bpf/bpf_cyclic.c
@@ -0,0 +1,30 @@
+#include "../../include/bpf_api.h"
+
+/* Cyclic dependency example to test the kernel's runtime upper
+ * bound on loops. Also demonstrates on how to use direct-actions,
+ * loaded as: tc filter add [...] bpf da obj [...]
+ */
+#define JMP_MAP_ID 0xabccba
+
+BPF_PROG_ARRAY(jmp_tc, JMP_MAP_ID, PIN_OBJECT_NS, 1);
+
+__section_tail(JMP_MAP_ID, 0)
+int cls_loop(struct __sk_buff *skb)
+{
+ char fmt[] = "cb: %u\n";
+
+ trace_printk(fmt, sizeof(fmt), skb->cb[0]++);
+ tail_call(skb, &jmp_tc, 0);
+
+ skb->tc_classid = TC_H_MAKE(1, 42);
+ return TC_ACT_OK;
+}
+
+__section_cls_entry
+int cls_entry(struct __sk_buff *skb)
+{
+ tail_call(skb, &jmp_tc, 0);
+ return TC_ACT_SHOT;
+}
+
+BPF_LICENSE("GPL");
diff --git a/iproute2/examples/bpf/bpf_graft.c b/iproute2/examples/bpf/bpf_graft.c
new file mode 100644
index 0000000..f48fd02
--- /dev/null
+++ b/iproute2/examples/bpf/bpf_graft.c
@@ -0,0 +1,67 @@
+#include "../../include/bpf_api.h"
+
+/* This example demonstrates how classifier run-time behaviour
+ * can be altered with tail calls. We start out with an empty
+ * jmp_tc array, then add section aaa to the array slot 0, and
+ * later on atomically replace it with section bbb. Note that
+ * as shown in other examples, the tc loader can prepopulate
+ * tail called sections, here we start out with an empty one
+ * on purpose to show it can also be done this way.
+ *
+ * tc filter add dev foo parent ffff: bpf obj graft.o
+ * tc exec bpf dbg
+ * [...]
+ * Socket Thread-20229 [001] ..s. 138993.003923: : fallthrough
+ * <idle>-0 [001] ..s. 138993.202265: : fallthrough
+ * Socket Thread-20229 [001] ..s. 138994.004149: : fallthrough
+ * [...]
+ *
+ * tc exec bpf graft m:globals/jmp_tc key 0 obj graft.o sec aaa
+ * tc exec bpf dbg
+ * [...]
+ * Socket Thread-19818 [002] ..s. 139012.053587: : aaa
+ * <idle>-0 [002] ..s. 139012.172359: : aaa
+ * Socket Thread-19818 [001] ..s. 139012.173556: : aaa
+ * [...]
+ *
+ * tc exec bpf graft m:globals/jmp_tc key 0 obj graft.o sec bbb
+ * tc exec bpf dbg
+ * [...]
+ * Socket Thread-19818 [002] ..s. 139022.102967: : bbb
+ * <idle>-0 [002] ..s. 139022.155640: : bbb
+ * Socket Thread-19818 [001] ..s. 139022.156730: : bbb
+ * [...]
+ */
+
+BPF_PROG_ARRAY(jmp_tc, 0, PIN_GLOBAL_NS, 1);
+
+__section("aaa")
+int cls_aaa(struct __sk_buff *skb)
+{
+ char fmt[] = "aaa\n";
+
+ trace_printk(fmt, sizeof(fmt));
+ return TC_H_MAKE(1, 42);
+}
+
+__section("bbb")
+int cls_bbb(struct __sk_buff *skb)
+{
+ char fmt[] = "bbb\n";
+
+ trace_printk(fmt, sizeof(fmt));
+ return TC_H_MAKE(1, 43);
+}
+
+__section_cls_entry
+int cls_entry(struct __sk_buff *skb)
+{
+ char fmt[] = "fallthrough\n";
+
+ tail_call(skb, &jmp_tc, 0);
+ trace_printk(fmt, sizeof(fmt));
+
+ return BPF_H_DEFAULT;
+}
+
+BPF_LICENSE("GPL");
diff --git a/iproute2/examples/bpf/bpf_prog.c b/iproute2/examples/bpf/bpf_prog.c
new file mode 100644
index 0000000..4728049
--- /dev/null
+++ b/iproute2/examples/bpf/bpf_prog.c
@@ -0,0 +1,499 @@
+/*
+ * eBPF kernel space program part
+ *
+ * Toy eBPF program for demonstration purposes, some parts derived from
+ * kernel tree's samples/bpf/sockex2_kern.c example.
+ *
+ * More background on eBPF, kernel tree: Documentation/networking/filter.txt
+ *
+ * Note, this file is rather large, and most classifier and actions are
+ * likely smaller to accomplish one specific use-case and are tailored
+ * for high performance. For performance reasons, you might also have the
+ * classifier and action already merged inside the classifier.
+ *
+ * In order to show various features it serves as a bigger programming
+ * example, which you should feel free to rip apart and experiment with.
+ *
+ * Compilation, configuration example:
+ *
+ * Note: as long as the BPF backend in LLVM is still experimental,
+ * you need to build LLVM with LLVM with --enable-experimental-targets=BPF
+ * Also, make sure your 4.1+ kernel is compiled with CONFIG_BPF_SYSCALL=y,
+ * and you have libelf.h and gelf.h headers and can link tc against -lelf.
+ *
+ * In case you need to sync kernel headers, go to your kernel source tree:
+ * # make headers_install INSTALL_HDR_PATH=/usr/
+ *
+ * $ export PATH=/home/<...>/llvm/Debug+Asserts/bin/:$PATH
+ * $ clang -O2 -emit-llvm -c bpf_prog.c -o - | llc -march=bpf -filetype=obj -o bpf.o
+ * $ objdump -h bpf.o
+ * [...]
+ * 3 classifier 000007f8 0000000000000000 0000000000000000 00000040 2**3
+ * CONTENTS, ALLOC, LOAD, RELOC, READONLY, CODE
+ * 4 action-mark 00000088 0000000000000000 0000000000000000 00000838 2**3
+ * CONTENTS, ALLOC, LOAD, RELOC, READONLY, CODE
+ * 5 action-rand 00000098 0000000000000000 0000000000000000 000008c0 2**3
+ * CONTENTS, ALLOC, LOAD, RELOC, READONLY, CODE
+ * 6 maps 00000030 0000000000000000 0000000000000000 00000958 2**2
+ * CONTENTS, ALLOC, LOAD, DATA
+ * 7 license 00000004 0000000000000000 0000000000000000 00000988 2**0
+ * CONTENTS, ALLOC, LOAD, DATA
+ * [...]
+ * # echo 1 > /proc/sys/net/core/bpf_jit_enable
+ * $ gcc bpf_agent.c -o bpf_agent -Wall -O2
+ * # ./bpf_agent /tmp/bpf-uds (e.g. on a different terminal)
+ * # tc filter add dev em1 parent 1: bpf obj bpf.o exp /tmp/bpf-uds flowid 1:1 \
+ * action bpf obj bpf.o sec action-mark \
+ * action bpf obj bpf.o sec action-rand ok
+ * # tc filter show dev em1
+ * filter parent 1: protocol all pref 49152 bpf
+ * filter parent 1: protocol all pref 49152 bpf handle 0x1 flowid 1:1 bpf.o:[classifier]
+ * action order 1: bpf bpf.o:[action-mark] default-action pipe
+ * index 52 ref 1 bind 1
+ *
+ * action order 2: bpf bpf.o:[action-rand] default-action pipe
+ * index 53 ref 1 bind 1
+ *
+ * action order 3: gact action pass
+ * random type none pass val 0
+ * index 38 ref 1 bind 1
+ *
+ * The same program can also be installed on ingress side (as opposed to above
+ * egress configuration), e.g.:
+ *
+ * # tc qdisc add dev em1 handle ffff: ingress
+ * # tc filter add dev em1 parent ffff: bpf obj ...
+ *
+ * Notes on BPF agent:
+ *
+ * In the above example, the bpf_agent creates the unix domain socket
+ * natively. "tc exec" can also spawn a shell and hold the socktes there:
+ *
+ * # tc exec bpf imp /tmp/bpf-uds
+ * # tc filter add dev em1 parent 1: bpf obj bpf.o exp /tmp/bpf-uds flowid 1:1 \
+ * action bpf obj bpf.o sec action-mark \
+ * action bpf obj bpf.o sec action-rand ok
+ * sh-4.2# (shell spawned from tc exec)
+ * sh-4.2# bpf_agent
+ * [...]
+ *
+ * This will read out fds over environment and produce the same data dump
+ * as below. This has the advantage that the spawned shell owns the fds
+ * and thus if the agent is restarted, it can reattach to the same fds, also
+ * various programs can easily read/modify the data simultaneously from user
+ * space side.
+ *
+ * If the shell is unnecessary, the agent can also just be spawned directly
+ * via tc exec:
+ *
+ * # tc exec bpf imp /tmp/bpf-uds run bpf_agent
+ * # tc filter add dev em1 parent 1: bpf obj bpf.o exp /tmp/bpf-uds flowid 1:1 \
+ * action bpf obj bpf.o sec action-mark \
+ * action bpf obj bpf.o sec action-rand ok
+ *
+ * BPF agent example output:
+ *
+ * ver: 1
+ * obj: bpf.o
+ * dev: 64770
+ * ino: 6045133
+ * maps: 3
+ * map0:
+ * `- fd: 4
+ * | serial: 1
+ * | type: 1
+ * | max elem: 256
+ * | size key: 1
+ * ` size val: 16
+ * map1:
+ * `- fd: 5
+ * | serial: 2
+ * | type: 1
+ * | max elem: 1024
+ * | size key: 4
+ * ` size val: 16
+ * map2:
+ * `- fd: 6
+ * | serial: 3
+ * | type: 2
+ * | max elem: 64
+ * | size key: 4
+ * ` size val: 8
+ * data, period: 5sec
+ * `- number of drops: cpu0: 0 cpu1: 0 cpu2: 0 cpu3: 0
+ * | nic queues: q0:[pkts: 0, mis: 0] q1:[pkts: 0, mis: 0] q2:[pkts: 0, mis: 0] q3:[pkts: 0, mis: 0]
+ * ` protos: tcp:[pkts: 0, bytes: 0] udp:[pkts: 0, bytes: 0] icmp:[pkts: 0, bytes: 0]
+ * data, period: 5sec
+ * `- number of drops: cpu0: 5 cpu1: 0 cpu2: 0 cpu3: 1
+ * | nic queues: q0:[pkts: 0, mis: 0] q1:[pkts: 0, mis: 0] q2:[pkts: 24, mis: 14] q3:[pkts: 0, mis: 0]
+ * ` protos: tcp:[pkts: 13, bytes: 1989] udp:[pkts: 10, bytes: 710] icmp:[pkts: 0, bytes: 0]
+ * data, period: 5sec
+ * `- number of drops: cpu0: 5 cpu1: 0 cpu2: 3 cpu3: 3
+ * | nic queues: q0:[pkts: 0, mis: 0] q1:[pkts: 0, mis: 0] q2:[pkts: 39, mis: 21] q3:[pkts: 0, mis: 0]
+ * ` protos: tcp:[pkts: 20, bytes: 3549] udp:[pkts: 18, bytes: 1278] icmp:[pkts: 0, bytes: 0]
+ * [...]
+ *
+ * This now means, the below classifier and action pipeline has been loaded
+ * as eBPF bytecode into the kernel, the kernel has verified that the
+ * execution of the bytecode is "safe", and it has JITed the programs
+ * afterwards, so that upon invocation they're running on native speed. tc
+ * has transferred all map file descriptors to the bpf_agent via IPC and
+ * even after tc exits, the agent can read out or modify all map data.
+ *
+ * Note that the export to the uds is done only once in the classifier and
+ * not in the action. It's enough to export the (here) shared descriptors
+ * once.
+ *
+ * If you need to disassemble the generated JIT image (echo with 2), the
+ * kernel tree has under tools/net/ a small helper, you can invoke e.g.
+ * `bpf_jit_disasm -o`.
+ *
+ * Please find in the code below further comments.
+ *
+ * -- Happy eBPF hacking! ;)
+ */
+#include <stdint.h>
+#include <stdbool.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <asm/types.h>
+#include <linux/in.h>
+#include <linux/if.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/if_tunnel.h>
+#include <linux/filter.h>
+#include <linux/bpf.h>
+
+/* Common, shared definitions with ebpf_agent.c. */
+#include "bpf_shared.h"
+/* BPF helper functions for our example. */
+#include "../../include/bpf_api.h"
+
+/* Could be defined here as well, or included from the header. */
+#define TC_ACT_UNSPEC (-1)
+#define TC_ACT_OK 0
+#define TC_ACT_RECLASSIFY 1
+#define TC_ACT_SHOT 2
+#define TC_ACT_PIPE 3
+#define TC_ACT_STOLEN 4
+#define TC_ACT_QUEUED 5
+#define TC_ACT_REPEAT 6
+
+/* Other, misc stuff. */
+#define IP_MF 0x2000
+#define IP_OFFSET 0x1FFF
+
+/* eBPF map definitions, all placed in section "maps". */
+struct bpf_elf_map __section("maps") map_proto = {
+ .type = BPF_MAP_TYPE_HASH,
+ .id = BPF_MAP_ID_PROTO,
+ .size_key = sizeof(uint8_t),
+ .size_value = sizeof(struct count_tuple),
+ .max_elem = 256,
+};
+
+struct bpf_elf_map __section("maps") map_queue = {
+ .type = BPF_MAP_TYPE_HASH,
+ .id = BPF_MAP_ID_QUEUE,
+ .size_key = sizeof(uint32_t),
+ .size_value = sizeof(struct count_queue),
+ .max_elem = 1024,
+};
+
+struct bpf_elf_map __section("maps") map_drops = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .id = BPF_MAP_ID_DROPS,
+ .size_key = sizeof(uint32_t),
+ .size_value = sizeof(long),
+ .max_elem = 64,
+};
+
+/* Helper functions and definitions for the flow dissector used by the
+ * example classifier. This resembles the kernel's flow dissector to
+ * some extend and is just used as an example to show what's possible
+ * with eBPF.
+ */
+struct sockaddr;
+
+struct vlan_hdr {
+ __be16 h_vlan_TCI;
+ __be16 h_vlan_encapsulated_proto;
+};
+
+struct flow_keys {
+ __u32 src;
+ __u32 dst;
+ union {
+ __u32 ports;
+ __u16 port16[2];
+ };
+ __s32 th_off;
+ __u8 ip_proto;
+};
+
+static inline int flow_ports_offset(__u8 ip_proto)
+{
+ switch (ip_proto) {
+ case IPPROTO_TCP:
+ case IPPROTO_UDP:
+ case IPPROTO_DCCP:
+ case IPPROTO_ESP:
+ case IPPROTO_SCTP:
+ case IPPROTO_UDPLITE:
+ default:
+ return 0;
+ case IPPROTO_AH:
+ return 4;
+ }
+}
+
+static inline bool flow_is_frag(struct __sk_buff *skb, int nh_off)
+{
+ return !!(load_half(skb, nh_off + offsetof(struct iphdr, frag_off)) &
+ (IP_MF | IP_OFFSET));
+}
+
+static inline int flow_parse_ipv4(struct __sk_buff *skb, int nh_off,
+ __u8 *ip_proto, struct flow_keys *flow)
+{
+ __u8 ip_ver_len;
+
+ if (unlikely(flow_is_frag(skb, nh_off)))
+ *ip_proto = 0;
+ else
+ *ip_proto = load_byte(skb, nh_off + offsetof(struct iphdr,
+ protocol));
+ if (*ip_proto != IPPROTO_GRE) {
+ flow->src = load_word(skb, nh_off + offsetof(struct iphdr, saddr));
+ flow->dst = load_word(skb, nh_off + offsetof(struct iphdr, daddr));
+ }
+
+ ip_ver_len = load_byte(skb, nh_off + 0 /* offsetof(struct iphdr, ihl) */);
+ if (likely(ip_ver_len == 0x45))
+ nh_off += 20;
+ else
+ nh_off += (ip_ver_len & 0xF) << 2;
+
+ return nh_off;
+}
+
+static inline __u32 flow_addr_hash_ipv6(struct __sk_buff *skb, int off)
+{
+ __u32 w0 = load_word(skb, off);
+ __u32 w1 = load_word(skb, off + sizeof(w0));
+ __u32 w2 = load_word(skb, off + sizeof(w0) * 2);
+ __u32 w3 = load_word(skb, off + sizeof(w0) * 3);
+
+ return w0 ^ w1 ^ w2 ^ w3;
+}
+
+static inline int flow_parse_ipv6(struct __sk_buff *skb, int nh_off,
+ __u8 *ip_proto, struct flow_keys *flow)
+{
+ *ip_proto = load_byte(skb, nh_off + offsetof(struct ipv6hdr, nexthdr));
+
+ flow->src = flow_addr_hash_ipv6(skb, nh_off + offsetof(struct ipv6hdr, saddr));
+ flow->dst = flow_addr_hash_ipv6(skb, nh_off + offsetof(struct ipv6hdr, daddr));
+
+ return nh_off + sizeof(struct ipv6hdr);
+}
+
+static inline bool flow_dissector(struct __sk_buff *skb,
+ struct flow_keys *flow)
+{
+ int poff, nh_off = BPF_LL_OFF + ETH_HLEN;
+ __be16 proto = skb->protocol;
+ __u8 ip_proto;
+
+ /* TODO: check for skb->vlan_tci, skb->vlan_proto first */
+ if (proto == htons(ETH_P_8021AD)) {
+ proto = load_half(skb, nh_off +
+ offsetof(struct vlan_hdr, h_vlan_encapsulated_proto));
+ nh_off += sizeof(struct vlan_hdr);
+ }
+ if (proto == htons(ETH_P_8021Q)) {
+ proto = load_half(skb, nh_off +
+ offsetof(struct vlan_hdr, h_vlan_encapsulated_proto));
+ nh_off += sizeof(struct vlan_hdr);
+ }
+
+ if (likely(proto == htons(ETH_P_IP)))
+ nh_off = flow_parse_ipv4(skb, nh_off, &ip_proto, flow);
+ else if (proto == htons(ETH_P_IPV6))
+ nh_off = flow_parse_ipv6(skb, nh_off, &ip_proto, flow);
+ else
+ return false;
+
+ switch (ip_proto) {
+ case IPPROTO_GRE: {
+ struct gre_hdr {
+ __be16 flags;
+ __be16 proto;
+ };
+
+ __u16 gre_flags = load_half(skb, nh_off +
+ offsetof(struct gre_hdr, flags));
+ __u16 gre_proto = load_half(skb, nh_off +
+ offsetof(struct gre_hdr, proto));
+
+ if (gre_flags & (GRE_VERSION | GRE_ROUTING))
+ break;
+
+ nh_off += 4;
+ if (gre_flags & GRE_CSUM)
+ nh_off += 4;
+ if (gre_flags & GRE_KEY)
+ nh_off += 4;
+ if (gre_flags & GRE_SEQ)
+ nh_off += 4;
+
+ if (gre_proto == ETH_P_8021Q) {
+ gre_proto = load_half(skb, nh_off +
+ offsetof(struct vlan_hdr,
+ h_vlan_encapsulated_proto));
+ nh_off += sizeof(struct vlan_hdr);
+ }
+ if (gre_proto == ETH_P_IP)
+ nh_off = flow_parse_ipv4(skb, nh_off, &ip_proto, flow);
+ else if (gre_proto == ETH_P_IPV6)
+ nh_off = flow_parse_ipv6(skb, nh_off, &ip_proto, flow);
+ else
+ return false;
+ break;
+ }
+ case IPPROTO_IPIP:
+ nh_off = flow_parse_ipv4(skb, nh_off, &ip_proto, flow);
+ break;
+ case IPPROTO_IPV6:
+ nh_off = flow_parse_ipv6(skb, nh_off, &ip_proto, flow);
+ default:
+ break;
+ }
+
+ nh_off += flow_ports_offset(ip_proto);
+
+ flow->ports = load_word(skb, nh_off);
+ flow->th_off = nh_off;
+ flow->ip_proto = ip_proto;
+
+ return true;
+}
+
+static inline void cls_update_proto_map(const struct __sk_buff *skb,
+ const struct flow_keys *flow)
+{
+ uint8_t proto = flow->ip_proto;
+ struct count_tuple *ct, _ct;
+
+ ct = map_lookup_elem(&map_proto, &proto);
+ if (likely(ct)) {
+ lock_xadd(&ct->packets, 1);
+ lock_xadd(&ct->bytes, skb->len);
+ return;
+ }
+
+ /* No hit yet, we need to create a new entry. */
+ _ct.packets = 1;
+ _ct.bytes = skb->len;
+
+ map_update_elem(&map_proto, &proto, &_ct, BPF_ANY);
+}
+
+static inline void cls_update_queue_map(const struct __sk_buff *skb)
+{
+ uint32_t queue = skb->queue_mapping;
+ struct count_queue *cq, _cq;
+ bool mismatch;
+
+ mismatch = skb->queue_mapping != get_smp_processor_id();
+
+ cq = map_lookup_elem(&map_queue, &queue);
+ if (likely(cq)) {
+ lock_xadd(&cq->total, 1);
+ if (mismatch)
+ lock_xadd(&cq->mismatch, 1);
+ return;
+ }
+
+ /* No hit yet, we need to create a new entry. */
+ _cq.total = 1;
+ _cq.mismatch = mismatch ? 1 : 0;
+
+ map_update_elem(&map_queue, &queue, &_cq, BPF_ANY);
+}
+
+/* eBPF program definitions, placed in various sections, which can
+ * have custom section names. If custom names are in use, it's
+ * required to point tc to the correct section, e.g.
+ *
+ * tc filter add [...] bpf obj cls.o sec cls-tos [...]
+ *
+ * in case the program resides in __section("cls-tos").
+ *
+ * Default section for cls_bpf is: "classifier", for act_bpf is:
+ * "action". Naturally, if for example multiple actions are present
+ * in the same file, they need to have distinct section names.
+ *
+ * It is however not required to have multiple programs sharing
+ * a file.
+ */
+__section("classifier")
+int cls_main(struct __sk_buff *skb)
+{
+ struct flow_keys flow;
+
+ if (!flow_dissector(skb, &flow))
+ return 0; /* No match in cls_bpf. */
+
+ cls_update_proto_map(skb, &flow);
+ cls_update_queue_map(skb);
+
+ return flow.ip_proto;
+}
+
+static inline void act_update_drop_map(void)
+{
+ uint32_t *count, cpu = get_smp_processor_id();
+
+ count = map_lookup_elem(&map_drops, &cpu);
+ if (count)
+ /* Only this cpu is accessing this element. */
+ (*count)++;
+}
+
+__section("action-mark")
+int act_mark_main(struct __sk_buff *skb)
+{
+ /* You could also mangle skb data here with the helper function
+ * BPF_FUNC_skb_store_bytes, etc. Or, alternatively you could
+ * do that already in the classifier itself as a merged combination
+ * of classifier'n'action model.
+ */
+
+ if (skb->mark == 0xcafe) {
+ act_update_drop_map();
+ return TC_ACT_SHOT;
+ }
+
+ /* Default configured tc opcode. */
+ return TC_ACT_UNSPEC;
+}
+
+__section("action-rand")
+int act_rand_main(struct __sk_buff *skb)
+{
+ /* Sorry, we're near event horizon ... */
+ if ((get_prandom_u32() & 3) == 0) {
+ act_update_drop_map();
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_UNSPEC;
+}
+
+/* Last but not least, the file contains a license. Some future helper
+ * functions may only be available with a GPL license.
+ */
+BPF_LICENSE("GPL");
diff --git a/iproute2/examples/bpf/bpf_shared.c b/iproute2/examples/bpf/bpf_shared.c
new file mode 100644
index 0000000..accc0ad
--- /dev/null
+++ b/iproute2/examples/bpf/bpf_shared.c
@@ -0,0 +1,48 @@
+#include "../../include/bpf_api.h"
+
+/* Minimal, stand-alone toy map pinning example:
+ *
+ * clang -target bpf -O2 [...] -o bpf_shared.o -c bpf_shared.c
+ * tc filter add dev foo parent 1: bpf obj bpf_shared.o sec egress
+ * tc filter add dev foo parent ffff: bpf obj bpf_shared.o sec ingress
+ *
+ * Both classifier will share the very same map instance in this example,
+ * so map content can be accessed from ingress *and* egress side!
+ *
+ * This example has a pinning of PIN_OBJECT_NS, so it's private and
+ * thus shared among various program sections within the object.
+ *
+ * A setting of PIN_GLOBAL_NS would place it into a global namespace,
+ * so that it can be shared among different object files. A setting
+ * of PIN_NONE (= 0) means no sharing, so each tc invocation a new map
+ * instance is being created.
+ */
+
+BPF_ARRAY4(map_sh, 0, PIN_OBJECT_NS, 1); /* or PIN_GLOBAL_NS, or PIN_NONE */
+
+__section("egress")
+int emain(struct __sk_buff *skb)
+{
+ int key = 0, *val;
+
+ val = map_lookup_elem(&map_sh, &key);
+ if (val)
+ lock_xadd(val, 1);
+
+ return BPF_H_DEFAULT;
+}
+
+__section("ingress")
+int imain(struct __sk_buff *skb)
+{
+ char fmt[] = "map val: %d\n";
+ int key = 0, *val;
+
+ val = map_lookup_elem(&map_sh, &key);
+ if (val)
+ trace_printk(fmt, sizeof(fmt), *val);
+
+ return BPF_H_DEFAULT;
+}
+
+BPF_LICENSE("GPL");
diff --git a/iproute2/examples/bpf/bpf_shared.h b/iproute2/examples/bpf/bpf_shared.h
new file mode 100644
index 0000000..a24038d
--- /dev/null
+++ b/iproute2/examples/bpf/bpf_shared.h
@@ -0,0 +1,22 @@
+#ifndef __BPF_SHARED__
+#define __BPF_SHARED__
+
+enum {
+ BPF_MAP_ID_PROTO,
+ BPF_MAP_ID_QUEUE,
+ BPF_MAP_ID_DROPS,
+ __BPF_MAP_ID_MAX,
+#define BPF_MAP_ID_MAX __BPF_MAP_ID_MAX
+};
+
+struct count_tuple {
+ long packets; /* type long for lock_xadd() */
+ long bytes;
+};
+
+struct count_queue {
+ long total;
+ long mismatch;
+};
+
+#endif /* __BPF_SHARED__ */
diff --git a/iproute2/examples/bpf/bpf_sys.h b/iproute2/examples/bpf/bpf_sys.h
new file mode 100644
index 0000000..6e4f09e
--- /dev/null
+++ b/iproute2/examples/bpf/bpf_sys.h
@@ -0,0 +1,23 @@
+#ifndef __BPF_SYS__
+#define __BPF_SYS__
+
+#include <sys/syscall.h>
+#include <linux/bpf.h>
+
+static inline __u64 bpf_ptr_to_u64(const void *ptr)
+{
+ return (__u64) (unsigned long) ptr;
+}
+
+static inline int bpf_lookup_elem(int fd, void *key, void *value)
+{
+ union bpf_attr attr = {
+ .map_fd = fd,
+ .key = bpf_ptr_to_u64(key),
+ .value = bpf_ptr_to_u64(value),
+ };
+
+ return syscall(__NR_bpf, BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
+}
+
+#endif /* __BPF_SYS__ */
diff --git a/iproute2/examples/bpf/bpf_tailcall.c b/iproute2/examples/bpf/bpf_tailcall.c
new file mode 100644
index 0000000..040790d
--- /dev/null
+++ b/iproute2/examples/bpf/bpf_tailcall.c
@@ -0,0 +1,99 @@
+#include "../../include/bpf_api.h"
+
+#define ENTRY_INIT 3
+#define ENTRY_0 0
+#define ENTRY_1 1
+#define MAX_JMP_SIZE 2
+
+#define FOO 42
+#define BAR 43
+
+/* This example doesn't really do anything useful, but it's purpose is to
+ * demonstrate eBPF tail calls on a very simple example.
+ *
+ * cls_entry() is our classifier entry point, from there we jump based on
+ * skb->hash into cls_case1() or cls_case2(). They are both part of the
+ * program array jmp_tc. Indicated via __section_tail(), the tc loader
+ * populates the program arrays with the loaded file descriptors already.
+ *
+ * To demonstrate nested jumps, cls_case2() jumps within the same jmp_tc
+ * array to cls_case1(). And whenever we arrive at cls_case1(), we jump
+ * into cls_exit(), part of the jump array jmp_ex.
+ *
+ * Also, to show it's possible, all programs share map_sh and dump the value
+ * that the entry point incremented. The sections that are loaded into a
+ * program array can be atomically replaced during run-time, e.g. to change
+ * classifier behaviour.
+ */
+
+BPF_PROG_ARRAY(jmp_tc, FOO, PIN_OBJECT_NS, MAX_JMP_SIZE);
+BPF_PROG_ARRAY(jmp_ex, BAR, PIN_OBJECT_NS, 1);
+
+BPF_ARRAY4(map_sh, 0, PIN_OBJECT_NS, 1);
+
+__section_tail(FOO, ENTRY_0)
+int cls_case1(struct __sk_buff *skb)
+{
+ char fmt[] = "case1: map-val: %d from:%u\n";
+ int key = 0, *val;
+
+ val = map_lookup_elem(&map_sh, &key);
+ if (val)
+ trace_printk(fmt, sizeof(fmt), *val, skb->cb[0]);
+
+ skb->cb[0] = ENTRY_0;
+ tail_call(skb, &jmp_ex, ENTRY_0);
+
+ return BPF_H_DEFAULT;
+}
+
+__section_tail(FOO, ENTRY_1)
+int cls_case2(struct __sk_buff *skb)
+{
+ char fmt[] = "case2: map-val: %d from:%u\n";
+ int key = 0, *val;
+
+ val = map_lookup_elem(&map_sh, &key);
+ if (val)
+ trace_printk(fmt, sizeof(fmt), *val, skb->cb[0]);
+
+ skb->cb[0] = ENTRY_1;
+ tail_call(skb, &jmp_tc, ENTRY_0);
+
+ return BPF_H_DEFAULT;
+}
+
+__section_tail(BAR, ENTRY_0)
+int cls_exit(struct __sk_buff *skb)
+{
+ char fmt[] = "exit: map-val: %d from:%u\n";
+ int key = 0, *val;
+
+ val = map_lookup_elem(&map_sh, &key);
+ if (val)
+ trace_printk(fmt, sizeof(fmt), *val, skb->cb[0]);
+
+ /* Termination point. */
+ return BPF_H_DEFAULT;
+}
+
+__section_cls_entry
+int cls_entry(struct __sk_buff *skb)
+{
+ char fmt[] = "fallthrough\n";
+ int key = 0, *val;
+
+ /* For transferring state, we can use skb->cb[0] ... skb->cb[4]. */
+ val = map_lookup_elem(&map_sh, &key);
+ if (val) {
+ lock_xadd(val, 1);
+
+ skb->cb[0] = ENTRY_INIT;
+ tail_call(skb, &jmp_tc, skb->hash & (MAX_JMP_SIZE - 1));
+ }
+
+ trace_printk(fmt, sizeof(fmt));
+ return BPF_H_DEFAULT;
+}
+
+BPF_LICENSE("GPL");
diff --git a/iproute2/examples/cbq.init-v0.7.3 b/iproute2/examples/cbq.init-v0.7.3
new file mode 100644
index 0000000..1bc0d44
--- /dev/null
+++ b/iproute2/examples/cbq.init-v0.7.3
@@ -0,0 +1,983 @@
+#!/bin/bash
+#
+# cbq.init v0.7.3
+# Copyright (C) 1999 Pavel Golubev <pg@ksi-linux.com>
+# Copyright (C) 2001-2004 Lubomir Bulej <pallas@kadan.cz>
+#
+# chkconfig: 2345 11 89
+# description: sets up CBQ-based traffic control
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, see <http://www.gnu.org/licenses/>.
+#
+# To get the latest version, check on Freshmeat for actual location:
+#
+# http://freshmeat.net/projects/cbq.init
+#
+#
+# VERSION HISTORY
+# ---------------
+# v0.7.3- Deepak Singhal <singhal at users.sourceforge.net>
+# - fix timecheck to not ignore regular TIME rules after
+# encountering a TIME rule that spans over midnight
+# - Nathan Shafer <nicodemus at users.sourceforge.net>
+# - allow symlinks to class files
+# - Seth J. Blank <antifreeze at users.sourceforge.net>
+# - replace hardcoded ip/tc location with variables
+# - Mark Davis <mark.davis at gmx.de>
+# - allow setting of PRIO_{MARK,RULE,REALM} in class file
+# - Fernando Sanch <toptnc at users.sourceforge.net>
+# - allow underscores in interface names
+# v0.7.2- Paulo Sedrez
+# - fix time2abs to allow hours with leading zero in TIME rules
+# - Svetlin Simeonov <zvero at yahoo.com>
+# - fix cbq_device_list to allow VLAN interfaces
+# - Mark Davis <mark.davis at gmx.de>
+# - ignore *~ backup files when looking for classes
+# - Mike Boyer <boyer at administrative.com>
+# - fix to allow arguments to be passed to "restart" command
+# v0.7.1- Lubomir Bulej <pallas at kadan.cz>
+# - default value for PERTURB
+# - fixed small bug in RULE parser to correctly parse rules with
+# identical source and destination fields
+# - faster initial scanning of DEVICE fields
+# v0.7 - Lubomir Bulej <pallas at kadan.cz>
+# - lots of various cleanups and reorganizations; the parsing is now
+# some 40% faster, but the class ID must be in range 0x0002-0xffff
+# (again). Because of the number of internal changes and the above
+# class ID restriction, I bumped the version to 0.7 to indicate
+# something might have got broken :)
+# - changed PRIO_{U32,FW,ROUTE} to PRIO_{RULE,MARK,REALM}
+# for consistency with filter keywords
+# - exposed "compile" command
+# - Catalin Petrescu <taz at dntis.ro>
+# - support for port masks in RULE (u32) filter
+# - Jordan Vrtanoski <obeliks at mt.net.mk>
+# - support for week days in TIME rules
+# v0.6.4- Lubomir Bulej <pallas at kadan.cz>
+# - added PRIO_* variables to allow easy control of filter priorities
+# - added caching to speed up CBQ start, the cache is invalidated
+# whenever any of the configuration files changes
+# - updated the readme section + some cosmetic fixes
+# v0.6.3- Lubomir Bulej <pallas at kadan.cz>
+# - removed setup of (unnecessary) class 1:1 - all classes
+# now use qdisc's default class 1:0 as their parent
+# - minor fix in the timecheck branch - classes
+# without leaf qdisc were not updated
+# - minor fix to avoid timecheck failure when run
+# at time with minutes equal to 08 or 09
+# - respect CBQ_PATH setting in environment
+# - made PRIO=5 default, rendering it optional in configs
+# - added support for route filter, see notes about REALM keyword
+# - added support for fw filter, see notes about MARK keyword
+# - added filter display to "list" and "stats" commands
+# - readme section update + various cosmetic fixes
+# v0.6.2- Catalin Petrescu <taz at dntis.ro>
+# - added tunnels interface handling
+# v0.6.1- Pavel Golubev <pg at ksi-linux.com>
+# - added sch_prio module loading
+# (thanks johan at iglo.virtual.or.id for reminding)
+# - resolved errors resulting from stricter syntax checking in bash2
+# - Lubomir Bulej <pallas at kadan.cz>
+# - various cosmetic fixes
+# v0.6 - Lubomir Bulej <pallas at kadan.cz>
+# - attempt to limit number of spawned processes by utilizing
+# more of sed power (use sed instead of grep+cut)
+# - simplified TIME parser, using bash builtins
+# - added initial support for SFQ as leaf qdisc
+# - reworked the documentation part a little
+# - incorporated pending patches and ideas submitted by
+# following people for versions 0.3 into version 0.6
+# - Miguel Freitas <miguel at cetuc.puc-rio.br>
+# - in case of overlapping TIME parameters, the last match is taken
+# - Juanjo Ciarlante <jjo at mendoza.gov.ar>
+# - chkconfig tags, list + stats startup parameters
+# - optional tc & ip command logging (into /var/run/cbq-*)
+# - Rafal Maszkowski <rzm at icm.edu.pl>
+# - PEAK parameter for setting TBF's burst peak rate
+# - fix for many config files (use find instead of ls)
+# v0.5.1- Lubomir Bulej <pallas at kadan.cz>
+# - fixed little but serious bug in RULE parser
+# v0.5 - Lubomir Bulej <pallas at kadan.cz>
+# - added options PARENT, LEAF, ISOLATED and BOUNDED. This allows
+# (with some attention to config file ordering) for creating
+# hierarchical structures of shapers with classes able (or unable)
+# to borrow bandwidth from their parents.
+# - class ID check allows hexadecimal numbers
+# - rewritten & simplified RULE parser
+# - cosmetic changes to improve readability
+# - reorganization to avoid duplicate code (timecheck etc.)
+# - timecheck doesn't check classes without TIME fields anymore
+# v0.4 - Lubomir Bulej <pallas at kadan.cz>
+# - small bugfix in RULE parsing code
+# - simplified configuration parsing code
+# - several small cosmetic changes
+# - TIME parameter can be now specified more than once allowing you to
+# differentiate RATE throughout the whole day. Time overlapping is
+# not checked, first match is taken. Midnight wrap (eg. 20:00-6:00)
+# is allowed and taken care of.
+# v0.3a4- fixed small bug in IF operator. Thanks to
+# Rafal Maszkowski <rzm at icm.edu.pl>
+# v0.3a3- fixed grep bug when using more than 10 eth devices. Thanks to David
+# Trcka <trcka at poda.cz>.
+# v0.3a2- fixed bug in "if" operator. Thanks kad at dgtu.donetsk.ua.
+# v0.3a - added TIME parameter. Example: TIME=00:00-19:00;64Kbit/6Kbit
+# So, between 00:00 and 19:00 the RATE will be 64Kbit.
+# Just start "cbq.init timecheck" periodically from cron
+# (every 10 minutes for example). DON'T FORGET though, to run
+# "cbq.init start" for CBQ to initialize.
+# v0.2 - Some cosmetic changes. Now it is more compatible with old bash
+# version. Thanks to Stanislav V. Voronyi <stas at cnti.uanet.kharkov.ua>.
+# v0.1 - First public release
+#
+#
+# README
+# ------
+#
+# First of all - this is just a SIMPLE EXAMPLE of CBQ power.
+# Don't ask me "why" and "how" :)
+#
+# This script is meant to simplify setup and management of relatively simple
+# CBQ-based traffic control on Linux. Access to advanced networking features
+# of Linux kernel is provided by "ip" and "tc" utilities from A. Kuznetsov's
+# iproute2 package, available at ftp://ftp.inr.ac.ru/ip-routing. Because the
+# utilities serve primarily to translate user wishes to RTNETLINK commands,
+# their interface is rather spartan, intolerant and requires quite a lot of
+# typing. And typing is what this script attempts to reduce :)
+#
+# The advanced networking stuff in Linux is pretty flexible and this script
+# aims to bring some of its features to the not-so-hard-core Linux users. Of
+# course, there is a tradeoff between simplicity and flexibility and you may
+# realize that the flexibility suffered too much for your needs -- time to
+# face "ip" and "tc" interface.
+#
+# To speed up the "start" command, simple caching was introduced in version
+# 0.6.4. The caching works so that the sequence of "tc" commands for given
+# configuration is stored in a file (/var/cache/cbq.init by default) which
+# is used next time the "start" command is run to avoid repeated parsing of
+# configuration files. This cache is invalidated whenever any of the CBQ
+# configuration files changes. If you want to run "cbq.init start" without
+# caching, run it as "cbq.init start nocache". If you want to force cache
+# invalidation, run it as "cbq.init start invalidate". Caching is disabled
+# if you have logging enabled (ie. CBQ_DEBUG is not empty).
+#
+# If you only want cqb.init to translate your configuration to "tc" commands,
+# use "compile" command which will output "tc" commands required to build
+# your configuration. Bear in mind that "compile" does not check if the "tc"
+# commands were successful - this is done (in certain places) only when the
+# "start nocache" command is used, which is also useful when creating the
+# configuration to check whether it is completely valid.
+#
+# All CBQ parameters are valid for Ethernet interfaces only, The script was
+# tested on various Linux kernel versions from series 2.1 to 2.4 and several
+# distributions with KSI Linux (Nostromo version) as the premier one.
+#
+#
+# HOW DOES IT WORK?
+# -----------------
+#
+# Every traffic class must be described by a file in the $CBQ_PATH directory
+# (/etc/sysconfig/cbq by default) - one file per class.
+#
+# The config file names must obey mandatory format: cbq-<clsid>.<name> where
+# <clsid> is two-byte hexadecimal number in range <0002-FFFF> (which in fact
+# is a CBQ class ID) and <name> is the name of the class -- anything to help
+# you distinguish the configuration files. For small amount of classes it is
+# often possible (and convenient) to let <clsid> resemble bandwidth of the
+# class.
+#
+# Example of valid config name:
+# cbq-1280.My_first_shaper
+#
+#
+# The configuration file may contain the following parameters:
+#
+### Device parameters
+#
+# DEVICE=<ifname>,<bandwidth>[,<weight>] mandatory
+# DEVICE=eth0,10Mbit,1Mbit
+#
+# <ifname> is the name of the interface you want to control
+# traffic on, e.g. eth0
+# <bandwidth> is the physical bandwidth of the device, e.g. for
+# ethernet 10Mbit or 100Mbit, for arcnet 2Mbit
+# <weight> is tuning parameter that should be proportional to
+# <bandwidth>. As a rule of thumb: <weight> = <bandwidth> / 10
+#
+# When you have more classes on one interface, it is enough to specify
+# <bandwidth> [and <weight>] only once, therefore in other files you only
+# need to set DEVICE=<ifname>.
+#
+### Class parameters
+#
+# RATE=<speed> mandatory
+# RATE=5Mbit
+#
+# Bandwidth allocated to the class. Traffic going through the class is
+# shaped to conform to specified rate. You can use Kbit, Mbit or bps,
+# Kbps and Mbps as suffices. If you don't specify any unit, bits/sec
+# are used. Also note that "bps" means "bytes per second", not bits.
+#
+# WEIGHT=<speed> mandatory
+# WEIGHT=500Kbit
+#
+# Tuning parameter that should be proportional to RATE. As a rule
+# of thumb, use WEIGHT ~= RATE / 10.
+#
+# PRIO=<1-8> optional, default 5
+# PRIO=5
+#
+# Priority of class traffic. The higher the number, the lesser
+# the priority. Priority of 5 is just fine.
+#
+# PARENT=<clsid> optional, default not set
+# PARENT=1280
+#
+# Specifies ID of the parent class to which you want this class be
+# attached. You might want to use LEAF=none for the parent class as
+# mentioned below. By using this parameter and carefully ordering the
+# configuration files, it is possible to create simple hierarchical
+# structures of CBQ classes. The ordering is important so that parent
+# classes are constructed prior to their children.
+#
+# LEAF=none|tbf|sfq optional, default "tbf"
+#
+# Tells the script to attach specified leaf queueing discipline to CBQ
+# class. By default, TBF is used. Note that attaching TBF to CBQ class
+# shapes the traffic to conform to TBF parameters and prevents the class
+# from borrowing bandwidth from its parent even if you have BOUNDED set
+# to "no". To allow the class to borrow bandwith (provided it is not
+# bounded), you must set LEAF to "none" or "sfq".
+#
+# If you want to ensure (approximately) fair sharing of bandwidth among
+# several hosts in the same class, you might want to specify LEAF=sfq to
+# attach SFQ as leaf queueing discipline to that class.
+#
+# BOUNDED=yes|no optional, default "yes"
+#
+# If set to "yes", the class is not allowed to borrow bandwidth from
+# its parent class in overlimit situation. If set to "no", the class
+# will be allowed to borrow bandwidth from its parent.
+#
+# Note: Don't forget to set LEAF to "none" or "sfq", otherwise the class will
+# have TBF attached to itself and will not be able to borrow unused
+# bandwith from its parent.
+#
+# ISOLATED=yes|no optional, default "no"
+#
+# If set to "yes", the class will not lend unused bandwidth to
+# its children.
+#
+### TBF qdisc parameters
+#
+# BUFFER=<bytes>[/<bytes>] optional, default "10Kb/8"
+#
+# This parameter controls the depth of the token bucket. In other
+# words it represents the maximal burst size the class can send.
+# The optional part of parameter is used to determine the length
+# of intervals in packet sizes, for which the transmission times
+# are kept.
+#
+# LIMIT=<bytes> optional, default "15Kb"
+#
+# This parameter determines the maximal length of backlog. If
+# the queue contains more data than specified by LIMIT, the
+# newly arriving packets are dropped. The length of backlog
+# determines queue latency in case of congestion.
+#
+# PEAK=<speed> optional, default not set
+#
+# Maximal peak rate for short-term burst traffic. This allows you
+# to control the absolute peak rate the class can send at, because
+# single TBF that allows 256Kbit/s would of course allow rate of
+# 512Kbit for half a second or 1Mbit for a quarter of second.
+#
+# MTU=<bytes> optional, default "1500"
+#
+# Maximum number of bytes that can be sent at once over the
+# physical medium. This parameter is required when you specify
+# PEAK parameter. It defaults to MTU of ethernet - for other
+# media types you might want to change it.
+#
+# Note: Setting TBF as leaf qdisc will effectively prevent the class from
+# borrowing bandwidth from the ancestor class, because even if the
+# class allows more traffic to pass through, it is then shaped to
+# conform to TBF.
+#
+### SFQ qdisc parameters
+#
+# The SFQ queueing discipline is a cheap way for sharing class bandwidth
+# among several hosts. As it is stochastic, the fairness is approximate but
+# it will do the job in most cases. If you want real fairness, you should
+# probably use WRR (weighted round robin) or WFQ queueing disciplines. Note
+# that SFQ does not do any traffic shaping - the shaping is done by the CBQ
+# class the SFQ is attached to.
+#
+# QUANTUM=<bytes> optional, default not set
+#
+# This parameter should not be set lower than link MTU, for ethernet
+# it is 1500b, or (with MAC header) 1514b which is the value used
+# in Alexey Kuznetsov's examples.
+#
+# PERTURB=<seconds> optional, default "10"
+#
+# Period of hash function perturbation. If unset, hash reconfiguration
+# will never take place which is what you probably don't want. The
+# default value of 10 seconds is probably a good one.
+#
+### Filter parameters
+#
+# RULE=[[saddr[/prefix]][:port[/mask]],][daddr[/prefix]][:port[/mask]]
+#
+# These parameters make up "u32" filter rules that select traffic for
+# each of the classes. You can use multiple RULE fields per config.
+#
+# The optional port mask should only be used by advanced users who
+# understand how the u32 filter works.
+#
+# Some examples:
+#
+# RULE=10.1.1.0/24:80
+# selects traffic going to port 80 in network 10.1.1.0
+#
+# RULE=10.2.2.5
+# selects traffic going to any port on single host 10.2.2.5
+#
+# RULE=10.2.2.5:20/0xfffe
+# selects traffic going to ports 20 and 21 on host 10.2.2.5
+#
+# RULE=:25,10.2.2.128/26:5000
+# selects traffic going from anywhere on port 50 to
+# port 5000 in network 10.2.2.128
+#
+# RULE=10.5.5.5:80,
+# selects traffic going from port 80 of single host 10.5.5.5
+#
+#
+#
+# REALM=[srealm,][drealm]
+#
+# These parameters make up "route" filter rules that classify traffic
+# according to packet source/destination realms. For information about
+# realms, see Alexey Kuznetsov's IP Command Reference. This script
+# does not define any realms, it justs builds "tc filter" commands
+# for you if you need to classify traffic this way.
+#
+# Realm is either a decimal number or a string referencing entry in
+# /etc/iproute2/rt_realms (usually).
+#
+# Some examples:
+#
+# REALM=russia,internet
+# selects traffic going from realm "russia" to realm "internet"
+#
+# REALM=freenet,
+# selects traffic going from realm "freenet"
+#
+# REALM=10
+# selects traffic going to realm 10
+#
+#
+#
+# MARK=<mark>
+#
+# These parameters make up "fw" filter rules that select traffic for
+# each of the classes accoring to firewall "mark". Mark is a decimal
+# number packets are tagged with if firewall rules say so. You can
+# use multiple MARK fields per config.
+#
+#
+# Note: Rules for different filter types can be combined. Attention must be
+# paid to the priority of filter rules, which can be set below using
+# PRIO_{RULE,MARK,REALM} variables.
+#
+### Time ranging parameters
+#
+# TIME=[<dow>,<dow>, ...,<dow>/]<from>-<till>;<rate>/<weight>[/<peak>]
+# TIME=0,1,2,5/18:00-06:00;256Kbit/25Kbit
+# TIME=60123/18:00-06:00;256Kbit/25Kbit
+# TIME=18:00-06:00;256Kbit/25Kbit
+#
+# This parameter allows you to differentiate the class bandwidth
+# throughout the day. You can specify multiple TIME parameters, if
+# the times overlap, last match is taken. The fields <rate>, <weight>
+# and <peak> correspond to parameters RATE, WEIGHT and PEAK (which
+# is optional and applies to TBF leaf qdisc only).
+#
+# You can also specify days of week when the TIME rule applies. <dow>
+# is numeric, 0 corresponds to sunday, 1 corresponds to monday, etc.
+#
+###
+#
+# Sample configuration file: cbq-1280.My_first_shaper
+#
+# --------------------------------------------------------------------------
+# DEVICE=eth0,10Mbit,1Mbit
+# RATE=128Kbit
+# WEIGHT=10Kbit
+# PRIO=5
+# RULE=192.128.1.0/24
+# --------------------------------------------------------------------------
+#
+# The configuration says that we will control traffic on 10Mbit ethernet
+# device eth0 and the traffic going to network 192.168.1.0 will be
+# processed with priority 5 and shaped to rate of 128Kbit.
+#
+# Note that you can control outgoing traffic only. If you want to control
+# traffic in both directions, you must set up CBQ for both interfaces.
+#
+# Consider the following example:
+#
+# +---------+ 192.168.1.1
+# BACKBONE -----eth0-| linux |-eth1------*-[client]
+# +---------+
+#
+# Imagine you want to shape traffic from backbone to the client to 28Kbit
+# and traffic in the opposite direction to 128Kbit. You need to setup CBQ
+# on both eth0 and eth1 interfaces, thus you need two config files:
+#
+# cbq-028.backbone-client
+# --------------------------------------------------------------------------
+# DEVICE=eth1,10Mbit,1Mbit
+# RATE=28Kbit
+# WEIGHT=2Kbit
+# PRIO=5
+# RULE=192.168.1.1
+# --------------------------------------------------------------------------
+#
+# cbq-128.client-backbone
+# --------------------------------------------------------------------------
+# DEVICE=eth0,10Mbit,1Mbit
+# RATE=128Kbit
+# WEIGHT=10Kbit
+# PRIO=5
+# RULE=192.168.1.1,
+# --------------------------------------------------------------------------
+#
+# Pay attention to comma "," in the RULE field - it denotes source address!
+#
+# Enjoy.
+#
+#############################################################################
+
+export LC_ALL=C
+
+### Command locations
+TC=/sbin/tc
+IP=/sbin/ip
+MP=/sbin/modprobe
+
+### Default filter priorities (must be different)
+PRIO_RULE_DEFAULT=${PRIO_RULE:-100}
+PRIO_MARK_DEFAULT=${PRIO_MARK:-200}
+PRIO_REALM_DEFAULT=${PRIO_REALM:-300}
+
+### Default CBQ_PATH & CBQ_CACHE settings
+CBQ_PATH=${CBQ_PATH:-/etc/sysconfig/cbq}
+CBQ_CACHE=${CBQ_CACHE:-/var/cache/cbq.init}
+
+### Uncomment to enable logfile for debugging
+#CBQ_DEBUG="/var/run/cbq-$1"
+
+### Modules to probe for. Uncomment the last CBQ_PROBE
+### line if you have QoS support compiled into kernel
+CBQ_PROBE="sch_cbq sch_tbf sch_sfq sch_prio"
+CBQ_PROBE="$CBQ_PROBE cls_fw cls_u32 cls_route"
+#CBQ_PROBE=""
+
+### Keywords required for qdisc & class configuration
+CBQ_WORDS="DEVICE|RATE|WEIGHT|PRIO|PARENT|LEAF|BOUNDED|ISOLATED"
+CBQ_WORDS="$CBQ_WORDS|PRIO_MARK|PRIO_RULE|PRIO_REALM|BUFFER"
+CBQ_WORDS="$CBQ_WORDS|LIMIT|PEAK|MTU|QUANTUM|PERTURB"
+
+### Source AVPKT if it exists
+[ -r /etc/sysconfig/cbq/avpkt ] && . /etc/sysconfig/cbq/avpkt
+AVPKT=${AVPKT:-3000}
+
+
+#############################################################################
+############################# SUPPORT FUNCTIONS #############################
+#############################################################################
+
+### Get list of network devices
+cbq_device_list () {
+ ip link show| sed -n "/^[0-9]/ \
+ { s/^[0-9]\+: \([a-z0-9._]\+\)[:@].*/\1/; p; }"
+} # cbq_device_list
+
+
+### Remove root class from device $1
+cbq_device_off () {
+ tc qdisc del dev $1 root 2> /dev/null
+} # cbq_device_off
+
+
+### Remove CBQ from all devices
+cbq_off () {
+ for dev in `cbq_device_list`; do
+ cbq_device_off $dev
+ done
+} # cbq_off
+
+
+### Prefixed message
+cbq_message () {
+ echo -e "**CBQ: $@"
+} # cbq_message
+
+### Failure message
+cbq_failure () {
+ cbq_message "$@"
+ exit 1
+} # cbq_failure
+
+### Failure w/ cbq-off
+cbq_fail_off () {
+ cbq_message "$@"
+ cbq_off
+ exit 1
+} # cbq_fail_off
+
+
+### Convert time to absolute value
+cbq_time2abs () {
+ local min=${1##*:}; min=${min##0}
+ local hrs=${1%%:*}; hrs=${hrs##0}
+ echo $[hrs*60 + min]
+} # cbq_time2abs
+
+
+### Display CBQ setup
+cbq_show () {
+ for dev in `cbq_device_list`; do
+ [ `tc qdisc show dev $dev| wc -l` -eq 0 ] && continue
+ echo -e "### $dev: queueing disciplines\n"
+ tc $1 qdisc show dev $dev; echo
+
+ [ `tc class show dev $dev| wc -l` -eq 0 ] && continue
+ echo -e "### $dev: traffic classes\n"
+ tc $1 class show dev $dev; echo
+
+ [ `tc filter show dev $dev| wc -l` -eq 0 ] && continue
+ echo -e "### $dev: filtering rules\n"
+ tc $1 filter show dev $dev; echo
+ done
+} # cbq_show
+
+
+### Check configuration and load DEVICES, DEVFIELDS and CLASSLIST from $1
+cbq_init () {
+ ### Get a list of configured classes
+ CLASSLIST=`find $1 -maxdepth 1 \( -type f -or -type l \) -name 'cbq-*' \
+ -not -name '*~' -printf "%f\n"| sort`
+ [ -z "$CLASSLIST" ] &&
+ cbq_failure "no configuration files found in $1!"
+
+ ### Gather all DEVICE fields from $1/cbq-*
+ DEVFIELDS=`find $1 -maxdepth 1 \( -type f -or -type l \) -name 'cbq-*' \
+ -not -name '*~' | xargs sed -n 's/#.*//; \
+ s/[[:space:]]//g; /^DEVICE=[^,]*,[^,]*\(,[^,]*\)\?/ \
+ { s/.*=//; p; }'| sort -u`
+ [ -z "$DEVFIELDS" ] &&
+ cbq_failure "no DEVICE field found in $1/cbq-*!"
+
+ ### Check for different DEVICE fields for the same device
+ DEVICES=`echo "$DEVFIELDS"| sed 's/,.*//'| sort -u`
+ [ `echo "$DEVICES"| wc -l` -ne `echo "$DEVFIELDS"| wc -l` ] &&
+ cbq_failure "different DEVICE fields for single device!\n$DEVFIELDS"
+} # cbq_init
+
+
+### Load class configuration from $1/$2
+cbq_load_class () {
+ CLASS=`echo $2| sed 's/^cbq-0*//; s/^\([0-9a-fA-F]\+\).*/\1/'`
+ CFILE=`sed -n 's/#.*//; s/[[:space:]]//g; /^[[:alnum:]_]\+=[[:alnum:].,:;/*@-_]\+$/ p' $1/$2`
+
+ ### Check class number
+ IDVAL=`/usr/bin/printf "%d" 0x$CLASS 2> /dev/null`
+ [ $? -ne 0 -o $IDVAL -lt 2 -o $IDVAL -gt 65535 ] &&
+ cbq_fail_off "class ID of $2 must be in range <0002-FFFF>!"
+
+ ### Set defaults & load class
+ RATE=""; WEIGHT=""; PARENT=""; PRIO=5
+ LEAF=tbf; BOUNDED=yes; ISOLATED=no
+ BUFFER=10Kb/8; LIMIT=15Kb; MTU=1500
+ PEAK=""; PERTURB=10; QUANTUM=""
+
+ PRIO_RULE=$PRIO_RULE_DEFAULT
+ PRIO_MARK=$PRIO_MARK_DEFAULT
+ PRIO_REALM=$PRIO_REALM_DEFAULT
+
+ eval `echo "$CFILE"| grep -E "^($CBQ_WORDS)="`
+
+ ### Require RATE/WEIGHT
+ [ -z "$RATE" -o -z "$WEIGHT" ] &&
+ cbq_fail_off "missing RATE or WEIGHT in $2!"
+
+ ### Class device
+ DEVICE=${DEVICE%%,*}
+ [ -z "$DEVICE" ] && cbq_fail_off "missing DEVICE field in $2!"
+
+ BANDWIDTH=`echo "$DEVFIELDS"| sed -n "/^$DEVICE,/ \
+ { s/[^,]*,\([^,]*\).*/\1/; p; q; }"`
+
+ ### Convert to "tc" options
+ PEAK=${PEAK:+peakrate $PEAK}
+ PERTURB=${PERTURB:+perturb $PERTURB}
+ QUANTUM=${QUANTUM:+quantum $QUANTUM}
+
+ [ "$BOUNDED" = "no" ] && BOUNDED="" || BOUNDED="bounded"
+ [ "$ISOLATED" = "yes" ] && ISOLATED="isolated" || ISOLATED=""
+} # cbq_load_class
+
+
+#############################################################################
+#################################### INIT ###################################
+#############################################################################
+
+### Check for presence of ip-route2 in usual place
+[ -x $TC -a -x $IP ] ||
+ cbq_failure "ip-route2 utilities not installed or executable!"
+
+
+### ip/tc wrappers
+if [ "$1" = "compile" ]; then
+ ### no module probing
+ CBQ_PROBE=""
+
+ ip () {
+ $IP "$@"
+ } # ip
+
+ ### echo-only version of "tc" command
+ tc () {
+ echo "$TC $@"
+ } # tc
+
+elif [ -n "$CBQ_DEBUG" ]; then
+ echo -e "# `date`" > $CBQ_DEBUG
+
+ ### Logging version of "ip" command
+ ip () {
+ echo -e "\n# ip $@" >> $CBQ_DEBUG
+ $IP "$@" 2>&1 | tee -a $CBQ_DEBUG
+ } # ip
+
+ ### Logging version of "tc" command
+ tc () {
+ echo -e "\n# tc $@" >> $CBQ_DEBUG
+ $TC "$@" 2>&1 | tee -a $CBQ_DEBUG
+ } # tc
+else
+ ### Default wrappers
+
+ ip () {
+ $IP "$@"
+ } # ip
+
+ tc () {
+ $TC "$@"
+ } # tc
+fi # ip/tc wrappers
+
+
+case "$1" in
+
+#############################################################################
+############################### START/COMPILE ###############################
+#############################################################################
+
+start|compile)
+
+### Probe QoS modules (start only)
+for module in $CBQ_PROBE; do
+ $MP $module || cbq_failure "failed to load module $module"
+done
+
+### If we are in compile/nocache/logging mode, don't bother with cache
+if [ "$1" != "compile" -a "$2" != "nocache" -a -z "$CBQ_DEBUG" ]; then
+ VALID=1
+
+ ### validate the cache
+ [ "$2" = "invalidate" -o ! -f $CBQ_CACHE ] && VALID=0
+ if [ $VALID -eq 1 ]; then
+ [ `find $CBQ_PATH -maxdepth 1 -newer $CBQ_CACHE| \
+ wc -l` -gt 0 ] && VALID=0
+ fi
+
+ ### compile the config if the cache is invalid
+ if [ $VALID -ne 1 ]; then
+ $0 compile > $CBQ_CACHE ||
+ cbq_fail_off "failed to compile CBQ configuration!"
+ fi
+
+ ### run the cached commands
+ exec /bin/sh $CBQ_CACHE 2> /dev/null
+fi
+
+### Load DEVICES, DEVFIELDS and CLASSLIST
+cbq_init $CBQ_PATH
+
+
+### Setup root qdisc on all configured devices
+for dev in $DEVICES; do
+ ### Retrieve device bandwidth and, optionally, weight
+ DEVTEMP=`echo "$DEVFIELDS"| sed -n "/^$dev,/ { s/$dev,//; p; q; }"`
+ DEVBWDT=${DEVTEMP%%,*}; DEVWGHT=${DEVTEMP##*,}
+ [ "$DEVBWDT" = "$DEVWGHT" ] && DEVWGHT=""
+
+ ### Device bandwidth is required
+ if [ -z "$DEVBWDT" ]; then
+ cbq_message "could not determine bandwidth for device $dev!"
+ cbq_failure "please set up the DEVICE fields properly!"
+ fi
+
+ ### Check if the device is there
+ ip link show $dev &> /dev/null ||
+ cbq_fail_off "device $dev not found!"
+
+ ### Remove old root qdisc from device
+ cbq_device_off $dev
+
+
+ ### Setup root qdisc + class for device
+ tc qdisc add dev $dev root handle 1 cbq \
+ bandwidth $DEVBWDT avpkt $AVPKT cell 8
+
+ ### Set weight of the root class if set
+ [ -n "$DEVWGHT" ] &&
+ tc class change dev $dev root cbq weight $DEVWGHT allot 1514
+
+ [ "$1" = "compile" ] && echo
+done # dev
+
+
+### Setup traffic classes
+for classfile in $CLASSLIST; do
+ cbq_load_class $CBQ_PATH $classfile
+
+ ### Create the class
+ tc class add dev $DEVICE parent 1:$PARENT classid 1:$CLASS cbq \
+ bandwidth $BANDWIDTH rate $RATE weight $WEIGHT prio $PRIO \
+ allot 1514 cell 8 maxburst 20 avpkt $AVPKT $BOUNDED $ISOLATED ||
+ cbq_fail_off "failed to add class $CLASS with parent $PARENT on $DEVICE!"
+
+ ### Create leaf qdisc if set
+ if [ "$LEAF" = "tbf" ]; then
+ tc qdisc add dev $DEVICE parent 1:$CLASS handle $CLASS tbf \
+ rate $RATE buffer $BUFFER limit $LIMIT mtu $MTU $PEAK
+ elif [ "$LEAF" = "sfq" ]; then
+ tc qdisc add dev $DEVICE parent 1:$CLASS handle $CLASS sfq \
+ $PERTURB $QUANTUM
+ fi
+
+
+ ### Create fw filter for MARK fields
+ for mark in `echo "$CFILE"| sed -n '/^MARK/ { s/.*=//; p; }'`; do
+ ### Attach fw filter to root class
+ tc filter add dev $DEVICE parent 1:0 protocol ip \
+ prio $PRIO_MARK handle $mark fw classid 1:$CLASS
+ done ### mark
+
+ ### Create route filter for REALM fields
+ for realm in `echo "$CFILE"| sed -n '/^REALM/ { s/.*=//; p; }'`; do
+ ### Split realm into source & destination realms
+ SREALM=${realm%%,*}; DREALM=${realm##*,}
+ [ "$SREALM" = "$DREALM" ] && SREALM=""
+
+ ### Convert asterisks to empty strings
+ SREALM=${SREALM#\*}; DREALM=${DREALM#\*}
+
+ ### Attach route filter to the root class
+ tc filter add dev $DEVICE parent 1:0 protocol ip \
+ prio $PRIO_REALM route ${SREALM:+from $SREALM} \
+ ${DREALM:+to $DREALM} classid 1:$CLASS
+ done ### realm
+
+ ### Create u32 filter for RULE fields
+ for rule in `echo "$CFILE"| sed -n '/^RULE/ { s/.*=//; p; }'`; do
+ ### Split rule into source & destination
+ SRC=${rule%%,*}; DST=${rule##*,}
+ [ "$SRC" = "$rule" ] && SRC=""
+
+
+ ### Split destination into address, port & mask fields
+ DADDR=${DST%%:*}; DTEMP=${DST##*:}
+ [ "$DADDR" = "$DST" ] && DTEMP=""
+
+ DPORT=${DTEMP%%/*}; DMASK=${DTEMP##*/}
+ [ "$DPORT" = "$DTEMP" ] && DMASK="0xffff"
+
+
+ ### Split up source (if specified)
+ SADDR=""; SPORT=""
+ if [ -n "$SRC" ]; then
+ SADDR=${SRC%%:*}; STEMP=${SRC##*:}
+ [ "$SADDR" = "$SRC" ] && STEMP=""
+
+ SPORT=${STEMP%%/*}; SMASK=${STEMP##*/}
+ [ "$SPORT" = "$STEMP" ] && SMASK="0xffff"
+ fi
+
+
+ ### Convert asterisks to empty strings
+ SADDR=${SADDR#\*}; DADDR=${DADDR#\*}
+
+ ### Compose u32 filter rules
+ u32_s="${SPORT:+match ip sport $SPORT $SMASK}"
+ u32_s="${SADDR:+match ip src $SADDR} $u32_s"
+ u32_d="${DPORT:+match ip dport $DPORT $DMASK}"
+ u32_d="${DADDR:+match ip dst $DADDR} $u32_d"
+
+ ### Uncomment the following if you want to see parsed rules
+ #echo "$rule: $u32_s $u32_d"
+
+ ### Attach u32 filter to the appropriate class
+ tc filter add dev $DEVICE parent 1:0 protocol ip \
+ prio $PRIO_RULE u32 $u32_s $u32_d classid 1:$CLASS
+ done ### rule
+
+ [ "$1" = "compile" ] && echo
+done ### classfile
+;;
+
+
+#############################################################################
+################################# TIME CHECK ################################
+#############################################################################
+
+timecheck)
+
+### Get time + weekday
+TIME_TMP=`date +%w/%k:%M`
+TIME_DOW=${TIME_TMP%%/*}
+TIME_NOW=${TIME_TMP##*/}
+
+### Load DEVICES, DEVFIELDS and CLASSLIST
+cbq_init $CBQ_PATH
+
+### Run through all classes
+for classfile in $CLASSLIST; do
+ ### Gather all TIME rules from class config
+ TIMESET=`sed -n 's/#.*//; s/[[:space:]]//g; /^TIME/ { s/.*=//; p; }' \
+ $CBQ_PATH/$classfile`
+ [ -z "$TIMESET" ] && continue
+
+ MATCH=0; CHANGE=0
+ for timerule in $TIMESET; do
+ TIME_ABS=`cbq_time2abs $TIME_NOW`
+
+ ### Split TIME rule to pieces
+ TIMESPEC=${timerule%%;*}; PARAMS=${timerule##*;}
+ WEEKDAYS=${TIMESPEC%%/*}; INTERVAL=${TIMESPEC##*/}
+ BEG_TIME=${INTERVAL%%-*}; END_TIME=${INTERVAL##*-}
+
+ ### Check the day-of-week (if present)
+ [ "$WEEKDAYS" != "$INTERVAL" -a \
+ -n "${WEEKDAYS##*$TIME_DOW*}" ] && continue
+
+ ### Compute interval boundaries
+ BEG_ABS=`cbq_time2abs $BEG_TIME`
+ END_ABS=`cbq_time2abs $END_TIME`
+
+ ### Midnight wrap fixup
+ if [ $BEG_ABS -gt $END_ABS ]; then
+ [ $TIME_ABS -le $END_ABS ] &&
+ TIME_ABS=$[TIME_ABS + 24*60]
+
+ END_ABS=$[END_ABS + 24*60]
+ fi
+
+ ### If the time matches, remember params and set MATCH flag
+ if [ $TIME_ABS -ge $BEG_ABS -a $TIME_ABS -lt $END_ABS ]; then
+ TMP_RATE=${PARAMS%%/*}; PARAMS=${PARAMS#*/}
+ TMP_WGHT=${PARAMS%%/*}; TMP_PEAK=${PARAMS##*/}
+
+ [ "$TMP_PEAK" = "$TMP_WGHT" ] && TMP_PEAK=""
+ TMP_PEAK=${TMP_PEAK:+peakrate $TMP_PEAK}
+
+ MATCH=1
+ fi
+ done ### timerule
+
+
+ cbq_load_class $CBQ_PATH $classfile
+
+ ### Get current RATE of CBQ class
+ RATE_NOW=`tc class show dev $DEVICE| sed -n \
+ "/cbq 1:$CLASS / { s/.*rate //; s/ .*//; p; q; }"`
+ [ -z "$RATE_NOW" ] && continue
+
+ ### Time interval matched
+ if [ $MATCH -ne 0 ]; then
+
+ ### Check if there is any change in class RATE
+ if [ "$RATE_NOW" != "$TMP_RATE" ]; then
+ NEW_RATE="$TMP_RATE"
+ NEW_WGHT="$TMP_WGHT"
+ NEW_PEAK="$TMP_PEAK"
+ CHANGE=1
+ fi
+
+ ### Match not found, reset to default RATE if necessary
+ elif [ "$RATE_NOW" != "$RATE" ]; then
+ NEW_WGHT="$WEIGHT"
+ NEW_RATE="$RATE"
+ NEW_PEAK="$PEAK"
+ CHANGE=1
+ fi
+
+ ### If there are no changes, go for next class
+ [ $CHANGE -eq 0 ] && continue
+
+ ### Replace CBQ class
+ tc class replace dev $DEVICE classid 1:$CLASS cbq \
+ bandwidth $BANDWIDTH rate $NEW_RATE weight $NEW_WGHT prio $PRIO \
+ allot 1514 cell 8 maxburst 20 avpkt $AVPKT $BOUNDED $ISOLATED
+
+ ### Replace leaf qdisc (if any)
+ if [ "$LEAF" = "tbf" ]; then
+ tc qdisc replace dev $DEVICE handle $CLASS tbf \
+ rate $NEW_RATE buffer $BUFFER limit $LIMIT mtu $MTU $NEW_PEAK
+ fi
+
+ cbq_message "$TIME_NOW: class $CLASS on $DEVICE changed rate ($RATE_NOW -> $NEW_RATE)"
+done ### class file
+;;
+
+
+#############################################################################
+################################## THE REST #################################
+#############################################################################
+
+stop)
+ cbq_off
+ ;;
+
+list)
+ cbq_show
+ ;;
+
+stats)
+ cbq_show -s
+ ;;
+
+restart)
+ shift
+ $0 stop
+ $0 start "$@"
+ ;;
+
+*)
+ echo "Usage: `basename $0` {start|compile|stop|restart|timecheck|list|stats}"
+esac
diff --git a/iproute2/examples/cbqinit.eth1 b/iproute2/examples/cbqinit.eth1
new file mode 100644
index 0000000..226ec1c
--- /dev/null
+++ b/iproute2/examples/cbqinit.eth1
@@ -0,0 +1,76 @@
+#! /bin/sh
+
+TC=/home/root/tc
+IP=/home/root/ip
+DEVICE=eth1
+BANDWIDTH="bandwidth 10Mbit"
+
+# Attach CBQ on $DEVICE. It will have handle 1:.
+# $BANDWIDTH is real $DEVICE bandwidth (10Mbit).
+# avpkt is average packet size.
+# mpu is minimal packet size.
+
+$TC qdisc add dev $DEVICE root handle 1: cbq \
+$BANDWIDTH avpkt 1000 mpu 64
+
+# Create root class with classid 1:1. This step is not necessary.
+# bandwidth is the same as on CBQ itself.
+# rate == all the bandwidth
+# allot is MTU + MAC header
+# maxburst measure allowed class burstiness (please,read S.Floyd and VJ papers)
+# est 1sec 8sec means, that kernel will evaluate average rate
+# on this class with period 1sec and time constant 8sec.
+# This rate is viewed with "tc -s class ls dev $DEVICE"
+
+$TC class add dev $DEVICE parent 1:0 classid :1 est 1sec 8sec cbq \
+$BANDWIDTH rate 10Mbit allot 1514 maxburst 50 avpkt 1000
+
+# Bulk.
+# New parameters are:
+# weight, which is set to be proportional to
+# "rate". It is not necessary, weight=1 will work as well.
+# defmap and split say that best effort ttraffic, not classfied
+# by another means will fall to this class.
+
+$TC class add dev $DEVICE parent 1:1 classid :2 est 1sec 8sec cbq \
+$BANDWIDTH rate 4Mbit allot 1514 weight 500Kbit \
+prio 6 maxburst 50 avpkt 1000 split 1:0 defmap ff3d
+
+# OPTIONAL.
+# Attach "sfq" qdisc to this class, quantum is MTU, perturb
+# gives period of hash function perturbation in seconds.
+#
+$TC qdisc add dev $DEVICE parent 1:2 sfq quantum 1514b perturb 15
+
+# Interactive-burst class
+
+$TC class add dev $DEVICE parent 1:1 classid :3 est 2sec 16sec cbq \
+$BANDWIDTH rate 1Mbit allot 1514 weight 100Kbit \
+prio 2 maxburst 100 avpkt 1000 split 1:0 defmap c0
+
+$TC qdisc add dev $DEVICE parent 1:3 sfq quantum 1514b perturb 15
+
+# Background.
+
+$TC class add dev $DEVICE parent 1:1 classid :4 est 1sec 8sec cbq \
+ $BANDWIDTH rate 100Kbit allot 1514 weight 10Mbit \
+ prio 7 maxburst 10 avpkt 1000 split 1:0 defmap 2
+
+$TC qdisc add dev $DEVICE parent 1:4 sfq quantum 1514b perturb 15
+
+# Realtime class for RSVP
+
+$TC class add dev $DEVICE parent 1:1 classid 1:7FFE cbq \
+rate 5Mbit $BANDWIDTH allot 1514b avpkt 1000 \
+maxburst 20
+
+# Reclassified realtime traffic
+#
+# New element: split is not 1:0, but 1:7FFE. It means,
+# that only real-time packets, which violated policing filters
+# or exceeded reshaping buffers will fall to it.
+
+$TC class add dev $DEVICE parent 1:7FFE classid 1:7FFF est 4sec 32sec cbq \
+rate 1Mbit $BANDWIDTH allot 1514b avpkt 1000 weight 10Kbit \
+prio 6 maxburst 10 split 1:7FFE defmap ffff
+
diff --git a/iproute2/examples/dhcp-client-script b/iproute2/examples/dhcp-client-script
new file mode 100644
index 0000000..f39bc10
--- /dev/null
+++ b/iproute2/examples/dhcp-client-script
@@ -0,0 +1,446 @@
+#!/bin/bash
+#
+# dhclient-script for Linux.
+#
+# This program is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License
+# as published by the Free Software Foundation; either version
+# 2 of the License, or (at your option) any later version.
+#
+# Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+#
+# Probably, I did not understand, what this funny feature as "alias"
+# means exactly. For now I suppose, that it is a static address, which
+# we should install and preserve.
+#
+
+exec >> /var/log/DHS.log 2>&1
+
+echo dhc-script $* reason=$reason
+set | grep "^\(old_\|new_\|check_\)"
+
+LOG () {
+ echo LOG $* ;
+}
+
+# convert 8bit mask to length
+# arg: $1 = mask
+#
+Mask8ToLen() {
+ local l=0;
+
+ while [ $l -le 7 ]; do
+ if [ $[ ( 1 << $l ) + $1 ] -eq 256 ]; then
+ return $[ 8 - $l ]
+ fi
+ l=$[ $l + 1 ]
+ done
+ return 0;
+}
+
+# convert inet dotted quad mask to length
+# arg: $1 = dotquad mask
+#
+MaskToLen() {
+ local masklen=0
+ local mask8=$1
+
+ case $1 in
+ 0.0.0.0)
+ return 0;
+ ;;
+ 255.*.0.0)
+ masklen=8
+ mask8=${mask8#255.}
+ mask8=${mask8%.0.0}
+ ;;
+ 255.255.*.0)
+ masklen=16
+ mask8=${mask8#255.255.}
+ mask8=${mask8%.0}
+ ;;
+ 255.255.255.*)
+ masklen=24
+ mask8=${mask8#255.255.255.}
+ ;;
+ *)
+ return 255
+ ;;
+ esac
+ Mask8ToLen $mask8
+ return $[ $? + $masklen ]
+}
+
+# calculate ABC "natural" mask
+# arg: $1 = dotquad address
+#
+ABCMask () {
+ local class;
+
+ class=${1%%.*}
+
+ if [ "$1" = "255.255.255.255" ]; then
+ echo $1
+ elif [ "$1" = "0.0.0.0" ]; then
+ echo $1
+ elif [ $class -ge 224 ]; then
+ echo 240.0.0.0
+ elif [ $class -ge 192 ]; then
+ echo 255.255.255.0
+ elif [ $class -ge 128 ]; then
+ echo 255.255.0.0
+ else
+ echo 255.0.0.0
+ fi
+}
+
+# calculate ABC "natural" mask length
+# arg: $1 = dotquad address
+#
+ABCMaskLen () {
+ local class;
+
+ class=${1%%.*}
+
+ if [ "$1" = "255.255.255.255" ]; then
+ return 32
+ elif [ "$1" = "0.0.0.0" ]; then
+ return 0
+ elif [ $class -ge 224 ]; then
+ return 4;
+ elif [ $class -ge 192 ]; then
+ return 24;
+ elif [ $class -ge 128 ]; then
+ return 16;
+ else
+ return 8;
+ fi
+}
+
+# Delete IP address
+# args: $1 = interface
+# $2 = address
+# $3 = mask
+# $4 = broadcast
+# $5 = label
+#
+DelINETAddr () {
+ local masklen=32
+ local addrid=$1
+
+ LOG DelINETAddr $*
+
+ if [ "$5" ]; then
+ addrid=$addrid:$5
+ fi
+ LOG ifconfig $addrid down
+ ifconfig $addrid down
+}
+
+# Add IP address
+# args: $1 = interface
+# $2 = address
+# $3 = mask
+# $4 = broadcast
+# $5 = label
+#
+AddINETAddr () {
+ local mask_arg
+ local brd_arg
+ local addrid=$1
+
+ LOG AddINETAddr $*
+
+ if [ "$5" ]; then
+ addrid=$addrid:$5
+ fi
+ if [ "$3" ]; then
+ mask_arg="netmask $3"
+ fi
+ if [ "$4" ]; then
+ brd_arg="broadcast $4"
+ fi
+
+ LOG ifconfig $addrid $2 $mask_arg $brd_arg up
+ ifconfig $addrid $2 $mask_arg $brd_arg up
+}
+
+# Add default routes
+# args: $1 = routers list
+#
+AddDefaultRoutes() {
+ local router
+
+ if [ "$1" ]; then
+ LOG AddDefaultRoutes $*
+ for router in $1; do
+ LOG route add default gw $router
+ route add default gw $router
+ done ;
+ fi
+}
+
+# Delete default routes
+# args: $1 = routers list
+#
+DelDefaultRoutes() {
+ local router
+
+ if [ "$1" ]; then
+ LOG DelDefaultRoutes $*
+
+ for router in $1; do
+ LOG route del default gw $router
+ route del default gw $router
+ done
+ fi
+}
+
+# ping a host
+# args: $1 = dotquad address of the host
+#
+PingNode() {
+ LOG PingNode $*
+ if ping -q -c 1 -w 2 $1 ; then
+ return 0;
+ fi
+ return 1;
+}
+
+# Check (and add route, if alive) default routers
+# args: $1 = routers list
+# returns: 0 if at least one router is alive.
+#
+CheckRouterList() {
+ local router
+ local succeed=1
+
+ LOG CheckRouterList $*
+
+ for router in $1; do
+ if PingNode $router ; then
+ succeed=0
+ route add default gw $router
+ fi
+ done
+ return $succeed
+}
+
+# Delete/create static routes.
+# args: $1 = operation (del/add)
+# $2 = routes list in format "dst1 nexthop1 dst2 ..."
+#
+# BEWARE: this feature of DHCP is obsolete, because does not
+# support subnetting.
+#
+X-StaticRouteList() {
+ local op=$1
+ local lst="$2"
+ local masklen
+
+ LOG X-StaticRouteList $*
+
+ if [ "$lst" ]; then
+ set $lst
+ while [ $# -gt 1 ]; do
+ route $op -net $1 netmask `ABCMask "$1"` gw $2
+ shift; shift;
+ done
+ fi
+}
+
+# Create static routes.
+# arg: $1 = routes list in format "dst1 nexthop1 dst2 ..."
+#
+AddStaticRouteList() {
+ LOG AddStaticRouteList $*
+ X-StaticRouteList add "$1"
+}
+
+# Delete static routes.
+# arg: $1 = routes list in format "dst1 nexthop1 dst2 ..."
+#
+DelStaticRouteList() {
+ LOG DelStaticRouteList $*
+ X-StaticRouteList del "$1"
+}
+
+# Broadcast unsolicited ARP to update neighbours' caches.
+# args: $1 = interface
+# $2 = address
+#
+UnsolicitedARP() {
+ if [ -f /sbin/arping ]; then
+ /sbin/arping -A -c 1 -I "$1" "$2" &
+ (sleep 2 ; /sbin/arping -U -c 1 -I "$1" "$2" ) &
+ fi
+}
+
+# Duplicate address detection.
+# args: $1 = interface
+# $2 = test address
+# returns: 0, if DAD succeeded.
+DAD() {
+ if [ -f /sbin/arping ]; then
+ /sbin/arping -c 2 -w 3 -D -I "$1" "$2"
+ return $?
+ fi
+ return 0
+}
+
+
+# Setup resolver.
+# args: NO
+# domain and nameserver list are passed in global variables.
+#
+# NOTE: we try to be careful and not to break user supplied resolv.conf.
+# The script mangles it, only if it has dhcp magic signature.
+#
+UpdateDNS() {
+ local nameserver
+ local idstring="#### Generated by DHCPCD"
+
+ LOG UpdateDNS $*
+
+ if [ "$new_domain_name" = "" -a "$new_domain_name_servers" = "" ]; then
+ return 0;
+ fi
+
+ echo $idstring > /etc/resolv.conf.dhcp
+ if [ "$new_domain_name" ]; then
+ echo search $new_domain_name >> /etc/resolv.conf.dhcp
+ fi
+ echo options ndots:1 >> /etc/resolv.conf.dhcp
+
+ if [ "$new_domain_name_servers" ]; then
+ for nameserver in $new_domain_name_servers; do
+ echo nameserver $nameserver >> /etc/resolv.conf.dhcp
+ done
+ else
+ echo nameserver 127.0.0.1 >> /etc/resolv.conf.dhcp
+ fi
+
+ if [ -f /etc/resolv.conf ]; then
+ if [ "`head -1 /etc/resolv.conf`" != "$idstring" ]; then
+ return 0
+ fi
+ if [ "$old_domain_name" = "$new_domain_name" -a
+ "$new_domain_name_servers" = "$old_domain_name_servers" ]; then
+ return 0
+ fi
+ fi
+ mv /etc/resolv.conf.dhcp /etc/resolv.conf
+}
+
+case $reason in
+NBI)
+ exit 1
+ ;;
+
+MEDIUM)
+ exit 0
+ ;;
+
+PREINIT)
+ ifconfig $interface:dhcp down
+ ifconfig $interface:dhcp1 down
+ if [ -d /proc/sys/net/ipv4/conf/$interface ]; then
+ ifconfig $interface:dhcp 10.10.10.10 netmask 255.255.255.255
+ ifconfig $interface:dhcp down
+ if [ -d /proc/sys/net/ipv4/conf/$interface ]; then
+ LOG The interface $interface already configured.
+ fi
+ fi
+ ifconfig $interface:dhcp up
+ exit 0
+ ;;
+
+ARPSEND)
+ exit 0
+ ;;
+
+ARPCHECK)
+ if DAD "$interface" "$check_ip_address" ; then
+ exit 0
+ fi
+ exit 1
+ ;;
+
+BOUND|RENEW|REBIND|REBOOT)
+ if [ "$old_ip_address" -a "$alias_ip_address" -a \
+ "$alias_ip_address" != "$old_ip_address" ]; then
+ DelINETAddr "$interface" "$alias_ip_address" "$alias_subnet_mask" "$alias_broadcast_address" dhcp1
+ fi
+ if [ "$old_ip_address" -a "$old_ip_address" != "$new_ip_address" ]; then
+ DelINETAddr "$interface" "$old_ip_address" "$old_subnet_mask" "$old_broadcast_address" dhcp
+ DelDefaultRoutes "$old_routers"
+ DelStaticRouteList "$old_static_routes"
+ fi
+ if [ "$old_ip_address" = "" -o "$old_ip_address" != "$new_ip_address" -o \
+ "$reason" = "BOUND" -o "$reason" = "REBOOT" ]; then
+ AddINETAddr "$interface" "$new_ip_address" "$new_subnet_mask" "$new_broadcast_address" dhcp
+ AddStaticRouteList "$new_static_routes"
+ AddDefaultRoutes "$new_routers"
+ UnsolicitedARP "$interface" "$new_ip_address"
+ fi
+ if [ "$new_ip_address" != "$alias_ip_address" -a "$alias_ip_address" ]; then
+ AddINETAddr "$interface" "$alias_ip_address" "$alias_subnet_mask" "$alias_broadcast_address" dhcp1
+ fi
+ UpdateDNS
+ exit 0
+ ;;
+
+EXPIRE|FAIL)
+ if [ "$alias_ip_address" ]; then
+ DelINETAddr "$interface" "$alias_ip_address" "$alias_subnet_mask" "$alias_broadcast_address" dhcp1
+ fi
+ if [ "$old_ip_address" ]; then
+ DelINETAddr "$interface" "$old_ip_address" "$old_subnet_mask" "$old_broadcast_address" dhcp
+ DelDefaultRoutes "$old_routers"
+ DelStaticRouteList "$old_static_routes"
+ fi
+ if [ "$alias_ip_address" ]; then
+ AddINETAddr "$interface" "$alias_ip_address" "$alias_subnet_mask" "$alias_broadcast_address" dhcp1
+ fi
+ exit 0
+ ;;
+
+TIMEOUT)
+ if [ "$alias_ip_address" ]; then
+ DelINETAddr "$interface" "$alias_ip_address" "$alias_subnet_mask" "$alias_broadcast_address" dhcp1
+ fi
+# Seems, <null address> means, that no more old leases found.
+# Or does it mean bug in dhcpcd? 8) Fail for now.
+ if [ "$new_ip_address" = "<null address>" ]; then
+ if [ "$old_ip_address" ]; then
+ DelINETAddr "$interface" "$old_ip_address" "$old_subnet_mask" "$old_broadcast_address" dhcp
+ fi
+ if [ "$alias_ip_address" ]; then
+ AddINETAddr "$interface" "$alias_ip_address" "$alias_subnet_mask" "$alias_broadcast_address" dhcp1
+ fi
+ exit 1
+ fi
+ if DAD "$interface" "$new_ip_address" ; then
+ AddINETAddr "$interface" "$new_ip_address" "$new_subnet_mask" "$new_broadcast_address" dhcp
+ UnsolicitedARP "$interface" "$new_ip_address"
+ if [ "$alias_ip_address" -a "$alias_ip_address" != "$new_ip_address" ]; then
+ AddINETAddr "$interface" "$alias_ip_address" "$alias_subnet_mask" "$alias_broadcast_address" dhcp1
+ UnsolicitedARP "$interface" "$alias_ip_address"
+ fi
+ if CheckRouterList "$new_routers" ; then
+ AddStaticRouteList "$new_static_routes"
+ UpdateDNS
+ exit 0
+ fi
+ fi
+ DelINETAddr "$interface" "$new_ip_address" "$new_subnet_mask" "$new_broadcast_address" dhcp
+ DelDefaultRoutes "$old_routers"
+ DelStaticRouteList "$old_static_routes"
+ if [ "$alias_ip_address" ]; then
+ AddINETAddr "$interface" "$alias_ip_address" "$alias_subnet_mask" "$alias_broadcast_address" dhcp1
+ fi
+ exit 1
+ ;;
+esac
+
+exit 0
diff --git a/iproute2/examples/diffserv/Edge1 b/iproute2/examples/diffserv/Edge1
new file mode 100644
index 0000000..4ddffdd
--- /dev/null
+++ b/iproute2/examples/diffserv/Edge1
@@ -0,0 +1,68 @@
+#! /bin/sh -x
+#
+# sample script on using the ingress capabilities
+# This script just tags on the ingress interfac using Ipchains
+# the result is used for fast classification and re-marking
+# on the egress interface
+#
+#path to various utilities;
+#change to reflect yours.
+#
+IPROUTE=/root/DS-6-beta/iproute2-990530-dsing
+TC=$IPROUTE/tc/tc
+IP=$IPROUTE/ip/ip
+IPCHAINS=/root/DS-6-beta/ipchains-1.3.9/ipchains
+INDEV=eth2
+EGDEV="dev eth1"
+#
+# tag all incoming packets from host 10.2.0.24 to value 1
+# tag all incoming packets from host 10.2.0.3 to value 2
+# tag the rest of incoming packets from subnet 10.2.0.0/24 to value 3
+#These values are used in the egress
+#
+############################################################
+$IPCHAINS -A input -s 10.2.0.4/24 -m 3
+$IPCHAINS -A input -i $INDEV -s 10.2.0.24 -m 1
+$IPCHAINS -A input -i $INDEV -s 10.2.0.3 -m 2
+
+######################## Egress side ########################
+
+
+# attach a dsmarker
+#
+$TC qdisc add $EGDEV handle 1:0 root dsmark indices 64 set_tc_index
+#
+# values of the DSCP to change depending on the class
+#
+#becomes EF
+$TC class change $EGDEV classid 1:1 dsmark mask 0x3 \
+ value 0xb8
+#becomes AF11
+$TC class change $EGDEV classid 1:2 dsmark mask 0x3 \
+ value 0x28
+#becomes AF21
+$TC class change $EGDEV classid 1:3 dsmark mask 0x3 \
+ value 0x48
+#
+#
+# The class mapping
+#
+$TC filter add $EGDEV parent 1:0 protocol ip prio 4 handle 1 fw classid 1:1
+$TC filter add $EGDEV parent 1:0 protocol ip prio 4 handle 2 fw classid 1:2
+$TC filter add $EGDEV parent 1:0 protocol ip prio 4 handle 3 fw classid 1:3
+#
+
+#
+echo "---- qdisc parameters Ingress ----------"
+$TC qdisc ls dev $INDEV
+echo "---- Class parameters Ingress ----------"
+$TC class ls dev $INDEV
+echo "---- filter parameters Ingress ----------"
+$TC filter ls dev $INDEV parent 1:0
+
+echo "---- qdisc parameters Egress ----------"
+$TC qdisc ls $EGDEV
+echo "---- Class parameters Egress ----------"
+$TC class ls $EGDEV
+echo "---- filter parameters Egress ----------"
+$TC filter ls $EGDEV parent 1:0
diff --git a/iproute2/examples/diffserv/Edge2 b/iproute2/examples/diffserv/Edge2
new file mode 100644
index 0000000..2f78da2
--- /dev/null
+++ b/iproute2/examples/diffserv/Edge2
@@ -0,0 +1,87 @@
+#! /bin/sh -x
+#
+# sample script on using the ingress capabilities
+# This script tags the fwmark on the ingress interface using IPchains
+# the result is used first for policing on the Ingress interface then
+# for fast classification and re-marking
+# on the egress interface
+#
+#path to various utilities;
+#change to reflect yours.
+#
+IPROUTE=/root/DS-6-beta/iproute2-990530-dsing
+TC=$IPROUTE/tc/tc
+IP=$IPROUTE/ip/ip
+IPCHAINS=/root/DS-6-beta/ipchains-1.3.9/ipchains
+INDEV=eth2
+EGDEV="dev eth1"
+#
+# tag all incoming packets from host 10.2.0.24 to value 1
+# tag all incoming packets from host 10.2.0.3 to value 2
+# tag the rest of incoming packets from subnet 10.2.0.0/24 to value 3
+#These values are used in the egress
+############################################################
+$IPCHAINS -A input -s 10.2.0.0/24 -m 3
+$IPCHAINS -A input -i $INDEV -s 10.2.0.24 -m 1
+$IPCHAINS -A input -i $INDEV -s 10.2.0.3 -m 2
+############################################################
+#
+# install the ingress qdisc on the ingress interface
+############################################################
+$TC qdisc add dev $INDEV handle ffff: ingress
+############################################################
+
+#
+# attach a fw classifier to the ingress which polices anything marked
+# by ipchains to tag value 3 (The rest of the subnet packets -- not
+# tag 1 or 2) to not go beyond 1.5Mbps
+# Allow up to at least 60 packets to burst (assuming maximum packet
+# size of # 1.5 KB) in the long run and upto about 6 packets in the
+# shot run
+
+############################################################
+$TC filter add dev $INDEV parent ffff: protocol ip prio 50 handle 3 fw \
+police rate 1500kbit burst 90k mtu 9k drop flowid :1
+############################################################
+
+######################## Egress side ########################
+
+
+# attach a dsmarker
+#
+$TC qdisc add $EGDEV handle 1:0 root dsmark indices 64
+#
+# values of the DSCP to change depending on the class
+#
+$TC class change $EGDEV classid 1:1 dsmark mask 0x3 \
+ value 0xb8
+$TC class change $EGDEV classid 1:2 dsmark mask 0x3 \
+ value 0x28
+$TC class change $EGDEV classid 1:3 dsmark mask 0x3 \
+ value 0x48
+#
+#
+# The class mapping
+#
+$TC filter add $EGDEV parent 1:0 protocol ip prio 4 handle 1 fw classid 1:1
+$TC filter add $EGDEV parent 1:0 protocol ip prio 4 handle 2 fw classid 1:2
+$TC filter add $EGDEV parent 1:0 protocol ip prio 4 handle 3 fw classid 1:3
+#
+
+#
+echo "---- qdisc parameters Ingress ----------"
+$TC qdisc ls dev $INDEV
+echo "---- Class parameters Ingress ----------"
+$TC class ls dev $INDEV
+echo "---- filter parameters Ingress ----------"
+$TC filter ls dev $INDEV parent ffff:
+
+echo "---- qdisc parameters Egress ----------"
+$TC qdisc ls $EGDEV
+echo "---- Class parameters Egress ----------"
+$TC class ls $EGDEV
+echo "---- filter parameters Egress ----------"
+$TC filter ls $EGDEV parent 1:0
+#
+#deleting the ingress qdisc
+#$TC qdisc del $DEV ingress
diff --git a/iproute2/examples/diffserv/Edge31-ca-u32 b/iproute2/examples/diffserv/Edge31-ca-u32
new file mode 100644
index 0000000..25e6c0b
--- /dev/null
+++ b/iproute2/examples/diffserv/Edge31-ca-u32
@@ -0,0 +1,170 @@
+#! /bin/sh -x
+#
+# sample script on using the ingress capabilities using u32 classifier
+# This script tags tcindex based on metering on the ingress
+# interface the result is used for fast classification and re-marking
+# on the egress interface
+# This is an example of a color aware mode marker with PIR configured
+# based on draft-wahjak-mcm-00.txt (section 3.1)
+#
+# The colors are defined using the Diffserv Fields
+#path to various utilities;
+#change to reflect yours.
+#
+IPROUTE=/usr/src/iproute2-current
+TC=$IPROUTE/tc/tc
+IP=$IPROUTE/ip/ip
+INDEV=eth0
+EGDEV="dev eth1"
+CIR1=1500kbit
+CIR2=1000kbit
+
+#The CBS is about 60 MTU sized packets
+CBS1=90k
+CBS2=90k
+
+############################################################
+#
+# install the ingress qdisc on the ingress interface
+$TC qdisc add dev $INDEV handle ffff: ingress
+############################################################
+#
+# Create u32 filters
+$TC filter add dev $INDEV parent ffff: protocol ip prio 4 handle 1: u32 \
+divisor 1
+############################################################
+
+# The meters: Note that we have shared meters in this case as identified
+# by the index parameter
+meter1=" police index 1 rate $CIR1 burst $CBS1 "
+meter2=" police index 2 rate $CIR2 burst $CBS1 "
+meter3=" police index 3 rate $CIR2 burst $CBS2 "
+meter4=" police index 4 rate $CIR1 burst $CBS2 "
+meter5=" police index 5 rate $CIR1 burst $CBS2 "
+
+# All packets are marked with a tcindex value which is used on the egress
+# tcindex 1 maps to AF41, 2->AF42, 3->AF43, 4->BE
+
+# *********************** AF41 ***************************
+#AF41 (DSCP 0x22) is passed on with a tcindex value 1
+#if it doesnt exceed its CIR/CBS
+#policer 1 is used.
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 4 u32 \
+match ip tos 0x88 0xfc \
+$meter1 \
+continue flowid :1
+#
+# if it exceeds the above but not the extra rate/burst below, it gets a
+# tcindex value of 2
+# policer 2 is used
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 5 u32 \
+match ip tos 0x88 0xfc \
+$meter2 \
+continue flowid :2
+#
+# if it exceeds the above but not the rule below, it gets a tcindex value
+# of 3 (policer 3)
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 6 u32 \
+match ip tos 0x88 0xfc \
+$meter3 \
+drop flowid :3
+#
+
+# *********************** AF42 ***************************
+#AF42 (DSCP 0x24) from is passed on with a tcindex value 2
+#if it doesnt exceed its CIR/CBS
+#policer 2 is used. Note that this is shared with the AF41
+#
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 5 u32 \
+match ip tos 0x90 0xfc \
+$meter2 \
+continue flowid :2
+#
+# if it exceeds the above but not the rule below, it gets a tcindex value
+# of 3 (policer 3)
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 6 u32 \
+match ip tos 0x90 0xfc \
+$meter3 \
+drop flowid :3
+#
+# *********************** AF43 ***************************
+#
+#AF43 (DSCP 0x26) from is passed on with a tcindex value 3
+#if it doesnt exceed its CIR/CBS
+#policer 3 is used. Note that this is shared with the AF41 and AF42
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 6 u32 \
+match ip tos 0x98 0xfc \
+$meter3 \
+drop flowid :3
+#
+# *********************** BE ***************************
+#
+# Anything else (not from the AF4*) gets discarded if it
+# exceeds 1Mbps and by default goes to BE if it doesnt
+# Note that the BE class is also used by the AF4* in the worst
+# case
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 7 u32 \
+match ip src 0/0\
+$meter4 \
+drop flowid :4
+
+######################## Egress side ########################
+
+# attach a dsmarker
+#
+$TC qdisc add $EGDEV handle 1:0 root dsmark indices 64
+#
+# values of the DSCP to change depending on the class
+#note that the ECN bits are masked out
+#
+#AF41 (0x88 is 0x22 shifted to the right by two bits)
+#
+$TC class change $EGDEV classid 1:1 dsmark mask 0x3 \
+ value 0x88
+#AF42
+$TC class change $EGDEV classid 1:2 dsmark mask 0x3 \
+ value 0x90
+#AF43
+$TC class change $EGDEV classid 1:3 dsmark mask 0x3 \
+ value 0x98
+#BE
+$TC class change $EGDEV classid 1:3 dsmark mask 0x3 \
+ value 0x0
+#
+#
+# The class mapping
+#
+$TC filter add $EGDEV parent 1:0 protocol ip prio 1 \
+ handle 1 tcindex classid 1:1
+$TC filter add $EGDEV parent 1:0 protocol ip prio 1 \
+ handle 2 tcindex classid 1:2
+$TC filter add $EGDEV parent 1:0 protocol ip prio 1 \
+ handle 3 tcindex classid 1:3
+$TC filter add $EGDEV parent 1:0 protocol ip prio 1 \
+ handle 4 tcindex classid 1:4
+#
+
+#
+echo "---- qdisc parameters Ingress ----------"
+$TC qdisc ls dev $INDEV
+echo "---- Class parameters Ingress ----------"
+$TC class ls dev $INDEV
+echo "---- filter parameters Ingress ----------"
+$TC filter ls dev $INDEV parent ffff:
+
+echo "---- qdisc parameters Egress ----------"
+$TC qdisc ls $EGDEV
+echo "---- Class parameters Egress ----------"
+$TC class ls $EGDEV
+echo "---- filter parameters Egress ----------"
+$TC filter ls $EGDEV parent 1:0
+#
+#deleting the ingress qdisc
+#$TC qdisc del $INDEV ingress
diff --git a/iproute2/examples/diffserv/Edge31-cb-chains b/iproute2/examples/diffserv/Edge31-cb-chains
new file mode 100644
index 0000000..d7faae9
--- /dev/null
+++ b/iproute2/examples/diffserv/Edge31-cb-chains
@@ -0,0 +1,132 @@
+#! /bin/sh -x
+#
+# sample script on using the ingress capabilities
+# This script fwmark tags(IPchains) based on metering on the ingress
+# interface the result is used for fast classification and re-marking
+# on the egress interface
+# This is an example of a color blind mode marker with no PIR configured
+# based on draft-wahjak-mcm-00.txt (section 3.1)
+#
+#path to various utilities;
+#change to reflect yours.
+#
+IPROUTE=/root/DS-6-beta/iproute2-990530-dsing
+TC=$IPROUTE/tc/tc
+IP=$IPROUTE/ip/ip
+IPCHAINS=/root/DS-6-beta/ipchains-1.3.9/ipchains
+INDEV=eth2
+EGDEV="dev eth1"
+CIR1=1500kbit
+CIR2=1000kbit
+
+#The CBS is about 60 MTU sized packets
+CBS1=90k
+CBS2=90k
+
+meter1="police rate $CIR1 burst $CBS1 "
+meter2="police rate $CIR1 burst $CBS2 "
+meter3="police rate $CIR2 burst $CBS1 "
+meter4="police rate $CIR2 burst $CBS2 "
+meter5="police rate $CIR2 burst $CBS2 "
+#
+# tag the rest of incoming packets from subnet 10.2.0.0/24 to fw value 1
+# tag all incoming packets from any other subnet to fw tag 2
+############################################################
+$IPCHAINS -A input -i $INDEV -s 0/0 -m 2
+$IPCHAINS -A input -i $INDEV -s 10.2.0.0/24 -m 1
+#
+############################################################
+# install the ingress qdisc on the ingress interface
+$TC qdisc add dev $INDEV handle ffff: ingress
+#
+############################################################
+
+# All packets are marked with a tcindex value which is used on the egress
+# tcindex 1 maps to AF41, 2->AF42, 3->AF43, 4->BE
+#
+############################################################
+#
+# anything with fw tag of 1 is passed on with a tcindex value 1
+#if it doesnt exceed its allocated rate (CIR/CBS)
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 4 handle 1 fw \
+$meter1 \
+continue flowid 4:1
+#
+# if it exceeds the above but not the extra rate/burst below, it gets a
+#tcindex value of 2
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 5 handle 1 fw \
+$meter2 \
+continue flowid 4:2
+#
+# if it exceeds the above but not the rule below, it gets a tcindex value
+# of 3
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 6 handle 1 fw \
+$meter3 \
+drop flowid 4:3
+#
+# Anything else (not from the subnet 10.2.0.24/24) gets discarded if it
+# exceeds 1Mbps and by default goes to BE if it doesnt
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 6 handle 2 fw \
+$meter5 \
+drop flowid 4:4
+
+
+######################## Egress side ########################
+
+
+# attach a dsmarker
+#
+$TC qdisc add $EGDEV handle 1:0 root dsmark indices 64
+#
+# values of the DSCP to change depending on the class
+#note that the ECN bits are masked out
+#
+#AF41 (0x88 is 0x22 shifted to the right by two bits)
+#
+$TC class change $EGDEV classid 1:1 dsmark mask 0x3 \
+ value 0x88
+#AF42
+$TC class change $EGDEV classid 1:2 dsmark mask 0x3 \
+ value 0x90
+#AF43
+$TC class change $EGDEV classid 1:3 dsmark mask 0x3 \
+ value 0x98
+#BE
+$TC class change $EGDEV classid 1:4 dsmark mask 0x3 \
+ value 0x0
+#
+#
+# The class mapping (using tcindex; could easily have
+# replaced it with the fw classifier instead)
+#
+$TC filter add $EGDEV parent 1:0 protocol ip prio 1 \
+ handle 1 tcindex classid 1:1
+$TC filter add $EGDEV parent 1:0 protocol ip prio 1 \
+ handle 2 tcindex classid 1:2
+$TC filter add $EGDEV parent 1:0 protocol ip prio 1 \
+ handle 3 tcindex classid 1:3
+$TC filter add $EGDEV parent 1:0 protocol ip prio 1 \
+ handle 4 tcindex classid 1:4
+#
+
+#
+echo "---- qdisc parameters Ingress ----------"
+$TC qdisc ls dev $INDEV
+echo "---- Class parameters Ingress ----------"
+$TC class ls dev $INDEV
+echo "---- filter parameters Ingress ----------"
+$TC filter ls dev $INDEV parent ffff:
+
+echo "---- qdisc parameters Egress ----------"
+$TC qdisc ls $EGDEV
+echo "---- Class parameters Egress ----------"
+$TC class ls $EGDEV
+echo "---- filter parameters Egress ----------"
+$TC filter ls $EGDEV parent 1:0
+#
+#deleting the ingress qdisc
+#$TC qdisc del $INDEV ingress
diff --git a/iproute2/examples/diffserv/Edge32-ca-u32 b/iproute2/examples/diffserv/Edge32-ca-u32
new file mode 100644
index 0000000..edf21e4
--- /dev/null
+++ b/iproute2/examples/diffserv/Edge32-ca-u32
@@ -0,0 +1,198 @@
+#! /bin/sh -x
+#
+# sample script on using the ingress capabilities using u32 classifier
+# This script tags tcindex based on metering on the ingress
+# interface the result is used for fast classification and re-marking
+# on the egress interface
+# This is an example of a color aware mode marker with PIR configured
+# based on draft-wahjak-mcm-00.txt (section 3.2)
+#
+# The colors are defined using the Diffserv Fields
+#path to various utilities;
+#change to reflect yours.
+#
+IPROUTE=/root/DS-6-beta/iproute2-990530-dsing
+TC=$IPROUTE/tc/tc
+IP=$IPROUTE/ip/ip
+IPCHAINS=/root/DS-6-beta/ipchains-1.3.9/ipchains
+INDEV=eth2
+EGDEV="dev eth1"
+CIR1=1000kbit
+CIR2=500kbit
+# the PIR is what is in excess of the CIR
+PIR1=1000kbit
+PIR2=500kbit
+
+#The CBS is about 60 MTU sized packets
+CBS1=90k
+CBS2=90k
+#the EBS is about 20 max sized packets
+EBS1=30k
+EBS2=30k
+
+# The meters: Note that we have shared meters in this case as identified
+# by the index parameter
+meter1=" police index 1 rate $CIR1 burst $CBS1 "
+meter1a=" police index 2 rate $PIR1 burst $EBS1 "
+meter2=" police index 3 rate $CIR2 burst $CBS1 "
+meter2a=" police index 4 rate $PIR2 burst $EBS1 "
+meter3=" police index 5 rate $CIR2 burst $CBS2 "
+meter3a=" police index 6 rate $PIR2 burst $EBS2 "
+meter4=" police index 7 rate $CIR1 burst $CBS2 "
+
+############################################################
+#
+# install the ingress qdisc on the ingress interface
+$TC qdisc add dev $INDEV handle ffff: ingress
+############################################################
+#
+# All packets are marked with a tcindex value which is used on the egress
+# tcindex 1 maps to AF41, 2->AF42, 3->AF43, 4->BE
+#
+# *********************** AF41 ***************************
+#AF41 (DSCP 0x22) from is passed on with a tcindex value 1
+#if it doesnt exceed its CIR/CBS + PIR/EBS
+#policer 1 is used.
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 1 u32 \
+match ip tos 0x88 0xfc \
+$meter1 \
+continue flowid :1
+$TC filter add dev $INDEV parent ffff: protocol ip prio 2 u32 \
+match ip tos 0x88 0xfc \
+$meter1a \
+continue flowid :1
+#
+# if it exceeds the above but not the extra rate/burst below, it gets a
+# tcindex value of 2
+# policer 2 is used
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 3 u32 \
+match ip tos 0x88 0xfc \
+$meter2 \
+continue flowid :2
+$TC filter add dev $INDEV parent ffff: protocol ip prio 4 u32 \
+match ip tos 0x88 0xfc \
+$meter2a \
+continue flowid :2
+#
+# if it exceeds the above but not the rule below, it gets a tcindex value
+# of 3 (policer 3)
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 5 u32 \
+match ip tos 0x88 0xfc \
+$meter3 \
+continue flowid :3
+$TC filter add dev $INDEV parent ffff: protocol ip prio 6 u32 \
+match ip tos 0x88 0xfc \
+$meter3a \
+drop flowid :3
+#
+# *********************** AF42 ***************************
+#AF42 (DSCP 0x24) from is passed on with a tcindex value 2
+#if it doesnt exceed its CIR/CBS + PIR/EBS
+#policer 2 is used. Note that this is shared with the AF41
+#
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 8 u32 \
+match ip tos 0x90 0xfc \
+$meter2 \
+continue flowid :2
+$TC filter add dev $INDEV parent ffff: protocol ip prio 9 u32 \
+match ip tos 0x90 0xfc \
+$meter2a \
+continue flowid :2
+#
+# if it exceeds the above but not the rule below, it gets a tcindex value
+# of 3 (policer 3)
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 10 u32 \
+match ip tos 0x90 0xfc \
+$meter3 \
+continue flowid :3
+$TC filter add dev $INDEV parent ffff: protocol ip prio 11 u32 \
+match ip tos 0x90 0xfc \
+$meter3a \
+drop flowid :3
+
+#
+# *********************** AF43 ***************************
+#
+#AF43 (DSCP 0x26) from is passed on with a tcindex value 3
+#if it doesnt exceed its CIR/CBS + PIR/EBS
+#policer 3 is used. Note that this is shared with the AF41 and AF42
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 13 u32 \
+match ip tos 0x98 0xfc \
+$meter3 \
+continue flowid :3
+$TC filter add dev $INDEV parent ffff: protocol ip prio 14 u32 \
+match ip tos 0x98 0xfc \
+$meter3a \
+drop flowid :3
+#
+## *********************** BE ***************************
+##
+## Anything else (not from the AF4*) gets discarded if it
+## exceeds 1Mbps and by default goes to BE if it doesnt
+## Note that the BE class is also used by the AF4* in the worst
+## case
+##
+$TC filter add dev $INDEV parent ffff: protocol ip prio 16 u32 \
+match ip src 0/0\
+$meter4 \
+drop flowid :4
+
+######################## Egress side ########################
+
+# attach a dsmarker
+#
+$TC qdisc add $EGDEV handle 1:0 root dsmark indices 64
+#
+# values of the DSCP to change depending on the class
+#note that the ECN bits are masked out
+#
+#AF41 (0x88 is 0x22 shifted to the right by two bits)
+#
+$TC class change $EGDEV classid 1:1 dsmark mask 0x3 \
+ value 0x88
+#AF42
+$TC class change $EGDEV classid 1:2 dsmark mask 0x3 \
+ value 0x90
+#AF43
+$TC class change $EGDEV classid 1:3 dsmark mask 0x3 \
+ value 0x98
+#BE
+$TC class change $EGDEV classid 1:3 dsmark mask 0x3 \
+ value 0x0
+#
+#
+# The class mapping
+#
+$TC filter add $EGDEV parent 1:0 protocol ip prio 1 \
+ handle 1 tcindex classid 1:1
+$TC filter add $EGDEV parent 1:0 protocol ip prio 1 \
+ handle 2 tcindex classid 1:2
+$TC filter add $EGDEV parent 1:0 protocol ip prio 1 \
+ handle 3 tcindex classid 1:3
+$TC filter add $EGDEV parent 1:0 protocol ip prio 1 \
+ handle 4 tcindex classid 1:4
+#
+
+#
+echo "---- qdisc parameters Ingress ----------"
+$TC qdisc ls dev $INDEV
+echo "---- Class parameters Ingress ----------"
+$TC class ls dev $INDEV
+echo "---- filter parameters Ingress ----------"
+$TC filter ls dev $INDEV parent ffff:
+
+echo "---- qdisc parameters Egress ----------"
+$TC qdisc ls $EGDEV
+echo "---- Class parameters Egress ----------"
+$TC class ls $EGDEV
+echo "---- filter parameters Egress ----------"
+$TC filter ls $EGDEV parent 1:0
+#
+#deleting the ingress qdisc
+#$TC qdisc del $INDEV ingress
diff --git a/iproute2/examples/diffserv/Edge32-cb-chains b/iproute2/examples/diffserv/Edge32-cb-chains
new file mode 100644
index 0000000..804fad1
--- /dev/null
+++ b/iproute2/examples/diffserv/Edge32-cb-chains
@@ -0,0 +1,144 @@
+#! /bin/sh -x
+#
+# sample script on using the ingress capabilities
+# This script fwmark tags(IPchains) based on metering on the ingress
+# interface the result is used for fast classification and re-marking
+# on the egress interface
+# This is an example of a color blind mode marker with no PIR configured
+# based on draft-wahjak-mcm-00.txt (section 3.1)
+#
+#path to various utilities;
+#change to reflect yours.
+#
+IPROUTE=/root/DS-6-beta/iproute2-990530-dsing
+TC=$IPROUTE/tc/tc
+IP=$IPROUTE/ip/ip
+IPCHAINS=/root/DS-6-beta/ipchains-1.3.9/ipchains
+INDEV=eth2
+EGDEV="dev eth1"
+CIR1=1500kbit
+CIR2=500kbit
+
+#The CBS is about 60 MTU sized packets
+CBS1=90k
+CBS2=90k
+
+meter1="police rate $CIR1 burst $CBS1 "
+meter1a="police rate $CIR2 burst $CBS1 "
+meter2="police rate $CIR1 burst $CBS2 "
+meter2a="police rate $CIR2 burst $CBS2 "
+meter3="police rate $CIR2 burst $CBS1 "
+meter3a="police rate $CIR2 burst $CBS1 "
+meter4="police rate $CIR2 burst $CBS2 "
+meter5="police rate $CIR1 burst $CBS2 "
+#
+# tag the rest of incoming packets from subnet 10.2.0.0/24 to fw value 1
+# tag all incoming packets from any other subnet to fw tag 2
+############################################################
+$IPCHAINS -A input -i $INDEV -s 0/0 -m 2
+$IPCHAINS -A input -i $INDEV -s 10.2.0.0/24 -m 1
+#
+############################################################
+# install the ingress qdisc on the ingress interface
+$TC qdisc add dev $INDEV handle ffff: ingress
+#
+############################################################
+
+# All packets are marked with a tcindex value which is used on the egress
+# tcindex 1 maps to AF41, 2->AF42, 3->AF43, 4->BE
+#
+############################################################
+#
+# anything with fw tag of 1 is passed on with a tcindex value 1
+#if it doesnt exceed its allocated rate (CIR/CBS)
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 1 handle 1 fw \
+$meter1 \
+continue flowid 4:1
+$TC filter add dev $INDEV parent ffff: protocol ip prio 2 handle 1 fw \
+$meter1a \
+continue flowid 4:1
+#
+# if it exceeds the above but not the extra rate/burst below, it gets a
+#tcindex value of 2
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 3 handle 1 fw \
+$meter2 \
+continue flowid 4:2
+$TC filter add dev $INDEV parent ffff: protocol ip prio 4 handle 1 fw \
+$meter2a \
+continue flowid 4:2
+#
+# if it exceeds the above but not the rule below, it gets a tcindex value
+# of 3
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 5 handle 1 fw \
+$meter3 \
+continue flowid 4:3
+$TC filter add dev $INDEV parent ffff: protocol ip prio 6 handle 1 fw \
+$meter3a \
+drop flowid 4:3
+#
+# Anything else (not from the subnet 10.2.0.24/24) gets discarded if it
+# exceeds 1Mbps and by default goes to BE if it doesnt
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 7 handle 2 fw \
+$meter5 \
+drop flowid 4:4
+
+
+######################## Egress side ########################
+
+
+# attach a dsmarker
+#
+$TC qdisc add $EGDEV handle 1:0 root dsmark indices 64
+#
+# values of the DSCP to change depending on the class
+#note that the ECN bits are masked out
+#
+#AF41 (0x88 is 0x22 shifted to the right by two bits)
+#
+$TC class change $EGDEV classid 1:1 dsmark mask 0x3 \
+ value 0x88
+#AF42
+$TC class change $EGDEV classid 1:2 dsmark mask 0x3 \
+ value 0x90
+#AF43
+$TC class change $EGDEV classid 1:3 dsmark mask 0x3 \
+ value 0x98
+#BE
+$TC class change $EGDEV classid 1:4 dsmark mask 0x3 \
+ value 0x0
+#
+#
+# The class mapping (using tcindex; could easily have
+# replaced it with the fw classifier instead)
+#
+$TC filter add $EGDEV parent 1:0 protocol ip prio 1 \
+ handle 1 tcindex classid 1:1
+$TC filter add $EGDEV parent 1:0 protocol ip prio 1 \
+ handle 2 tcindex classid 1:2
+$TC filter add $EGDEV parent 1:0 protocol ip prio 1 \
+ handle 3 tcindex classid 1:3
+$TC filter add $EGDEV parent 1:0 protocol ip prio 1 \
+ handle 4 tcindex classid 1:4
+#
+
+#
+echo "---- qdisc parameters Ingress ----------"
+$TC qdisc ls dev $INDEV
+echo "---- Class parameters Ingress ----------"
+$TC class ls dev $INDEV
+echo "---- filter parameters Ingress ----------"
+$TC filter ls dev $INDEV parent ffff:
+
+echo "---- qdisc parameters Egress ----------"
+$TC qdisc ls $EGDEV
+echo "---- Class parameters Egress ----------"
+$TC class ls $EGDEV
+echo "---- filter parameters Egress ----------"
+$TC filter ls $EGDEV parent 1:0
+#
+#deleting the ingress qdisc
+#$TC qdisc del $INDEV ingress
diff --git a/iproute2/examples/diffserv/Edge32-cb-u32 b/iproute2/examples/diffserv/Edge32-cb-u32
new file mode 100644
index 0000000..cc2ebb4
--- /dev/null
+++ b/iproute2/examples/diffserv/Edge32-cb-u32
@@ -0,0 +1,145 @@
+#! /bin/sh
+#
+# sample script on using the ingress capabilities using u32 classifier
+# This script tags tcindex based on metering on the ingress
+# interface the result is used for fast classification and re-marking
+# on the egress interface
+# This is an example of a color blind mode marker with PIR configured
+# based on draft-wahjak-mcm-00.txt (section 3.2)
+#
+#path to various utilities;
+#change to reflect yours.
+#
+IPROUTE=/root/DS-6-beta/iproute2-990530-dsing
+TC=$IPROUTE/tc/tc
+IP=$IPROUTE/ip/ip
+INDEV=eth2
+EGDEV="dev eth1"
+CIR1=1000kbit
+CIR2=1000kbit
+# The PIR is the excess (in addition to the CIR i.e if always
+# going to the PIR --> average rate is CIR+PIR)
+PIR1=1000kbit
+PIR2=500kbit
+
+#The CBS is about 60 MTU sized packets
+CBS1=90k
+CBS2=90k
+#the EBS is about 10 max sized packets
+EBS1=15k
+EBS2=15k
+# The meters
+meter1=" police rate $CIR1 burst $CBS1 "
+meter1a=" police rate $PIR1 burst $EBS1 "
+meter2=" police rate $CIR2 burst $CBS1 "
+meter2a="police rate $PIR2 burst $CBS1 "
+meter3=" police rate $CIR2 burst $CBS2 "
+meter3a=" police rate $PIR2 burst $EBS2 "
+meter4=" police rate $CIR1 burst $CBS2 "
+meter5=" police rate $CIR1 burst $CBS2 "
+
+
+# install the ingress qdisc on the ingress interface
+############################################################
+$TC qdisc add dev $INDEV handle ffff: ingress
+############################################################
+#
+############################################################
+
+# All packets are marked with a tcindex value which is used on the egress
+# NOTE: tcindex 1 maps to AF41, 2->AF42, 3->AF43, 4->BE
+#
+#anything from subnet 10.2.0.2/24 is passed on with a tcindex value 1
+#if it doesnt exceed its CIR/CBS + PIR/EBS
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 1 u32 \
+match ip src 10.2.0.0/24 $meter1 \
+continue flowid :1
+$TC filter add dev $INDEV parent ffff: protocol ip prio 2 u32 \
+match ip src 10.2.0.0/24 $meter1a \
+continue flowid :1
+
+#
+# if it exceeds the above but not the extra rate/burst below, it gets a
+#tcindex value of 2
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 3 u32 \
+match ip src 10.2.0.0/24 $meter2 \
+continue flowid :2
+$TC filter add dev $INDEV parent ffff: protocol ip prio 4 u32 \
+match ip src 10.2.0.0/24 $meter2a \
+continue flowid :2
+#
+# if it exceeds the above but not the rule below, it gets a tcindex value
+# of 3
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 5 u32 \
+match ip src 10.2.0.0/24 $meter3 \
+continue flowid :3
+$TC filter add dev $INDEV parent ffff: protocol ip prio 6 u32 \
+match ip src 10.2.0.0/24 $meter3a \
+drop flowid :3
+#
+#
+# Anything else (not from the subnet 10.2.0.24/24) gets discarded if it
+# exceeds 1Mbps and by default goes to BE if it doesnt
+#
+$TC filter add dev $INDEV parent ffff: protocol ip prio 7 u32 \
+match ip src 0/0 $meter5 \
+drop flowid :4
+
+
+######################## Egress side ########################
+
+
+# attach a dsmarker
+#
+$TC qdisc add $EGDEV handle 1:0 root dsmark indices 64
+#
+# values of the DSCP to change depending on the class
+#note that the ECN bits are masked out
+#
+#AF41 (0x88 is 0x22 shifted to the right by two bits)
+#
+$TC class change $EGDEV classid 1:1 dsmark mask 0x3 \
+ value 0x88
+#AF42
+$TC class change $EGDEV classid 1:2 dsmark mask 0x3 \
+ value 0x90
+#AF43
+$TC class change $EGDEV classid 1:3 dsmark mask 0x3 \
+ value 0x98
+#BE
+$TC class change $EGDEV classid 1:3 dsmark mask 0x3 \
+ value 0x0
+#
+#
+# The class mapping
+#
+$TC filter add $EGDEV parent 1:0 protocol ip prio 1 \
+ handle 1 tcindex classid 1:1
+$TC filter add $EGDEV parent 1:0 protocol ip prio 1 \
+ handle 2 tcindex classid 1:2
+$TC filter add $EGDEV parent 1:0 protocol ip prio 1 \
+ handle 3 tcindex classid 1:3
+$TC filter add $EGDEV parent 1:0 protocol ip prio 1 \
+ handle 4 tcindex classid 1:4
+#
+
+#
+echo "---- qdisc parameters Ingress ----------"
+$TC qdisc ls dev $INDEV
+echo "---- Class parameters Ingress ----------"
+$TC class ls dev $INDEV
+echo "---- filter parameters Ingress ----------"
+$TC filter ls dev $INDEV parent ffff:
+
+echo "---- qdisc parameters Egress ----------"
+$TC qdisc ls $EGDEV
+echo "---- Class parameters Egress ----------"
+$TC class ls $EGDEV
+echo "---- filter parameters Egress ----------"
+$TC filter ls $EGDEV parent 1:0
+#
+#deleting the ingress qdisc
+#$TC qdisc del $INDEV ingress
diff --git a/iproute2/examples/diffserv/README b/iproute2/examples/diffserv/README
new file mode 100644
index 0000000..ec91d63
--- /dev/null
+++ b/iproute2/examples/diffserv/README
@@ -0,0 +1,98 @@
+
+Note all these are mere examples which can be customized to your needs
+
+AFCBQ
+-----
+AF PHB built using CBQ, DSMARK,GRED (default in GRIO mode) ,RED for BE
+and the tcindex classifier with some algorithmic mapping
+
+EFCBQ
+-----
+EF PHB built using CBQ (for rate control and prioritization),
+DSMARK( to remark DSCPs), tcindex classifier and RED for the BE
+traffic.
+
+EFPRIO
+------
+EF PHB using the PRIO scheduler, Token Bucket to rate control EF,
+tcindex classifier, DSMARK to remark, and RED for the BE traffic
+
+EDGE scripts
+==============
+
+CB-3(1|2)-(u32/chains)
+======================
+
+
+The major differences are that the classifier is u32 on -u32 extension
+and IPchains on the chains extension. CB stands for color Blind
+and 31 is for the mode where only a CIR and CBS are defined whereas
+32 stands for a mode where a CIR/CBS + PIR/EBS are defined.
+
+Color Blind (CB)
+==========-----=
+We look at one special subnet that we are interested in for simplicty
+reasons to demonstrate the capability. We send the packets from that
+subnet to AF4*, BE or end up dropping depending on the metering results.
+
+
+The algorithm overview is as follows:
+
+*classify:
+
+**case: subnet X
+----------------
+ if !exceed meter1 tag as AF41
+ else
+ if !exceed meter2 tag as AF42
+ else
+ if !exceed meter 3 tag as AF43
+ else
+ drop
+
+default case: Any other subnet
+-------------------------------
+ if !exceed meter 5 tag as AF43
+ else
+ drop
+
+
+One Egress side change the DSCPs of the packets to reflect AF4* and BE
+based on the tags from the ingress.
+
+-------------------------------------------------------------
+
+Color Aware
+===========
+
+Define some meters with + policing and give them IDs eg
+
+meter1=police index 1 rate $CIR1 burst $CBS1
+meter2=police index 2 rate $CIR2 burst $CBS2 etc
+
+General overview:
+classify based on the DSCPs and use the policer ids to decide tagging
+
+
+*classify on ingress:
+
+switch (dscp) {
+ case AF41: /* tos&0xfc == 0x88 */
+ if (!exceed meter1) break;
+ case AF42: /* tos&0xfc == 0x90 */
+ if (!exceed meter2) {
+ tag as AF42;
+ break;
+ }
+ case AF43: /* tos&0xfc == 0x98 */
+ if (!exceed meter3) {
+ tag as AF43;
+ break;
+ } else
+ drop;
+ default:
+ if (!exceed meter4) tag as BE;
+ else drop;
+}
+
+On the Egress side mark the proper AF tags
diff --git a/iproute2/examples/diffserv/afcbq b/iproute2/examples/diffserv/afcbq
new file mode 100644
index 0000000..10d6d93
--- /dev/null
+++ b/iproute2/examples/diffserv/afcbq
@@ -0,0 +1,105 @@
+#!/usr/bin/perl
+#
+#
+# AF using CBQ for a single interface eth0
+# 4 AF classes using GRED and one BE using RED
+# Things you might want to change:
+# - the device bandwidth (set at 10Mbits)
+# - the bandwidth allocated for each AF class and the BE class
+# - the drop probability associated with each AF virtual queue
+#
+# AF DSCP values used (based on AF draft 04)
+# -----------------------------------------
+# AF DSCP values
+# AF1 1. 0x0a 2. 0x0c 3. 0x0e
+# AF2 1. 0x12 2. 0x14 3. 0x16
+# AF3 1. 0x1a 2. 0x1c 3. 0x1e
+# AF4 1. 0x22 2. 0x24 3. 0x26
+
+#
+#
+# A simple DSCP-class relationship formula used to generate
+# values in the for loop of this script; $drop stands for the
+# DP
+# $dscp = ($class*8+$drop*2)
+#
+# if you use GRIO buffer sharing, then GRED priority is set as follows:
+# $gprio=$drop+1;
+#
+
+$TC = "/usr/src/iproute2-current/tc/tc";
+$DEV = "dev lo";
+$DEV = "dev eth1";
+$DEV = "dev eth0";
+# the BE-class number
+$beclass = "5";
+
+#GRIO buffer sharing on or off?
+$GRIO = "";
+$GRIO = "grio";
+# The bandwidth of your device
+$linerate="10Mbit";
+# The BE and AF rates
+%rate_table=();
+$berate="1500Kbit";
+$rate_table{"AF1rate"}="1500Kbit";
+$rate_table{"AF2rate"}="1500Kbit";
+$rate_table{"AF3rate"}="1500Kbit";
+$rate_table{"AF4rate"}="1500Kbit";
+#
+#
+#
+print "\n# --- General setup ---\n";
+print "$TC qdisc add $DEV handle 1:0 root dsmark indices 64 set_tc_index\n";
+print "$TC filter add $DEV parent 1:0 protocol ip prio 1 tcindex mask 0xfc " .
+ "shift 2 pass_on\n";
+ #"shift 2\n";
+print "$TC qdisc add $DEV parent 1:0 handle 2:0 cbq bandwidth $linerate ".
+ "cell 8 avpkt 1000 mpu 64\n";
+print "$TC filter add $DEV parent 2:0 protocol ip prio 1 tcindex ".
+ "mask 0xf0 shift 4 pass_on\n";
+for $class (1..4) {
+ print "\n# --- AF Class $class specific setup---\n";
+ $AFrate=sprintf("AF%drate",$class);
+ print "$TC class add $DEV parent 2:0 classid 2:$class cbq ".
+ "bandwidth $linerate rate $rate_table{$AFrate} avpkt 1000 prio ".
+ (6-$class)." bounded allot 1514 weight 1 maxburst 21\n";
+ print "$TC filter add $DEV parent 2:0 protocol ip prio 1 handle $class ".
+ "tcindex classid 2:$class\n";
+ print "$TC qdisc add $DEV parent 2:$class gred setup DPs 3 default 2 ".
+ "$GRIO\n";
+#
+# per DP setup
+#
+ for $drop (1..3) {
+ print "\n# --- AF Class $class DP $drop---\n";
+ $dscp = $class*8+$drop*2;
+ $tcindex = sprintf("1%x%x",$class,$drop);
+ print "$TC filter add $DEV parent 1:0 protocol ip prio 1 ".
+ "handle $dscp tcindex classid 1:$tcindex\n";
+ $prob = $drop*0.02;
+ if ($GRIO) {
+ $gprio = $drop+1;
+ print "$TC qdisc change $DEV parent 2:$class gred limit 60KB min 15KB ".
+ "max 45KB burst 20 avpkt 1000 bandwidth $linerate DP $drop ".
+ "probability $prob ".
+ "prio $gprio\n";
+ } else {
+ print "$TC qdisc change $DEV parent 2:$class gred limit 60KB min 15KB ".
+ "max 45KB burst 20 avpkt 1000 bandwidth $linerate DP $drop ".
+ "probability $prob \n";
+ }
+ }
+}
+#
+#
+print "\n#------BE Queue setup------\n";
+print "$TC filter add $DEV parent 1:0 protocol ip prio 2 ".
+ "handle 0 tcindex mask 0 classid 1:1\n";
+print "$TC class add $DEV parent 2:0 classid 2:$beclass cbq ".
+ "bandwidth $linerate rate $berate avpkt 1000 prio 6 " .
+ "bounded allot 1514 weight 1 maxburst 21 \n";
+print "$TC filter add $DEV parent 2:0 protocol ip prio 1 handle 0 tcindex ".
+ "classid 2:5\n";
+print "$TC qdisc add $DEV parent 2:5 red limit 60KB min 15KB max 45KB ".
+ "burst 20 avpkt 1000 bandwidth $linerate probability 0.4\n";
diff --git a/iproute2/examples/diffserv/ef-prio b/iproute2/examples/diffserv/ef-prio
new file mode 100644
index 0000000..48611bd
--- /dev/null
+++ b/iproute2/examples/diffserv/ef-prio
@@ -0,0 +1,25 @@
+#!/usr/bin/perl
+$TC = "/root/DS-6-beta/iproute2-990530-dsing/tc/tc";
+$DEV = "dev eth1";
+$efrate="1.5Mbit";
+$MTU="1.5kB";
+print "$TC qdisc add $DEV handle 1:0 root dsmark indices 64 set_tc_index\n";
+print "$TC filter add $DEV parent 1:0 protocol ip prio 1 tcindex ".
+ "mask 0xfc shift 2\n";
+print "$TC qdisc add $DEV parent 1:0 handle 2:0 prio\n";
+#
+# EF class: Maximum about one MTU sized packet allowed on the queue
+#
+print "$TC qdisc add $DEV parent 2:1 tbf rate $efrate burst $MTU limit 1.6kB\n";
+print "$TC filter add $DEV parent 2:0 protocol ip prio 1 ".
+ "handle 0x2e tcindex classid 2:1 pass_on\n";
+#
+# BE class
+#
+print "#BE class(2:2) \n";
+print "$TC qdisc add $DEV parent 2:2 red limit 60KB ".
+ "min 15KB max 45KB burst 20 avpkt 1000 bandwidth 10Mbit ".
+ "probability 0.4\n";
+#
+print "$TC filter add $DEV parent 2:0 protocol ip prio 2 ".
+ "handle 0 tcindex mask 0 classid 2:2 pass_on\n";
diff --git a/iproute2/examples/diffserv/efcbq b/iproute2/examples/diffserv/efcbq
new file mode 100644
index 0000000..bcc437b
--- /dev/null
+++ b/iproute2/examples/diffserv/efcbq
@@ -0,0 +1,31 @@
+#!/usr/bin/perl
+#
+$TC = "/root/DS-6-beta/iproute2-990530-dsing/tc/tc";
+$DEV = "dev eth1";
+print "$TC qdisc add $DEV handle 1:0 root dsmark indices 64 set_tc_index\n";
+print "$TC filter add $DEV parent 1:0 protocol ip prio 1 tcindex ".
+ "mask 0xfc shift 2\n";
+print "$TC qdisc add $DEV parent 1:0 handle 2:0 cbq bandwidth ".
+ "10Mbit cell 8 avpkt 1000 mpu 64\n";
+#
+# EF class
+#
+print "$TC class add $DEV parent 2:0 classid 2:1 cbq bandwidth ".
+ "10Mbit rate 1500Kbit avpkt 1000 prio 1 bounded isolated ".
+ "allot 1514 weight 1 maxburst 10 \n";
+# packet fifo for EF?
+print "$TC qdisc add $DEV parent 2:1 pfifo limit 5\n";
+print "$TC filter add $DEV parent 2:0 protocol ip prio 1 ".
+ "handle 0x2e tcindex classid 2:1 pass_on\n";
+#
+# BE class
+#
+print "#BE class(2:2) \n";
+print "$TC class add $DEV parent 2:0 classid 2:2 cbq bandwidth ".
+ "10Mbit rate 5Mbit avpkt 1000 prio 7 allot 1514 weight 1 ".
+ "maxburst 21 borrow split 2:0 defmap 0xffff \n";
+print "$TC qdisc add $DEV parent 2:2 red limit 60KB ".
+ "min 15KB max 45KB burst 20 avpkt 1000 bandwidth 10Mbit ".
+ "probability 0.4\n";
+print "$TC filter add $DEV parent 2:0 protocol ip prio 2 ".
+ "handle 0 tcindex mask 0 classid 2:2 pass_on\n";
diff --git a/iproute2/examples/diffserv/regression-testing b/iproute2/examples/diffserv/regression-testing
new file mode 100644
index 0000000..0ec705c
--- /dev/null
+++ b/iproute2/examples/diffserv/regression-testing
@@ -0,0 +1,125 @@
+
+These were the tests done to validate the Diffserv scripts.
+This document will be updated continously. If you do more
+thorough validation testing please post the details to the
+diffserv mailing list.
+Nevertheless, these tests should serve for basic validation.
+
+AFCBQ, EFCBQ, EFPRIO
+----------------------
+
+generate all possible DSCPs and observe that they
+get sent to the proper classes. In the case of AF also
+to the correct Virtual Queues.
+
+Edge1
+-----
+generate TOS values 0x0,0x10,0xbb each with IP addresses
+10.2.0.24 (mark 1), 10.2.0.3 (mark2) and 10.2.0.30 (mark 3)
+and observe that they get marked as expected.
+
+Edge2
+-----
+
+-Repeat the tests in Edge1
+-ftp with data direction from 10.2.0.2
+ *observe that the metering/policing works correctly (and the marking
+ as well). In this case the mark used will be 3
+
+Edge31-cb-chains
+----------------
+
+-ftp with data direction from 10.2.0.2
+
+ *observe that the metering/policing works correctly (and the marking
+ as well). In this case the mark used will be 1.
+
+ Metering: The data throughput should not exceed 2*CIR1 + 2*CIR2
+ which is roughly: 5mbps
+
+ Marking: the should be a variation of marked packets:
+ AF41(TOS=0x88) AF42(0x90) AF43(0x98) and BE (0x0)
+
+More tests required to see the interaction of several sources (other
+than subnet 10.2.0.0/24).
+
+Edge31-ca-u32
+--------------
+
+Generate data using modified tcpblast from 10.2.0.2 (behind eth2) to the
+discard port of 10.1.0.2 (behind eth1)
+
+1) generate with src tos = 0x88
+ Metering: Allocated throughput should not exceed 2*CIR1 + 2*CIR2
+ approximately 5mbps
+ Marking: Should vary between 0x88,0x90,0x98 and 0x0
+
+2) generate with src tos = 0x90
+ Metering: Allocated throughput should not exceed CIR1 + 2*CIR2
+ approximately 3.5mbps
+ Marking: Should vary between 0x90,0x98 and 0x0
+
+3) generate with src tos = 0x98
+ Metering: Allocated throughput should not exceed CIR1 + CIR2
+ approximately 2.5mbps
+ Marking: Should vary between 0x98 and 0x0
+
+4) generate with src tos any other than the above
+ Metering: Allocated throughput should not exceed CIR1
+ approximately 1.5mbps
+ Marking: Should be consistent at 0x0
+
+TODO: Testing on how each color shares when all 4 types of packets
+are going through the edge device
+
+Edge32-cb-u32, Edge32-cb-chains
+-------------------------------
+
+-ftp with data direction from 10.2.0.2
+
+ *observe that the metering/policing works correctly (and the marking
+ as well).
+
+ Metering:
+ The data throughput should not exceed 2*CIR1 + 2*CIR2
+ + 2*PIR2 + PIR1 for u32 which is roughly: 6mbps
+ The data throughput should not exceed 2*CIR1 + 5*CIR2
+ for chains which is roughly: 6mbps
+
+ Marking: the should be a variation of marked packets:
+ AF41(TOS=0x88) AF42(0x90) AF43(0x98) and BE (0x0)
+
+TODO:
+-More tests required to see the interaction of several sources (other
+than subnet 10.2.0.0/24).
+-More tests needed to capture stats on how many times the CIR was exceeded
+but the data was not remarked etc.
+
+Edge32-ca-u32
+--------------
+
+Generate data using modified tcpblast from 10.2.0.2 (behind eth2) to the
+discard port of 10.1.0.2 (behind eth1)
+
+1) generate with src tos = 0x88
+ Metering: Allocated throughput should not exceed 2*CIR1 + 2*CIR2
+ +PIR1 -- approximately 4mbps
+ Marking: Should vary between 0x88,0x90,0x98 and 0x0
+
+2) generate with src tos = 0x90
+ Metering: Allocated throughput should not exceed CIR1 + 2*CIR2
+ + 2* PIR2 approximately 3mbps
+ Marking: Should vary between 0x90,0x98 and 0x0
+
+3) generate with src tos = 0x98
+ Metering: Allocated throughput should not exceed PIR1+ CIR1 + CIR2
+ approximately 2.5mbps
+ Marking: Should vary between 0x98 and 0x0
+
+4) generate with src tos any other than the above
+ Metering: Allocated throughput should not exceed CIR1
+ approximately 1mbps
+ Marking: Should be consistent at 0x0
+
+TODO: Testing on how each color shares when all 4 types of packets
+are going through the edge device
diff --git a/iproute2/examples/gaiconf b/iproute2/examples/gaiconf
new file mode 100644
index 0000000..d75292b
--- /dev/null
+++ b/iproute2/examples/gaiconf
@@ -0,0 +1,134 @@
+#!/bin/sh
+
+#
+# Setup address label from /etc/gai.conf
+#
+# Written by YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>, 2010.
+#
+
+IP=ip
+DEFAULT_GAICONF=/etc/gai.conf
+verbose=
+debug=
+
+function run ()
+{
+ if [ x"$verbose" != x"" ]; then
+ echo "$@"
+ fi
+ if [ x"$debug" = x"" ]; then
+ "$@"
+ fi
+}
+
+function do_load_config ()
+{
+ file=$1; shift
+ flush=1
+ cat $file | while read command prefix label; do
+ if [ x"$command" = x"#label" ]; then
+ if [ ${flush} = 1 ]; then
+ run ${IP} -6 addrlabel flush
+ flush=0
+ fi
+ run ${IP} -6 addrlabel add prefix $prefix label $label
+ fi
+ done
+}
+
+function do_list_config ()
+{
+ ${IP} -6 addrlabel list | while read p pfx l lbl; do
+ echo label ${pfx} ${lbl}
+ done
+}
+
+function help ()
+{
+ echo "Usage: $0 [-v] {--list | --config [ ${DEFAULT_GAICONF} ] | --default}"
+ exit 1
+}
+
+TEMP=`getopt -o c::dlv -l config::,default,list,verbose -n gaiconf -- "$@"`
+
+if [ $? != 0 ]; then
+ echo "Terminating..." >&2
+ exit 1
+fi
+
+TEMPFILE=`mktemp`
+
+eval set -- "$TEMP"
+
+while true ; do
+ case "$1" in
+ -c|--config)
+ if [ x"$cmd" != x"" ]; then
+ help
+ fi
+ case "$2" in
+ "") gai_conf="${DEFAULT_GAICONF}"
+ shift 2
+ ;;
+ *) gai_conf="$2"
+ shift 2
+ esac
+ cmd=config
+ ;;
+ -d|--default)
+ if [ x"$cmd" != x"" ]; then
+ help
+ fi
+ gai_conf=${TEMPFILE}
+ cmd=config
+ ;;
+ -l|--list)
+ if [ x"$cmd" != x"" ]; then
+ help
+ fi
+ cmd=list
+ shift
+ ;;
+ -v)
+ verbose=1
+ shift
+ ;;
+ --)
+ shift;
+ break
+ ;;
+ *)
+ echo "Internal error!" >&2
+ exit 1
+ ;;
+ esac
+done
+
+case "$cmd" in
+ config)
+ if [ x"$gai_conf" = x"${TEMPFILE}" ]; then
+ sed -e 's/^[[:space:]]*//' <<END_OF_DEFAULT >${TEMPFILE}
+ label ::1/128 0
+ label ::/0 1
+ label 2002::/16 2
+ label ::/96 3
+ label ::ffff:0:0/96 4
+ label fec0::/10 5
+ label fc00::/7 6
+ label 2001:0::/32 7
+END_OF_DEFAULT
+ fi
+ do_load_config "$gai_conf"
+ ;;
+ list)
+ do_list_config
+ ;;
+ *)
+ help
+ ;;
+esac
+
+rm -f "${TEMPFILE}"
+
+exit 0
+
diff --git a/iproute2/genl/Makefile b/iproute2/genl/Makefile
new file mode 100644
index 0000000..03d1f26
--- /dev/null
+++ b/iproute2/genl/Makefile
@@ -0,0 +1,40 @@
+GENLOBJ=genl.o
+
+include ../Config
+SHARED_LIBS ?= y
+
+CFLAGS += -fno-strict-aliasing
+
+GENLMODULES :=
+GENLMODULES += ctrl.o
+
+GENLOBJ += $(GENLMODULES)
+
+GENLLIB :=
+
+ifeq ($(SHARED_LIBS),y)
+LDFLAGS += -Wl,-export-dynamic
+LDLIBS += -lm -ldl
+endif
+
+all: genl
+
+genl: $(GENLOBJ) $(LIBNETLINK) $(LIBUTIL) $(GENLLIB)
+
+install: all
+ install -m 0755 genl $(DESTDIR)$(SBINDIR)
+
+clean:
+ rm -f $(GENLOBJ) $(GENLLIB) genl
+
+ifneq ($(SHARED_LIBS),y)
+
+genl: static-syms.o
+static-syms.o: static-syms.h
+static-syms.h: $(wildcard *.c)
+ files="$^" ; \
+ for s in `grep -B 3 '\<dlsym' $$files | sed -n '/snprintf/{s:.*"\([^"]*\)".*:\1:;s:%s::;p}'` ; do \
+ sed -n '/'$$s'[^ ]* =/{s:.* \([^ ]*'$$s'[^ ]*\) .*:extern char \1[] __attribute__((weak)); if (!strcmp(sym, "\1")) return \1;:;p}' $$files ; \
+ done > $@
+
+endif
diff --git a/iproute2/genl/ctrl.c b/iproute2/genl/ctrl.c
new file mode 100644
index 0000000..b7a8878
--- /dev/null
+++ b/iproute2/genl/ctrl.c
@@ -0,0 +1,419 @@
+/*
+ * ctrl.c generic netlink controller
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: J Hadi Salim (hadi@cyberus.ca)
+ * Johannes Berg (johannes@sipsolutions.net)
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "genl_utils.h"
+
+#define GENL_MAX_FAM_OPS 256
+#define GENL_MAX_FAM_GRPS 256
+
+static int usage(void)
+{
+ fprintf(stderr,"Usage: ctrl <CMD>\n" \
+ "CMD := get <PARMS> | list | monitor\n" \
+ "PARMS := name <name> | id <id>\n" \
+ "Examples:\n" \
+ "\tctrl ls\n" \
+ "\tctrl monitor\n" \
+ "\tctrl get name foobar\n" \
+ "\tctrl get id 0xF\n");
+ return -1;
+}
+
+int genl_ctrl_resolve_family(const char *family)
+{
+ struct rtnl_handle rth;
+ struct nlmsghdr *nlh;
+ struct genlmsghdr *ghdr;
+ int ret = 0;
+ struct {
+ struct nlmsghdr n;
+ char buf[4096];
+ } req;
+
+ memset(&req, 0, sizeof(req));
+
+ nlh = &req.n;
+ nlh->nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN);
+ nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+ nlh->nlmsg_type = GENL_ID_CTRL;
+
+ ghdr = NLMSG_DATA(&req.n);
+ ghdr->cmd = CTRL_CMD_GETFAMILY;
+
+ if (rtnl_open_byproto(&rth, 0, NETLINK_GENERIC) < 0) {
+ fprintf(stderr, "Cannot open generic netlink socket\n");
+ exit(1);
+ }
+
+ addattr_l(nlh, 128, CTRL_ATTR_FAMILY_NAME, family, strlen(family) + 1);
+
+ if (rtnl_talk(&rth, nlh, nlh, sizeof(req)) < 0) {
+ fprintf(stderr, "Error talking to the kernel\n");
+ goto errout;
+ }
+
+ {
+ struct rtattr *tb[CTRL_ATTR_MAX + 1];
+ struct genlmsghdr *ghdr = NLMSG_DATA(nlh);
+ int len = nlh->nlmsg_len;
+ struct rtattr *attrs;
+
+ if (nlh->nlmsg_type != GENL_ID_CTRL) {
+ fprintf(stderr, "Not a controller message, nlmsg_len=%d "
+ "nlmsg_type=0x%x\n", nlh->nlmsg_len, nlh->nlmsg_type);
+ goto errout;
+ }
+
+ if (ghdr->cmd != CTRL_CMD_NEWFAMILY) {
+ fprintf(stderr, "Unknown controller command %d\n", ghdr->cmd);
+ goto errout;
+ }
+
+ len -= NLMSG_LENGTH(GENL_HDRLEN);
+
+ if (len < 0) {
+ fprintf(stderr, "wrong controller message len %d\n", len);
+ return -1;
+ }
+
+ attrs = (struct rtattr *) ((char *) ghdr + GENL_HDRLEN);
+ parse_rtattr(tb, CTRL_ATTR_MAX, attrs, len);
+
+ if (tb[CTRL_ATTR_FAMILY_ID] == NULL) {
+ fprintf(stderr, "Missing family id TLV\n");
+ goto errout;
+ }
+
+ ret = rta_getattr_u16(tb[CTRL_ATTR_FAMILY_ID]);
+ }
+
+errout:
+ rtnl_close(&rth);
+ return ret;
+}
+
+static void print_ctrl_cmd_flags(FILE *fp, __u32 fl)
+{
+ fprintf(fp, "\n\t\tCapabilities (0x%x):\n ", fl);
+ if (!fl) {
+ fprintf(fp, "\n");
+ return;
+ }
+ fprintf(fp, "\t\t ");
+
+ if (fl & GENL_ADMIN_PERM)
+ fprintf(fp, " requires admin permission;");
+ if (fl & GENL_CMD_CAP_DO)
+ fprintf(fp, " can doit;");
+ if (fl & GENL_CMD_CAP_DUMP)
+ fprintf(fp, " can dumpit;");
+ if (fl & GENL_CMD_CAP_HASPOL)
+ fprintf(fp, " has policy");
+
+ fprintf(fp, "\n");
+}
+
+static int print_ctrl_cmds(FILE *fp, struct rtattr *arg, __u32 ctrl_ver)
+{
+ struct rtattr *tb[CTRL_ATTR_OP_MAX + 1];
+
+ if (arg == NULL)
+ return -1;
+
+ parse_rtattr_nested(tb, CTRL_ATTR_OP_MAX, arg);
+ if (tb[CTRL_ATTR_OP_ID]) {
+ __u32 *id = RTA_DATA(tb[CTRL_ATTR_OP_ID]);
+ fprintf(fp, " ID-0x%x ",*id);
+ }
+ /* we are only gonna do this for newer version of the controller */
+ if (tb[CTRL_ATTR_OP_FLAGS] && ctrl_ver >= 0x2) {
+ __u32 *fl = RTA_DATA(tb[CTRL_ATTR_OP_FLAGS]);
+ print_ctrl_cmd_flags(fp, *fl);
+ }
+ return 0;
+
+}
+
+static int print_ctrl_grp(FILE *fp, struct rtattr *arg, __u32 ctrl_ver)
+{
+ struct rtattr *tb[CTRL_ATTR_MCAST_GRP_MAX + 1];
+
+ if (arg == NULL)
+ return -1;
+
+ parse_rtattr_nested(tb, CTRL_ATTR_MCAST_GRP_MAX, arg);
+ if (tb[2]) {
+ __u32 *id = RTA_DATA(tb[CTRL_ATTR_MCAST_GRP_ID]);
+ fprintf(fp, " ID-0x%x ",*id);
+ }
+ if (tb[1]) {
+ char *name = RTA_DATA(tb[CTRL_ATTR_MCAST_GRP_NAME]);
+ fprintf(fp, " name: %s ", name);
+ }
+ return 0;
+
+}
+
+/*
+ * The controller sends one nlmsg per family
+*/
+static int print_ctrl(const struct sockaddr_nl *who,
+ struct rtnl_ctrl_data *ctrl,
+ struct nlmsghdr *n, void *arg)
+{
+ struct rtattr *tb[CTRL_ATTR_MAX + 1];
+ struct genlmsghdr *ghdr = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr *attrs;
+ FILE *fp = (FILE *) arg;
+ __u32 ctrl_v = 0x1;
+
+ if (n->nlmsg_type != GENL_ID_CTRL) {
+ fprintf(stderr, "Not a controller message, nlmsg_len=%d "
+ "nlmsg_type=0x%x\n", n->nlmsg_len, n->nlmsg_type);
+ return 0;
+ }
+
+ if (ghdr->cmd != CTRL_CMD_GETFAMILY &&
+ ghdr->cmd != CTRL_CMD_DELFAMILY &&
+ ghdr->cmd != CTRL_CMD_NEWFAMILY &&
+ ghdr->cmd != CTRL_CMD_NEWMCAST_GRP &&
+ ghdr->cmd != CTRL_CMD_DELMCAST_GRP) {
+ fprintf(stderr, "Unknown controller command %d\n", ghdr->cmd);
+ return 0;
+ }
+
+ len -= NLMSG_LENGTH(GENL_HDRLEN);
+
+ if (len < 0) {
+ fprintf(stderr, "wrong controller message len %d\n", len);
+ return -1;
+ }
+
+ attrs = (struct rtattr *) ((char *) ghdr + GENL_HDRLEN);
+ parse_rtattr(tb, CTRL_ATTR_MAX, attrs, len);
+
+ if (tb[CTRL_ATTR_FAMILY_NAME]) {
+ char *name = RTA_DATA(tb[CTRL_ATTR_FAMILY_NAME]);
+ fprintf(fp, "\nName: %s\n",name);
+ }
+ if (tb[CTRL_ATTR_FAMILY_ID]) {
+ __u16 *id = RTA_DATA(tb[CTRL_ATTR_FAMILY_ID]);
+ fprintf(fp, "\tID: 0x%x ",*id);
+ }
+ if (tb[CTRL_ATTR_VERSION]) {
+ __u32 *v = RTA_DATA(tb[CTRL_ATTR_VERSION]);
+ fprintf(fp, " Version: 0x%x ",*v);
+ ctrl_v = *v;
+ }
+ if (tb[CTRL_ATTR_HDRSIZE]) {
+ __u32 *h = RTA_DATA(tb[CTRL_ATTR_HDRSIZE]);
+ fprintf(fp, " header size: %d ",*h);
+ }
+ if (tb[CTRL_ATTR_MAXATTR]) {
+ __u32 *ma = RTA_DATA(tb[CTRL_ATTR_MAXATTR]);
+ fprintf(fp, " max attribs: %d ",*ma);
+ }
+ /* end of family definitions .. */
+ fprintf(fp,"\n");
+ if (tb[CTRL_ATTR_OPS]) {
+ struct rtattr *tb2[GENL_MAX_FAM_OPS];
+ int i=0;
+ parse_rtattr_nested(tb2, GENL_MAX_FAM_OPS, tb[CTRL_ATTR_OPS]);
+ fprintf(fp, "\tcommands supported: \n");
+ for (i = 0; i < GENL_MAX_FAM_OPS; i++) {
+ if (tb2[i]) {
+ fprintf(fp, "\t\t#%d: ", i);
+ if (0 > print_ctrl_cmds(fp, tb2[i], ctrl_v)) {
+ fprintf(fp, "Error printing command\n");
+ }
+ /* for next command */
+ fprintf(fp,"\n");
+ }
+ }
+
+ /* end of family::cmds definitions .. */
+ fprintf(fp,"\n");
+ }
+
+ if (tb[CTRL_ATTR_MCAST_GROUPS]) {
+ struct rtattr *tb2[GENL_MAX_FAM_GRPS + 1];
+ int i;
+
+ parse_rtattr_nested(tb2, GENL_MAX_FAM_GRPS,
+ tb[CTRL_ATTR_MCAST_GROUPS]);
+ fprintf(fp, "\tmulticast groups:\n");
+
+ for (i = 0; i < GENL_MAX_FAM_GRPS; i++) {
+ if (tb2[i]) {
+ fprintf(fp, "\t\t#%d: ", i);
+ if (0 > print_ctrl_grp(fp, tb2[i], ctrl_v))
+ fprintf(fp, "Error printing group\n");
+ /* for next group */
+ fprintf(fp,"\n");
+ }
+ }
+
+ /* end of family::groups definitions .. */
+ fprintf(fp,"\n");
+ }
+
+ fflush(fp);
+ return 0;
+}
+
+static int print_ctrl2(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg)
+{
+ return print_ctrl(who, NULL, n, arg);
+}
+
+static int ctrl_list(int cmd, int argc, char **argv)
+{
+ struct rtnl_handle rth;
+ struct nlmsghdr *nlh;
+ struct genlmsghdr *ghdr;
+ int ret = -1;
+ char d[GENL_NAMSIZ];
+ struct {
+ struct nlmsghdr n;
+ char buf[4096];
+ } req;
+
+ memset(&req, 0, sizeof(req));
+
+ nlh = &req.n;
+ nlh->nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN);
+ nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+ nlh->nlmsg_type = GENL_ID_CTRL;
+
+ ghdr = NLMSG_DATA(&req.n);
+ ghdr->cmd = CTRL_CMD_GETFAMILY;
+
+ if (rtnl_open_byproto(&rth, 0, NETLINK_GENERIC) < 0) {
+ fprintf(stderr, "Cannot open generic netlink socket\n");
+ exit(1);
+ }
+
+ if (cmd == CTRL_CMD_GETFAMILY) {
+ if (argc != 2) {
+ fprintf(stderr, "Wrong number of params\n");
+ return -1;
+ }
+
+ if (matches(*argv, "name") == 0) {
+ NEXT_ARG();
+ strncpy(d, *argv, sizeof (d) - 1);
+ addattr_l(nlh, 128, CTRL_ATTR_FAMILY_NAME,
+ d, strlen(d) + 1);
+ } else if (matches(*argv, "id") == 0) {
+ __u16 id;
+ NEXT_ARG();
+ if (get_u16(&id, *argv, 0)) {
+ fprintf(stderr, "Illegal \"id\"\n");
+ goto ctrl_done;
+ }
+
+ addattr_l(nlh, 128, CTRL_ATTR_FAMILY_ID, &id, 2);
+
+ } else {
+ fprintf(stderr, "Wrong params\n");
+ goto ctrl_done;
+ }
+
+ if (rtnl_talk(&rth, nlh, nlh, sizeof(req)) < 0) {
+ fprintf(stderr, "Error talking to the kernel\n");
+ goto ctrl_done;
+ }
+
+ if (print_ctrl2(NULL, nlh, (void *) stdout) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ goto ctrl_done;
+ }
+
+ }
+
+ if (cmd == CTRL_CMD_UNSPEC) {
+ nlh->nlmsg_flags = NLM_F_ROOT|NLM_F_MATCH|NLM_F_REQUEST;
+ nlh->nlmsg_seq = rth.dump = ++rth.seq;
+
+ if (rtnl_send(&rth, nlh, nlh->nlmsg_len) < 0) {
+ perror("Failed to send dump request\n");
+ goto ctrl_done;
+ }
+
+ rtnl_dump_filter(&rth, print_ctrl2, stdout);
+
+ }
+
+ ret = 0;
+ctrl_done:
+ rtnl_close(&rth);
+ return ret;
+}
+
+static int ctrl_listen(int argc, char **argv)
+{
+ struct rtnl_handle rth;
+
+ if (rtnl_open_byproto(&rth, nl_mgrp(GENL_ID_CTRL), NETLINK_GENERIC) < 0) {
+ fprintf(stderr, "Canot open generic netlink socket\n");
+ return -1;
+ }
+
+ if (rtnl_listen(&rth, print_ctrl, (void *) stdout) < 0)
+ return -1;
+
+ return 0;
+}
+
+static int parse_ctrl(struct genl_util *a, int argc, char **argv)
+{
+ argv++;
+ if (--argc <= 0) {
+ fprintf(stderr, "wrong controller params\n");
+ return -1;
+ }
+
+ if (matches(*argv, "monitor") == 0)
+ return ctrl_listen(argc-1, argv+1);
+ if (matches(*argv, "get") == 0)
+ return ctrl_list(CTRL_CMD_GETFAMILY, argc-1, argv+1);
+ if (matches(*argv, "list") == 0 ||
+ matches(*argv, "show") == 0 ||
+ matches(*argv, "lst") == 0)
+ return ctrl_list(CTRL_CMD_UNSPEC, argc-1, argv+1);
+ if (matches(*argv, "help") == 0)
+ return usage();
+
+ fprintf(stderr, "ctrl command \"%s\" is unknown, try \"ctrl help\".\n",
+ *argv);
+
+ return -1;
+}
+
+struct genl_util ctrl_genl_util = {
+ .name = "ctrl",
+ .parse_genlopt = parse_ctrl,
+ .print_genlopt = print_ctrl2,
+};
diff --git a/iproute2/genl/genl.c b/iproute2/genl/genl.c
new file mode 100644
index 0000000..e33fafd
--- /dev/null
+++ b/iproute2/genl/genl.c
@@ -0,0 +1,149 @@
+/*
+ * genl.c "genl" utility frontend.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Jamal Hadi Salim
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <dlfcn.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <errno.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h> /* until we put our own header */
+#include "SNAPSHOT.h"
+#include "utils.h"
+#include "genl_utils.h"
+
+int show_stats = 0;
+int show_details = 0;
+int show_raw = 0;
+int resolve_hosts = 0;
+
+static void *BODY;
+static struct genl_util * genl_list;
+
+
+static int print_nofopt(const struct sockaddr_nl *who, struct nlmsghdr *n,
+ void *arg)
+{
+ fprintf((FILE *) arg, "unknown genl type ..\n");
+ return 0;
+}
+
+static int parse_nofopt(struct genl_util *f, int argc, char **argv)
+{
+ if (argc) {
+ fprintf(stderr, "Unknown genl \"%s\", hence option \"%s\" "
+ "is unparsable\n", f->name, *argv);
+ return -1;
+ }
+
+ return 0;
+}
+
+static struct genl_util *get_genl_kind(const char *str)
+{
+ void *dlh;
+ char buf[256];
+ struct genl_util *f;
+
+ for (f = genl_list; f; f = f->next)
+ if (strcmp(f->name, str) == 0)
+ return f;
+
+ snprintf(buf, sizeof(buf), "%s.so", str);
+ dlh = dlopen(buf, RTLD_LAZY);
+ if (dlh == NULL) {
+ dlh = BODY;
+ if (dlh == NULL) {
+ dlh = BODY = dlopen(NULL, RTLD_LAZY);
+ if (dlh == NULL)
+ goto noexist;
+ }
+ }
+
+ snprintf(buf, sizeof(buf), "%s_genl_util", str);
+
+ f = dlsym(dlh, buf);
+ if (f == NULL)
+ goto noexist;
+reg:
+ f->next = genl_list;
+ genl_list = f;
+ return f;
+
+noexist:
+ f = malloc(sizeof(*f));
+ if (f) {
+ memset(f, 0, sizeof(*f));
+ strncpy(f->name, str, 15);
+ f->parse_genlopt = parse_nofopt;
+ f->print_genlopt = print_nofopt;
+ goto reg;
+ }
+ return f;
+}
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: genl [ OPTIONS ] OBJECT | help }\n"
+ "where OBJECT := { ctrl etc }\n"
+ " OPTIONS := { -s[tatistics] | -d[etails] | -r[aw] }\n");
+ exit(-1);
+}
+
+int main(int argc, char **argv)
+{
+ while (argc > 1) {
+ if (argv[1][0] != '-')
+ break;
+ if (matches(argv[1], "-stats") == 0 ||
+ matches(argv[1], "-statistics") == 0) {
+ ++show_stats;
+ } else if (matches(argv[1], "-details") == 0) {
+ ++show_details;
+ } else if (matches(argv[1], "-raw") == 0) {
+ ++show_raw;
+ } else if (matches(argv[1], "-Version") == 0) {
+ printf("genl utility, iproute2-ss%s\n", SNAPSHOT);
+ exit(0);
+ } else if (matches(argv[1], "-help") == 0) {
+ usage();
+ } else {
+ fprintf(stderr, "Option \"%s\" is unknown, try "
+ "\"genl -help\".\n", argv[1]);
+ exit(-1);
+ }
+ argc--; argv++;
+ }
+
+ if (argc > 1) {
+ int ret;
+ struct genl_util *a = NULL;
+ a = get_genl_kind(argv[1]);
+ if (!a) {
+ fprintf(stderr,"bad genl %s\n", argv[1]);
+ exit(-1);
+ }
+
+ ret = a->parse_genlopt(a, argc-1, argv+1);
+ return ret;
+ }
+
+ usage();
+}
diff --git a/iproute2/genl/genl_utils.h b/iproute2/genl/genl_utils.h
new file mode 100644
index 0000000..85b5183
--- /dev/null
+++ b/iproute2/genl/genl_utils.h
@@ -0,0 +1,17 @@
+#ifndef _TC_UTIL_H_
+#define _TC_UTIL_H_ 1
+
+#include "utils.h"
+#include "linux/genetlink.h"
+
+struct genl_util
+{
+ struct genl_util *next;
+ char name[16];
+ int (*parse_genlopt)(struct genl_util *fu, int argc, char **argv);
+ int (*print_genlopt)(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg);
+};
+
+extern int genl_ctrl_resolve_family(const char *family);
+
+#endif
diff --git a/iproute2/genl/static-syms.c b/iproute2/genl/static-syms.c
new file mode 100644
index 0000000..0bc8074
--- /dev/null
+++ b/iproute2/genl/static-syms.c
@@ -0,0 +1,14 @@
+/*
+ * This file creates a dummy version of dynamic loading
+ * for environments where dynamic linking
+ * is not used or available.
+ */
+
+#include <string.h>
+#include "dlfcn.h"
+
+void *_dlsym(const char *sym)
+{
+#include "static-syms.h"
+ return NULL;
+}
diff --git a/iproute2/include/SNAPSHOT.h b/iproute2/include/SNAPSHOT.h
new file mode 100644
index 0000000..58d3632
--- /dev/null
+++ b/iproute2/include/SNAPSHOT.h
@@ -0,0 +1 @@
+static const char SNAPSHOT[] = "160111";
diff --git a/iproute2/include/bpf_api.h b/iproute2/include/bpf_api.h
new file mode 100644
index 0000000..0666a31
--- /dev/null
+++ b/iproute2/include/bpf_api.h
@@ -0,0 +1,225 @@
+#ifndef __BPF_API__
+#define __BPF_API__
+
+/* Note:
+ *
+ * This file can be included into eBPF kernel programs. It contains
+ * a couple of useful helper functions, map/section ABI (bpf_elf.h),
+ * misc macros and some eBPF specific LLVM built-ins.
+ */
+
+#include <stdint.h>
+
+#include <linux/pkt_cls.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
+
+#include <asm/byteorder.h>
+
+#include "bpf_elf.h"
+
+/** Misc macros. */
+
+#ifndef __stringify
+# define __stringify(X) #X
+#endif
+
+#ifndef __maybe_unused
+# define __maybe_unused __attribute__((__unused__))
+#endif
+
+#ifndef offsetof
+# define offsetof(TYPE, MEMBER) __builtin_offsetof(TYPE, MEMBER)
+#endif
+
+#ifndef likely
+# define likely(X) __builtin_expect(!!(X), 1)
+#endif
+
+#ifndef unlikely
+# define unlikely(X) __builtin_expect(!!(X), 0)
+#endif
+
+#ifndef htons
+# define htons(X) __constant_htons((X))
+#endif
+
+#ifndef ntohs
+# define ntohs(X) __constant_ntohs((X))
+#endif
+
+#ifndef htonl
+# define htonl(X) __constant_htonl((X))
+#endif
+
+#ifndef ntohl
+# define ntohl(X) __constant_ntohl((X))
+#endif
+
+/** Section helper macros. */
+
+#ifndef __section
+# define __section(NAME) \
+ __attribute__((section(NAME), used))
+#endif
+
+#ifndef __section_tail
+# define __section_tail(ID, KEY) \
+ __section(__stringify(ID) "/" __stringify(KEY))
+#endif
+
+#ifndef __section_cls_entry
+# define __section_cls_entry \
+ __section(ELF_SECTION_CLASSIFIER)
+#endif
+
+#ifndef __section_act_entry
+# define __section_act_entry \
+ __section(ELF_SECTION_ACTION)
+#endif
+
+#ifndef __section_license
+# define __section_license \
+ __section(ELF_SECTION_LICENSE)
+#endif
+
+#ifndef __section_maps
+# define __section_maps \
+ __section(ELF_SECTION_MAPS)
+#endif
+
+/** Declaration helper macros. */
+
+#ifndef BPF_LICENSE
+# define BPF_LICENSE(NAME) \
+ char ____license[] __section_license = NAME
+#endif
+
+#ifndef __BPF_MAP
+# define __BPF_MAP(NAME, TYPE, ID, SIZE_KEY, SIZE_VALUE, PIN, MAX_ELEM) \
+ struct bpf_elf_map __section_maps NAME = { \
+ .type = (TYPE), \
+ .id = (ID), \
+ .size_key = (SIZE_KEY), \
+ .size_value = (SIZE_VALUE), \
+ .pinning = (PIN), \
+ .max_elem = (MAX_ELEM), \
+ }
+#endif
+
+#ifndef BPF_HASH
+# define BPF_HASH(NAME, ID, SIZE_KEY, SIZE_VALUE, PIN, MAX_ELEM) \
+ __BPF_MAP(NAME, BPF_MAP_TYPE_HASH, ID, SIZE_KEY, SIZE_VALUE, \
+ PIN, MAX_ELEM)
+#endif
+
+#ifndef BPF_ARRAY
+# define BPF_ARRAY(NAME, ID, SIZE_VALUE, PIN, MAX_ELEM) \
+ __BPF_MAP(NAME, BPF_MAP_TYPE_ARRAY, ID, sizeof(uint32_t), \
+ SIZE_VALUE, PIN, MAX_ELEM)
+#endif
+
+#ifndef BPF_ARRAY2
+# define BPF_ARRAY2(NAME, ID, PIN, MAX_ELEM) \
+ BPF_ARRAY(NAME, ID, sizeof(uint16_t), PIN, MAX_ELEM)
+#endif
+
+#ifndef BPF_ARRAY4
+# define BPF_ARRAY4(NAME, ID, PIN, MAX_ELEM) \
+ BPF_ARRAY(NAME, ID, sizeof(uint32_t), PIN, MAX_ELEM)
+#endif
+
+#ifndef BPF_ARRAY8
+# define BPF_ARRAY8(NAME, ID, PIN, MAX_ELEM) \
+ BPF_ARRAY(NAME, ID, sizeof(uint64_t), PIN, MAX_ELEM)
+#endif
+
+#ifndef BPF_PROG_ARRAY
+# define BPF_PROG_ARRAY(NAME, ID, PIN, MAX_ELEM) \
+ __BPF_MAP(NAME, BPF_MAP_TYPE_PROG_ARRAY, ID, sizeof(uint32_t), \
+ sizeof(uint32_t), PIN, MAX_ELEM)
+#endif
+
+/** Classifier helper */
+
+#ifndef BPF_H_DEFAULT
+# define BPF_H_DEFAULT -1
+#endif
+
+/** BPF helper functions for tc. */
+
+#ifndef BPF_FUNC
+# define BPF_FUNC(NAME, ...) \
+ (* NAME)(__VA_ARGS__) __maybe_unused = (void *) BPF_FUNC_##NAME
+#endif
+
+/* Map access/manipulation */
+static void *BPF_FUNC(map_lookup_elem, void *map, const void *key);
+static int BPF_FUNC(map_update_elem, void *map, const void *key,
+ const void *value, uint32_t flags);
+static int BPF_FUNC(map_delete_elem, void *map, const void *key);
+
+/* Time access */
+static uint64_t BPF_FUNC(ktime_get_ns);
+
+/* Debugging */
+static void BPF_FUNC(trace_printk, const char *fmt, int fmt_size, ...);
+
+/* Random numbers */
+static uint32_t BPF_FUNC(get_prandom_u32);
+
+/* Tail calls */
+static void BPF_FUNC(tail_call, struct __sk_buff *skb, void *map,
+ uint32_t index);
+
+/* System helpers */
+static uint32_t BPF_FUNC(get_smp_processor_id);
+
+/* Packet misc meta data */
+static uint32_t BPF_FUNC(get_cgroup_classid, struct __sk_buff *skb);
+static uint32_t BPF_FUNC(get_route_realm, struct __sk_buff *skb);
+
+/* Packet redirection */
+static int BPF_FUNC(redirect, int ifindex, uint32_t flags);
+static int BPF_FUNC(clone_redirect, struct __sk_buff *skb, int ifindex,
+ uint32_t flags);
+
+/* Packet manipulation */
+#define BPF_PSEUDO_HDR 0x10
+#define BPF_HAS_PSEUDO_HDR(flags) ((flags) & BPF_PSEUDO_HDR)
+#define BPF_HDR_FIELD_SIZE(flags) ((flags) & 0x0f)
+
+static int BPF_FUNC(skb_store_bytes, struct __sk_buff *skb, uint32_t off,
+ void *from, uint32_t len, uint32_t flags);
+static int BPF_FUNC(l3_csum_replace, struct __sk_buff *skb, uint32_t off,
+ uint32_t from, uint32_t to, uint32_t flags);
+static int BPF_FUNC(l4_csum_replace, struct __sk_buff *skb, uint32_t off,
+ uint32_t from, uint32_t to, uint32_t flags);
+
+/* Packet vlan encap/decap */
+static int BPF_FUNC(skb_vlan_push, struct __sk_buff *skb, uint16_t proto,
+ uint16_t vlan_tci);
+static int BPF_FUNC(skb_vlan_pop, struct __sk_buff *skb);
+
+/* Packet tunnel encap/decap */
+static int BPF_FUNC(skb_get_tunnel_key, struct __sk_buff *skb,
+ struct bpf_tunnel_key *to, uint32_t size, uint32_t flags);
+static int BPF_FUNC(skb_set_tunnel_key, struct __sk_buff *skb,
+ struct bpf_tunnel_key *from, uint32_t size, uint32_t flags);
+
+/** LLVM built-ins */
+
+#ifndef lock_xadd
+# define lock_xadd(ptr, val) ((void) __sync_fetch_and_add(ptr, val))
+#endif
+
+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 /* __BPF_API__ */
diff --git a/iproute2/include/bpf_elf.h b/iproute2/include/bpf_elf.h
new file mode 100644
index 0000000..31a8974
--- /dev/null
+++ b/iproute2/include/bpf_elf.h
@@ -0,0 +1,39 @@
+#ifndef __BPF_ELF__
+#define __BPF_ELF__
+
+#include <asm/types.h>
+
+/* Note:
+ *
+ * Below ELF section names and bpf_elf_map structure definition
+ * are not (!) kernel ABI. It's rather a "contract" between the
+ * application and the BPF loader in tc. For compatibility, the
+ * section names should stay as-is. Introduction of aliases, if
+ * needed, are a possibility, though.
+ */
+
+/* ELF section names, etc */
+#define ELF_SECTION_LICENSE "license"
+#define ELF_SECTION_MAPS "maps"
+#define ELF_SECTION_CLASSIFIER "classifier"
+#define ELF_SECTION_ACTION "action"
+
+#define ELF_MAX_MAPS 64
+#define ELF_MAX_LICENSE_LEN 128
+
+/* Object pinning settings */
+#define PIN_NONE 0
+#define PIN_OBJECT_NS 1
+#define PIN_GLOBAL_NS 2
+
+/* ELF map definition */
+struct bpf_elf_map {
+ __u32 type;
+ __u32 size_key;
+ __u32 size_value;
+ __u32 max_elem;
+ __u32 id;
+ __u32 pinning;
+};
+
+#endif /* __BPF_ELF__ */
diff --git a/iproute2/include/bpf_scm.h b/iproute2/include/bpf_scm.h
new file mode 100644
index 0000000..35117d1
--- /dev/null
+++ b/iproute2/include/bpf_scm.h
@@ -0,0 +1,75 @@
+#ifndef __BPF_SCM__
+#define __BPF_SCM__
+
+#include <sys/types.h>
+#include <sys/socket.h>
+
+#include "utils.h"
+#include "bpf_elf.h"
+
+#define BPF_SCM_AUX_VER 1
+#define BPF_SCM_MAX_FDS ELF_MAX_MAPS
+#define BPF_SCM_MSG_SIZE 1024
+
+struct bpf_elf_st {
+ dev_t st_dev;
+ ino_t st_ino;
+};
+
+struct bpf_map_aux {
+ unsigned short uds_ver;
+ unsigned short num_ent;
+ char obj_name[64];
+ struct bpf_elf_st obj_st;
+ struct bpf_elf_map ent[BPF_SCM_MAX_FDS];
+};
+
+struct bpf_map_set_msg {
+ struct msghdr hdr;
+ struct iovec iov;
+ char msg_buf[BPF_SCM_MSG_SIZE];
+ struct bpf_map_aux aux;
+};
+
+static inline int *bpf_map_set_init(struct bpf_map_set_msg *msg,
+ struct sockaddr_un *addr,
+ unsigned int addr_len)
+{
+ const unsigned int cmsg_ctl_len = sizeof(int) * BPF_SCM_MAX_FDS;
+ struct cmsghdr *cmsg;
+
+ msg->iov.iov_base = &msg->aux;
+ msg->iov.iov_len = sizeof(msg->aux);
+
+ msg->hdr.msg_iov = &msg->iov;
+ msg->hdr.msg_iovlen = 1;
+
+ msg->hdr.msg_name = (struct sockaddr *)addr;
+ msg->hdr.msg_namelen = addr_len;
+
+ BUILD_BUG_ON(sizeof(msg->msg_buf) < cmsg_ctl_len);
+ msg->hdr.msg_control = &msg->msg_buf;
+ msg->hdr.msg_controllen = cmsg_ctl_len;
+
+ cmsg = CMSG_FIRSTHDR(&msg->hdr);
+ cmsg->cmsg_len = msg->hdr.msg_controllen;
+ cmsg->cmsg_level = SOL_SOCKET;
+ cmsg->cmsg_type = SCM_RIGHTS;
+
+ return (int *)CMSG_DATA(cmsg);
+}
+
+static inline void bpf_map_set_init_single(struct bpf_map_set_msg *msg,
+ int num)
+{
+ struct cmsghdr *cmsg;
+
+ msg->hdr.msg_controllen = CMSG_LEN(sizeof(int) * num);
+ msg->iov.iov_len = offsetof(struct bpf_map_aux, ent) +
+ sizeof(struct bpf_elf_map) * num;
+
+ cmsg = CMSG_FIRSTHDR(&msg->hdr);
+ cmsg->cmsg_len = msg->hdr.msg_controllen;
+}
+
+#endif /* __BPF_SCM__ */
diff --git a/iproute2/include/color.h b/iproute2/include/color.h
new file mode 100644
index 0000000..b85003a
--- /dev/null
+++ b/iproute2/include/color.h
@@ -0,0 +1,16 @@
+#ifndef __COLOR_H__
+#define __COLOR_H__ 1
+
+enum color_attr {
+ COLOR_IFNAME,
+ COLOR_MAC,
+ COLOR_INET,
+ COLOR_INET6,
+ COLOR_OPERSTATE_UP,
+ COLOR_OPERSTATE_DOWN
+};
+
+void enable_color(void);
+int color_fprintf(FILE *fp, enum color_attr attr, const char *fmt, ...);
+
+#endif
diff --git a/iproute2/include/dlfcn.h b/iproute2/include/dlfcn.h
new file mode 100644
index 0000000..f15bc2c
--- /dev/null
+++ b/iproute2/include/dlfcn.h
@@ -0,0 +1,40 @@
+/*
+ * Stub dlfcn implementation for systems that lack shared library support
+ * but obviously can still reference compiled-in symbols.
+ */
+
+#ifndef NO_SHARED_LIBS
+#include_next <dlfcn.h>
+#else
+
+#define RTLD_LAZY 0
+#define RTLD_GLOBAL 1
+#define _FAKE_DLFCN_HDL (void *)0xbeefcafe
+
+static inline void *dlopen(const char *file, int flag)
+{
+ if (file == NULL)
+ return _FAKE_DLFCN_HDL;
+ else
+ return NULL;
+}
+
+void *_dlsym(const char *sym);
+static inline void *dlsym(void *handle, const char *sym)
+{
+ if (handle != _FAKE_DLFCN_HDL)
+ return NULL;
+ return _dlsym(sym);
+}
+
+static inline char *dlerror(void)
+{
+ return NULL;
+}
+
+static inline int dlclose(void *handle)
+{
+ return (handle == _FAKE_DLFCN_HDL) ? 0 : 1;
+}
+
+#endif
diff --git a/iproute2/include/hlist.h b/iproute2/include/hlist.h
new file mode 100644
index 0000000..4e8de9e
--- /dev/null
+++ b/iproute2/include/hlist.h
@@ -0,0 +1,56 @@
+#ifndef __HLIST_H__
+#define __HLIST_H__ 1
+/* Hash list stuff from kernel */
+
+#include <stddef.h>
+
+#define container_of(ptr, type, member) ({ \
+ const typeof( ((type *)0)->member ) *__mptr = (ptr); \
+ (type *)( (char *)__mptr - offsetof(type,member) );})
+
+struct hlist_head {
+ struct hlist_node *first;
+};
+
+struct hlist_node {
+ struct hlist_node *next, **pprev;
+};
+
+static inline void hlist_del(struct hlist_node *n)
+{
+ struct hlist_node *next = n->next;
+ struct hlist_node **pprev = n->pprev;
+ *pprev = next;
+ if (next)
+ next->pprev = pprev;
+}
+
+static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h)
+{
+ struct hlist_node *first = h->first;
+ n->next = first;
+ if (first)
+ first->pprev = &n->next;
+ h->first = n;
+ n->pprev = &h->first;
+}
+
+#define hlist_for_each(pos, head) \
+ for (pos = (head)->first; pos ; pos = pos->next)
+
+
+#define hlist_for_each_safe(pos, n, head) \
+ for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \
+ pos = n)
+
+#define hlist_entry_safe(ptr, type, member) \
+ ({ typeof(ptr) ____ptr = (ptr); \
+ ____ptr ? hlist_entry(____ptr, type, member) : NULL; \
+ })
+
+#define hlist_for_each_entry(pos, head, member) \
+ for (pos = hlist_entry_safe((head)->first, typeof(*(pos)), member);\
+ pos; \
+ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member))
+
+#endif /* __HLIST_H__ */
diff --git a/iproute2/include/ip6tables.h b/iproute2/include/ip6tables.h
new file mode 100644
index 0000000..5f1c5b6
--- /dev/null
+++ b/iproute2/include/ip6tables.h
@@ -0,0 +1,20 @@
+#ifndef _IP6TABLES_USER_H
+#define _IP6TABLES_USER_H
+
+#include <netinet/ip.h>
+#include <xtables.h>
+#include <libiptc/libip6tc.h>
+#include <iptables/internal.h>
+
+/* Your shared library should call one of these. */
+extern int do_command6(int argc, char *argv[], char **table,
+ struct xtc_handle **handle, bool restore);
+
+extern int for_each_chain6(int (*fn)(const xt_chainlabel, int, struct xtc_handle *), int verbose, int builtinstoo, struct xtc_handle *handle);
+extern int flush_entries6(const xt_chainlabel chain, int verbose, struct xtc_handle *handle);
+extern int delete_chain6(const xt_chainlabel chain, int verbose, struct xtc_handle *handle);
+void print_rule6(const struct ip6t_entry *e, struct xtc_handle *h, const char *chain, int counters);
+
+extern struct xtables_globals ip6tables_globals;
+
+#endif /*_IP6TABLES_USER_H*/
diff --git a/iproute2/include/iptables.h b/iproute2/include/iptables.h
new file mode 100644
index 0000000..78c10ab
--- /dev/null
+++ b/iproute2/include/iptables.h
@@ -0,0 +1,25 @@
+#ifndef _IPTABLES_USER_H
+#define _IPTABLES_USER_H
+
+#include <netinet/ip.h>
+#include <xtables.h>
+#include <libiptc/libiptc.h>
+#include <iptables/internal.h>
+
+/* Your shared library should call one of these. */
+extern int do_command4(int argc, char *argv[], char **table,
+ struct xtc_handle **handle, bool restore);
+extern int delete_chain4(const xt_chainlabel chain, int verbose,
+ struct xtc_handle *handle);
+extern int flush_entries4(const xt_chainlabel chain, int verbose,
+ struct xtc_handle *handle);
+extern int for_each_chain4(int (*fn)(const xt_chainlabel, int, struct xtc_handle *),
+ int verbose, int builtinstoo, struct xtc_handle *handle);
+extern void print_rule4(const struct ipt_entry *e,
+ struct xtc_handle *handle, const char *chain, int counters);
+
+extern struct xtables_globals iptables_globals;
+
+extern struct xtables_globals xtables_globals;
+
+#endif /*_IPTABLES_USER_H*/
diff --git a/iproute2/include/iptables/internal.h b/iproute2/include/iptables/internal.h
new file mode 100644
index 0000000..62a8ecb
--- /dev/null
+++ b/iproute2/include/iptables/internal.h
@@ -0,0 +1,13 @@
+#ifndef IPTABLES_INTERNAL_H
+#define IPTABLES_INTERNAL_H 1
+
+#define IPTABLES_VERSION "1.6.0"
+
+/**
+ * Program's own name and version.
+ */
+extern const char *program_name, *program_version;
+
+extern int line;
+
+#endif /* IPTABLES_INTERNAL_H */
diff --git a/iproute2/include/iptables_common.h b/iproute2/include/iptables_common.h
new file mode 100644
index 0000000..9099667
--- /dev/null
+++ b/iproute2/include/iptables_common.h
@@ -0,0 +1,51 @@
+#ifndef _IPTABLES_COMMON_H
+#define _IPTABLES_COMMON_H
+/* Shared definitions between ipv4 and ipv6. */
+
+enum exittype {
+ OTHER_PROBLEM = 1,
+ PARAMETER_PROBLEM,
+ VERSION_PROBLEM,
+ RESOURCE_PROBLEM
+};
+
+/* this is a special 64bit data type that is 8-byte aligned */
+#define aligned_u64 unsigned long long __attribute__((aligned(8)))
+
+extern void exit_printhelp(void) __attribute__((noreturn));
+extern void exit_tryhelp(int) __attribute__((noreturn));
+int check_inverse(const char option[], int *invert, int *optind, int argc);
+extern int string_to_number(const char *,
+ unsigned int,
+ unsigned int,
+ unsigned int *);
+extern int string_to_number_l(const char *,
+ unsigned long int,
+ unsigned long int,
+ unsigned long *);
+extern int string_to_number_ll(const char *,
+ unsigned long long int,
+ unsigned long long int,
+ unsigned long long *);
+extern int iptables_insmod(const char *modname, const char *modprobe);
+extern int load_iptables_ko(const char *modprobe);
+void exit_error(enum exittype, char *, ...)__attribute__((noreturn,
+ format(printf,2,3)));
+extern const char *program_name, *program_version;
+extern char *lib_dir;
+
+#define _init __attribute__((constructor)) my_init
+#ifdef NO_SHARED_LIBS
+# ifdef _INIT
+# undef _init
+# define _init _INIT
+# endif
+ extern void init_extensions(void);
+#endif
+
+#define __be32 u_int32_t
+#define __le32 u_int32_t
+#define __be16 u_int16_t
+#define __le16 u_int16_t
+
+#endif /*_IPTABLES_COMMON_H*/
diff --git a/iproute2/include/json_writer.h b/iproute2/include/json_writer.h
new file mode 100644
index 0000000..ab9a008
--- /dev/null
+++ b/iproute2/include/json_writer.h
@@ -0,0 +1,61 @@
+/*
+ * Simple streaming JSON writer
+ *
+ * This takes care of the annoying bits of JSON syntax like the commas
+ * after elements
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Stephen Hemminger <stephen@networkplumber.org>
+ */
+
+#ifndef _JSON_WRITER_H_
+#define _JSON_WRITER_H_
+
+#include <stdbool.h>
+#include <stdint.h>
+
+/* Opaque class structure */
+typedef struct json_writer json_writer_t;
+
+/* Create a new JSON stream */
+json_writer_t *jsonw_new(FILE *f);
+/* End output to JSON stream */
+void jsonw_destroy(json_writer_t **self_p);
+
+/* Cause output to have pretty whitespace */
+void jsonw_pretty(json_writer_t *self, bool on);
+
+/* Add property name */
+void jsonw_name(json_writer_t *self, const char *name);
+
+/* Add value */
+void jsonw_string(json_writer_t *self, const char *value);
+void jsonw_bool(json_writer_t *self, bool value);
+void jsonw_float(json_writer_t *self, double number);
+void jsonw_uint(json_writer_t *self, uint64_t number);
+void jsonw_int(json_writer_t *self, int64_t number);
+void jsonw_null(json_writer_t *self);
+
+/* Useful Combinations of name and value */
+void jsonw_string_field(json_writer_t *self, const char *prop, const char *val);
+void jsonw_bool_field(json_writer_t *self, const char *prop, bool value);
+void jsonw_float_field(json_writer_t *self, const char *prop, double num);
+void jsonw_uint_field(json_writer_t *self, const char *prop, uint64_t num);
+void jsonw_int_field(json_writer_t *self, const char *prop, int64_t num);
+void jsonw_null_field(json_writer_t *self, const char *prop);
+
+/* Collections */
+void jsonw_start_object(json_writer_t *self);
+void jsonw_end_object(json_writer_t *self);
+
+void jsonw_start_array(json_writer_t *self);
+void jsonw_end_array(json_writer_t *self);
+
+/* Override default exception handling */
+typedef void (jsonw_err_handler_fn)(const char *);
+
+#endif /* _JSON_WRITER_H_ */
diff --git a/iproute2/include/libgenl.h b/iproute2/include/libgenl.h
new file mode 100644
index 0000000..9db4baf
--- /dev/null
+++ b/iproute2/include/libgenl.h
@@ -0,0 +1,25 @@
+#ifndef __LIBGENL_H__
+#define __LIBGENL_H__
+
+#include "libnetlink.h"
+
+#define GENL_REQUEST(_req, _bufsiz, _family, _hdrsiz, _ver, _cmd, _flags) \
+struct { \
+ struct nlmsghdr n; \
+ struct genlmsghdr g; \
+ char buf[NLMSG_ALIGN(_hdrsiz) + (_bufsiz)]; \
+} _req = { \
+ .n = { \
+ .nlmsg_type = (_family), \
+ .nlmsg_flags = (_flags), \
+ .nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN + (_hdrsiz)), \
+ }, \
+ .g = { \
+ .cmd = (_cmd), \
+ .version = (_ver), \
+ }, \
+}
+
+extern int genl_resolve_family(struct rtnl_handle *grth, const char *family);
+
+#endif /* __LIBGENL_H__ */
diff --git a/iproute2/include/libiptc/ipt_kernel_headers.h b/iproute2/include/libiptc/ipt_kernel_headers.h
new file mode 100644
index 0000000..a5963e9
--- /dev/null
+++ b/iproute2/include/libiptc/ipt_kernel_headers.h
@@ -0,0 +1,15 @@
+/* This is the userspace/kernel interface for Generic IP Chains,
+ required for libc6. */
+#ifndef _FWCHAINS_KERNEL_HEADERS_H
+#define _FWCHAINS_KERNEL_HEADERS_H
+
+#include <limits.h>
+
+#include <netinet/ip.h>
+#include <netinet/in.h>
+#include <netinet/ip_icmp.h>
+#include <netinet/tcp.h>
+#include <netinet/udp.h>
+#include <net/if.h>
+#include <sys/types.h>
+#endif
diff --git a/iproute2/include/libiptc/libip6tc.h b/iproute2/include/libiptc/libip6tc.h
new file mode 100644
index 0000000..9aed80a
--- /dev/null
+++ b/iproute2/include/libiptc/libip6tc.h
@@ -0,0 +1,161 @@
+#ifndef _LIBIP6TC_H
+#define _LIBIP6TC_H
+/* Library which manipulates firewall rules. Version 0.2. */
+
+#include <linux/types.h>
+#include <libiptc/ipt_kernel_headers.h>
+#ifdef __cplusplus
+# include <climits>
+#else
+# include <limits.h> /* INT_MAX in ip6_tables.h */
+#endif
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <libiptc/xtcshared.h>
+
+#define ip6tc_handle xtc_handle
+#define ip6t_chainlabel xt_chainlabel
+
+#define IP6TC_LABEL_ACCEPT "ACCEPT"
+#define IP6TC_LABEL_DROP "DROP"
+#define IP6TC_LABEL_QUEUE "QUEUE"
+#define IP6TC_LABEL_RETURN "RETURN"
+
+/* Does this chain exist? */
+int ip6tc_is_chain(const char *chain, struct xtc_handle *const handle);
+
+/* Take a snapshot of the rules. Returns NULL on error. */
+struct xtc_handle *ip6tc_init(const char *tablename);
+
+/* Cleanup after ip6tc_init(). */
+void ip6tc_free(struct xtc_handle *h);
+
+/* Iterator functions to run through the chains. Returns NULL at end. */
+const char *ip6tc_first_chain(struct xtc_handle *handle);
+const char *ip6tc_next_chain(struct xtc_handle *handle);
+
+/* Get first rule in the given chain: NULL for empty chain. */
+const struct ip6t_entry *ip6tc_first_rule(const char *chain,
+ struct xtc_handle *handle);
+
+/* Returns NULL when rules run out. */
+const struct ip6t_entry *ip6tc_next_rule(const struct ip6t_entry *prev,
+ struct xtc_handle *handle);
+
+/* Returns a pointer to the target name of this position. */
+const char *ip6tc_get_target(const struct ip6t_entry *e,
+ struct xtc_handle *handle);
+
+/* Is this a built-in chain? */
+int ip6tc_builtin(const char *chain, struct xtc_handle *const handle);
+
+/* Get the policy of a given built-in chain */
+const char *ip6tc_get_policy(const char *chain,
+ struct xt_counters *counters,
+ struct xtc_handle *handle);
+
+/* These functions return TRUE for OK or 0 and set errno. If errno ==
+ 0, it means there was a version error (ie. upgrade libiptc). */
+/* Rule numbers start at 1 for the first rule. */
+
+/* Insert the entry `fw' in chain `chain' into position `rulenum'. */
+int ip6tc_insert_entry(const xt_chainlabel chain,
+ const struct ip6t_entry *e,
+ unsigned int rulenum,
+ struct xtc_handle *handle);
+
+/* Atomically replace rule `rulenum' in `chain' with `fw'. */
+int ip6tc_replace_entry(const xt_chainlabel chain,
+ const struct ip6t_entry *e,
+ unsigned int rulenum,
+ struct xtc_handle *handle);
+
+/* Append entry `fw' to chain `chain'. Equivalent to insert with
+ rulenum = length of chain. */
+int ip6tc_append_entry(const xt_chainlabel chain,
+ const struct ip6t_entry *e,
+ struct xtc_handle *handle);
+
+/* Check whether a matching rule exists */
+int ip6tc_check_entry(const xt_chainlabel chain,
+ const struct ip6t_entry *origfw,
+ unsigned char *matchmask,
+ struct xtc_handle *handle);
+
+/* Delete the first rule in `chain' which matches `fw'. */
+int ip6tc_delete_entry(const xt_chainlabel chain,
+ const struct ip6t_entry *origfw,
+ unsigned char *matchmask,
+ struct xtc_handle *handle);
+
+/* Delete the rule in position `rulenum' in `chain'. */
+int ip6tc_delete_num_entry(const xt_chainlabel chain,
+ unsigned int rulenum,
+ struct xtc_handle *handle);
+
+/* Check the packet `fw' on chain `chain'. Returns the verdict, or
+ NULL and sets errno. */
+const char *ip6tc_check_packet(const xt_chainlabel chain,
+ struct ip6t_entry *,
+ struct xtc_handle *handle);
+
+/* Flushes the entries in the given chain (ie. empties chain). */
+int ip6tc_flush_entries(const xt_chainlabel chain,
+ struct xtc_handle *handle);
+
+/* Zeroes the counters in a chain. */
+int ip6tc_zero_entries(const xt_chainlabel chain,
+ struct xtc_handle *handle);
+
+/* Creates a new chain. */
+int ip6tc_create_chain(const xt_chainlabel chain,
+ struct xtc_handle *handle);
+
+/* Deletes a chain. */
+int ip6tc_delete_chain(const xt_chainlabel chain,
+ struct xtc_handle *handle);
+
+/* Renames a chain. */
+int ip6tc_rename_chain(const xt_chainlabel oldname,
+ const xt_chainlabel newname,
+ struct xtc_handle *handle);
+
+/* Sets the policy on a built-in chain. */
+int ip6tc_set_policy(const xt_chainlabel chain,
+ const xt_chainlabel policy,
+ struct xt_counters *counters,
+ struct xtc_handle *handle);
+
+/* Get the number of references to this chain */
+int ip6tc_get_references(unsigned int *ref, const xt_chainlabel chain,
+ struct xtc_handle *handle);
+
+/* read packet and byte counters for a specific rule */
+struct xt_counters *ip6tc_read_counter(const xt_chainlabel chain,
+ unsigned int rulenum,
+ struct xtc_handle *handle);
+
+/* zero packet and byte counters for a specific rule */
+int ip6tc_zero_counter(const xt_chainlabel chain,
+ unsigned int rulenum,
+ struct xtc_handle *handle);
+
+/* set packet and byte counters for a specific rule */
+int ip6tc_set_counter(const xt_chainlabel chain,
+ unsigned int rulenum,
+ struct xt_counters *counters,
+ struct xtc_handle *handle);
+
+/* Makes the actual changes. */
+int ip6tc_commit(struct xtc_handle *handle);
+
+/* Get raw socket. */
+int ip6tc_get_raw_socket(void);
+
+/* Translates errno numbers into more human-readable form than strerror. */
+const char *ip6tc_strerror(int err);
+
+extern void dump_entries6(struct xtc_handle *const);
+
+extern const struct xtc_ops ip6tc_ops;
+
+#endif /* _LIBIP6TC_H */
diff --git a/iproute2/include/libiptc/libiptc.h b/iproute2/include/libiptc/libiptc.h
new file mode 100644
index 0000000..24cdbdb
--- /dev/null
+++ b/iproute2/include/libiptc/libiptc.h
@@ -0,0 +1,172 @@
+#ifndef _LIBIPTC_H
+#define _LIBIPTC_H
+/* Library which manipulates filtering rules. */
+
+#include <linux/types.h>
+#include <libiptc/ipt_kernel_headers.h>
+#ifdef __cplusplus
+# include <climits>
+#else
+# include <limits.h> /* INT_MAX in ip_tables.h */
+#endif
+#include <linux/netfilter_ipv4/ip_tables.h>
+#include <libiptc/xtcshared.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#define iptc_handle xtc_handle
+#define ipt_chainlabel xt_chainlabel
+
+#define IPTC_LABEL_ACCEPT "ACCEPT"
+#define IPTC_LABEL_DROP "DROP"
+#define IPTC_LABEL_QUEUE "QUEUE"
+#define IPTC_LABEL_RETURN "RETURN"
+
+/* Does this chain exist? */
+int iptc_is_chain(const char *chain, struct xtc_handle *const handle);
+
+/* Take a snapshot of the rules. Returns NULL on error. */
+struct xtc_handle *iptc_init(const char *tablename);
+
+/* Cleanup after iptc_init(). */
+void iptc_free(struct xtc_handle *h);
+
+/* Iterator functions to run through the chains. Returns NULL at end. */
+const char *iptc_first_chain(struct xtc_handle *handle);
+const char *iptc_next_chain(struct xtc_handle *handle);
+
+/* Get first rule in the given chain: NULL for empty chain. */
+const struct ipt_entry *iptc_first_rule(const char *chain,
+ struct xtc_handle *handle);
+
+/* Returns NULL when rules run out. */
+const struct ipt_entry *iptc_next_rule(const struct ipt_entry *prev,
+ struct xtc_handle *handle);
+
+/* Returns a pointer to the target name of this entry. */
+const char *iptc_get_target(const struct ipt_entry *e,
+ struct xtc_handle *handle);
+
+/* Is this a built-in chain? */
+int iptc_builtin(const char *chain, struct xtc_handle *const handle);
+
+/* Get the policy of a given built-in chain */
+const char *iptc_get_policy(const char *chain,
+ struct xt_counters *counter,
+ struct xtc_handle *handle);
+
+/* These functions return TRUE for OK or 0 and set errno. If errno ==
+ 0, it means there was a version error (ie. upgrade libiptc). */
+/* Rule numbers start at 1 for the first rule. */
+
+/* Insert the entry `e' in chain `chain' into position `rulenum'. */
+int iptc_insert_entry(const xt_chainlabel chain,
+ const struct ipt_entry *e,
+ unsigned int rulenum,
+ struct xtc_handle *handle);
+
+/* Atomically replace rule `rulenum' in `chain' with `e'. */
+int iptc_replace_entry(const xt_chainlabel chain,
+ const struct ipt_entry *e,
+ unsigned int rulenum,
+ struct xtc_handle *handle);
+
+/* Append entry `e' to chain `chain'. Equivalent to insert with
+ rulenum = length of chain. */
+int iptc_append_entry(const xt_chainlabel chain,
+ const struct ipt_entry *e,
+ struct xtc_handle *handle);
+
+/* Check whether a mathching rule exists */
+int iptc_check_entry(const xt_chainlabel chain,
+ const struct ipt_entry *origfw,
+ unsigned char *matchmask,
+ struct xtc_handle *handle);
+
+/* Delete the first rule in `chain' which matches `e', subject to
+ matchmask (array of length == origfw) */
+int iptc_delete_entry(const xt_chainlabel chain,
+ const struct ipt_entry *origfw,
+ unsigned char *matchmask,
+ struct xtc_handle *handle);
+
+/* Delete the rule in position `rulenum' in `chain'. */
+int iptc_delete_num_entry(const xt_chainlabel chain,
+ unsigned int rulenum,
+ struct xtc_handle *handle);
+
+/* Check the packet `e' on chain `chain'. Returns the verdict, or
+ NULL and sets errno. */
+const char *iptc_check_packet(const xt_chainlabel chain,
+ struct ipt_entry *entry,
+ struct xtc_handle *handle);
+
+/* Flushes the entries in the given chain (ie. empties chain). */
+int iptc_flush_entries(const xt_chainlabel chain,
+ struct xtc_handle *handle);
+
+/* Zeroes the counters in a chain. */
+int iptc_zero_entries(const xt_chainlabel chain,
+ struct xtc_handle *handle);
+
+/* Creates a new chain. */
+int iptc_create_chain(const xt_chainlabel chain,
+ struct xtc_handle *handle);
+
+/* Deletes a chain. */
+int iptc_delete_chain(const xt_chainlabel chain,
+ struct xtc_handle *handle);
+
+/* Renames a chain. */
+int iptc_rename_chain(const xt_chainlabel oldname,
+ const xt_chainlabel newname,
+ struct xtc_handle *handle);
+
+/* Sets the policy on a built-in chain. */
+int iptc_set_policy(const xt_chainlabel chain,
+ const xt_chainlabel policy,
+ struct xt_counters *counters,
+ struct xtc_handle *handle);
+
+/* Get the number of references to this chain */
+int iptc_get_references(unsigned int *ref,
+ const xt_chainlabel chain,
+ struct xtc_handle *handle);
+
+/* read packet and byte counters for a specific rule */
+struct xt_counters *iptc_read_counter(const xt_chainlabel chain,
+ unsigned int rulenum,
+ struct xtc_handle *handle);
+
+/* zero packet and byte counters for a specific rule */
+int iptc_zero_counter(const xt_chainlabel chain,
+ unsigned int rulenum,
+ struct xtc_handle *handle);
+
+/* set packet and byte counters for a specific rule */
+int iptc_set_counter(const xt_chainlabel chain,
+ unsigned int rulenum,
+ struct xt_counters *counters,
+ struct xtc_handle *handle);
+
+/* Makes the actual changes. */
+int iptc_commit(struct xtc_handle *handle);
+
+/* Get raw socket. */
+int iptc_get_raw_socket(void);
+
+/* Translates errno numbers into more human-readable form than strerror. */
+const char *iptc_strerror(int err);
+
+extern void dump_entries(struct xtc_handle *const);
+
+extern const struct xtc_ops iptc_ops;
+
+#ifdef __cplusplus
+}
+#endif
+
+
+#endif /* _LIBIPTC_H */
diff --git a/iproute2/include/libiptc/libxtc.h b/iproute2/include/libiptc/libxtc.h
new file mode 100644
index 0000000..3701018
--- /dev/null
+++ b/iproute2/include/libiptc/libxtc.h
@@ -0,0 +1,33 @@
+#ifndef _LIBXTC_H
+#define _LIBXTC_H
+/* Library which manipulates filtering rules. */
+
+#include <libiptc/ipt_kernel_headers.h>
+#include <linux/netfilter/x_tables.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifndef XT_MIN_ALIGN
+/* xt_entry has pointers and u_int64_t's in it, so if you align to
+ it, you'll also align to any crazy matches and targets someone
+ might write */
+#define XT_MIN_ALIGN (__alignof__(struct xt_entry))
+#endif
+
+#ifndef XT_ALIGN
+#define XT_ALIGN(s) (((s) + ((XT_MIN_ALIGN)-1)) & ~((XT_MIN_ALIGN)-1))
+#endif
+
+#define XTC_LABEL_ACCEPT "ACCEPT"
+#define XTC_LABEL_DROP "DROP"
+#define XTC_LABEL_QUEUE "QUEUE"
+#define XTC_LABEL_RETURN "RETURN"
+
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _LIBXTC_H */
diff --git a/iproute2/include/libiptc/xtcshared.h b/iproute2/include/libiptc/xtcshared.h
new file mode 100644
index 0000000..773ebc4
--- /dev/null
+++ b/iproute2/include/libiptc/xtcshared.h
@@ -0,0 +1,20 @@
+#ifndef _LIBXTC_SHARED_H
+#define _LIBXTC_SHARED_H 1
+
+typedef char xt_chainlabel[32];
+struct xtc_handle;
+struct xt_counters;
+
+struct xtc_ops {
+ int (*commit)(struct xtc_handle *);
+ void (*free)(struct xtc_handle *);
+ int (*builtin)(const char *, struct xtc_handle *const);
+ int (*is_chain)(const char *, struct xtc_handle *const);
+ int (*flush_entries)(const xt_chainlabel, struct xtc_handle *);
+ int (*create_chain)(const xt_chainlabel, struct xtc_handle *);
+ int (*set_policy)(const xt_chainlabel, const xt_chainlabel,
+ struct xt_counters *, struct xtc_handle *);
+ const char *(*strerror)(int);
+};
+
+#endif /* _LIBXTC_SHARED_H */
diff --git a/iproute2/include/libnetlink.h b/iproute2/include/libnetlink.h
new file mode 100644
index 0000000..431189e
--- /dev/null
+++ b/iproute2/include/libnetlink.h
@@ -0,0 +1,205 @@
+#ifndef __LIBNETLINK_H__
+#define __LIBNETLINK_H__ 1
+
+#include <stdio.h>
+#include <string.h>
+#include <asm/types.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <linux/if_link.h>
+#include <linux/if_addr.h>
+#include <linux/neighbour.h>
+#include <linux/netconf.h>
+
+struct rtnl_handle
+{
+ int fd;
+ struct sockaddr_nl local;
+ struct sockaddr_nl peer;
+ __u32 seq;
+ __u32 dump;
+ int proto;
+ FILE *dump_fp;
+#define RTNL_HANDLE_F_LISTEN_ALL_NSID 0x01
+ int flags;
+};
+
+extern int rcvbuf;
+
+int rtnl_open(struct rtnl_handle *rth, unsigned subscriptions)
+ __attribute__((warn_unused_result));
+
+int rtnl_open_byproto(struct rtnl_handle *rth, unsigned subscriptions,
+ int protocol)
+ __attribute__((warn_unused_result));
+
+void rtnl_close(struct rtnl_handle *rth);
+int rtnl_wilddump_request(struct rtnl_handle *rth, int fam, int type)
+ __attribute__((warn_unused_result));
+int rtnl_wilddump_req_filter(struct rtnl_handle *rth, int fam, int type,
+ __u32 filt_mask)
+ __attribute__((warn_unused_result));
+int rtnl_dump_request(struct rtnl_handle *rth, int type, void *req,
+ int len)
+ __attribute__((warn_unused_result));
+int rtnl_dump_request_n(struct rtnl_handle *rth, struct nlmsghdr *n)
+ __attribute__((warn_unused_result));
+
+struct rtnl_ctrl_data {
+ int nsid;
+};
+
+typedef int (*rtnl_filter_t)(const struct sockaddr_nl *,
+ struct nlmsghdr *n, void *);
+
+typedef int (*rtnl_listen_filter_t)(const struct sockaddr_nl *,
+ struct rtnl_ctrl_data *,
+ struct nlmsghdr *n, void *);
+
+struct rtnl_dump_filter_arg
+{
+ rtnl_filter_t filter;
+ void *arg1;
+ __u16 nc_flags;
+};
+
+int rtnl_dump_filter_l(struct rtnl_handle *rth,
+ const struct rtnl_dump_filter_arg *arg);
+int rtnl_dump_filter_nc(struct rtnl_handle *rth,
+ rtnl_filter_t filter,
+ void *arg, __u16 nc_flags);
+#define rtnl_dump_filter(rth, filter, arg) \
+ rtnl_dump_filter_nc(rth, filter, arg, 0)
+int rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
+ struct nlmsghdr *answer, size_t len)
+ __attribute__((warn_unused_result));
+int rtnl_send(struct rtnl_handle *rth, const void *buf, int)
+ __attribute__((warn_unused_result));
+int rtnl_send_check(struct rtnl_handle *rth, const void *buf, int)
+ __attribute__((warn_unused_result));
+
+int addattr(struct nlmsghdr *n, int maxlen, int type);
+int addattr8(struct nlmsghdr *n, int maxlen, int type, __u8 data);
+int addattr16(struct nlmsghdr *n, int maxlen, int type, __u16 data);
+int addattr32(struct nlmsghdr *n, int maxlen, int type, __u32 data);
+int addattr64(struct nlmsghdr *n, int maxlen, int type, __u64 data);
+int addattrstrz(struct nlmsghdr *n, int maxlen, int type, const char *data);
+
+int addattr_l(struct nlmsghdr *n, int maxlen, int type,
+ const void *data, int alen);
+int addraw_l(struct nlmsghdr *n, int maxlen, const void *data, int len);
+struct rtattr *addattr_nest(struct nlmsghdr *n, int maxlen, int type);
+int addattr_nest_end(struct nlmsghdr *n, struct rtattr *nest);
+struct rtattr *addattr_nest_compat(struct nlmsghdr *n, int maxlen, int type,
+ const void *data, int len);
+int addattr_nest_compat_end(struct nlmsghdr *n, struct rtattr *nest);
+int rta_addattr8(struct rtattr *rta, int maxlen, int type, __u8 data);
+int rta_addattr16(struct rtattr *rta, int maxlen, int type, __u16 data);
+int rta_addattr32(struct rtattr *rta, int maxlen, int type, __u32 data);
+int rta_addattr64(struct rtattr *rta, int maxlen, int type, __u64 data);
+int rta_addattr_l(struct rtattr *rta, int maxlen, int type,
+ const void *data, int alen);
+
+int parse_rtattr(struct rtattr *tb[], int max, struct rtattr *rta, int len);
+int parse_rtattr_flags(struct rtattr *tb[], int max, struct rtattr *rta,
+ int len, unsigned short flags);
+int parse_rtattr_byindex(struct rtattr *tb[], int max,
+ struct rtattr *rta, int len);
+struct rtattr *parse_rtattr_one(int type, struct rtattr *rta, int len);
+int __parse_rtattr_nested_compat(struct rtattr *tb[], int max, struct rtattr *rta, int len);
+
+struct rtattr *rta_nest(struct rtattr *rta, int maxlen, int type);
+int rta_nest_end(struct rtattr *rta, struct rtattr *nest);
+
+#define RTA_TAIL(rta) \
+ ((struct rtattr *) (((void *) (rta)) + \
+ RTA_ALIGN((rta)->rta_len)))
+
+#define parse_rtattr_nested(tb, max, rta) \
+ (parse_rtattr((tb), (max), RTA_DATA(rta), RTA_PAYLOAD(rta)))
+
+#define parse_rtattr_one_nested(type, rta) \
+ (parse_rtattr_one(type, RTA_DATA(rta), RTA_PAYLOAD(rta)))
+
+#define parse_rtattr_nested_compat(tb, max, rta, data, len) \
+ ({ data = RTA_PAYLOAD(rta) >= len ? RTA_DATA(rta) : NULL; \
+ __parse_rtattr_nested_compat(tb, max, rta, len); })
+
+static inline __u8 rta_getattr_u8(const struct rtattr *rta)
+{
+ return *(__u8 *)RTA_DATA(rta);
+}
+static inline __u16 rta_getattr_u16(const struct rtattr *rta)
+{
+ return *(__u16 *)RTA_DATA(rta);
+}
+static inline __u32 rta_getattr_u32(const struct rtattr *rta)
+{
+ return *(__u32 *)RTA_DATA(rta);
+}
+static inline __u64 rta_getattr_u64(const struct rtattr *rta)
+{
+ __u64 tmp;
+ memcpy(&tmp, RTA_DATA(rta), sizeof(__u64));
+ return tmp;
+}
+static inline const char *rta_getattr_str(const struct rtattr *rta)
+{
+ return (const char *)RTA_DATA(rta);
+}
+
+int rtnl_listen_all_nsid(struct rtnl_handle *);
+int rtnl_listen(struct rtnl_handle *, rtnl_listen_filter_t handler,
+ void *jarg);
+int rtnl_from_file(FILE *, rtnl_listen_filter_t handler,
+ void *jarg);
+
+#define NLMSG_TAIL(nmsg) \
+ ((struct rtattr *) (((void *) (nmsg)) + NLMSG_ALIGN((nmsg)->nlmsg_len)))
+
+#ifndef IFA_RTA
+#define IFA_RTA(r) \
+ ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifaddrmsg))))
+#endif
+#ifndef IFA_PAYLOAD
+#define IFA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifaddrmsg))
+#endif
+
+#ifndef IFLA_RTA
+#define IFLA_RTA(r) \
+ ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg))))
+#endif
+#ifndef IFLA_PAYLOAD
+#define IFLA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifinfomsg))
+#endif
+
+#ifndef NDA_RTA
+#define NDA_RTA(r) \
+ ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ndmsg))))
+#endif
+#ifndef NDA_PAYLOAD
+#define NDA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ndmsg))
+#endif
+
+#ifndef NDTA_RTA
+#define NDTA_RTA(r) \
+ ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ndtmsg))))
+#endif
+#ifndef NDTA_PAYLOAD
+#define NDTA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ndtmsg))
+#endif
+
+#ifndef NETNS_RTA
+#define NETNS_RTA(r) \
+ ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct rtgenmsg))))
+#endif
+#ifndef NETNS_PAYLOAD
+#define NETNS_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct rtgenmsg))
+#endif
+
+/* User defined nlmsg_type which is used mostly for logging netlink
+ * messages from dump file */
+#define NLMSG_TSTAMP 15
+
+#endif /* __LIBNETLINK_H__ */
+
diff --git a/iproute2/include/linux/atm.h b/iproute2/include/linux/atm.h
new file mode 100644
index 0000000..08e27be
--- /dev/null
+++ b/iproute2/include/linux/atm.h
@@ -0,0 +1,241 @@
+/* atm.h - general ATM declarations */
+
+/* Written 1995-2000 by Werner Almesberger, EPFL LRC/ICA */
+
+
+/*
+ * WARNING: User-space programs should not #include <linux/atm.h> directly.
+ * Instead, #include <atm.h>
+ */
+
+#ifndef _LINUX_ATM_H
+#define _LINUX_ATM_H
+
+/*
+ * BEGIN_xx and END_xx markers are used for automatic generation of
+ * documentation. Do not change them.
+ */
+
+
+#include <linux/atmapi.h>
+#include <linux/atmsap.h>
+#include <linux/atmioc.h>
+#include <linux/types.h>
+
+
+/* general ATM constants */
+#define ATM_CELL_SIZE 53 /* ATM cell size incl. header */
+#define ATM_CELL_PAYLOAD 48 /* ATM payload size */
+#define ATM_AAL0_SDU 52 /* AAL0 SDU size */
+#define ATM_MAX_AAL34_PDU 65535 /* maximum AAL3/4 PDU payload */
+#define ATM_AAL5_TRAILER 8 /* AAL5 trailer size */
+#define ATM_MAX_AAL5_PDU 65535 /* maximum AAL5 PDU payload */
+#define ATM_MAX_CDV 9999 /* maximum (default) CDV */
+#define ATM_NOT_RSV_VCI 32 /* first non-reserved VCI value */
+
+#define ATM_MAX_VPI 255 /* maximum VPI at the UNI */
+#define ATM_MAX_VPI_NNI 4096 /* maximum VPI at the NNI */
+#define ATM_MAX_VCI 65535 /* maximum VCI */
+
+
+/* "protcol" values for the socket system call */
+#define ATM_NO_AAL 0 /* AAL not specified */
+#define ATM_AAL0 13 /* "raw" ATM cells */
+#define ATM_AAL1 1 /* AAL1 (CBR) */
+#define ATM_AAL2 2 /* AAL2 (VBR) */
+#define ATM_AAL34 3 /* AAL3/4 (data) */
+#define ATM_AAL5 5 /* AAL5 (data) */
+
+/*
+ * socket option name coding functions
+ *
+ * Note that __SO_ENCODE and __SO_LEVEL are somewhat a hack since the
+ * << 22 only reserves 9 bits for the level. On some architectures
+ * SOL_SOCKET is 0xFFFF, so that's a bit of a problem
+ */
+
+#define __SO_ENCODE(l,n,t) ((((l) & 0x1FF) << 22) | ((n) << 16) | \
+ sizeof(t))
+#define __SO_LEVEL_MATCH(c,m) (((c) >> 22) == ((m) & 0x1FF))
+#define __SO_NUMBER(c) (((c) >> 16) & 0x3f)
+#define __SO_SIZE(c) ((c) & 0x3fff)
+
+/*
+ * ATM layer
+ */
+
+#define SO_SETCLP __SO_ENCODE(SOL_ATM,0,int)
+ /* set CLP bit value - TODO */
+#define SO_CIRANGE __SO_ENCODE(SOL_ATM,1,struct atm_cirange)
+ /* connection identifier range; socket must be
+ bound or connected */
+#define SO_ATMQOS __SO_ENCODE(SOL_ATM,2,struct atm_qos)
+ /* Quality of Service setting */
+#define SO_ATMSAP __SO_ENCODE(SOL_ATM,3,struct atm_sap)
+ /* Service Access Point */
+#define SO_ATMPVC __SO_ENCODE(SOL_ATM,4,struct sockaddr_atmpvc)
+ /* "PVC" address (also for SVCs); get only */
+#define SO_MULTIPOINT __SO_ENCODE(SOL_ATM, 5, int)
+ /* make this vc a p2mp */
+
+
+/*
+ * Note @@@: since the socket layers don't really distinguish the control and
+ * the data plane but generally seems to be data plane-centric, any layer is
+ * about equally wrong for the SAP. If you have a better idea about this,
+ * please speak up ...
+ */
+
+
+/* ATM cell header (for AAL0) */
+
+/* BEGIN_CH */
+#define ATM_HDR_GFC_MASK 0xf0000000
+#define ATM_HDR_GFC_SHIFT 28
+#define ATM_HDR_VPI_MASK 0x0ff00000
+#define ATM_HDR_VPI_SHIFT 20
+#define ATM_HDR_VCI_MASK 0x000ffff0
+#define ATM_HDR_VCI_SHIFT 4
+#define ATM_HDR_PTI_MASK 0x0000000e
+#define ATM_HDR_PTI_SHIFT 1
+#define ATM_HDR_CLP 0x00000001
+/* END_CH */
+
+
+/* PTI codings */
+
+/* BEGIN_PTI */
+#define ATM_PTI_US0 0 /* user data cell, congestion not exp, SDU-type 0 */
+#define ATM_PTI_US1 1 /* user data cell, congestion not exp, SDU-type 1 */
+#define ATM_PTI_UCES0 2 /* user data cell, cong. experienced, SDU-type 0 */
+#define ATM_PTI_UCES1 3 /* user data cell, cong. experienced, SDU-type 1 */
+#define ATM_PTI_SEGF5 4 /* segment OAM F5 flow related cell */
+#define ATM_PTI_E2EF5 5 /* end-to-end OAM F5 flow related cell */
+#define ATM_PTI_RSV_RM 6 /* reserved for traffic control/resource mgmt */
+#define ATM_PTI_RSV 7 /* reserved */
+/* END_PTI */
+
+
+/*
+ * The following items should stay in linux/atm.h, which should be linked to
+ * netatm/atm.h
+ */
+
+/* Traffic description */
+
+#define ATM_NONE 0 /* no traffic */
+#define ATM_UBR 1
+#define ATM_CBR 2
+#define ATM_VBR 3
+#define ATM_ABR 4
+#define ATM_ANYCLASS 5 /* compatible with everything */
+
+#define ATM_MAX_PCR -1 /* maximum available PCR */
+
+struct atm_trafprm {
+ unsigned char traffic_class; /* traffic class (ATM_UBR, ...) */
+ int max_pcr; /* maximum PCR in cells per second */
+ int pcr; /* desired PCR in cells per second */
+ int min_pcr; /* minimum PCR in cells per second */
+ int max_cdv; /* maximum CDV in microseconds */
+ int max_sdu; /* maximum SDU in bytes */
+ /* extra params for ABR */
+ unsigned int icr; /* Initial Cell Rate (24-bit) */
+ unsigned int tbe; /* Transient Buffer Exposure (24-bit) */
+ unsigned int frtt : 24; /* Fixed Round Trip Time (24-bit) */
+ unsigned int rif : 4; /* Rate Increment Factor (4-bit) */
+ unsigned int rdf : 4; /* Rate Decrease Factor (4-bit) */
+ unsigned int nrm_pres :1; /* nrm present bit */
+ unsigned int trm_pres :1; /* rm present bit */
+ unsigned int adtf_pres :1; /* adtf present bit */
+ unsigned int cdf_pres :1; /* cdf present bit*/
+ unsigned int nrm :3; /* Max # of Cells for each forward RM cell (3-bit) */
+ unsigned int trm :3; /* Time between forward RM cells (3-bit) */
+ unsigned int adtf :10; /* ACR Decrease Time Factor (10-bit) */
+ unsigned int cdf :3; /* Cutoff Decrease Factor (3-bit) */
+ unsigned int spare :9; /* spare bits */
+};
+
+struct atm_qos {
+ struct atm_trafprm txtp; /* parameters in TX direction */
+ struct atm_trafprm rxtp __ATM_API_ALIGN;
+ /* parameters in RX direction */
+ unsigned char aal __ATM_API_ALIGN;
+};
+
+/* PVC addressing */
+
+#define ATM_ITF_ANY -1 /* "magic" PVC address values */
+#define ATM_VPI_ANY -1
+#define ATM_VCI_ANY -1
+#define ATM_VPI_UNSPEC -2
+#define ATM_VCI_UNSPEC -2
+
+
+struct sockaddr_atmpvc {
+ unsigned short sap_family; /* address family, AF_ATMPVC */
+ struct { /* PVC address */
+ short itf; /* ATM interface */
+ short vpi; /* VPI (only 8 bits at UNI) */
+ int vci; /* VCI (only 16 bits at UNI) */
+ } sap_addr __ATM_API_ALIGN; /* PVC address */
+};
+
+/* SVC addressing */
+
+#define ATM_ESA_LEN 20 /* ATM End System Address length */
+#define ATM_E164_LEN 12 /* maximum E.164 number length */
+
+#define ATM_AFI_DCC 0x39 /* DCC ATM Format */
+#define ATM_AFI_ICD 0x47 /* ICD ATM Format */
+#define ATM_AFI_E164 0x45 /* E.164 ATM Format */
+#define ATM_AFI_LOCAL 0x49 /* Local ATM Format */
+
+#define ATM_AFI_DCC_GROUP 0xBD /* DCC ATM Group Format */
+#define ATM_AFI_ICD_GROUP 0xC5 /* ICD ATM Group Format */
+#define ATM_AFI_E164_GROUP 0xC3 /* E.164 ATM Group Format */
+#define ATM_AFI_LOCAL_GROUP 0xC7 /* Local ATM Group Format */
+
+#define ATM_LIJ_NONE 0 /* no leaf-initiated join */
+#define ATM_LIJ 1 /* request joining */
+#define ATM_LIJ_RPJ 2 /* set to root-prompted join */
+#define ATM_LIJ_NJ 3 /* set to network join */
+
+
+struct sockaddr_atmsvc {
+ unsigned short sas_family; /* address family, AF_ATMSVC */
+ struct { /* SVC address */
+ unsigned char prv[ATM_ESA_LEN];/* private ATM address */
+ char pub[ATM_E164_LEN+1]; /* public address (E.164) */
+ /* unused addresses must be bzero'ed */
+ char lij_type; /* role in LIJ call; one of ATM_LIJ* */
+ __u32 lij_id; /* LIJ call identifier */
+ } sas_addr __ATM_API_ALIGN; /* SVC address */
+};
+
+
+static __inline__ int atmsvc_addr_in_use(struct sockaddr_atmsvc addr)
+{
+ return *addr.sas_addr.prv || *addr.sas_addr.pub;
+}
+
+
+static __inline__ int atmpvc_addr_in_use(struct sockaddr_atmpvc addr)
+{
+ return addr.sap_addr.itf || addr.sap_addr.vpi || addr.sap_addr.vci;
+}
+
+
+/*
+ * Some stuff for linux/sockios.h
+ */
+
+struct atmif_sioc {
+ int number;
+ int length;
+ void *arg;
+};
+
+
+typedef unsigned short atm_backend_t;
+#endif /* _LINUX_ATM_H */
diff --git a/iproute2/include/linux/atmapi.h b/iproute2/include/linux/atmapi.h
new file mode 100644
index 0000000..8fe54d9
--- /dev/null
+++ b/iproute2/include/linux/atmapi.h
@@ -0,0 +1,29 @@
+/* atmapi.h - ATM API user space/kernel compatibility */
+
+/* Written 1999,2000 by Werner Almesberger, EPFL ICA */
+
+
+#ifndef _LINUX_ATMAPI_H
+#define _LINUX_ATMAPI_H
+
+#if defined(__sparc__) || defined(__ia64__)
+/* such alignment is not required on 32 bit sparcs, but we can't
+ figure that we are on a sparc64 while compiling user-space programs. */
+#define __ATM_API_ALIGN __attribute__((aligned(8)))
+#else
+#define __ATM_API_ALIGN
+#endif
+
+
+/*
+ * Opaque type for kernel pointers. Note that _ is never accessed. We need
+ * the struct in order hide the array, so that we can make simple assignments
+ * instead of being forced to use memcpy. It also improves error reporting for
+ * code that still assumes that we're passing unsigned longs.
+ *
+ * Convention: NULL pointers are passed as a field of all zeroes.
+ */
+
+typedef struct { unsigned char _[8]; } __ATM_API_ALIGN atm_kptr_t;
+
+#endif
diff --git a/iproute2/include/linux/atmioc.h b/iproute2/include/linux/atmioc.h
new file mode 100644
index 0000000..37f67aa
--- /dev/null
+++ b/iproute2/include/linux/atmioc.h
@@ -0,0 +1,41 @@
+/* atmioc.h - ranges for ATM-related ioctl numbers */
+
+/* Written 1995-1999 by Werner Almesberger, EPFL LRC/ICA */
+
+
+/*
+ * See http://icawww1.epfl.ch/linux-atm/magic.html for the complete list of
+ * "magic" ioctl numbers.
+ */
+
+
+#ifndef _LINUX_ATMIOC_H
+#define _LINUX_ATMIOC_H
+
+#include <asm/ioctl.h>
+ /* everybody including atmioc.h will also need _IO{,R,W,WR} */
+
+#define ATMIOC_PHYCOM 0x00 /* PHY device common ioctls, globally unique */
+#define ATMIOC_PHYCOM_END 0x0f
+#define ATMIOC_PHYTYP 0x10 /* PHY dev type ioctls, unique per PHY type */
+#define ATMIOC_PHYTYP_END 0x2f
+#define ATMIOC_PHYPRV 0x30 /* PHY dev private ioctls, unique per driver */
+#define ATMIOC_PHYPRV_END 0x4f
+#define ATMIOC_SARCOM 0x50 /* SAR device common ioctls, globally unique */
+#define ATMIOC_SARCOM_END 0x50
+#define ATMIOC_SARPRV 0x60 /* SAR dev private ioctls, unique per driver */
+#define ATMIOC_SARPRV_END 0x7f
+#define ATMIOC_ITF 0x80 /* Interface ioctls, globally unique */
+#define ATMIOC_ITF_END 0x8f
+#define ATMIOC_BACKEND 0x90 /* ATM generic backend ioctls, u. per backend */
+#define ATMIOC_BACKEND_END 0xaf
+/* 0xb0-0xbf: Reserved for future use */
+#define ATMIOC_AREQUIPA 0xc0 /* Application requested IP over ATM, glob. u. */
+#define ATMIOC_LANE 0xd0 /* LAN Emulation, globally unique */
+#define ATMIOC_MPOA 0xd8 /* MPOA, globally unique */
+#define ATMIOC_CLIP 0xe0 /* Classical IP over ATM control, globally u. */
+#define ATMIOC_CLIP_END 0xef
+#define ATMIOC_SPECIAL 0xf0 /* Special-purpose controls, globally unique */
+#define ATMIOC_SPECIAL_END 0xff
+
+#endif
diff --git a/iproute2/include/linux/atmsap.h b/iproute2/include/linux/atmsap.h
new file mode 100644
index 0000000..799b104
--- /dev/null
+++ b/iproute2/include/linux/atmsap.h
@@ -0,0 +1,162 @@
+/* atmsap.h - ATM Service Access Point addressing definitions */
+
+/* Written 1995-1999 by Werner Almesberger, EPFL LRC/ICA */
+
+
+#ifndef _LINUX_ATMSAP_H
+#define _LINUX_ATMSAP_H
+
+#include <linux/atmapi.h>
+
+/*
+ * BEGIN_xx and END_xx markers are used for automatic generation of
+ * documentation. Do not change them.
+ */
+
+
+/*
+ * Layer 2 protocol identifiers
+ */
+
+/* BEGIN_L2 */
+#define ATM_L2_NONE 0 /* L2 not specified */
+#define ATM_L2_ISO1745 0x01 /* Basic mode ISO 1745 */
+#define ATM_L2_Q291 0x02 /* ITU-T Q.291 (Rec. I.441) */
+#define ATM_L2_X25_LL 0x06 /* ITU-T X.25, link layer */
+#define ATM_L2_X25_ML 0x07 /* ITU-T X.25, multilink */
+#define ATM_L2_LAPB 0x08 /* Extended LAPB, half-duplex (Rec. T.71) */
+#define ATM_L2_HDLC_ARM 0x09 /* HDLC ARM (ISO/IEC 4335) */
+#define ATM_L2_HDLC_NRM 0x0a /* HDLC NRM (ISO/IEC 4335) */
+#define ATM_L2_HDLC_ABM 0x0b /* HDLC ABM (ISO/IEC 4335) */
+#define ATM_L2_ISO8802 0x0c /* LAN LLC (ISO/IEC 8802/2) */
+#define ATM_L2_X75 0x0d /* ITU-T X.75, SLP */
+#define ATM_L2_Q922 0x0e /* ITU-T Q.922 */
+#define ATM_L2_USER 0x10 /* user-specified */
+#define ATM_L2_ISO7776 0x11 /* ISO 7776 DTE-DTE */
+/* END_L2 */
+
+
+/*
+ * Layer 3 protocol identifiers
+ */
+
+/* BEGIN_L3 */
+#define ATM_L3_NONE 0 /* L3 not specified */
+#define ATM_L3_X25 0x06 /* ITU-T X.25, packet layer */
+#define ATM_L3_ISO8208 0x07 /* ISO/IEC 8208 */
+#define ATM_L3_X223 0x08 /* ITU-T X.223 | ISO/IEC 8878 */
+#define ATM_L3_ISO8473 0x09 /* ITU-T X.233 | ISO/IEC 8473 */
+#define ATM_L3_T70 0x0a /* ITU-T T.70 minimum network layer */
+#define ATM_L3_TR9577 0x0b /* ISO/IEC TR 9577 */
+#define ATM_L3_H310 0x0c /* ITU-T Recommendation H.310 */
+#define ATM_L3_H321 0x0d /* ITU-T Recommendation H.321 */
+#define ATM_L3_USER 0x10 /* user-specified */
+/* END_L3 */
+
+
+/*
+ * High layer identifiers
+ */
+
+/* BEGIN_HL */
+#define ATM_HL_NONE 0 /* HL not specified */
+#define ATM_HL_ISO 0x01 /* ISO */
+#define ATM_HL_USER 0x02 /* user-specific */
+#define ATM_HL_HLP 0x03 /* high layer profile - UNI 3.0 only */
+#define ATM_HL_VENDOR 0x04 /* vendor-specific application identifier */
+/* END_HL */
+
+
+/*
+ * ITU-T coded mode of operation
+ */
+
+/* BEGIN_IMD */
+#define ATM_IMD_NONE 0 /* mode not specified */
+#define ATM_IMD_NORMAL 1 /* normal mode of operation */
+#define ATM_IMD_EXTENDED 2 /* extended mode of operation */
+/* END_IMD */
+
+/*
+ * H.310 code points
+ */
+
+#define ATM_TT_NONE 0 /* terminal type not specified */
+#define ATM_TT_RX 1 /* receive only */
+#define ATM_TT_TX 2 /* send only */
+#define ATM_TT_RXTX 3 /* receive and send */
+
+#define ATM_MC_NONE 0 /* no multiplexing */
+#define ATM_MC_TS 1 /* transport stream (TS) */
+#define ATM_MC_TS_FEC 2 /* transport stream with forward error corr. */
+#define ATM_MC_PS 3 /* program stream (PS) */
+#define ATM_MC_PS_FEC 4 /* program stream with forward error corr. */
+#define ATM_MC_H221 5 /* ITU-T Rec. H.221 */
+
+/*
+ * SAP structures
+ */
+
+#define ATM_MAX_HLI 8 /* maximum high-layer information length */
+
+
+struct atm_blli {
+ unsigned char l2_proto; /* layer 2 protocol */
+ union {
+ struct {
+ unsigned char mode; /* mode of operation (ATM_IMD_xxx), 0 if */
+ /* absent */
+ unsigned char window; /* window size (k), 1-127 (0 to omit) */
+ } itu; /* ITU-T encoding */
+ unsigned char user; /* user-specified l2 information */
+ } l2;
+ unsigned char l3_proto; /* layer 3 protocol */
+ union {
+ struct {
+ unsigned char mode; /* mode of operation (ATM_IMD_xxx), 0 if */
+ /* absent */
+ unsigned char def_size; /* default packet size (log2), 4-12 (0 to */
+ /* omit) */
+ unsigned char window;/* packet window size, 1-127 (0 to omit) */
+ } itu; /* ITU-T encoding */
+ unsigned char user; /* user specified l3 information */
+ struct { /* if l3_proto = ATM_L3_H310 */
+ unsigned char term_type; /* terminal type */
+ unsigned char fw_mpx_cap; /* forward multiplexing capability */
+ /* only if term_type != ATM_TT_NONE */
+ unsigned char bw_mpx_cap; /* backward multiplexing capability */
+ /* only if term_type != ATM_TT_NONE */
+ } h310;
+ struct { /* if l3_proto = ATM_L3_TR9577 */
+ unsigned char ipi; /* initial protocol id */
+ unsigned char snap[5];/* IEEE 802.1 SNAP identifier */
+ /* (only if ipi == NLPID_IEEE802_1_SNAP) */
+ } tr9577;
+ } l3;
+} __ATM_API_ALIGN;
+
+
+struct atm_bhli {
+ unsigned char hl_type; /* high layer information type */
+ unsigned char hl_length; /* length (only if hl_type == ATM_HL_USER || */
+ /* hl_type == ATM_HL_ISO) */
+ unsigned char hl_info[ATM_MAX_HLI];/* high layer information */
+};
+
+
+#define ATM_MAX_BLLI 3 /* maximum number of BLLI elements */
+
+
+struct atm_sap {
+ struct atm_bhli bhli; /* local SAP, high-layer information */
+ struct atm_blli blli[ATM_MAX_BLLI] __ATM_API_ALIGN;
+ /* local SAP, low-layer info */
+};
+
+
+static __inline__ int blli_in_use(struct atm_blli blli)
+{
+ return blli.l2_proto || blli.l3_proto;
+}
+
+#endif
diff --git a/iproute2/include/linux/bpf.h b/iproute2/include/linux/bpf.h
new file mode 100644
index 0000000..f970f9d
--- /dev/null
+++ b/iproute2/include/linux/bpf.h
@@ -0,0 +1,326 @@
+/* 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 __LINUX_BPF_H__
+#define __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_ALU64 0x07 /* alu mode in double word width */
+
+/* ld/ldx fields */
+#define BPF_DW 0x18 /* double word */
+#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
+
+#define BPF_JNE 0x50 /* jump != */
+#define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */
+#define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */
+#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 */
+};
+
+/* 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,
+};
+
+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,
+};
+
+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,
+};
+
+#define BPF_PSEUDO_MAP_FD 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 */
+
+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 */
+ };
+
+ 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; /* checked when prog_type=kprobe */
+ };
+
+ struct { /* anonymous struct used by BPF_OBJ_* commands */
+ __aligned_u64 pathname;
+ __u32 bpf_fd;
+ };
+} __attribute__((aligned(8)));
+
+/* integer value in 'imm' field of BPF_CALL instruction selects which helper
+ * function eBPF program intends to call
+ */
+enum bpf_func_id {
+ BPF_FUNC_unspec,
+ BPF_FUNC_map_lookup_elem, /* void *map_lookup_elem(&map, &key) */
+ BPF_FUNC_map_update_elem, /* int map_update_elem(&map, &key, &value, flags) */
+ BPF_FUNC_map_delete_elem, /* int map_delete_elem(&map, &key) */
+ BPF_FUNC_probe_read, /* int bpf_probe_read(void *dst, int size, void *src) */
+ BPF_FUNC_ktime_get_ns, /* u64 bpf_ktime_get_ns(void) */
+ BPF_FUNC_trace_printk, /* int bpf_trace_printk(const char *fmt, int fmt_size, ...) */
+ BPF_FUNC_get_prandom_u32, /* u32 prandom_u32(void) */
+ BPF_FUNC_get_smp_processor_id, /* u32 raw_smp_processor_id(void) */
+
+ /**
+ * skb_store_bytes(skb, offset, from, len, flags) - store bytes into packet
+ * @skb: pointer to skb
+ * @offset: offset within packet from skb->mac_header
+ * @from: pointer where to copy bytes from
+ * @len: number of bytes to store into packet
+ * @flags: bit 0 - if true, recompute skb->csum
+ * other bits - reserved
+ * Return: 0 on success
+ */
+ BPF_FUNC_skb_store_bytes,
+
+ /**
+ * l3_csum_replace(skb, offset, from, to, flags) - recompute IP checksum
+ * @skb: pointer to skb
+ * @offset: offset within packet where IP checksum is located
+ * @from: old value of header field
+ * @to: new value of header field
+ * @flags: bits 0-3 - size of header field
+ * other bits - reserved
+ * Return: 0 on success
+ */
+ BPF_FUNC_l3_csum_replace,
+
+ /**
+ * l4_csum_replace(skb, offset, from, to, flags) - recompute TCP/UDP checksum
+ * @skb: pointer to skb
+ * @offset: offset within packet where TCP/UDP checksum is located
+ * @from: old value of header field
+ * @to: new value of header field
+ * @flags: bits 0-3 - size of header field
+ * bit 4 - is pseudo header
+ * other bits - reserved
+ * Return: 0 on success
+ */
+ BPF_FUNC_l4_csum_replace,
+
+ /**
+ * bpf_tail_call(ctx, prog_array_map, index) - jump into another BPF program
+ * @ctx: context pointer passed to next program
+ * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
+ * @index: index inside array that selects specific program to run
+ * Return: 0 on success
+ */
+ BPF_FUNC_tail_call,
+
+ /**
+ * bpf_clone_redirect(skb, ifindex, flags) - redirect to another netdev
+ * @skb: pointer to skb
+ * @ifindex: ifindex of the net device
+ * @flags: bit 0 - if set, redirect to ingress instead of egress
+ * other bits - reserved
+ * Return: 0 on success
+ */
+ BPF_FUNC_clone_redirect,
+
+ /**
+ * u64 bpf_get_current_pid_tgid(void)
+ * Return: current->tgid << 32 | current->pid
+ */
+ BPF_FUNC_get_current_pid_tgid,
+
+ /**
+ * u64 bpf_get_current_uid_gid(void)
+ * Return: current_gid << 32 | current_uid
+ */
+ BPF_FUNC_get_current_uid_gid,
+
+ /**
+ * bpf_get_current_comm(char *buf, int size_of_buf)
+ * stores current->comm into buf
+ * Return: 0 on success
+ */
+ BPF_FUNC_get_current_comm,
+
+ /**
+ * bpf_get_cgroup_classid(skb) - retrieve a proc's classid
+ * @skb: pointer to skb
+ * Return: classid if != 0
+ */
+ BPF_FUNC_get_cgroup_classid,
+ BPF_FUNC_skb_vlan_push, /* bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) */
+ BPF_FUNC_skb_vlan_pop, /* bpf_skb_vlan_pop(skb) */
+
+ /**
+ * bpf_skb_[gs]et_tunnel_key(skb, key, size, flags)
+ * retrieve or populate tunnel metadata
+ * @skb: pointer to skb
+ * @key: pointer to 'struct bpf_tunnel_key'
+ * @size: size of 'struct bpf_tunnel_key'
+ * @flags: room for future extensions
+ * Retrun: 0 on success
+ */
+ BPF_FUNC_skb_get_tunnel_key,
+ BPF_FUNC_skb_set_tunnel_key,
+ BPF_FUNC_perf_event_read, /* u64 bpf_perf_event_read(&map, index) */
+ /**
+ * bpf_redirect(ifindex, flags) - redirect to another netdev
+ * @ifindex: ifindex of the net device
+ * @flags: bit 0 - if set, redirect to ingress instead of egress
+ * other bits - reserved
+ * Return: TC_ACT_REDIRECT
+ */
+ BPF_FUNC_redirect,
+
+ /**
+ * bpf_get_route_realm(skb) - retrieve a dst's tclassid
+ * @skb: pointer to skb
+ * Return: realm if != 0
+ */
+ BPF_FUNC_get_route_realm,
+
+ /**
+ * bpf_perf_event_output(ctx, map, index, data, size) - output perf raw sample
+ * @ctx: struct pt_regs*
+ * @map: pointer to perf_event_array map
+ * @index: index of event in the map
+ * @data: data on stack to be output as raw data
+ * @size: size of data
+ * Return: 0 on success
+ */
+ BPF_FUNC_perf_event_output,
+ BPF_FUNC_skb_load_bytes,
+ __BPF_FUNC_MAX_ID,
+};
+
+/* All flags used by eBPF helper functions, placed here. */
+
+/* BPF_FUNC_skb_store_bytes flags. */
+#define BPF_F_RECOMPUTE_CSUM (1ULL << 0)
+
+/* 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)
+
+/* 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)
+
+/* 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;
+};
+
+struct bpf_tunnel_key {
+ __u32 tunnel_id;
+ union {
+ __u32 remote_ipv4;
+ __u32 remote_ipv6[4];
+ };
+ __u8 tunnel_tos;
+ __u8 tunnel_ttl;
+};
+
+#endif /* __LINUX_BPF_H__ */
diff --git a/iproute2/include/linux/bpf_common.h b/iproute2/include/linux/bpf_common.h
new file mode 100644
index 0000000..afe7433
--- /dev/null
+++ b/iproute2/include/linux/bpf_common.h
@@ -0,0 +1,55 @@
+#ifndef __LINUX_BPF_COMMON_H__
+#define __LINUX_BPF_COMMON_H__
+
+/* Instruction classes */
+#define BPF_CLASS(code) ((code) & 0x07)
+#define BPF_LD 0x00
+#define BPF_LDX 0x01
+#define BPF_ST 0x02
+#define BPF_STX 0x03
+#define BPF_ALU 0x04
+#define BPF_JMP 0x05
+#define BPF_RET 0x06
+#define BPF_MISC 0x07
+
+/* ld/ldx fields */
+#define BPF_SIZE(code) ((code) & 0x18)
+#define BPF_W 0x00
+#define BPF_H 0x08
+#define BPF_B 0x10
+#define BPF_MODE(code) ((code) & 0xe0)
+#define BPF_IMM 0x00
+#define BPF_ABS 0x20
+#define BPF_IND 0x40
+#define BPF_MEM 0x60
+#define BPF_LEN 0x80
+#define BPF_MSH 0xa0
+
+/* alu/jmp fields */
+#define BPF_OP(code) ((code) & 0xf0)
+#define BPF_ADD 0x00
+#define BPF_SUB 0x10
+#define BPF_MUL 0x20
+#define BPF_DIV 0x30
+#define BPF_OR 0x40
+#define BPF_AND 0x50
+#define BPF_LSH 0x60
+#define BPF_RSH 0x70
+#define BPF_NEG 0x80
+#define BPF_MOD 0x90
+#define BPF_XOR 0xa0
+
+#define BPF_JA 0x00
+#define BPF_JEQ 0x10
+#define BPF_JGT 0x20
+#define BPF_JGE 0x30
+#define BPF_JSET 0x40
+#define BPF_SRC(code) ((code) & 0x08)
+#define BPF_K 0x00
+#define BPF_X 0x08
+
+#ifndef BPF_MAXINSNS
+#define BPF_MAXINSNS 4096
+#endif
+
+#endif /* __LINUX_BPF_COMMON_H__ */
diff --git a/iproute2/include/linux/can.h b/iproute2/include/linux/can.h
new file mode 100644
index 0000000..4af39b0
--- /dev/null
+++ b/iproute2/include/linux/can.h
@@ -0,0 +1,200 @@
+/*
+ * linux/can.h
+ *
+ * Definitions for CAN network layer (socket addr / CAN frame / CAN filter)
+ *
+ * Authors: Oliver Hartkopp <oliver.hartkopp@volkswagen.de>
+ * Urs Thuermann <urs.thuermann@volkswagen.de>
+ * Copyright (c) 2002-2007 Volkswagen Group Electronic Research
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of Volkswagen nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ *
+ * Alternatively, provided that this notice is retained in full, this
+ * software may be distributed under the terms of the GNU General
+ * Public License ("GPL") version 2, in which case the provisions of the
+ * GPL apply INSTEAD OF those given above.
+ *
+ * The provided data structures and external interfaces from this code
+ * are not restricted to be used by modules with a GPL compatible license.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
+ */
+
+#ifndef _CAN_H
+#define _CAN_H
+
+#include <linux/types.h>
+#include <linux/socket.h>
+
+/* controller area network (CAN) kernel definitions */
+
+/* special address description flags for the CAN_ID */
+#define CAN_EFF_FLAG 0x80000000U /* EFF/SFF is set in the MSB */
+#define CAN_RTR_FLAG 0x40000000U /* remote transmission request */
+#define CAN_ERR_FLAG 0x20000000U /* error message frame */
+
+/* valid bits in CAN ID for frame formats */
+#define CAN_SFF_MASK 0x000007FFU /* standard frame format (SFF) */
+#define CAN_EFF_MASK 0x1FFFFFFFU /* extended frame format (EFF) */
+#define CAN_ERR_MASK 0x1FFFFFFFU /* omit EFF, RTR, ERR flags */
+
+/*
+ * Controller Area Network Identifier structure
+ *
+ * bit 0-28 : CAN identifier (11/29 bit)
+ * bit 29 : error message frame flag (0 = data frame, 1 = error message)
+ * bit 30 : remote transmission request flag (1 = rtr frame)
+ * bit 31 : frame format flag (0 = standard 11 bit, 1 = extended 29 bit)
+ */
+typedef __u32 canid_t;
+
+#define CAN_SFF_ID_BITS 11
+#define CAN_EFF_ID_BITS 29
+
+/*
+ * Controller Area Network Error Message Frame Mask structure
+ *
+ * bit 0-28 : error class mask (see include/linux/can/error.h)
+ * bit 29-31 : set to zero
+ */
+typedef __u32 can_err_mask_t;
+
+/* CAN payload length and DLC definitions according to ISO 11898-1 */
+#define CAN_MAX_DLC 8
+#define CAN_MAX_DLEN 8
+
+/* CAN FD payload length and DLC definitions according to ISO 11898-7 */
+#define CANFD_MAX_DLC 15
+#define CANFD_MAX_DLEN 64
+
+/**
+ * struct can_frame - basic CAN frame structure
+ * @can_id: CAN ID of the frame and CAN_*_FLAG flags, see canid_t definition
+ * @can_dlc: frame payload length in byte (0 .. 8) aka data length code
+ * N.B. the DLC field from ISO 11898-1 Chapter 8.4.2.3 has a 1:1
+ * mapping of the 'data length code' to the real payload length
+ * @__pad: padding
+ * @__res0: reserved / padding
+ * @__res1: reserved / padding
+ * @data: CAN frame payload (up to 8 byte)
+ */
+struct can_frame {
+ canid_t can_id; /* 32 bit CAN_ID + EFF/RTR/ERR flags */
+ __u8 can_dlc; /* frame payload length in byte (0 .. CAN_MAX_DLEN) */
+ __u8 __pad; /* padding */
+ __u8 __res0; /* reserved / padding */
+ __u8 __res1; /* reserved / padding */
+ __u8 data[CAN_MAX_DLEN] __attribute__((aligned(8)));
+};
+
+/*
+ * defined bits for canfd_frame.flags
+ *
+ * The use of struct canfd_frame implies the Extended Data Length (EDL) bit to
+ * be set in the CAN frame bitstream on the wire. The EDL bit switch turns
+ * the CAN controllers bitstream processor into the CAN FD mode which creates
+ * two new options within the CAN FD frame specification:
+ *
+ * Bit Rate Switch - to indicate a second bitrate is/was used for the payload
+ * Error State Indicator - represents the error state of the transmitting node
+ *
+ * As the CANFD_ESI bit is internally generated by the transmitting CAN
+ * controller only the CANFD_BRS bit is relevant for real CAN controllers when
+ * building a CAN FD frame for transmission. Setting the CANFD_ESI bit can make
+ * sense for virtual CAN interfaces to test applications with echoed frames.
+ */
+#define CANFD_BRS 0x01 /* bit rate switch (second bitrate for payload data) */
+#define CANFD_ESI 0x02 /* error state indicator of the transmitting node */
+
+/**
+ * struct canfd_frame - CAN flexible data rate frame structure
+ * @can_id: CAN ID of the frame and CAN_*_FLAG flags, see canid_t definition
+ * @len: frame payload length in byte (0 .. CANFD_MAX_DLEN)
+ * @flags: additional flags for CAN FD
+ * @__res0: reserved / padding
+ * @__res1: reserved / padding
+ * @data: CAN FD frame payload (up to CANFD_MAX_DLEN byte)
+ */
+struct canfd_frame {
+ canid_t can_id; /* 32 bit CAN_ID + EFF/RTR/ERR flags */
+ __u8 len; /* frame payload length in byte */
+ __u8 flags; /* additional flags for CAN FD */
+ __u8 __res0; /* reserved / padding */
+ __u8 __res1; /* reserved / padding */
+ __u8 data[CANFD_MAX_DLEN] __attribute__((aligned(8)));
+};
+
+#define CAN_MTU (sizeof(struct can_frame))
+#define CANFD_MTU (sizeof(struct canfd_frame))
+
+/* particular protocols of the protocol family PF_CAN */
+#define CAN_RAW 1 /* RAW sockets */
+#define CAN_BCM 2 /* Broadcast Manager */
+#define CAN_TP16 3 /* VAG Transport Protocol v1.6 */
+#define CAN_TP20 4 /* VAG Transport Protocol v2.0 */
+#define CAN_MCNET 5 /* Bosch MCNet */
+#define CAN_ISOTP 6 /* ISO 15765-2 Transport Protocol */
+#define CAN_NPROTO 7
+
+#define SOL_CAN_BASE 100
+
+/**
+ * struct sockaddr_can - the sockaddr structure for CAN sockets
+ * @can_family: address family number AF_CAN.
+ * @can_ifindex: CAN network interface index.
+ * @can_addr: protocol specific address information
+ */
+struct sockaddr_can {
+ __kernel_sa_family_t can_family;
+ int can_ifindex;
+ union {
+ /* transport protocol class address information (e.g. ISOTP) */
+ struct { canid_t rx_id, tx_id; } tp;
+
+ /* reserved for future CAN protocols address information */
+ } can_addr;
+};
+
+/**
+ * struct can_filter - CAN ID based filter in can_register().
+ * @can_id: relevant bits of CAN ID which are not masked out.
+ * @can_mask: CAN mask (see description)
+ *
+ * Description:
+ * A filter matches, when
+ *
+ * <received_can_id> & mask == can_id & mask
+ *
+ * The filter can be inverted (CAN_INV_FILTER bit set in can_id) or it can
+ * filter for error message frames (CAN_ERR_FLAG bit set in mask).
+ */
+struct can_filter {
+ canid_t can_id;
+ canid_t can_mask;
+};
+
+#define CAN_INV_FILTER 0x20000000U /* to be set in can_filter.can_id */
+
+#endif /* !_UAPI_CAN_H */
diff --git a/iproute2/include/linux/can/netlink.h b/iproute2/include/linux/can/netlink.h
new file mode 100644
index 0000000..6d4ec2a
--- /dev/null
+++ b/iproute2/include/linux/can/netlink.h
@@ -0,0 +1,135 @@
+/*
+ * linux/can/netlink.h
+ *
+ * Definitions for the CAN netlink interface
+ *
+ * Copyright (c) 2009 Wolfgang Grandegger <wg@grandegger.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the version 2 of the GNU General Public License
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CAN_NETLINK_H
+#define _CAN_NETLINK_H
+
+#include <linux/types.h>
+
+/*
+ * CAN bit-timing parameters
+ *
+ * For further information, please read chapter "8 BIT TIMING
+ * REQUIREMENTS" of the "Bosch CAN Specification version 2.0"
+ * at http://www.semiconductors.bosch.de/pdf/can2spec.pdf.
+ */
+struct can_bittiming {
+ __u32 bitrate; /* Bit-rate in bits/second */
+ __u32 sample_point; /* Sample point in one-tenth of a percent */
+ __u32 tq; /* Time quanta (TQ) in nanoseconds */
+ __u32 prop_seg; /* Propagation segment in TQs */
+ __u32 phase_seg1; /* Phase buffer segment 1 in TQs */
+ __u32 phase_seg2; /* Phase buffer segment 2 in TQs */
+ __u32 sjw; /* Synchronisation jump width in TQs */
+ __u32 brp; /* Bit-rate prescaler */
+};
+
+/*
+ * CAN harware-dependent bit-timing constant
+ *
+ * Used for calculating and checking bit-timing parameters
+ */
+struct can_bittiming_const {
+ char name[16]; /* Name of the CAN controller hardware */
+ __u32 tseg1_min; /* Time segement 1 = prop_seg + phase_seg1 */
+ __u32 tseg1_max;
+ __u32 tseg2_min; /* Time segement 2 = phase_seg2 */
+ __u32 tseg2_max;
+ __u32 sjw_max; /* Synchronisation jump width */
+ __u32 brp_min; /* Bit-rate prescaler */
+ __u32 brp_max;
+ __u32 brp_inc;
+};
+
+/*
+ * CAN clock parameters
+ */
+struct can_clock {
+ __u32 freq; /* CAN system clock frequency in Hz */
+};
+
+/*
+ * CAN operational and error states
+ */
+enum can_state {
+ CAN_STATE_ERROR_ACTIVE = 0, /* RX/TX error count < 96 */
+ CAN_STATE_ERROR_WARNING, /* RX/TX error count < 128 */
+ CAN_STATE_ERROR_PASSIVE, /* RX/TX error count < 256 */
+ CAN_STATE_BUS_OFF, /* RX/TX error count >= 256 */
+ CAN_STATE_STOPPED, /* Device is stopped */
+ CAN_STATE_SLEEPING, /* Device is sleeping */
+ CAN_STATE_MAX
+};
+
+/*
+ * CAN bus error counters
+ */
+struct can_berr_counter {
+ __u16 txerr;
+ __u16 rxerr;
+};
+
+/*
+ * CAN controller mode
+ */
+struct can_ctrlmode {
+ __u32 mask;
+ __u32 flags;
+};
+
+#define CAN_CTRLMODE_LOOPBACK 0x01 /* Loopback mode */
+#define CAN_CTRLMODE_LISTENONLY 0x02 /* Listen-only mode */
+#define CAN_CTRLMODE_3_SAMPLES 0x04 /* Triple sampling mode */
+#define CAN_CTRLMODE_ONE_SHOT 0x08 /* One-Shot mode */
+#define CAN_CTRLMODE_BERR_REPORTING 0x10 /* Bus-error reporting */
+#define CAN_CTRLMODE_FD 0x20 /* CAN FD mode */
+#define CAN_CTRLMODE_PRESUME_ACK 0x40 /* Ignore missing CAN ACKs */
+#define CAN_CTRLMODE_FD_NON_ISO 0x80 /* CAN FD in non-ISO mode */
+
+/*
+ * CAN device statistics
+ */
+struct can_device_stats {
+ __u32 bus_error; /* Bus errors */
+ __u32 error_warning; /* Changes to error warning state */
+ __u32 error_passive; /* Changes to error passive state */
+ __u32 bus_off; /* Changes to bus off state */
+ __u32 arbitration_lost; /* Arbitration lost errors */
+ __u32 restarts; /* CAN controller re-starts */
+};
+
+/*
+ * CAN netlink interface
+ */
+enum {
+ IFLA_CAN_UNSPEC,
+ IFLA_CAN_BITTIMING,
+ IFLA_CAN_BITTIMING_CONST,
+ IFLA_CAN_CLOCK,
+ IFLA_CAN_STATE,
+ IFLA_CAN_CTRLMODE,
+ IFLA_CAN_RESTART_MS,
+ IFLA_CAN_RESTART,
+ IFLA_CAN_BERR_COUNTER,
+ IFLA_CAN_DATA_BITTIMING,
+ IFLA_CAN_DATA_BITTIMING_CONST,
+ __IFLA_CAN_MAX
+};
+
+#define IFLA_CAN_MAX (__IFLA_CAN_MAX - 1)
+
+#endif /* !_UAPI_CAN_NETLINK_H */
diff --git a/iproute2/include/linux/fib_rules.h b/iproute2/include/linux/fib_rules.h
new file mode 100644
index 0000000..6dcde64
--- /dev/null
+++ b/iproute2/include/linux/fib_rules.h
@@ -0,0 +1,74 @@
+#ifndef __LINUX_FIB_RULES_H
+#define __LINUX_FIB_RULES_H
+
+#include <linux/types.h>
+#include <linux/rtnetlink.h>
+
+/* rule is permanent, and cannot be deleted */
+#define FIB_RULE_PERMANENT 0x00000001
+#define FIB_RULE_INVERT 0x00000002
+#define FIB_RULE_UNRESOLVED 0x00000004
+#define FIB_RULE_IIF_DETACHED 0x00000008
+#define FIB_RULE_DEV_DETACHED FIB_RULE_IIF_DETACHED
+#define FIB_RULE_OIF_DETACHED 0x00000010
+
+/* try to find source address in routing lookups */
+#define FIB_RULE_FIND_SADDR 0x00010000
+
+struct fib_rule_hdr {
+ __u8 family;
+ __u8 dst_len;
+ __u8 src_len;
+ __u8 tos;
+
+ __u8 table;
+ __u8 res1; /* reserved */
+ __u8 res2; /* reserved */
+ __u8 action;
+
+ __u32 flags;
+};
+
+enum {
+ FRA_UNSPEC,
+ FRA_DST, /* destination address */
+ FRA_SRC, /* source address */
+ FRA_IIFNAME, /* interface name */
+#define FRA_IFNAME FRA_IIFNAME
+ FRA_GOTO, /* target to jump to (FR_ACT_GOTO) */
+ FRA_UNUSED2,
+ FRA_PRIORITY, /* priority/preference */
+ FRA_UNUSED3,
+ FRA_UNUSED4,
+ FRA_UNUSED5,
+ FRA_FWMARK, /* mark */
+ FRA_FLOW, /* flow/class id */
+ FRA_TUN_ID,
+ FRA_SUPPRESS_IFGROUP,
+ FRA_SUPPRESS_PREFIXLEN,
+ FRA_TABLE, /* Extended table id */
+ FRA_FWMASK, /* mask for netfilter mark */
+ FRA_OIFNAME,
+ FRA_UID_START,
+ FRA_UID_END,
+ __FRA_MAX
+};
+
+#define FRA_MAX (__FRA_MAX - 1)
+
+enum {
+ FR_ACT_UNSPEC,
+ FR_ACT_TO_TBL, /* Pass to fixed table */
+ FR_ACT_GOTO, /* Jump to another rule */
+ FR_ACT_NOP, /* No operation */
+ FR_ACT_RES3,
+ FR_ACT_RES4,
+ FR_ACT_BLACKHOLE, /* Drop without notification */
+ FR_ACT_UNREACHABLE, /* Drop with ENETUNREACH */
+ FR_ACT_PROHIBIT, /* Drop with EACCES */
+ __FR_ACT_MAX,
+};
+
+#define FR_ACT_MAX (__FR_ACT_MAX - 1)
+
+#endif
diff --git a/iproute2/include/linux/filter.h b/iproute2/include/linux/filter.h
new file mode 100644
index 0000000..e4f2f74
--- /dev/null
+++ b/iproute2/include/linux/filter.h
@@ -0,0 +1,89 @@
+/*
+ * Linux Socket Filter Data Structures
+ */
+
+#ifndef __LINUX_FILTER_H__
+#define __LINUX_FILTER_H__
+
+
+#include <linux/types.h>
+#include <linux/bpf_common.h>
+
+/*
+ * Current version of the filter code architecture.
+ */
+#define BPF_MAJOR_VERSION 1
+#define BPF_MINOR_VERSION 1
+
+/*
+ * Try and keep these values and structures similar to BSD, especially
+ * the BPF code definitions which need to match so you can share filters
+ */
+
+struct sock_filter { /* Filter block */
+ __u16 code; /* Actual filter code */
+ __u8 jt; /* Jump true */
+ __u8 jf; /* Jump false */
+ __u32 k; /* Generic multiuse field */
+};
+
+struct sock_fprog { /* Required for SO_ATTACH_FILTER. */
+ unsigned short len; /* Number of filter blocks */
+ struct sock_filter *filter;
+};
+
+/* ret - BPF_K and BPF_X also apply */
+#define BPF_RVAL(code) ((code) & 0x18)
+#define BPF_A 0x10
+
+/* misc */
+#define BPF_MISCOP(code) ((code) & 0xf8)
+#define BPF_TAX 0x00
+#define BPF_TXA 0x80
+
+/*
+ * Macros for filter block array initializers.
+ */
+#ifndef BPF_STMT
+#define BPF_STMT(code, k) { (unsigned short)(code), 0, 0, k }
+#endif
+#ifndef BPF_JUMP
+#define BPF_JUMP(code, k, jt, jf) { (unsigned short)(code), jt, jf, k }
+#endif
+
+/*
+ * Number of scratch memory words for: BPF_ST and BPF_STX
+ */
+#define BPF_MEMWORDS 16
+
+/* RATIONALE. Negative offsets are invalid in BPF.
+ We use them to reference ancillary data.
+ Unlike introduction new instructions, it does not break
+ existing compilers/optimizers.
+ */
+#define SKF_AD_OFF (-0x1000)
+#define SKF_AD_PROTOCOL 0
+#define SKF_AD_PKTTYPE 4
+#define SKF_AD_IFINDEX 8
+#define SKF_AD_NLATTR 12
+#define SKF_AD_NLATTR_NEST 16
+#define SKF_AD_MARK 20
+#define SKF_AD_QUEUE 24
+#define SKF_AD_HATYPE 28
+#define SKF_AD_RXHASH 32
+#define SKF_AD_CPU 36
+#define SKF_AD_ALU_XOR_X 40
+#define SKF_AD_VLAN_TAG 44
+#define SKF_AD_VLAN_TAG_PRESENT 48
+#define SKF_AD_PAY_OFFSET 52
+#define SKF_AD_RANDOM 56
+#define SKF_AD_VLAN_TPID 60
+#define SKF_AD_MAX 64
+
+#define SKF_NET_OFF (-0x100000)
+#define SKF_LL_OFF (-0x200000)
+
+#define BPF_NET_OFF SKF_NET_OFF
+#define BPF_LL_OFF SKF_LL_OFF
+
+#endif /* __LINUX_FILTER_H__ */
diff --git a/iproute2/include/linux/fou.h b/iproute2/include/linux/fou.h
new file mode 100644
index 0000000..744c323
--- /dev/null
+++ b/iproute2/include/linux/fou.h
@@ -0,0 +1,41 @@
+/* fou.h - FOU Interface */
+
+#ifndef _LINUX_FOU_H
+#define _LINUX_FOU_H
+
+/* NETLINK_GENERIC related info
+ */
+#define FOU_GENL_NAME "fou"
+#define FOU_GENL_VERSION 0x1
+
+enum {
+ FOU_ATTR_UNSPEC,
+ FOU_ATTR_PORT, /* u16 */
+ FOU_ATTR_AF, /* u8 */
+ FOU_ATTR_IPPROTO, /* u8 */
+ FOU_ATTR_TYPE, /* u8 */
+ FOU_ATTR_REMCSUM_NOPARTIAL, /* flag */
+
+ __FOU_ATTR_MAX,
+};
+
+#define FOU_ATTR_MAX (__FOU_ATTR_MAX - 1)
+
+enum {
+ FOU_CMD_UNSPEC,
+ FOU_CMD_ADD,
+ FOU_CMD_DEL,
+ FOU_CMD_GET,
+
+ __FOU_CMD_MAX,
+};
+
+enum {
+ FOU_ENCAP_UNSPEC,
+ FOU_ENCAP_DIRECT,
+ FOU_ENCAP_GUE,
+};
+
+#define FOU_CMD_MAX (__FOU_CMD_MAX - 1)
+
+#endif /* _LINUX_FOU_H */
diff --git a/iproute2/include/linux/gen_stats.h b/iproute2/include/linux/gen_stats.h
new file mode 100644
index 0000000..6487317
--- /dev/null
+++ b/iproute2/include/linux/gen_stats.h
@@ -0,0 +1,78 @@
+#ifndef __LINUX_GEN_STATS_H
+#define __LINUX_GEN_STATS_H
+
+#include <linux/types.h>
+
+enum {
+ TCA_STATS_UNSPEC,
+ TCA_STATS_BASIC,
+ TCA_STATS_RATE_EST,
+ TCA_STATS_QUEUE,
+ TCA_STATS_APP,
+ TCA_STATS_RATE_EST64,
+ __TCA_STATS_MAX,
+};
+#define TCA_STATS_MAX (__TCA_STATS_MAX - 1)
+
+/**
+ * struct gnet_stats_basic - byte/packet throughput statistics
+ * @bytes: number of seen bytes
+ * @packets: number of seen packets
+ */
+struct gnet_stats_basic {
+ __u64 bytes;
+ __u32 packets;
+};
+struct gnet_stats_basic_packed {
+ __u64 bytes;
+ __u32 packets;
+} __attribute__ ((packed));
+
+/**
+ * struct gnet_stats_rate_est - rate estimator
+ * @bps: current byte rate
+ * @pps: current packet rate
+ */
+struct gnet_stats_rate_est {
+ __u32 bps;
+ __u32 pps;
+};
+
+/**
+ * struct gnet_stats_rate_est64 - rate estimator
+ * @bps: current byte rate
+ * @pps: current packet rate
+ */
+struct gnet_stats_rate_est64 {
+ __u64 bps;
+ __u64 pps;
+};
+
+/**
+ * struct gnet_stats_queue - queuing statistics
+ * @qlen: queue length
+ * @backlog: backlog size of queue
+ * @drops: number of dropped packets
+ * @requeues: number of requeues
+ * @overlimits: number of enqueues over the limit
+ */
+struct gnet_stats_queue {
+ __u32 qlen;
+ __u32 backlog;
+ __u32 drops;
+ __u32 requeues;
+ __u32 overlimits;
+};
+
+/**
+ * struct gnet_estimator - rate estimator configuration
+ * @interval: sampling period
+ * @ewma_log: the log of measurement window weight
+ */
+struct gnet_estimator {
+ signed char interval;
+ unsigned char ewma_log;
+};
+
+
+#endif /* __LINUX_GEN_STATS_H */
diff --git a/iproute2/include/linux/genetlink.h b/iproute2/include/linux/genetlink.h
new file mode 100644
index 0000000..8a1d500
--- /dev/null
+++ b/iproute2/include/linux/genetlink.h
@@ -0,0 +1,86 @@
+#ifndef __LINUX_GENERIC_NETLINK_H
+#define __LINUX_GENERIC_NETLINK_H
+
+#include <linux/types.h>
+#include <linux/netlink.h>
+
+#define GENL_NAMSIZ 16 /* length of family name */
+
+#define GENL_MIN_ID NLMSG_MIN_TYPE
+#define GENL_MAX_ID 1023
+
+struct genlmsghdr {
+ __u8 cmd;
+ __u8 version;
+ __u16 reserved;
+};
+
+#define GENL_HDRLEN NLMSG_ALIGN(sizeof(struct genlmsghdr))
+
+#define GENL_ADMIN_PERM 0x01
+#define GENL_CMD_CAP_DO 0x02
+#define GENL_CMD_CAP_DUMP 0x04
+#define GENL_CMD_CAP_HASPOL 0x08
+
+/*
+ * List of reserved static generic netlink identifiers:
+ */
+#define GENL_ID_GENERATE 0
+#define GENL_ID_CTRL NLMSG_MIN_TYPE
+#define GENL_ID_VFS_DQUOT (NLMSG_MIN_TYPE + 1)
+#define GENL_ID_PMCRAID (NLMSG_MIN_TYPE + 2)
+
+/**************************************************************************
+ * Controller
+ **************************************************************************/
+
+enum {
+ CTRL_CMD_UNSPEC,
+ CTRL_CMD_NEWFAMILY,
+ CTRL_CMD_DELFAMILY,
+ CTRL_CMD_GETFAMILY,
+ CTRL_CMD_NEWOPS,
+ CTRL_CMD_DELOPS,
+ CTRL_CMD_GETOPS,
+ CTRL_CMD_NEWMCAST_GRP,
+ CTRL_CMD_DELMCAST_GRP,
+ CTRL_CMD_GETMCAST_GRP, /* unused */
+ __CTRL_CMD_MAX,
+};
+
+#define CTRL_CMD_MAX (__CTRL_CMD_MAX - 1)
+
+enum {
+ CTRL_ATTR_UNSPEC,
+ CTRL_ATTR_FAMILY_ID,
+ CTRL_ATTR_FAMILY_NAME,
+ CTRL_ATTR_VERSION,
+ CTRL_ATTR_HDRSIZE,
+ CTRL_ATTR_MAXATTR,
+ CTRL_ATTR_OPS,
+ CTRL_ATTR_MCAST_GROUPS,
+ __CTRL_ATTR_MAX,
+};
+
+#define CTRL_ATTR_MAX (__CTRL_ATTR_MAX - 1)
+
+enum {
+ CTRL_ATTR_OP_UNSPEC,
+ CTRL_ATTR_OP_ID,
+ CTRL_ATTR_OP_FLAGS,
+ __CTRL_ATTR_OP_MAX,
+};
+
+#define CTRL_ATTR_OP_MAX (__CTRL_ATTR_OP_MAX - 1)
+
+enum {
+ CTRL_ATTR_MCAST_GRP_UNSPEC,
+ CTRL_ATTR_MCAST_GRP_NAME,
+ CTRL_ATTR_MCAST_GRP_ID,
+ __CTRL_ATTR_MCAST_GRP_MAX,
+};
+
+#define CTRL_ATTR_MCAST_GRP_MAX (__CTRL_ATTR_MCAST_GRP_MAX - 1)
+
+
+#endif /* __LINUX_GENERIC_NETLINK_H */
diff --git a/iproute2/include/linux/hdlc/ioctl.h b/iproute2/include/linux/hdlc/ioctl.h
new file mode 100644
index 0000000..04bc027
--- /dev/null
+++ b/iproute2/include/linux/hdlc/ioctl.h
@@ -0,0 +1,84 @@
+#ifndef __HDLC_IOCTL_H__
+#define __HDLC_IOCTL_H__
+
+
+#define GENERIC_HDLC_VERSION 4 /* For synchronization with sethdlc utility */
+
+#define CLOCK_DEFAULT 0 /* Default setting */
+#define CLOCK_EXT 1 /* External TX and RX clock - DTE */
+#define CLOCK_INT 2 /* Internal TX and RX clock - DCE */
+#define CLOCK_TXINT 3 /* Internal TX and external RX clock */
+#define CLOCK_TXFROMRX 4 /* TX clock derived from external RX clock */
+
+
+#define ENCODING_DEFAULT 0 /* Default setting */
+#define ENCODING_NRZ 1
+#define ENCODING_NRZI 2
+#define ENCODING_FM_MARK 3
+#define ENCODING_FM_SPACE 4
+#define ENCODING_MANCHESTER 5
+
+
+#define PARITY_DEFAULT 0 /* Default setting */
+#define PARITY_NONE 1 /* No parity */
+#define PARITY_CRC16_PR0 2 /* CRC16, initial value 0x0000 */
+#define PARITY_CRC16_PR1 3 /* CRC16, initial value 0xFFFF */
+#define PARITY_CRC16_PR0_CCITT 4 /* CRC16, initial 0x0000, ITU-T version */
+#define PARITY_CRC16_PR1_CCITT 5 /* CRC16, initial 0xFFFF, ITU-T version */
+#define PARITY_CRC32_PR0_CCITT 6 /* CRC32, initial value 0x00000000 */
+#define PARITY_CRC32_PR1_CCITT 7 /* CRC32, initial value 0xFFFFFFFF */
+
+#define LMI_DEFAULT 0 /* Default setting */
+#define LMI_NONE 1 /* No LMI, all PVCs are static */
+#define LMI_ANSI 2 /* ANSI Annex D */
+#define LMI_CCITT 3 /* ITU-T Annex A */
+#define LMI_CISCO 4 /* The "original" LMI, aka Gang of Four */
+
+#ifndef __ASSEMBLY__
+
+typedef struct {
+ unsigned int clock_rate; /* bits per second */
+ unsigned int clock_type; /* internal, external, TX-internal etc. */
+ unsigned short loopback;
+} sync_serial_settings; /* V.35, V.24, X.21 */
+
+typedef struct {
+ unsigned int clock_rate; /* bits per second */
+ unsigned int clock_type; /* internal, external, TX-internal etc. */
+ unsigned short loopback;
+ unsigned int slot_map;
+} te1_settings; /* T1, E1 */
+
+typedef struct {
+ unsigned short encoding;
+ unsigned short parity;
+} raw_hdlc_proto;
+
+typedef struct {
+ unsigned int t391;
+ unsigned int t392;
+ unsigned int n391;
+ unsigned int n392;
+ unsigned int n393;
+ unsigned short lmi;
+ unsigned short dce; /* 1 for DCE (network side) operation */
+} fr_proto;
+
+typedef struct {
+ unsigned int dlci;
+} fr_proto_pvc; /* for creating/deleting FR PVCs */
+
+typedef struct {
+ unsigned int dlci;
+ char master[IFNAMSIZ]; /* Name of master FRAD device */
+}fr_proto_pvc_info; /* for returning PVC information only */
+
+typedef struct {
+ unsigned int interval;
+ unsigned int timeout;
+} cisco_proto;
+
+/* PPP doesn't need any info now - supply length = 0 to ioctl */
+
+#endif /* __ASSEMBLY__ */
+#endif /* __HDLC_IOCTL_H__ */
diff --git a/iproute2/include/linux/if.h b/iproute2/include/linux/if.h
new file mode 100644
index 0000000..a55a9e0
--- /dev/null
+++ b/iproute2/include/linux/if.h
@@ -0,0 +1,262 @@
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * Global definitions for the INET interface module.
+ *
+ * Version: @(#)if.h 1.0.2 04/18/93
+ *
+ * Authors: Original taken from Berkeley UNIX 4.3, (c) UCB 1982-1988
+ * Ross Biro
+ * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _LINUX_IF_H
+#define _LINUX_IF_H
+
+#include <linux/types.h> /* for "__kernel_caddr_t" et al */
+#include <linux/socket.h> /* for "struct sockaddr" et al */
+ /* for "__user" et al */
+
+#define IFNAMSIZ 16
+#define IFALIASZ 256
+#include <linux/hdlc/ioctl.h>
+
+/**
+ * enum net_device_flags - &struct net_device flags
+ *
+ * These are the &struct net_device flags, they can be set by drivers, the
+ * kernel and some can be triggered by userspace. Userspace can query and
+ * set these flags using userspace utilities but there is also a sysfs
+ * entry available for all dev flags which can be queried and set. These flags
+ * are shared for all types of net_devices. The sysfs entries are available
+ * via /sys/class/net/<dev>/flags. Flags which can be toggled through sysfs
+ * are annotated below, note that only a few flags can be toggled and some
+ * other flags are always always preserved from the original net_device flags
+ * even if you try to set them via sysfs. Flags which are always preserved
+ * are kept under the flag grouping @IFF_VOLATILE. Flags which are __volatile__
+ * are annotated below as such.
+ *
+ * You should have a pretty good reason to be extending these flags.
+ *
+ * @IFF_UP: interface is up. Can be toggled through sysfs.
+ * @IFF_BROADCAST: broadcast address valid. Volatile.
+ * @IFF_DEBUG: turn on debugging. Can be toggled through sysfs.
+ * @IFF_LOOPBACK: is a loopback net. Volatile.
+ * @IFF_POINTOPOINT: interface is has p-p link. Volatile.
+ * @IFF_NOTRAILERS: avoid use of trailers. Can be toggled through sysfs.
+ * Volatile.
+ * @IFF_RUNNING: interface RFC2863 OPER_UP. Volatile.
+ * @IFF_NOARP: no ARP protocol. Can be toggled through sysfs. Volatile.
+ * @IFF_PROMISC: receive all packets. Can be toggled through sysfs.
+ * @IFF_ALLMULTI: receive all multicast packets. Can be toggled through
+ * sysfs.
+ * @IFF_MASTER: master of a load balancer. Volatile.
+ * @IFF_SLAVE: slave of a load balancer. Volatile.
+ * @IFF_MULTICAST: Supports multicast. Can be toggled through sysfs.
+ * @IFF_PORTSEL: can set media type. Can be toggled through sysfs.
+ * @IFF_AUTOMEDIA: auto media select active. Can be toggled through sysfs.
+ * @IFF_DYNAMIC: dialup device with changing addresses. Can be toggled
+ * through sysfs.
+ * @IFF_LOWER_UP: driver signals L1 up. Volatile.
+ * @IFF_DORMANT: driver signals dormant. Volatile.
+ * @IFF_ECHO: echo sent packets. Volatile.
+ */
+enum net_device_flags {
+ IFF_UP = 1<<0, /* sysfs */
+ IFF_BROADCAST = 1<<1, /* __volatile__ */
+ IFF_DEBUG = 1<<2, /* sysfs */
+ IFF_LOOPBACK = 1<<3, /* __volatile__ */
+ IFF_POINTOPOINT = 1<<4, /* __volatile__ */
+ IFF_NOTRAILERS = 1<<5, /* sysfs */
+ IFF_RUNNING = 1<<6, /* __volatile__ */
+ IFF_NOARP = 1<<7, /* sysfs */
+ IFF_PROMISC = 1<<8, /* sysfs */
+ IFF_ALLMULTI = 1<<9, /* sysfs */
+ IFF_MASTER = 1<<10, /* __volatile__ */
+ IFF_SLAVE = 1<<11, /* __volatile__ */
+ IFF_MULTICAST = 1<<12, /* sysfs */
+ IFF_PORTSEL = 1<<13, /* sysfs */
+ IFF_AUTOMEDIA = 1<<14, /* sysfs */
+ IFF_DYNAMIC = 1<<15, /* sysfs */
+ IFF_LOWER_UP = 1<<16, /* __volatile__ */
+ IFF_DORMANT = 1<<17, /* __volatile__ */
+ IFF_ECHO = 1<<18, /* __volatile__ */
+};
+
+#define IFF_UP IFF_UP
+#define IFF_BROADCAST IFF_BROADCAST
+#define IFF_DEBUG IFF_DEBUG
+#define IFF_LOOPBACK IFF_LOOPBACK
+#define IFF_POINTOPOINT IFF_POINTOPOINT
+#define IFF_NOTRAILERS IFF_NOTRAILERS
+#define IFF_RUNNING IFF_RUNNING
+#define IFF_NOARP IFF_NOARP
+#define IFF_PROMISC IFF_PROMISC
+#define IFF_ALLMULTI IFF_ALLMULTI
+#define IFF_MASTER IFF_MASTER
+#define IFF_SLAVE IFF_SLAVE
+#define IFF_MULTICAST IFF_MULTICAST
+#define IFF_PORTSEL IFF_PORTSEL
+#define IFF_AUTOMEDIA IFF_AUTOMEDIA
+#define IFF_DYNAMIC IFF_DYNAMIC
+#define IFF_LOWER_UP IFF_LOWER_UP
+#define IFF_DORMANT IFF_DORMANT
+#define IFF_ECHO IFF_ECHO
+
+#define IFF_VOLATILE (IFF_LOOPBACK|IFF_POINTOPOINT|IFF_BROADCAST|IFF_ECHO|\
+ IFF_MASTER|IFF_SLAVE|IFF_RUNNING|IFF_LOWER_UP|IFF_DORMANT)
+
+#define IF_GET_IFACE 0x0001 /* for querying only */
+#define IF_GET_PROTO 0x0002
+
+/* For definitions see hdlc.h */
+#define IF_IFACE_V35 0x1000 /* V.35 serial interface */
+#define IF_IFACE_V24 0x1001 /* V.24 serial interface */
+#define IF_IFACE_X21 0x1002 /* X.21 serial interface */
+#define IF_IFACE_T1 0x1003 /* T1 telco serial interface */
+#define IF_IFACE_E1 0x1004 /* E1 telco serial interface */
+#define IF_IFACE_SYNC_SERIAL 0x1005 /* can't be set by software */
+#define IF_IFACE_X21D 0x1006 /* X.21 Dual Clocking (FarSite) */
+
+/* For definitions see hdlc.h */
+#define IF_PROTO_HDLC 0x2000 /* raw HDLC protocol */
+#define IF_PROTO_PPP 0x2001 /* PPP protocol */
+#define IF_PROTO_CISCO 0x2002 /* Cisco HDLC protocol */
+#define IF_PROTO_FR 0x2003 /* Frame Relay protocol */
+#define IF_PROTO_FR_ADD_PVC 0x2004 /* Create FR PVC */
+#define IF_PROTO_FR_DEL_PVC 0x2005 /* Delete FR PVC */
+#define IF_PROTO_X25 0x2006 /* X.25 */
+#define IF_PROTO_HDLC_ETH 0x2007 /* raw HDLC, Ethernet emulation */
+#define IF_PROTO_FR_ADD_ETH_PVC 0x2008 /* Create FR Ethernet-bridged PVC */
+#define IF_PROTO_FR_DEL_ETH_PVC 0x2009 /* Delete FR Ethernet-bridged PVC */
+#define IF_PROTO_FR_PVC 0x200A /* for reading PVC status */
+#define IF_PROTO_FR_ETH_PVC 0x200B
+#define IF_PROTO_RAW 0x200C /* RAW Socket */
+
+/* RFC 2863 operational status */
+enum {
+ IF_OPER_UNKNOWN,
+ IF_OPER_NOTPRESENT,
+ IF_OPER_DOWN,
+ IF_OPER_LOWERLAYERDOWN,
+ IF_OPER_TESTING,
+ IF_OPER_DORMANT,
+ IF_OPER_UP,
+};
+
+/* link modes */
+enum {
+ IF_LINK_MODE_DEFAULT,
+ IF_LINK_MODE_DORMANT, /* limit upward transition to dormant */
+};
+
+/*
+ * Device mapping structure. I'd just gone off and designed a
+ * beautiful scheme using only loadable modules with arguments
+ * for driver options and along come the PCMCIA people 8)
+ *
+ * Ah well. The get() side of this is good for WDSETUP, and it'll
+ * be handy for debugging things. The set side is fine for now and
+ * being very small might be worth keeping for clean configuration.
+ */
+
+struct ifmap {
+ unsigned long mem_start;
+ unsigned long mem_end;
+ unsigned short base_addr;
+ unsigned char irq;
+ unsigned char dma;
+ unsigned char port;
+ /* 3 bytes spare */
+};
+
+struct if_settings {
+ unsigned int type; /* Type of physical device or protocol */
+ unsigned int size; /* Size of the data allocated by the caller */
+ union {
+ /* {atm/eth/dsl}_settings anyone ? */
+ raw_hdlc_proto *raw_hdlc;
+ cisco_proto *cisco;
+ fr_proto *fr;
+ fr_proto_pvc *fr_pvc;
+ fr_proto_pvc_info *fr_pvc_info;
+
+ /* interface settings */
+ sync_serial_settings *sync;
+ te1_settings *te1;
+ } ifs_ifsu;
+};
+
+/*
+ * Interface request structure used for socket
+ * ioctl's. All interface ioctl's must have parameter
+ * definitions which begin with ifr_name. The
+ * remainder may be interface specific.
+ */
+
+struct ifreq {
+#define IFHWADDRLEN 6
+ union
+ {
+ char ifrn_name[IFNAMSIZ]; /* if name, e.g. "en0" */
+ } ifr_ifrn;
+
+ union {
+ struct sockaddr ifru_addr;
+ struct sockaddr ifru_dstaddr;
+ struct sockaddr ifru_broadaddr;
+ struct sockaddr ifru_netmask;
+ struct sockaddr ifru_hwaddr;
+ short ifru_flags;
+ int ifru_ivalue;
+ int ifru_mtu;
+ struct ifmap ifru_map;
+ char ifru_slave[IFNAMSIZ]; /* Just fits the size */
+ char ifru_newname[IFNAMSIZ];
+ void * ifru_data;
+ struct if_settings ifru_settings;
+ } ifr_ifru;
+};
+
+#define ifr_name ifr_ifrn.ifrn_name /* interface name */
+#define ifr_hwaddr ifr_ifru.ifru_hwaddr /* MAC address */
+#define ifr_addr ifr_ifru.ifru_addr /* address */
+#define ifr_dstaddr ifr_ifru.ifru_dstaddr /* other end of p-p lnk */
+#define ifr_broadaddr ifr_ifru.ifru_broadaddr /* broadcast address */
+#define ifr_netmask ifr_ifru.ifru_netmask /* interface net mask */
+#define ifr_flags ifr_ifru.ifru_flags /* flags */
+#define ifr_metric ifr_ifru.ifru_ivalue /* metric */
+#define ifr_mtu ifr_ifru.ifru_mtu /* mtu */
+#define ifr_map ifr_ifru.ifru_map /* device map */
+#define ifr_slave ifr_ifru.ifru_slave /* slave device */
+#define ifr_data ifr_ifru.ifru_data /* for use by interface */
+#define ifr_ifindex ifr_ifru.ifru_ivalue /* interface index */
+#define ifr_bandwidth ifr_ifru.ifru_ivalue /* link bandwidth */
+#define ifr_qlen ifr_ifru.ifru_ivalue /* Queue length */
+#define ifr_newname ifr_ifru.ifru_newname /* New name */
+#define ifr_settings ifr_ifru.ifru_settings /* Device/proto settings*/
+
+/*
+ * Structure used in SIOCGIFCONF request.
+ * Used to retrieve interface configuration
+ * for machine (useful for programs which
+ * must know all networks accessible).
+ */
+
+struct ifconf {
+ int ifc_len; /* size of buffer */
+ union {
+ char *ifcu_buf;
+ struct ifreq *ifcu_req;
+ } ifc_ifcu;
+};
+#define ifc_buf ifc_ifcu.ifcu_buf /* buffer address */
+#define ifc_req ifc_ifcu.ifcu_req /* array of structures */
+
+#endif /* _LINUX_IF_H */
diff --git a/iproute2/include/linux/if_addr.h b/iproute2/include/linux/if_addr.h
new file mode 100644
index 0000000..26f0ecf
--- /dev/null
+++ b/iproute2/include/linux/if_addr.h
@@ -0,0 +1,67 @@
+#ifndef __LINUX_IF_ADDR_H
+#define __LINUX_IF_ADDR_H
+
+#include <linux/types.h>
+#include <linux/netlink.h>
+
+struct ifaddrmsg {
+ __u8 ifa_family;
+ __u8 ifa_prefixlen; /* The prefix length */
+ __u8 ifa_flags; /* Flags */
+ __u8 ifa_scope; /* Address scope */
+ __u32 ifa_index; /* Link index */
+};
+
+/*
+ * Important comment:
+ * IFA_ADDRESS is prefix address, rather than local interface address.
+ * It makes no difference for normally configured broadcast interfaces,
+ * but for point-to-point IFA_ADDRESS is DESTINATION address,
+ * local address is supplied in IFA_LOCAL attribute.
+ *
+ * IFA_FLAGS is a u32 attribute that extends the u8 field ifa_flags.
+ * If present, the value from struct ifaddrmsg will be ignored.
+ */
+enum {
+ IFA_UNSPEC,
+ IFA_ADDRESS,
+ IFA_LOCAL,
+ IFA_LABEL,
+ IFA_BROADCAST,
+ IFA_ANYCAST,
+ IFA_CACHEINFO,
+ IFA_MULTICAST,
+ IFA_FLAGS,
+ __IFA_MAX,
+};
+
+#define IFA_MAX (__IFA_MAX - 1)
+
+/* ifa_flags */
+#define IFA_F_SECONDARY 0x01
+#define IFA_F_TEMPORARY IFA_F_SECONDARY
+
+#define IFA_F_NODAD 0x02
+#define IFA_F_OPTIMISTIC 0x04
+#define IFA_F_DADFAILED 0x08
+#define IFA_F_HOMEADDRESS 0x10
+#define IFA_F_DEPRECATED 0x20
+#define IFA_F_TENTATIVE 0x40
+#define IFA_F_PERMANENT 0x80
+#define IFA_F_MANAGETEMPADDR 0x100
+#define IFA_F_NOPREFIXROUTE 0x200
+#define IFA_F_MCAUTOJOIN 0x400
+#define IFA_F_STABLE_PRIVACY 0x800
+
+struct ifa_cacheinfo {
+ __u32 ifa_prefered;
+ __u32 ifa_valid;
+ __u32 cstamp; /* created timestamp, hundredths of seconds */
+ __u32 tstamp; /* updated timestamp, hundredths of seconds */
+};
+
+/* backwards compatibility for userspace */
+#define IFA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifaddrmsg))))
+#define IFA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifaddrmsg))
+
+#endif
diff --git a/iproute2/include/linux/if_addrlabel.h b/iproute2/include/linux/if_addrlabel.h
new file mode 100644
index 0000000..54580c2
--- /dev/null
+++ b/iproute2/include/linux/if_addrlabel.h
@@ -0,0 +1,32 @@
+/*
+ * if_addrlabel.h - netlink interface for address labels
+ *
+ * Copyright (C)2007 USAGI/WIDE Project, All Rights Reserved.
+ *
+ * Authors:
+ * YOSHIFUJI Hideaki @ USAGI/WIDE <yoshfuji@linux-ipv6.org>
+ */
+
+#ifndef __LINUX_IF_ADDRLABEL_H
+#define __LINUX_IF_ADDRLABEL_H
+
+#include <linux/types.h>
+
+struct ifaddrlblmsg {
+ __u8 ifal_family; /* Address family */
+ __u8 __ifal_reserved; /* Reserved */
+ __u8 ifal_prefixlen; /* Prefix length */
+ __u8 ifal_flags; /* Flags */
+ __u32 ifal_index; /* Link index */
+ __u32 ifal_seq; /* sequence number */
+};
+
+enum {
+ IFAL_ADDRESS = 1,
+ IFAL_LABEL = 2,
+ __IFAL_MAX
+};
+
+#define IFAL_MAX (__IFAL_MAX - 1)
+
+#endif
diff --git a/iproute2/include/linux/if_arp.h b/iproute2/include/linux/if_arp.h
new file mode 100644
index 0000000..d001bdb
--- /dev/null
+++ b/iproute2/include/linux/if_arp.h
@@ -0,0 +1,161 @@
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * Global definitions for the ARP (RFC 826) protocol.
+ *
+ * Version: @(#)if_arp.h 1.0.1 04/16/93
+ *
+ * Authors: Original taken from Berkeley UNIX 4.3, (c) UCB 1986-1988
+ * Portions taken from the KA9Q/NOS (v2.00m PA0GRI) source.
+ * Ross Biro
+ * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ * Florian La Roche,
+ * Jonathan Layes <layes@loran.com>
+ * Arnaldo Carvalho de Melo <acme@conectiva.com.br> ARPHRD_HWX25
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _LINUX_IF_ARP_H
+#define _LINUX_IF_ARP_H
+
+#include <linux/netdevice.h>
+
+/* ARP protocol HARDWARE identifiers. */
+#define ARPHRD_NETROM 0 /* from KA9Q: NET/ROM pseudo */
+#define ARPHRD_ETHER 1 /* Ethernet 10Mbps */
+#define ARPHRD_EETHER 2 /* Experimental Ethernet */
+#define ARPHRD_AX25 3 /* AX.25 Level 2 */
+#define ARPHRD_PRONET 4 /* PROnet token ring */
+#define ARPHRD_CHAOS 5 /* Chaosnet */
+#define ARPHRD_IEEE802 6 /* IEEE 802.2 Ethernet/TR/TB */
+#define ARPHRD_ARCNET 7 /* ARCnet */
+#define ARPHRD_APPLETLK 8 /* APPLEtalk */
+#define ARPHRD_DLCI 15 /* Frame Relay DLCI */
+#define ARPHRD_ATM 19 /* ATM */
+#define ARPHRD_METRICOM 23 /* Metricom STRIP (new IANA id) */
+#define ARPHRD_IEEE1394 24 /* IEEE 1394 IPv4 - RFC 2734 */
+#define ARPHRD_EUI64 27 /* EUI-64 */
+#define ARPHRD_INFINIBAND 32 /* InfiniBand */
+
+/* Dummy types for non ARP hardware */
+#define ARPHRD_SLIP 256
+#define ARPHRD_CSLIP 257
+#define ARPHRD_SLIP6 258
+#define ARPHRD_CSLIP6 259
+#define ARPHRD_RSRVD 260 /* Notional KISS type */
+#define ARPHRD_ADAPT 264
+#define ARPHRD_ROSE 270
+#define ARPHRD_X25 271 /* CCITT X.25 */
+#define ARPHRD_HWX25 272 /* Boards with X.25 in firmware */
+#define ARPHRD_CAN 280 /* Controller Area Network */
+#define ARPHRD_PPP 512
+#define ARPHRD_CISCO 513 /* Cisco HDLC */
+#define ARPHRD_HDLC ARPHRD_CISCO
+#define ARPHRD_LAPB 516 /* LAPB */
+#define ARPHRD_DDCMP 517 /* Digital's DDCMP protocol */
+#define ARPHRD_RAWHDLC 518 /* Raw HDLC */
+
+#define ARPHRD_TUNNEL 768 /* IPIP tunnel */
+#define ARPHRD_TUNNEL6 769 /* IP6IP6 tunnel */
+#define ARPHRD_FRAD 770 /* Frame Relay Access Device */
+#define ARPHRD_SKIP 771 /* SKIP vif */
+#define ARPHRD_LOOPBACK 772 /* Loopback device */
+#define ARPHRD_LOCALTLK 773 /* Localtalk device */
+#define ARPHRD_FDDI 774 /* Fiber Distributed Data Interface */
+#define ARPHRD_BIF 775 /* AP1000 BIF */
+#define ARPHRD_SIT 776 /* sit0 device - IPv6-in-IPv4 */
+#define ARPHRD_IPDDP 777 /* IP over DDP tunneller */
+#define ARPHRD_IPGRE 778 /* GRE over IP */
+#define ARPHRD_PIMREG 779 /* PIMSM register interface */
+#define ARPHRD_HIPPI 780 /* High Performance Parallel Interface */
+#define ARPHRD_ASH 781 /* Nexus 64Mbps Ash */
+#define ARPHRD_ECONET 782 /* Acorn Econet */
+#define ARPHRD_IRDA 783 /* Linux-IrDA */
+/* ARP works differently on different FC media .. so */
+#define ARPHRD_FCPP 784 /* Point to point fibrechannel */
+#define ARPHRD_FCAL 785 /* Fibrechannel arbitrated loop */
+#define ARPHRD_FCPL 786 /* Fibrechannel public loop */
+#define ARPHRD_FCFABRIC 787 /* Fibrechannel fabric */
+ /* 787->799 reserved for fibrechannel media types */
+#define ARPHRD_IEEE802_TR 800 /* Magic type ident for TR */
+#define ARPHRD_IEEE80211 801 /* IEEE 802.11 */
+#define ARPHRD_IEEE80211_PRISM 802 /* IEEE 802.11 + Prism2 header */
+#define ARPHRD_IEEE80211_RADIOTAP 803 /* IEEE 802.11 + radiotap header */
+#define ARPHRD_IEEE802154 804
+#define ARPHRD_IEEE802154_MONITOR 805 /* IEEE 802.15.4 network monitor */
+
+#define ARPHRD_PHONET 820 /* PhoNet media type */
+#define ARPHRD_PHONET_PIPE 821 /* PhoNet pipe header */
+#define ARPHRD_CAIF 822 /* CAIF media type */
+#define ARPHRD_IP6GRE 823 /* GRE over IPv6 */
+#define ARPHRD_NETLINK 824 /* Netlink header */
+#define ARPHRD_6LOWPAN 825 /* IPv6 over LoWPAN */
+
+#define ARPHRD_VOID 0xFFFF /* Void type, nothing is known */
+#define ARPHRD_NONE 0xFFFE /* zero header length */
+
+/* ARP protocol opcodes. */
+#define ARPOP_REQUEST 1 /* ARP request */
+#define ARPOP_REPLY 2 /* ARP reply */
+#define ARPOP_RREQUEST 3 /* RARP request */
+#define ARPOP_RREPLY 4 /* RARP reply */
+#define ARPOP_InREQUEST 8 /* InARP request */
+#define ARPOP_InREPLY 9 /* InARP reply */
+#define ARPOP_NAK 10 /* (ATM)ARP NAK */
+
+
+/* ARP ioctl request. */
+struct arpreq {
+ struct sockaddr arp_pa; /* protocol address */
+ struct sockaddr arp_ha; /* hardware address */
+ int arp_flags; /* flags */
+ struct sockaddr arp_netmask; /* netmask (only for proxy arps) */
+ char arp_dev[16];
+};
+
+struct arpreq_old {
+ struct sockaddr arp_pa; /* protocol address */
+ struct sockaddr arp_ha; /* hardware address */
+ int arp_flags; /* flags */
+ struct sockaddr arp_netmask; /* netmask (only for proxy arps) */
+};
+
+/* ARP Flag values. */
+#define ATF_COM 0x02 /* completed entry (ha valid) */
+#define ATF_PERM 0x04 /* permanent entry */
+#define ATF_PUBL 0x08 /* publish entry */
+#define ATF_USETRAILERS 0x10 /* has requested trailers */
+#define ATF_NETMASK 0x20 /* want to use a netmask (only
+ for proxy entries) */
+#define ATF_DONTPUB 0x40 /* don't answer this addresses */
+
+/*
+ * This structure defines an ethernet arp header.
+ */
+
+struct arphdr {
+ __be16 ar_hrd; /* format of hardware address */
+ __be16 ar_pro; /* format of protocol address */
+ unsigned char ar_hln; /* length of hardware address */
+ unsigned char ar_pln; /* length of protocol address */
+ __be16 ar_op; /* ARP opcode (command) */
+
+#if 0
+ /*
+ * Ethernet looks like this : This bit is variable sized however...
+ */
+ unsigned char ar_sha[ETH_ALEN]; /* sender hardware address */
+ unsigned char ar_sip[4]; /* sender IP address */
+ unsigned char ar_tha[ETH_ALEN]; /* target hardware address */
+ unsigned char ar_tip[4]; /* target IP address */
+#endif
+
+};
+
+
+#endif /* _LINUX_IF_ARP_H */
diff --git a/iproute2/include/linux/if_bridge.h b/iproute2/include/linux/if_bridge.h
new file mode 100644
index 0000000..ee197a3
--- /dev/null
+++ b/iproute2/include/linux/if_bridge.h
@@ -0,0 +1,203 @@
+/*
+ * Linux ethernet bridge
+ *
+ * Authors:
+ * Lennert Buytenhek <buytenh@gnu.org>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _LINUX_IF_BRIDGE_H
+#define _LINUX_IF_BRIDGE_H
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+#include <linux/in6.h>
+
+#define SYSFS_BRIDGE_ATTR "bridge"
+#define SYSFS_BRIDGE_FDB "brforward"
+#define SYSFS_BRIDGE_PORT_SUBDIR "brif"
+#define SYSFS_BRIDGE_PORT_ATTR "brport"
+#define SYSFS_BRIDGE_PORT_LINK "bridge"
+
+#define BRCTL_VERSION 1
+
+#define BRCTL_GET_VERSION 0
+#define BRCTL_GET_BRIDGES 1
+#define BRCTL_ADD_BRIDGE 2
+#define BRCTL_DEL_BRIDGE 3
+#define BRCTL_ADD_IF 4
+#define BRCTL_DEL_IF 5
+#define BRCTL_GET_BRIDGE_INFO 6
+#define BRCTL_GET_PORT_LIST 7
+#define BRCTL_SET_BRIDGE_FORWARD_DELAY 8
+#define BRCTL_SET_BRIDGE_HELLO_TIME 9
+#define BRCTL_SET_BRIDGE_MAX_AGE 10
+#define BRCTL_SET_AGEING_TIME 11
+#define BRCTL_SET_GC_INTERVAL 12
+#define BRCTL_GET_PORT_INFO 13
+#define BRCTL_SET_BRIDGE_STP_STATE 14
+#define BRCTL_SET_BRIDGE_PRIORITY 15
+#define BRCTL_SET_PORT_PRIORITY 16
+#define BRCTL_SET_PATH_COST 17
+#define BRCTL_GET_FDB_ENTRIES 18
+
+#define BR_STATE_DISABLED 0
+#define BR_STATE_LISTENING 1
+#define BR_STATE_LEARNING 2
+#define BR_STATE_FORWARDING 3
+#define BR_STATE_BLOCKING 4
+
+struct __bridge_info {
+ __u64 designated_root;
+ __u64 bridge_id;
+ __u32 root_path_cost;
+ __u32 max_age;
+ __u32 hello_time;
+ __u32 forward_delay;
+ __u32 bridge_max_age;
+ __u32 bridge_hello_time;
+ __u32 bridge_forward_delay;
+ __u8 topology_change;
+ __u8 topology_change_detected;
+ __u8 root_port;
+ __u8 stp_enabled;
+ __u32 ageing_time;
+ __u32 gc_interval;
+ __u32 hello_timer_value;
+ __u32 tcn_timer_value;
+ __u32 topology_change_timer_value;
+ __u32 gc_timer_value;
+};
+
+struct __port_info {
+ __u64 designated_root;
+ __u64 designated_bridge;
+ __u16 port_id;
+ __u16 designated_port;
+ __u32 path_cost;
+ __u32 designated_cost;
+ __u8 state;
+ __u8 top_change_ack;
+ __u8 config_pending;
+ __u8 unused0;
+ __u32 message_age_timer_value;
+ __u32 forward_delay_timer_value;
+ __u32 hold_timer_value;
+};
+
+struct __fdb_entry {
+ __u8 mac_addr[ETH_ALEN];
+ __u8 port_no;
+ __u8 is_local;
+ __u32 ageing_timer_value;
+ __u8 port_hi;
+ __u8 pad0;
+ __u16 unused;
+};
+
+/* Bridge Flags */
+#define BRIDGE_FLAGS_MASTER 1 /* Bridge command to/from master */
+#define BRIDGE_FLAGS_SELF 2 /* Bridge command to/from lowerdev */
+
+#define BRIDGE_MODE_VEB 0 /* Default loopback mode */
+#define BRIDGE_MODE_VEPA 1 /* 802.1Qbg defined VEPA mode */
+#define BRIDGE_MODE_UNDEF 0xFFFF /* mode undefined */
+
+/* Bridge management nested attributes
+ * [IFLA_AF_SPEC] = {
+ * [IFLA_BRIDGE_FLAGS]
+ * [IFLA_BRIDGE_MODE]
+ * [IFLA_BRIDGE_VLAN_INFO]
+ * }
+ */
+enum {
+ IFLA_BRIDGE_FLAGS,
+ IFLA_BRIDGE_MODE,
+ IFLA_BRIDGE_VLAN_INFO,
+ __IFLA_BRIDGE_MAX,
+};
+#define IFLA_BRIDGE_MAX (__IFLA_BRIDGE_MAX - 1)
+
+#define BRIDGE_VLAN_INFO_MASTER (1<<0) /* Operate on Bridge device as well */
+#define BRIDGE_VLAN_INFO_PVID (1<<1) /* VLAN is PVID, ingress untagged */
+#define BRIDGE_VLAN_INFO_UNTAGGED (1<<2) /* VLAN egresses untagged */
+#define BRIDGE_VLAN_INFO_RANGE_BEGIN (1<<3) /* VLAN is start of vlan range */
+#define BRIDGE_VLAN_INFO_RANGE_END (1<<4) /* VLAN is end of vlan range */
+#define BRIDGE_VLAN_INFO_BRENTRY (1<<5) /* Global bridge VLAN entry */
+
+struct bridge_vlan_info {
+ __u16 flags;
+ __u16 vid;
+};
+
+/* Bridge multicast database attributes
+ * [MDBA_MDB] = {
+ * [MDBA_MDB_ENTRY] = {
+ * [MDBA_MDB_ENTRY_INFO]
+ * }
+ * }
+ * [MDBA_ROUTER] = {
+ * [MDBA_ROUTER_PORT]
+ * }
+ */
+enum {
+ MDBA_UNSPEC,
+ MDBA_MDB,
+ MDBA_ROUTER,
+ __MDBA_MAX,
+};
+#define MDBA_MAX (__MDBA_MAX - 1)
+
+enum {
+ MDBA_MDB_UNSPEC,
+ MDBA_MDB_ENTRY,
+ __MDBA_MDB_MAX,
+};
+#define MDBA_MDB_MAX (__MDBA_MDB_MAX - 1)
+
+enum {
+ MDBA_MDB_ENTRY_UNSPEC,
+ MDBA_MDB_ENTRY_INFO,
+ __MDBA_MDB_ENTRY_MAX,
+};
+#define MDBA_MDB_ENTRY_MAX (__MDBA_MDB_ENTRY_MAX - 1)
+
+enum {
+ MDBA_ROUTER_UNSPEC,
+ MDBA_ROUTER_PORT,
+ __MDBA_ROUTER_MAX,
+};
+#define MDBA_ROUTER_MAX (__MDBA_ROUTER_MAX - 1)
+
+struct br_port_msg {
+ __u8 family;
+ __u32 ifindex;
+};
+
+struct br_mdb_entry {
+ __u32 ifindex;
+#define MDB_TEMPORARY 0
+#define MDB_PERMANENT 1
+ __u8 state;
+ __u16 vid;
+ struct {
+ union {
+ __be32 ip4;
+ struct in6_addr ip6;
+ } u;
+ __be16 proto;
+ } addr;
+};
+
+enum {
+ MDBA_SET_ENTRY_UNSPEC,
+ MDBA_SET_ENTRY,
+ __MDBA_SET_ENTRY_MAX,
+};
+#define MDBA_SET_ENTRY_MAX (__MDBA_SET_ENTRY_MAX - 1)
+
+#endif /* _LINUX_IF_BRIDGE_H */
diff --git a/iproute2/include/linux/if_ether.h b/iproute2/include/linux/if_ether.h
new file mode 100644
index 0000000..bf278d6
--- /dev/null
+++ b/iproute2/include/linux/if_ether.h
@@ -0,0 +1,145 @@
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * Global definitions for the Ethernet IEEE 802.3 interface.
+ *
+ * Version: @(#)if_ether.h 1.0.1a 02/08/94
+ *
+ * Author: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ * Donald Becker, <becker@super.org>
+ * Alan Cox, <alan@lxorguk.ukuu.org.uk>
+ * Steve Whitehouse, <gw7rrm@eeshack3.swan.ac.uk>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _LINUX_IF_ETHER_H
+#define _LINUX_IF_ETHER_H
+
+#include <linux/types.h>
+
+/*
+ * IEEE 802.3 Ethernet magic constants. The frame sizes omit the preamble
+ * and FCS/CRC (frame check sequence).
+ */
+
+#define ETH_ALEN 6 /* Octets in one ethernet addr */
+#define ETH_HLEN 14 /* Total octets in header. */
+#define ETH_ZLEN 60 /* Min. octets in frame sans FCS */
+#define ETH_DATA_LEN 1500 /* Max. octets in payload */
+#define ETH_FRAME_LEN 1514 /* Max. octets in frame sans FCS */
+#define ETH_FCS_LEN 4 /* Octets in the FCS */
+
+/*
+ * These are the defined Ethernet Protocol ID's.
+ */
+
+#define ETH_P_LOOP 0x0060 /* Ethernet Loopback packet */
+#define ETH_P_PUP 0x0200 /* Xerox PUP packet */
+#define ETH_P_PUPAT 0x0201 /* Xerox PUP Addr Trans packet */
+#define ETH_P_TSN 0x22F0 /* TSN (IEEE 1722) packet */
+#define ETH_P_IP 0x0800 /* Internet Protocol packet */
+#define ETH_P_X25 0x0805 /* CCITT X.25 */
+#define ETH_P_ARP 0x0806 /* Address Resolution packet */
+#define ETH_P_BPQ 0x08FF /* G8BPQ AX.25 Ethernet Packet [ NOT AN OFFICIALLY REGISTERED ID ] */
+#define ETH_P_IEEEPUP 0x0a00 /* Xerox IEEE802.3 PUP packet */
+#define ETH_P_IEEEPUPAT 0x0a01 /* Xerox IEEE802.3 PUP Addr Trans packet */
+#define ETH_P_BATMAN 0x4305 /* B.A.T.M.A.N.-Advanced packet [ NOT AN OFFICIALLY REGISTERED ID ] */
+#define ETH_P_DEC 0x6000 /* DEC Assigned proto */
+#define ETH_P_DNA_DL 0x6001 /* DEC DNA Dump/Load */
+#define ETH_P_DNA_RC 0x6002 /* DEC DNA Remote Console */
+#define ETH_P_DNA_RT 0x6003 /* DEC DNA Routing */
+#define ETH_P_LAT 0x6004 /* DEC LAT */
+#define ETH_P_DIAG 0x6005 /* DEC Diagnostics */
+#define ETH_P_CUST 0x6006 /* DEC Customer use */
+#define ETH_P_SCA 0x6007 /* DEC Systems Comms Arch */
+#define ETH_P_TEB 0x6558 /* Trans Ether Bridging */
+#define ETH_P_RARP 0x8035 /* Reverse Addr Res packet */
+#define ETH_P_ATALK 0x809B /* Appletalk DDP */
+#define ETH_P_AARP 0x80F3 /* Appletalk AARP */
+#define ETH_P_8021Q 0x8100 /* 802.1Q VLAN Extended Header */
+#define ETH_P_IPX 0x8137 /* IPX over DIX */
+#define ETH_P_IPV6 0x86DD /* IPv6 over bluebook */
+#define ETH_P_PAUSE 0x8808 /* IEEE Pause frames. See 802.3 31B */
+#define ETH_P_SLOW 0x8809 /* Slow Protocol. See 802.3ad 43B */
+#define ETH_P_WCCP 0x883E /* Web-cache coordination protocol
+ * defined in draft-wilson-wrec-wccp-v2-00.txt */
+#define ETH_P_MPLS_UC 0x8847 /* MPLS Unicast traffic */
+#define ETH_P_MPLS_MC 0x8848 /* MPLS Multicast traffic */
+#define ETH_P_ATMMPOA 0x884c /* MultiProtocol Over ATM */
+#define ETH_P_PPP_DISC 0x8863 /* PPPoE discovery messages */
+#define ETH_P_PPP_SES 0x8864 /* PPPoE session messages */
+#define ETH_P_LINK_CTL 0x886c /* HPNA, wlan link local tunnel */
+#define ETH_P_ATMFATE 0x8884 /* Frame-based ATM Transport
+ * over Ethernet
+ */
+#define ETH_P_PAE 0x888E /* Port Access Entity (IEEE 802.1X) */
+#define ETH_P_AOE 0x88A2 /* ATA over Ethernet */
+#define ETH_P_8021AD 0x88A8 /* 802.1ad Service VLAN */
+#define ETH_P_802_EX1 0x88B5 /* 802.1 Local Experimental 1. */
+#define ETH_P_TIPC 0x88CA /* TIPC */
+#define ETH_P_8021AH 0x88E7 /* 802.1ah Backbone Service Tag */
+#define ETH_P_MVRP 0x88F5 /* 802.1Q MVRP */
+#define ETH_P_1588 0x88F7 /* IEEE 1588 Timesync */
+#define ETH_P_PRP 0x88FB /* IEC 62439-3 PRP/HSRv0 */
+#define ETH_P_FCOE 0x8906 /* Fibre Channel over Ethernet */
+#define ETH_P_TDLS 0x890D /* TDLS */
+#define ETH_P_FIP 0x8914 /* FCoE Initialization Protocol */
+#define ETH_P_80221 0x8917 /* IEEE 802.21 Media Independent Handover Protocol */
+#define ETH_P_LOOPBACK 0x9000 /* Ethernet loopback packet, per IEEE 802.3 */
+#define ETH_P_QINQ1 0x9100 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */
+#define ETH_P_QINQ2 0x9200 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */
+#define ETH_P_QINQ3 0x9300 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */
+#define ETH_P_EDSA 0xDADA /* Ethertype DSA [ NOT AN OFFICIALLY REGISTERED ID ] */
+#define ETH_P_AF_IUCV 0xFBFB /* IBM af_iucv [ NOT AN OFFICIALLY REGISTERED ID ] */
+
+#define ETH_P_802_3_MIN 0x0600 /* If the value in the ethernet type is less than this value
+ * then the frame is Ethernet II. Else it is 802.3 */
+
+/*
+ * Non DIX types. Won't clash for 1500 types.
+ */
+
+#define ETH_P_802_3 0x0001 /* Dummy type for 802.3 frames */
+#define ETH_P_AX25 0x0002 /* Dummy protocol id for AX.25 */
+#define ETH_P_ALL 0x0003 /* Every packet (be careful!!!) */
+#define ETH_P_802_2 0x0004 /* 802.2 frames */
+#define ETH_P_SNAP 0x0005 /* Internal only */
+#define ETH_P_DDCMP 0x0006 /* DEC DDCMP: Internal only */
+#define ETH_P_WAN_PPP 0x0007 /* Dummy type for WAN PPP frames*/
+#define ETH_P_PPP_MP 0x0008 /* Dummy type for PPP MP frames */
+#define ETH_P_LOCALTALK 0x0009 /* Localtalk pseudo type */
+#define ETH_P_CAN 0x000C /* CAN: Controller Area Network */
+#define ETH_P_CANFD 0x000D /* CANFD: CAN flexible data rate*/
+#define ETH_P_PPPTALK 0x0010 /* Dummy type for Atalk over PPP*/
+#define ETH_P_TR_802_2 0x0011 /* 802.2 frames */
+#define ETH_P_MOBITEX 0x0015 /* Mobitex (kaz@cafe.net) */
+#define ETH_P_CONTROL 0x0016 /* Card specific control frames */
+#define ETH_P_IRDA 0x0017 /* Linux-IrDA */
+#define ETH_P_ECONET 0x0018 /* Acorn Econet */
+#define ETH_P_HDLC 0x0019 /* HDLC frames */
+#define ETH_P_ARCNET 0x001A /* 1A for ArcNet :-) */
+#define ETH_P_DSA 0x001B /* Distributed Switch Arch. */
+#define ETH_P_TRAILER 0x001C /* Trailer switch tagging */
+#define ETH_P_PHONET 0x00F5 /* Nokia Phonet frames */
+#define ETH_P_IEEE802154 0x00F6 /* IEEE802.15.4 frame */
+#define ETH_P_CAIF 0x00F7 /* ST-Ericsson CAIF protocol */
+#define ETH_P_XDSA 0x00F8 /* Multiplexed DSA protocol */
+
+/*
+ * This is an Ethernet frame header.
+ */
+
+struct ethhdr {
+ unsigned char h_dest[ETH_ALEN]; /* destination eth addr */
+ unsigned char h_source[ETH_ALEN]; /* source ether addr */
+ __be16 h_proto; /* packet type ID field */
+} __attribute__((packed));
+
+
+#endif /* _LINUX_IF_ETHER_H */
diff --git a/iproute2/include/linux/if_link.h b/iproute2/include/linux/if_link.h
new file mode 100644
index 0000000..d91f2c9
--- /dev/null
+++ b/iproute2/include/linux/if_link.h
@@ -0,0 +1,728 @@
+#ifndef _LINUX_IF_LINK_H
+#define _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;
+};
+
+/* 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;
+};
+
+/* 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_MAX
+};
+
+
+#define IFLA_MAX (__IFLA_MAX - 1)
+
+/* backwards compatibility for userspace */
+#define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg))))
+#define IFLA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifinfomsg))
+
+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_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_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)
+
+/* IPVLAN section */
+enum {
+ IFLA_IPVLAN_UNSPEC,
+ IFLA_IPVLAN_MODE,
+ __IFLA_IPVLAN_MAX
+};
+
+#define IFLA_IPVLAN_MAX (__IFLA_IPVLAN_MAX - 1)
+
+enum ipvlan_mode {
+ IPVLAN_MODE_L2 = 0,
+ IPVLAN_MODE_L3,
+ IPVLAN_MODE_MAX
+};
+
+/* 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_MAX
+};
+#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
+
+struct ifla_vxlan_port_range {
+ __be16 low;
+ __be16 high;
+};
+
+/* 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_MAX
+};
+#define IFLA_GENEVE_MAX (__IFLA_GENEVE_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,
+ 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_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;
+};
+
+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;
+};
+
+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_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_MAX,
+};
+
+#define IFLA_HSR_MAX (__IFLA_HSR_MAX - 1)
+
+#endif /* _LINUX_IF_LINK_H */
diff --git a/iproute2/include/linux/if_tun.h b/iproute2/include/linux/if_tun.h
new file mode 100644
index 0000000..d5ecb42
--- /dev/null
+++ b/iproute2/include/linux/if_tun.h
@@ -0,0 +1,107 @@
+/*
+ * Universal TUN/TAP device driver.
+ * Copyright (C) 1999-2000 Maxim Krasnyansky <max_mk@yahoo.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __IF_TUN_H
+#define __IF_TUN_H
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+#include <linux/filter.h>
+
+/* Read queue size */
+#define TUN_READQ_SIZE 500
+/* TUN device type flags: deprecated. Use IFF_TUN/IFF_TAP instead. */
+#define TUN_TUN_DEV IFF_TUN
+#define TUN_TAP_DEV IFF_TAP
+#define TUN_TYPE_MASK 0x000f
+
+/* Ioctl defines */
+#define TUNSETNOCSUM _IOW('T', 200, int)
+#define TUNSETDEBUG _IOW('T', 201, int)
+#define TUNSETIFF _IOW('T', 202, int)
+#define TUNSETPERSIST _IOW('T', 203, int)
+#define TUNSETOWNER _IOW('T', 204, int)
+#define TUNSETLINK _IOW('T', 205, int)
+#define TUNSETGROUP _IOW('T', 206, int)
+#define TUNGETFEATURES _IOR('T', 207, unsigned int)
+#define TUNSETOFFLOAD _IOW('T', 208, unsigned int)
+#define TUNSETTXFILTER _IOW('T', 209, unsigned int)
+#define TUNGETIFF _IOR('T', 210, unsigned int)
+#define TUNGETSNDBUF _IOR('T', 211, int)
+#define TUNSETSNDBUF _IOW('T', 212, int)
+#define TUNATTACHFILTER _IOW('T', 213, struct sock_fprog)
+#define TUNDETACHFILTER _IOW('T', 214, struct sock_fprog)
+#define TUNGETVNETHDRSZ _IOR('T', 215, int)
+#define TUNSETVNETHDRSZ _IOW('T', 216, int)
+#define TUNSETQUEUE _IOW('T', 217, int)
+#define TUNSETIFINDEX _IOW('T', 218, unsigned int)
+#define TUNGETFILTER _IOR('T', 219, struct sock_fprog)
+#define TUNSETVNETLE _IOW('T', 220, int)
+#define TUNGETVNETLE _IOR('T', 221, int)
+/* The TUNSETVNETBE and TUNGETVNETBE ioctls are for cross-endian support on
+ * little-endian hosts. Not all kernel configurations support them, but all
+ * configurations that support SET also support GET.
+ */
+#define TUNSETVNETBE _IOW('T', 222, int)
+#define TUNGETVNETBE _IOR('T', 223, int)
+
+/* TUNSETIFF ifr flags */
+#define IFF_TUN 0x0001
+#define IFF_TAP 0x0002
+#define IFF_NO_PI 0x1000
+/* This flag has no real effect */
+#define IFF_ONE_QUEUE 0x2000
+#define IFF_VNET_HDR 0x4000
+#define IFF_TUN_EXCL 0x8000
+#define IFF_MULTI_QUEUE 0x0100
+#define IFF_ATTACH_QUEUE 0x0200
+#define IFF_DETACH_QUEUE 0x0400
+/* read-only flag */
+#define IFF_PERSIST 0x0800
+#define IFF_NOFILTER 0x1000
+
+/* Socket options */
+#define TUN_TX_TIMESTAMP 1
+
+/* Features for GSO (TUNSETOFFLOAD). */
+#define TUN_F_CSUM 0x01 /* You can hand me unchecksummed packets. */
+#define TUN_F_TSO4 0x02 /* I can handle TSO for IPv4 packets */
+#define TUN_F_TSO6 0x04 /* I can handle TSO for IPv6 packets */
+#define TUN_F_TSO_ECN 0x08 /* I can handle TSO with ECN bits. */
+#define TUN_F_UFO 0x10 /* I can handle UFO packets */
+
+/* Protocol info prepended to the packets (when IFF_NO_PI is not set) */
+#define TUN_PKT_STRIP 0x0001
+struct tun_pi {
+ __u16 flags;
+ __be16 proto;
+};
+
+/*
+ * Filter spec (used for SETXXFILTER ioctls)
+ * This stuff is applicable only to the TAP (Ethernet) devices.
+ * If the count is zero the filter is disabled and the driver accepts
+ * all packets (promisc mode).
+ * If the filter is enabled in order to accept broadcast packets
+ * broadcast addr must be explicitly included in the addr list.
+ */
+#define TUN_FLT_ALLMULTI 0x0001 /* Accept all multicast packets */
+struct tun_filter {
+ __u16 flags; /* TUN_FLT_ flags see above */
+ __u16 count; /* Number of addresses */
+ __u8 addr[0][ETH_ALEN];
+};
+
+#endif /* __IF_TUN_H */
diff --git a/iproute2/include/linux/if_tunnel.h b/iproute2/include/linux/if_tunnel.h
new file mode 100644
index 0000000..f0201ca
--- /dev/null
+++ b/iproute2/include/linux/if_tunnel.h
@@ -0,0 +1,135 @@
+#ifndef _IF_TUNNEL_H_
+#define _IF_TUNNEL_H_
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+
+#define SIOCGETTUNNEL (SIOCDEVPRIVATE + 0)
+#define SIOCADDTUNNEL (SIOCDEVPRIVATE + 1)
+#define SIOCDELTUNNEL (SIOCDEVPRIVATE + 2)
+#define SIOCCHGTUNNEL (SIOCDEVPRIVATE + 3)
+#define SIOCGETPRL (SIOCDEVPRIVATE + 4)
+#define SIOCADDPRL (SIOCDEVPRIVATE + 5)
+#define SIOCDELPRL (SIOCDEVPRIVATE + 6)
+#define SIOCCHGPRL (SIOCDEVPRIVATE + 7)
+#define SIOCGET6RD (SIOCDEVPRIVATE + 8)
+#define SIOCADD6RD (SIOCDEVPRIVATE + 9)
+#define SIOCDEL6RD (SIOCDEVPRIVATE + 10)
+#define SIOCCHG6RD (SIOCDEVPRIVATE + 11)
+
+#define GRE_CSUM __cpu_to_be16(0x8000)
+#define GRE_ROUTING __cpu_to_be16(0x4000)
+#define GRE_KEY __cpu_to_be16(0x2000)
+#define GRE_SEQ __cpu_to_be16(0x1000)
+#define GRE_STRICT __cpu_to_be16(0x0800)
+#define GRE_REC __cpu_to_be16(0x0700)
+#define GRE_FLAGS __cpu_to_be16(0x00F8)
+#define GRE_VERSION __cpu_to_be16(0x0007)
+
+struct ip_tunnel_parm {
+ char name[IFNAMSIZ];
+ int link;
+ __be16 i_flags;
+ __be16 o_flags;
+ __be32 i_key;
+ __be32 o_key;
+ struct iphdr iph;
+};
+
+enum {
+ IFLA_IPTUN_UNSPEC,
+ IFLA_IPTUN_LINK,
+ IFLA_IPTUN_LOCAL,
+ IFLA_IPTUN_REMOTE,
+ IFLA_IPTUN_TTL,
+ IFLA_IPTUN_TOS,
+ IFLA_IPTUN_ENCAP_LIMIT,
+ IFLA_IPTUN_FLOWINFO,
+ IFLA_IPTUN_FLAGS,
+ IFLA_IPTUN_PROTO,
+ IFLA_IPTUN_PMTUDISC,
+ IFLA_IPTUN_6RD_PREFIX,
+ IFLA_IPTUN_6RD_RELAY_PREFIX,
+ IFLA_IPTUN_6RD_PREFIXLEN,
+ IFLA_IPTUN_6RD_RELAY_PREFIXLEN,
+ IFLA_IPTUN_ENCAP_TYPE,
+ IFLA_IPTUN_ENCAP_FLAGS,
+ IFLA_IPTUN_ENCAP_SPORT,
+ IFLA_IPTUN_ENCAP_DPORT,
+ __IFLA_IPTUN_MAX,
+};
+#define IFLA_IPTUN_MAX (__IFLA_IPTUN_MAX - 1)
+
+enum tunnel_encap_types {
+ TUNNEL_ENCAP_NONE,
+ TUNNEL_ENCAP_FOU,
+ TUNNEL_ENCAP_GUE,
+};
+
+#define TUNNEL_ENCAP_FLAG_CSUM (1<<0)
+#define TUNNEL_ENCAP_FLAG_CSUM6 (1<<1)
+#define TUNNEL_ENCAP_FLAG_REMCSUM (1<<2)
+
+/* SIT-mode i_flags */
+#define SIT_ISATAP 0x0001
+
+struct ip_tunnel_prl {
+ __be32 addr;
+ __u16 flags;
+ __u16 __reserved;
+ __u32 datalen;
+ __u32 __reserved2;
+ /* data follows */
+};
+
+/* PRL flags */
+#define PRL_DEFAULT 0x0001
+
+struct ip_tunnel_6rd {
+ struct in6_addr prefix;
+ __be32 relay_prefix;
+ __u16 prefixlen;
+ __u16 relay_prefixlen;
+};
+
+enum {
+ IFLA_GRE_UNSPEC,
+ IFLA_GRE_LINK,
+ IFLA_GRE_IFLAGS,
+ IFLA_GRE_OFLAGS,
+ IFLA_GRE_IKEY,
+ IFLA_GRE_OKEY,
+ IFLA_GRE_LOCAL,
+ IFLA_GRE_REMOTE,
+ IFLA_GRE_TTL,
+ IFLA_GRE_TOS,
+ IFLA_GRE_PMTUDISC,
+ IFLA_GRE_ENCAP_LIMIT,
+ IFLA_GRE_FLOWINFO,
+ IFLA_GRE_FLAGS,
+ IFLA_GRE_ENCAP_TYPE,
+ IFLA_GRE_ENCAP_FLAGS,
+ IFLA_GRE_ENCAP_SPORT,
+ IFLA_GRE_ENCAP_DPORT,
+ IFLA_GRE_COLLECT_METADATA,
+ __IFLA_GRE_MAX,
+};
+
+#define IFLA_GRE_MAX (__IFLA_GRE_MAX - 1)
+
+/* VTI-mode i_flags */
+#define VTI_ISVTI ((__be16)0x0001)
+
+enum {
+ IFLA_VTI_UNSPEC,
+ IFLA_VTI_LINK,
+ IFLA_VTI_IKEY,
+ IFLA_VTI_OKEY,
+ IFLA_VTI_LOCAL,
+ IFLA_VTI_REMOTE,
+ __IFLA_VTI_MAX,
+};
+
+#define IFLA_VTI_MAX (__IFLA_VTI_MAX - 1)
+#endif /* _IF_TUNNEL_H_ */
diff --git a/iproute2/include/linux/if_vlan.h b/iproute2/include/linux/if_vlan.h
new file mode 100644
index 0000000..24ae007
--- /dev/null
+++ b/iproute2/include/linux/if_vlan.h
@@ -0,0 +1,64 @@
+/*
+ * VLAN An implementation of 802.1Q VLAN tagging.
+ *
+ * Authors: Ben Greear <greearb@candelatech.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#ifndef _LINUX_IF_VLAN_H_
+#define _LINUX_IF_VLAN_H_
+
+
+/* VLAN IOCTLs are found in sockios.h */
+
+/* Passed in vlan_ioctl_args structure to determine behaviour. */
+enum vlan_ioctl_cmds {
+ ADD_VLAN_CMD,
+ DEL_VLAN_CMD,
+ SET_VLAN_INGRESS_PRIORITY_CMD,
+ SET_VLAN_EGRESS_PRIORITY_CMD,
+ GET_VLAN_INGRESS_PRIORITY_CMD,
+ GET_VLAN_EGRESS_PRIORITY_CMD,
+ SET_VLAN_NAME_TYPE_CMD,
+ SET_VLAN_FLAG_CMD,
+ GET_VLAN_REALDEV_NAME_CMD, /* If this works, you know it's a VLAN device, btw */
+ GET_VLAN_VID_CMD /* Get the VID of this VLAN (specified by name) */
+};
+
+enum vlan_flags {
+ VLAN_FLAG_REORDER_HDR = 0x1,
+ VLAN_FLAG_GVRP = 0x2,
+ VLAN_FLAG_LOOSE_BINDING = 0x4,
+ VLAN_FLAG_MVRP = 0x8,
+};
+
+enum vlan_name_types {
+ VLAN_NAME_TYPE_PLUS_VID, /* Name will look like: vlan0005 */
+ VLAN_NAME_TYPE_RAW_PLUS_VID, /* name will look like: eth1.0005 */
+ VLAN_NAME_TYPE_PLUS_VID_NO_PAD, /* Name will look like: vlan5 */
+ VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD, /* Name will look like: eth0.5 */
+ VLAN_NAME_TYPE_HIGHEST
+};
+
+struct vlan_ioctl_args {
+ int cmd; /* Should be one of the vlan_ioctl_cmds enum above. */
+ char device1[24];
+
+ union {
+ char device2[24];
+ int VID;
+ unsigned int skb_priority;
+ unsigned int name_type;
+ unsigned int bind_type;
+ unsigned int flag; /* Matches vlan_dev_priv flags */
+ } u;
+
+ short vlan_qos;
+};
+
+#endif /* _LINUX_IF_VLAN_H_ */
diff --git a/iproute2/include/linux/ila.h b/iproute2/include/linux/ila.h
new file mode 100644
index 0000000..4f9e1de
--- /dev/null
+++ b/iproute2/include/linux/ila.h
@@ -0,0 +1,37 @@
+/* ila.h - ILA Interface */
+
+#ifndef _LINUX_ILA_H
+#define _LINUX_ILA_H
+
+/* NETLINK_GENERIC related info */
+#define ILA_GENL_NAME "ila"
+#define ILA_GENL_VERSION 0x1
+
+enum {
+ ILA_ATTR_UNSPEC,
+ ILA_ATTR_LOCATOR, /* u64 */
+ ILA_ATTR_IDENTIFIER, /* u64 */
+ ILA_ATTR_LOCATOR_MATCH, /* u64 */
+ ILA_ATTR_IFINDEX, /* s32 */
+ ILA_ATTR_DIR, /* u32 */
+
+ __ILA_ATTR_MAX,
+};
+
+#define ILA_ATTR_MAX (__ILA_ATTR_MAX - 1)
+
+enum {
+ ILA_CMD_UNSPEC,
+ ILA_CMD_ADD,
+ ILA_CMD_DEL,
+ ILA_CMD_GET,
+
+ __ILA_CMD_MAX,
+};
+
+#define ILA_CMD_MAX (__ILA_CMD_MAX - 1)
+
+#define ILA_DIR_IN (1 << 0)
+#define ILA_DIR_OUT (1 << 1)
+
+#endif /* _LINUX_ILA_H */
diff --git a/iproute2/include/linux/in.h b/iproute2/include/linux/in.h
new file mode 100644
index 0000000..194b43b
--- /dev/null
+++ b/iproute2/include/linux/in.h
@@ -0,0 +1,299 @@
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * Definitions of the Internet Protocol.
+ *
+ * Version: @(#)in.h 1.0.1 04/21/93
+ *
+ * Authors: Original taken from the GNU Project <netinet/in.h> file.
+ * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _LINUX_IN_H
+#define _LINUX_IN_H
+
+#include <linux/types.h>
+#include <linux/libc-compat.h>
+#include <linux/socket.h>
+
+#if __UAPI_DEF_IN_IPPROTO
+/* Standard well-defined IP protocols. */
+enum {
+ IPPROTO_IP = 0, /* Dummy protocol for TCP */
+#define IPPROTO_IP IPPROTO_IP
+ IPPROTO_ICMP = 1, /* Internet Control Message Protocol */
+#define IPPROTO_ICMP IPPROTO_ICMP
+ IPPROTO_IGMP = 2, /* Internet Group Management Protocol */
+#define IPPROTO_IGMP IPPROTO_IGMP
+ IPPROTO_IPIP = 4, /* IPIP tunnels (older KA9Q tunnels use 94) */
+#define IPPROTO_IPIP IPPROTO_IPIP
+ IPPROTO_TCP = 6, /* Transmission Control Protocol */
+#define IPPROTO_TCP IPPROTO_TCP
+ IPPROTO_EGP = 8, /* Exterior Gateway Protocol */
+#define IPPROTO_EGP IPPROTO_EGP
+ IPPROTO_PUP = 12, /* PUP protocol */
+#define IPPROTO_PUP IPPROTO_PUP
+ IPPROTO_UDP = 17, /* User Datagram Protocol */
+#define IPPROTO_UDP IPPROTO_UDP
+ IPPROTO_IDP = 22, /* XNS IDP protocol */
+#define IPPROTO_IDP IPPROTO_IDP
+ IPPROTO_TP = 29, /* SO Transport Protocol Class 4 */
+#define IPPROTO_TP IPPROTO_TP
+ IPPROTO_DCCP = 33, /* Datagram Congestion Control Protocol */
+#define IPPROTO_DCCP IPPROTO_DCCP
+ IPPROTO_IPV6 = 41, /* IPv6-in-IPv4 tunnelling */
+#define IPPROTO_IPV6 IPPROTO_IPV6
+ IPPROTO_RSVP = 46, /* RSVP Protocol */
+#define IPPROTO_RSVP IPPROTO_RSVP
+ IPPROTO_GRE = 47, /* Cisco GRE tunnels (rfc 1701,1702) */
+#define IPPROTO_GRE IPPROTO_GRE
+ IPPROTO_ESP = 50, /* Encapsulation Security Payload protocol */
+#define IPPROTO_ESP IPPROTO_ESP
+ IPPROTO_AH = 51, /* Authentication Header protocol */
+#define IPPROTO_AH IPPROTO_AH
+ IPPROTO_MTP = 92, /* Multicast Transport Protocol */
+#define IPPROTO_MTP IPPROTO_MTP
+ IPPROTO_BEETPH = 94, /* IP option pseudo header for BEET */
+#define IPPROTO_BEETPH IPPROTO_BEETPH
+ IPPROTO_ENCAP = 98, /* Encapsulation Header */
+#define IPPROTO_ENCAP IPPROTO_ENCAP
+ IPPROTO_PIM = 103, /* Protocol Independent Multicast */
+#define IPPROTO_PIM IPPROTO_PIM
+ IPPROTO_COMP = 108, /* Compression Header Protocol */
+#define IPPROTO_COMP IPPROTO_COMP
+ IPPROTO_SCTP = 132, /* Stream Control Transport Protocol */
+#define IPPROTO_SCTP IPPROTO_SCTP
+ IPPROTO_UDPLITE = 136, /* UDP-Lite (RFC 3828) */
+#define IPPROTO_UDPLITE IPPROTO_UDPLITE
+ IPPROTO_MPLS = 137, /* MPLS in IP (RFC 4023) */
+#define IPPROTO_MPLS IPPROTO_MPLS
+ IPPROTO_RAW = 255, /* Raw IP packets */
+#define IPPROTO_RAW IPPROTO_RAW
+ IPPROTO_MAX
+};
+#endif
+
+#if __UAPI_DEF_IN_ADDR
+/* Internet address. */
+struct in_addr {
+ __be32 s_addr;
+};
+#endif
+
+#define IP_TOS 1
+#define IP_TTL 2
+#define IP_HDRINCL 3
+#define IP_OPTIONS 4
+#define IP_ROUTER_ALERT 5
+#define IP_RECVOPTS 6
+#define IP_RETOPTS 7
+#define IP_PKTINFO 8
+#define IP_PKTOPTIONS 9
+#define IP_MTU_DISCOVER 10
+#define IP_RECVERR 11
+#define IP_RECVTTL 12
+#define IP_RECVTOS 13
+#define IP_MTU 14
+#define IP_FREEBIND 15
+#define IP_IPSEC_POLICY 16
+#define IP_XFRM_POLICY 17
+#define IP_PASSSEC 18
+#define IP_TRANSPARENT 19
+
+/* BSD compatibility */
+#define IP_RECVRETOPTS IP_RETOPTS
+
+/* TProxy original addresses */
+#define IP_ORIGDSTADDR 20
+#define IP_RECVORIGDSTADDR IP_ORIGDSTADDR
+
+#define IP_MINTTL 21
+#define IP_NODEFRAG 22
+#define IP_CHECKSUM 23
+#define IP_BIND_ADDRESS_NO_PORT 24
+
+/* IP_MTU_DISCOVER values */
+#define IP_PMTUDISC_DONT 0 /* Never send DF frames */
+#define IP_PMTUDISC_WANT 1 /* Use per route hints */
+#define IP_PMTUDISC_DO 2 /* Always DF */
+#define IP_PMTUDISC_PROBE 3 /* Ignore dst pmtu */
+/* Always use interface mtu (ignores dst pmtu) but don't set DF flag.
+ * Also incoming ICMP frag_needed notifications will be ignored on
+ * this socket to prevent accepting spoofed ones.
+ */
+#define IP_PMTUDISC_INTERFACE 4
+/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get
+ * fragmented if they exeed the interface mtu
+ */
+#define IP_PMTUDISC_OMIT 5
+
+#define IP_MULTICAST_IF 32
+#define IP_MULTICAST_TTL 33
+#define IP_MULTICAST_LOOP 34
+#define IP_ADD_MEMBERSHIP 35
+#define IP_DROP_MEMBERSHIP 36
+#define IP_UNBLOCK_SOURCE 37
+#define IP_BLOCK_SOURCE 38
+#define IP_ADD_SOURCE_MEMBERSHIP 39
+#define IP_DROP_SOURCE_MEMBERSHIP 40
+#define IP_MSFILTER 41
+#define MCAST_JOIN_GROUP 42
+#define MCAST_BLOCK_SOURCE 43
+#define MCAST_UNBLOCK_SOURCE 44
+#define MCAST_LEAVE_GROUP 45
+#define MCAST_JOIN_SOURCE_GROUP 46
+#define MCAST_LEAVE_SOURCE_GROUP 47
+#define MCAST_MSFILTER 48
+#define IP_MULTICAST_ALL 49
+#define IP_UNICAST_IF 50
+
+#define MCAST_EXCLUDE 0
+#define MCAST_INCLUDE 1
+
+/* These need to appear somewhere around here */
+#define IP_DEFAULT_MULTICAST_TTL 1
+#define IP_DEFAULT_MULTICAST_LOOP 1
+
+/* Request struct for multicast socket ops */
+
+#if __UAPI_DEF_IP_MREQ
+struct ip_mreq {
+ struct in_addr imr_multiaddr; /* IP multicast address of group */
+ struct in_addr imr_interface; /* local IP address of interface */
+};
+
+struct ip_mreqn {
+ struct in_addr imr_multiaddr; /* IP multicast address of group */
+ struct in_addr imr_address; /* local IP address of interface */
+ int imr_ifindex; /* Interface index */
+};
+
+struct ip_mreq_source {
+ __be32 imr_multiaddr;
+ __be32 imr_interface;
+ __be32 imr_sourceaddr;
+};
+
+struct ip_msfilter {
+ __be32 imsf_multiaddr;
+ __be32 imsf_interface;
+ __u32 imsf_fmode;
+ __u32 imsf_numsrc;
+ __be32 imsf_slist[1];
+};
+
+#define IP_MSFILTER_SIZE(numsrc) \
+ (sizeof(struct ip_msfilter) - sizeof(__u32) \
+ + (numsrc) * sizeof(__u32))
+
+struct group_req {
+ __u32 gr_interface; /* interface index */
+ struct __kernel_sockaddr_storage gr_group; /* group address */
+};
+
+struct group_source_req {
+ __u32 gsr_interface; /* interface index */
+ struct __kernel_sockaddr_storage gsr_group; /* group address */
+ struct __kernel_sockaddr_storage gsr_source; /* source address */
+};
+
+struct group_filter {
+ __u32 gf_interface; /* interface index */
+ struct __kernel_sockaddr_storage gf_group; /* multicast address */
+ __u32 gf_fmode; /* filter mode */
+ __u32 gf_numsrc; /* number of sources */
+ struct __kernel_sockaddr_storage gf_slist[1]; /* interface index */
+};
+
+#define GROUP_FILTER_SIZE(numsrc) \
+ (sizeof(struct group_filter) - sizeof(struct __kernel_sockaddr_storage) \
+ + (numsrc) * sizeof(struct __kernel_sockaddr_storage))
+#endif
+
+#if __UAPI_DEF_IN_PKTINFO
+struct in_pktinfo {
+ int ipi_ifindex;
+ struct in_addr ipi_spec_dst;
+ struct in_addr ipi_addr;
+};
+#endif
+
+/* Structure describing an Internet (IP) socket address. */
+#if __UAPI_DEF_SOCKADDR_IN
+#define __SOCK_SIZE__ 16 /* sizeof(struct sockaddr) */
+struct sockaddr_in {
+ __kernel_sa_family_t sin_family; /* Address family */
+ __be16 sin_port; /* Port number */
+ struct in_addr sin_addr; /* Internet address */
+
+ /* Pad to size of `struct sockaddr'. */
+ unsigned char __pad[__SOCK_SIZE__ - sizeof(short int) -
+ sizeof(unsigned short int) - sizeof(struct in_addr)];
+};
+#define sin_zero __pad /* for BSD UNIX comp. -FvK */
+#endif
+
+#if __UAPI_DEF_IN_CLASS
+/*
+ * Definitions of the bits in an Internet address integer.
+ * On subnets, host and network parts are found according
+ * to the subnet mask, not these masks.
+ */
+#define IN_CLASSA(a) ((((long int) (a)) & 0x80000000) == 0)
+#define IN_CLASSA_NET 0xff000000
+#define IN_CLASSA_NSHIFT 24
+#define IN_CLASSA_HOST (0xffffffff & ~IN_CLASSA_NET)
+#define IN_CLASSA_MAX 128
+
+#define IN_CLASSB(a) ((((long int) (a)) & 0xc0000000) == 0x80000000)
+#define IN_CLASSB_NET 0xffff0000
+#define IN_CLASSB_NSHIFT 16
+#define IN_CLASSB_HOST (0xffffffff & ~IN_CLASSB_NET)
+#define IN_CLASSB_MAX 65536
+
+#define IN_CLASSC(a) ((((long int) (a)) & 0xe0000000) == 0xc0000000)
+#define IN_CLASSC_NET 0xffffff00
+#define IN_CLASSC_NSHIFT 8
+#define IN_CLASSC_HOST (0xffffffff & ~IN_CLASSC_NET)
+
+#define IN_CLASSD(a) ((((long int) (a)) & 0xf0000000) == 0xe0000000)
+#define IN_MULTICAST(a) IN_CLASSD(a)
+#define IN_MULTICAST_NET 0xF0000000
+
+#define IN_EXPERIMENTAL(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000)
+#define IN_BADCLASS(a) IN_EXPERIMENTAL((a))
+
+/* Address to accept any incoming messages. */
+#define INADDR_ANY ((unsigned long int) 0x00000000)
+
+/* Address to send to all hosts. */
+#define INADDR_BROADCAST ((unsigned long int) 0xffffffff)
+
+/* Address indicating an error return. */
+#define INADDR_NONE ((unsigned long int) 0xffffffff)
+
+/* Network number for local host loopback. */
+#define IN_LOOPBACKNET 127
+
+/* Address to loopback in software to local host. */
+#define INADDR_LOOPBACK 0x7f000001 /* 127.0.0.1 */
+#define IN_LOOPBACK(a) ((((long int) (a)) & 0xff000000) == 0x7f000000)
+
+/* Defines for Multicast INADDR */
+#define INADDR_UNSPEC_GROUP 0xe0000000U /* 224.0.0.0 */
+#define INADDR_ALLHOSTS_GROUP 0xe0000001U /* 224.0.0.1 */
+#define INADDR_ALLRTRS_GROUP 0xe0000002U /* 224.0.0.2 */
+#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU /* 224.0.0.255 */
+#endif
+
+/* <asm/byteorder.h> contains the htonl type stuff.. */
+#include <asm/byteorder.h>
+
+
+#endif /* _LINUX_IN_H */
diff --git a/iproute2/include/linux/in6.h b/iproute2/include/linux/in6.h
new file mode 100644
index 0000000..aa5b66d
--- /dev/null
+++ b/iproute2/include/linux/in6.h
@@ -0,0 +1,294 @@
+/*
+ * Types and definitions for AF_INET6
+ * Linux INET6 implementation
+ *
+ * Authors:
+ * Pedro Roque <roque@di.fc.ul.pt>
+ *
+ * Sources:
+ * IPv6 Program Interfaces for BSD Systems
+ * <draft-ietf-ipngwg-bsd-api-05.txt>
+ *
+ * Advanced Sockets API for IPv6
+ * <draft-stevens-advanced-api-00.txt>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _LINUX_IN6_H
+#define _LINUX_IN6_H
+
+#include <linux/types.h>
+#include <linux/libc-compat.h>
+
+/*
+ * IPv6 address structure
+ */
+
+#if __UAPI_DEF_IN6_ADDR
+struct in6_addr {
+ union {
+ __u8 u6_addr8[16];
+#if __UAPI_DEF_IN6_ADDR_ALT
+ __be16 u6_addr16[8];
+ __be32 u6_addr32[4];
+#endif
+ } in6_u;
+#define s6_addr in6_u.u6_addr8
+#if __UAPI_DEF_IN6_ADDR_ALT
+#define s6_addr16 in6_u.u6_addr16
+#define s6_addr32 in6_u.u6_addr32
+#endif
+};
+#endif /* __UAPI_DEF_IN6_ADDR */
+
+#if __UAPI_DEF_SOCKADDR_IN6
+struct sockaddr_in6 {
+ unsigned short int sin6_family; /* AF_INET6 */
+ __be16 sin6_port; /* Transport layer port # */
+ __be32 sin6_flowinfo; /* IPv6 flow information */
+ struct in6_addr sin6_addr; /* IPv6 address */
+ __u32 sin6_scope_id; /* scope id (new in RFC2553) */
+};
+#endif /* __UAPI_DEF_SOCKADDR_IN6 */
+
+#if __UAPI_DEF_IPV6_MREQ
+struct ipv6_mreq {
+ /* IPv6 multicast address of group */
+ struct in6_addr ipv6mr_multiaddr;
+
+ /* local IPv6 address of interface */
+ int ipv6mr_ifindex;
+};
+#endif /* __UAPI_DEF_IVP6_MREQ */
+
+#define ipv6mr_acaddr ipv6mr_multiaddr
+
+struct in6_flowlabel_req {
+ struct in6_addr flr_dst;
+ __be32 flr_label;
+ __u8 flr_action;
+ __u8 flr_share;
+ __u16 flr_flags;
+ __u16 flr_expires;
+ __u16 flr_linger;
+ __u32 __flr_pad;
+ /* Options in format of IPV6_PKTOPTIONS */
+};
+
+#define IPV6_FL_A_GET 0
+#define IPV6_FL_A_PUT 1
+#define IPV6_FL_A_RENEW 2
+
+#define IPV6_FL_F_CREATE 1
+#define IPV6_FL_F_EXCL 2
+#define IPV6_FL_F_REFLECT 4
+#define IPV6_FL_F_REMOTE 8
+
+#define IPV6_FL_S_NONE 0
+#define IPV6_FL_S_EXCL 1
+#define IPV6_FL_S_PROCESS 2
+#define IPV6_FL_S_USER 3
+#define IPV6_FL_S_ANY 255
+
+
+/*
+ * Bitmask constant declarations to help applications select out the
+ * flow label and priority fields.
+ *
+ * Note that this are in host byte order while the flowinfo field of
+ * sockaddr_in6 is in network byte order.
+ */
+
+#define IPV6_FLOWINFO_FLOWLABEL 0x000fffff
+#define IPV6_FLOWINFO_PRIORITY 0x0ff00000
+
+/* These definitions are obsolete */
+#define IPV6_PRIORITY_UNCHARACTERIZED 0x0000
+#define IPV6_PRIORITY_FILLER 0x0100
+#define IPV6_PRIORITY_UNATTENDED 0x0200
+#define IPV6_PRIORITY_RESERVED1 0x0300
+#define IPV6_PRIORITY_BULK 0x0400
+#define IPV6_PRIORITY_RESERVED2 0x0500
+#define IPV6_PRIORITY_INTERACTIVE 0x0600
+#define IPV6_PRIORITY_CONTROL 0x0700
+#define IPV6_PRIORITY_8 0x0800
+#define IPV6_PRIORITY_9 0x0900
+#define IPV6_PRIORITY_10 0x0a00
+#define IPV6_PRIORITY_11 0x0b00
+#define IPV6_PRIORITY_12 0x0c00
+#define IPV6_PRIORITY_13 0x0d00
+#define IPV6_PRIORITY_14 0x0e00
+#define IPV6_PRIORITY_15 0x0f00
+
+/*
+ * IPV6 extension headers
+ */
+#if __UAPI_DEF_IPPROTO_V6
+#define IPPROTO_HOPOPTS 0 /* IPv6 hop-by-hop options */
+#define IPPROTO_ROUTING 43 /* IPv6 routing header */
+#define IPPROTO_FRAGMENT 44 /* IPv6 fragmentation header */
+#define IPPROTO_ICMPV6 58 /* ICMPv6 */
+#define IPPROTO_NONE 59 /* IPv6 no next header */
+#define IPPROTO_DSTOPTS 60 /* IPv6 destination options */
+#define IPPROTO_MH 135 /* IPv6 mobility header */
+#endif /* __UAPI_DEF_IPPROTO_V6 */
+
+/*
+ * IPv6 TLV options.
+ */
+#define IPV6_TLV_PAD1 0
+#define IPV6_TLV_PADN 1
+#define IPV6_TLV_ROUTERALERT 5
+#define IPV6_TLV_JUMBO 194
+#define IPV6_TLV_HAO 201 /* home address option */
+
+/*
+ * IPV6 socket options
+ */
+#if __UAPI_DEF_IPV6_OPTIONS
+#define IPV6_ADDRFORM 1
+#define IPV6_2292PKTINFO 2
+#define IPV6_2292HOPOPTS 3
+#define IPV6_2292DSTOPTS 4
+#define IPV6_2292RTHDR 5
+#define IPV6_2292PKTOPTIONS 6
+#define IPV6_CHECKSUM 7
+#define IPV6_2292HOPLIMIT 8
+#define IPV6_NEXTHOP 9
+#define IPV6_AUTHHDR 10 /* obsolete */
+#define IPV6_FLOWINFO 11
+
+#define IPV6_UNICAST_HOPS 16
+#define IPV6_MULTICAST_IF 17
+#define IPV6_MULTICAST_HOPS 18
+#define IPV6_MULTICAST_LOOP 19
+#define IPV6_ADD_MEMBERSHIP 20
+#define IPV6_DROP_MEMBERSHIP 21
+#define IPV6_ROUTER_ALERT 22
+#define IPV6_MTU_DISCOVER 23
+#define IPV6_MTU 24
+#define IPV6_RECVERR 25
+#define IPV6_V6ONLY 26
+#define IPV6_JOIN_ANYCAST 27
+#define IPV6_LEAVE_ANYCAST 28
+
+/* IPV6_MTU_DISCOVER values */
+#define IPV6_PMTUDISC_DONT 0
+#define IPV6_PMTUDISC_WANT 1
+#define IPV6_PMTUDISC_DO 2
+#define IPV6_PMTUDISC_PROBE 3
+/* same as IPV6_PMTUDISC_PROBE, provided for symetry with IPv4
+ * also see comments on IP_PMTUDISC_INTERFACE
+ */
+#define IPV6_PMTUDISC_INTERFACE 4
+/* weaker version of IPV6_PMTUDISC_INTERFACE, which allows packets to
+ * get fragmented if they exceed the interface mtu
+ */
+#define IPV6_PMTUDISC_OMIT 5
+
+/* Flowlabel */
+#define IPV6_FLOWLABEL_MGR 32
+#define IPV6_FLOWINFO_SEND 33
+
+#define IPV6_IPSEC_POLICY 34
+#define IPV6_XFRM_POLICY 35
+#define IPV6_HDRINCL 36
+#endif
+
+/*
+ * Multicast:
+ * Following socket options are shared between IPv4 and IPv6.
+ *
+ * MCAST_JOIN_GROUP 42
+ * MCAST_BLOCK_SOURCE 43
+ * MCAST_UNBLOCK_SOURCE 44
+ * MCAST_LEAVE_GROUP 45
+ * MCAST_JOIN_SOURCE_GROUP 46
+ * MCAST_LEAVE_SOURCE_GROUP 47
+ * MCAST_MSFILTER 48
+ */
+
+/*
+ * Advanced API (RFC3542) (1)
+ *
+ * Note: IPV6_RECVRTHDRDSTOPTS does not exist. see net/ipv6/datagram.c.
+ */
+
+#define IPV6_RECVPKTINFO 49
+#define IPV6_PKTINFO 50
+#define IPV6_RECVHOPLIMIT 51
+#define IPV6_HOPLIMIT 52
+#define IPV6_RECVHOPOPTS 53
+#define IPV6_HOPOPTS 54
+#define IPV6_RTHDRDSTOPTS 55
+#define IPV6_RECVRTHDR 56
+#define IPV6_RTHDR 57
+#define IPV6_RECVDSTOPTS 58
+#define IPV6_DSTOPTS 59
+#define IPV6_RECVPATHMTU 60
+#define IPV6_PATHMTU 61
+#define IPV6_DONTFRAG 62
+#if 0 /* not yet */
+#define IPV6_USE_MIN_MTU 63
+#endif
+
+/*
+ * Netfilter (1)
+ *
+ * Following socket options are used in ip6_tables;
+ * see include/linux/netfilter_ipv6/ip6_tables.h.
+ *
+ * IP6T_SO_SET_REPLACE / IP6T_SO_GET_INFO 64
+ * IP6T_SO_SET_ADD_COUNTERS / IP6T_SO_GET_ENTRIES 65
+ */
+
+/*
+ * Advanced API (RFC3542) (2)
+ */
+#define IPV6_RECVTCLASS 66
+#define IPV6_TCLASS 67
+
+/*
+ * Netfilter (2)
+ *
+ * Following socket options are used in ip6_tables;
+ * see include/linux/netfilter_ipv6/ip6_tables.h.
+ *
+ * IP6T_SO_GET_REVISION_MATCH 68
+ * IP6T_SO_GET_REVISION_TARGET 69
+ * IP6T_SO_ORIGINAL_DST 80
+ */
+
+#define IPV6_AUTOFLOWLABEL 70
+/* RFC5014: Source address selection */
+#define IPV6_ADDR_PREFERENCES 72
+
+#define IPV6_PREFER_SRC_TMP 0x0001
+#define IPV6_PREFER_SRC_PUBLIC 0x0002
+#define IPV6_PREFER_SRC_PUBTMP_DEFAULT 0x0100
+#define IPV6_PREFER_SRC_COA 0x0004
+#define IPV6_PREFER_SRC_HOME 0x0400
+#define IPV6_PREFER_SRC_CGA 0x0008
+#define IPV6_PREFER_SRC_NONCGA 0x0800
+
+/* RFC5082: Generalized Ttl Security Mechanism */
+#define IPV6_MINHOPCOUNT 73
+
+#define IPV6_ORIGDSTADDR 74
+#define IPV6_RECVORIGDSTADDR IPV6_ORIGDSTADDR
+#define IPV6_TRANSPARENT 75
+#define IPV6_UNICAST_IF 76
+
+/*
+ * Multicast Routing:
+ * see include/uapi/linux/mroute6.h.
+ *
+ * MRT6_BASE 200
+ * ...
+ * MRT6_MAX
+ */
+#endif /* _LINUX_IN6_H */
diff --git a/iproute2/include/linux/inet_diag.h b/iproute2/include/linux/inet_diag.h
new file mode 100644
index 0000000..1db4116
--- /dev/null
+++ b/iproute2/include/linux/inet_diag.h
@@ -0,0 +1,152 @@
+#ifndef _INET_DIAG_H_
+#define _INET_DIAG_H_
+
+#include <linux/types.h>
+
+/* Just some random number */
+#define TCPDIAG_GETSOCK 18
+#define DCCPDIAG_GETSOCK 19
+
+#define INET_DIAG_GETSOCK_MAX 24
+
+/* Socket identity */
+struct inet_diag_sockid {
+ __be16 idiag_sport;
+ __be16 idiag_dport;
+ __be32 idiag_src[4];
+ __be32 idiag_dst[4];
+ __u32 idiag_if;
+ __u32 idiag_cookie[2];
+#define INET_DIAG_NOCOOKIE (~0U)
+};
+
+/* Request structure */
+
+struct inet_diag_req {
+ __u8 idiag_family; /* Family of addresses. */
+ __u8 idiag_src_len;
+ __u8 idiag_dst_len;
+ __u8 idiag_ext; /* Query extended information */
+
+ struct inet_diag_sockid id;
+
+ __u32 idiag_states; /* States to dump */
+ __u32 idiag_dbs; /* Tables to dump (NI) */
+};
+
+struct inet_diag_req_v2 {
+ __u8 sdiag_family;
+ __u8 sdiag_protocol;
+ __u8 idiag_ext;
+ __u8 pad;
+ __u32 idiag_states;
+ struct inet_diag_sockid id;
+};
+
+enum {
+ INET_DIAG_REQ_NONE,
+ INET_DIAG_REQ_BYTECODE,
+};
+
+#define INET_DIAG_REQ_MAX INET_DIAG_REQ_BYTECODE
+
+/* Bytecode is sequence of 4 byte commands followed by variable arguments.
+ * All the commands identified by "code" are conditional jumps forward:
+ * to offset cc+"yes" or to offset cc+"no". "yes" is supposed to be
+ * length of the command and its arguments.
+ */
+
+struct inet_diag_bc_op {
+ unsigned char code;
+ unsigned char yes;
+ unsigned short no;
+};
+
+enum {
+ INET_DIAG_BC_NOP,
+ INET_DIAG_BC_JMP,
+ INET_DIAG_BC_S_GE,
+ INET_DIAG_BC_S_LE,
+ INET_DIAG_BC_D_GE,
+ INET_DIAG_BC_D_LE,
+ INET_DIAG_BC_AUTO,
+ INET_DIAG_BC_S_COND,
+ INET_DIAG_BC_D_COND,
+};
+
+struct inet_diag_hostcond {
+ __u8 family;
+ __u8 prefix_len;
+ int port;
+ __be32 addr[0];
+};
+
+/* Base info structure. It contains socket identity (addrs/ports/cookie)
+ * and, alas, the information shown by netstat. */
+struct inet_diag_msg {
+ __u8 idiag_family;
+ __u8 idiag_state;
+ __u8 idiag_timer;
+ __u8 idiag_retrans;
+
+ struct inet_diag_sockid id;
+
+ __u32 idiag_expires;
+ __u32 idiag_rqueue;
+ __u32 idiag_wqueue;
+ __u32 idiag_uid;
+ __u32 idiag_inode;
+};
+
+/* Extensions */
+
+enum {
+ INET_DIAG_NONE,
+ INET_DIAG_MEMINFO,
+ INET_DIAG_INFO,
+ INET_DIAG_VEGASINFO,
+ INET_DIAG_CONG,
+ INET_DIAG_TOS,
+ INET_DIAG_TCLASS,
+ INET_DIAG_SKMEMINFO,
+ INET_DIAG_SHUTDOWN,
+ INET_DIAG_DCTCPINFO,
+ INET_DIAG_PROTOCOL, /* response attribute only */
+ INET_DIAG_SKV6ONLY,
+};
+
+#define INET_DIAG_MAX INET_DIAG_SKV6ONLY
+
+/* INET_DIAG_MEM */
+
+struct inet_diag_meminfo {
+ __u32 idiag_rmem;
+ __u32 idiag_wmem;
+ __u32 idiag_fmem;
+ __u32 idiag_tmem;
+};
+
+/* INET_DIAG_VEGASINFO */
+
+struct tcpvegas_info {
+ __u32 tcpv_enabled;
+ __u32 tcpv_rttcnt;
+ __u32 tcpv_rtt;
+ __u32 tcpv_minrtt;
+};
+
+/* INET_DIAG_DCTCPINFO */
+
+struct tcp_dctcp_info {
+ __u16 dctcp_enabled;
+ __u16 dctcp_ce_state;
+ __u32 dctcp_alpha;
+ __u32 dctcp_ab_ecn;
+ __u32 dctcp_ab_tot;
+};
+
+union tcp_cc_info {
+ struct tcpvegas_info vegas;
+ struct tcp_dctcp_info dctcp;
+};
+#endif /* _INET_DIAG_H_ */
diff --git a/iproute2/include/linux/ip6_tunnel.h b/iproute2/include/linux/ip6_tunnel.h
new file mode 100644
index 0000000..48af63c
--- /dev/null
+++ b/iproute2/include/linux/ip6_tunnel.h
@@ -0,0 +1,51 @@
+#ifndef _IP6_TUNNEL_H
+#define _IP6_TUNNEL_H
+
+#include <linux/types.h>
+
+#define IPV6_TLV_TNL_ENCAP_LIMIT 4
+#define IPV6_DEFAULT_TNL_ENCAP_LIMIT 4
+
+/* don't add encapsulation limit if one isn't present in inner packet */
+#define IP6_TNL_F_IGN_ENCAP_LIMIT 0x1
+/* copy the traffic class field from the inner packet */
+#define IP6_TNL_F_USE_ORIG_TCLASS 0x2
+/* copy the flowlabel from the inner packet */
+#define IP6_TNL_F_USE_ORIG_FLOWLABEL 0x4
+/* being used for Mobile IPv6 */
+#define IP6_TNL_F_MIP6_DEV 0x8
+/* copy DSCP from the outer packet */
+#define IP6_TNL_F_RCV_DSCP_COPY 0x10
+/* copy fwmark from inner packet */
+#define IP6_TNL_F_USE_ORIG_FWMARK 0x20
+
+struct ip6_tnl_parm {
+ char name[IFNAMSIZ]; /* name of tunnel device */
+ int link; /* ifindex of underlying L2 interface */
+ __u8 proto; /* tunnel protocol */
+ __u8 encap_limit; /* encapsulation limit for tunnel */
+ __u8 hop_limit; /* hop limit for tunnel */
+ __be32 flowinfo; /* traffic class and flowlabel for tunnel */
+ __u32 flags; /* tunnel flags */
+ struct in6_addr laddr; /* local tunnel end-point address */
+ struct in6_addr raddr; /* remote tunnel end-point address */
+};
+
+struct ip6_tnl_parm2 {
+ char name[IFNAMSIZ]; /* name of tunnel device */
+ int link; /* ifindex of underlying L2 interface */
+ __u8 proto; /* tunnel protocol */
+ __u8 encap_limit; /* encapsulation limit for tunnel */
+ __u8 hop_limit; /* hop limit for tunnel */
+ __be32 flowinfo; /* traffic class and flowlabel for tunnel */
+ __u32 flags; /* tunnel flags */
+ struct in6_addr laddr; /* local tunnel end-point address */
+ struct in6_addr raddr; /* remote tunnel end-point address */
+
+ __be16 i_flags;
+ __be16 o_flags;
+ __be32 i_key;
+ __be32 o_key;
+};
+
+#endif
diff --git a/iproute2/include/linux/l2tp.h b/iproute2/include/linux/l2tp.h
new file mode 100644
index 0000000..5b0e36d
--- /dev/null
+++ b/iproute2/include/linux/l2tp.h
@@ -0,0 +1,181 @@
+/*
+ * L2TP-over-IP socket for L2TPv3.
+ *
+ * Author: James Chapman <jchapman@katalix.com>
+ */
+
+#ifndef _LINUX_L2TP_H_
+#define _LINUX_L2TP_H_
+
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <netinet/in.h>
+
+#define IPPROTO_L2TP 115
+
+/**
+ * struct sockaddr_l2tpip - the sockaddr structure for L2TP-over-IP sockets
+ * @l2tp_family: address family number AF_L2TPIP.
+ * @l2tp_addr: protocol specific address information
+ * @l2tp_conn_id: connection id of tunnel
+ */
+#define __SOCK_SIZE__ 16 /* sizeof(struct sockaddr) */
+struct sockaddr_l2tpip {
+ /* The first fields must match struct sockaddr_in */
+ __kernel_sa_family_t l2tp_family; /* AF_INET */
+ __be16 l2tp_unused; /* INET port number (unused) */
+ struct in_addr l2tp_addr; /* Internet address */
+
+ __u32 l2tp_conn_id; /* Connection ID of tunnel */
+
+ /* Pad to size of `struct sockaddr'. */
+ unsigned char __pad[sizeof(struct sockaddr) -
+ sizeof(__kernel_sa_family_t) -
+ sizeof(__be16) - sizeof(struct in_addr) -
+ sizeof(__u32)];
+};
+
+/**
+ * struct sockaddr_l2tpip6 - the sockaddr structure for L2TP-over-IPv6 sockets
+ * @l2tp_family: address family number AF_L2TPIP.
+ * @l2tp_addr: protocol specific address information
+ * @l2tp_conn_id: connection id of tunnel
+ */
+struct sockaddr_l2tpip6 {
+ /* The first fields must match struct sockaddr_in6 */
+ __kernel_sa_family_t l2tp_family; /* AF_INET6 */
+ __be16 l2tp_unused; /* INET port number (unused) */
+ __be32 l2tp_flowinfo; /* IPv6 flow information */
+ struct in6_addr l2tp_addr; /* IPv6 address */
+ __u32 l2tp_scope_id; /* scope id (new in RFC2553) */
+ __u32 l2tp_conn_id; /* Connection ID of tunnel */
+};
+
+/*****************************************************************************
+ * NETLINK_GENERIC netlink family.
+ *****************************************************************************/
+
+/*
+ * Commands.
+ * Valid TLVs of each command are:-
+ * TUNNEL_CREATE - CONN_ID, pw_type, netns, ifname, ipinfo, udpinfo, udpcsum, vlanid
+ * TUNNEL_DELETE - CONN_ID
+ * TUNNEL_MODIFY - CONN_ID, udpcsum
+ * TUNNEL_GETSTATS - CONN_ID, (stats)
+ * TUNNEL_GET - CONN_ID, (...)
+ * SESSION_CREATE - SESSION_ID, PW_TYPE, offset, data_seq, cookie, peer_cookie, offset, l2spec
+ * SESSION_DELETE - SESSION_ID
+ * SESSION_MODIFY - SESSION_ID, data_seq
+ * SESSION_GET - SESSION_ID, (...)
+ * SESSION_GETSTATS - SESSION_ID, (stats)
+ *
+ */
+enum {
+ L2TP_CMD_NOOP,
+ L2TP_CMD_TUNNEL_CREATE,
+ L2TP_CMD_TUNNEL_DELETE,
+ L2TP_CMD_TUNNEL_MODIFY,
+ L2TP_CMD_TUNNEL_GET,
+ L2TP_CMD_SESSION_CREATE,
+ L2TP_CMD_SESSION_DELETE,
+ L2TP_CMD_SESSION_MODIFY,
+ L2TP_CMD_SESSION_GET,
+ __L2TP_CMD_MAX,
+};
+
+#define L2TP_CMD_MAX (__L2TP_CMD_MAX - 1)
+
+/*
+ * ATTR types defined for L2TP
+ */
+enum {
+ L2TP_ATTR_NONE, /* no data */
+ L2TP_ATTR_PW_TYPE, /* u16, enum l2tp_pwtype */
+ L2TP_ATTR_ENCAP_TYPE, /* u16, enum l2tp_encap_type */
+ L2TP_ATTR_OFFSET, /* u16 */
+ L2TP_ATTR_DATA_SEQ, /* u16 */
+ L2TP_ATTR_L2SPEC_TYPE, /* u8, enum l2tp_l2spec_type */
+ L2TP_ATTR_L2SPEC_LEN, /* u8, enum l2tp_l2spec_type */
+ L2TP_ATTR_PROTO_VERSION, /* u8 */
+ L2TP_ATTR_IFNAME, /* string */
+ L2TP_ATTR_CONN_ID, /* u32 */
+ L2TP_ATTR_PEER_CONN_ID, /* u32 */
+ L2TP_ATTR_SESSION_ID, /* u32 */
+ L2TP_ATTR_PEER_SESSION_ID, /* u32 */
+ L2TP_ATTR_UDP_CSUM, /* u8 */
+ L2TP_ATTR_VLAN_ID, /* u16 */
+ L2TP_ATTR_COOKIE, /* 0, 4 or 8 bytes */
+ L2TP_ATTR_PEER_COOKIE, /* 0, 4 or 8 bytes */
+ L2TP_ATTR_DEBUG, /* u32 */
+ L2TP_ATTR_RECV_SEQ, /* u8 */
+ L2TP_ATTR_SEND_SEQ, /* u8 */
+ L2TP_ATTR_LNS_MODE, /* u8 */
+ L2TP_ATTR_USING_IPSEC, /* u8 */
+ L2TP_ATTR_RECV_TIMEOUT, /* msec */
+ L2TP_ATTR_FD, /* int */
+ L2TP_ATTR_IP_SADDR, /* u32 */
+ L2TP_ATTR_IP_DADDR, /* u32 */
+ L2TP_ATTR_UDP_SPORT, /* u16 */
+ L2TP_ATTR_UDP_DPORT, /* u16 */
+ L2TP_ATTR_MTU, /* u16 */
+ L2TP_ATTR_MRU, /* u16 */
+ L2TP_ATTR_STATS, /* nested */
+ L2TP_ATTR_IP6_SADDR, /* struct in6_addr */
+ L2TP_ATTR_IP6_DADDR, /* struct in6_addr */
+ L2TP_ATTR_UDP_ZERO_CSUM6_TX, /* u8 */
+ L2TP_ATTR_UDP_ZERO_CSUM6_RX, /* u8 */
+ __L2TP_ATTR_MAX,
+};
+
+#define L2TP_ATTR_MAX (__L2TP_ATTR_MAX - 1)
+
+/* Nested in L2TP_ATTR_STATS */
+enum {
+ L2TP_ATTR_STATS_NONE, /* no data */
+ L2TP_ATTR_TX_PACKETS, /* u64 */
+ L2TP_ATTR_TX_BYTES, /* u64 */
+ L2TP_ATTR_TX_ERRORS, /* u64 */
+ L2TP_ATTR_RX_PACKETS, /* u64 */
+ L2TP_ATTR_RX_BYTES, /* u64 */
+ L2TP_ATTR_RX_SEQ_DISCARDS, /* u64 */
+ L2TP_ATTR_RX_OOS_PACKETS, /* u64 */
+ L2TP_ATTR_RX_ERRORS, /* u64 */
+ __L2TP_ATTR_STATS_MAX,
+};
+
+#define L2TP_ATTR_STATS_MAX (__L2TP_ATTR_STATS_MAX - 1)
+
+enum l2tp_pwtype {
+ L2TP_PWTYPE_NONE = 0x0000,
+ L2TP_PWTYPE_ETH_VLAN = 0x0004,
+ L2TP_PWTYPE_ETH = 0x0005,
+ L2TP_PWTYPE_PPP = 0x0007,
+ L2TP_PWTYPE_PPP_AC = 0x0008,
+ L2TP_PWTYPE_IP = 0x000b,
+ __L2TP_PWTYPE_MAX
+};
+
+enum l2tp_l2spec_type {
+ L2TP_L2SPECTYPE_NONE,
+ L2TP_L2SPECTYPE_DEFAULT,
+};
+
+enum l2tp_encap_type {
+ L2TP_ENCAPTYPE_UDP,
+ L2TP_ENCAPTYPE_IP,
+};
+
+enum l2tp_seqmode {
+ L2TP_SEQ_NONE = 0,
+ L2TP_SEQ_IP = 1,
+ L2TP_SEQ_ALL = 2,
+};
+
+/*
+ * NETLINK_GENERIC related info
+ */
+#define L2TP_GENL_NAME "l2tp"
+#define L2TP_GENL_VERSION 0x1
+#define L2TP_GENL_MCGROUP "l2tp"
+
+#endif /* _LINUX_L2TP_H_ */
diff --git a/iproute2/include/linux/libc-compat.h b/iproute2/include/linux/libc-compat.h
new file mode 100644
index 0000000..9bed5b6
--- /dev/null
+++ b/iproute2/include/linux/libc-compat.h
@@ -0,0 +1,143 @@
+/*
+ * Compatibility interface for userspace libc header coordination:
+ *
+ * Define compatibility macros that are used to control the inclusion or
+ * exclusion of UAPI structures and definitions in coordination with another
+ * userspace C library.
+ *
+ * This header is intended to solve the problem of UAPI definitions that
+ * conflict with userspace definitions. If a UAPI header has such conflicting
+ * definitions then the solution is as follows:
+ *
+ * * Synchronize the UAPI header and the libc headers so either one can be
+ * used and such that the ABI is preserved. If this is not possible then
+ * no simple compatibility interface exists (you need to write translating
+ * wrappers and rename things) and you can't use this interface.
+ *
+ * Then follow this process:
+ *
+ * (a) Include libc-compat.h in the UAPI header.
+ * e.g. #include <linux/libc-compat.h>
+ * This include must be as early as possible.
+ *
+ * (b) In libc-compat.h add enough code to detect that the comflicting
+ * userspace libc header has been included first.
+ *
+ * (c) If the userspace libc header has been included first define a set of
+ * guard macros of the form __UAPI_DEF_FOO and set their values to 1, else
+ * set their values to 0.
+ *
+ * (d) Back in the UAPI header with the conflicting definitions, guard the
+ * definitions with:
+ * #if __UAPI_DEF_FOO
+ * ...
+ * #endif
+ *
+ * This fixes the situation where the linux headers are included *after* the
+ * libc headers. To fix the problem with the inclusion in the other order the
+ * userspace libc headers must be fixed like this:
+ *
+ * * For all definitions that conflict with kernel definitions wrap those
+ * defines in the following:
+ * #if !__UAPI_DEF_FOO
+ * ...
+ * #endif
+ *
+ * This prevents the redefinition of a construct already defined by the kernel.
+ */
+#ifndef _LIBC_COMPAT_H
+#define _LIBC_COMPAT_H
+
+/* We have included glibc headers... */
+#if defined(__GLIBC__)
+
+/* Coordinate with glibc netinet/in.h header. */
+#if defined(_NETINET_IN_H)
+
+/* GLIBC headers included first so don't define anything
+ * that would already be defined. */
+#define __UAPI_DEF_IN_ADDR 0
+#define __UAPI_DEF_IN_IPPROTO 0
+#define __UAPI_DEF_IN_PKTINFO 0
+#define __UAPI_DEF_IP_MREQ 0
+#define __UAPI_DEF_SOCKADDR_IN 0
+#define __UAPI_DEF_IN_CLASS 0
+
+#define __UAPI_DEF_IN6_ADDR 0
+/* The exception is the in6_addr macros which must be defined
+ * if the glibc code didn't define them. This guard matches
+ * the guard in glibc/inet/netinet/in.h which defines the
+ * additional in6_addr macros e.g. s6_addr16, and s6_addr32. */
+#if defined(__USE_MISC) || defined (__USE_GNU)
+#define __UAPI_DEF_IN6_ADDR_ALT 0
+#else
+#define __UAPI_DEF_IN6_ADDR_ALT 1
+#endif
+#define __UAPI_DEF_SOCKADDR_IN6 0
+#define __UAPI_DEF_IPV6_MREQ 0
+#define __UAPI_DEF_IPPROTO_V6 0
+#define __UAPI_DEF_IPV6_OPTIONS 0
+#define __UAPI_DEF_IN6_PKTINFO 0
+#define __UAPI_DEF_IP6_MTUINFO 0
+
+#else
+
+/* Linux headers included first, and we must define everything
+ * we need. The expectation is that glibc will check the
+ * __UAPI_DEF_* defines and adjust appropriately. */
+#define __UAPI_DEF_IN_ADDR 1
+#define __UAPI_DEF_IN_IPPROTO 1
+#define __UAPI_DEF_IN_PKTINFO 1
+#define __UAPI_DEF_IP_MREQ 1
+#define __UAPI_DEF_SOCKADDR_IN 1
+#define __UAPI_DEF_IN_CLASS 1
+
+#define __UAPI_DEF_IN6_ADDR 1
+/* We unconditionally define the in6_addr macros and glibc must
+ * coordinate. */
+#define __UAPI_DEF_IN6_ADDR_ALT 1
+#define __UAPI_DEF_SOCKADDR_IN6 1
+#define __UAPI_DEF_IPV6_MREQ 1
+#define __UAPI_DEF_IPPROTO_V6 1
+#define __UAPI_DEF_IPV6_OPTIONS 1
+#define __UAPI_DEF_IN6_PKTINFO 1
+#define __UAPI_DEF_IP6_MTUINFO 1
+
+#endif /* _NETINET_IN_H */
+
+/* Definitions for xattr.h */
+#if defined(_SYS_XATTR_H)
+#define __UAPI_DEF_XATTR 0
+#else
+#define __UAPI_DEF_XATTR 1
+#endif
+
+/* If we did not see any headers from any supported C libraries,
+ * or we are being included in the kernel, then define everything
+ * that we need. */
+#else /* !defined(__GLIBC__) */
+
+/* Definitions for in.h */
+#define __UAPI_DEF_IN_ADDR 1
+#define __UAPI_DEF_IN_IPPROTO 1
+#define __UAPI_DEF_IN_PKTINFO 1
+#define __UAPI_DEF_IP_MREQ 1
+#define __UAPI_DEF_SOCKADDR_IN 1
+#define __UAPI_DEF_IN_CLASS 1
+
+/* Definitions for in6.h */
+#define __UAPI_DEF_IN6_ADDR 1
+#define __UAPI_DEF_IN6_ADDR_ALT 1
+#define __UAPI_DEF_SOCKADDR_IN6 1
+#define __UAPI_DEF_IPV6_MREQ 1
+#define __UAPI_DEF_IPPROTO_V6 1
+#define __UAPI_DEF_IPV6_OPTIONS 1
+#define __UAPI_DEF_IN6_PKTINFO 1
+#define __UAPI_DEF_IP6_MTUINFO 1
+
+/* Definitions for xattr.h */
+#define __UAPI_DEF_XATTR 1
+
+#endif /* __GLIBC__ */
+
+#endif /* _LIBC_COMPAT_H */
diff --git a/iproute2/include/linux/lwtunnel.h b/iproute2/include/linux/lwtunnel.h
new file mode 100644
index 0000000..1d2f4f6
--- /dev/null
+++ b/iproute2/include/linux/lwtunnel.h
@@ -0,0 +1,43 @@
+#ifndef _LWTUNNEL_H_
+#define _LWTUNNEL_H_
+
+#include <linux/types.h>
+
+enum lwtunnel_encap_types {
+ LWTUNNEL_ENCAP_NONE,
+ LWTUNNEL_ENCAP_MPLS,
+ LWTUNNEL_ENCAP_IP,
+ LWTUNNEL_ENCAP_ILA,
+ LWTUNNEL_ENCAP_IP6,
+ __LWTUNNEL_ENCAP_MAX,
+};
+
+#define LWTUNNEL_ENCAP_MAX (__LWTUNNEL_ENCAP_MAX - 1)
+
+enum lwtunnel_ip_t {
+ LWTUNNEL_IP_UNSPEC,
+ LWTUNNEL_IP_ID,
+ LWTUNNEL_IP_DST,
+ LWTUNNEL_IP_SRC,
+ LWTUNNEL_IP_TTL,
+ LWTUNNEL_IP_TOS,
+ LWTUNNEL_IP_FLAGS,
+ __LWTUNNEL_IP_MAX,
+};
+
+#define LWTUNNEL_IP_MAX (__LWTUNNEL_IP_MAX - 1)
+
+enum lwtunnel_ip6_t {
+ LWTUNNEL_IP6_UNSPEC,
+ LWTUNNEL_IP6_ID,
+ LWTUNNEL_IP6_DST,
+ LWTUNNEL_IP6_SRC,
+ LWTUNNEL_IP6_HOPLIMIT,
+ LWTUNNEL_IP6_TC,
+ LWTUNNEL_IP6_FLAGS,
+ __LWTUNNEL_IP6_MAX,
+};
+
+#define LWTUNNEL_IP6_MAX (__LWTUNNEL_IP6_MAX - 1)
+
+#endif /* _LWTUNNEL_H_ */
diff --git a/iproute2/include/linux/mpls.h b/iproute2/include/linux/mpls.h
new file mode 100644
index 0000000..a14b54b
--- /dev/null
+++ b/iproute2/include/linux/mpls.h
@@ -0,0 +1,46 @@
+#ifndef _MPLS_H
+#define _MPLS_H
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+/* Reference: RFC 5462, RFC 3032
+ *
+ * 0 1 2 3
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Label | TC |S| TTL |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * Label: Label Value, 20 bits
+ * TC: Traffic Class field, 3 bits
+ * S: Bottom of Stack, 1 bit
+ * TTL: Time to Live, 8 bits
+ */
+
+struct mpls_label {
+ __be32 entry;
+};
+
+#define MPLS_LS_LABEL_MASK 0xFFFFF000
+#define MPLS_LS_LABEL_SHIFT 12
+#define MPLS_LS_TC_MASK 0x00000E00
+#define MPLS_LS_TC_SHIFT 9
+#define MPLS_LS_S_MASK 0x00000100
+#define MPLS_LS_S_SHIFT 8
+#define MPLS_LS_TTL_MASK 0x000000FF
+#define MPLS_LS_TTL_SHIFT 0
+
+/* Reserved labels */
+#define MPLS_LABEL_IPV4NULL 0 /* RFC3032 */
+#define MPLS_LABEL_RTALERT 1 /* RFC3032 */
+#define MPLS_LABEL_IPV6NULL 2 /* RFC3032 */
+#define MPLS_LABEL_IMPLNULL 3 /* RFC3032 */
+#define MPLS_LABEL_ENTROPY 7 /* RFC6790 */
+#define MPLS_LABEL_GAL 13 /* RFC5586 */
+#define MPLS_LABEL_OAMALERT 14 /* RFC3429 */
+#define MPLS_LABEL_EXTENSION 15 /* RFC7274 */
+
+#define MPLS_LABEL_FIRST_UNRESERVED 16 /* RFC3032 */
+
+#endif /* _MPLS_H */
diff --git a/iproute2/include/linux/mpls_iptunnel.h b/iproute2/include/linux/mpls_iptunnel.h
new file mode 100644
index 0000000..4132c3c
--- /dev/null
+++ b/iproute2/include/linux/mpls_iptunnel.h
@@ -0,0 +1,28 @@
+/*
+ * mpls tunnel api
+ *
+ * Authors:
+ * Roopa Prabhu <roopa@cumulusnetworks.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _LINUX_MPLS_IPTUNNEL_H
+#define _LINUX_MPLS_IPTUNNEL_H
+
+/* MPLS tunnel attributes
+ * [RTA_ENCAP] = {
+ * [MPLS_IPTUNNEL_DST]
+ * }
+ */
+enum {
+ MPLS_IPTUNNEL_UNSPEC,
+ MPLS_IPTUNNEL_DST,
+ __MPLS_IPTUNNEL_MAX,
+};
+#define MPLS_IPTUNNEL_MAX (__MPLS_IPTUNNEL_MAX - 1)
+
+#endif /* _LINUX_MPLS_IPTUNNEL_H */
diff --git a/iproute2/include/linux/neighbour.h b/iproute2/include/linux/neighbour.h
new file mode 100644
index 0000000..788655b
--- /dev/null
+++ b/iproute2/include/linux/neighbour.h
@@ -0,0 +1,167 @@
+#ifndef __LINUX_NEIGHBOUR_H
+#define __LINUX_NEIGHBOUR_H
+
+#include <linux/types.h>
+#include <linux/netlink.h>
+
+struct ndmsg {
+ __u8 ndm_family;
+ __u8 ndm_pad1;
+ __u16 ndm_pad2;
+ __s32 ndm_ifindex;
+ __u16 ndm_state;
+ __u8 ndm_flags;
+ __u8 ndm_type;
+};
+
+enum {
+ NDA_UNSPEC,
+ NDA_DST,
+ NDA_LLADDR,
+ NDA_CACHEINFO,
+ NDA_PROBES,
+ NDA_VLAN,
+ NDA_PORT,
+ NDA_VNI,
+ NDA_IFINDEX,
+ NDA_MASTER,
+ NDA_LINK_NETNSID,
+ __NDA_MAX
+};
+
+#define NDA_MAX (__NDA_MAX - 1)
+
+/*
+ * Neighbor Cache Entry Flags
+ */
+
+#define NTF_USE 0x01
+#define NTF_SELF 0x02
+#define NTF_MASTER 0x04
+#define NTF_PROXY 0x08 /* == ATF_PUBL */
+#define NTF_EXT_LEARNED 0x10
+#define NTF_ROUTER 0x80
+
+/*
+ * Neighbor Cache Entry States.
+ */
+
+#define NUD_INCOMPLETE 0x01
+#define NUD_REACHABLE 0x02
+#define NUD_STALE 0x04
+#define NUD_DELAY 0x08
+#define NUD_PROBE 0x10
+#define NUD_FAILED 0x20
+
+/* Dummy states */
+#define NUD_NOARP 0x40
+#define NUD_PERMANENT 0x80
+#define NUD_NONE 0x00
+
+/* NUD_NOARP & NUD_PERMANENT are pseudostates, they never change
+ and make no address resolution or NUD.
+ NUD_PERMANENT also cannot be deleted by garbage collectors.
+ */
+
+struct nda_cacheinfo {
+ __u32 ndm_confirmed;
+ __u32 ndm_used;
+ __u32 ndm_updated;
+ __u32 ndm_refcnt;
+};
+
+/*****************************************************************
+ * Neighbour tables specific messages.
+ *
+ * To retrieve the neighbour tables send RTM_GETNEIGHTBL with the
+ * NLM_F_DUMP flag set. Every neighbour table configuration is
+ * spread over multiple messages to avoid running into message
+ * size limits on systems with many interfaces. The first message
+ * in the sequence transports all not device specific data such as
+ * statistics, configuration, and the default parameter set.
+ * This message is followed by 0..n messages carrying device
+ * specific parameter sets.
+ * Although the ordering should be sufficient, NDTA_NAME can be
+ * used to identify sequences. The initial message can be identified
+ * by checking for NDTA_CONFIG. The device specific messages do
+ * not contain this TLV but have NDTPA_IFINDEX set to the
+ * corresponding interface index.
+ *
+ * To change neighbour table attributes, send RTM_SETNEIGHTBL
+ * with NDTA_NAME set. Changeable attribute include NDTA_THRESH[1-3],
+ * NDTA_GC_INTERVAL, and all TLVs in NDTA_PARMS unless marked
+ * otherwise. Device specific parameter sets can be changed by
+ * setting NDTPA_IFINDEX to the interface index of the corresponding
+ * device.
+ ****/
+
+struct ndt_stats {
+ __u64 ndts_allocs;
+ __u64 ndts_destroys;
+ __u64 ndts_hash_grows;
+ __u64 ndts_res_failed;
+ __u64 ndts_lookups;
+ __u64 ndts_hits;
+ __u64 ndts_rcv_probes_mcast;
+ __u64 ndts_rcv_probes_ucast;
+ __u64 ndts_periodic_gc_runs;
+ __u64 ndts_forced_gc_runs;
+ __u64 ndts_table_fulls;
+};
+
+enum {
+ NDTPA_UNSPEC,
+ NDTPA_IFINDEX, /* u32, unchangeable */
+ NDTPA_REFCNT, /* u32, read-only */
+ NDTPA_REACHABLE_TIME, /* u64, read-only, msecs */
+ NDTPA_BASE_REACHABLE_TIME, /* u64, msecs */
+ NDTPA_RETRANS_TIME, /* u64, msecs */
+ NDTPA_GC_STALETIME, /* u64, msecs */
+ NDTPA_DELAY_PROBE_TIME, /* u64, msecs */
+ NDTPA_QUEUE_LEN, /* u32 */
+ NDTPA_APP_PROBES, /* u32 */
+ NDTPA_UCAST_PROBES, /* u32 */
+ NDTPA_MCAST_PROBES, /* u32 */
+ NDTPA_ANYCAST_DELAY, /* u64, msecs */
+ NDTPA_PROXY_DELAY, /* u64, msecs */
+ NDTPA_PROXY_QLEN, /* u32 */
+ NDTPA_LOCKTIME, /* u64, msecs */
+ NDTPA_QUEUE_LENBYTES, /* u32 */
+ NDTPA_MCAST_REPROBES, /* u32 */
+ __NDTPA_MAX
+};
+#define NDTPA_MAX (__NDTPA_MAX - 1)
+
+struct ndtmsg {
+ __u8 ndtm_family;
+ __u8 ndtm_pad1;
+ __u16 ndtm_pad2;
+};
+
+struct ndt_config {
+ __u16 ndtc_key_len;
+ __u16 ndtc_entry_size;
+ __u32 ndtc_entries;
+ __u32 ndtc_last_flush; /* delta to now in msecs */
+ __u32 ndtc_last_rand; /* delta to now in msecs */
+ __u32 ndtc_hash_rnd;
+ __u32 ndtc_hash_mask;
+ __u32 ndtc_hash_chain_gc;
+ __u32 ndtc_proxy_qlen;
+};
+
+enum {
+ NDTA_UNSPEC,
+ NDTA_NAME, /* char *, unchangeable */
+ NDTA_THRESH1, /* u32 */
+ NDTA_THRESH2, /* u32 */
+ NDTA_THRESH3, /* u32 */
+ NDTA_CONFIG, /* struct ndt_config, read-only */
+ NDTA_PARMS, /* nested TLV NDTPA_* */
+ NDTA_STATS, /* struct ndt_stats, read-only */
+ NDTA_GC_INTERVAL, /* u64, msecs */
+ __NDTA_MAX
+};
+#define NDTA_MAX (__NDTA_MAX - 1)
+
+#endif
diff --git a/iproute2/include/linux/net_namespace.h b/iproute2/include/linux/net_namespace.h
new file mode 100644
index 0000000..9a92b7e
--- /dev/null
+++ b/iproute2/include/linux/net_namespace.h
@@ -0,0 +1,23 @@
+/* Copyright (c) 2015 6WIND S.A.
+ * Author: Nicolas Dichtel <nicolas.dichtel@6wind.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ */
+#ifndef _LINUX_NET_NAMESPACE_H_
+#define _LINUX_NET_NAMESPACE_H_
+
+/* Attributes of RTM_NEWNSID/RTM_GETNSID messages */
+enum {
+ NETNSA_NONE,
+#define NETNSA_NSID_NOT_ASSIGNED -1
+ NETNSA_NSID,
+ NETNSA_PID,
+ NETNSA_FD,
+ __NETNSA_MAX,
+};
+
+#define NETNSA_MAX (__NETNSA_MAX - 1)
+
+#endif /* _LINUX_NET_NAMESPACE_H_ */
diff --git a/iproute2/include/linux/netconf.h b/iproute2/include/linux/netconf.h
new file mode 100644
index 0000000..7210fe4
--- /dev/null
+++ b/iproute2/include/linux/netconf.h
@@ -0,0 +1,26 @@
+#ifndef _LINUX_NETCONF_H_
+#define _LINUX_NETCONF_H_
+
+#include <linux/types.h>
+#include <linux/netlink.h>
+
+struct netconfmsg {
+ __u8 ncm_family;
+};
+
+enum {
+ NETCONFA_UNSPEC,
+ NETCONFA_IFINDEX,
+ NETCONFA_FORWARDING,
+ NETCONFA_RP_FILTER,
+ NETCONFA_MC_FORWARDING,
+ NETCONFA_PROXY_NEIGH,
+ NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
+ __NETCONFA_MAX
+};
+#define NETCONFA_MAX (__NETCONFA_MAX - 1)
+
+#define NETCONFA_IFINDEX_ALL -1
+#define NETCONFA_IFINDEX_DEFAULT -2
+
+#endif /* _LINUX_NETCONF_H_ */
diff --git a/iproute2/include/linux/netdevice.h b/iproute2/include/linux/netdevice.h
new file mode 100644
index 0000000..66fceb4
--- /dev/null
+++ b/iproute2/include/linux/netdevice.h
@@ -0,0 +1,65 @@
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * Definitions for the Interfaces handler.
+ *
+ * Version: @(#)dev.h 1.0.10 08/12/93
+ *
+ * Authors: Ross Biro
+ * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ * Corey Minyard <wf-rch!minyard@relay.EU.net>
+ * Donald J. Becker, <becker@cesdis.gsfc.nasa.gov>
+ * Alan Cox, <alan@lxorguk.ukuu.org.uk>
+ * Bjorn Ekwall. <bj0rn@blox.se>
+ * Pekka Riikonen <priikone@poseidon.pspt.fi>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Moved to /usr/include/linux for NET3
+ */
+#ifndef _LINUX_NETDEVICE_H
+#define _LINUX_NETDEVICE_H
+
+#include <linux/if.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/if_link.h>
+
+
+#define MAX_ADDR_LEN 32 /* Largest hardware address length */
+
+/* Initial net device group. All devices belong to group 0 by default. */
+#define INIT_NETDEV_GROUP 0
+
+
+/* interface name assignment types (sysfs name_assign_type attribute) */
+#define NET_NAME_UNKNOWN 0 /* unknown origin (not exposed to userspace) */
+#define NET_NAME_ENUM 1 /* enumerated by kernel */
+#define NET_NAME_PREDICTABLE 2 /* predictably named by the kernel */
+#define NET_NAME_USER 3 /* provided by user-space */
+#define NET_NAME_RENAMED 4 /* renamed by user-space */
+
+/* Media selection options. */
+enum {
+ IF_PORT_UNKNOWN = 0,
+ IF_PORT_10BASE2,
+ IF_PORT_10BASET,
+ IF_PORT_AUI,
+ IF_PORT_100BASET,
+ IF_PORT_100BASETX,
+ IF_PORT_100BASEFX
+};
+
+/* hardware address assignment types */
+#define NET_ADDR_PERM 0 /* address is permanent (default) */
+#define NET_ADDR_RANDOM 1 /* address is generated randomly */
+#define NET_ADDR_STOLEN 2 /* address is stolen from other device */
+#define NET_ADDR_SET 3 /* address is set using
+ * dev_set_mac_address() */
+
+#endif /* _LINUX_NETDEVICE_H */
diff --git a/iproute2/include/linux/netfilter.h b/iproute2/include/linux/netfilter.h
new file mode 100644
index 0000000..b71b4c9
--- /dev/null
+++ b/iproute2/include/linux/netfilter.h
@@ -0,0 +1,78 @@
+#ifndef __LINUX_NETFILTER_H
+#define __LINUX_NETFILTER_H
+
+#include <linux/types.h>
+
+#include <linux/sysctl.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+
+/* Responses from hook functions. */
+#define NF_DROP 0
+#define NF_ACCEPT 1
+#define NF_STOLEN 2
+#define NF_QUEUE 3
+#define NF_REPEAT 4
+#define NF_STOP 5
+#define NF_MAX_VERDICT NF_STOP
+
+/* we overload the higher bits for encoding auxiliary data such as the queue
+ * number or errno values. Not nice, but better than additional function
+ * arguments. */
+#define NF_VERDICT_MASK 0x000000ff
+
+/* extra verdict flags have mask 0x0000ff00 */
+#define NF_VERDICT_FLAG_QUEUE_BYPASS 0x00008000
+
+/* queue number (NF_QUEUE) or errno (NF_DROP) */
+#define NF_VERDICT_QMASK 0xffff0000
+#define NF_VERDICT_QBITS 16
+
+#define NF_QUEUE_NR(x) ((((x) << 16) & NF_VERDICT_QMASK) | NF_QUEUE)
+
+#define NF_DROP_ERR(x) (((-x) << 16) | NF_DROP)
+
+/* only for userspace compatibility */
+/* Generic cache responses from hook functions.
+ <= 0x2000 is used for protocol-flags. */
+#define NFC_UNKNOWN 0x4000
+#define NFC_ALTERED 0x8000
+
+/* NF_VERDICT_BITS should be 8 now, but userspace might break if this changes */
+#define NF_VERDICT_BITS 16
+
+enum nf_inet_hooks {
+ NF_INET_PRE_ROUTING,
+ NF_INET_LOCAL_IN,
+ NF_INET_FORWARD,
+ NF_INET_LOCAL_OUT,
+ NF_INET_POST_ROUTING,
+ NF_INET_NUMHOOKS
+};
+
+enum nf_dev_hooks {
+ NF_NETDEV_INGRESS,
+ NF_NETDEV_NUMHOOKS
+};
+
+enum {
+ NFPROTO_UNSPEC = 0,
+ NFPROTO_INET = 1,
+ NFPROTO_IPV4 = 2,
+ NFPROTO_ARP = 3,
+ NFPROTO_NETDEV = 5,
+ NFPROTO_BRIDGE = 7,
+ NFPROTO_IPV6 = 10,
+ NFPROTO_DECNET = 12,
+ NFPROTO_NUMPROTO,
+};
+
+union nf_inet_addr {
+ __u32 all[4];
+ __be32 ip;
+ __be32 ip6[4];
+ struct in_addr in;
+ struct in6_addr in6;
+};
+
+#endif /* __LINUX_NETFILTER_H */
diff --git a/iproute2/include/linux/netfilter/x_tables.h b/iproute2/include/linux/netfilter/x_tables.h
new file mode 100644
index 0000000..4120970
--- /dev/null
+++ b/iproute2/include/linux/netfilter/x_tables.h
@@ -0,0 +1,185 @@
+#ifndef _X_TABLES_H
+#define _X_TABLES_H
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+#define XT_FUNCTION_MAXNAMELEN 30
+#define XT_EXTENSION_MAXNAMELEN 29
+#define XT_TABLE_MAXNAMELEN 32
+
+struct xt_entry_match {
+ union {
+ struct {
+ __u16 match_size;
+
+ /* Used by userspace */
+ char name[XT_EXTENSION_MAXNAMELEN];
+ __u8 revision;
+ } user;
+ struct {
+ __u16 match_size;
+
+ /* Used inside the kernel */
+ struct xt_match *match;
+ } kernel;
+
+ /* Total length */
+ __u16 match_size;
+ } u;
+
+ unsigned char data[0];
+};
+
+struct xt_entry_target {
+ union {
+ struct {
+ __u16 target_size;
+
+ /* Used by userspace */
+ char name[XT_EXTENSION_MAXNAMELEN];
+ __u8 revision;
+ } user;
+ struct {
+ __u16 target_size;
+
+ /* Used inside the kernel */
+ struct xt_target *target;
+ } kernel;
+
+ /* Total length */
+ __u16 target_size;
+ } u;
+
+ unsigned char data[0];
+};
+
+#define XT_TARGET_INIT(__name, __size) \
+{ \
+ .target.u.user = { \
+ .target_size = XT_ALIGN(__size), \
+ .name = __name, \
+ }, \
+}
+
+struct xt_standard_target {
+ struct xt_entry_target target;
+ int verdict;
+};
+
+struct xt_error_target {
+ struct xt_entry_target target;
+ char errorname[XT_FUNCTION_MAXNAMELEN];
+};
+
+/* The argument to IPT_SO_GET_REVISION_*. Returns highest revision
+ * kernel supports, if >= revision. */
+struct xt_get_revision {
+ char name[XT_EXTENSION_MAXNAMELEN];
+ __u8 revision;
+};
+
+/* CONTINUE verdict for targets */
+#define XT_CONTINUE 0xFFFFFFFF
+
+/* For standard target */
+#define XT_RETURN (-NF_REPEAT - 1)
+
+/* this is a dummy structure to find out the alignment requirement for a struct
+ * containing all the fundamental data types that are used in ipt_entry,
+ * ip6t_entry and arpt_entry. This sucks, and it is a hack. It will be my
+ * personal pleasure to remove it -HW
+ */
+struct _xt_align {
+ __u8 u8;
+ __u16 u16;
+ __u32 u32;
+ __u64 u64;
+};
+
+#define XT_ALIGN(s) __ALIGN_KERNEL((s), __alignof__(struct _xt_align))
+
+/* Standard return verdict, or do jump. */
+#define XT_STANDARD_TARGET ""
+/* Error verdict. */
+#define XT_ERROR_TARGET "ERROR"
+
+#define SET_COUNTER(c,b,p) do { (c).bcnt = (b); (c).pcnt = (p); } while(0)
+#define ADD_COUNTER(c,b,p) do { (c).bcnt += (b); (c).pcnt += (p); } while(0)
+
+struct xt_counters {
+ __u64 pcnt, bcnt; /* Packet and byte counters */
+};
+
+/* The argument to IPT_SO_ADD_COUNTERS. */
+struct xt_counters_info {
+ /* Which table. */
+ char name[XT_TABLE_MAXNAMELEN];
+
+ unsigned int num_counters;
+
+ /* The counters (actually `number' of these). */
+ struct xt_counters counters[0];
+};
+
+#define XT_INV_PROTO 0x40 /* Invert the sense of PROTO. */
+
+/* fn returns 0 to continue iteration */
+#define XT_MATCH_ITERATE(type, e, fn, args...) \
+({ \
+ unsigned int __i; \
+ int __ret = 0; \
+ struct xt_entry_match *__m; \
+ \
+ for (__i = sizeof(type); \
+ __i < (e)->target_offset; \
+ __i += __m->u.match_size) { \
+ __m = (void *)e + __i; \
+ \
+ __ret = fn(__m , ## args); \
+ if (__ret != 0) \
+ break; \
+ } \
+ __ret; \
+})
+
+/* fn returns 0 to continue iteration */
+#define XT_ENTRY_ITERATE_CONTINUE(type, entries, size, n, fn, args...) \
+({ \
+ unsigned int __i, __n; \
+ int __ret = 0; \
+ type *__entry; \
+ \
+ for (__i = 0, __n = 0; __i < (size); \
+ __i += __entry->next_offset, __n++) { \
+ __entry = (void *)(entries) + __i; \
+ if (__n < n) \
+ continue; \
+ \
+ __ret = fn(__entry , ## args); \
+ if (__ret != 0) \
+ break; \
+ } \
+ __ret; \
+})
+
+/* fn returns 0 to continue iteration */
+#define XT_ENTRY_ITERATE(type, entries, size, fn, args...) \
+ XT_ENTRY_ITERATE_CONTINUE(type, entries, size, 0, fn, args)
+
+
+/* pos is normally a struct ipt_entry/ip6t_entry/etc. */
+#define xt_entry_foreach(pos, ehead, esize) \
+ for ((pos) = (typeof(pos))(ehead); \
+ (pos) < (typeof(pos))((char *)(ehead) + (esize)); \
+ (pos) = (typeof(pos))((char *)(pos) + (pos)->next_offset))
+
+/* can only be xt_entry_match, so no use of typeof here */
+#define xt_ematch_foreach(pos, entry) \
+ for ((pos) = (struct xt_entry_match *)entry->elems; \
+ (pos) < (struct xt_entry_match *)((char *)(entry) + \
+ (entry)->target_offset); \
+ (pos) = (struct xt_entry_match *)((char *)(pos) + \
+ (pos)->u.match_size))
+
+
+#endif /* _X_TABLES_H */
diff --git a/iproute2/include/linux/netfilter/xt_tcpudp.h b/iproute2/include/linux/netfilter/xt_tcpudp.h
new file mode 100644
index 0000000..38aa7b3
--- /dev/null
+++ b/iproute2/include/linux/netfilter/xt_tcpudp.h
@@ -0,0 +1,36 @@
+#ifndef _XT_TCPUDP_H
+#define _XT_TCPUDP_H
+
+#include <linux/types.h>
+
+/* TCP matching stuff */
+struct xt_tcp {
+ __u16 spts[2]; /* Source port range. */
+ __u16 dpts[2]; /* Destination port range. */
+ __u8 option; /* TCP Option iff non-zero*/
+ __u8 flg_mask; /* TCP flags mask byte */
+ __u8 flg_cmp; /* TCP flags compare byte */
+ __u8 invflags; /* Inverse flags */
+};
+
+/* Values for "inv" field in struct ipt_tcp. */
+#define XT_TCP_INV_SRCPT 0x01 /* Invert the sense of source ports. */
+#define XT_TCP_INV_DSTPT 0x02 /* Invert the sense of dest ports. */
+#define XT_TCP_INV_FLAGS 0x04 /* Invert the sense of TCP flags. */
+#define XT_TCP_INV_OPTION 0x08 /* Invert the sense of option test. */
+#define XT_TCP_INV_MASK 0x0F /* All possible flags. */
+
+/* UDP matching stuff */
+struct xt_udp {
+ __u16 spts[2]; /* Source port range. */
+ __u16 dpts[2]; /* Destination port range. */
+ __u8 invflags; /* Inverse flags */
+};
+
+/* Values for "invflags" field in struct ipt_udp. */
+#define XT_UDP_INV_SRCPT 0x01 /* Invert the sense of source ports. */
+#define XT_UDP_INV_DSTPT 0x02 /* Invert the sense of dest ports. */
+#define XT_UDP_INV_MASK 0x03 /* All possible flags. */
+
+
+#endif
diff --git a/iproute2/include/linux/netfilter_ipv4.h b/iproute2/include/linux/netfilter_ipv4.h
new file mode 100644
index 0000000..a5f4dc7
--- /dev/null
+++ b/iproute2/include/linux/netfilter_ipv4.h
@@ -0,0 +1,79 @@
+/* IPv4-specific defines for netfilter.
+ * (C)1998 Rusty Russell -- This code is GPL.
+ */
+#ifndef __LINUX_IP_NETFILTER_H
+#define __LINUX_IP_NETFILTER_H
+
+
+#include <linux/netfilter.h>
+
+/* only for userspace compatibility */
+
+#include <limits.h> /* for INT_MIN, INT_MAX */
+
+/* IP Cache bits. */
+/* Src IP address. */
+#define NFC_IP_SRC 0x0001
+/* Dest IP address. */
+#define NFC_IP_DST 0x0002
+/* Input device. */
+#define NFC_IP_IF_IN 0x0004
+/* Output device. */
+#define NFC_IP_IF_OUT 0x0008
+/* TOS. */
+#define NFC_IP_TOS 0x0010
+/* Protocol. */
+#define NFC_IP_PROTO 0x0020
+/* IP options. */
+#define NFC_IP_OPTIONS 0x0040
+/* Frag & flags. */
+#define NFC_IP_FRAG 0x0080
+
+/* Per-protocol information: only matters if proto match. */
+/* TCP flags. */
+#define NFC_IP_TCPFLAGS 0x0100
+/* Source port. */
+#define NFC_IP_SRC_PT 0x0200
+/* Dest port. */
+#define NFC_IP_DST_PT 0x0400
+/* Something else about the proto */
+#define NFC_IP_PROTO_UNKNOWN 0x2000
+
+/* IP Hooks */
+/* After promisc drops, checksum checks. */
+#define NF_IP_PRE_ROUTING 0
+/* If the packet is destined for this box. */
+#define NF_IP_LOCAL_IN 1
+/* If the packet is destined for another interface. */
+#define NF_IP_FORWARD 2
+/* Packets coming from a local process. */
+#define NF_IP_LOCAL_OUT 3
+/* Packets about to hit the wire. */
+#define NF_IP_POST_ROUTING 4
+#define NF_IP_NUMHOOKS 5
+
+enum nf_ip_hook_priorities {
+ NF_IP_PRI_FIRST = INT_MIN,
+ NF_IP_PRI_CONNTRACK_DEFRAG = -400,
+ NF_IP_PRI_RAW = -300,
+ NF_IP_PRI_SELINUX_FIRST = -225,
+ NF_IP_PRI_CONNTRACK = -200,
+ NF_IP_PRI_MANGLE = -150,
+ NF_IP_PRI_NAT_DST = -100,
+ NF_IP_PRI_FILTER = 0,
+ NF_IP_PRI_SECURITY = 50,
+ NF_IP_PRI_NAT_SRC = 100,
+ NF_IP_PRI_SELINUX_LAST = 225,
+ NF_IP_PRI_CONNTRACK_HELPER = 300,
+ NF_IP_PRI_CONNTRACK_CONFIRM = INT_MAX,
+ NF_IP_PRI_LAST = INT_MAX,
+};
+
+/* Arguments for setsockopt SOL_IP: */
+/* 2.0 firewalling went from 64 through 71 (and +256, +512, etc). */
+/* 2.2 firewalling (+ masq) went from 64 through 76 */
+/* 2.4 firewalling went 64 through 67. */
+#define SO_ORIGINAL_DST 80
+
+
+#endif /* __LINUX_IP_NETFILTER_H */
diff --git a/iproute2/include/linux/netfilter_ipv4/ip_tables.h b/iproute2/include/linux/netfilter_ipv4/ip_tables.h
new file mode 100644
index 0000000..38542b4
--- /dev/null
+++ b/iproute2/include/linux/netfilter_ipv4/ip_tables.h
@@ -0,0 +1,227 @@
+/*
+ * 25-Jul-1998 Major changes to allow for ip chain table
+ *
+ * 3-Jan-2000 Named tables to allow packet selection for different uses.
+ */
+
+/*
+ * Format of an IP firewall descriptor
+ *
+ * src, dst, src_mask, dst_mask are always stored in network byte order.
+ * flags are stored in host byte order (of course).
+ * Port numbers are stored in HOST byte order.
+ */
+
+#ifndef _IPTABLES_H
+#define _IPTABLES_H
+
+#include <linux/types.h>
+
+#include <linux/netfilter_ipv4.h>
+
+#include <linux/netfilter/x_tables.h>
+
+#define IPT_FUNCTION_MAXNAMELEN XT_FUNCTION_MAXNAMELEN
+#define IPT_TABLE_MAXNAMELEN XT_TABLE_MAXNAMELEN
+#define ipt_match xt_match
+#define ipt_target xt_target
+#define ipt_table xt_table
+#define ipt_get_revision xt_get_revision
+#define ipt_entry_match xt_entry_match
+#define ipt_entry_target xt_entry_target
+#define ipt_standard_target xt_standard_target
+#define ipt_error_target xt_error_target
+#define ipt_counters xt_counters
+#define IPT_CONTINUE XT_CONTINUE
+#define IPT_RETURN XT_RETURN
+
+/* This group is older than old (iptables < v1.4.0-rc1~89) */
+#include <linux/netfilter/xt_tcpudp.h>
+#define ipt_udp xt_udp
+#define ipt_tcp xt_tcp
+#define IPT_TCP_INV_SRCPT XT_TCP_INV_SRCPT
+#define IPT_TCP_INV_DSTPT XT_TCP_INV_DSTPT
+#define IPT_TCP_INV_FLAGS XT_TCP_INV_FLAGS
+#define IPT_TCP_INV_OPTION XT_TCP_INV_OPTION
+#define IPT_TCP_INV_MASK XT_TCP_INV_MASK
+#define IPT_UDP_INV_SRCPT XT_UDP_INV_SRCPT
+#define IPT_UDP_INV_DSTPT XT_UDP_INV_DSTPT
+#define IPT_UDP_INV_MASK XT_UDP_INV_MASK
+
+/* The argument to IPT_SO_ADD_COUNTERS. */
+#define ipt_counters_info xt_counters_info
+/* Standard return verdict, or do jump. */
+#define IPT_STANDARD_TARGET XT_STANDARD_TARGET
+/* Error verdict. */
+#define IPT_ERROR_TARGET XT_ERROR_TARGET
+
+/* fn returns 0 to continue iteration */
+#define IPT_MATCH_ITERATE(e, fn, args...) \
+ XT_MATCH_ITERATE(struct ipt_entry, e, fn, ## args)
+
+/* fn returns 0 to continue iteration */
+#define IPT_ENTRY_ITERATE(entries, size, fn, args...) \
+ XT_ENTRY_ITERATE(struct ipt_entry, entries, size, fn, ## args)
+
+/* Yes, Virginia, you have to zero the padding. */
+struct ipt_ip {
+ /* Source and destination IP addr */
+ struct in_addr src, dst;
+ /* Mask for src and dest IP addr */
+ struct in_addr smsk, dmsk;
+ char iniface[IFNAMSIZ], outiface[IFNAMSIZ];
+ unsigned char iniface_mask[IFNAMSIZ], outiface_mask[IFNAMSIZ];
+
+ /* Protocol, 0 = ANY */
+ __u16 proto;
+
+ /* Flags word */
+ __u8 flags;
+ /* Inverse flags */
+ __u8 invflags;
+};
+
+/* Values for "flag" field in struct ipt_ip (general ip structure). */
+#define IPT_F_FRAG 0x01 /* Set if rule is a fragment rule */
+#define IPT_F_GOTO 0x02 /* Set if jump is a goto */
+#define IPT_F_MASK 0x03 /* All possible flag bits mask. */
+
+/* Values for "inv" field in struct ipt_ip. */
+#define IPT_INV_VIA_IN 0x01 /* Invert the sense of IN IFACE. */
+#define IPT_INV_VIA_OUT 0x02 /* Invert the sense of OUT IFACE */
+#define IPT_INV_TOS 0x04 /* Invert the sense of TOS. */
+#define IPT_INV_SRCIP 0x08 /* Invert the sense of SRC IP. */
+#define IPT_INV_DSTIP 0x10 /* Invert the sense of DST OP. */
+#define IPT_INV_FRAG 0x20 /* Invert the sense of FRAG. */
+#define IPT_INV_PROTO XT_INV_PROTO
+#define IPT_INV_MASK 0x7F /* All possible flag bits mask. */
+
+/* This structure defines each of the firewall rules. Consists of 3
+ parts which are 1) general IP header stuff 2) match specific
+ stuff 3) the target to perform if the rule matches */
+struct ipt_entry {
+ struct ipt_ip ip;
+
+ /* Mark with fields that we care about. */
+ unsigned int nfcache;
+
+ /* Size of ipt_entry + matches */
+ __u16 target_offset;
+ /* Size of ipt_entry + matches + target */
+ __u16 next_offset;
+
+ /* Back pointer */
+ unsigned int comefrom;
+
+ /* Packet and byte counters. */
+ struct xt_counters counters;
+
+ /* The matches (if any), then the target. */
+ unsigned char elems[0];
+};
+
+/*
+ * New IP firewall options for [gs]etsockopt at the RAW IP level.
+ * Unlike BSD Linux inherits IP options so you don't have to use a raw
+ * socket for this. Instead we check rights in the calls.
+ *
+ * ATTENTION: check linux/in.h before adding new number here.
+ */
+#define IPT_BASE_CTL 64
+
+#define IPT_SO_SET_REPLACE (IPT_BASE_CTL)
+#define IPT_SO_SET_ADD_COUNTERS (IPT_BASE_CTL + 1)
+#define IPT_SO_SET_MAX IPT_SO_SET_ADD_COUNTERS
+
+#define IPT_SO_GET_INFO (IPT_BASE_CTL)
+#define IPT_SO_GET_ENTRIES (IPT_BASE_CTL + 1)
+#define IPT_SO_GET_REVISION_MATCH (IPT_BASE_CTL + 2)
+#define IPT_SO_GET_REVISION_TARGET (IPT_BASE_CTL + 3)
+#define IPT_SO_GET_MAX IPT_SO_GET_REVISION_TARGET
+
+/* ICMP matching stuff */
+struct ipt_icmp {
+ __u8 type; /* type to match */
+ __u8 code[2]; /* range of code */
+ __u8 invflags; /* Inverse flags */
+};
+
+/* Values for "inv" field for struct ipt_icmp. */
+#define IPT_ICMP_INV 0x01 /* Invert the sense of type/code test */
+
+/* The argument to IPT_SO_GET_INFO */
+struct ipt_getinfo {
+ /* Which table: caller fills this in. */
+ char name[XT_TABLE_MAXNAMELEN];
+
+ /* Kernel fills these in. */
+ /* Which hook entry points are valid: bitmask */
+ unsigned int valid_hooks;
+
+ /* Hook entry points: one per netfilter hook. */
+ unsigned int hook_entry[NF_INET_NUMHOOKS];
+
+ /* Underflow points. */
+ unsigned int underflow[NF_INET_NUMHOOKS];
+
+ /* Number of entries */
+ unsigned int num_entries;
+
+ /* Size of entries. */
+ unsigned int size;
+};
+
+/* The argument to IPT_SO_SET_REPLACE. */
+struct ipt_replace {
+ /* Which table. */
+ char name[XT_TABLE_MAXNAMELEN];
+
+ /* Which hook entry points are valid: bitmask. You can't
+ change this. */
+ unsigned int valid_hooks;
+
+ /* Number of entries */
+ unsigned int num_entries;
+
+ /* Total size of new entries */
+ unsigned int size;
+
+ /* Hook entry points. */
+ unsigned int hook_entry[NF_INET_NUMHOOKS];
+
+ /* Underflow points. */
+ unsigned int underflow[NF_INET_NUMHOOKS];
+
+ /* Information about old entries: */
+ /* Number of counters (must be equal to current number of entries). */
+ unsigned int num_counters;
+ /* The old entries' counters. */
+ struct xt_counters *counters;
+
+ /* The entries (hang off end: not really an array). */
+ struct ipt_entry entries[0];
+};
+
+/* The argument to IPT_SO_GET_ENTRIES. */
+struct ipt_get_entries {
+ /* Which table: user fills this in. */
+ char name[XT_TABLE_MAXNAMELEN];
+
+ /* User fills this in: total entry size. */
+ unsigned int size;
+
+ /* The entries. */
+ struct ipt_entry entrytable[0];
+};
+
+/* Helper functions */
+static __inline__ struct xt_entry_target *
+ipt_get_target(struct ipt_entry *e)
+{
+ return (void *)e + e->target_offset;
+}
+
+/*
+ * Main firewall chains definitions and global var's definitions.
+ */
+#endif /* _IPTABLES_H */
diff --git a/iproute2/include/linux/netlink.h b/iproute2/include/linux/netlink.h
new file mode 100644
index 0000000..8a7ca5c
--- /dev/null
+++ b/iproute2/include/linux/netlink.h
@@ -0,0 +1,189 @@
+#ifndef __LINUX_NETLINK_H
+#define __LINUX_NETLINK_H
+
+#include <linux/kernel.h>
+#include <linux/socket.h> /* for __kernel_sa_family_t */
+#include <linux/types.h>
+
+#define NETLINK_ROUTE 0 /* Routing/device hook */
+#define NETLINK_UNUSED 1 /* Unused number */
+#define NETLINK_USERSOCK 2 /* Reserved for user mode socket protocols */
+#define NETLINK_FIREWALL 3 /* Unused number, formerly ip_queue */
+#define NETLINK_SOCK_DIAG 4 /* socket monitoring */
+#define NETLINK_NFLOG 5 /* netfilter/iptables ULOG */
+#define NETLINK_XFRM 6 /* ipsec */
+#define NETLINK_SELINUX 7 /* SELinux event notifications */
+#define NETLINK_ISCSI 8 /* Open-iSCSI */
+#define NETLINK_AUDIT 9 /* auditing */
+#define NETLINK_FIB_LOOKUP 10
+#define NETLINK_CONNECTOR 11
+#define NETLINK_NETFILTER 12 /* netfilter subsystem */
+#define NETLINK_IP6_FW 13
+#define NETLINK_DNRTMSG 14 /* DECnet routing messages */
+#define NETLINK_KOBJECT_UEVENT 15 /* Kernel messages to userspace */
+#define NETLINK_GENERIC 16
+/* leave room for NETLINK_DM (DM Events) */
+#define NETLINK_SCSITRANSPORT 18 /* SCSI Transports */
+#define NETLINK_ECRYPTFS 19
+#define NETLINK_RDMA 20
+#define NETLINK_CRYPTO 21 /* Crypto layer */
+
+#define NETLINK_INET_DIAG NETLINK_SOCK_DIAG
+
+#define MAX_LINKS 32
+
+struct sockaddr_nl {
+ __kernel_sa_family_t nl_family; /* AF_NETLINK */
+ unsigned short nl_pad; /* zero */
+ __u32 nl_pid; /* port ID */
+ __u32 nl_groups; /* multicast groups mask */
+};
+
+struct nlmsghdr {
+ __u32 nlmsg_len; /* Length of message including header */
+ __u16 nlmsg_type; /* Message content */
+ __u16 nlmsg_flags; /* Additional flags */
+ __u32 nlmsg_seq; /* Sequence number */
+ __u32 nlmsg_pid; /* Sending process port ID */
+};
+
+/* Flags values */
+
+#define NLM_F_REQUEST 1 /* It is request message. */
+#define NLM_F_MULTI 2 /* Multipart message, terminated by NLMSG_DONE */
+#define NLM_F_ACK 4 /* Reply with ack, with zero or error code */
+#define NLM_F_ECHO 8 /* Echo this request */
+#define NLM_F_DUMP_INTR 16 /* Dump was inconsistent due to sequence change */
+#define NLM_F_DUMP_FILTERED 32 /* Dump was filtered as requested */
+
+/* Modifiers to GET request */
+#define NLM_F_ROOT 0x100 /* specify tree root */
+#define NLM_F_MATCH 0x200 /* return all matching */
+#define NLM_F_ATOMIC 0x400 /* atomic GET */
+#define NLM_F_DUMP (NLM_F_ROOT|NLM_F_MATCH)
+
+/* Modifiers to NEW request */
+#define NLM_F_REPLACE 0x100 /* Override existing */
+#define NLM_F_EXCL 0x200 /* Do not touch, if it exists */
+#define NLM_F_CREATE 0x400 /* Create, if it does not exist */
+#define NLM_F_APPEND 0x800 /* Add to end of list */
+
+/*
+ 4.4BSD ADD NLM_F_CREATE|NLM_F_EXCL
+ 4.4BSD CHANGE NLM_F_REPLACE
+
+ True CHANGE NLM_F_CREATE|NLM_F_REPLACE
+ Append NLM_F_CREATE
+ Check NLM_F_EXCL
+ */
+
+#define NLMSG_ALIGNTO 4U
+#define NLMSG_ALIGN(len) ( ((len)+NLMSG_ALIGNTO-1) & ~(NLMSG_ALIGNTO-1) )
+#define NLMSG_HDRLEN ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr)))
+#define NLMSG_LENGTH(len) ((len) + NLMSG_HDRLEN)
+#define NLMSG_SPACE(len) NLMSG_ALIGN(NLMSG_LENGTH(len))
+#define NLMSG_DATA(nlh) ((void*)(((char*)nlh) + NLMSG_LENGTH(0)))
+#define NLMSG_NEXT(nlh,len) ((len) -= NLMSG_ALIGN((nlh)->nlmsg_len), \
+ (struct nlmsghdr*)(((char*)(nlh)) + NLMSG_ALIGN((nlh)->nlmsg_len)))
+#define NLMSG_OK(nlh,len) ((len) >= (int)sizeof(struct nlmsghdr) && \
+ (nlh)->nlmsg_len >= sizeof(struct nlmsghdr) && \
+ (nlh)->nlmsg_len <= (len))
+#define NLMSG_PAYLOAD(nlh,len) ((nlh)->nlmsg_len - NLMSG_SPACE((len)))
+
+#define NLMSG_NOOP 0x1 /* Nothing. */
+#define NLMSG_ERROR 0x2 /* Error */
+#define NLMSG_DONE 0x3 /* End of a dump */
+#define NLMSG_OVERRUN 0x4 /* Data lost */
+
+#define NLMSG_MIN_TYPE 0x10 /* < 0x10: reserved control messages */
+
+struct nlmsgerr {
+ int error;
+ struct nlmsghdr msg;
+};
+
+#define NETLINK_ADD_MEMBERSHIP 1
+#define NETLINK_DROP_MEMBERSHIP 2
+#define NETLINK_PKTINFO 3
+#define NETLINK_BROADCAST_ERROR 4
+#define NETLINK_NO_ENOBUFS 5
+#define NETLINK_RX_RING 6
+#define NETLINK_TX_RING 7
+#define NETLINK_LISTEN_ALL_NSID 8
+#define NETLINK_LIST_MEMBERSHIPS 9
+#define NETLINK_CAP_ACK 10
+
+struct nl_pktinfo {
+ __u32 group;
+};
+
+struct nl_mmap_req {
+ unsigned int nm_block_size;
+ unsigned int nm_block_nr;
+ unsigned int nm_frame_size;
+ unsigned int nm_frame_nr;
+};
+
+struct nl_mmap_hdr {
+ unsigned int nm_status;
+ unsigned int nm_len;
+ __u32 nm_group;
+ /* credentials */
+ __u32 nm_pid;
+ __u32 nm_uid;
+ __u32 nm_gid;
+};
+
+enum nl_mmap_status {
+ NL_MMAP_STATUS_UNUSED,
+ NL_MMAP_STATUS_RESERVED,
+ NL_MMAP_STATUS_VALID,
+ NL_MMAP_STATUS_COPY,
+ NL_MMAP_STATUS_SKIP,
+};
+
+#define NL_MMAP_MSG_ALIGNMENT NLMSG_ALIGNTO
+#define NL_MMAP_MSG_ALIGN(sz) __ALIGN_KERNEL(sz, NL_MMAP_MSG_ALIGNMENT)
+#define NL_MMAP_HDRLEN NL_MMAP_MSG_ALIGN(sizeof(struct nl_mmap_hdr))
+
+#define NET_MAJOR 36 /* Major 36 is reserved for networking */
+
+enum {
+ NETLINK_UNCONNECTED = 0,
+ NETLINK_CONNECTED,
+};
+
+/*
+ * <------- NLA_HDRLEN ------> <-- NLA_ALIGN(payload)-->
+ * +---------------------+- - -+- - - - - - - - - -+- - -+
+ * | Header | Pad | Payload | Pad |
+ * | (struct nlattr) | ing | | ing |
+ * +---------------------+- - -+- - - - - - - - - -+- - -+
+ * <-------------- nlattr->nla_len -------------->
+ */
+
+struct nlattr {
+ __u16 nla_len;
+ __u16 nla_type;
+};
+
+/*
+ * nla_type (16 bits)
+ * +---+---+-------------------------------+
+ * | N | O | Attribute Type |
+ * +---+---+-------------------------------+
+ * N := Carries nested attributes
+ * O := Payload stored in network byte order
+ *
+ * Note: The N and O flag are mutually exclusive.
+ */
+#define NLA_F_NESTED (1 << 15)
+#define NLA_F_NET_BYTEORDER (1 << 14)
+#define NLA_TYPE_MASK ~(NLA_F_NESTED | NLA_F_NET_BYTEORDER)
+
+#define NLA_ALIGNTO 4
+#define NLA_ALIGN(len) (((len) + NLA_ALIGNTO - 1) & ~(NLA_ALIGNTO - 1))
+#define NLA_HDRLEN ((int) NLA_ALIGN(sizeof(struct nlattr)))
+
+
+#endif /* __LINUX_NETLINK_H */
diff --git a/iproute2/include/linux/netlink_diag.h b/iproute2/include/linux/netlink_diag.h
new file mode 100644
index 0000000..f2159d3
--- /dev/null
+++ b/iproute2/include/linux/netlink_diag.h
@@ -0,0 +1,53 @@
+#ifndef __NETLINK_DIAG_H__
+#define __NETLINK_DIAG_H__
+
+#include <linux/types.h>
+
+struct netlink_diag_req {
+ __u8 sdiag_family;
+ __u8 sdiag_protocol;
+ __u16 pad;
+ __u32 ndiag_ino;
+ __u32 ndiag_show;
+ __u32 ndiag_cookie[2];
+};
+
+struct netlink_diag_msg {
+ __u8 ndiag_family;
+ __u8 ndiag_type;
+ __u8 ndiag_protocol;
+ __u8 ndiag_state;
+
+ __u32 ndiag_portid;
+ __u32 ndiag_dst_portid;
+ __u32 ndiag_dst_group;
+ __u32 ndiag_ino;
+ __u32 ndiag_cookie[2];
+};
+
+struct netlink_diag_ring {
+ __u32 ndr_block_size;
+ __u32 ndr_block_nr;
+ __u32 ndr_frame_size;
+ __u32 ndr_frame_nr;
+};
+
+enum {
+ /* NETLINK_DIAG_NONE, standard nl API requires this attribute! */
+ NETLINK_DIAG_MEMINFO,
+ NETLINK_DIAG_GROUPS,
+ NETLINK_DIAG_RX_RING,
+ NETLINK_DIAG_TX_RING,
+
+ __NETLINK_DIAG_MAX,
+};
+
+#define NETLINK_DIAG_MAX (__NETLINK_DIAG_MAX - 1)
+
+#define NDIAG_PROTO_ALL ((__u8) ~0)
+
+#define NDIAG_SHOW_MEMINFO 0x00000001 /* show memory info of a socket */
+#define NDIAG_SHOW_GROUPS 0x00000002 /* show groups of a netlink socket */
+#define NDIAG_SHOW_RING_CFG 0x00000004 /* show ring configuration */
+
+#endif
diff --git a/iproute2/include/linux/packet_diag.h b/iproute2/include/linux/packet_diag.h
new file mode 100644
index 0000000..d08c63f
--- /dev/null
+++ b/iproute2/include/linux/packet_diag.h
@@ -0,0 +1,80 @@
+#ifndef __PACKET_DIAG_H__
+#define __PACKET_DIAG_H__
+
+#include <linux/types.h>
+
+struct packet_diag_req {
+ __u8 sdiag_family;
+ __u8 sdiag_protocol;
+ __u16 pad;
+ __u32 pdiag_ino;
+ __u32 pdiag_show;
+ __u32 pdiag_cookie[2];
+};
+
+#define PACKET_SHOW_INFO 0x00000001 /* Basic packet_sk information */
+#define PACKET_SHOW_MCLIST 0x00000002 /* A set of packet_diag_mclist-s */
+#define PACKET_SHOW_RING_CFG 0x00000004 /* Rings configuration parameters */
+#define PACKET_SHOW_FANOUT 0x00000008
+#define PACKET_SHOW_MEMINFO 0x00000010
+#define PACKET_SHOW_FILTER 0x00000020
+
+struct packet_diag_msg {
+ __u8 pdiag_family;
+ __u8 pdiag_type;
+ __u16 pdiag_num;
+
+ __u32 pdiag_ino;
+ __u32 pdiag_cookie[2];
+};
+
+enum {
+ /* PACKET_DIAG_NONE, standard nl API requires this attribute! */
+ PACKET_DIAG_INFO,
+ PACKET_DIAG_MCLIST,
+ PACKET_DIAG_RX_RING,
+ PACKET_DIAG_TX_RING,
+ PACKET_DIAG_FANOUT,
+ PACKET_DIAG_UID,
+ PACKET_DIAG_MEMINFO,
+ PACKET_DIAG_FILTER,
+
+ __PACKET_DIAG_MAX,
+};
+
+#define PACKET_DIAG_MAX (__PACKET_DIAG_MAX - 1)
+
+struct packet_diag_info {
+ __u32 pdi_index;
+ __u32 pdi_version;
+ __u32 pdi_reserve;
+ __u32 pdi_copy_thresh;
+ __u32 pdi_tstamp;
+ __u32 pdi_flags;
+
+#define PDI_RUNNING 0x1
+#define PDI_AUXDATA 0x2
+#define PDI_ORIGDEV 0x4
+#define PDI_VNETHDR 0x8
+#define PDI_LOSS 0x10
+};
+
+struct packet_diag_mclist {
+ __u32 pdmc_index;
+ __u32 pdmc_count;
+ __u16 pdmc_type;
+ __u16 pdmc_alen;
+ __u8 pdmc_addr[MAX_ADDR_LEN];
+};
+
+struct packet_diag_ring {
+ __u32 pdr_block_size;
+ __u32 pdr_block_nr;
+ __u32 pdr_frame_size;
+ __u32 pdr_frame_nr;
+ __u32 pdr_retire_tmo;
+ __u32 pdr_sizeof_priv;
+ __u32 pdr_features;
+};
+
+#endif
diff --git a/iproute2/include/linux/pkt_cls.h b/iproute2/include/linux/pkt_cls.h
new file mode 100644
index 0000000..a323146
--- /dev/null
+++ b/iproute2/include/linux/pkt_cls.h
@@ -0,0 +1,448 @@
+#ifndef __LINUX_PKT_CLS_H
+#define __LINUX_PKT_CLS_H
+
+#include <linux/types.h>
+#include <linux/pkt_sched.h>
+
+
+/* Action attributes */
+enum {
+ TCA_ACT_UNSPEC,
+ TCA_ACT_KIND,
+ TCA_ACT_OPTIONS,
+ TCA_ACT_INDEX,
+ TCA_ACT_STATS,
+ __TCA_ACT_MAX
+};
+
+#define TCA_ACT_MAX __TCA_ACT_MAX
+#define TCA_OLD_COMPAT (TCA_ACT_MAX+1)
+#define TCA_ACT_MAX_PRIO 32
+#define TCA_ACT_BIND 1
+#define TCA_ACT_NOBIND 0
+#define TCA_ACT_UNBIND 1
+#define TCA_ACT_NOUNBIND 0
+#define TCA_ACT_REPLACE 1
+#define TCA_ACT_NOREPLACE 0
+
+#define TC_ACT_UNSPEC (-1)
+#define TC_ACT_OK 0
+#define TC_ACT_RECLASSIFY 1
+#define TC_ACT_SHOT 2
+#define TC_ACT_PIPE 3
+#define TC_ACT_STOLEN 4
+#define TC_ACT_QUEUED 5
+#define TC_ACT_REPEAT 6
+#define TC_ACT_REDIRECT 7
+#define TC_ACT_JUMP 0x10000000
+
+/* Action type identifiers*/
+enum {
+ TCA_ID_UNSPEC=0,
+ TCA_ID_POLICE=1,
+ /* other actions go here */
+ __TCA_ID_MAX=255
+};
+
+#define TCA_ID_MAX __TCA_ID_MAX
+
+struct tc_police {
+ __u32 index;
+ int action;
+#define TC_POLICE_UNSPEC TC_ACT_UNSPEC
+#define TC_POLICE_OK TC_ACT_OK
+#define TC_POLICE_RECLASSIFY TC_ACT_RECLASSIFY
+#define TC_POLICE_SHOT TC_ACT_SHOT
+#define TC_POLICE_PIPE TC_ACT_PIPE
+
+ __u32 limit;
+ __u32 burst;
+ __u32 mtu;
+ struct tc_ratespec rate;
+ struct tc_ratespec peakrate;
+ int refcnt;
+ int bindcnt;
+ __u32 capab;
+};
+
+struct tcf_t {
+ __u64 install;
+ __u64 lastuse;
+ __u64 expires;
+};
+
+struct tc_cnt {
+ int refcnt;
+ int bindcnt;
+};
+
+#define tc_gen \
+ __u32 index; \
+ __u32 capab; \
+ int action; \
+ int refcnt; \
+ int bindcnt
+
+enum {
+ TCA_POLICE_UNSPEC,
+ TCA_POLICE_TBF,
+ TCA_POLICE_RATE,
+ TCA_POLICE_PEAKRATE,
+ TCA_POLICE_AVRATE,
+ TCA_POLICE_RESULT,
+ __TCA_POLICE_MAX
+#define TCA_POLICE_RESULT TCA_POLICE_RESULT
+};
+
+#define TCA_POLICE_MAX (__TCA_POLICE_MAX - 1)
+
+/* U32 filters */
+
+#define TC_U32_HTID(h) ((h)&0xFFF00000)
+#define TC_U32_USERHTID(h) (TC_U32_HTID(h)>>20)
+#define TC_U32_HASH(h) (((h)>>12)&0xFF)
+#define TC_U32_NODE(h) ((h)&0xFFF)
+#define TC_U32_KEY(h) ((h)&0xFFFFF)
+#define TC_U32_UNSPEC 0
+#define TC_U32_ROOT (0xFFF00000)
+
+enum {
+ TCA_U32_UNSPEC,
+ TCA_U32_CLASSID,
+ TCA_U32_HASH,
+ TCA_U32_LINK,
+ TCA_U32_DIVISOR,
+ TCA_U32_SEL,
+ TCA_U32_POLICE,
+ TCA_U32_ACT,
+ TCA_U32_INDEV,
+ TCA_U32_PCNT,
+ TCA_U32_MARK,
+ __TCA_U32_MAX
+};
+
+#define TCA_U32_MAX (__TCA_U32_MAX - 1)
+
+struct tc_u32_key {
+ __be32 mask;
+ __be32 val;
+ int off;
+ int offmask;
+};
+
+struct tc_u32_sel {
+ unsigned char flags;
+ unsigned char offshift;
+ unsigned char nkeys;
+
+ __be16 offmask;
+ __u16 off;
+ short offoff;
+
+ short hoff;
+ __be32 hmask;
+ struct tc_u32_key keys[0];
+};
+
+struct tc_u32_mark {
+ __u32 val;
+ __u32 mask;
+ __u32 success;
+};
+
+struct tc_u32_pcnt {
+ __u64 rcnt;
+ __u64 rhit;
+ __u64 kcnts[0];
+};
+
+/* Flags */
+
+#define TC_U32_TERMINAL 1
+#define TC_U32_OFFSET 2
+#define TC_U32_VAROFFSET 4
+#define TC_U32_EAT 8
+
+#define TC_U32_MAXDEPTH 8
+
+
+/* RSVP filter */
+
+enum {
+ TCA_RSVP_UNSPEC,
+ TCA_RSVP_CLASSID,
+ TCA_RSVP_DST,
+ TCA_RSVP_SRC,
+ TCA_RSVP_PINFO,
+ TCA_RSVP_POLICE,
+ TCA_RSVP_ACT,
+ __TCA_RSVP_MAX
+};
+
+#define TCA_RSVP_MAX (__TCA_RSVP_MAX - 1 )
+
+struct tc_rsvp_gpi {
+ __u32 key;
+ __u32 mask;
+ int offset;
+};
+
+struct tc_rsvp_pinfo {
+ struct tc_rsvp_gpi dpi;
+ struct tc_rsvp_gpi spi;
+ __u8 protocol;
+ __u8 tunnelid;
+ __u8 tunnelhdr;
+ __u8 pad;
+};
+
+/* ROUTE filter */
+
+enum {
+ TCA_ROUTE4_UNSPEC,
+ TCA_ROUTE4_CLASSID,
+ TCA_ROUTE4_TO,
+ TCA_ROUTE4_FROM,
+ TCA_ROUTE4_IIF,
+ TCA_ROUTE4_POLICE,
+ TCA_ROUTE4_ACT,
+ __TCA_ROUTE4_MAX
+};
+
+#define TCA_ROUTE4_MAX (__TCA_ROUTE4_MAX - 1)
+
+
+/* FW filter */
+
+enum {
+ TCA_FW_UNSPEC,
+ TCA_FW_CLASSID,
+ TCA_FW_POLICE,
+ TCA_FW_INDEV, /* used by CONFIG_NET_CLS_IND */
+ TCA_FW_ACT, /* used by CONFIG_NET_CLS_ACT */
+ TCA_FW_MASK,
+ __TCA_FW_MAX
+};
+
+#define TCA_FW_MAX (__TCA_FW_MAX - 1)
+
+/* TC index filter */
+
+enum {
+ TCA_TCINDEX_UNSPEC,
+ TCA_TCINDEX_HASH,
+ TCA_TCINDEX_MASK,
+ TCA_TCINDEX_SHIFT,
+ TCA_TCINDEX_FALL_THROUGH,
+ TCA_TCINDEX_CLASSID,
+ TCA_TCINDEX_POLICE,
+ TCA_TCINDEX_ACT,
+ __TCA_TCINDEX_MAX
+};
+
+#define TCA_TCINDEX_MAX (__TCA_TCINDEX_MAX - 1)
+
+/* Flow filter */
+
+enum {
+ FLOW_KEY_SRC,
+ FLOW_KEY_DST,
+ FLOW_KEY_PROTO,
+ FLOW_KEY_PROTO_SRC,
+ FLOW_KEY_PROTO_DST,
+ FLOW_KEY_IIF,
+ FLOW_KEY_PRIORITY,
+ FLOW_KEY_MARK,
+ FLOW_KEY_NFCT,
+ FLOW_KEY_NFCT_SRC,
+ FLOW_KEY_NFCT_DST,
+ FLOW_KEY_NFCT_PROTO_SRC,
+ FLOW_KEY_NFCT_PROTO_DST,
+ FLOW_KEY_RTCLASSID,
+ FLOW_KEY_SKUID,
+ FLOW_KEY_SKGID,
+ FLOW_KEY_VLAN_TAG,
+ FLOW_KEY_RXHASH,
+ __FLOW_KEY_MAX,
+};
+
+#define FLOW_KEY_MAX (__FLOW_KEY_MAX - 1)
+
+enum {
+ FLOW_MODE_MAP,
+ FLOW_MODE_HASH,
+};
+
+enum {
+ TCA_FLOW_UNSPEC,
+ TCA_FLOW_KEYS,
+ TCA_FLOW_MODE,
+ TCA_FLOW_BASECLASS,
+ TCA_FLOW_RSHIFT,
+ TCA_FLOW_ADDEND,
+ TCA_FLOW_MASK,
+ TCA_FLOW_XOR,
+ TCA_FLOW_DIVISOR,
+ TCA_FLOW_ACT,
+ TCA_FLOW_POLICE,
+ TCA_FLOW_EMATCHES,
+ TCA_FLOW_PERTURB,
+ __TCA_FLOW_MAX
+};
+
+#define TCA_FLOW_MAX (__TCA_FLOW_MAX - 1)
+
+/* Basic filter */
+
+enum {
+ TCA_BASIC_UNSPEC,
+ TCA_BASIC_CLASSID,
+ TCA_BASIC_EMATCHES,
+ TCA_BASIC_ACT,
+ TCA_BASIC_POLICE,
+ __TCA_BASIC_MAX
+};
+
+#define TCA_BASIC_MAX (__TCA_BASIC_MAX - 1)
+
+
+/* Cgroup classifier */
+
+enum {
+ TCA_CGROUP_UNSPEC,
+ TCA_CGROUP_ACT,
+ TCA_CGROUP_POLICE,
+ TCA_CGROUP_EMATCHES,
+ __TCA_CGROUP_MAX,
+};
+
+#define TCA_CGROUP_MAX (__TCA_CGROUP_MAX - 1)
+
+/* BPF classifier */
+
+#define TCA_BPF_FLAG_ACT_DIRECT (1 << 0)
+
+enum {
+ TCA_BPF_UNSPEC,
+ TCA_BPF_ACT,
+ TCA_BPF_POLICE,
+ TCA_BPF_CLASSID,
+ TCA_BPF_OPS_LEN,
+ TCA_BPF_OPS,
+ TCA_BPF_FD,
+ TCA_BPF_NAME,
+ TCA_BPF_FLAGS,
+ __TCA_BPF_MAX,
+};
+
+#define TCA_BPF_MAX (__TCA_BPF_MAX - 1)
+
+/* Flower classifier */
+
+enum {
+ TCA_FLOWER_UNSPEC,
+ TCA_FLOWER_CLASSID,
+ TCA_FLOWER_INDEV,
+ TCA_FLOWER_ACT,
+ TCA_FLOWER_KEY_ETH_DST, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ETH_DST_MASK, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ETH_SRC, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ETH_SRC_MASK, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ETH_TYPE, /* be16 */
+ TCA_FLOWER_KEY_IP_PROTO, /* u8 */
+ TCA_FLOWER_KEY_IPV4_SRC, /* be32 */
+ TCA_FLOWER_KEY_IPV4_SRC_MASK, /* be32 */
+ TCA_FLOWER_KEY_IPV4_DST, /* be32 */
+ TCA_FLOWER_KEY_IPV4_DST_MASK, /* be32 */
+ TCA_FLOWER_KEY_IPV6_SRC, /* struct in6_addr */
+ TCA_FLOWER_KEY_IPV6_SRC_MASK, /* struct in6_addr */
+ TCA_FLOWER_KEY_IPV6_DST, /* struct in6_addr */
+ TCA_FLOWER_KEY_IPV6_DST_MASK, /* struct in6_addr */
+ TCA_FLOWER_KEY_TCP_SRC, /* be16 */
+ TCA_FLOWER_KEY_TCP_DST, /* be16 */
+ TCA_FLOWER_KEY_UDP_SRC, /* be16 */
+ TCA_FLOWER_KEY_UDP_DST, /* be16 */
+ __TCA_FLOWER_MAX,
+};
+
+#define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1)
+
+/* Extended Matches */
+
+struct tcf_ematch_tree_hdr {
+ __u16 nmatches;
+ __u16 progid;
+};
+
+enum {
+ TCA_EMATCH_TREE_UNSPEC,
+ TCA_EMATCH_TREE_HDR,
+ TCA_EMATCH_TREE_LIST,
+ __TCA_EMATCH_TREE_MAX
+};
+#define TCA_EMATCH_TREE_MAX (__TCA_EMATCH_TREE_MAX - 1)
+
+struct tcf_ematch_hdr {
+ __u16 matchid;
+ __u16 kind;
+ __u16 flags;
+ __u16 pad; /* currently unused */
+};
+
+/* 0 1
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5
+ * +-----------------------+-+-+---+
+ * | Unused |S|I| R |
+ * +-----------------------+-+-+---+
+ *
+ * R(2) ::= relation to next ematch
+ * where: 0 0 END (last ematch)
+ * 0 1 AND
+ * 1 0 OR
+ * 1 1 Unused (invalid)
+ * I(1) ::= invert result
+ * S(1) ::= simple payload
+ */
+#define TCF_EM_REL_END 0
+#define TCF_EM_REL_AND (1<<0)
+#define TCF_EM_REL_OR (1<<1)
+#define TCF_EM_INVERT (1<<2)
+#define TCF_EM_SIMPLE (1<<3)
+
+#define TCF_EM_REL_MASK 3
+#define TCF_EM_REL_VALID(v) (((v) & TCF_EM_REL_MASK) != TCF_EM_REL_MASK)
+
+enum {
+ TCF_LAYER_LINK,
+ TCF_LAYER_NETWORK,
+ TCF_LAYER_TRANSPORT,
+ __TCF_LAYER_MAX
+};
+#define TCF_LAYER_MAX (__TCF_LAYER_MAX - 1)
+
+/* Ematch type assignments
+ * 1..32767 Reserved for ematches inside kernel tree
+ * 32768..65535 Free to use, not reliable
+ */
+#define TCF_EM_CONTAINER 0
+#define TCF_EM_CMP 1
+#define TCF_EM_NBYTE 2
+#define TCF_EM_U32 3
+#define TCF_EM_META 4
+#define TCF_EM_TEXT 5
+#define TCF_EM_VLAN 6
+#define TCF_EM_CANID 7
+#define TCF_EM_IPSET 8
+#define TCF_EM_MAX 8
+
+enum {
+ TCF_EM_PROG_TC
+};
+
+enum {
+ TCF_EM_OPND_EQ,
+ TCF_EM_OPND_GT,
+ TCF_EM_OPND_LT
+};
+
+#endif
diff --git a/iproute2/include/linux/pkt_sched.h b/iproute2/include/linux/pkt_sched.h
new file mode 100644
index 0000000..8cb18b4
--- /dev/null
+++ b/iproute2/include/linux/pkt_sched.h
@@ -0,0 +1,857 @@
+#ifndef __LINUX_PKT_SCHED_H
+#define __LINUX_PKT_SCHED_H
+
+#include <linux/types.h>
+
+/* Logical priority bands not depending on specific packet scheduler.
+ Every scheduler will map them to real traffic classes, if it has
+ no more precise mechanism to classify packets.
+
+ These numbers have no special meaning, though their coincidence
+ with obsolete IPv6 values is not occasional :-). New IPv6 drafts
+ preferred full anarchy inspired by diffserv group.
+
+ Note: TC_PRIO_BESTEFFORT does not mean that it is the most unhappy
+ class, actually, as rule it will be handled with more care than
+ filler or even bulk.
+ */
+
+#define TC_PRIO_BESTEFFORT 0
+#define TC_PRIO_FILLER 1
+#define TC_PRIO_BULK 2
+#define TC_PRIO_INTERACTIVE_BULK 4
+#define TC_PRIO_INTERACTIVE 6
+#define TC_PRIO_CONTROL 7
+
+#define TC_PRIO_MAX 15
+
+/* Generic queue statistics, available for all the elements.
+ Particular schedulers may have also their private records.
+ */
+
+struct tc_stats {
+ __u64 bytes; /* Number of enqueued bytes */
+ __u32 packets; /* Number of enqueued packets */
+ __u32 drops; /* Packets dropped because of lack of resources */
+ __u32 overlimits; /* Number of throttle events when this
+ * flow goes out of allocated bandwidth */
+ __u32 bps; /* Current flow byte rate */
+ __u32 pps; /* Current flow packet rate */
+ __u32 qlen;
+ __u32 backlog;
+};
+
+struct tc_estimator {
+ signed char interval;
+ unsigned char ewma_log;
+};
+
+/* "Handles"
+ ---------
+
+ All the traffic control objects have 32bit identifiers, or "handles".
+
+ They can be considered as opaque numbers from user API viewpoint,
+ but actually they always consist of two fields: major and
+ minor numbers, which are interpreted by kernel specially,
+ that may be used by applications, though not recommended.
+
+ F.e. qdisc handles always have minor number equal to zero,
+ classes (or flows) have major equal to parent qdisc major, and
+ minor uniquely identifying class inside qdisc.
+
+ Macros to manipulate handles:
+ */
+
+#define TC_H_MAJ_MASK (0xFFFF0000U)
+#define TC_H_MIN_MASK (0x0000FFFFU)
+#define TC_H_MAJ(h) ((h)&TC_H_MAJ_MASK)
+#define TC_H_MIN(h) ((h)&TC_H_MIN_MASK)
+#define TC_H_MAKE(maj,min) (((maj)&TC_H_MAJ_MASK)|((min)&TC_H_MIN_MASK))
+
+#define TC_H_UNSPEC (0U)
+#define TC_H_ROOT (0xFFFFFFFFU)
+#define TC_H_INGRESS (0xFFFFFFF1U)
+#define TC_H_CLSACT TC_H_INGRESS
+
+#define TC_H_MIN_INGRESS 0xFFF2U
+#define TC_H_MIN_EGRESS 0xFFF3U
+
+/* Need to corrospond to iproute2 tc/tc_core.h "enum link_layer" */
+enum tc_link_layer {
+ TC_LINKLAYER_UNAWARE, /* Indicate unaware old iproute2 util */
+ TC_LINKLAYER_ETHERNET,
+ TC_LINKLAYER_ATM,
+};
+#define TC_LINKLAYER_MASK 0x0F /* limit use to lower 4 bits */
+
+struct tc_ratespec {
+ unsigned char cell_log;
+ __u8 linklayer; /* lower 4 bits */
+ unsigned short overhead;
+ short cell_align;
+ unsigned short mpu;
+ __u32 rate;
+};
+
+#define TC_RTAB_SIZE 1024
+
+struct tc_sizespec {
+ unsigned char cell_log;
+ unsigned char size_log;
+ short cell_align;
+ int overhead;
+ unsigned int linklayer;
+ unsigned int mpu;
+ unsigned int mtu;
+ unsigned int tsize;
+};
+
+enum {
+ TCA_STAB_UNSPEC,
+ TCA_STAB_BASE,
+ TCA_STAB_DATA,
+ __TCA_STAB_MAX
+};
+
+#define TCA_STAB_MAX (__TCA_STAB_MAX - 1)
+
+/* FIFO section */
+
+struct tc_fifo_qopt {
+ __u32 limit; /* Queue length: bytes for bfifo, packets for pfifo */
+};
+
+/* PRIO section */
+
+#define TCQ_PRIO_BANDS 16
+#define TCQ_MIN_PRIO_BANDS 2
+
+struct tc_prio_qopt {
+ int bands; /* Number of bands */
+ __u8 priomap[TC_PRIO_MAX+1]; /* Map: logical priority -> PRIO band */
+};
+
+/* MULTIQ section */
+
+struct tc_multiq_qopt {
+ __u16 bands; /* Number of bands */
+ __u16 max_bands; /* Maximum number of queues */
+};
+
+/* PLUG section */
+
+#define TCQ_PLUG_BUFFER 0
+#define TCQ_PLUG_RELEASE_ONE 1
+#define TCQ_PLUG_RELEASE_INDEFINITE 2
+#define TCQ_PLUG_LIMIT 3
+
+struct tc_plug_qopt {
+ /* TCQ_PLUG_BUFFER: Inset a plug into the queue and
+ * buffer any incoming packets
+ * TCQ_PLUG_RELEASE_ONE: Dequeue packets from queue head
+ * to beginning of the next plug.
+ * TCQ_PLUG_RELEASE_INDEFINITE: Dequeue all packets from queue.
+ * Stop buffering packets until the next TCQ_PLUG_BUFFER
+ * command is received (just act as a pass-thru queue).
+ * TCQ_PLUG_LIMIT: Increase/decrease queue size
+ */
+ int action;
+ __u32 limit;
+};
+
+/* TBF section */
+
+struct tc_tbf_qopt {
+ struct tc_ratespec rate;
+ struct tc_ratespec peakrate;
+ __u32 limit;
+ __u32 buffer;
+ __u32 mtu;
+};
+
+enum {
+ TCA_TBF_UNSPEC,
+ TCA_TBF_PARMS,
+ TCA_TBF_RTAB,
+ TCA_TBF_PTAB,
+ TCA_TBF_RATE64,
+ TCA_TBF_PRATE64,
+ TCA_TBF_BURST,
+ TCA_TBF_PBURST,
+ __TCA_TBF_MAX,
+};
+
+#define TCA_TBF_MAX (__TCA_TBF_MAX - 1)
+
+
+/* TEQL section */
+
+/* TEQL does not require any parameters */
+
+/* SFQ section */
+
+struct tc_sfq_qopt {
+ unsigned quantum; /* Bytes per round allocated to flow */
+ int perturb_period; /* Period of hash perturbation */
+ __u32 limit; /* Maximal packets in queue */
+ unsigned divisor; /* Hash divisor */
+ unsigned flows; /* Maximal number of flows */
+};
+
+struct tc_sfqred_stats {
+ __u32 prob_drop; /* Early drops, below max threshold */
+ __u32 forced_drop; /* Early drops, after max threshold */
+ __u32 prob_mark; /* Marked packets, below max threshold */
+ __u32 forced_mark; /* Marked packets, after max threshold */
+ __u32 prob_mark_head; /* Marked packets, below max threshold */
+ __u32 forced_mark_head;/* Marked packets, after max threshold */
+};
+
+struct tc_sfq_qopt_v1 {
+ struct tc_sfq_qopt v0;
+ unsigned int depth; /* max number of packets per flow */
+ unsigned int headdrop;
+/* SFQRED parameters */
+ __u32 limit; /* HARD maximal flow queue length (bytes) */
+ __u32 qth_min; /* Min average length threshold (bytes) */
+ __u32 qth_max; /* Max average length threshold (bytes) */
+ unsigned char Wlog; /* log(W) */
+ unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */
+ unsigned char Scell_log; /* cell size for idle damping */
+ unsigned char flags;
+ __u32 max_P; /* probability, high resolution */
+/* SFQRED stats */
+ struct tc_sfqred_stats stats;
+};
+
+
+struct tc_sfq_xstats {
+ __s32 allot;
+};
+
+/* RED section */
+
+enum {
+ TCA_RED_UNSPEC,
+ TCA_RED_PARMS,
+ TCA_RED_STAB,
+ TCA_RED_MAX_P,
+ __TCA_RED_MAX,
+};
+
+#define TCA_RED_MAX (__TCA_RED_MAX - 1)
+
+struct tc_red_qopt {
+ __u32 limit; /* HARD maximal queue length (bytes) */
+ __u32 qth_min; /* Min average length threshold (bytes) */
+ __u32 qth_max; /* Max average length threshold (bytes) */
+ unsigned char Wlog; /* log(W) */
+ unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */
+ unsigned char Scell_log; /* cell size for idle damping */
+ unsigned char flags;
+#define TC_RED_ECN 1
+#define TC_RED_HARDDROP 2
+#define TC_RED_ADAPTATIVE 4
+};
+
+struct tc_red_xstats {
+ __u32 early; /* Early drops */
+ __u32 pdrop; /* Drops due to queue limits */
+ __u32 other; /* Drops due to drop() calls */
+ __u32 marked; /* Marked packets */
+};
+
+/* GRED section */
+
+#define MAX_DPs 16
+
+enum {
+ TCA_GRED_UNSPEC,
+ TCA_GRED_PARMS,
+ TCA_GRED_STAB,
+ TCA_GRED_DPS,
+ TCA_GRED_MAX_P,
+ TCA_GRED_LIMIT,
+ __TCA_GRED_MAX,
+};
+
+#define TCA_GRED_MAX (__TCA_GRED_MAX - 1)
+
+struct tc_gred_qopt {
+ __u32 limit; /* HARD maximal queue length (bytes) */
+ __u32 qth_min; /* Min average length threshold (bytes) */
+ __u32 qth_max; /* Max average length threshold (bytes) */
+ __u32 DP; /* up to 2^32 DPs */
+ __u32 backlog;
+ __u32 qave;
+ __u32 forced;
+ __u32 early;
+ __u32 other;
+ __u32 pdrop;
+ __u8 Wlog; /* log(W) */
+ __u8 Plog; /* log(P_max/(qth_max-qth_min)) */
+ __u8 Scell_log; /* cell size for idle damping */
+ __u8 prio; /* prio of this VQ */
+ __u32 packets;
+ __u32 bytesin;
+};
+
+/* gred setup */
+struct tc_gred_sopt {
+ __u32 DPs;
+ __u32 def_DP;
+ __u8 grio;
+ __u8 flags;
+ __u16 pad1;
+};
+
+/* CHOKe section */
+
+enum {
+ TCA_CHOKE_UNSPEC,
+ TCA_CHOKE_PARMS,
+ TCA_CHOKE_STAB,
+ TCA_CHOKE_MAX_P,
+ __TCA_CHOKE_MAX,
+};
+
+#define TCA_CHOKE_MAX (__TCA_CHOKE_MAX - 1)
+
+struct tc_choke_qopt {
+ __u32 limit; /* Hard queue length (packets) */
+ __u32 qth_min; /* Min average threshold (packets) */
+ __u32 qth_max; /* Max average threshold (packets) */
+ unsigned char Wlog; /* log(W) */
+ unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */
+ unsigned char Scell_log; /* cell size for idle damping */
+ unsigned char flags; /* see RED flags */
+};
+
+struct tc_choke_xstats {
+ __u32 early; /* Early drops */
+ __u32 pdrop; /* Drops due to queue limits */
+ __u32 other; /* Drops due to drop() calls */
+ __u32 marked; /* Marked packets */
+ __u32 matched; /* Drops due to flow match */
+};
+
+/* HTB section */
+#define TC_HTB_NUMPRIO 8
+#define TC_HTB_MAXDEPTH 8
+#define TC_HTB_PROTOVER 3 /* the same as HTB and TC's major */
+
+struct tc_htb_opt {
+ struct tc_ratespec rate;
+ struct tc_ratespec ceil;
+ __u32 buffer;
+ __u32 cbuffer;
+ __u32 quantum;
+ __u32 level; /* out only */
+ __u32 prio;
+};
+struct tc_htb_glob {
+ __u32 version; /* to match HTB/TC */
+ __u32 rate2quantum; /* bps->quantum divisor */
+ __u32 defcls; /* default class number */
+ __u32 debug; /* debug flags */
+
+ /* stats */
+ __u32 direct_pkts; /* count of non shaped packets */
+};
+enum {
+ TCA_HTB_UNSPEC,
+ TCA_HTB_PARMS,
+ TCA_HTB_INIT,
+ TCA_HTB_CTAB,
+ TCA_HTB_RTAB,
+ TCA_HTB_DIRECT_QLEN,
+ TCA_HTB_RATE64,
+ TCA_HTB_CEIL64,
+ __TCA_HTB_MAX,
+};
+
+#define TCA_HTB_MAX (__TCA_HTB_MAX - 1)
+
+struct tc_htb_xstats {
+ __u32 lends;
+ __u32 borrows;
+ __u32 giants; /* too big packets (rate will not be accurate) */
+ __u32 tokens;
+ __u32 ctokens;
+};
+
+/* HFSC section */
+
+struct tc_hfsc_qopt {
+ __u16 defcls; /* default class */
+};
+
+struct tc_service_curve {
+ __u32 m1; /* slope of the first segment in bps */
+ __u32 d; /* x-projection of the first segment in us */
+ __u32 m2; /* slope of the second segment in bps */
+};
+
+struct tc_hfsc_stats {
+ __u64 work; /* total work done */
+ __u64 rtwork; /* work done by real-time criteria */
+ __u32 period; /* current period */
+ __u32 level; /* class level in hierarchy */
+};
+
+enum {
+ TCA_HFSC_UNSPEC,
+ TCA_HFSC_RSC,
+ TCA_HFSC_FSC,
+ TCA_HFSC_USC,
+ __TCA_HFSC_MAX,
+};
+
+#define TCA_HFSC_MAX (__TCA_HFSC_MAX - 1)
+
+
+/* CBQ section */
+
+#define TC_CBQ_MAXPRIO 8
+#define TC_CBQ_MAXLEVEL 8
+#define TC_CBQ_DEF_EWMA 5
+
+struct tc_cbq_lssopt {
+ unsigned char change;
+ unsigned char flags;
+#define TCF_CBQ_LSS_BOUNDED 1
+#define TCF_CBQ_LSS_ISOLATED 2
+ unsigned char ewma_log;
+ unsigned char level;
+#define TCF_CBQ_LSS_FLAGS 1
+#define TCF_CBQ_LSS_EWMA 2
+#define TCF_CBQ_LSS_MAXIDLE 4
+#define TCF_CBQ_LSS_MINIDLE 8
+#define TCF_CBQ_LSS_OFFTIME 0x10
+#define TCF_CBQ_LSS_AVPKT 0x20
+ __u32 maxidle;
+ __u32 minidle;
+ __u32 offtime;
+ __u32 avpkt;
+};
+
+struct tc_cbq_wrropt {
+ unsigned char flags;
+ unsigned char priority;
+ unsigned char cpriority;
+ unsigned char __reserved;
+ __u32 allot;
+ __u32 weight;
+};
+
+struct tc_cbq_ovl {
+ unsigned char strategy;
+#define TC_CBQ_OVL_CLASSIC 0
+#define TC_CBQ_OVL_DELAY 1
+#define TC_CBQ_OVL_LOWPRIO 2
+#define TC_CBQ_OVL_DROP 3
+#define TC_CBQ_OVL_RCLASSIC 4
+ unsigned char priority2;
+ __u16 pad;
+ __u32 penalty;
+};
+
+struct tc_cbq_police {
+ unsigned char police;
+ unsigned char __res1;
+ unsigned short __res2;
+};
+
+struct tc_cbq_fopt {
+ __u32 split;
+ __u32 defmap;
+ __u32 defchange;
+};
+
+struct tc_cbq_xstats {
+ __u32 borrows;
+ __u32 overactions;
+ __s32 avgidle;
+ __s32 undertime;
+};
+
+enum {
+ TCA_CBQ_UNSPEC,
+ TCA_CBQ_LSSOPT,
+ TCA_CBQ_WRROPT,
+ TCA_CBQ_FOPT,
+ TCA_CBQ_OVL_STRATEGY,
+ TCA_CBQ_RATE,
+ TCA_CBQ_RTAB,
+ TCA_CBQ_POLICE,
+ __TCA_CBQ_MAX,
+};
+
+#define TCA_CBQ_MAX (__TCA_CBQ_MAX - 1)
+
+/* dsmark section */
+
+enum {
+ TCA_DSMARK_UNSPEC,
+ TCA_DSMARK_INDICES,
+ TCA_DSMARK_DEFAULT_INDEX,
+ TCA_DSMARK_SET_TC_INDEX,
+ TCA_DSMARK_MASK,
+ TCA_DSMARK_VALUE,
+ __TCA_DSMARK_MAX,
+};
+
+#define TCA_DSMARK_MAX (__TCA_DSMARK_MAX - 1)
+
+/* ATM section */
+
+enum {
+ TCA_ATM_UNSPEC,
+ TCA_ATM_FD, /* file/socket descriptor */
+ TCA_ATM_PTR, /* pointer to descriptor - later */
+ TCA_ATM_HDR, /* LL header */
+ TCA_ATM_EXCESS, /* excess traffic class (0 for CLP) */
+ TCA_ATM_ADDR, /* PVC address (for output only) */
+ TCA_ATM_STATE, /* VC state (ATM_VS_*; for output only) */
+ __TCA_ATM_MAX,
+};
+
+#define TCA_ATM_MAX (__TCA_ATM_MAX - 1)
+
+/* Network emulator */
+
+enum {
+ TCA_NETEM_UNSPEC,
+ TCA_NETEM_CORR,
+ TCA_NETEM_DELAY_DIST,
+ TCA_NETEM_REORDER,
+ TCA_NETEM_CORRUPT,
+ TCA_NETEM_LOSS,
+ TCA_NETEM_RATE,
+ TCA_NETEM_ECN,
+ TCA_NETEM_RATE64,
+ __TCA_NETEM_MAX,
+};
+
+#define TCA_NETEM_MAX (__TCA_NETEM_MAX - 1)
+
+struct tc_netem_qopt {
+ __u32 latency; /* added delay (us) */
+ __u32 limit; /* fifo limit (packets) */
+ __u32 loss; /* random packet loss (0=none ~0=100%) */
+ __u32 gap; /* re-ordering gap (0 for none) */
+ __u32 duplicate; /* random packet dup (0=none ~0=100%) */
+ __u32 jitter; /* random jitter in latency (us) */
+};
+
+struct tc_netem_corr {
+ __u32 delay_corr; /* delay correlation */
+ __u32 loss_corr; /* packet loss correlation */
+ __u32 dup_corr; /* duplicate correlation */
+};
+
+struct tc_netem_reorder {
+ __u32 probability;
+ __u32 correlation;
+};
+
+struct tc_netem_corrupt {
+ __u32 probability;
+ __u32 correlation;
+};
+
+struct tc_netem_rate {
+ __u32 rate; /* byte/s */
+ __s32 packet_overhead;
+ __u32 cell_size;
+ __s32 cell_overhead;
+};
+
+enum {
+ NETEM_LOSS_UNSPEC,
+ NETEM_LOSS_GI, /* General Intuitive - 4 state model */
+ NETEM_LOSS_GE, /* Gilbert Elliot models */
+ __NETEM_LOSS_MAX
+};
+#define NETEM_LOSS_MAX (__NETEM_LOSS_MAX - 1)
+
+/* State transition probabilities for 4 state model */
+struct tc_netem_gimodel {
+ __u32 p13;
+ __u32 p31;
+ __u32 p32;
+ __u32 p14;
+ __u32 p23;
+};
+
+/* Gilbert-Elliot models */
+struct tc_netem_gemodel {
+ __u32 p;
+ __u32 r;
+ __u32 h;
+ __u32 k1;
+};
+
+#define NETEM_DIST_SCALE 8192
+#define NETEM_DIST_MAX 16384
+
+/* DRR */
+
+enum {
+ TCA_DRR_UNSPEC,
+ TCA_DRR_QUANTUM,
+ __TCA_DRR_MAX
+};
+
+#define TCA_DRR_MAX (__TCA_DRR_MAX - 1)
+
+struct tc_drr_stats {
+ __u32 deficit;
+};
+
+/* MQPRIO */
+#define TC_QOPT_BITMASK 15
+#define TC_QOPT_MAX_QUEUE 16
+
+struct tc_mqprio_qopt {
+ __u8 num_tc;
+ __u8 prio_tc_map[TC_QOPT_BITMASK + 1];
+ __u8 hw;
+ __u16 count[TC_QOPT_MAX_QUEUE];
+ __u16 offset[TC_QOPT_MAX_QUEUE];
+};
+
+/* SFB */
+
+enum {
+ TCA_SFB_UNSPEC,
+ TCA_SFB_PARMS,
+ __TCA_SFB_MAX,
+};
+
+#define TCA_SFB_MAX (__TCA_SFB_MAX - 1)
+
+/*
+ * Note: increment, decrement are Q0.16 fixed-point values.
+ */
+struct tc_sfb_qopt {
+ __u32 rehash_interval; /* delay between hash move, in ms */
+ __u32 warmup_time; /* double buffering warmup time in ms (warmup_time < rehash_interval) */
+ __u32 max; /* max len of qlen_min */
+ __u32 bin_size; /* maximum queue length per bin */
+ __u32 increment; /* probability increment, (d1 in Blue) */
+ __u32 decrement; /* probability decrement, (d2 in Blue) */
+ __u32 limit; /* max SFB queue length */
+ __u32 penalty_rate; /* inelastic flows are rate limited to 'rate' pps */
+ __u32 penalty_burst;
+};
+
+struct tc_sfb_xstats {
+ __u32 earlydrop;
+ __u32 penaltydrop;
+ __u32 bucketdrop;
+ __u32 queuedrop;
+ __u32 childdrop; /* drops in child qdisc */
+ __u32 marked;
+ __u32 maxqlen;
+ __u32 maxprob;
+ __u32 avgprob;
+};
+
+#define SFB_MAX_PROB 0xFFFF
+
+/* QFQ */
+enum {
+ TCA_QFQ_UNSPEC,
+ TCA_QFQ_WEIGHT,
+ TCA_QFQ_LMAX,
+ __TCA_QFQ_MAX
+};
+
+#define TCA_QFQ_MAX (__TCA_QFQ_MAX - 1)
+
+struct tc_qfq_stats {
+ __u32 weight;
+ __u32 lmax;
+};
+
+/* CODEL */
+
+enum {
+ TCA_CODEL_UNSPEC,
+ TCA_CODEL_TARGET,
+ TCA_CODEL_LIMIT,
+ TCA_CODEL_INTERVAL,
+ TCA_CODEL_ECN,
+ TCA_CODEL_CE_THRESHOLD,
+ __TCA_CODEL_MAX
+};
+
+#define TCA_CODEL_MAX (__TCA_CODEL_MAX - 1)
+
+struct tc_codel_xstats {
+ __u32 maxpacket; /* largest packet we've seen so far */
+ __u32 count; /* how many drops we've done since the last time we
+ * entered dropping state
+ */
+ __u32 lastcount; /* count at entry to dropping state */
+ __u32 ldelay; /* in-queue delay seen by most recently dequeued packet */
+ __s32 drop_next; /* time to drop next packet */
+ __u32 drop_overlimit; /* number of time max qdisc packet limit was hit */
+ __u32 ecn_mark; /* number of packets we ECN marked instead of dropped */
+ __u32 dropping; /* are we in dropping state ? */
+ __u32 ce_mark; /* number of CE marked packets because of ce_threshold */
+};
+
+/* FQ_CODEL */
+
+enum {
+ TCA_FQ_CODEL_UNSPEC,
+ TCA_FQ_CODEL_TARGET,
+ TCA_FQ_CODEL_LIMIT,
+ TCA_FQ_CODEL_INTERVAL,
+ TCA_FQ_CODEL_ECN,
+ TCA_FQ_CODEL_FLOWS,
+ TCA_FQ_CODEL_QUANTUM,
+ TCA_FQ_CODEL_CE_THRESHOLD,
+ __TCA_FQ_CODEL_MAX
+};
+
+#define TCA_FQ_CODEL_MAX (__TCA_FQ_CODEL_MAX - 1)
+
+enum {
+ TCA_FQ_CODEL_XSTATS_QDISC,
+ TCA_FQ_CODEL_XSTATS_CLASS,
+};
+
+struct tc_fq_codel_qd_stats {
+ __u32 maxpacket; /* largest packet we've seen so far */
+ __u32 drop_overlimit; /* number of time max qdisc
+ * packet limit was hit
+ */
+ __u32 ecn_mark; /* number of packets we ECN marked
+ * instead of being dropped
+ */
+ __u32 new_flow_count; /* number of time packets
+ * created a 'new flow'
+ */
+ __u32 new_flows_len; /* count of flows in new list */
+ __u32 old_flows_len; /* count of flows in old list */
+ __u32 ce_mark; /* packets above ce_threshold */
+};
+
+struct tc_fq_codel_cl_stats {
+ __s32 deficit;
+ __u32 ldelay; /* in-queue delay seen by most recently
+ * dequeued packet
+ */
+ __u32 count;
+ __u32 lastcount;
+ __u32 dropping;
+ __s32 drop_next;
+};
+
+struct tc_fq_codel_xstats {
+ __u32 type;
+ union {
+ struct tc_fq_codel_qd_stats qdisc_stats;
+ struct tc_fq_codel_cl_stats class_stats;
+ };
+};
+
+/* FQ */
+
+enum {
+ TCA_FQ_UNSPEC,
+
+ TCA_FQ_PLIMIT, /* limit of total number of packets in queue */
+
+ TCA_FQ_FLOW_PLIMIT, /* limit of packets per flow */
+
+ TCA_FQ_QUANTUM, /* RR quantum */
+
+ TCA_FQ_INITIAL_QUANTUM, /* RR quantum for new flow */
+
+ TCA_FQ_RATE_ENABLE, /* enable/disable rate limiting */
+
+ TCA_FQ_FLOW_DEFAULT_RATE,/* obsolete, do not use */
+
+ TCA_FQ_FLOW_MAX_RATE, /* per flow max rate */
+
+ TCA_FQ_BUCKETS_LOG, /* log2(number of buckets) */
+
+ TCA_FQ_FLOW_REFILL_DELAY, /* flow credit refill delay in usec */
+
+ TCA_FQ_ORPHAN_MASK, /* mask applied to orphaned skb hashes */
+
+ __TCA_FQ_MAX
+};
+
+#define TCA_FQ_MAX (__TCA_FQ_MAX - 1)
+
+struct tc_fq_qd_stats {
+ __u64 gc_flows;
+ __u64 highprio_packets;
+ __u64 tcp_retrans;
+ __u64 throttled;
+ __u64 flows_plimit;
+ __u64 pkts_too_long;
+ __u64 allocation_errors;
+ __s64 time_next_delayed_flow;
+ __u32 flows;
+ __u32 inactive_flows;
+ __u32 throttled_flows;
+ __u32 pad;
+};
+
+/* Heavy-Hitter Filter */
+
+enum {
+ TCA_HHF_UNSPEC,
+ TCA_HHF_BACKLOG_LIMIT,
+ TCA_HHF_QUANTUM,
+ TCA_HHF_HH_FLOWS_LIMIT,
+ TCA_HHF_RESET_TIMEOUT,
+ TCA_HHF_ADMIT_BYTES,
+ TCA_HHF_EVICT_TIMEOUT,
+ TCA_HHF_NON_HH_WEIGHT,
+ __TCA_HHF_MAX
+};
+
+#define TCA_HHF_MAX (__TCA_HHF_MAX - 1)
+
+struct tc_hhf_xstats {
+ __u32 drop_overlimit; /* number of times max qdisc packet limit
+ * was hit
+ */
+ __u32 hh_overlimit; /* number of times max heavy-hitters was hit */
+ __u32 hh_tot_count; /* number of captured heavy-hitters so far */
+ __u32 hh_cur_count; /* number of current heavy-hitters */
+};
+
+/* PIE */
+enum {
+ TCA_PIE_UNSPEC,
+ TCA_PIE_TARGET,
+ TCA_PIE_LIMIT,
+ TCA_PIE_TUPDATE,
+ TCA_PIE_ALPHA,
+ TCA_PIE_BETA,
+ TCA_PIE_ECN,
+ TCA_PIE_BYTEMODE,
+ __TCA_PIE_MAX
+};
+#define TCA_PIE_MAX (__TCA_PIE_MAX - 1)
+
+struct tc_pie_xstats {
+ __u32 prob; /* current probability */
+ __u32 delay; /* current delay in ms */
+ __u32 avg_dq_rate; /* current average dq_rate in bits/pie_time */
+ __u32 packets_in; /* total number of packets enqueued */
+ __u32 dropped; /* packets dropped due to pie_action */
+ __u32 overlimit; /* dropped due to lack of space in queue */
+ __u32 maxq; /* maximum queue size */
+ __u32 ecn_mark; /* packets marked with ecn*/
+};
+#endif
diff --git a/iproute2/include/linux/rtnetlink.h b/iproute2/include/linux/rtnetlink.h
new file mode 100644
index 0000000..dad2e8e
--- /dev/null
+++ b/iproute2/include/linux/rtnetlink.h
@@ -0,0 +1,676 @@
+#ifndef __LINUX_RTNETLINK_H
+#define __LINUX_RTNETLINK_H
+
+#include <linux/types.h>
+#include <linux/netlink.h>
+#include <linux/if_link.h>
+#include <linux/if_addr.h>
+#include <linux/neighbour.h>
+
+/* rtnetlink families. Values up to 127 are reserved for real address
+ * families, values above 128 may be used arbitrarily.
+ */
+#define RTNL_FAMILY_IPMR 128
+#define RTNL_FAMILY_IP6MR 129
+#define RTNL_FAMILY_MAX 129
+
+/****
+ * Routing/neighbour discovery messages.
+ ****/
+
+/* Types of messages */
+
+enum {
+ RTM_BASE = 16,
+#define RTM_BASE RTM_BASE
+
+ RTM_NEWLINK = 16,
+#define RTM_NEWLINK RTM_NEWLINK
+ RTM_DELLINK,
+#define RTM_DELLINK RTM_DELLINK
+ RTM_GETLINK,
+#define RTM_GETLINK RTM_GETLINK
+ RTM_SETLINK,
+#define RTM_SETLINK RTM_SETLINK
+
+ RTM_NEWADDR = 20,
+#define RTM_NEWADDR RTM_NEWADDR
+ RTM_DELADDR,
+#define RTM_DELADDR RTM_DELADDR
+ RTM_GETADDR,
+#define RTM_GETADDR RTM_GETADDR
+
+ RTM_NEWROUTE = 24,
+#define RTM_NEWROUTE RTM_NEWROUTE
+ RTM_DELROUTE,
+#define RTM_DELROUTE RTM_DELROUTE
+ RTM_GETROUTE,
+#define RTM_GETROUTE RTM_GETROUTE
+
+ RTM_NEWNEIGH = 28,
+#define RTM_NEWNEIGH RTM_NEWNEIGH
+ RTM_DELNEIGH,
+#define RTM_DELNEIGH RTM_DELNEIGH
+ RTM_GETNEIGH,
+#define RTM_GETNEIGH RTM_GETNEIGH
+
+ RTM_NEWRULE = 32,
+#define RTM_NEWRULE RTM_NEWRULE
+ RTM_DELRULE,
+#define RTM_DELRULE RTM_DELRULE
+ RTM_GETRULE,
+#define RTM_GETRULE RTM_GETRULE
+
+ RTM_NEWQDISC = 36,
+#define RTM_NEWQDISC RTM_NEWQDISC
+ RTM_DELQDISC,
+#define RTM_DELQDISC RTM_DELQDISC
+ RTM_GETQDISC,
+#define RTM_GETQDISC RTM_GETQDISC
+
+ RTM_NEWTCLASS = 40,
+#define RTM_NEWTCLASS RTM_NEWTCLASS
+ RTM_DELTCLASS,
+#define RTM_DELTCLASS RTM_DELTCLASS
+ RTM_GETTCLASS,
+#define RTM_GETTCLASS RTM_GETTCLASS
+
+ RTM_NEWTFILTER = 44,
+#define RTM_NEWTFILTER RTM_NEWTFILTER
+ RTM_DELTFILTER,
+#define RTM_DELTFILTER RTM_DELTFILTER
+ RTM_GETTFILTER,
+#define RTM_GETTFILTER RTM_GETTFILTER
+
+ RTM_NEWACTION = 48,
+#define RTM_NEWACTION RTM_NEWACTION
+ RTM_DELACTION,
+#define RTM_DELACTION RTM_DELACTION
+ RTM_GETACTION,
+#define RTM_GETACTION RTM_GETACTION
+
+ RTM_NEWPREFIX = 52,
+#define RTM_NEWPREFIX RTM_NEWPREFIX
+
+ RTM_GETMULTICAST = 58,
+#define RTM_GETMULTICAST RTM_GETMULTICAST
+
+ RTM_GETANYCAST = 62,
+#define RTM_GETANYCAST RTM_GETANYCAST
+
+ RTM_NEWNEIGHTBL = 64,
+#define RTM_NEWNEIGHTBL RTM_NEWNEIGHTBL
+ RTM_GETNEIGHTBL = 66,
+#define RTM_GETNEIGHTBL RTM_GETNEIGHTBL
+ RTM_SETNEIGHTBL,
+#define RTM_SETNEIGHTBL RTM_SETNEIGHTBL
+
+ RTM_NEWNDUSEROPT = 68,
+#define RTM_NEWNDUSEROPT RTM_NEWNDUSEROPT
+
+ RTM_NEWADDRLABEL = 72,
+#define RTM_NEWADDRLABEL RTM_NEWADDRLABEL
+ RTM_DELADDRLABEL,
+#define RTM_DELADDRLABEL RTM_DELADDRLABEL
+ RTM_GETADDRLABEL,
+#define RTM_GETADDRLABEL RTM_GETADDRLABEL
+
+ RTM_GETDCB = 78,
+#define RTM_GETDCB RTM_GETDCB
+ RTM_SETDCB,
+#define RTM_SETDCB RTM_SETDCB
+
+ RTM_NEWNETCONF = 80,
+#define RTM_NEWNETCONF RTM_NEWNETCONF
+ RTM_GETNETCONF = 82,
+#define RTM_GETNETCONF RTM_GETNETCONF
+
+ RTM_NEWMDB = 84,
+#define RTM_NEWMDB RTM_NEWMDB
+ RTM_DELMDB = 85,
+#define RTM_DELMDB RTM_DELMDB
+ RTM_GETMDB = 86,
+#define RTM_GETMDB RTM_GETMDB
+
+ RTM_NEWNSID = 88,
+#define RTM_NEWNSID RTM_NEWNSID
+ RTM_DELNSID = 89,
+#define RTM_DELNSID RTM_DELNSID
+ RTM_GETNSID = 90,
+#define RTM_GETNSID RTM_GETNSID
+
+ __RTM_MAX,
+#define RTM_MAX (((__RTM_MAX + 3) & ~3) - 1)
+};
+
+#define RTM_NR_MSGTYPES (RTM_MAX + 1 - RTM_BASE)
+#define RTM_NR_FAMILIES (RTM_NR_MSGTYPES >> 2)
+#define RTM_FAM(cmd) (((cmd) - RTM_BASE) >> 2)
+
+/*
+ Generic structure for encapsulation of optional route information.
+ It is reminiscent of sockaddr, but with sa_family replaced
+ with attribute type.
+ */
+
+struct rtattr {
+ unsigned short rta_len;
+ unsigned short rta_type;
+};
+
+/* Macros to handle rtattributes */
+
+#define RTA_ALIGNTO 4U
+#define RTA_ALIGN(len) ( ((len)+RTA_ALIGNTO-1) & ~(RTA_ALIGNTO-1) )
+#define RTA_OK(rta,len) ((len) >= (int)sizeof(struct rtattr) && \
+ (rta)->rta_len >= sizeof(struct rtattr) && \
+ (rta)->rta_len <= (len))
+#define RTA_NEXT(rta,attrlen) ((attrlen) -= RTA_ALIGN((rta)->rta_len), \
+ (struct rtattr*)(((char*)(rta)) + RTA_ALIGN((rta)->rta_len)))
+#define RTA_LENGTH(len) (RTA_ALIGN(sizeof(struct rtattr)) + (len))
+#define RTA_SPACE(len) RTA_ALIGN(RTA_LENGTH(len))
+#define RTA_DATA(rta) ((void*)(((char*)(rta)) + RTA_LENGTH(0)))
+#define RTA_PAYLOAD(rta) ((int)((rta)->rta_len) - RTA_LENGTH(0))
+
+
+
+
+/******************************************************************************
+ * Definitions used in routing table administration.
+ ****/
+
+struct rtmsg {
+ unsigned char rtm_family;
+ unsigned char rtm_dst_len;
+ unsigned char rtm_src_len;
+ unsigned char rtm_tos;
+
+ unsigned char rtm_table; /* Routing table id */
+ unsigned char rtm_protocol; /* Routing protocol; see below */
+ unsigned char rtm_scope; /* See below */
+ unsigned char rtm_type; /* See below */
+
+ unsigned rtm_flags;
+};
+
+/* rtm_type */
+
+enum {
+ RTN_UNSPEC,
+ RTN_UNICAST, /* Gateway or direct route */
+ RTN_LOCAL, /* Accept locally */
+ RTN_BROADCAST, /* Accept locally as broadcast,
+ send as broadcast */
+ RTN_ANYCAST, /* Accept locally as broadcast,
+ but send as unicast */
+ RTN_MULTICAST, /* Multicast route */
+ RTN_BLACKHOLE, /* Drop */
+ RTN_UNREACHABLE, /* Destination is unreachable */
+ RTN_PROHIBIT, /* Administratively prohibited */
+ RTN_THROW, /* Not in this table */
+ RTN_NAT, /* Translate this address */
+ RTN_XRESOLVE, /* Use external resolver */
+ __RTN_MAX
+};
+
+#define RTN_MAX (__RTN_MAX - 1)
+
+
+/* rtm_protocol */
+
+#define RTPROT_UNSPEC 0
+#define RTPROT_REDIRECT 1 /* Route installed by ICMP redirects;
+ not used by current IPv4 */
+#define RTPROT_KERNEL 2 /* Route installed by kernel */
+#define RTPROT_BOOT 3 /* Route installed during boot */
+#define RTPROT_STATIC 4 /* Route installed by administrator */
+
+/* Values of protocol >= RTPROT_STATIC are not interpreted by kernel;
+ they are just passed from user and back as is.
+ It will be used by hypothetical multiple routing daemons.
+ Note that protocol values should be standardized in order to
+ avoid conflicts.
+ */
+
+#define RTPROT_GATED 8 /* Apparently, GateD */
+#define RTPROT_RA 9 /* RDISC/ND router advertisements */
+#define RTPROT_MRT 10 /* Merit MRT */
+#define RTPROT_ZEBRA 11 /* Zebra */
+#define RTPROT_BIRD 12 /* BIRD */
+#define RTPROT_DNROUTED 13 /* DECnet routing daemon */
+#define RTPROT_XORP 14 /* XORP */
+#define RTPROT_NTK 15 /* Netsukuku */
+#define RTPROT_DHCP 16 /* DHCP client */
+#define RTPROT_MROUTED 17 /* Multicast daemon */
+#define RTPROT_BABEL 42 /* Babel daemon */
+
+/* rtm_scope
+
+ Really it is not scope, but sort of distance to the destination.
+ NOWHERE are reserved for not existing destinations, HOST is our
+ local addresses, LINK are destinations, located on directly attached
+ link and UNIVERSE is everywhere in the Universe.
+
+ Intermediate values are also possible f.e. interior routes
+ could be assigned a value between UNIVERSE and LINK.
+*/
+
+enum rt_scope_t {
+ RT_SCOPE_UNIVERSE=0,
+/* User defined values */
+ RT_SCOPE_SITE=200,
+ RT_SCOPE_LINK=253,
+ RT_SCOPE_HOST=254,
+ RT_SCOPE_NOWHERE=255
+};
+
+/* rtm_flags */
+
+#define RTM_F_NOTIFY 0x100 /* Notify user of route change */
+#define RTM_F_CLONED 0x200 /* This route is cloned */
+#define RTM_F_EQUALIZE 0x400 /* Multipath equalizer: NI */
+#define RTM_F_PREFIX 0x800 /* Prefix addresses */
+#define RTM_F_LOOKUP_TABLE 0x1000 /* set rtm_table to FIB lookup result */
+
+/* Reserved table identifiers */
+
+enum rt_class_t {
+ RT_TABLE_UNSPEC=0,
+/* User defined values */
+ RT_TABLE_COMPAT=252,
+ RT_TABLE_DEFAULT=253,
+ RT_TABLE_MAIN=254,
+ RT_TABLE_LOCAL=255,
+ RT_TABLE_MAX=0xFFFFFFFF
+};
+
+
+/* Routing message attributes */
+
+enum rtattr_type_t {
+ RTA_UNSPEC,
+ RTA_DST,
+ RTA_SRC,
+ RTA_IIF,
+ RTA_OIF,
+ RTA_GATEWAY,
+ RTA_PRIORITY,
+ RTA_PREFSRC,
+ RTA_METRICS,
+ RTA_MULTIPATH,
+ RTA_PROTOINFO, /* no longer used */
+ RTA_FLOW,
+ RTA_CACHEINFO,
+ RTA_SESSION, /* no longer used */
+ RTA_MP_ALGO, /* no longer used */
+ RTA_TABLE,
+ RTA_MARK,
+ RTA_MFC_STATS, /* not used - backported from the future */
+ RTA_UID,
+ RTA_VIA,
+ RTA_NEWDST,
+ RTA_PREF,
+ RTA_ENCAP_TYPE,
+ RTA_ENCAP,
+ RTA_EXPIRES,
+ __RTA_MAX
+};
+
+#define RTA_MAX (__RTA_MAX - 1)
+
+#define RTM_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct rtmsg))))
+#define RTM_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct rtmsg))
+
+/* RTM_MULTIPATH --- array of struct rtnexthop.
+ *
+ * "struct rtnexthop" describes all necessary nexthop information,
+ * i.e. parameters of path to a destination via this nexthop.
+ *
+ * At the moment it is impossible to set different prefsrc, mtu, window
+ * and rtt for different paths from multipath.
+ */
+
+struct rtnexthop {
+ unsigned short rtnh_len;
+ unsigned char rtnh_flags;
+ unsigned char rtnh_hops;
+ int rtnh_ifindex;
+};
+
+/* rtnh_flags */
+
+#define RTNH_F_DEAD 1 /* Nexthop is dead (used by multipath) */
+#define RTNH_F_PERVASIVE 2 /* Do recursive gateway lookup */
+#define RTNH_F_ONLINK 4 /* Gateway is forced on link */
+#define RTNH_F_OFFLOAD 8 /* offloaded route */
+#define RTNH_F_LINKDOWN 16 /* carrier-down on nexthop */
+
+#define RTNH_COMPARE_MASK (RTNH_F_DEAD | RTNH_F_LINKDOWN)
+
+/* Macros to handle hexthops */
+
+#define RTNH_ALIGNTO 4
+#define RTNH_ALIGN(len) ( ((len)+RTNH_ALIGNTO-1) & ~(RTNH_ALIGNTO-1) )
+#define RTNH_OK(rtnh,len) ((rtnh)->rtnh_len >= sizeof(struct rtnexthop) && \
+ ((int)(rtnh)->rtnh_len) <= (len))
+#define RTNH_NEXT(rtnh) ((struct rtnexthop*)(((char*)(rtnh)) + RTNH_ALIGN((rtnh)->rtnh_len)))
+#define RTNH_LENGTH(len) (RTNH_ALIGN(sizeof(struct rtnexthop)) + (len))
+#define RTNH_SPACE(len) RTNH_ALIGN(RTNH_LENGTH(len))
+#define RTNH_DATA(rtnh) ((struct rtattr*)(((char*)(rtnh)) + RTNH_LENGTH(0)))
+
+/* RTA_VIA */
+struct rtvia {
+ __kernel_sa_family_t rtvia_family;
+ __u8 rtvia_addr[0];
+};
+
+/* RTM_CACHEINFO */
+
+struct rta_cacheinfo {
+ __u32 rta_clntref;
+ __u32 rta_lastuse;
+ __s32 rta_expires;
+ __u32 rta_error;
+ __u32 rta_used;
+
+#define RTNETLINK_HAVE_PEERINFO 1
+ __u32 rta_id;
+ __u32 rta_ts;
+ __u32 rta_tsage;
+};
+
+/* RTM_METRICS --- array of struct rtattr with types of RTAX_* */
+
+enum {
+ RTAX_UNSPEC,
+#define RTAX_UNSPEC RTAX_UNSPEC
+ RTAX_LOCK,
+#define RTAX_LOCK RTAX_LOCK
+ RTAX_MTU,
+#define RTAX_MTU RTAX_MTU
+ RTAX_WINDOW,
+#define RTAX_WINDOW RTAX_WINDOW
+ RTAX_RTT,
+#define RTAX_RTT RTAX_RTT
+ RTAX_RTTVAR,
+#define RTAX_RTTVAR RTAX_RTTVAR
+ RTAX_SSTHRESH,
+#define RTAX_SSTHRESH RTAX_SSTHRESH
+ RTAX_CWND,
+#define RTAX_CWND RTAX_CWND
+ RTAX_ADVMSS,
+#define RTAX_ADVMSS RTAX_ADVMSS
+ RTAX_REORDERING,
+#define RTAX_REORDERING RTAX_REORDERING
+ RTAX_HOPLIMIT,
+#define RTAX_HOPLIMIT RTAX_HOPLIMIT
+ RTAX_INITCWND,
+#define RTAX_INITCWND RTAX_INITCWND
+ RTAX_FEATURES,
+#define RTAX_FEATURES RTAX_FEATURES
+ RTAX_RTO_MIN,
+#define RTAX_RTO_MIN RTAX_RTO_MIN
+ RTAX_INITRWND,
+#define RTAX_INITRWND RTAX_INITRWND
+ RTAX_QUICKACK,
+#define RTAX_QUICKACK RTAX_QUICKACK
+ RTAX_CC_ALGO,
+#define RTAX_CC_ALGO RTAX_CC_ALGO
+ __RTAX_MAX
+};
+
+#define RTAX_MAX (__RTAX_MAX - 1)
+
+#define RTAX_FEATURE_ECN (1 << 0)
+#define RTAX_FEATURE_SACK (1 << 1)
+#define RTAX_FEATURE_TIMESTAMP (1 << 2)
+#define RTAX_FEATURE_ALLFRAG (1 << 3)
+
+#define RTAX_FEATURE_MASK (RTAX_FEATURE_ECN | RTAX_FEATURE_SACK | \
+ RTAX_FEATURE_TIMESTAMP | RTAX_FEATURE_ALLFRAG)
+
+struct rta_session {
+ __u8 proto;
+ __u8 pad1;
+ __u16 pad2;
+
+ union {
+ struct {
+ __u16 sport;
+ __u16 dport;
+ } ports;
+
+ struct {
+ __u8 type;
+ __u8 code;
+ __u16 ident;
+ } icmpt;
+
+ __u32 spi;
+ } u;
+};
+
+struct rta_mfc_stats {
+ __u64 mfcs_packets;
+ __u64 mfcs_bytes;
+ __u64 mfcs_wrong_if;
+};
+
+/****
+ * General form of address family dependent message.
+ ****/
+
+struct rtgenmsg {
+ unsigned char rtgen_family;
+};
+
+/*****************************************************************
+ * Link layer specific messages.
+ ****/
+
+/* struct ifinfomsg
+ * passes link level specific information, not dependent
+ * on network protocol.
+ */
+
+struct ifinfomsg {
+ unsigned char ifi_family;
+ unsigned char __ifi_pad;
+ unsigned short ifi_type; /* ARPHRD_* */
+ int ifi_index; /* Link index */
+ unsigned ifi_flags; /* IFF_* flags */
+ unsigned ifi_change; /* IFF_* change mask */
+};
+
+/********************************************************************
+ * prefix information
+ ****/
+
+struct prefixmsg {
+ unsigned char prefix_family;
+ unsigned char prefix_pad1;
+ unsigned short prefix_pad2;
+ int prefix_ifindex;
+ unsigned char prefix_type;
+ unsigned char prefix_len;
+ unsigned char prefix_flags;
+ unsigned char prefix_pad3;
+};
+
+enum
+{
+ PREFIX_UNSPEC,
+ PREFIX_ADDRESS,
+ PREFIX_CACHEINFO,
+ __PREFIX_MAX
+};
+
+#define PREFIX_MAX (__PREFIX_MAX - 1)
+
+struct prefix_cacheinfo {
+ __u32 preferred_time;
+ __u32 valid_time;
+};
+
+
+/*****************************************************************
+ * Traffic control messages.
+ ****/
+
+struct tcmsg {
+ unsigned char tcm_family;
+ unsigned char tcm__pad1;
+ unsigned short tcm__pad2;
+ int tcm_ifindex;
+ __u32 tcm_handle;
+ __u32 tcm_parent;
+ __u32 tcm_info;
+};
+
+enum {
+ TCA_UNSPEC,
+ TCA_KIND,
+ TCA_OPTIONS,
+ TCA_STATS,
+ TCA_XSTATS,
+ TCA_RATE,
+ TCA_FCNT,
+ TCA_STATS2,
+ TCA_STAB,
+ __TCA_MAX
+};
+
+#define TCA_MAX (__TCA_MAX - 1)
+
+#define TCA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct tcmsg))))
+#define TCA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcmsg))
+
+/********************************************************************
+ * Neighbor Discovery userland options
+ ****/
+
+struct nduseroptmsg {
+ unsigned char nduseropt_family;
+ unsigned char nduseropt_pad1;
+ unsigned short nduseropt_opts_len; /* Total length of options */
+ int nduseropt_ifindex;
+ __u8 nduseropt_icmp_type;
+ __u8 nduseropt_icmp_code;
+ unsigned short nduseropt_pad2;
+ unsigned int nduseropt_pad3;
+ /* Followed by one or more ND options */
+};
+
+enum {
+ NDUSEROPT_UNSPEC,
+ NDUSEROPT_SRCADDR,
+ __NDUSEROPT_MAX
+};
+
+#define NDUSEROPT_MAX (__NDUSEROPT_MAX - 1)
+
+/* RTnetlink multicast groups - backwards compatibility for userspace */
+#define RTMGRP_LINK 1
+#define RTMGRP_NOTIFY 2
+#define RTMGRP_NEIGH 4
+#define RTMGRP_TC 8
+
+#define RTMGRP_IPV4_IFADDR 0x10
+#define RTMGRP_IPV4_MROUTE 0x20
+#define RTMGRP_IPV4_ROUTE 0x40
+#define RTMGRP_IPV4_RULE 0x80
+
+#define RTMGRP_IPV6_IFADDR 0x100
+#define RTMGRP_IPV6_MROUTE 0x200
+#define RTMGRP_IPV6_ROUTE 0x400
+#define RTMGRP_IPV6_IFINFO 0x800
+
+#define RTMGRP_DECnet_IFADDR 0x1000
+#define RTMGRP_DECnet_ROUTE 0x4000
+
+#define RTMGRP_IPV6_PREFIX 0x20000
+
+/* RTnetlink multicast groups */
+enum rtnetlink_groups {
+ RTNLGRP_NONE,
+#define RTNLGRP_NONE RTNLGRP_NONE
+ RTNLGRP_LINK,
+#define RTNLGRP_LINK RTNLGRP_LINK
+ RTNLGRP_NOTIFY,
+#define RTNLGRP_NOTIFY RTNLGRP_NOTIFY
+ RTNLGRP_NEIGH,
+#define RTNLGRP_NEIGH RTNLGRP_NEIGH
+ RTNLGRP_TC,
+#define RTNLGRP_TC RTNLGRP_TC
+ RTNLGRP_IPV4_IFADDR,
+#define RTNLGRP_IPV4_IFADDR RTNLGRP_IPV4_IFADDR
+ RTNLGRP_IPV4_MROUTE,
+#define RTNLGRP_IPV4_MROUTE RTNLGRP_IPV4_MROUTE
+ RTNLGRP_IPV4_ROUTE,
+#define RTNLGRP_IPV4_ROUTE RTNLGRP_IPV4_ROUTE
+ RTNLGRP_IPV4_RULE,
+#define RTNLGRP_IPV4_RULE RTNLGRP_IPV4_RULE
+ RTNLGRP_IPV6_IFADDR,
+#define RTNLGRP_IPV6_IFADDR RTNLGRP_IPV6_IFADDR
+ RTNLGRP_IPV6_MROUTE,
+#define RTNLGRP_IPV6_MROUTE RTNLGRP_IPV6_MROUTE
+ RTNLGRP_IPV6_ROUTE,
+#define RTNLGRP_IPV6_ROUTE RTNLGRP_IPV6_ROUTE
+ RTNLGRP_IPV6_IFINFO,
+#define RTNLGRP_IPV6_IFINFO RTNLGRP_IPV6_IFINFO
+ RTNLGRP_DECnet_IFADDR,
+#define RTNLGRP_DECnet_IFADDR RTNLGRP_DECnet_IFADDR
+ RTNLGRP_NOP2,
+ RTNLGRP_DECnet_ROUTE,
+#define RTNLGRP_DECnet_ROUTE RTNLGRP_DECnet_ROUTE
+ RTNLGRP_DECnet_RULE,
+#define RTNLGRP_DECnet_RULE RTNLGRP_DECnet_RULE
+ RTNLGRP_NOP4,
+ RTNLGRP_IPV6_PREFIX,
+#define RTNLGRP_IPV6_PREFIX RTNLGRP_IPV6_PREFIX
+ RTNLGRP_IPV6_RULE,
+#define RTNLGRP_IPV6_RULE RTNLGRP_IPV6_RULE
+ RTNLGRP_ND_USEROPT,
+#define RTNLGRP_ND_USEROPT RTNLGRP_ND_USEROPT
+ RTNLGRP_PHONET_IFADDR,
+#define RTNLGRP_PHONET_IFADDR RTNLGRP_PHONET_IFADDR
+ RTNLGRP_PHONET_ROUTE,
+#define RTNLGRP_PHONET_ROUTE RTNLGRP_PHONET_ROUTE
+ RTNLGRP_DCB,
+#define RTNLGRP_DCB RTNLGRP_DCB
+ RTNLGRP_IPV4_NETCONF,
+#define RTNLGRP_IPV4_NETCONF RTNLGRP_IPV4_NETCONF
+ RTNLGRP_IPV6_NETCONF,
+#define RTNLGRP_IPV6_NETCONF RTNLGRP_IPV6_NETCONF
+ RTNLGRP_MDB,
+#define RTNLGRP_MDB RTNLGRP_MDB
+ RTNLGRP_MPLS_ROUTE,
+#define RTNLGRP_MPLS_ROUTE RTNLGRP_MPLS_ROUTE
+ RTNLGRP_NSID,
+#define RTNLGRP_NSID RTNLGRP_NSID
+ __RTNLGRP_MAX
+};
+#define RTNLGRP_MAX (__RTNLGRP_MAX - 1)
+
+/* TC action piece */
+struct tcamsg {
+ unsigned char tca_family;
+ unsigned char tca__pad1;
+ unsigned short tca__pad2;
+};
+#define TA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct tcamsg))))
+#define TA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcamsg))
+#define TCA_ACT_TAB 1 /* attr type must be >=1 */
+#define TCAA_MAX 1
+
+/* New extended info filters for IFLA_EXT_MASK */
+#define RTEXT_FILTER_VF (1 << 0)
+#define RTEXT_FILTER_BRVLAN (1 << 1)
+#define RTEXT_FILTER_BRVLAN_COMPRESSED (1 << 2)
+#define RTEXT_FILTER_SKIP_STATS (1 << 3)
+
+/* End of information exported to user level */
+
+
+
+#endif /* __LINUX_RTNETLINK_H */
diff --git a/iproute2/include/linux/sock_diag.h b/iproute2/include/linux/sock_diag.h
new file mode 100644
index 0000000..dafcb89
--- /dev/null
+++ b/iproute2/include/linux/sock_diag.h
@@ -0,0 +1,37 @@
+#ifndef __SOCK_DIAG_H__
+#define __SOCK_DIAG_H__
+
+#include <linux/types.h>
+
+#define SOCK_DIAG_BY_FAMILY 20
+#define SOCK_DESTROY 21
+
+struct sock_diag_req {
+ __u8 sdiag_family;
+ __u8 sdiag_protocol;
+};
+
+enum {
+ SK_MEMINFO_RMEM_ALLOC,
+ SK_MEMINFO_RCVBUF,
+ SK_MEMINFO_WMEM_ALLOC,
+ SK_MEMINFO_SNDBUF,
+ SK_MEMINFO_FWD_ALLOC,
+ SK_MEMINFO_WMEM_QUEUED,
+ SK_MEMINFO_OPTMEM,
+ SK_MEMINFO_BACKLOG,
+
+ SK_MEMINFO_VARS,
+};
+
+enum sknetlink_groups {
+ SKNLGRP_NONE,
+ SKNLGRP_INET_TCP_DESTROY,
+ SKNLGRP_INET_UDP_DESTROY,
+ SKNLGRP_INET6_TCP_DESTROY,
+ SKNLGRP_INET6_UDP_DESTROY,
+ __SKNLGRP_MAX,
+};
+#define SKNLGRP_MAX (__SKNLGRP_MAX - 1)
+
+#endif /* __SOCK_DIAG_H__ */
diff --git a/iproute2/include/linux/tc_act/tc_bpf.h b/iproute2/include/linux/tc_act/tc_bpf.h
new file mode 100644
index 0000000..07f17cc
--- /dev/null
+++ b/iproute2/include/linux/tc_act/tc_bpf.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __LINUX_TC_BPF_H
+#define __LINUX_TC_BPF_H
+
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_BPF 13
+
+struct tc_act_bpf {
+ tc_gen;
+};
+
+enum {
+ TCA_ACT_BPF_UNSPEC,
+ TCA_ACT_BPF_TM,
+ TCA_ACT_BPF_PARMS,
+ TCA_ACT_BPF_OPS_LEN,
+ TCA_ACT_BPF_OPS,
+ TCA_ACT_BPF_FD,
+ TCA_ACT_BPF_NAME,
+ __TCA_ACT_BPF_MAX,
+};
+#define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1)
+
+#endif
diff --git a/iproute2/include/linux/tc_act/tc_connmark.h b/iproute2/include/linux/tc_act/tc_connmark.h
new file mode 100644
index 0000000..994b097
--- /dev/null
+++ b/iproute2/include/linux/tc_act/tc_connmark.h
@@ -0,0 +1,22 @@
+#ifndef __UAPI_TC_CONNMARK_H
+#define __UAPI_TC_CONNMARK_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_CONNMARK 14
+
+struct tc_connmark {
+ tc_gen;
+ __u16 zone;
+};
+
+enum {
+ TCA_CONNMARK_UNSPEC,
+ TCA_CONNMARK_PARMS,
+ TCA_CONNMARK_TM,
+ __TCA_CONNMARK_MAX
+};
+#define TCA_CONNMARK_MAX (__TCA_CONNMARK_MAX - 1)
+
+#endif
diff --git a/iproute2/include/linux/tc_act/tc_csum.h b/iproute2/include/linux/tc_act/tc_csum.h
new file mode 100644
index 0000000..a047c49
--- /dev/null
+++ b/iproute2/include/linux/tc_act/tc_csum.h
@@ -0,0 +1,32 @@
+#ifndef __LINUX_TC_CSUM_H
+#define __LINUX_TC_CSUM_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_CSUM 16
+
+enum {
+ TCA_CSUM_UNSPEC,
+ TCA_CSUM_PARMS,
+ TCA_CSUM_TM,
+ __TCA_CSUM_MAX
+};
+#define TCA_CSUM_MAX (__TCA_CSUM_MAX - 1)
+
+enum {
+ TCA_CSUM_UPDATE_FLAG_IPV4HDR = 1,
+ TCA_CSUM_UPDATE_FLAG_ICMP = 2,
+ TCA_CSUM_UPDATE_FLAG_IGMP = 4,
+ TCA_CSUM_UPDATE_FLAG_TCP = 8,
+ TCA_CSUM_UPDATE_FLAG_UDP = 16,
+ TCA_CSUM_UPDATE_FLAG_UDPLITE = 32
+};
+
+struct tc_csum {
+ tc_gen;
+
+ __u32 update_flags;
+};
+
+#endif /* __LINUX_TC_CSUM_H */
diff --git a/iproute2/include/linux/tc_act/tc_defact.h b/iproute2/include/linux/tc_act/tc_defact.h
new file mode 100644
index 0000000..17dddb4
--- /dev/null
+++ b/iproute2/include/linux/tc_act/tc_defact.h
@@ -0,0 +1,19 @@
+#ifndef __LINUX_TC_DEF_H
+#define __LINUX_TC_DEF_H
+
+#include <linux/pkt_cls.h>
+
+struct tc_defact {
+ tc_gen;
+};
+
+enum {
+ TCA_DEF_UNSPEC,
+ TCA_DEF_TM,
+ TCA_DEF_PARMS,
+ TCA_DEF_DATA,
+ __TCA_DEF_MAX
+};
+#define TCA_DEF_MAX (__TCA_DEF_MAX - 1)
+
+#endif
diff --git a/iproute2/include/linux/tc_act/tc_gact.h b/iproute2/include/linux/tc_act/tc_gact.h
new file mode 100644
index 0000000..f7bf94e
--- /dev/null
+++ b/iproute2/include/linux/tc_act/tc_gact.h
@@ -0,0 +1,32 @@
+#ifndef __LINUX_TC_GACT_H
+#define __LINUX_TC_GACT_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_GACT 5
+struct tc_gact {
+ tc_gen;
+
+};
+
+struct tc_gact_p {
+#define PGACT_NONE 0
+#define PGACT_NETRAND 1
+#define PGACT_DETERM 2
+#define MAX_RAND (PGACT_DETERM + 1 )
+ __u16 ptype;
+ __u16 pval;
+ int paction;
+};
+
+enum {
+ TCA_GACT_UNSPEC,
+ TCA_GACT_TM,
+ TCA_GACT_PARMS,
+ TCA_GACT_PROB,
+ __TCA_GACT_MAX
+};
+#define TCA_GACT_MAX (__TCA_GACT_MAX - 1)
+
+#endif
diff --git a/iproute2/include/linux/tc_act/tc_ipt.h b/iproute2/include/linux/tc_act/tc_ipt.h
new file mode 100644
index 0000000..130aaad
--- /dev/null
+++ b/iproute2/include/linux/tc_act/tc_ipt.h
@@ -0,0 +1,21 @@
+#ifndef __LINUX_TC_IPT_H
+#define __LINUX_TC_IPT_H
+
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_IPT 6
+#define TCA_ACT_XT 10
+
+enum {
+ TCA_IPT_UNSPEC,
+ TCA_IPT_TABLE,
+ TCA_IPT_HOOK,
+ TCA_IPT_INDEX,
+ TCA_IPT_CNT,
+ TCA_IPT_TM,
+ TCA_IPT_TARG,
+ __TCA_IPT_MAX
+};
+#define TCA_IPT_MAX (__TCA_IPT_MAX - 1)
+
+#endif
diff --git a/iproute2/include/linux/tc_act/tc_mirred.h b/iproute2/include/linux/tc_act/tc_mirred.h
new file mode 100644
index 0000000..7561750
--- /dev/null
+++ b/iproute2/include/linux/tc_act/tc_mirred.h
@@ -0,0 +1,27 @@
+#ifndef __LINUX_TC_MIR_H
+#define __LINUX_TC_MIR_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_MIRRED 8
+#define TCA_EGRESS_REDIR 1 /* packet redirect to EGRESS*/
+#define TCA_EGRESS_MIRROR 2 /* mirror packet to EGRESS */
+#define TCA_INGRESS_REDIR 3 /* packet redirect to INGRESS*/
+#define TCA_INGRESS_MIRROR 4 /* mirror packet to INGRESS */
+
+struct tc_mirred {
+ tc_gen;
+ int eaction; /* one of IN/EGRESS_MIRROR/REDIR */
+ __u32 ifindex; /* ifindex of egress port */
+};
+
+enum {
+ TCA_MIRRED_UNSPEC,
+ TCA_MIRRED_TM,
+ TCA_MIRRED_PARMS,
+ __TCA_MIRRED_MAX
+};
+#define TCA_MIRRED_MAX (__TCA_MIRRED_MAX - 1)
+
+#endif
diff --git a/iproute2/include/linux/tc_act/tc_nat.h b/iproute2/include/linux/tc_act/tc_nat.h
new file mode 100644
index 0000000..6663aeb
--- /dev/null
+++ b/iproute2/include/linux/tc_act/tc_nat.h
@@ -0,0 +1,27 @@
+#ifndef __LINUX_TC_NAT_H
+#define __LINUX_TC_NAT_H
+
+#include <linux/pkt_cls.h>
+#include <linux/types.h>
+
+#define TCA_ACT_NAT 9
+
+enum {
+ TCA_NAT_UNSPEC,
+ TCA_NAT_PARMS,
+ TCA_NAT_TM,
+ __TCA_NAT_MAX
+};
+#define TCA_NAT_MAX (__TCA_NAT_MAX - 1)
+
+#define TCA_NAT_FLAG_EGRESS 1
+
+struct tc_nat {
+ tc_gen;
+ __be32 old_addr;
+ __be32 new_addr;
+ __be32 mask;
+ __u32 flags;
+};
+
+#endif
diff --git a/iproute2/include/linux/tc_act/tc_pedit.h b/iproute2/include/linux/tc_act/tc_pedit.h
new file mode 100644
index 0000000..716cfab
--- /dev/null
+++ b/iproute2/include/linux/tc_act/tc_pedit.h
@@ -0,0 +1,34 @@
+#ifndef __LINUX_TC_PED_H
+#define __LINUX_TC_PED_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_PEDIT 7
+
+enum {
+ TCA_PEDIT_UNSPEC,
+ TCA_PEDIT_TM,
+ TCA_PEDIT_PARMS,
+ __TCA_PEDIT_MAX
+};
+#define TCA_PEDIT_MAX (__TCA_PEDIT_MAX - 1)
+
+struct tc_pedit_key {
+ __u32 mask; /* AND */
+ __u32 val; /*XOR */
+ __u32 off; /*offset */
+ __u32 at;
+ __u32 offmask;
+ __u32 shift;
+};
+
+struct tc_pedit_sel {
+ tc_gen;
+ unsigned char nkeys;
+ unsigned char flags;
+ struct tc_pedit_key keys[0];
+};
+#define tc_pedit tc_pedit_sel
+
+#endif
diff --git a/iproute2/include/linux/tc_act/tc_skbedit.h b/iproute2/include/linux/tc_act/tc_skbedit.h
new file mode 100644
index 0000000..7a2e910
--- /dev/null
+++ b/iproute2/include/linux/tc_act/tc_skbedit.h
@@ -0,0 +1,46 @@
+/*
+ * Copyright (c) 2008, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * Author: Alexander Duyck <alexander.h.duyck@intel.com>
+ */
+
+#ifndef __LINUX_TC_SKBEDIT_H
+#define __LINUX_TC_SKBEDIT_H
+
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_SKBEDIT 11
+
+#define SKBEDIT_F_PRIORITY 0x1
+#define SKBEDIT_F_QUEUE_MAPPING 0x2
+#define SKBEDIT_F_MARK 0x4
+
+struct tc_skbedit {
+ tc_gen;
+};
+
+enum {
+ TCA_SKBEDIT_UNSPEC,
+ TCA_SKBEDIT_TM,
+ TCA_SKBEDIT_PARMS,
+ TCA_SKBEDIT_PRIORITY,
+ TCA_SKBEDIT_QUEUE_MAPPING,
+ TCA_SKBEDIT_MARK,
+ __TCA_SKBEDIT_MAX
+};
+#define TCA_SKBEDIT_MAX (__TCA_SKBEDIT_MAX - 1)
+
+#endif
diff --git a/iproute2/include/linux/tc_act/tc_vlan.h b/iproute2/include/linux/tc_act/tc_vlan.h
new file mode 100644
index 0000000..f7b8d44
--- /dev/null
+++ b/iproute2/include/linux/tc_act/tc_vlan.h
@@ -0,0 +1,35 @@
+/*
+ * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __LINUX_TC_VLAN_H
+#define __LINUX_TC_VLAN_H
+
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_VLAN 12
+
+#define TCA_VLAN_ACT_POP 1
+#define TCA_VLAN_ACT_PUSH 2
+
+struct tc_vlan {
+ tc_gen;
+ int v_action;
+};
+
+enum {
+ TCA_VLAN_UNSPEC,
+ TCA_VLAN_TM,
+ TCA_VLAN_PARMS,
+ TCA_VLAN_PUSH_VLAN_ID,
+ TCA_VLAN_PUSH_VLAN_PROTOCOL,
+ __TCA_VLAN_MAX,
+};
+#define TCA_VLAN_MAX (__TCA_VLAN_MAX - 1)
+
+#endif
diff --git a/iproute2/include/linux/tc_ematch/tc_em_cmp.h b/iproute2/include/linux/tc_ematch/tc_em_cmp.h
new file mode 100644
index 0000000..f34bb1b
--- /dev/null
+++ b/iproute2/include/linux/tc_ematch/tc_em_cmp.h
@@ -0,0 +1,25 @@
+#ifndef __LINUX_TC_EM_CMP_H
+#define __LINUX_TC_EM_CMP_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+struct tcf_em_cmp {
+ __u32 val;
+ __u32 mask;
+ __u16 off;
+ __u8 align:4;
+ __u8 flags:4;
+ __u8 layer:4;
+ __u8 opnd:4;
+};
+
+enum {
+ TCF_EM_ALIGN_U8 = 1,
+ TCF_EM_ALIGN_U16 = 2,
+ TCF_EM_ALIGN_U32 = 4
+};
+
+#define TCF_EM_CMP_TRANS 1
+
+#endif
diff --git a/iproute2/include/linux/tc_ematch/tc_em_meta.h b/iproute2/include/linux/tc_ematch/tc_em_meta.h
new file mode 100644
index 0000000..b11f8ce
--- /dev/null
+++ b/iproute2/include/linux/tc_ematch/tc_em_meta.h
@@ -0,0 +1,92 @@
+#ifndef __LINUX_TC_EM_META_H
+#define __LINUX_TC_EM_META_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+enum {
+ TCA_EM_META_UNSPEC,
+ TCA_EM_META_HDR,
+ TCA_EM_META_LVALUE,
+ TCA_EM_META_RVALUE,
+ __TCA_EM_META_MAX
+};
+#define TCA_EM_META_MAX (__TCA_EM_META_MAX - 1)
+
+struct tcf_meta_val {
+ __u16 kind;
+ __u8 shift;
+ __u8 op;
+};
+
+#define TCF_META_TYPE_MASK (0xf << 12)
+#define TCF_META_TYPE(kind) (((kind) & TCF_META_TYPE_MASK) >> 12)
+#define TCF_META_ID_MASK 0x7ff
+#define TCF_META_ID(kind) ((kind) & TCF_META_ID_MASK)
+
+enum {
+ TCF_META_TYPE_VAR,
+ TCF_META_TYPE_INT,
+ __TCF_META_TYPE_MAX
+};
+#define TCF_META_TYPE_MAX (__TCF_META_TYPE_MAX - 1)
+
+enum {
+ TCF_META_ID_VALUE,
+ TCF_META_ID_RANDOM,
+ TCF_META_ID_LOADAVG_0,
+ TCF_META_ID_LOADAVG_1,
+ TCF_META_ID_LOADAVG_2,
+ TCF_META_ID_DEV,
+ TCF_META_ID_PRIORITY,
+ TCF_META_ID_PROTOCOL,
+ TCF_META_ID_PKTTYPE,
+ TCF_META_ID_PKTLEN,
+ TCF_META_ID_DATALEN,
+ TCF_META_ID_MACLEN,
+ TCF_META_ID_NFMARK,
+ TCF_META_ID_TCINDEX,
+ TCF_META_ID_RTCLASSID,
+ TCF_META_ID_RTIIF,
+ TCF_META_ID_SK_FAMILY,
+ TCF_META_ID_SK_STATE,
+ TCF_META_ID_SK_REUSE,
+ TCF_META_ID_SK_BOUND_IF,
+ TCF_META_ID_SK_REFCNT,
+ TCF_META_ID_SK_SHUTDOWN,
+ TCF_META_ID_SK_PROTO,
+ TCF_META_ID_SK_TYPE,
+ TCF_META_ID_SK_RCVBUF,
+ TCF_META_ID_SK_RMEM_ALLOC,
+ TCF_META_ID_SK_WMEM_ALLOC,
+ TCF_META_ID_SK_OMEM_ALLOC,
+ TCF_META_ID_SK_WMEM_QUEUED,
+ TCF_META_ID_SK_RCV_QLEN,
+ TCF_META_ID_SK_SND_QLEN,
+ TCF_META_ID_SK_ERR_QLEN,
+ TCF_META_ID_SK_FORWARD_ALLOCS,
+ TCF_META_ID_SK_SNDBUF,
+ TCF_META_ID_SK_ALLOCS,
+ __TCF_META_ID_SK_ROUTE_CAPS, /* unimplemented but in ABI already */
+ TCF_META_ID_SK_HASH,
+ TCF_META_ID_SK_LINGERTIME,
+ TCF_META_ID_SK_ACK_BACKLOG,
+ TCF_META_ID_SK_MAX_ACK_BACKLOG,
+ TCF_META_ID_SK_PRIO,
+ TCF_META_ID_SK_RCVLOWAT,
+ TCF_META_ID_SK_RCVTIMEO,
+ TCF_META_ID_SK_SNDTIMEO,
+ TCF_META_ID_SK_SENDMSG_OFF,
+ TCF_META_ID_SK_WRITE_PENDING,
+ TCF_META_ID_VLAN_TAG,
+ TCF_META_ID_RXHASH,
+ __TCF_META_ID_MAX
+};
+#define TCF_META_ID_MAX (__TCF_META_ID_MAX - 1)
+
+struct tcf_meta_hdr {
+ struct tcf_meta_val left;
+ struct tcf_meta_val right;
+};
+
+#endif
diff --git a/iproute2/include/linux/tc_ematch/tc_em_nbyte.h b/iproute2/include/linux/tc_ematch/tc_em_nbyte.h
new file mode 100644
index 0000000..7172cfb
--- /dev/null
+++ b/iproute2/include/linux/tc_ematch/tc_em_nbyte.h
@@ -0,0 +1,13 @@
+#ifndef __LINUX_TC_EM_NBYTE_H
+#define __LINUX_TC_EM_NBYTE_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+struct tcf_em_nbyte {
+ __u16 off;
+ __u16 len:12;
+ __u8 layer:4;
+};
+
+#endif
diff --git a/iproute2/include/linux/tc_ematch/tc_em_text.h b/iproute2/include/linux/tc_ematch/tc_em_text.h
new file mode 100644
index 0000000..5aac404
--- /dev/null
+++ b/iproute2/include/linux/tc_ematch/tc_em_text.h
@@ -0,0 +1,19 @@
+#ifndef __LINUX_TC_EM_TEXT_H
+#define __LINUX_TC_EM_TEXT_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+#define TC_EM_TEXT_ALGOSIZ 16
+
+struct tcf_em_text {
+ char algo[TC_EM_TEXT_ALGOSIZ];
+ __u16 from_offset;
+ __u16 to_offset;
+ __u16 pattern_len;
+ __u8 from_layer:4;
+ __u8 to_layer:4;
+ __u8 pad;
+};
+
+#endif
diff --git a/iproute2/include/linux/tcp.h b/iproute2/include/linux/tcp.h
new file mode 100644
index 0000000..1e9b4a6
--- /dev/null
+++ b/iproute2/include/linux/tcp.h
@@ -0,0 +1,212 @@
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * Definitions for the TCP protocol.
+ *
+ * Version: @(#)tcp.h 1.0.2 04/28/93
+ *
+ * Author: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _LINUX_TCP_H
+#define _LINUX_TCP_H
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+#include <linux/socket.h>
+
+struct tcphdr {
+ __be16 source;
+ __be16 dest;
+ __be32 seq;
+ __be32 ack_seq;
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+ __u16 res1:4,
+ doff:4,
+ fin:1,
+ syn:1,
+ rst:1,
+ psh:1,
+ ack:1,
+ urg:1,
+ ece:1,
+ cwr:1;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+ __u16 doff:4,
+ res1:4,
+ cwr:1,
+ ece:1,
+ urg:1,
+ ack:1,
+ psh:1,
+ rst:1,
+ syn:1,
+ fin:1;
+#else
+#error "Adjust your <asm/byteorder.h> defines"
+#endif
+ __be16 window;
+ __sum16 check;
+ __be16 urg_ptr;
+};
+
+/*
+ * The union cast uses a gcc extension to avoid aliasing problems
+ * (union is compatible to any of its members)
+ * This means this part of the code is -fstrict-aliasing safe now.
+ */
+union tcp_word_hdr {
+ struct tcphdr hdr;
+ __be32 words[5];
+};
+
+#define tcp_flag_word(tp) ( ((union tcp_word_hdr *)(tp))->words [3])
+
+enum {
+ TCP_FLAG_CWR = __constant_cpu_to_be32(0x00800000),
+ TCP_FLAG_ECE = __constant_cpu_to_be32(0x00400000),
+ TCP_FLAG_URG = __constant_cpu_to_be32(0x00200000),
+ TCP_FLAG_ACK = __constant_cpu_to_be32(0x00100000),
+ TCP_FLAG_PSH = __constant_cpu_to_be32(0x00080000),
+ TCP_FLAG_RST = __constant_cpu_to_be32(0x00040000),
+ TCP_FLAG_SYN = __constant_cpu_to_be32(0x00020000),
+ TCP_FLAG_FIN = __constant_cpu_to_be32(0x00010000),
+ TCP_RESERVED_BITS = __constant_cpu_to_be32(0x0F000000),
+ TCP_DATA_OFFSET = __constant_cpu_to_be32(0xF0000000)
+};
+
+/*
+ * TCP general constants
+ */
+#define TCP_MSS_DEFAULT 536U /* IPv4 (RFC1122, RFC2581) */
+#define TCP_MSS_DESIRED 1220U /* IPv6 (tunneled), EDNS0 (RFC3226) */
+
+/* TCP socket options */
+#define TCP_NODELAY 1 /* Turn off Nagle's algorithm. */
+#define TCP_MAXSEG 2 /* Limit MSS */
+#define TCP_CORK 3 /* Never send partially complete segments */
+#define TCP_KEEPIDLE 4 /* Start keeplives after this period */
+#define TCP_KEEPINTVL 5 /* Interval between keepalives */
+#define TCP_KEEPCNT 6 /* Number of keepalives before death */
+#define TCP_SYNCNT 7 /* Number of SYN retransmits */
+#define TCP_LINGER2 8 /* Life time of orphaned FIN-WAIT-2 state */
+#define TCP_DEFER_ACCEPT 9 /* Wake up listener only when data arrive */
+#define TCP_WINDOW_CLAMP 10 /* Bound advertised window */
+#define TCP_INFO 11 /* Information about this connection. */
+#define TCP_QUICKACK 12 /* Block/reenable quick acks */
+#define TCP_CONGESTION 13 /* Congestion control algorithm */
+#define TCP_MD5SIG 14 /* TCP MD5 Signature (RFC2385) */
+#define TCP_THIN_LINEAR_TIMEOUTS 16 /* Use linear timeouts for thin streams*/
+#define TCP_THIN_DUPACK 17 /* Fast retrans. after 1 dupack */
+#define TCP_USER_TIMEOUT 18 /* How long for loss retry before timeout */
+#define TCP_REPAIR 19 /* TCP sock is under repair right now */
+#define TCP_REPAIR_QUEUE 20
+#define TCP_QUEUE_SEQ 21
+#define TCP_REPAIR_OPTIONS 22
+#define TCP_FASTOPEN 23 /* Enable FastOpen on listeners */
+#define TCP_TIMESTAMP 24
+#define TCP_NOTSENT_LOWAT 25 /* limit number of unsent bytes in write queue */
+#define TCP_CC_INFO 26 /* Get Congestion Control (optional) info */
+#define TCP_SAVE_SYN 27 /* Record SYN headers for new connections */
+#define TCP_SAVED_SYN 28 /* Get SYN headers recorded for connection */
+
+struct tcp_repair_opt {
+ __u32 opt_code;
+ __u32 opt_val;
+};
+
+enum {
+ TCP_NO_QUEUE,
+ TCP_RECV_QUEUE,
+ TCP_SEND_QUEUE,
+ TCP_QUEUES_NR,
+};
+
+/* for TCP_INFO socket option */
+#define TCPI_OPT_TIMESTAMPS 1
+#define TCPI_OPT_SACK 2
+#define TCPI_OPT_WSCALE 4
+#define TCPI_OPT_ECN 8 /* ECN was negociated at TCP session init */
+#define TCPI_OPT_ECN_SEEN 16 /* we received at least one packet with ECT */
+#define TCPI_OPT_SYN_DATA 32 /* SYN-ACK acked data in SYN sent or rcvd */
+
+enum tcp_ca_state {
+ TCP_CA_Open = 0,
+#define TCPF_CA_Open (1<<TCP_CA_Open)
+ TCP_CA_Disorder = 1,
+#define TCPF_CA_Disorder (1<<TCP_CA_Disorder)
+ TCP_CA_CWR = 2,
+#define TCPF_CA_CWR (1<<TCP_CA_CWR)
+ TCP_CA_Recovery = 3,
+#define TCPF_CA_Recovery (1<<TCP_CA_Recovery)
+ TCP_CA_Loss = 4
+#define TCPF_CA_Loss (1<<TCP_CA_Loss)
+};
+
+struct tcp_info {
+ __u8 tcpi_state;
+ __u8 tcpi_ca_state;
+ __u8 tcpi_retransmits;
+ __u8 tcpi_probes;
+ __u8 tcpi_backoff;
+ __u8 tcpi_options;
+ __u8 tcpi_snd_wscale : 4, tcpi_rcv_wscale : 4;
+
+ __u32 tcpi_rto;
+ __u32 tcpi_ato;
+ __u32 tcpi_snd_mss;
+ __u32 tcpi_rcv_mss;
+
+ __u32 tcpi_unacked;
+ __u32 tcpi_sacked;
+ __u32 tcpi_lost;
+ __u32 tcpi_retrans;
+ __u32 tcpi_fackets;
+
+ /* Times. */
+ __u32 tcpi_last_data_sent;
+ __u32 tcpi_last_ack_sent; /* Not remembered, sorry. */
+ __u32 tcpi_last_data_recv;
+ __u32 tcpi_last_ack_recv;
+
+ /* Metrics. */
+ __u32 tcpi_pmtu;
+ __u32 tcpi_rcv_ssthresh;
+ __u32 tcpi_rtt;
+ __u32 tcpi_rttvar;
+ __u32 tcpi_snd_ssthresh;
+ __u32 tcpi_snd_cwnd;
+ __u32 tcpi_advmss;
+ __u32 tcpi_reordering;
+
+ __u32 tcpi_rcv_rtt;
+ __u32 tcpi_rcv_space;
+
+ __u32 tcpi_total_retrans;
+
+ __u64 tcpi_pacing_rate;
+ __u64 tcpi_max_pacing_rate;
+ __u64 tcpi_bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked */
+ __u64 tcpi_bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived */
+ __u32 tcpi_segs_out; /* RFC4898 tcpEStatsPerfSegsOut */
+ __u32 tcpi_segs_in; /* RFC4898 tcpEStatsPerfSegsIn */
+};
+
+/* for TCP_MD5SIG socket option */
+#define TCP_MD5SIG_MAXKEYLEN 80
+
+struct tcp_md5sig {
+ struct __kernel_sockaddr_storage tcpm_addr; /* address associated */
+ __u16 __tcpm_pad1; /* zero */
+ __u16 tcpm_keylen; /* key length */
+ __u32 __tcpm_pad2; /* zero */
+ __u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN]; /* key (binary) */
+};
+
+#endif /* _LINUX_TCP_H */
diff --git a/iproute2/include/linux/tcp_metrics.h b/iproute2/include/linux/tcp_metrics.h
new file mode 100644
index 0000000..9353392
--- /dev/null
+++ b/iproute2/include/linux/tcp_metrics.h
@@ -0,0 +1,59 @@
+/* tcp_metrics.h - TCP Metrics Interface */
+
+#ifndef _LINUX_TCP_METRICS_H
+#define _LINUX_TCP_METRICS_H
+
+#include <linux/types.h>
+
+/* NETLINK_GENERIC related info
+ */
+#define TCP_METRICS_GENL_NAME "tcp_metrics"
+#define TCP_METRICS_GENL_VERSION 0x1
+
+enum tcp_metric_index {
+ TCP_METRIC_RTT, /* in ms units */
+ TCP_METRIC_RTTVAR, /* in ms units */
+ TCP_METRIC_SSTHRESH,
+ TCP_METRIC_CWND,
+ TCP_METRIC_REORDERING,
+
+ TCP_METRIC_RTT_US, /* in usec units */
+ TCP_METRIC_RTTVAR_US, /* in usec units */
+
+ /* Always last. */
+ __TCP_METRIC_MAX,
+};
+
+#define TCP_METRIC_MAX (__TCP_METRIC_MAX - 1)
+
+enum {
+ TCP_METRICS_ATTR_UNSPEC,
+ TCP_METRICS_ATTR_ADDR_IPV4, /* u32 */
+ TCP_METRICS_ATTR_ADDR_IPV6, /* binary */
+ TCP_METRICS_ATTR_AGE, /* msecs */
+ TCP_METRICS_ATTR_TW_TSVAL, /* u32, raw, rcv tsval */
+ TCP_METRICS_ATTR_TW_TS_STAMP, /* s32, sec age */
+ TCP_METRICS_ATTR_VALS, /* nested +1, u32 */
+ TCP_METRICS_ATTR_FOPEN_MSS, /* u16 */
+ TCP_METRICS_ATTR_FOPEN_SYN_DROPS, /* u16, count of drops */
+ TCP_METRICS_ATTR_FOPEN_SYN_DROP_TS, /* msecs age */
+ TCP_METRICS_ATTR_FOPEN_COOKIE, /* binary */
+ TCP_METRICS_ATTR_SADDR_IPV4, /* u32 */
+ TCP_METRICS_ATTR_SADDR_IPV6, /* binary */
+
+ __TCP_METRICS_ATTR_MAX,
+};
+
+#define TCP_METRICS_ATTR_MAX (__TCP_METRICS_ATTR_MAX - 1)
+
+enum {
+ TCP_METRICS_CMD_UNSPEC,
+ TCP_METRICS_CMD_GET,
+ TCP_METRICS_CMD_DEL,
+
+ __TCP_METRICS_CMD_MAX,
+};
+
+#define TCP_METRICS_CMD_MAX (__TCP_METRICS_CMD_MAX - 1)
+
+#endif /* _LINUX_TCP_METRICS_H */
diff --git a/iproute2/include/linux/tipc.h b/iproute2/include/linux/tipc.h
new file mode 100644
index 0000000..ebd3b63
--- /dev/null
+++ b/iproute2/include/linux/tipc.h
@@ -0,0 +1,232 @@
+/*
+ * include/uapi/linux/tipc.h: Header for TIPC socket interface
+ *
+ * Copyright (c) 2003-2006, Ericsson AB
+ * Copyright (c) 2005, 2010-2011, Wind River Systems
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _LINUX_TIPC_H_
+#define _LINUX_TIPC_H_
+
+#include <linux/types.h>
+#include <linux/sockios.h>
+
+/*
+ * TIPC addressing primitives
+ */
+
+struct tipc_portid {
+ __u32 ref;
+ __u32 node;
+};
+
+struct tipc_name {
+ __u32 type;
+ __u32 instance;
+};
+
+struct tipc_name_seq {
+ __u32 type;
+ __u32 lower;
+ __u32 upper;
+};
+
+static __inline__ __u32 tipc_addr(unsigned int zone,
+ unsigned int cluster,
+ unsigned int node)
+{
+ return (zone << 24) | (cluster << 12) | node;
+}
+
+static __inline__ unsigned int tipc_zone(__u32 addr)
+{
+ return addr >> 24;
+}
+
+static __inline__ unsigned int tipc_cluster(__u32 addr)
+{
+ return (addr >> 12) & 0xfff;
+}
+
+static __inline__ unsigned int tipc_node(__u32 addr)
+{
+ return addr & 0xfff;
+}
+
+/*
+ * Application-accessible port name types
+ */
+
+#define TIPC_CFG_SRV 0 /* configuration service name type */
+#define TIPC_TOP_SRV 1 /* topology service name type */
+#define TIPC_LINK_STATE 2 /* link state name type */
+#define TIPC_RESERVED_TYPES 64 /* lowest user-publishable name type */
+
+/*
+ * Publication scopes when binding port names and port name sequences
+ */
+
+#define TIPC_ZONE_SCOPE 1
+#define TIPC_CLUSTER_SCOPE 2
+#define TIPC_NODE_SCOPE 3
+
+/*
+ * Limiting values for messages
+ */
+
+#define TIPC_MAX_USER_MSG_SIZE 66000U
+
+/*
+ * Message importance levels
+ */
+
+#define TIPC_LOW_IMPORTANCE 0
+#define TIPC_MEDIUM_IMPORTANCE 1
+#define TIPC_HIGH_IMPORTANCE 2
+#define TIPC_CRITICAL_IMPORTANCE 3
+
+/*
+ * Msg rejection/connection shutdown reasons
+ */
+
+#define TIPC_OK 0
+#define TIPC_ERR_NO_NAME 1
+#define TIPC_ERR_NO_PORT 2
+#define TIPC_ERR_NO_NODE 3
+#define TIPC_ERR_OVERLOAD 4
+#define TIPC_CONN_SHUTDOWN 5
+
+/*
+ * TIPC topology subscription service definitions
+ */
+
+#define TIPC_SUB_PORTS 0x01 /* filter for port availability */
+#define TIPC_SUB_SERVICE 0x02 /* filter for service availability */
+#define TIPC_SUB_CANCEL 0x04 /* cancel a subscription */
+
+#define TIPC_WAIT_FOREVER (~0) /* timeout for permanent subscription */
+
+struct tipc_subscr {
+ struct tipc_name_seq seq; /* name sequence of interest */
+ __u32 timeout; /* subscription duration (in ms) */
+ __u32 filter; /* bitmask of filter options */
+ char usr_handle[8]; /* available for subscriber use */
+};
+
+#define TIPC_PUBLISHED 1 /* publication event */
+#define TIPC_WITHDRAWN 2 /* withdraw event */
+#define TIPC_SUBSCR_TIMEOUT 3 /* subscription timeout event */
+
+struct tipc_event {
+ __u32 event; /* event type */
+ __u32 found_lower; /* matching name seq instances */
+ __u32 found_upper; /* " " " " */
+ struct tipc_portid port; /* associated port */
+ struct tipc_subscr s; /* associated subscription */
+};
+
+/*
+ * Socket API
+ */
+
+#ifndef AF_TIPC
+#define AF_TIPC 30
+#endif
+
+#ifndef PF_TIPC
+#define PF_TIPC AF_TIPC
+#endif
+
+#ifndef SOL_TIPC
+#define SOL_TIPC 271
+#endif
+
+#define TIPC_ADDR_NAMESEQ 1
+#define TIPC_ADDR_MCAST 1
+#define TIPC_ADDR_NAME 2
+#define TIPC_ADDR_ID 3
+
+struct sockaddr_tipc {
+ unsigned short family;
+ unsigned char addrtype;
+ signed char scope;
+ union {
+ struct tipc_portid id;
+ struct tipc_name_seq nameseq;
+ struct {
+ struct tipc_name name;
+ __u32 domain;
+ } name;
+ } addr;
+};
+
+/*
+ * Ancillary data objects supported by recvmsg()
+ */
+
+#define TIPC_ERRINFO 1 /* error info */
+#define TIPC_RETDATA 2 /* returned data */
+#define TIPC_DESTNAME 3 /* destination name */
+
+/*
+ * TIPC-specific socket option values
+ */
+
+#define TIPC_IMPORTANCE 127 /* Default: TIPC_LOW_IMPORTANCE */
+#define TIPC_SRC_DROPPABLE 128 /* Default: based on socket type */
+#define TIPC_DEST_DROPPABLE 129 /* Default: based on socket type */
+#define TIPC_CONN_TIMEOUT 130 /* Default: 8000 (ms) */
+#define TIPC_NODE_RECVQ_DEPTH 131 /* Default: none (read only) */
+#define TIPC_SOCK_RECVQ_DEPTH 132 /* Default: none (read only) */
+
+/*
+ * Maximum sizes of TIPC bearer-related names (including terminating NULL)
+ * The string formatting for each name element is:
+ * media: media
+ * interface: media:interface name
+ * link: Z.C.N:interface-Z.C.N:interface
+ *
+ */
+
+#define TIPC_MAX_MEDIA_NAME 16
+#define TIPC_MAX_IF_NAME 16
+#define TIPC_MAX_BEARER_NAME 32
+#define TIPC_MAX_LINK_NAME 60
+
+#define SIOCGETLINKNAME SIOCPROTOPRIVATE
+
+struct tipc_sioc_ln_req {
+ __u32 peer;
+ __u32 bearer_id;
+ char linkname[TIPC_MAX_LINK_NAME];
+};
+#endif
diff --git a/iproute2/include/linux/tipc_netlink.h b/iproute2/include/linux/tipc_netlink.h
new file mode 100644
index 0000000..25eb645
--- /dev/null
+++ b/iproute2/include/linux/tipc_netlink.h
@@ -0,0 +1,254 @@
+/*
+ * Copyright (c) 2014, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _LINUX_TIPC_NETLINK_H_
+#define _LINUX_TIPC_NETLINK_H_
+
+#define TIPC_GENL_V2_NAME "TIPCv2"
+#define TIPC_GENL_V2_VERSION 0x1
+
+/* Netlink commands */
+enum {
+ TIPC_NL_UNSPEC,
+ TIPC_NL_LEGACY,
+ TIPC_NL_BEARER_DISABLE,
+ TIPC_NL_BEARER_ENABLE,
+ TIPC_NL_BEARER_GET,
+ TIPC_NL_BEARER_SET,
+ TIPC_NL_SOCK_GET,
+ TIPC_NL_PUBL_GET,
+ TIPC_NL_LINK_GET,
+ TIPC_NL_LINK_SET,
+ TIPC_NL_LINK_RESET_STATS,
+ TIPC_NL_MEDIA_GET,
+ TIPC_NL_MEDIA_SET,
+ TIPC_NL_NODE_GET,
+ TIPC_NL_NET_GET,
+ TIPC_NL_NET_SET,
+ TIPC_NL_NAME_TABLE_GET,
+ TIPC_NL_PEER_REMOVE,
+
+ __TIPC_NL_CMD_MAX,
+ TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1
+};
+
+/* Top level netlink attributes */
+enum {
+ TIPC_NLA_UNSPEC,
+ TIPC_NLA_BEARER, /* nest */
+ TIPC_NLA_SOCK, /* nest */
+ TIPC_NLA_PUBL, /* nest */
+ TIPC_NLA_LINK, /* nest */
+ TIPC_NLA_MEDIA, /* nest */
+ TIPC_NLA_NODE, /* nest */
+ TIPC_NLA_NET, /* nest */
+ TIPC_NLA_NAME_TABLE, /* nest */
+
+ __TIPC_NLA_MAX,
+ TIPC_NLA_MAX = __TIPC_NLA_MAX - 1
+};
+
+/* Bearer info */
+enum {
+ TIPC_NLA_BEARER_UNSPEC,
+ TIPC_NLA_BEARER_NAME, /* string */
+ TIPC_NLA_BEARER_PROP, /* nest */
+ TIPC_NLA_BEARER_DOMAIN, /* u32 */
+ TIPC_NLA_BEARER_UDP_OPTS, /* nest */
+
+ __TIPC_NLA_BEARER_MAX,
+ TIPC_NLA_BEARER_MAX = __TIPC_NLA_BEARER_MAX - 1
+};
+
+enum {
+ TIPC_NLA_UDP_UNSPEC,
+ TIPC_NLA_UDP_LOCAL, /* sockaddr_storage */
+ TIPC_NLA_UDP_REMOTE, /* sockaddr_storage */
+
+ __TIPC_NLA_UDP_MAX,
+ TIPC_NLA_UDP_MAX = __TIPC_NLA_UDP_MAX - 1
+};
+/* Socket info */
+enum {
+ TIPC_NLA_SOCK_UNSPEC,
+ TIPC_NLA_SOCK_ADDR, /* u32 */
+ TIPC_NLA_SOCK_REF, /* u32 */
+ TIPC_NLA_SOCK_CON, /* nest */
+ TIPC_NLA_SOCK_HAS_PUBL, /* flag */
+
+ __TIPC_NLA_SOCK_MAX,
+ TIPC_NLA_SOCK_MAX = __TIPC_NLA_SOCK_MAX - 1
+};
+
+/* Link info */
+enum {
+ TIPC_NLA_LINK_UNSPEC,
+ TIPC_NLA_LINK_NAME, /* string */
+ TIPC_NLA_LINK_DEST, /* u32 */
+ TIPC_NLA_LINK_MTU, /* u32 */
+ TIPC_NLA_LINK_BROADCAST, /* flag */
+ TIPC_NLA_LINK_UP, /* flag */
+ TIPC_NLA_LINK_ACTIVE, /* flag */
+ TIPC_NLA_LINK_PROP, /* nest */
+ TIPC_NLA_LINK_STATS, /* nest */
+ TIPC_NLA_LINK_RX, /* u32 */
+ TIPC_NLA_LINK_TX, /* u32 */
+
+ __TIPC_NLA_LINK_MAX,
+ TIPC_NLA_LINK_MAX = __TIPC_NLA_LINK_MAX - 1
+};
+
+/* Media info */
+enum {
+ TIPC_NLA_MEDIA_UNSPEC,
+ TIPC_NLA_MEDIA_NAME, /* string */
+ TIPC_NLA_MEDIA_PROP, /* nest */
+
+ __TIPC_NLA_MEDIA_MAX,
+ TIPC_NLA_MEDIA_MAX = __TIPC_NLA_MEDIA_MAX - 1
+};
+
+/* Node info */
+enum {
+ TIPC_NLA_NODE_UNSPEC,
+ TIPC_NLA_NODE_ADDR, /* u32 */
+ TIPC_NLA_NODE_UP, /* flag */
+
+ __TIPC_NLA_NODE_MAX,
+ TIPC_NLA_NODE_MAX = __TIPC_NLA_NODE_MAX - 1
+};
+
+/* Net info */
+enum {
+ TIPC_NLA_NET_UNSPEC,
+ TIPC_NLA_NET_ID, /* u32 */
+ TIPC_NLA_NET_ADDR, /* u32 */
+
+ __TIPC_NLA_NET_MAX,
+ TIPC_NLA_NET_MAX = __TIPC_NLA_NET_MAX - 1
+};
+
+/* Name table info */
+enum {
+ TIPC_NLA_NAME_TABLE_UNSPEC,
+ TIPC_NLA_NAME_TABLE_PUBL, /* nest */
+
+ __TIPC_NLA_NAME_TABLE_MAX,
+ TIPC_NLA_NAME_TABLE_MAX = __TIPC_NLA_NAME_TABLE_MAX - 1
+};
+
+/* Publication info */
+enum {
+ TIPC_NLA_PUBL_UNSPEC,
+
+ TIPC_NLA_PUBL_TYPE, /* u32 */
+ TIPC_NLA_PUBL_LOWER, /* u32 */
+ TIPC_NLA_PUBL_UPPER, /* u32 */
+ TIPC_NLA_PUBL_SCOPE, /* u32 */
+ TIPC_NLA_PUBL_NODE, /* u32 */
+ TIPC_NLA_PUBL_REF, /* u32 */
+ TIPC_NLA_PUBL_KEY, /* u32 */
+
+ __TIPC_NLA_PUBL_MAX,
+ TIPC_NLA_PUBL_MAX = __TIPC_NLA_PUBL_MAX - 1
+};
+
+/* Nest, connection info */
+enum {
+ TIPC_NLA_CON_UNSPEC,
+
+ TIPC_NLA_CON_FLAG, /* flag */
+ TIPC_NLA_CON_NODE, /* u32 */
+ TIPC_NLA_CON_SOCK, /* u32 */
+ TIPC_NLA_CON_TYPE, /* u32 */
+ TIPC_NLA_CON_INST, /* u32 */
+
+ __TIPC_NLA_CON_MAX,
+ TIPC_NLA_CON_MAX = __TIPC_NLA_CON_MAX - 1
+};
+
+/* Nest, link propreties. Valid for link, media and bearer */
+enum {
+ TIPC_NLA_PROP_UNSPEC,
+
+ TIPC_NLA_PROP_PRIO, /* u32 */
+ TIPC_NLA_PROP_TOL, /* u32 */
+ TIPC_NLA_PROP_WIN, /* u32 */
+
+ __TIPC_NLA_PROP_MAX,
+ TIPC_NLA_PROP_MAX = __TIPC_NLA_PROP_MAX - 1
+};
+
+/* Nest, statistics info */
+enum {
+ TIPC_NLA_STATS_UNSPEC,
+
+ TIPC_NLA_STATS_RX_INFO, /* u32 */
+ TIPC_NLA_STATS_RX_FRAGMENTS, /* u32 */
+ TIPC_NLA_STATS_RX_FRAGMENTED, /* u32 */
+ TIPC_NLA_STATS_RX_BUNDLES, /* u32 */
+ TIPC_NLA_STATS_RX_BUNDLED, /* u32 */
+ TIPC_NLA_STATS_TX_INFO, /* u32 */
+ TIPC_NLA_STATS_TX_FRAGMENTS, /* u32 */
+ TIPC_NLA_STATS_TX_FRAGMENTED, /* u32 */
+ TIPC_NLA_STATS_TX_BUNDLES, /* u32 */
+ TIPC_NLA_STATS_TX_BUNDLED, /* u32 */
+ TIPC_NLA_STATS_MSG_PROF_TOT, /* u32 */
+ TIPC_NLA_STATS_MSG_LEN_CNT, /* u32 */
+ TIPC_NLA_STATS_MSG_LEN_TOT, /* u32 */
+ TIPC_NLA_STATS_MSG_LEN_P0, /* u32 */
+ TIPC_NLA_STATS_MSG_LEN_P1, /* u32 */
+ TIPC_NLA_STATS_MSG_LEN_P2, /* u32 */
+ TIPC_NLA_STATS_MSG_LEN_P3, /* u32 */
+ TIPC_NLA_STATS_MSG_LEN_P4, /* u32 */
+ TIPC_NLA_STATS_MSG_LEN_P5, /* u32 */
+ TIPC_NLA_STATS_MSG_LEN_P6, /* u32 */
+ TIPC_NLA_STATS_RX_STATES, /* u32 */
+ TIPC_NLA_STATS_RX_PROBES, /* u32 */
+ TIPC_NLA_STATS_RX_NACKS, /* u32 */
+ TIPC_NLA_STATS_RX_DEFERRED, /* u32 */
+ TIPC_NLA_STATS_TX_STATES, /* u32 */
+ TIPC_NLA_STATS_TX_PROBES, /* u32 */
+ TIPC_NLA_STATS_TX_NACKS, /* u32 */
+ TIPC_NLA_STATS_TX_ACKS, /* u32 */
+ TIPC_NLA_STATS_RETRANSMITTED, /* u32 */
+ TIPC_NLA_STATS_DUPLICATES, /* u32 */
+ TIPC_NLA_STATS_LINK_CONGS, /* u32 */
+ TIPC_NLA_STATS_MAX_QUEUE, /* u32 */
+ TIPC_NLA_STATS_AVG_QUEUE, /* u32 */
+
+ __TIPC_NLA_STATS_MAX,
+ TIPC_NLA_STATS_MAX = __TIPC_NLA_STATS_MAX - 1
+};
+
+#endif
diff --git a/iproute2/include/linux/unix_diag.h b/iproute2/include/linux/unix_diag.h
new file mode 100644
index 0000000..1eb0b8d
--- /dev/null
+++ b/iproute2/include/linux/unix_diag.h
@@ -0,0 +1,58 @@
+#ifndef __UNIX_DIAG_H__
+#define __UNIX_DIAG_H__
+
+#include <linux/types.h>
+
+struct unix_diag_req {
+ __u8 sdiag_family;
+ __u8 sdiag_protocol;
+ __u16 pad;
+ __u32 udiag_states;
+ __u32 udiag_ino;
+ __u32 udiag_show;
+ __u32 udiag_cookie[2];
+};
+
+#define UDIAG_SHOW_NAME 0x00000001 /* show name (not path) */
+#define UDIAG_SHOW_VFS 0x00000002 /* show VFS inode info */
+#define UDIAG_SHOW_PEER 0x00000004 /* show peer socket info */
+#define UDIAG_SHOW_ICONS 0x00000008 /* show pending connections */
+#define UDIAG_SHOW_RQLEN 0x00000010 /* show skb receive queue len */
+#define UDIAG_SHOW_MEMINFO 0x00000020 /* show memory info of a socket */
+
+struct unix_diag_msg {
+ __u8 udiag_family;
+ __u8 udiag_type;
+ __u8 udiag_state;
+ __u8 pad;
+
+ __u32 udiag_ino;
+ __u32 udiag_cookie[2];
+};
+
+enum {
+ /* UNIX_DIAG_NONE, standard nl API requires this attribute! */
+ UNIX_DIAG_NAME,
+ UNIX_DIAG_VFS,
+ UNIX_DIAG_PEER,
+ UNIX_DIAG_ICONS,
+ UNIX_DIAG_RQLEN,
+ UNIX_DIAG_MEMINFO,
+ UNIX_DIAG_SHUTDOWN,
+
+ __UNIX_DIAG_MAX,
+};
+
+#define UNIX_DIAG_MAX (__UNIX_DIAG_MAX - 1)
+
+struct unix_diag_vfs {
+ __u32 udiag_vfs_ino;
+ __u32 udiag_vfs_dev;
+};
+
+struct unix_diag_rqlen {
+ __u32 udiag_rqueue;
+ __u32 udiag_wqueue;
+};
+
+#endif
diff --git a/iproute2/include/linux/veth.h b/iproute2/include/linux/veth.h
new file mode 100644
index 0000000..3354c1e
--- /dev/null
+++ b/iproute2/include/linux/veth.h
@@ -0,0 +1,12 @@
+#ifndef __NET_VETH_H_
+#define __NET_VETH_H_
+
+enum {
+ VETH_INFO_UNSPEC,
+ VETH_INFO_PEER,
+
+ __VETH_INFO_MAX
+#define VETH_INFO_MAX (__VETH_INFO_MAX - 1)
+};
+
+#endif
diff --git a/iproute2/include/linux/xfrm.h b/iproute2/include/linux/xfrm.h
new file mode 100644
index 0000000..b8f5451
--- /dev/null
+++ b/iproute2/include/linux/xfrm.h
@@ -0,0 +1,526 @@
+#ifndef _LINUX_XFRM_H
+#define _LINUX_XFRM_H
+
+#include <linux/in6.h>
+#include <linux/types.h>
+
+/* All of the structures in this file may not change size as they are
+ * passed into the kernel from userspace via netlink sockets.
+ */
+
+/* Structure to encapsulate addresses. I do not want to use
+ * "standard" structure. My apologies.
+ */
+typedef union {
+ __be32 a4;
+ __be32 a6[4];
+ struct in6_addr in6;
+} xfrm_address_t;
+
+/* Ident of a specific xfrm_state. It is used on input to lookup
+ * the state by (spi,daddr,ah/esp) or to store information about
+ * spi, protocol and tunnel address on output.
+ */
+struct xfrm_id {
+ xfrm_address_t daddr;
+ __be32 spi;
+ __u8 proto;
+};
+
+struct xfrm_sec_ctx {
+ __u8 ctx_doi;
+ __u8 ctx_alg;
+ __u16 ctx_len;
+ __u32 ctx_sid;
+ char ctx_str[0];
+};
+
+/* Security Context Domains of Interpretation */
+#define XFRM_SC_DOI_RESERVED 0
+#define XFRM_SC_DOI_LSM 1
+
+/* Security Context Algorithms */
+#define XFRM_SC_ALG_RESERVED 0
+#define XFRM_SC_ALG_SELINUX 1
+
+/* Selector, used as selector both on policy rules (SPD) and SAs. */
+
+struct xfrm_selector {
+ xfrm_address_t daddr;
+ xfrm_address_t saddr;
+ __be16 dport;
+ __be16 dport_mask;
+ __be16 sport;
+ __be16 sport_mask;
+ __u16 family;
+ __u8 prefixlen_d;
+ __u8 prefixlen_s;
+ __u8 proto;
+ int ifindex;
+ __kernel_uid32_t user;
+};
+
+#define XFRM_INF (~(__u64)0)
+
+struct xfrm_lifetime_cfg {
+ __u64 soft_byte_limit;
+ __u64 hard_byte_limit;
+ __u64 soft_packet_limit;
+ __u64 hard_packet_limit;
+ __u64 soft_add_expires_seconds;
+ __u64 hard_add_expires_seconds;
+ __u64 soft_use_expires_seconds;
+ __u64 hard_use_expires_seconds;
+};
+
+struct xfrm_lifetime_cur {
+ __u64 bytes;
+ __u64 packets;
+ __u64 add_time;
+ __u64 use_time;
+};
+
+struct xfrm_replay_state {
+ __u32 oseq;
+ __u32 seq;
+ __u32 bitmap;
+};
+
+#define XFRMA_REPLAY_ESN_MAX 4096
+
+struct xfrm_replay_state_esn {
+ unsigned int bmp_len;
+ __u32 oseq;
+ __u32 seq;
+ __u32 oseq_hi;
+ __u32 seq_hi;
+ __u32 replay_window;
+ __u32 bmp[0];
+};
+
+struct xfrm_algo {
+ char alg_name[64];
+ unsigned int alg_key_len; /* in bits */
+ char alg_key[0];
+};
+
+struct xfrm_algo_auth {
+ char alg_name[64];
+ unsigned int alg_key_len; /* in bits */
+ unsigned int alg_trunc_len; /* in bits */
+ char alg_key[0];
+};
+
+struct xfrm_algo_aead {
+ char alg_name[64];
+ unsigned int alg_key_len; /* in bits */
+ unsigned int alg_icv_len; /* in bits */
+ char alg_key[0];
+};
+
+struct xfrm_stats {
+ __u32 replay_window;
+ __u32 replay;
+ __u32 integrity_failed;
+};
+
+enum {
+ XFRM_POLICY_TYPE_MAIN = 0,
+ XFRM_POLICY_TYPE_SUB = 1,
+ XFRM_POLICY_TYPE_MAX = 2,
+ XFRM_POLICY_TYPE_ANY = 255
+};
+
+enum {
+ XFRM_POLICY_IN = 0,
+ XFRM_POLICY_OUT = 1,
+ XFRM_POLICY_FWD = 2,
+ XFRM_POLICY_MASK = 3,
+ XFRM_POLICY_MAX = 3
+};
+
+enum {
+ XFRM_SHARE_ANY, /* No limitations */
+ XFRM_SHARE_SESSION, /* For this session only */
+ XFRM_SHARE_USER, /* For this user only */
+ XFRM_SHARE_UNIQUE /* Use once */
+};
+
+#define XFRM_MODE_TRANSPORT 0
+#define XFRM_MODE_TUNNEL 1
+#define XFRM_MODE_ROUTEOPTIMIZATION 2
+#define XFRM_MODE_IN_TRIGGER 3
+#define XFRM_MODE_BEET 4
+#define XFRM_MODE_MAX 5
+
+/* Netlink configuration messages. */
+enum {
+ XFRM_MSG_BASE = 0x10,
+
+ XFRM_MSG_NEWSA = 0x10,
+#define XFRM_MSG_NEWSA XFRM_MSG_NEWSA
+ XFRM_MSG_DELSA,
+#define XFRM_MSG_DELSA XFRM_MSG_DELSA
+ XFRM_MSG_GETSA,
+#define XFRM_MSG_GETSA XFRM_MSG_GETSA
+
+ XFRM_MSG_NEWPOLICY,
+#define XFRM_MSG_NEWPOLICY XFRM_MSG_NEWPOLICY
+ XFRM_MSG_DELPOLICY,
+#define XFRM_MSG_DELPOLICY XFRM_MSG_DELPOLICY
+ XFRM_MSG_GETPOLICY,
+#define XFRM_MSG_GETPOLICY XFRM_MSG_GETPOLICY
+
+ XFRM_MSG_ALLOCSPI,
+#define XFRM_MSG_ALLOCSPI XFRM_MSG_ALLOCSPI
+ XFRM_MSG_ACQUIRE,
+#define XFRM_MSG_ACQUIRE XFRM_MSG_ACQUIRE
+ XFRM_MSG_EXPIRE,
+#define XFRM_MSG_EXPIRE XFRM_MSG_EXPIRE
+
+ XFRM_MSG_UPDPOLICY,
+#define XFRM_MSG_UPDPOLICY XFRM_MSG_UPDPOLICY
+ XFRM_MSG_UPDSA,
+#define XFRM_MSG_UPDSA XFRM_MSG_UPDSA
+
+ XFRM_MSG_POLEXPIRE,
+#define XFRM_MSG_POLEXPIRE XFRM_MSG_POLEXPIRE
+
+ XFRM_MSG_FLUSHSA,
+#define XFRM_MSG_FLUSHSA XFRM_MSG_FLUSHSA
+ XFRM_MSG_FLUSHPOLICY,
+#define XFRM_MSG_FLUSHPOLICY XFRM_MSG_FLUSHPOLICY
+
+ XFRM_MSG_NEWAE,
+#define XFRM_MSG_NEWAE XFRM_MSG_NEWAE
+ XFRM_MSG_GETAE,
+#define XFRM_MSG_GETAE XFRM_MSG_GETAE
+
+ XFRM_MSG_REPORT,
+#define XFRM_MSG_REPORT XFRM_MSG_REPORT
+
+ XFRM_MSG_MIGRATE,
+#define XFRM_MSG_MIGRATE XFRM_MSG_MIGRATE
+
+ XFRM_MSG_NEWSADINFO,
+#define XFRM_MSG_NEWSADINFO XFRM_MSG_NEWSADINFO
+ XFRM_MSG_GETSADINFO,
+#define XFRM_MSG_GETSADINFO XFRM_MSG_GETSADINFO
+
+ XFRM_MSG_NEWSPDINFO,
+#define XFRM_MSG_NEWSPDINFO XFRM_MSG_NEWSPDINFO
+ XFRM_MSG_GETSPDINFO,
+#define XFRM_MSG_GETSPDINFO XFRM_MSG_GETSPDINFO
+
+ XFRM_MSG_MAPPING,
+#define XFRM_MSG_MAPPING XFRM_MSG_MAPPING
+ __XFRM_MSG_MAX
+};
+#define XFRM_MSG_MAX (__XFRM_MSG_MAX - 1)
+
+#define XFRM_NR_MSGTYPES (XFRM_MSG_MAX + 1 - XFRM_MSG_BASE)
+
+/*
+ * Generic LSM security context for comunicating to user space
+ * NOTE: Same format as sadb_x_sec_ctx
+ */
+struct xfrm_user_sec_ctx {
+ __u16 len;
+ __u16 exttype;
+ __u8 ctx_alg; /* LSMs: e.g., selinux == 1 */
+ __u8 ctx_doi;
+ __u16 ctx_len;
+};
+
+struct xfrm_user_tmpl {
+ struct xfrm_id id;
+ __u16 family;
+ xfrm_address_t saddr;
+ __u32 reqid;
+ __u8 mode;
+ __u8 share;
+ __u8 optional;
+ __u32 aalgos;
+ __u32 ealgos;
+ __u32 calgos;
+};
+
+struct xfrm_encap_tmpl {
+ __u16 encap_type;
+ __be16 encap_sport;
+ __be16 encap_dport;
+ xfrm_address_t encap_oa;
+};
+
+/* AEVENT flags */
+enum xfrm_ae_ftype_t {
+ XFRM_AE_UNSPEC,
+ XFRM_AE_RTHR=1, /* replay threshold*/
+ XFRM_AE_RVAL=2, /* replay value */
+ XFRM_AE_LVAL=4, /* lifetime value */
+ XFRM_AE_ETHR=8, /* expiry timer threshold */
+ XFRM_AE_CR=16, /* Event cause is replay update */
+ XFRM_AE_CE=32, /* Event cause is timer expiry */
+ XFRM_AE_CU=64, /* Event cause is policy update */
+ __XFRM_AE_MAX
+
+#define XFRM_AE_MAX (__XFRM_AE_MAX - 1)
+};
+
+struct xfrm_userpolicy_type {
+ __u8 type;
+ __u16 reserved1;
+ __u8 reserved2;
+};
+
+/* Netlink message attributes. */
+enum xfrm_attr_type_t {
+ XFRMA_UNSPEC,
+ XFRMA_ALG_AUTH, /* struct xfrm_algo */
+ XFRMA_ALG_CRYPT, /* struct xfrm_algo */
+ XFRMA_ALG_COMP, /* struct xfrm_algo */
+ XFRMA_ENCAP, /* struct xfrm_algo + struct xfrm_encap_tmpl */
+ XFRMA_TMPL, /* 1 or more struct xfrm_user_tmpl */
+ XFRMA_SA, /* struct xfrm_usersa_info */
+ XFRMA_POLICY, /*struct xfrm_userpolicy_info */
+ XFRMA_SEC_CTX, /* struct xfrm_sec_ctx */
+ XFRMA_LTIME_VAL,
+ XFRMA_REPLAY_VAL,
+ XFRMA_REPLAY_THRESH,
+ XFRMA_ETIMER_THRESH,
+ XFRMA_SRCADDR, /* xfrm_address_t */
+ XFRMA_COADDR, /* xfrm_address_t */
+ XFRMA_LASTUSED, /* unsigned long */
+ XFRMA_POLICY_TYPE, /* struct xfrm_userpolicy_type */
+ XFRMA_MIGRATE,
+ XFRMA_ALG_AEAD, /* struct xfrm_algo_aead */
+ XFRMA_KMADDRESS, /* struct xfrm_user_kmaddress */
+ XFRMA_ALG_AUTH_TRUNC, /* struct xfrm_algo_auth */
+ XFRMA_MARK, /* struct xfrm_mark */
+ XFRMA_TFCPAD, /* __u32 */
+ XFRMA_REPLAY_ESN_VAL, /* struct xfrm_replay_esn */
+ XFRMA_SA_EXTRA_FLAGS, /* __u32 */
+ XFRMA_PROTO, /* __u8 */
+ XFRMA_ADDRESS_FILTER, /* struct xfrm_address_filter */
+ __XFRMA_MAX
+
+#define XFRMA_MAX (__XFRMA_MAX - 1)
+};
+
+struct xfrm_mark {
+ __u32 v; /* value */
+ __u32 m; /* mask */
+};
+
+enum xfrm_sadattr_type_t {
+ XFRMA_SAD_UNSPEC,
+ XFRMA_SAD_CNT,
+ XFRMA_SAD_HINFO,
+ __XFRMA_SAD_MAX
+
+#define XFRMA_SAD_MAX (__XFRMA_SAD_MAX - 1)
+};
+
+struct xfrmu_sadhinfo {
+ __u32 sadhcnt; /* current hash bkts */
+ __u32 sadhmcnt; /* max allowed hash bkts */
+};
+
+enum xfrm_spdattr_type_t {
+ XFRMA_SPD_UNSPEC,
+ XFRMA_SPD_INFO,
+ XFRMA_SPD_HINFO,
+ XFRMA_SPD_IPV4_HTHRESH,
+ XFRMA_SPD_IPV6_HTHRESH,
+ __XFRMA_SPD_MAX
+
+#define XFRMA_SPD_MAX (__XFRMA_SPD_MAX - 1)
+};
+
+struct xfrmu_spdinfo {
+ __u32 incnt;
+ __u32 outcnt;
+ __u32 fwdcnt;
+ __u32 inscnt;
+ __u32 outscnt;
+ __u32 fwdscnt;
+};
+
+struct xfrmu_spdhinfo {
+ __u32 spdhcnt;
+ __u32 spdhmcnt;
+};
+
+struct xfrmu_spdhthresh {
+ __u8 lbits;
+ __u8 rbits;
+};
+
+struct xfrm_usersa_info {
+ struct xfrm_selector sel;
+ struct xfrm_id id;
+ xfrm_address_t saddr;
+ struct xfrm_lifetime_cfg lft;
+ struct xfrm_lifetime_cur curlft;
+ struct xfrm_stats stats;
+ __u32 seq;
+ __u32 reqid;
+ __u16 family;
+ __u8 mode; /* XFRM_MODE_xxx */
+ __u8 replay_window;
+ __u8 flags;
+#define XFRM_STATE_NOECN 1
+#define XFRM_STATE_DECAP_DSCP 2
+#define XFRM_STATE_NOPMTUDISC 4
+#define XFRM_STATE_WILDRECV 8
+#define XFRM_STATE_ICMP 16
+#define XFRM_STATE_AF_UNSPEC 32
+#define XFRM_STATE_ALIGN4 64
+#define XFRM_STATE_ESN 128
+};
+
+#define XFRM_SA_XFLAG_DONT_ENCAP_DSCP 1
+
+struct xfrm_usersa_id {
+ xfrm_address_t daddr;
+ __be32 spi;
+ __u16 family;
+ __u8 proto;
+};
+
+struct xfrm_aevent_id {
+ struct xfrm_usersa_id sa_id;
+ xfrm_address_t saddr;
+ __u32 flags;
+ __u32 reqid;
+};
+
+struct xfrm_userspi_info {
+ struct xfrm_usersa_info info;
+ __u32 min;
+ __u32 max;
+};
+
+struct xfrm_userpolicy_info {
+ struct xfrm_selector sel;
+ struct xfrm_lifetime_cfg lft;
+ struct xfrm_lifetime_cur curlft;
+ __u32 priority;
+ __u32 index;
+ __u8 dir;
+ __u8 action;
+#define XFRM_POLICY_ALLOW 0
+#define XFRM_POLICY_BLOCK 1
+ __u8 flags;
+#define XFRM_POLICY_LOCALOK 1 /* Allow user to override global policy */
+ /* Automatically expand selector to include matching ICMP payloads. */
+#define XFRM_POLICY_ICMP 2
+ __u8 share;
+};
+
+struct xfrm_userpolicy_id {
+ struct xfrm_selector sel;
+ __u32 index;
+ __u8 dir;
+};
+
+struct xfrm_user_acquire {
+ struct xfrm_id id;
+ xfrm_address_t saddr;
+ struct xfrm_selector sel;
+ struct xfrm_userpolicy_info policy;
+ __u32 aalgos;
+ __u32 ealgos;
+ __u32 calgos;
+ __u32 seq;
+};
+
+struct xfrm_user_expire {
+ struct xfrm_usersa_info state;
+ __u8 hard;
+};
+
+struct xfrm_user_polexpire {
+ struct xfrm_userpolicy_info pol;
+ __u8 hard;
+};
+
+struct xfrm_usersa_flush {
+ __u8 proto;
+};
+
+struct xfrm_user_report {
+ __u8 proto;
+ struct xfrm_selector sel;
+};
+
+/* Used by MIGRATE to pass addresses IKE should use to perform
+ * SA negotiation with the peer */
+struct xfrm_user_kmaddress {
+ xfrm_address_t local;
+ xfrm_address_t remote;
+ __u32 reserved;
+ __u16 family;
+};
+
+struct xfrm_user_migrate {
+ xfrm_address_t old_daddr;
+ xfrm_address_t old_saddr;
+ xfrm_address_t new_daddr;
+ xfrm_address_t new_saddr;
+ __u8 proto;
+ __u8 mode;
+ __u16 reserved;
+ __u32 reqid;
+ __u16 old_family;
+ __u16 new_family;
+};
+
+struct xfrm_user_mapping {
+ struct xfrm_usersa_id id;
+ __u32 reqid;
+ xfrm_address_t old_saddr;
+ xfrm_address_t new_saddr;
+ __be16 old_sport;
+ __be16 new_sport;
+};
+
+struct xfrm_address_filter {
+ xfrm_address_t saddr;
+ xfrm_address_t daddr;
+ __u16 family;
+ __u8 splen;
+ __u8 dplen;
+};
+
+/* backwards compatibility for userspace */
+#define XFRMGRP_ACQUIRE 1
+#define XFRMGRP_EXPIRE 2
+#define XFRMGRP_SA 4
+#define XFRMGRP_POLICY 8
+#define XFRMGRP_REPORT 0x20
+
+enum xfrm_nlgroups {
+ XFRMNLGRP_NONE,
+#define XFRMNLGRP_NONE XFRMNLGRP_NONE
+ XFRMNLGRP_ACQUIRE,
+#define XFRMNLGRP_ACQUIRE XFRMNLGRP_ACQUIRE
+ XFRMNLGRP_EXPIRE,
+#define XFRMNLGRP_EXPIRE XFRMNLGRP_EXPIRE
+ XFRMNLGRP_SA,
+#define XFRMNLGRP_SA XFRMNLGRP_SA
+ XFRMNLGRP_POLICY,
+#define XFRMNLGRP_POLICY XFRMNLGRP_POLICY
+ XFRMNLGRP_AEVENTS,
+#define XFRMNLGRP_AEVENTS XFRMNLGRP_AEVENTS
+ XFRMNLGRP_REPORT,
+#define XFRMNLGRP_REPORT XFRMNLGRP_REPORT
+ XFRMNLGRP_MIGRATE,
+#define XFRMNLGRP_MIGRATE XFRMNLGRP_MIGRATE
+ XFRMNLGRP_MAPPING,
+#define XFRMNLGRP_MAPPING XFRMNLGRP_MAPPING
+ __XFRMNLGRP_MAX
+};
+#define XFRMNLGRP_MAX (__XFRMNLGRP_MAX - 1)
+
+#endif /* _LINUX_XFRM_H */
diff --git a/iproute2/include/ll_map.h b/iproute2/include/ll_map.h
new file mode 100644
index 0000000..949bfc3
--- /dev/null
+++ b/iproute2/include/ll_map.h
@@ -0,0 +1,15 @@
+#ifndef __LL_MAP_H__
+#define __LL_MAP_H__ 1
+
+int ll_remember_index(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg);
+
+void ll_init_map(struct rtnl_handle *rth);
+unsigned ll_name_to_index(const char *name);
+const char *ll_index_to_name(unsigned idx);
+const char *ll_idx_n2a(unsigned idx, char *buf);
+int ll_index_to_type(unsigned idx);
+int ll_index_to_flags(unsigned idx);
+unsigned namehash(const char *str);
+
+#endif /* __LL_MAP_H__ */
diff --git a/iproute2/include/names.h b/iproute2/include/names.h
new file mode 100644
index 0000000..6fed581
--- /dev/null
+++ b/iproute2/include/names.h
@@ -0,0 +1,26 @@
+#ifndef DB_NAMES_H_
+#define DB_NAMES_H_ 1
+
+#define IDNAME_MAX 256
+
+struct db_entry {
+ struct db_entry *next;
+ unsigned int id;
+ char *name;
+};
+
+struct db_names {
+ unsigned int size;
+ struct db_entry *cached;
+ struct db_entry **hash;
+ int max;
+};
+
+struct db_names *db_names_alloc(void);
+int db_names_load(struct db_names *db, const char *path);
+void db_names_free(struct db_names *db);
+
+char *id_to_name(struct db_names *db, int id, char *name);
+int name_to_id(struct db_names *db, int *id, const char *name);
+
+#endif
diff --git a/iproute2/include/namespace.h b/iproute2/include/namespace.h
new file mode 100644
index 0000000..51324b2
--- /dev/null
+++ b/iproute2/include/namespace.h
@@ -0,0 +1,55 @@
+#ifndef __NAMESPACE_H__
+#define __NAMESPACE_H__ 1
+
+#include <sched.h>
+#include <sys/mount.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <errno.h>
+
+#define NETNS_RUN_DIR "/var/run/netns"
+#define NETNS_ETC_DIR "/etc/netns"
+
+#ifndef CLONE_NEWNET
+#define CLONE_NEWNET 0x40000000 /* New network namespace (lo, device, names sockets, etc) */
+#endif
+
+#ifndef MNT_DETACH
+#define MNT_DETACH 0x00000002 /* Just detach from the tree */
+#endif /* MNT_DETACH */
+
+/* sys/mount.h may be out too old to have these */
+#ifndef MS_REC
+#define MS_REC 16384
+#endif
+
+#ifndef MS_SLAVE
+#define MS_SLAVE (1 << 19)
+#endif
+
+#ifndef MS_SHARED
+#define MS_SHARED (1 << 20)
+#endif
+
+#ifndef HAVE_SETNS
+static inline int setns(int fd, int nstype)
+{
+#ifdef __NR_setns
+ return syscall(__NR_setns, fd, nstype);
+#else
+ errno = ENOSYS;
+ return -1;
+#endif
+}
+#endif /* HAVE_SETNS */
+
+int netns_switch(char *netns);
+int netns_get_fd(const char *netns);
+int netns_foreach(int (*func)(char *nsname, void *arg), void *arg);
+
+struct netns_func {
+ int (*func)(char *nsname, void *arg);
+ void *arg;
+};
+
+#endif /* __NAMESPACE_H__ */
diff --git a/iproute2/include/netinet/tcp.h b/iproute2/include/netinet/tcp.h
new file mode 100644
index 0000000..3f890a1
--- /dev/null
+++ b/iproute2/include/netinet/tcp.h
@@ -0,0 +1,231 @@
+/*
+ * Copyright (c) 1982, 1986, 1993
+ * The Regents of the University of California. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 4. Neither the name of the University nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ * @(#)tcp.h 8.1 (Berkeley) 6/10/93
+ */
+
+#ifndef _NETINET_TCP_H
+#define _NETINET_TCP_H 1
+
+#include <features.h>
+
+/*
+ * User-settable options (used with setsockopt).
+ */
+#define TCP_NODELAY 1 /* Don't delay send to coalesce packets */
+#define TCP_MAXSEG 2 /* Set maximum segment size */
+#define TCP_CORK 3 /* Control sending of partial frames */
+#define TCP_KEEPIDLE 4 /* Start keeplives after this period */
+#define TCP_KEEPINTVL 5 /* Interval between keepalives */
+#define TCP_KEEPCNT 6 /* Number of keepalives before death */
+#define TCP_SYNCNT 7 /* Number of SYN retransmits */
+#define TCP_LINGER2 8 /* Life time of orphaned FIN-WAIT-2 state */
+#define TCP_DEFER_ACCEPT 9 /* Wake up listener only when data arrive */
+#define TCP_WINDOW_CLAMP 10 /* Bound advertised window */
+#define TCP_INFO 11 /* Information about this connection. */
+#define TCP_QUICKACK 12 /* Bock/reenable quick ACKs. */
+#define TCP_CONGESTION 13 /* Congestion control algorithm. */
+
+#ifdef __USE_MISC
+# include <sys/types.h>
+
+# ifdef __FAVOR_BSD
+typedef u_int32_t tcp_seq;
+/*
+ * TCP header.
+ * Per RFC 793, September, 1981.
+ */
+struct tcphdr
+ {
+ u_int16_t th_sport; /* source port */
+ u_int16_t th_dport; /* destination port */
+ tcp_seq th_seq; /* sequence number */
+ tcp_seq th_ack; /* acknowledgement number */
+# if __BYTE_ORDER == __LITTLE_ENDIAN
+ u_int8_t th_x2:4; /* (unused) */
+ u_int8_t th_off:4; /* data offset */
+# endif
+# if __BYTE_ORDER == __BIG_ENDIAN
+ u_int8_t th_off:4; /* data offset */
+ u_int8_t th_x2:4; /* (unused) */
+# endif
+ u_int8_t th_flags;
+# define TH_FIN 0x01
+# define TH_SYN 0x02
+# define TH_RST 0x04
+# define TH_PUSH 0x08
+# define TH_ACK 0x10
+# define TH_URG 0x20
+ u_int16_t th_win; /* window */
+ u_int16_t th_sum; /* checksum */
+ u_int16_t th_urp; /* urgent pointer */
+};
+
+# else /* !__FAVOR_BSD */
+struct tcphdr
+ {
+ u_int16_t source;
+ u_int16_t dest;
+ u_int32_t seq;
+ u_int32_t ack_seq;
+# if __BYTE_ORDER == __LITTLE_ENDIAN
+ u_int16_t res1:4;
+ u_int16_t doff:4;
+ u_int16_t fin:1;
+ u_int16_t syn:1;
+ u_int16_t rst:1;
+ u_int16_t psh:1;
+ u_int16_t ack:1;
+ u_int16_t urg:1;
+ u_int16_t res2:2;
+# elif __BYTE_ORDER == __BIG_ENDIAN
+ u_int16_t doff:4;
+ u_int16_t res1:4;
+ u_int16_t res2:2;
+ u_int16_t urg:1;
+ u_int16_t ack:1;
+ u_int16_t psh:1;
+ u_int16_t rst:1;
+ u_int16_t syn:1;
+ u_int16_t fin:1;
+# else
+# error "Adjust your <bits/endian.h> defines"
+# endif
+ u_int16_t window;
+ u_int16_t check;
+ u_int16_t urg_ptr;
+};
+# endif /* __FAVOR_BSD */
+
+enum
+{
+ TCP_ESTABLISHED = 1,
+ TCP_SYN_SENT,
+ TCP_SYN_RECV,
+ TCP_FIN_WAIT1,
+ TCP_FIN_WAIT2,
+ TCP_TIME_WAIT,
+ TCP_CLOSE,
+ TCP_CLOSE_WAIT,
+ TCP_LAST_ACK,
+ TCP_LISTEN,
+ TCP_CLOSING /* now a valid state */
+};
+
+# define TCPOPT_EOL 0
+# define TCPOPT_NOP 1
+# define TCPOPT_MAXSEG 2
+# define TCPOLEN_MAXSEG 4
+# define TCPOPT_WINDOW 3
+# define TCPOLEN_WINDOW 3
+# define TCPOPT_SACK_PERMITTED 4 /* Experimental */
+# define TCPOLEN_SACK_PERMITTED 2
+# define TCPOPT_SACK 5 /* Experimental */
+# define TCPOPT_TIMESTAMP 8
+# define TCPOLEN_TIMESTAMP 10
+# define TCPOLEN_TSTAMP_APPA (TCPOLEN_TIMESTAMP+2) /* appendix A */
+
+# define TCPOPT_TSTAMP_HDR \
+ (TCPOPT_NOP<<24|TCPOPT_NOP<<16|TCPOPT_TIMESTAMP<<8|TCPOLEN_TIMESTAMP)
+
+/*
+ * Default maximum segment size for TCP.
+ * With an IP MSS of 576, this is 536,
+ * but 512 is probably more convenient.
+ * This should be defined as MIN(512, IP_MSS - sizeof (struct tcpiphdr)).
+ */
+# define TCP_MSS 512
+
+# define TCP_MAXWIN 65535 /* largest value for (unscaled) window */
+
+# define TCP_MAX_WINSHIFT 14 /* maximum window shift */
+
+# define SOL_TCP 6 /* TCP level */
+
+
+# define TCPI_OPT_TIMESTAMPS 1
+# define TCPI_OPT_SACK 2
+# define TCPI_OPT_WSCALE 4
+# define TCPI_OPT_ECN 8
+# define TCPI_OPT_ECN_SEEN 16
+
+/* Values for tcpi_state. */
+enum tcp_ca_state
+{
+ TCP_CA_Open = 0,
+ TCP_CA_Disorder = 1,
+ TCP_CA_CWR = 2,
+ TCP_CA_Recovery = 3,
+ TCP_CA_Loss = 4
+};
+
+struct tcp_info
+{
+ u_int8_t tcpi_state;
+ u_int8_t tcpi_ca_state;
+ u_int8_t tcpi_retransmits;
+ u_int8_t tcpi_probes;
+ u_int8_t tcpi_backoff;
+ u_int8_t tcpi_options;
+ u_int8_t tcpi_snd_wscale : 4, tcpi_rcv_wscale : 4;
+
+ u_int32_t tcpi_rto;
+ u_int32_t tcpi_ato;
+ u_int32_t tcpi_snd_mss;
+ u_int32_t tcpi_rcv_mss;
+
+ u_int32_t tcpi_unacked;
+ u_int32_t tcpi_sacked;
+ u_int32_t tcpi_lost;
+ u_int32_t tcpi_retrans;
+ u_int32_t tcpi_fackets;
+
+ /* Times. */
+ u_int32_t tcpi_last_data_sent;
+ u_int32_t tcpi_last_ack_sent; /* Not remembered, sorry. */
+ u_int32_t tcpi_last_data_recv;
+ u_int32_t tcpi_last_ack_recv;
+
+ /* Metrics. */
+ u_int32_t tcpi_pmtu;
+ u_int32_t tcpi_rcv_ssthresh;
+ u_int32_t tcpi_rtt;
+ u_int32_t tcpi_rttvar;
+ u_int32_t tcpi_snd_ssthresh;
+ u_int32_t tcpi_snd_cwnd;
+ u_int32_t tcpi_advmss;
+ u_int32_t tcpi_reordering;
+ u_int32_t tcpi_rcv_rtt;
+ u_int32_t tcpi_rcv_space;
+ u_int32_t tcpi_total_retrans;
+
+};
+
+#endif /* Misc. */
+
+#endif /* netinet/tcp.h */
diff --git a/iproute2/include/rt_names.h b/iproute2/include/rt_names.h
new file mode 100644
index 0000000..921be06
--- /dev/null
+++ b/iproute2/include/rt_names.h
@@ -0,0 +1,35 @@
+#ifndef RT_NAMES_H_
+#define RT_NAMES_H_ 1
+
+#include <asm/types.h>
+
+const char *rtnl_rtprot_n2a(int id, char *buf, int len);
+const char *rtnl_rtscope_n2a(int id, char *buf, int len);
+const char *rtnl_rttable_n2a(__u32 id, char *buf, int len);
+const char *rtnl_rtrealm_n2a(int id, char *buf, int len);
+const char *rtnl_dsfield_n2a(int id, char *buf, int len);
+const char *rtnl_group_n2a(int id, char *buf, int len);
+
+int rtnl_rtprot_a2n(__u32 *id, const char *arg);
+int rtnl_rtscope_a2n(__u32 *id, const char *arg);
+int rtnl_rttable_a2n(__u32 *id, const char *arg);
+int rtnl_rtrealm_a2n(__u32 *id, const char *arg);
+int rtnl_dsfield_a2n(__u32 *id, const char *arg);
+int rtnl_group_a2n(int *id, const char *arg);
+
+const char *inet_proto_n2a(int proto, char *buf, int len);
+int inet_proto_a2n(const char *buf);
+
+
+const char * ll_type_n2a(int type, char *buf, int len);
+const char *ll_addr_n2a(const unsigned char *addr, int alen,
+ int type, char *buf, int blen);
+int ll_addr_a2n(char *lladdr, int len, const char *arg);
+
+const char * ll_proto_n2a(unsigned short id, char *buf, int len);
+int ll_proto_a2n(unsigned short *id, const char *buf);
+
+const char *nl_proto_n2a(int id, char *buf, int len);
+int nl_proto_a2n(__u32 *id, const char *arg);
+
+#endif
diff --git a/iproute2/include/rtm_map.h b/iproute2/include/rtm_map.h
new file mode 100644
index 0000000..d6e5885
--- /dev/null
+++ b/iproute2/include/rtm_map.h
@@ -0,0 +1,9 @@
+#ifndef __RTM_MAP_H__
+#define __RTM_MAP_H__ 1
+
+char *rtnl_rtntype_n2a(int id, char *buf, int len);
+int rtnl_rtntype_a2n(int *id, char *arg);
+
+int get_rt_realms_or_raw(__u32 *realms, char *arg);
+
+#endif /* __RTM_MAP_H__ */
diff --git a/iproute2/include/utils.h b/iproute2/include/utils.h
new file mode 100644
index 0000000..7310f4e
--- /dev/null
+++ b/iproute2/include/utils.h
@@ -0,0 +1,224 @@
+#ifndef __UTILS_H__
+#define __UTILS_H__ 1
+
+#include <sys/types.h>
+#include <asm/types.h>
+#include <resolv.h>
+#include <stdlib.h>
+#include <stdbool.h>
+
+#include "libnetlink.h"
+#include "ll_map.h"
+#include "rtm_map.h"
+
+extern int preferred_family;
+extern int human_readable;
+extern int use_iec;
+extern int show_stats;
+extern int show_details;
+extern int show_raw;
+extern int resolve_hosts;
+extern int oneline;
+extern int brief;
+extern int timestamp;
+extern int timestamp_short;
+extern const char * _SL_;
+extern int max_flush_loops;
+extern int batch_mode;
+extern bool do_all;
+
+#ifndef IPPROTO_ESP
+#define IPPROTO_ESP 50
+#endif
+#ifndef IPPROTO_AH
+#define IPPROTO_AH 51
+#endif
+#ifndef IPPROTO_COMP
+#define IPPROTO_COMP 108
+#endif
+#ifndef IPSEC_PROTO_ANY
+#define IPSEC_PROTO_ANY 255
+#endif
+
+#ifndef CONFDIR
+#define CONFDIR "/etc/iproute2"
+#endif
+
+#define SPRINT_BSIZE 64
+#define SPRINT_BUF(x) char x[SPRINT_BSIZE]
+
+void incomplete_command(void) __attribute__((noreturn));
+
+#define NEXT_ARG() do { argv++; if (--argc <= 0) incomplete_command(); } while(0)
+#define NEXT_ARG_OK() (argc - 1 > 0)
+#define NEXT_ARG_FWD() do { argv++; argc--; } while(0)
+#define PREV_ARG() do { argv--; argc++; } while(0)
+
+typedef struct
+{
+ __u16 flags;
+ __u16 bytelen;
+ __s16 bitlen;
+ /* These next two fields match rtvia */
+ __u16 family;
+ __u32 data[8];
+} inet_prefix;
+
+#define PREFIXLEN_SPECIFIED 1
+
+#define DN_MAXADDL 20
+#ifndef AF_DECnet
+#define AF_DECnet 12
+#endif
+
+struct dn_naddr
+{
+ unsigned short a_len;
+ unsigned char a_addr[DN_MAXADDL];
+};
+
+#define IPX_NODE_LEN 6
+
+struct ipx_addr {
+ u_int32_t ipx_net;
+ u_int8_t ipx_node[IPX_NODE_LEN];
+};
+
+#ifndef AF_MPLS
+# define AF_MPLS 28
+#endif
+
+/* Maximum number of labels the mpls helpers support */
+#define MPLS_MAX_LABELS 8
+
+__u32 get_addr32(const char *name);
+int get_addr_1(inet_prefix *dst, const char *arg, int family);
+int get_prefix_1(inet_prefix *dst, char *arg, int family);
+int get_addr(inet_prefix *dst, const char *arg, int family);
+int get_prefix(inet_prefix *dst, char *arg, int family);
+int mask2bits(__u32 netmask);
+int get_addr_ila(__u64 *val, const char *arg);
+
+int get_integer(int *val, const char *arg, int base);
+int get_unsigned(unsigned *val, const char *arg, int base);
+int get_time_rtt(unsigned *val, const char *arg, int *raw);
+#define get_byte get_u8
+#define get_ushort get_u16
+#define get_short get_s16
+int get_u64(__u64 *val, const char *arg, int base);
+int get_u32(__u32 *val, const char *arg, int base);
+int get_s32(__s32 *val, const char *arg, int base);
+int get_u16(__u16 *val, const char *arg, int base);
+int get_s16(__s16 *val, const char *arg, int base);
+int get_u8(__u8 *val, const char *arg, int base);
+int get_s8(__s8 *val, const char *arg, int base);
+int get_addr64(__u64 *ap, const char *cp);
+
+char* hexstring_n2a(const __u8 *str, int len, char *buf, int blen);
+__u8* hexstring_a2n(const char *str, __u8 *buf, int blen);
+#define ADDR64_BUF_SIZE sizeof("xxxx:xxxx:xxxx:xxxx")
+int addr64_n2a(__u64 addr, char *buff, size_t len);
+
+int af_bit_len(int af);
+int af_byte_len(int af);
+
+const char *format_host(int af, int len, const void *addr,
+ char *buf, int buflen);
+const char *rt_addr_n2a(int af, int len, const void *addr,
+ char *buf, int buflen);
+
+int read_family(const char *name);
+const char *family_name(int family);
+
+void missarg(const char *) __attribute__((noreturn));
+void invarg(const char *, const char *) __attribute__((noreturn));
+void duparg(const char *, const char *) __attribute__((noreturn));
+void duparg2(const char *, const char *) __attribute__((noreturn));
+int matches(const char *arg, const char *pattern);
+int inet_addr_match(const inet_prefix *a, const inet_prefix *b, int bits);
+
+const char *dnet_ntop(int af, const void *addr, char *str, size_t len);
+int dnet_pton(int af, const char *src, void *addr);
+
+const char *ipx_ntop(int af, const void *addr, char *str, size_t len);
+int ipx_pton(int af, const char *src, void *addr);
+
+const char *mpls_ntop(int af, const void *addr, char *str, size_t len);
+int mpls_pton(int af, const char *src, void *addr);
+
+extern int __iproute2_hz_internal;
+int __get_hz(void);
+
+static __inline__ int get_hz(void)
+{
+ if (__iproute2_hz_internal == 0)
+ __iproute2_hz_internal = __get_hz();
+ return __iproute2_hz_internal;
+}
+
+extern int __iproute2_user_hz_internal;
+int __get_user_hz(void);
+
+static __inline__ int get_user_hz(void)
+{
+ if (__iproute2_user_hz_internal == 0)
+ __iproute2_user_hz_internal = __get_user_hz();
+ return __iproute2_user_hz_internal;
+}
+
+static inline __u32 nl_mgrp(__u32 group)
+{
+ if (group > 31 ) {
+ fprintf(stderr, "Use setsockopt for this group %d\n", group);
+ exit(-1);
+ }
+ return group ? (1 << (group - 1)) : 0;
+}
+
+
+int print_timestamp(FILE *fp);
+void print_nlmsg_timestamp(FILE *fp, const struct nlmsghdr *n);
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+
+#define BUILD_BUG_ON(cond) ((void)sizeof(char[1 - 2 * !!(cond)]))
+
+#ifndef offsetof
+# define offsetof(type, member) ((size_t) &((type *)0)->member)
+#endif
+
+#ifndef min
+# define min(x, y) ({ \
+ typeof(x) _min1 = (x); \
+ typeof(y) _min2 = (y); \
+ (void) (&_min1 == &_min2); \
+ _min1 < _min2 ? _min1 : _min2; })
+#endif
+
+#ifndef __check_format_string
+# define __check_format_string(pos_str, pos_args) \
+ __attribute__ ((format (printf, (pos_str), (pos_args))))
+#endif
+
+#define _textify(x) #x
+#define textify(x) _textify(x)
+
+#define htonll(x) ((1==htonl(1)) ? (x) : ((uint64_t)htonl((x) & 0xFFFFFFFF) << 32) | htonl((x) >> 32))
+#define ntohll(x) ((1==ntohl(1)) ? (x) : ((uint64_t)ntohl((x) & 0xFFFFFFFF) << 32) | ntohl((x) >> 32))
+
+extern int cmdlineno;
+ssize_t getcmdline(char **line, size_t *len, FILE *in);
+int makeargs(char *line, char *argv[], int maxargs);
+int inet_get_addr(const char *src, __u32 *dst, struct in6_addr *dst6);
+
+struct iplink_req;
+int iplink_parse(int argc, char **argv, struct iplink_req *req,
+ char **name, char **type, char **link, char **dev,
+ int *group, int *index);
+
+int do_each_netns(int (*func)(char *nsname, void *arg), void *arg,
+ bool show_label);
+
+char *int_to_str(int val, char *buf);
+
+#endif /* __UTILS_H__ */
diff --git a/iproute2/include/xt-internal.h b/iproute2/include/xt-internal.h
new file mode 100644
index 0000000..b8ea67d
--- /dev/null
+++ b/iproute2/include/xt-internal.h
@@ -0,0 +1,66 @@
+#ifndef _XTABLES_INTERNAL_H
+#define _XTABLES_INTERNAL_H 1
+
+#ifndef XT_LIB_DIR
+# define XT_LIB_DIR "/lib/xtables"
+#endif
+
+/* protocol family dependent informations */
+struct afinfo {
+ /* protocol family */
+ int family;
+
+ /* prefix of library name (ex "libipt_" */
+ char *libprefix;
+
+ /* used by setsockopt (ex IPPROTO_IP */
+ int ipproto;
+
+ /* kernel module (ex "ip_tables" */
+ char *kmod;
+
+ /* optname to check revision support of match */
+ int so_rev_match;
+
+ /* optname to check revision support of match */
+ int so_rev_target;
+};
+
+enum xt_tryload {
+ DONT_LOAD,
+ DURING_LOAD,
+ TRY_LOAD,
+ LOAD_MUST_SUCCEED
+};
+
+struct xtables_rule_match {
+ struct xtables_rule_match *next;
+ struct xtables_match *match;
+ /* Multiple matches of the same type: the ones before
+ the current one are completed from parsing point of view */
+ unsigned int completed;
+};
+
+extern char *lib_dir;
+
+extern void *fw_calloc(size_t count, size_t size);
+extern void *fw_malloc(size_t size);
+
+extern const char *modprobe_program;
+extern int xtables_insmod(const char *modname, const char *modprobe, int quiet);
+extern int load_xtables_ko(const char *modprobe, int quiet);
+
+/* This is decleared in ip[6]tables.c */
+extern struct afinfo afinfo;
+
+/* Keeping track of external matches and targets: linked lists. */
+extern struct xtables_match *xtables_matches;
+extern struct xtables_target *xtables_targets;
+
+extern struct xtables_match *find_match(const char *name, enum xt_tryload,
+ struct xtables_rule_match **match);
+extern struct xtables_target *find_target(const char *name, enum xt_tryload);
+
+extern void _init(void);
+
+#endif /* _XTABLES_INTERNAL_H */
diff --git a/iproute2/include/xtables.h b/iproute2/include/xtables.h
new file mode 100644
index 0000000..978ae0d
--- /dev/null
+++ b/iproute2/include/xtables.h
@@ -0,0 +1,567 @@
+#ifndef _XTABLES_H
+#define _XTABLES_H
+
+/*
+ * Changing any structs/functions may incur a needed change
+ * in libxtables_vcurrent/vage too.
+ */
+
+#include <sys/socket.h> /* PF_* */
+#include <sys/types.h>
+#include <limits.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdint.h>
+#include <netinet/in.h>
+#include <net/if.h>
+#include <linux/types.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/x_tables.h>
+
+#ifndef IPPROTO_SCTP
+#define IPPROTO_SCTP 132
+#endif
+#ifndef IPPROTO_DCCP
+#define IPPROTO_DCCP 33
+#endif
+#ifndef IPPROTO_MH
+# define IPPROTO_MH 135
+#endif
+#ifndef IPPROTO_UDPLITE
+#define IPPROTO_UDPLITE 136
+#endif
+
+#include <xtables-version.h>
+
+struct in_addr;
+
+/*
+ * .size is here so that there is a somewhat reasonable check
+ * against the chosen .type.
+ */
+#define XTOPT_POINTER(stype, member) \
+ .ptroff = offsetof(stype, member), \
+ .size = sizeof(((stype *)NULL)->member)
+#define XTOPT_TABLEEND {.name = NULL}
+
+/**
+ * Select the format the input has to conform to, as well as the target type
+ * (area pointed to with XTOPT_POINTER). Note that the storing is not always
+ * uniform. @cb->val will be populated with as much as there is space, i.e.
+ * exactly 2 items for ranges, but the target area can receive more values
+ * (e.g. in case of ranges), or less values (e.g. %XTTYPE_HOSTMASK).
+ *
+ * %XTTYPE_NONE: option takes no argument
+ * %XTTYPE_UINT*: standard integer
+ * %XTTYPE_UINT*RC: colon-separated range of standard integers
+ * %XTTYPE_DOUBLE: double-precision floating point number
+ * %XTTYPE_STRING: arbitrary string
+ * %XTTYPE_TOSMASK: 8-bit TOS value with optional mask
+ * %XTTYPE_MARKMASK32: 32-bit mark with optional mask
+ * %XTTYPE_SYSLOGLEVEL: syslog level by name or number
+ * %XTTYPE_HOST: one host or address (ptr: union nf_inet_addr)
+ * %XTTYPE_HOSTMASK: one host or address, with an optional prefix length
+ * (ptr: union nf_inet_addr; only host portion is stored)
+ * %XTTYPE_PROTOCOL: protocol number/name from /etc/protocols (ptr: uint8_t)
+ * %XTTYPE_PORT: 16-bit port name or number (supports %XTOPT_NBO)
+ * %XTTYPE_PORTRC: colon-separated port range (names acceptable),
+ * (supports %XTOPT_NBO)
+ * %XTTYPE_PLEN: prefix length
+ * %XTTYPE_PLENMASK: prefix length (ptr: union nf_inet_addr)
+ * %XTTYPE_ETHERMAC: Ethernet MAC address in hex form
+ */
+enum xt_option_type {
+ XTTYPE_NONE,
+ XTTYPE_UINT8,
+ XTTYPE_UINT16,
+ XTTYPE_UINT32,
+ XTTYPE_UINT64,
+ XTTYPE_UINT8RC,
+ XTTYPE_UINT16RC,
+ XTTYPE_UINT32RC,
+ XTTYPE_UINT64RC,
+ XTTYPE_DOUBLE,
+ XTTYPE_STRING,
+ XTTYPE_TOSMASK,
+ XTTYPE_MARKMASK32,
+ XTTYPE_SYSLOGLEVEL,
+ XTTYPE_HOST,
+ XTTYPE_HOSTMASK,
+ XTTYPE_PROTOCOL,
+ XTTYPE_PORT,
+ XTTYPE_PORTRC,
+ XTTYPE_PLEN,
+ XTTYPE_PLENMASK,
+ XTTYPE_ETHERMAC,
+};
+
+/**
+ * %XTOPT_INVERT: option is invertible (usable with !)
+ * %XTOPT_MAND: option is mandatory
+ * %XTOPT_MULTI: option may be specified multiple times
+ * %XTOPT_PUT: store value into memory at @ptroff
+ * %XTOPT_NBO: store value in network-byte order
+ * (only certain XTTYPEs recognize this)
+ */
+enum xt_option_flags {
+ XTOPT_INVERT = 1 << 0,
+ XTOPT_MAND = 1 << 1,
+ XTOPT_MULTI = 1 << 2,
+ XTOPT_PUT = 1 << 3,
+ XTOPT_NBO = 1 << 4,
+};
+
+/**
+ * @name: name of option
+ * @type: type of input and validation method, see %XTTYPE_*
+ * @id: unique number (within extension) for option, 0-31
+ * @excl: bitmask of flags that cannot be used with this option
+ * @also: bitmask of flags that must be used with this option
+ * @flags: bitmask of option flags, see %XTOPT_*
+ * @ptroff: offset into private structure for member
+ * @size: size of the item pointed to by @ptroff; this is a safeguard
+ * @min: lowest allowed value (for singular integral types)
+ * @max: highest allowed value (for singular integral types)
+ */
+struct xt_option_entry {
+ const char *name;
+ enum xt_option_type type;
+ unsigned int id, excl, also, flags;
+ unsigned int ptroff;
+ size_t size;
+ unsigned int min, max;
+};
+
+/**
+ * @arg: input from command line
+ * @ext_name: name of extension currently being processed
+ * @entry: current option being processed
+ * @data: per-extension kernel data block
+ * @xflags: options of the extension that have been used
+ * @invert: whether option was used with !
+ * @nvals: number of results in uXX_multi
+ * @val: parsed result
+ * @udata: per-extension private scratch area
+ * (cf. xtables_{match,target}->udata_size)
+ */
+struct xt_option_call {
+ const char *arg, *ext_name;
+ const struct xt_option_entry *entry;
+ void *data;
+ unsigned int xflags;
+ bool invert;
+ uint8_t nvals;
+ union {
+ uint8_t u8, u8_range[2], syslog_level, protocol;
+ uint16_t u16, u16_range[2], port, port_range[2];
+ uint32_t u32, u32_range[2];
+ uint64_t u64, u64_range[2];
+ double dbl;
+ struct {
+ union nf_inet_addr haddr, hmask;
+ uint8_t hlen;
+ };
+ struct {
+ uint8_t tos_value, tos_mask;
+ };
+ struct {
+ uint32_t mark, mask;
+ };
+ uint8_t ethermac[6];
+ } val;
+ /* Wished for a world where the ones below were gone: */
+ union {
+ struct xt_entry_match **match;
+ struct xt_entry_target **target;
+ };
+ void *xt_entry;
+ void *udata;
+};
+
+/**
+ * @ext_name: name of extension currently being processed
+ * @data: per-extension (kernel) data block
+ * @udata: per-extension private scratch area
+ * (cf. xtables_{match,target}->udata_size)
+ * @xflags: options of the extension that have been used
+ */
+struct xt_fcheck_call {
+ const char *ext_name;
+ void *data, *udata;
+ unsigned int xflags;
+};
+
+/**
+ * A "linear"/linked-list based name<->id map, for files similar to
+ * /etc/iproute2/.
+ */
+struct xtables_lmap {
+ char *name;
+ int id;
+ struct xtables_lmap *next;
+};
+
+enum xtables_ext_flags {
+ XTABLES_EXT_ALIAS = 1 << 0,
+};
+
+/* Include file for additions: new matches and targets. */
+struct xtables_match
+{
+ /*
+ * ABI/API version this module requires. Must be first member,
+ * as the rest of this struct may be subject to ABI changes.
+ */
+ const char *version;
+
+ struct xtables_match *next;
+
+ const char *name;
+ const char *real_name;
+
+ /* Revision of match (0 by default). */
+ uint8_t revision;
+
+ /* Extension flags */
+ uint8_t ext_flags;
+
+ uint16_t family;
+
+ /* Size of match data. */
+ size_t size;
+
+ /* Size of match data relevant for userspace comparison purposes */
+ size_t userspacesize;
+
+ /* Function which prints out usage message. */
+ void (*help)(void);
+
+ /* Initialize the match. */
+ void (*init)(struct xt_entry_match *m);
+
+ /* Function which parses command options; returns true if it
+ ate an option */
+ /* entry is struct ipt_entry for example */
+ int (*parse)(int c, char **argv, int invert, unsigned int *flags,
+ const void *entry,
+ struct xt_entry_match **match);
+
+ /* Final check; exit if not ok. */
+ void (*final_check)(unsigned int flags);
+
+ /* Prints out the match iff non-NULL: put space at end */
+ /* ip is struct ipt_ip * for example */
+ void (*print)(const void *ip,
+ const struct xt_entry_match *match, int numeric);
+
+ /* Saves the match info in parsable form to stdout. */
+ /* ip is struct ipt_ip * for example */
+ void (*save)(const void *ip, const struct xt_entry_match *match);
+
+ /* Print match name or alias */
+ const char *(*alias)(const struct xt_entry_match *match);
+
+ /* Pointer to list of extra command-line options */
+ const struct option *extra_opts;
+
+ /* New parser */
+ void (*x6_parse)(struct xt_option_call *);
+ void (*x6_fcheck)(struct xt_fcheck_call *);
+ const struct xt_option_entry *x6_options;
+
+ /* Size of per-extension instance extra "global" scratch space */
+ size_t udata_size;
+
+ /* Ignore these men behind the curtain: */
+ void *udata;
+ unsigned int option_offset;
+ struct xt_entry_match *m;
+ unsigned int mflags;
+ unsigned int loaded; /* simulate loading so options are merged properly */
+};
+
+struct xtables_target
+{
+ /*
+ * ABI/API version this module requires. Must be first member,
+ * as the rest of this struct may be subject to ABI changes.
+ */
+ const char *version;
+
+ struct xtables_target *next;
+
+
+ const char *name;
+
+ /* Real target behind this, if any. */
+ const char *real_name;
+
+ /* Revision of target (0 by default). */
+ uint8_t revision;
+
+ /* Extension flags */
+ uint8_t ext_flags;
+
+ uint16_t family;
+
+
+ /* Size of target data. */
+ size_t size;
+
+ /* Size of target data relevant for userspace comparison purposes */
+ size_t userspacesize;
+
+ /* Function which prints out usage message. */
+ void (*help)(void);
+
+ /* Initialize the target. */
+ void (*init)(struct xt_entry_target *t);
+
+ /* Function which parses command options; returns true if it
+ ate an option */
+ /* entry is struct ipt_entry for example */
+ int (*parse)(int c, char **argv, int invert, unsigned int *flags,
+ const void *entry,
+ struct xt_entry_target **targetinfo);
+
+ /* Final check; exit if not ok. */
+ void (*final_check)(unsigned int flags);
+
+ /* Prints out the target iff non-NULL: put space at end */
+ void (*print)(const void *ip,
+ const struct xt_entry_target *target, int numeric);
+
+ /* Saves the targinfo in parsable form to stdout. */
+ void (*save)(const void *ip,
+ const struct xt_entry_target *target);
+
+ /* Print target name or alias */
+ const char *(*alias)(const struct xt_entry_target *target);
+
+ /* Pointer to list of extra command-line options */
+ const struct option *extra_opts;
+
+ /* New parser */
+ void (*x6_parse)(struct xt_option_call *);
+ void (*x6_fcheck)(struct xt_fcheck_call *);
+ const struct xt_option_entry *x6_options;
+
+ size_t udata_size;
+
+ /* Ignore these men behind the curtain: */
+ void *udata;
+ unsigned int option_offset;
+ struct xt_entry_target *t;
+ unsigned int tflags;
+ unsigned int used;
+ unsigned int loaded; /* simulate loading so options are merged properly */
+};
+
+struct xtables_rule_match {
+ struct xtables_rule_match *next;
+ struct xtables_match *match;
+ /* Multiple matches of the same type: the ones before
+ the current one are completed from parsing point of view */
+ bool completed;
+};
+
+/**
+ * struct xtables_pprot -
+ *
+ * A few hardcoded protocols for 'all' and in case the user has no
+ * /etc/protocols.
+ */
+struct xtables_pprot {
+ const char *name;
+ uint8_t num;
+};
+
+enum xtables_tryload {
+ XTF_DONT_LOAD,
+ XTF_DURING_LOAD,
+ XTF_TRY_LOAD,
+ XTF_LOAD_MUST_SUCCEED,
+};
+
+enum xtables_exittype {
+ OTHER_PROBLEM = 1,
+ PARAMETER_PROBLEM,
+ VERSION_PROBLEM,
+ RESOURCE_PROBLEM,
+ XTF_ONLY_ONCE,
+ XTF_NO_INVERT,
+ XTF_BAD_VALUE,
+ XTF_ONE_ACTION,
+};
+
+struct xtables_globals
+{
+ unsigned int option_offset;
+ const char *program_name, *program_version;
+ struct option *orig_opts;
+ struct option *opts;
+ void (*exit_err)(enum xtables_exittype status, const char *msg, ...) __attribute__((noreturn, format(printf,2,3)));
+ int (*compat_rev)(const char *name, uint8_t rev, int opt);
+};
+
+#define XT_GETOPT_TABLEEND {.name = NULL, .has_arg = false}
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+extern const char *xtables_modprobe_program;
+extern struct xtables_match *xtables_matches;
+extern struct xtables_target *xtables_targets;
+
+extern void xtables_init(void);
+extern void xtables_set_nfproto(uint8_t);
+extern void *xtables_calloc(size_t, size_t);
+extern void *xtables_malloc(size_t);
+extern void *xtables_realloc(void *, size_t);
+
+extern int xtables_insmod(const char *, const char *, bool);
+extern int xtables_load_ko(const char *, bool);
+extern int xtables_set_params(struct xtables_globals *xtp);
+extern void xtables_free_opts(int reset_offset);
+extern struct option *xtables_merge_options(struct option *origopts,
+ struct option *oldopts, const struct option *newopts,
+ unsigned int *option_offset);
+
+extern int xtables_init_all(struct xtables_globals *xtp, uint8_t nfproto);
+extern struct xtables_match *xtables_find_match(const char *name,
+ enum xtables_tryload, struct xtables_rule_match **match);
+extern struct xtables_target *xtables_find_target(const char *name,
+ enum xtables_tryload);
+extern int xtables_compatible_revision(const char *name, uint8_t revision,
+ int opt);
+
+extern void xtables_rule_matches_free(struct xtables_rule_match **matches);
+
+/* Your shared library should call one of these. */
+extern void xtables_register_match(struct xtables_match *me);
+extern void xtables_register_matches(struct xtables_match *, unsigned int);
+extern void xtables_register_target(struct xtables_target *me);
+extern void xtables_register_targets(struct xtables_target *, unsigned int);
+
+extern bool xtables_strtoul(const char *, char **, uintmax_t *,
+ uintmax_t, uintmax_t);
+extern bool xtables_strtoui(const char *, char **, unsigned int *,
+ unsigned int, unsigned int);
+extern int xtables_service_to_port(const char *name, const char *proto);
+extern uint16_t xtables_parse_port(const char *port, const char *proto);
+extern void
+xtables_parse_interface(const char *arg, char *vianame, unsigned char *mask);
+
+/* this is a special 64bit data type that is 8-byte aligned */
+#define aligned_u64 uint64_t __attribute__((aligned(8)))
+
+extern struct xtables_globals *xt_params;
+#define xtables_error (xt_params->exit_err)
+
+extern void xtables_param_act(unsigned int, const char *, ...);
+
+extern const char *xtables_ipaddr_to_numeric(const struct in_addr *);
+extern const char *xtables_ipaddr_to_anyname(const struct in_addr *);
+extern const char *xtables_ipmask_to_numeric(const struct in_addr *);
+extern struct in_addr *xtables_numeric_to_ipaddr(const char *);
+extern struct in_addr *xtables_numeric_to_ipmask(const char *);
+extern int xtables_ipmask_to_cidr(const struct in_addr *);
+extern void xtables_ipparse_any(const char *, struct in_addr **,
+ struct in_addr *, unsigned int *);
+extern void xtables_ipparse_multiple(const char *, struct in_addr **,
+ struct in_addr **, unsigned int *);
+
+extern struct in6_addr *xtables_numeric_to_ip6addr(const char *);
+extern const char *xtables_ip6addr_to_numeric(const struct in6_addr *);
+extern const char *xtables_ip6addr_to_anyname(const struct in6_addr *);
+extern const char *xtables_ip6mask_to_numeric(const struct in6_addr *);
+extern int xtables_ip6mask_to_cidr(const struct in6_addr *);
+extern void xtables_ip6parse_any(const char *, struct in6_addr **,
+ struct in6_addr *, unsigned int *);
+extern void xtables_ip6parse_multiple(const char *, struct in6_addr **,
+ struct in6_addr **, unsigned int *);
+
+/**
+ * Print the specified value to standard output, quoting dangerous
+ * characters if required.
+ */
+extern void xtables_save_string(const char *value);
+
+#define FMT_NUMERIC 0x0001
+#define FMT_NOCOUNTS 0x0002
+#define FMT_KILOMEGAGIGA 0x0004
+#define FMT_OPTIONS 0x0008
+#define FMT_NOTABLE 0x0010
+#define FMT_NOTARGET 0x0020
+#define FMT_VIA 0x0040
+#define FMT_NONEWLINE 0x0080
+#define FMT_LINENUMBERS 0x0100
+
+#define FMT_PRINT_RULE (FMT_NOCOUNTS | FMT_OPTIONS | FMT_VIA \
+ | FMT_NUMERIC | FMT_NOTABLE)
+#define FMT(tab,notab) ((format) & FMT_NOTABLE ? (notab) : (tab))
+
+extern void xtables_print_num(uint64_t number, unsigned int format);
+
+#if defined(ALL_INCLUSIVE) || defined(NO_SHARED_LIBS)
+# ifdef _INIT
+# undef _init
+# define _init _INIT
+# endif
+ extern void init_extensions(void);
+ extern void init_extensions4(void);
+ extern void init_extensions6(void);
+#else
+# define _init __attribute__((constructor)) _INIT
+#endif
+
+extern const struct xtables_pprot xtables_chain_protos[];
+extern uint16_t xtables_parse_protocol(const char *s);
+
+/* kernel revision handling */
+extern int kernel_version;
+extern void get_kernel_version(void);
+#define LINUX_VERSION(x,y,z) (0x10000*(x) + 0x100*(y) + z)
+#define LINUX_VERSION_MAJOR(x) (((x)>>16) & 0xFF)
+#define LINUX_VERSION_MINOR(x) (((x)>> 8) & 0xFF)
+#define LINUX_VERSION_PATCH(x) ( (x) & 0xFF)
+
+/* xtoptions.c */
+extern void xtables_option_metavalidate(const char *,
+ const struct xt_option_entry *);
+extern struct option *xtables_options_xfrm(struct option *, struct option *,
+ const struct xt_option_entry *,
+ unsigned int *);
+extern void xtables_option_parse(struct xt_option_call *);
+extern void xtables_option_tpcall(unsigned int, char **, bool,
+ struct xtables_target *, void *);
+extern void xtables_option_mpcall(unsigned int, char **, bool,
+ struct xtables_match *, void *);
+extern void xtables_option_tfcall(struct xtables_target *);
+extern void xtables_option_mfcall(struct xtables_match *);
+extern void xtables_options_fcheck(const char *, unsigned int,
+ const struct xt_option_entry *);
+
+extern struct xtables_lmap *xtables_lmap_init(const char *);
+extern void xtables_lmap_free(struct xtables_lmap *);
+extern int xtables_lmap_name2id(const struct xtables_lmap *, const char *);
+extern const char *xtables_lmap_id2name(const struct xtables_lmap *, int);
+
+#ifdef XTABLES_INTERNAL
+
+/* Shipped modules rely on this... */
+
+# ifndef ARRAY_SIZE
+# define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
+# endif
+
+extern void _init(void);
+
+#endif
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
+#endif /* _XTABLES_H */
diff --git a/iproute2/ip/Android.mk b/iproute2/ip/Android.mk
new file mode 100644
index 0000000..5c45bc7
--- /dev/null
+++ b/iproute2/ip/Android.mk
@@ -0,0 +1,38 @@
+LOCAL_PATH := $(call my-dir)
+
+include $(CLEAR_VARS)
+LOCAL_SRC_FILES := ip.c ipaddress.c ipaddrlabel.c iproute.c iprule.c ipnetns.c \
+ rtm_map.c iptunnel.c ip6tunnel.c tunnel.c ipneigh.c ipntable.c iplink.c \
+ ipmaddr.c ipmonitor.c ipmroute.c ipprefix.c iptuntap.c \
+ ipxfrm.c xfrm_state.c xfrm_policy.c xfrm_monitor.c \
+ iplink_vlan.c link_veth.c link_gre.c iplink_can.c \
+ iplink_macvlan.c ipl2tp.c \
+ ipfou.c iptoken.c tcp_metrics.c ipnetconf.c \
+ iproute_lwtunnel.c
+
+LOCAL_MODULE := ip
+
+LOCAL_MODULE_TAGS := optional
+
+LOCAL_SHARED_LIBRARIES := libc libm libdl
+
+LOCAL_SHARED_LIBRARIES += libiprouteutil libnetlink
+
+LOCAL_C_INCLUDES := $(LOCAL_PATH)/../include
+
+LOCAL_CFLAGS := \
+ -O2 -g \
+ -W -Wall \
+ -Wno-implicit-function-declaration \
+ -Wno-missing-field-initializers \
+ -Wno-pointer-arith \
+ -Wno-sign-compare \
+ -Wno-unused-parameter \
+ -Werror \
+ -D_GNU_SOURCE \
+ -DHAVE_SETNS \
+
+LOCAL_LDFLAGS := -Wl,-export-dynamic -Wl,--no-gc-sections
+
+include $(BUILD_EXECUTABLE)
+
diff --git a/iproute2/ip/MODULE_LICENSE_GPL b/iproute2/ip/MODULE_LICENSE_GPL
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/iproute2/ip/MODULE_LICENSE_GPL
diff --git a/iproute2/ip/Makefile b/iproute2/ip/Makefile
new file mode 100644
index 0000000..f3d2987
--- /dev/null
+++ b/iproute2/ip/Makefile
@@ -0,0 +1,53 @@
+IPOBJ=ip.o ipaddress.o ipaddrlabel.o iproute.o iprule.o ipnetns.o \
+ rtm_map.o iptunnel.o ip6tunnel.o tunnel.o ipneigh.o ipntable.o iplink.o \
+ ipmaddr.o ipmonitor.o ipmroute.o ipprefix.o iptuntap.o iptoken.o \
+ ipxfrm.o xfrm_state.o xfrm_policy.o xfrm_monitor.o \
+ iplink_vlan.o link_veth.o link_gre.o iplink_can.o \
+ iplink_macvlan.o ipl2tp.o link_vti.o link_vti6.o \
+ iplink_vxlan.o tcp_metrics.o iplink_ipoib.o ipnetconf.o link_ip6tnl.o \
+ link_iptnl.o link_gre6.o iplink_bond.o iplink_bond_slave.o iplink_hsr.o \
+ iplink_bridge.o iplink_bridge_slave.o ipfou.o iplink_ipvlan.o \
+ iplink_geneve.o iplink_vrf.o iproute_lwtunnel.o
+
+RTMONOBJ=rtmon.o
+
+include ../Config
+
+ifeq ($(IP_CONFIG_SETNS),y)
+ CFLAGS += -DHAVE_SETNS
+endif
+
+ALLOBJ=$(IPOBJ) $(RTMONOBJ)
+SCRIPTS=ifcfg rtpr routel routef
+TARGETS=ip rtmon
+
+all: $(TARGETS) $(SCRIPTS)
+
+ip: $(IPOBJ) $(LIBNETLINK)
+
+rtmon: $(RTMONOBJ)
+
+install: all
+ install -m 0755 $(TARGETS) $(DESTDIR)$(SBINDIR)
+ install -m 0755 $(SCRIPTS) $(DESTDIR)$(SBINDIR)
+
+clean:
+ rm -f $(ALLOBJ) $(TARGETS)
+
+SHARED_LIBS ?= y
+ifeq ($(SHARED_LIBS),y)
+
+LDLIBS += -ldl
+LDFLAGS += -Wl,-export-dynamic
+
+else
+
+ip: static-syms.o
+static-syms.o: static-syms.h
+static-syms.h: $(wildcard *.c)
+ files="$^" ; \
+ for s in `grep -B 3 '\<dlsym' $$files | sed -n '/snprintf/{s:.*"\([^"]*\)".*:\1:;s:%s::;p}'` ; do \
+ sed -n '/'$$s'[^ ]* =/{s:.* \([^ ]*'$$s'[^ ]*\) .*:extern char \1[] __attribute__((weak)); if (!strcmp(sym, "\1")) return \1;:;p}' $$files ; \
+ done > $@
+
+endif
diff --git a/iproute2/ip/NOTICE b/iproute2/ip/NOTICE
new file mode 100644
index 0000000..3912109
--- /dev/null
+++ b/iproute2/ip/NOTICE
@@ -0,0 +1,340 @@
+ GNU GENERAL PUBLIC LICENSE
+ Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.
+ 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+ Preamble
+
+ The licenses for most software are designed to take away your
+freedom to share and change it. By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users. This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it. (Some other Free Software Foundation software is covered by
+the GNU Library General Public License instead.) You can apply it to
+your programs, too.
+
+ When we speak of free software, we are referring to freedom, not
+price. Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+ To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+ For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have. You must make sure that they, too, receive or can get the
+source code. And you must show them these terms so they know their
+rights.
+
+ We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+ Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software. If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+ Finally, any free program is threatened constantly by software
+patents. We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary. To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+ The precise terms and conditions for copying, distribution and
+modification follow.
+
+ GNU GENERAL PUBLIC LICENSE
+ TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+ 0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License. The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language. (Hereinafter, translation is included without limitation in
+the term "modification".) Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope. The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+ 1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+ 2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+ a) You must cause the modified files to carry prominent notices
+ stating that you changed the files and the date of any change.
+
+ b) You must cause any work that you distribute or publish, that in
+ whole or in part contains or is derived from the Program or any
+ part thereof, to be licensed as a whole at no charge to all third
+ parties under the terms of this License.
+
+ c) If the modified program normally reads commands interactively
+ when run, you must cause it, when started running for such
+ interactive use in the most ordinary way, to print or display an
+ announcement including an appropriate copyright notice and a
+ notice that there is no warranty (or else, saying that you provide
+ a warranty) and that users may redistribute the program under
+ these conditions, and telling the user how to view a copy of this
+ License. (Exception: if the Program itself is interactive but
+ does not normally print such an announcement, your work based on
+ the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole. If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works. But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+ 3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+ a) Accompany it with the complete corresponding machine-readable
+ source code, which must be distributed under the terms of Sections
+ 1 and 2 above on a medium customarily used for software interchange; or,
+
+ b) Accompany it with a written offer, valid for at least three
+ years, to give any third party, for a charge no more than your
+ cost of physically performing source distribution, a complete
+ machine-readable copy of the corresponding source code, to be
+ distributed under the terms of Sections 1 and 2 above on a medium
+ customarily used for software interchange; or,
+
+ c) Accompany it with the information you received as to the offer
+ to distribute corresponding source code. (This alternative is
+ allowed only for noncommercial distribution and only if you
+ received the program in object code or executable form with such
+ an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it. For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable. However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+ 4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License. Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+ 5. You are not required to accept this License, since you have not
+signed it. However, nothing else grants you permission to modify or
+distribute the Program or its derivative works. These actions are
+prohibited by law if you do not accept this License. Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+ 6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions. You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+ 7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License. If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all. For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices. Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+ 8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded. In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+ 9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time. Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number. If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation. If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+ 10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission. For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this. Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+ NO WARRANTY
+
+ 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+ 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+ END OF TERMS AND CONDITIONS
+
+ How to Apply These Terms to Your New Programs
+
+ If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+ To do so, attach the following notices to the program. It is safest
+to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+ <one line to give the program's name and a brief idea of what it does.>
+ Copyright (C) <year> <name of author>
+
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 2 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+ Gnomovision version 69, Copyright (C) year name of author
+ Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+ This is free software, and you are welcome to redistribute it
+ under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License. Of course, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary. Here is a sample; alter the names:
+
+ Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+ `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+ <signature of Ty Coon>, 1 April 1989
+ Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs. If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library. If this is what you want to do, use the GNU Library General
+Public License instead of this License.
diff --git a/iproute2/ip/ifcfg b/iproute2/ip/ifcfg
new file mode 100644
index 0000000..083d9df
--- /dev/null
+++ b/iproute2/ip/ifcfg
@@ -0,0 +1,149 @@
+#! /bin/bash
+
+CheckForwarding () {
+ local sbase fwd
+ sbase=/proc/sys/net/ipv4/conf
+ fwd=0
+ if [ -d $sbase ]; then
+ for dir in $sbase/*/forwarding; do
+ fwd=$[$fwd + `cat $dir`]
+ done
+ else
+ fwd=2
+ fi
+ return $fwd
+}
+
+RestartRDISC () {
+ killall -HUP rdisc || rdisc -fs
+}
+
+ABCMaskLen () {
+ local class;
+
+ class=${1%%.*}
+ if [ "$1" = "" -o $class -eq 0 -o $class -ge 224 ]; then return 0
+ elif [ $class -ge 224 ]; then return 0
+ elif [ $class -ge 192 ]; then return 24
+ elif [ $class -ge 128 ]; then return 16
+ else return 8; fi
+}
+
+label="label $1"
+ldev="$1"
+dev=${1%:*}
+if [ "$dev" = "" -o "$1" = "help" ]; then
+ echo "Usage: ifcfg DEV [[add|del [ADDR[/LEN]] [PEER] | stop]" 1>&2
+ echo " add - add new address" 1>&2
+ echo " del - delete address" 1>&2
+ echo " stop - completely disable IP" 1>&2
+ exit 1
+fi
+shift
+
+CheckForwarding
+fwd=$?
+if [ $fwd -ne 0 ]; then
+ echo "Forwarding is ON or its state is unknown ($fwd). OK, No RDISC." 1>&2
+fi
+
+
+deleting=0
+case "$1" in
+add) shift ;;
+stop)
+ if [ "$ldev" != "$dev" ]; then
+ echo "Cannot stop alias $ldev" 1>&2
+ exit 1;
+ fi
+ ip -4 addr flush dev $dev $label || exit 1
+ if [ $fwd -eq 0 ]; then RestartRDISC; fi
+ exit 0 ;;
+del*)
+ deleting=1; shift ;;
+*)
+esac
+
+ipaddr=
+pfxlen=
+if [ "$1" != "" ]; then
+ ipaddr=${1%/*}
+ if [ "$1" != "$ipaddr" ]; then
+ pfxlen=${1#*/}
+ fi
+ if [ "$ipaddr" = "" ]; then
+ echo "$1 is bad IP address." 1>&2
+ exit 1
+ fi
+fi
+shift
+
+peer=$1
+if [ "$peer" != "" ]; then
+ if [ "$pfxlen" != "" -a "$pfxlen" != "32" ]; then
+ echo "Peer address with non-trivial netmask." 1>&2
+ exit 1
+ fi
+ pfx="$ipaddr peer $peer"
+else
+ if [ "$ipaddr" = "" ]; then
+ echo "Missing IP address argument." 1>&2
+ exit 1
+ fi
+ if [ "$pfxlen" = "" ]; then
+ ABCMaskLen $ipaddr
+ pfxlen=$?
+ fi
+ pfx="$ipaddr/$pfxlen"
+fi
+
+if [ "$ldev" = "$dev" -a "$ipaddr" != "" ]; then
+ label=
+fi
+
+if [ $deleting -ne 0 ]; then
+ ip addr del $pfx dev $dev $label || exit 1
+ if [ $fwd -eq 0 ]; then RestartRDISC; fi
+ exit 0
+fi
+
+
+if ! ip link set up dev $dev ; then
+ echo "Error: cannot enable interface $dev." 1>&2
+ exit 1
+fi
+if [ "$ipaddr" = "" ]; then exit 0; fi
+
+if ! arping -q -c 2 -w 3 -D -I $dev $ipaddr ; then
+ echo "Error: some host already uses address $ipaddr on $dev." 1>&2
+ exit 1
+fi
+
+if ! ip address add $pfx brd + dev $dev $label; then
+ echo "Error: failed to add $pfx on $dev." 1>&2
+ exit 1
+fi
+
+arping -q -A -c 1 -I $dev $ipaddr
+noarp=$?
+( sleep 2 ;
+ arping -q -U -c 1 -I $dev $ipaddr ) >& /dev/null </dev/null &
+
+ip route add unreachable 224.0.0.0/24 >& /dev/null
+ip route add unreachable 255.255.255.255 >& /dev/null
+if [ `ip link ls $dev | grep -c MULTICAST` -ge 1 ]; then
+ ip route add 224.0.0.0/4 dev $dev scope global >& /dev/null
+fi
+
+if [ $fwd -eq 0 ]; then
+ if [ $noarp -eq 0 ]; then
+ ip ro append default dev $dev metric 30000 scope global
+ elif [ "$peer" != "" ]; then
+ if ping -q -c 2 -w 4 $peer ; then
+ ip ro append default via $peer dev $dev metric 30001
+ fi
+ fi
+ RestartRDISC
+fi
+
+exit 0
diff --git a/iproute2/ip/ip.c b/iproute2/ip/ip.c
new file mode 100644
index 0000000..5162100
--- /dev/null
+++ b/iproute2/ip/ip.c
@@ -0,0 +1,312 @@
+/*
+ * ip.c "ip" utility frontend.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <string.h>
+#include <errno.h>
+
+#include "SNAPSHOT.h"
+#include "utils.h"
+#include "ip_common.h"
+#include "namespace.h"
+#include "color.h"
+
+int preferred_family = AF_UNSPEC;
+int human_readable;
+int use_iec;
+int show_stats;
+int show_details;
+int resolve_hosts;
+int oneline;
+int brief;
+int timestamp;
+const char *_SL_;
+int force;
+int max_flush_loops = 10;
+int batch_mode;
+bool do_all;
+
+struct rtnl_handle rth = { .fd = -1 };
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr,
+"Usage: ip [ OPTIONS ] OBJECT { COMMAND | help }\n"
+" ip [ -force ] -batch filename\n"
+"where OBJECT := { link | address | addrlabel | route | rule | neighbor | ntable |\n"
+" tunnel | tuntap | maddress | mroute | mrule | monitor | xfrm |\n"
+" netns | l2tp | fou | tcp_metrics | token | netconf }\n"
+" OPTIONS := { -V[ersion] | -s[tatistics] | -d[etails] | -r[esolve] |\n"
+" -h[uman-readable] | -iec |\n"
+" -f[amily] { inet | inet6 | ipx | dnet | mpls | bridge | link } |\n"
+" -4 | -6 | -I | -D | -B | -0 |\n"
+" -l[oops] { maximum-addr-flush-attempts } | -br[ief] |\n"
+" -o[neline] | -t[imestamp] | -ts[hort] | -b[atch] [filename] |\n"
+" -rc[vbuf] [size] | -n[etns] name | -a[ll] | -c[olor]}\n");
+ exit(-1);
+}
+
+static int do_help(int argc, char **argv)
+{
+ usage();
+ return 0;
+}
+
+static const struct cmd {
+ const char *cmd;
+ int (*func)(int argc, char **argv);
+} cmds[] = {
+ { "address", do_ipaddr },
+ { "addrlabel", do_ipaddrlabel },
+ { "maddress", do_multiaddr },
+ { "route", do_iproute },
+ { "rule", do_iprule },
+ { "neighbor", do_ipneigh },
+ { "neighbour", do_ipneigh },
+ { "ntable", do_ipntable },
+ { "ntbl", do_ipntable },
+ { "link", do_iplink },
+ { "l2tp", do_ipl2tp },
+ { "fou", do_ipfou },
+ { "tunnel", do_iptunnel },
+ { "tunl", do_iptunnel },
+ { "tuntap", do_iptuntap },
+ { "tap", do_iptuntap },
+ { "token", do_iptoken },
+ { "tcpmetrics", do_tcp_metrics },
+ { "tcp_metrics", do_tcp_metrics },
+ { "monitor", do_ipmonitor },
+ { "xfrm", do_xfrm },
+ { "mroute", do_multiroute },
+ { "mrule", do_multirule },
+ { "netns", do_netns },
+ { "netconf", do_ipnetconf },
+ { "help", do_help },
+ { 0 }
+};
+
+static int do_cmd(const char *argv0, int argc, char **argv)
+{
+ const struct cmd *c;
+
+ for (c = cmds; c->cmd; ++c) {
+ if (matches(argv0, c->cmd) == 0)
+ return -(c->func(argc-1, argv+1));
+ }
+
+ fprintf(stderr, "Object \"%s\" is unknown, try \"ip help\".\n", argv0);
+ return EXIT_FAILURE;
+}
+
+#ifndef ANDROID
+static int batch(const char *name)
+{
+ char *line = NULL;
+ size_t len = 0;
+ int ret = EXIT_SUCCESS;
+ int orig_family = preferred_family;
+
+ batch_mode = 1;
+
+ if (name && strcmp(name, "-") != 0) {
+ if (freopen(name, "r", stdin) == NULL) {
+ fprintf(stderr,
+ "Cannot open file \"%s\" for reading: %s\n",
+ name, strerror(errno));
+ return EXIT_FAILURE;
+ }
+ }
+
+ if (rtnl_open(&rth, 0) < 0) {
+ fprintf(stderr, "Cannot open rtnetlink\n");
+ return EXIT_FAILURE;
+ }
+
+ cmdlineno = 0;
+ while (getcmdline(&line, &len, stdin) != -1) {
+ char *largv[100];
+ int largc;
+
+ preferred_family = orig_family;
+
+ largc = makeargs(line, largv, 100);
+ if (largc == 0)
+ continue; /* blank line */
+
+ if (do_cmd(largv[0], largc, largv)) {
+ fprintf(stderr, "Command failed %s:%d\n",
+ name, cmdlineno);
+ ret = EXIT_FAILURE;
+ if (!force)
+ break;
+ }
+ }
+ if (line)
+ free(line);
+
+ rtnl_close(&rth);
+ return ret;
+}
+#endif
+
+
+int main(int argc, char **argv)
+{
+ char *basename;
+#ifndef ANDROID
+ char *batch_file = NULL;
+#endif
+
+ basename = strrchr(argv[0], '/');
+ if (basename == NULL)
+ basename = argv[0];
+ else
+ basename++;
+
+ while (argc > 1) {
+ char *opt = argv[1];
+
+ if (strcmp(opt, "--") == 0) {
+ argc--; argv++;
+ break;
+ }
+ if (opt[0] != '-')
+ break;
+ if (opt[1] == '-')
+ opt++;
+ if (matches(opt, "-loops") == 0) {
+ argc--;
+ argv++;
+ if (argc <= 1)
+ usage();
+ max_flush_loops = atoi(argv[1]);
+ } else if (matches(opt, "-family") == 0) {
+ argc--;
+ argv++;
+ if (argc <= 1)
+ usage();
+ if (strcmp(argv[1], "help") == 0)
+ usage();
+ else
+ preferred_family = read_family(argv[1]);
+ if (preferred_family == AF_UNSPEC)
+ invarg("invalid protocol family", argv[1]);
+ } else if (strcmp(opt, "-4") == 0) {
+ preferred_family = AF_INET;
+ } else if (strcmp(opt, "-6") == 0) {
+ preferred_family = AF_INET6;
+ } else if (strcmp(opt, "-0") == 0) {
+ preferred_family = AF_PACKET;
+ } else if (strcmp(opt, "-I") == 0) {
+ preferred_family = AF_IPX;
+ } else if (strcmp(opt, "-D") == 0) {
+ preferred_family = AF_DECnet;
+ } else if (strcmp(opt, "-M") == 0) {
+ preferred_family = AF_MPLS;
+ } else if (strcmp(opt, "-B") == 0) {
+ preferred_family = AF_BRIDGE;
+ } else if (matches(opt, "-human") == 0 ||
+ matches(opt, "-human-readable") == 0) {
+ ++human_readable;
+ } else if (matches(opt, "-iec") == 0) {
+ ++use_iec;
+ } else if (matches(opt, "-stats") == 0 ||
+ matches(opt, "-statistics") == 0) {
+ ++show_stats;
+ } else if (matches(opt, "-details") == 0) {
+ ++show_details;
+ } else if (matches(opt, "-resolve") == 0) {
+ ++resolve_hosts;
+ } else if (matches(opt, "-oneline") == 0) {
+ ++oneline;
+ } else if (matches(opt, "-timestamp") == 0) {
+ ++timestamp;
+ } else if (matches(opt, "-tshort") == 0) {
+ ++timestamp;
+ ++timestamp_short;
+#if 0
+ } else if (matches(opt, "-numeric") == 0) {
+ rtnl_names_numeric++;
+#endif
+ } else if (matches(opt, "-Version") == 0) {
+ printf("ip utility, iproute2-ss%s\n", SNAPSHOT);
+ exit(0);
+ } else if (matches(opt, "-force") == 0) {
+ ++force;
+#ifndef ANDROID
+ } else if (matches(opt, "-batch") == 0) {
+ argc--;
+ argv++;
+ if (argc <= 1)
+ usage();
+ batch_file = argv[1];
+#endif
+ } else if (matches(opt, "-brief") == 0) {
+ ++brief;
+ } else if (matches(opt, "-rcvbuf") == 0) {
+ unsigned int size;
+
+ argc--;
+ argv++;
+ if (argc <= 1)
+ usage();
+ if (get_unsigned(&size, argv[1], 0)) {
+ fprintf(stderr, "Invalid rcvbuf size '%s'\n",
+ argv[1]);
+ exit(-1);
+ }
+ rcvbuf = size;
+ } else if (matches(opt, "-color") == 0) {
+ enable_color();
+ } else if (matches(opt, "-help") == 0) {
+ usage();
+ } else if (matches(opt, "-netns") == 0) {
+ NEXT_ARG();
+ if (netns_switch(argv[1]))
+ exit(-1);
+ } else if (matches(opt, "-all") == 0) {
+ do_all = true;
+ } else {
+ fprintf(stderr,
+ "Option \"%s\" is unknown, try \"ip -help\".\n",
+ opt);
+ exit(-1);
+ }
+ argc--; argv++;
+ }
+
+ _SL_ = oneline ? "\\" : "\n";
+
+#ifndef ANDROID
+ if (batch_file)
+ return batch(batch_file);
+#endif
+
+ if (rtnl_open(&rth, 0) < 0)
+ exit(1);
+
+ if (strlen(basename) > 2)
+ return do_cmd(basename+2, argc, argv);
+
+ if (argc > 1)
+ return do_cmd(argv[1], argc-1, argv+1);
+
+ rtnl_close(&rth);
+ usage();
+}
diff --git a/iproute2/ip/ip6tunnel.c b/iproute2/ip/ip6tunnel.c
new file mode 100644
index 0000000..7a3cd04
--- /dev/null
+++ b/iproute2/ip/ip6tunnel.c
@@ -0,0 +1,478 @@
+/*
+ * Copyright (C)2006 USAGI/WIDE Project
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses>.
+ */
+/*
+ * Author:
+ * Masahide NAKAMURA @USAGI
+ */
+
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+#include <sys/ioctl.h>
+#include <linux/ip.h>
+#include <linux/if.h>
+#include <linux/if_arp.h>
+#include <linux/if_tunnel.h>
+#include <linux/ip6_tunnel.h>
+
+#include "utils.h"
+#include "tunnel.h"
+#include "ip_common.h"
+
+#define IP6_FLOWINFO_TCLASS htonl(0x0FF00000)
+#define IP6_FLOWINFO_FLOWLABEL htonl(0x000FFFFF)
+
+#define DEFAULT_TNL_HOP_LIMIT (64)
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: ip -f inet6 tunnel { add | change | del | show } [ NAME ]\n");
+ fprintf(stderr, " [ mode { ip6ip6 | ipip6 | ip6gre | vti6 | any } ]\n");
+ fprintf(stderr, " [ remote ADDR local ADDR ] [ dev PHYS_DEV ]\n");
+ fprintf(stderr, " [ encaplimit ELIM ]\n");
+ fprintf(stderr ," [ hoplimit TTL ] [ tclass TCLASS ] [ flowlabel FLOWLABEL ]\n");
+ fprintf(stderr, " [ dscp inherit ]\n");
+ fprintf(stderr, " [ [i|o]seq ] [ [i|o]key KEY ] [ [i|o]csum ]\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "Where: NAME := STRING\n");
+ fprintf(stderr, " ADDR := IPV6_ADDRESS\n");
+ fprintf(stderr, " ELIM := { none | 0..255 }(default=%d)\n",
+ IPV6_DEFAULT_TNL_ENCAP_LIMIT);
+ fprintf(stderr, " TTL := 0..255 (default=%d)\n",
+ DEFAULT_TNL_HOP_LIMIT);
+ fprintf(stderr, " TCLASS := { 0x0..0xff | inherit }\n");
+ fprintf(stderr, " FLOWLABEL := { 0x0..0xfffff | inherit }\n");
+ fprintf(stderr, " KEY := { DOTTED_QUAD | NUMBER }\n");
+ exit(-1);
+}
+
+static void print_tunnel(struct ip6_tnl_parm2 *p)
+{
+ char s1[1024];
+ char s2[1024];
+
+ /* Do not use format_host() for local addr,
+ * symbolic name will not be useful.
+ */
+ printf("%s: %s/ipv6 remote %s local %s",
+ p->name,
+ tnl_strproto(p->proto),
+ format_host(AF_INET6, 16, &p->raddr, s1, sizeof(s1)),
+ rt_addr_n2a(AF_INET6, 16, &p->laddr, s2, sizeof(s2)));
+ if (p->link) {
+ const char *n = ll_index_to_name(p->link);
+ if (n)
+ printf(" dev %s", n);
+ }
+
+ if (p->flags & IP6_TNL_F_IGN_ENCAP_LIMIT)
+ printf(" encaplimit none");
+ else
+ printf(" encaplimit %u", p->encap_limit);
+
+ printf(" hoplimit %u", p->hop_limit);
+
+ if (p->flags & IP6_TNL_F_USE_ORIG_TCLASS)
+ printf(" tclass inherit");
+ else {
+ __u32 val = ntohl(p->flowinfo & IP6_FLOWINFO_TCLASS);
+ printf(" tclass 0x%02x", (__u8)(val >> 20));
+ }
+
+ if (p->flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)
+ printf(" flowlabel inherit");
+ else
+ printf(" flowlabel 0x%05x", ntohl(p->flowinfo & IP6_FLOWINFO_FLOWLABEL));
+
+ printf(" (flowinfo 0x%08x)", ntohl(p->flowinfo));
+
+ if (p->flags & IP6_TNL_F_RCV_DSCP_COPY)
+ printf(" dscp inherit");
+
+ if (p->proto == IPPROTO_GRE) {
+ if ((p->i_flags & GRE_KEY) && (p->o_flags & GRE_KEY) && p->o_key == p->i_key)
+ printf(" key %u", ntohl(p->i_key));
+ else if ((p->i_flags | p->o_flags) & GRE_KEY) {
+ if (p->i_flags & GRE_KEY)
+ printf(" ikey %u", ntohl(p->i_key));
+ if (p->o_flags & GRE_KEY)
+ printf(" okey %u", ntohl(p->o_key));
+ }
+
+ if (p->i_flags & GRE_SEQ)
+ printf("%s Drop packets out of sequence.", _SL_);
+ if (p->i_flags & GRE_CSUM)
+ printf("%s Checksum in received packet is required.", _SL_);
+ if (p->o_flags & GRE_SEQ)
+ printf("%s Sequence packets on output.", _SL_);
+ if (p->o_flags & GRE_CSUM)
+ printf("%s Checksum output packets.", _SL_);
+ }
+}
+
+static int parse_args(int argc, char **argv, int cmd, struct ip6_tnl_parm2 *p)
+{
+ int count = 0;
+ char medium[IFNAMSIZ];
+
+ memset(medium, 0, sizeof(medium));
+
+ while (argc > 0) {
+ if (strcmp(*argv, "mode") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "ipv6/ipv6") == 0 ||
+ strcmp(*argv, "ip6ip6") == 0)
+ p->proto = IPPROTO_IPV6;
+ else if (strcmp(*argv, "vti6") == 0) {
+ p->proto = IPPROTO_IPV6;
+ p->i_flags |= VTI_ISVTI;
+ } else if (strcmp(*argv, "ip/ipv6") == 0 ||
+ strcmp(*argv, "ipv4/ipv6") == 0 ||
+ strcmp(*argv, "ipip6") == 0 ||
+ strcmp(*argv, "ip4ip6") == 0)
+ p->proto = IPPROTO_IPIP;
+ else if (strcmp(*argv, "ip6gre") == 0 ||
+ strcmp(*argv, "gre/ipv6") == 0)
+ p->proto = IPPROTO_GRE;
+ else if (strcmp(*argv, "any/ipv6") == 0 ||
+ strcmp(*argv, "any") == 0)
+ p->proto = 0;
+ else {
+ fprintf(stderr,"Unknown tunnel mode \"%s\"\n", *argv);
+ exit(-1);
+ }
+ } else if (strcmp(*argv, "remote") == 0) {
+ inet_prefix raddr;
+ NEXT_ARG();
+ get_prefix(&raddr, *argv, preferred_family);
+ if (raddr.family == AF_UNSPEC)
+ invarg("\"remote\" address family is AF_UNSPEC", *argv);
+ memcpy(&p->raddr, &raddr.data, sizeof(p->raddr));
+ } else if (strcmp(*argv, "local") == 0) {
+ inet_prefix laddr;
+ NEXT_ARG();
+ get_prefix(&laddr, *argv, preferred_family);
+ if (laddr.family == AF_UNSPEC)
+ invarg("\"local\" address family is AF_UNSPEC", *argv);
+ memcpy(&p->laddr, &laddr.data, sizeof(p->laddr));
+ } else if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ strncpy(medium, *argv, IFNAMSIZ - 1);
+ } else if (strcmp(*argv, "encaplimit") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "none") == 0) {
+ p->flags |= IP6_TNL_F_IGN_ENCAP_LIMIT;
+ } else {
+ __u8 uval;
+ if (get_u8(&uval, *argv, 0) < -1)
+ invarg("invalid ELIM", *argv);
+ p->encap_limit = uval;
+ p->flags &= ~IP6_TNL_F_IGN_ENCAP_LIMIT;
+ }
+ } else if (strcmp(*argv, "hoplimit") == 0 ||
+ strcmp(*argv, "ttl") == 0 ||
+ strcmp(*argv, "hlim") == 0) {
+ __u8 uval;
+ NEXT_ARG();
+ if (get_u8(&uval, *argv, 0))
+ invarg("invalid TTL", *argv);
+ p->hop_limit = uval;
+ } else if (strcmp(*argv, "tclass") == 0 ||
+ strcmp(*argv, "tc") == 0 ||
+ strcmp(*argv, "tos") == 0 ||
+ matches(*argv, "dsfield") == 0) {
+ __u8 uval;
+ NEXT_ARG();
+ p->flowinfo &= ~IP6_FLOWINFO_TCLASS;
+ if (strcmp(*argv, "inherit") == 0)
+ p->flags |= IP6_TNL_F_USE_ORIG_TCLASS;
+ else {
+ if (get_u8(&uval, *argv, 16))
+ invarg("invalid TClass", *argv);
+ p->flowinfo |= htonl((__u32)uval << 20) & IP6_FLOWINFO_TCLASS;
+ p->flags &= ~IP6_TNL_F_USE_ORIG_TCLASS;
+ }
+ } else if (strcmp(*argv, "flowlabel") == 0 ||
+ strcmp(*argv, "fl") == 0) {
+ __u32 uval;
+ NEXT_ARG();
+ p->flowinfo &= ~IP6_FLOWINFO_FLOWLABEL;
+ if (strcmp(*argv, "inherit") == 0)
+ p->flags |= IP6_TNL_F_USE_ORIG_FLOWLABEL;
+ else {
+ if (get_u32(&uval, *argv, 16))
+ invarg("invalid Flowlabel", *argv);
+ if (uval > 0xFFFFF)
+ invarg("invalid Flowlabel", *argv);
+ p->flowinfo |= htonl(uval) & IP6_FLOWINFO_FLOWLABEL;
+ p->flags &= ~IP6_TNL_F_USE_ORIG_FLOWLABEL;
+ }
+ } else if (strcmp(*argv, "dscp") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "inherit") != 0)
+ invarg("not inherit", *argv);
+ p->flags |= IP6_TNL_F_RCV_DSCP_COPY;
+ } else if (strcmp(*argv, "key") == 0) {
+ NEXT_ARG();
+ p->i_flags |= GRE_KEY;
+ p->o_flags |= GRE_KEY;
+ p->i_key = p->o_key = tnl_parse_key("key", *argv);
+ } else if (strcmp(*argv, "ikey") == 0) {
+ NEXT_ARG();
+ p->i_flags |= GRE_KEY;
+ p->i_key = tnl_parse_key("ikey", *argv);
+ } else if (strcmp(*argv, "okey") == 0) {
+ NEXT_ARG();
+ p->o_flags |= GRE_KEY;
+ p->o_key = tnl_parse_key("okey", *argv);
+ } else if (strcmp(*argv, "seq") == 0) {
+ p->i_flags |= GRE_SEQ;
+ p->o_flags |= GRE_SEQ;
+ } else if (strcmp(*argv, "iseq") == 0) {
+ p->i_flags |= GRE_SEQ;
+ } else if (strcmp(*argv, "oseq") == 0) {
+ p->o_flags |= GRE_SEQ;
+ } else if (strcmp(*argv, "csum") == 0) {
+ p->i_flags |= GRE_CSUM;
+ p->o_flags |= GRE_CSUM;
+ } else if (strcmp(*argv, "icsum") == 0) {
+ p->i_flags |= GRE_CSUM;
+ } else if (strcmp(*argv, "ocsum") == 0) {
+ p->o_flags |= GRE_CSUM;
+ } else {
+ if (strcmp(*argv, "name") == 0) {
+ NEXT_ARG();
+ } else if (matches(*argv, "help") == 0)
+ usage();
+ if (p->name[0])
+ duparg2("name", *argv);
+ strncpy(p->name, *argv, IFNAMSIZ - 1);
+ if (cmd == SIOCCHGTUNNEL && count == 0) {
+ struct ip6_tnl_parm2 old_p;
+ memset(&old_p, 0, sizeof(old_p));
+ if (tnl_get_ioctl(*argv, &old_p))
+ return -1;
+ *p = old_p;
+ }
+ }
+ count++;
+ argc--; argv++;
+ }
+ if (medium[0]) {
+ p->link = ll_name_to_index(medium);
+ if (p->link == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", medium);
+ return -1;
+ }
+ }
+ return 0;
+}
+
+static void ip6_tnl_parm_init(struct ip6_tnl_parm2 *p, int apply_default)
+{
+ memset(p, 0, sizeof(*p));
+ p->proto = IPPROTO_IPV6;
+ if (apply_default) {
+ p->hop_limit = DEFAULT_TNL_HOP_LIMIT;
+ p->encap_limit = IPV6_DEFAULT_TNL_ENCAP_LIMIT;
+ }
+}
+
+/*
+ * @p1: user specified parameter
+ * @p2: database entry
+ */
+static int ip6_tnl_parm_match(const struct ip6_tnl_parm2 *p1,
+ const struct ip6_tnl_parm2 *p2)
+{
+ return ((!p1->link || p1->link == p2->link) &&
+ (!p1->name[0] || strcmp(p1->name, p2->name) == 0) &&
+ (memcmp(&p1->laddr, &in6addr_any, sizeof(p1->laddr)) == 0 ||
+ memcmp(&p1->laddr, &p2->laddr, sizeof(p1->laddr)) == 0) &&
+ (memcmp(&p1->raddr, &in6addr_any, sizeof(p1->raddr)) == 0 ||
+ memcmp(&p1->raddr, &p2->raddr, sizeof(p1->raddr)) == 0) &&
+ (!p1->proto || !p2->proto || p1->proto == p2->proto) &&
+ (!p1->encap_limit || p1->encap_limit == p2->encap_limit) &&
+ (!p1->hop_limit || p1->hop_limit == p2->hop_limit) &&
+ (!(p1->flowinfo & IP6_FLOWINFO_TCLASS) ||
+ !((p1->flowinfo ^ p2->flowinfo) & IP6_FLOWINFO_TCLASS)) &&
+ (!(p1->flowinfo & IP6_FLOWINFO_FLOWLABEL) ||
+ !((p1->flowinfo ^ p2->flowinfo) & IP6_FLOWINFO_FLOWLABEL)) &&
+ (!p1->flags || (p1->flags & p2->flags)));
+}
+
+static int do_tunnels_list(struct ip6_tnl_parm2 *p)
+{
+ char buf[512];
+ int err = -1;
+ FILE *fp = fopen("/proc/net/dev", "r");
+ if (fp == NULL) {
+ perror("fopen");
+ return -1;
+ }
+
+ /* skip two lines at the begenning of the file */
+ if (!fgets(buf, sizeof(buf), fp) ||
+ !fgets(buf, sizeof(buf), fp)) {
+ fprintf(stderr, "/proc/net/dev read error\n");
+ goto end;
+ }
+
+ while (fgets(buf, sizeof(buf), fp) != NULL) {
+ char name[IFNAMSIZ];
+ int index, type;
+ struct ip6_tnl_parm2 p1;
+ char *ptr;
+
+ buf[sizeof(buf) - 1] = '\0';
+ if ((ptr = strchr(buf, ':')) == NULL ||
+ (*ptr++ = 0, sscanf(buf, "%s", name) != 1)) {
+ fprintf(stderr, "Wrong format for /proc/net/dev. Giving up.\n");
+ goto end;
+ }
+ if (p->name[0] && strcmp(p->name, name))
+ continue;
+ index = ll_name_to_index(name);
+ if (index == 0)
+ continue;
+ type = ll_index_to_type(index);
+ if (type == -1) {
+ fprintf(stderr, "Failed to get type of \"%s\"\n", name);
+ continue;
+ }
+ if (type != ARPHRD_TUNNEL6 && type != ARPHRD_IP6GRE)
+ continue;
+ memset(&p1, 0, sizeof(p1));
+ ip6_tnl_parm_init(&p1, 0);
+ if (type == ARPHRD_IP6GRE)
+ p1.proto = IPPROTO_GRE;
+ strcpy(p1.name, name);
+ p1.link = ll_name_to_index(p1.name);
+ if (p1.link == 0)
+ continue;
+ if (tnl_get_ioctl(p1.name, &p1))
+ continue;
+ if (!ip6_tnl_parm_match(p, &p1))
+ continue;
+ print_tunnel(&p1);
+ if (show_stats)
+ tnl_print_stats(ptr);
+ printf("\n");
+ }
+ err = 0;
+ end:
+ fclose(fp);
+ return err;
+}
+
+static int do_show(int argc, char **argv)
+{
+ struct ip6_tnl_parm2 p;
+
+ ll_init_map(&rth);
+ ip6_tnl_parm_init(&p, 0);
+ p.proto = 0; /* default to any */
+
+ if (parse_args(argc, argv, SIOCGETTUNNEL, &p) < 0)
+ return -1;
+
+ if (!p.name[0] || show_stats)
+ do_tunnels_list(&p);
+ else {
+ if (tnl_get_ioctl(p.name, &p))
+ return -1;
+ print_tunnel(&p);
+ printf("\n");
+ }
+
+ return 0;
+}
+
+static int do_add(int cmd, int argc, char **argv)
+{
+ struct ip6_tnl_parm2 p;
+ const char *basedev = "ip6tnl0";
+
+ ip6_tnl_parm_init(&p, 1);
+
+ if (parse_args(argc, argv, cmd, &p) < 0)
+ return -1;
+
+ if (p.proto == IPPROTO_GRE)
+ basedev = "ip6gre0";
+ else if (p.i_flags & VTI_ISVTI)
+ basedev = "ip6_vti0";
+
+ return tnl_add_ioctl(cmd, basedev, p.name, &p);
+}
+
+static int do_del(int argc, char **argv)
+{
+ struct ip6_tnl_parm2 p;
+ const char *basedev = "ip6tnl0";
+
+ ip6_tnl_parm_init(&p, 1);
+
+ if (parse_args(argc, argv, SIOCDELTUNNEL, &p) < 0)
+ return -1;
+
+ if (p.proto == IPPROTO_GRE)
+ basedev = "ip6gre0";
+ else if (p.i_flags & VTI_ISVTI)
+ basedev = "ip6_vti0";
+
+ return tnl_del_ioctl(basedev, p.name, &p);
+}
+
+int do_ip6tunnel(int argc, char **argv)
+{
+ switch (preferred_family) {
+ case AF_UNSPEC:
+ preferred_family = AF_INET6;
+ break;
+ case AF_INET6:
+ break;
+ default:
+ fprintf(stderr, "Unsupported protocol family: %d\n", preferred_family);
+ exit(-1);
+ }
+
+ if (argc > 0) {
+ if (matches(*argv, "add") == 0)
+ return do_add(SIOCADDTUNNEL, argc - 1, argv + 1);
+ if (matches(*argv, "change") == 0)
+ return do_add(SIOCCHGTUNNEL, argc - 1, argv + 1);
+ if (matches(*argv, "delete") == 0)
+ return do_del(argc - 1, argv + 1);
+ if (matches(*argv, "show") == 0 ||
+ matches(*argv, "lst") == 0 ||
+ matches(*argv, "list") == 0)
+ return do_show(argc - 1, argv + 1);
+ if (matches(*argv, "help") == 0)
+ usage();
+ } else
+ return do_show(0, NULL);
+
+ fprintf(stderr, "Command \"%s\" is unknown, try \"ip -f inet6 tunnel help\".\n", *argv);
+ exit(-1);
+}
diff --git a/iproute2/ip/ip_common.h b/iproute2/ip/ip_common.h
new file mode 100644
index 0000000..9a846df
--- /dev/null
+++ b/iproute2/ip/ip_common.h
@@ -0,0 +1,92 @@
+int get_operstate(const char *name);
+int print_linkinfo(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg);
+int print_linkinfo_brief(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg);
+int print_addrinfo(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg);
+int print_addrlabel(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg);
+int print_neigh(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg);
+int ipaddr_list_link(int argc, char **argv);
+void ipaddr_get_vf_rate(int, int *, int *, int);
+void iplink_usage(void) __attribute__((noreturn));
+
+void iproute_reset_filter(int ifindex);
+void ipmroute_reset_filter(int ifindex);
+void ipaddr_reset_filter(int oneline, int ifindex);
+void ipneigh_reset_filter(int ifindex);
+void ipnetconf_reset_filter(int ifindex);
+
+int print_route(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg);
+int print_mroute(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg);
+int print_prefix(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg);
+int print_rule(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg);
+int print_netconf(const struct sockaddr_nl *who,
+ struct rtnl_ctrl_data *ctrl,
+ struct nlmsghdr *n, void *arg);
+void netns_map_init(void);
+int print_nsid(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg);
+int do_ipaddr(int argc, char **argv);
+int do_ipaddrlabel(int argc, char **argv);
+int do_iproute(int argc, char **argv);
+int do_iprule(int argc, char **argv);
+int do_ipneigh(int argc, char **argv);
+int do_ipntable(int argc, char **argv);
+int do_iptunnel(int argc, char **argv);
+int do_ip6tunnel(int argc, char **argv);
+int do_iptuntap(int argc, char **argv);
+int do_iplink(int argc, char **argv);
+int do_ipmonitor(int argc, char **argv);
+int do_multiaddr(int argc, char **argv);
+int do_multiroute(int argc, char **argv);
+int do_multirule(int argc, char **argv);
+int do_netns(int argc, char **argv);
+int do_xfrm(int argc, char **argv);
+int do_ipl2tp(int argc, char **argv);
+int do_ipfou(int argc, char **argv);
+int do_tcp_metrics(int argc, char **argv);
+int do_ipnetconf(int argc, char **argv);
+int do_iptoken(int argc, char **argv);
+int iplink_get(unsigned int flags, char *name, __u32 filt_mask);
+
+static inline int rtm_get_table(struct rtmsg *r, struct rtattr **tb)
+{
+ __u32 table = r->rtm_table;
+ if (tb[RTA_TABLE])
+ table = rta_getattr_u32(tb[RTA_TABLE]);
+ return table;
+}
+
+extern struct rtnl_handle rth;
+
+#include <stdbool.h>
+
+struct link_util
+{
+ struct link_util *next;
+ const char *id;
+ int maxattr;
+ int (*parse_opt)(struct link_util *, int, char **,
+ struct nlmsghdr *);
+ void (*print_opt)(struct link_util *, FILE *,
+ struct rtattr *[]);
+ void (*print_xstats)(struct link_util *, FILE *,
+ struct rtattr *);
+ void (*print_help)(struct link_util *, int, char **,
+ FILE *);
+ bool slave;
+};
+
+struct link_util *get_link_kind(const char *kind);
+struct link_util *get_link_slave_kind(const char *slave_kind);
+
+#ifndef INFINITY_LIFE_TIME
+#define INFINITY_LIFE_TIME 0xFFFFFFFFU
+#endif
diff --git a/iproute2/ip/ipaddress.c b/iproute2/ip/ipaddress.c
new file mode 100644
index 0000000..9d254d2
--- /dev/null
+++ b/iproute2/ip/ipaddress.c
@@ -0,0 +1,1997 @@
+/*
+ * ipaddress.c "ip address".
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <inttypes.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <errno.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <fnmatch.h>
+
+#include <linux/netdevice.h>
+#include <linux/if_arp.h>
+#include <linux/sockios.h>
+#include <linux/net_namespace.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ll_map.h"
+#include "ip_common.h"
+#include "color.h"
+
+enum {
+ IPADD_LIST,
+ IPADD_FLUSH,
+ IPADD_SAVE,
+};
+
+static struct
+{
+ int ifindex;
+ int family;
+ int oneline;
+ int showqueue;
+ inet_prefix pfx;
+ int scope, scopemask;
+ int flags, flagmask;
+ int up;
+ char *label;
+ int flushed;
+ char *flushb;
+ int flushp;
+ int flushe;
+ int group;
+ int master;
+ char *kind;
+} filter;
+
+static int do_link;
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ if (do_link) {
+ iplink_usage();
+ }
+ fprintf(stderr, "Usage: ip address {add|change|replace} IFADDR dev IFNAME [ LIFETIME ]\n");
+ fprintf(stderr, " [ CONFFLAG-LIST ]\n");
+ fprintf(stderr, " ip address del IFADDR dev IFNAME [mngtmpaddr]\n");
+ fprintf(stderr, " ip address {show|save|flush} [ dev IFNAME ] [ scope SCOPE-ID ]\n");
+ fprintf(stderr, " [ to PREFIX ] [ FLAG-LIST ] [ label LABEL ] [up]\n");
+ fprintf(stderr, " ip address {showdump|restore}\n");
+ fprintf(stderr, "IFADDR := PREFIX | ADDR peer PREFIX\n");
+ fprintf(stderr, " [ broadcast ADDR ] [ anycast ADDR ]\n");
+ fprintf(stderr, " [ label IFNAME ] [ scope SCOPE-ID ]\n");
+ fprintf(stderr, "SCOPE-ID := [ host | link | global | NUMBER ]\n");
+ fprintf(stderr, "FLAG-LIST := [ FLAG-LIST ] FLAG\n");
+ fprintf(stderr, "FLAG := [ permanent | dynamic | secondary | primary |\n");
+ fprintf(stderr, " [-]tentative | [-]deprecated | [-]dadfailed | temporary |\n");
+ fprintf(stderr, " CONFFLAG-LIST ]\n");
+ fprintf(stderr, "CONFFLAG-LIST := [ CONFFLAG-LIST ] CONFFLAG\n");
+ fprintf(stderr, "CONFFLAG := [ home | nodad | mngtmpaddr | noprefixroute | autojoin ]\n");
+ fprintf(stderr, "LIFETIME := [ valid_lft LFT ] [ preferred_lft LFT ]\n");
+ fprintf(stderr, "LFT := forever | SECONDS\n");
+
+ exit(-1);
+}
+
+static void print_link_flags(FILE *fp, unsigned flags, unsigned mdown)
+{
+ fprintf(fp, "<");
+ if (flags & IFF_UP && !(flags & IFF_RUNNING))
+ fprintf(fp, "NO-CARRIER%s", flags ? "," : "");
+ flags &= ~IFF_RUNNING;
+#define _PF(f) if (flags&IFF_##f) { \
+ flags &= ~IFF_##f ; \
+ fprintf(fp, #f "%s", flags ? "," : ""); }
+ _PF(LOOPBACK);
+ _PF(BROADCAST);
+ _PF(POINTOPOINT);
+ _PF(MULTICAST);
+ _PF(NOARP);
+ _PF(ALLMULTI);
+ _PF(PROMISC);
+ _PF(MASTER);
+ _PF(SLAVE);
+ _PF(DEBUG);
+ _PF(DYNAMIC);
+ _PF(AUTOMEDIA);
+ _PF(PORTSEL);
+ _PF(NOTRAILERS);
+ _PF(UP);
+ _PF(LOWER_UP);
+ _PF(DORMANT);
+ _PF(ECHO);
+#undef _PF
+ if (flags)
+ fprintf(fp, "%x", flags);
+ if (mdown)
+ fprintf(fp, ",M-DOWN");
+ fprintf(fp, "> ");
+}
+
+static const char *oper_states[] = {
+ "UNKNOWN", "NOTPRESENT", "DOWN", "LOWERLAYERDOWN",
+ "TESTING", "DORMANT", "UP"
+};
+
+static void print_operstate(FILE *f, __u8 state)
+{
+ if (state >= sizeof(oper_states)/sizeof(oper_states[0]))
+ fprintf(f, "state %#x ", state);
+ else {
+ if (brief) {
+ if (strcmp(oper_states[state], "UP") == 0)
+ color_fprintf(f, COLOR_OPERSTATE_UP, "%-14s ", oper_states[state]);
+ else if (strcmp(oper_states[state], "DOWN") == 0)
+ color_fprintf(f, COLOR_OPERSTATE_DOWN, "%-14s ", oper_states[state]);
+ else
+ fprintf(f, "%-14s ", oper_states[state]);
+ } else {
+ fprintf(f, "state ");
+ if (strcmp(oper_states[state], "UP") == 0)
+ color_fprintf(f, COLOR_OPERSTATE_UP, "%s ", oper_states[state]);
+ else if (strcmp(oper_states[state], "DOWN") == 0)
+ color_fprintf(f, COLOR_OPERSTATE_DOWN, "%s ", oper_states[state]);
+ else
+ fprintf(f, "%s ", oper_states[state]);
+ }
+ }
+}
+
+int get_operstate(const char *name)
+{
+ int i;
+
+ for (i = 0; i < sizeof(oper_states)/sizeof(oper_states[0]); i++)
+ if (strcasecmp(name, oper_states[i]) == 0)
+ return i;
+ return -1;
+}
+
+static void print_queuelen(FILE *f, struct rtattr *tb[IFLA_MAX + 1])
+{
+ int qlen;
+
+ if (tb[IFLA_TXQLEN])
+ qlen = *(int *)RTA_DATA(tb[IFLA_TXQLEN]);
+ else {
+ struct ifreq ifr;
+ int s = socket(AF_INET, SOCK_STREAM, 0);
+
+ if (s < 0)
+ return;
+
+ memset(&ifr, 0, sizeof(ifr));
+ strcpy(ifr.ifr_name, rta_getattr_str(tb[IFLA_IFNAME]));
+ if (ioctl(s, SIOCGIFTXQLEN, &ifr) < 0) {
+ fprintf(f, "ioctl(SIOCGIFTXQLEN) failed: %s\n", strerror(errno));
+ close(s);
+ return;
+ }
+ close(s);
+ qlen = ifr.ifr_qlen;
+ }
+ if (qlen)
+ fprintf(f, "qlen %d", qlen);
+}
+
+static const char *link_modes[] = {
+ "DEFAULT", "DORMANT"
+};
+
+static void print_linkmode(FILE *f, struct rtattr *tb)
+{
+ unsigned int mode = rta_getattr_u8(tb);
+
+ if (mode >= sizeof(link_modes) / sizeof(link_modes[0]))
+ fprintf(f, "mode %d ", mode);
+ else
+ fprintf(f, "mode %s ", link_modes[mode]);
+}
+
+static char *parse_link_kind(struct rtattr *tb)
+{
+ struct rtattr *linkinfo[IFLA_INFO_MAX+1];
+
+ parse_rtattr_nested(linkinfo, IFLA_INFO_MAX, tb);
+
+ if (linkinfo[IFLA_INFO_KIND])
+ return RTA_DATA(linkinfo[IFLA_INFO_KIND]);
+
+ return "";
+}
+
+static void print_linktype(FILE *fp, struct rtattr *tb)
+{
+ struct rtattr *linkinfo[IFLA_INFO_MAX+1];
+ struct link_util *lu;
+ struct link_util *slave_lu;
+ char *kind;
+ char *slave_kind;
+
+ parse_rtattr_nested(linkinfo, IFLA_INFO_MAX, tb);
+
+ if (linkinfo[IFLA_INFO_KIND]) {
+ kind = RTA_DATA(linkinfo[IFLA_INFO_KIND]);
+
+ fprintf(fp, "%s", _SL_);
+ fprintf(fp, " %s ", kind);
+
+ lu = get_link_kind(kind);
+ if (lu && lu->print_opt) {
+ struct rtattr *attr[lu->maxattr+1], **data = NULL;
+
+ if (linkinfo[IFLA_INFO_DATA]) {
+ parse_rtattr_nested(attr, lu->maxattr,
+ linkinfo[IFLA_INFO_DATA]);
+ data = attr;
+ }
+ lu->print_opt(lu, fp, data);
+
+ if (linkinfo[IFLA_INFO_XSTATS] && show_stats &&
+ lu->print_xstats)
+ lu->print_xstats(lu, fp, linkinfo[IFLA_INFO_XSTATS]);
+ }
+ }
+
+ if (linkinfo[IFLA_INFO_SLAVE_KIND]) {
+ slave_kind = RTA_DATA(linkinfo[IFLA_INFO_SLAVE_KIND]);
+
+ fprintf(fp, "%s", _SL_);
+ fprintf(fp, " %s_slave ", slave_kind);
+
+ slave_lu = get_link_slave_kind(slave_kind);
+ if (slave_lu && slave_lu->print_opt) {
+ struct rtattr *attr[slave_lu->maxattr+1], **data = NULL;
+
+ if (linkinfo[IFLA_INFO_SLAVE_DATA]) {
+ parse_rtattr_nested(attr, slave_lu->maxattr,
+ linkinfo[IFLA_INFO_SLAVE_DATA]);
+ data = attr;
+ }
+ slave_lu->print_opt(slave_lu, fp, data);
+ }
+ }
+}
+
+static void print_af_spec(FILE *fp, struct rtattr *af_spec_attr)
+{
+ struct rtattr *inet6_attr;
+ struct rtattr *tb[IFLA_INET6_MAX + 1];
+
+ inet6_attr = parse_rtattr_one_nested(AF_INET6, af_spec_attr);
+ if (!inet6_attr)
+ return;
+
+ parse_rtattr_nested(tb, IFLA_INET6_MAX, inet6_attr);
+
+ if (tb[IFLA_INET6_ADDR_GEN_MODE]) {
+ __u8 mode = rta_getattr_u8(tb[IFLA_INET6_ADDR_GEN_MODE]);
+ switch (mode) {
+ case IN6_ADDR_GEN_MODE_EUI64:
+ fprintf(fp, "addrgenmode eui64 ");
+ break;
+ case IN6_ADDR_GEN_MODE_NONE:
+ fprintf(fp, "addrgenmode none ");
+ break;
+ case IN6_ADDR_GEN_MODE_STABLE_PRIVACY:
+ fprintf(fp, "addrgenmode stable_secret ");
+ break;
+ case IN6_ADDR_GEN_MODE_RANDOM:
+ fprintf(fp, "addrgenmode random ");
+ break;
+ default:
+ fprintf(fp, "addrgenmode %#.2hhx ", mode);
+ break;
+ }
+ }
+}
+
+static void print_vf_stats64(FILE *fp, struct rtattr *vfstats);
+
+static void print_vfinfo(FILE *fp, struct rtattr *vfinfo)
+{
+ struct ifla_vf_mac *vf_mac;
+ struct ifla_vf_vlan *vf_vlan;
+ struct ifla_vf_tx_rate *vf_tx_rate;
+ struct ifla_vf_spoofchk *vf_spoofchk;
+ struct ifla_vf_link_state *vf_linkstate;
+ struct rtattr *vf[IFLA_VF_MAX + 1] = {};
+ struct rtattr *tmp;
+ SPRINT_BUF(b1);
+
+ if (vfinfo->rta_type != IFLA_VF_INFO) {
+ fprintf(stderr, "BUG: rta type is %d\n", vfinfo->rta_type);
+ return;
+ }
+
+ parse_rtattr_nested(vf, IFLA_VF_MAX, vfinfo);
+
+ vf_mac = RTA_DATA(vf[IFLA_VF_MAC]);
+ vf_vlan = RTA_DATA(vf[IFLA_VF_VLAN]);
+ vf_tx_rate = RTA_DATA(vf[IFLA_VF_TX_RATE]);
+
+ /* Check if the spoof checking vf info type is supported by
+ * this kernel.
+ */
+ tmp = (struct rtattr *)((char *)vf[IFLA_VF_TX_RATE] +
+ vf[IFLA_VF_TX_RATE]->rta_len);
+
+ if (tmp->rta_type != IFLA_VF_SPOOFCHK)
+ vf_spoofchk = NULL;
+ else
+ vf_spoofchk = RTA_DATA(vf[IFLA_VF_SPOOFCHK]);
+
+ if (vf_spoofchk) {
+ /* Check if the link state vf info type is supported by
+ * this kernel.
+ */
+ tmp = (struct rtattr *)((char *)vf[IFLA_VF_SPOOFCHK] +
+ vf[IFLA_VF_SPOOFCHK]->rta_len);
+
+ if (tmp->rta_type != IFLA_VF_LINK_STATE)
+ vf_linkstate = NULL;
+ else
+ vf_linkstate = RTA_DATA(vf[IFLA_VF_LINK_STATE]);
+ } else
+ vf_linkstate = NULL;
+
+ fprintf(fp, "%s vf %d MAC %s", _SL_, vf_mac->vf,
+ ll_addr_n2a((unsigned char *)&vf_mac->mac,
+ ETH_ALEN, 0, b1, sizeof(b1)));
+ if (vf_vlan->vlan)
+ fprintf(fp, ", vlan %d", vf_vlan->vlan);
+ if (vf_vlan->qos)
+ fprintf(fp, ", qos %d", vf_vlan->qos);
+ if (vf_tx_rate->rate)
+ fprintf(fp, ", tx rate %d (Mbps)", vf_tx_rate->rate);
+
+ if (vf[IFLA_VF_RATE]) {
+ struct ifla_vf_rate *vf_rate = RTA_DATA(vf[IFLA_VF_RATE]);
+
+ if (vf_rate->max_tx_rate)
+ fprintf(fp, ", max_tx_rate %dMbps", vf_rate->max_tx_rate);
+ if (vf_rate->min_tx_rate)
+ fprintf(fp, ", min_tx_rate %dMbps", vf_rate->min_tx_rate);
+ }
+
+ if (vf_spoofchk && vf_spoofchk->setting != -1) {
+ if (vf_spoofchk->setting)
+ fprintf(fp, ", spoof checking on");
+ else
+ fprintf(fp, ", spoof checking off");
+ }
+ if (vf_linkstate) {
+ if (vf_linkstate->link_state == IFLA_VF_LINK_STATE_AUTO)
+ fprintf(fp, ", link-state auto");
+ else if (vf_linkstate->link_state == IFLA_VF_LINK_STATE_ENABLE)
+ fprintf(fp, ", link-state enable");
+ else
+ fprintf(fp, ", link-state disable");
+ }
+ if (vf[IFLA_VF_STATS] && show_stats)
+ print_vf_stats64(fp, vf[IFLA_VF_STATS]);
+}
+
+static void print_num(FILE *fp, unsigned width, uint64_t count)
+{
+ const char *prefix = "kMGTPE";
+ const unsigned int base = use_iec ? 1024 : 1000;
+ uint64_t powi = 1;
+ uint16_t powj = 1;
+ uint8_t precision = 2;
+ char buf[64];
+
+ if (!human_readable || count < base) {
+ fprintf(fp, "%-*"PRIu64" ", width, count);
+ return;
+ }
+
+ /* increase value by a factor of 1000/1024 and print
+ * if result is something a human can read */
+ for(;;) {
+ powi *= base;
+ if (count / base < powi)
+ break;
+
+ if (!prefix[1])
+ break;
+ ++prefix;
+ }
+
+ /* try to guess a good number of digits for precision */
+ for (; precision > 0; precision--) {
+ powj *= 10;
+ if (count / powi < powj)
+ break;
+ }
+
+ snprintf(buf, sizeof(buf), "%.*f%c%s", precision,
+ (double) count / powi, *prefix, use_iec ? "i" : "");
+
+ fprintf(fp, "%-*s ", width, buf);
+}
+
+static void print_vf_stats64(FILE *fp, struct rtattr *vfstats)
+{
+ struct rtattr *vf[IFLA_VF_STATS_MAX + 1] = {};
+
+ if (vfstats->rta_type != IFLA_VF_STATS) {
+ fprintf(stderr, "BUG: rta type is %d\n", vfstats->rta_type);
+ return;
+ }
+
+ parse_rtattr_nested(vf, IFLA_VF_MAX, vfstats);
+
+ /* RX stats */
+ fprintf(fp, "%s", _SL_);
+ fprintf(fp, " RX: bytes packets mcast bcast %s", _SL_);
+ fprintf(fp, " ");
+
+ print_num(fp, 10, *(__u64 *)RTA_DATA(vf[IFLA_VF_STATS_RX_BYTES]));
+ print_num(fp, 8, *(__u64 *)RTA_DATA(vf[IFLA_VF_STATS_RX_PACKETS]));
+ print_num(fp, 7, *(__u64 *)RTA_DATA(vf[IFLA_VF_STATS_MULTICAST]));
+ print_num(fp, 7, *(__u64 *)RTA_DATA(vf[IFLA_VF_STATS_BROADCAST]));
+
+ /* TX stats */
+ fprintf(fp, "%s", _SL_);
+ fprintf(fp, " TX: bytes packets %s", _SL_);
+ fprintf(fp, " ");
+
+ print_num(fp, 10, *(__u64 *)RTA_DATA(vf[IFLA_VF_STATS_TX_BYTES]));
+ print_num(fp, 8, *(__u64 *)RTA_DATA(vf[IFLA_VF_STATS_TX_PACKETS]));
+}
+
+static void print_link_stats64(FILE *fp, const struct rtnl_link_stats64 *s,
+ const struct rtattr *carrier_changes)
+{
+ /* RX stats */
+ fprintf(fp, " RX: bytes packets errors dropped overrun mcast %s%s",
+ s->rx_compressed ? "compressed" : "", _SL_);
+
+ fprintf(fp, " ");
+ print_num(fp, 10, s->rx_bytes);
+ print_num(fp, 8, s->rx_packets);
+ print_num(fp, 7, s->rx_errors);
+ print_num(fp, 7, s->rx_dropped);
+ print_num(fp, 7, s->rx_over_errors);
+ print_num(fp, 7, s->multicast);
+ if (s->rx_compressed)
+ print_num(fp, 7, s->rx_compressed);
+
+ /* RX error stats */
+ if (show_stats > 1) {
+ fprintf(fp, "%s", _SL_);
+ fprintf(fp, " RX errors: length crc frame fifo missed%s", _SL_);
+
+ fprintf(fp, " ");
+ print_num(fp, 8, s->rx_length_errors);
+ print_num(fp, 7, s->rx_crc_errors);
+ print_num(fp, 7, s->rx_frame_errors);
+ print_num(fp, 7, s->rx_fifo_errors);
+ print_num(fp, 7, s->rx_missed_errors);
+ }
+ fprintf(fp, "%s", _SL_);
+
+ /* TX stats */
+ fprintf(fp, " TX: bytes packets errors dropped carrier collsns %s%s",
+ s->tx_compressed ? "compressed" : "", _SL_);
+
+
+ fprintf(fp, " ");
+ print_num(fp, 10, s->tx_bytes);
+ print_num(fp, 8, s->tx_packets);
+ print_num(fp, 7, s->tx_errors);
+ print_num(fp, 7, s->tx_dropped);
+ print_num(fp, 7, s->tx_carrier_errors);
+ print_num(fp, 7, s->collisions);
+ if (s->tx_compressed)
+ print_num(fp, 7, s->tx_compressed);
+
+ /* TX error stats */
+ if (show_stats > 1) {
+ fprintf(fp, "%s", _SL_);
+ fprintf(fp, " TX errors: aborted fifo window heartbeat");
+ if (carrier_changes)
+ fprintf(fp, " transns");
+ fprintf(fp, "%s", _SL_);
+
+ fprintf(fp, " ");
+ print_num(fp, 8, s->tx_aborted_errors);
+ print_num(fp, 7, s->tx_fifo_errors);
+ print_num(fp, 7, s->tx_window_errors);
+ print_num(fp, 7, s->tx_heartbeat_errors);
+ if (carrier_changes)
+ print_num(fp, 7, *(uint32_t*)RTA_DATA(carrier_changes));
+ }
+}
+
+static void print_link_stats32(FILE *fp, const struct rtnl_link_stats *s,
+ const struct rtattr *carrier_changes)
+{
+ /* RX stats */
+ fprintf(fp, " RX: bytes packets errors dropped overrun mcast %s%s",
+ s->rx_compressed ? "compressed" : "", _SL_);
+
+
+ fprintf(fp, " ");
+ print_num(fp, 10, s->rx_bytes);
+ print_num(fp, 8, s->rx_packets);
+ print_num(fp, 7, s->rx_errors);
+ print_num(fp, 7, s->rx_dropped);
+ print_num(fp, 7, s->rx_over_errors);
+ print_num(fp, 7, s->multicast);
+ if (s->rx_compressed)
+ print_num(fp, 7, s->rx_compressed);
+
+ /* RX error stats */
+ if (show_stats > 1) {
+ fprintf(fp, "%s", _SL_);
+ fprintf(fp, " RX errors: length crc frame fifo missed%s", _SL_);
+ fprintf(fp, " ");
+ print_num(fp, 8, s->rx_length_errors);
+ print_num(fp, 7, s->rx_crc_errors);
+ print_num(fp, 7, s->rx_frame_errors);
+ print_num(fp, 7, s->rx_fifo_errors);
+ print_num(fp, 7, s->rx_missed_errors);
+ }
+ fprintf(fp, "%s", _SL_);
+
+ /* TX stats */
+ fprintf(fp, " TX: bytes packets errors dropped carrier collsns %s%s",
+ s->tx_compressed ? "compressed" : "", _SL_);
+
+ fprintf(fp, " ");
+ print_num(fp, 10, s->tx_bytes);
+ print_num(fp, 8, s->tx_packets);
+ print_num(fp, 7, s->tx_errors);
+ print_num(fp, 7, s->tx_dropped);
+ print_num(fp, 7, s->tx_carrier_errors);
+ print_num(fp, 7, s->collisions);
+ if (s->tx_compressed)
+ print_num(fp, 7, s->tx_compressed);
+
+ /* TX error stats */
+ if (show_stats > 1) {
+ fprintf(fp, "%s", _SL_);
+ fprintf(fp, " TX errors: aborted fifo window heartbeat");
+ if (carrier_changes)
+ fprintf(fp, " transns");
+ fprintf(fp, "%s", _SL_);
+
+ fprintf(fp, " ");
+ print_num(fp, 8, s->tx_aborted_errors);
+ print_num(fp, 7, s->tx_fifo_errors);
+ print_num(fp, 7, s->tx_window_errors);
+ print_num(fp, 7, s->tx_heartbeat_errors);
+ if (carrier_changes)
+ print_num(fp, 7, *(uint32_t*)RTA_DATA(carrier_changes));
+ }
+}
+
+static void __print_link_stats(FILE *fp, struct rtattr **tb)
+{
+ if (tb[IFLA_STATS64])
+ print_link_stats64(fp, RTA_DATA(tb[IFLA_STATS64]),
+ tb[IFLA_CARRIER_CHANGES]);
+ else if (tb[IFLA_STATS])
+ print_link_stats32(fp, RTA_DATA(tb[IFLA_STATS]),
+ tb[IFLA_CARRIER_CHANGES]);
+}
+
+static void print_link_stats(FILE *fp, struct nlmsghdr *n)
+{
+ struct ifinfomsg *ifi = NLMSG_DATA(n);
+ struct rtattr * tb[IFLA_MAX+1];
+
+ parse_rtattr(tb, IFLA_MAX, IFLA_RTA(ifi),
+ n->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi)));
+ __print_link_stats(fp, tb);
+ fprintf(fp, "%s", _SL_);
+}
+
+int print_linkinfo_brief(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ struct ifinfomsg *ifi = NLMSG_DATA(n);
+ struct rtattr * tb[IFLA_MAX+1];
+ int len = n->nlmsg_len;
+ char *name;
+ char buf[32] = { 0, };
+ unsigned m_flag = 0;
+
+ if (n->nlmsg_type != RTM_NEWLINK && n->nlmsg_type != RTM_DELLINK)
+ return -1;
+
+ len -= NLMSG_LENGTH(sizeof(*ifi));
+ if (len < 0)
+ return -1;
+
+ if (filter.ifindex && ifi->ifi_index != filter.ifindex)
+ return -1;
+ if (filter.up && !(ifi->ifi_flags&IFF_UP))
+ return -1;
+
+ parse_rtattr(tb, IFLA_MAX, IFLA_RTA(ifi), len);
+ if (tb[IFLA_IFNAME] == NULL) {
+ fprintf(stderr, "BUG: device with ifindex %d has nil ifname\n", ifi->ifi_index);
+ }
+ if (filter.label &&
+ (!filter.family || filter.family == AF_PACKET) &&
+ fnmatch(filter.label, RTA_DATA(tb[IFLA_IFNAME]), 0))
+ return -1;
+
+ if (tb[IFLA_GROUP]) {
+ int group = *(int*)RTA_DATA(tb[IFLA_GROUP]);
+ if (filter.group != -1 && group != filter.group)
+ return -1;
+ }
+
+ if (tb[IFLA_MASTER]) {
+ int master = *(int*)RTA_DATA(tb[IFLA_MASTER]);
+ if (filter.master > 0 && master != filter.master)
+ return -1;
+ }
+ else if (filter.master > 0)
+ return -1;
+
+ if (filter.kind) {
+ if (tb[IFLA_LINKINFO]) {
+ char *kind = parse_link_kind(tb[IFLA_LINKINFO]);
+
+ if (strcmp(kind, filter.kind))
+ return -1;
+ } else {
+ return -1;
+ }
+ }
+
+ if (n->nlmsg_type == RTM_DELLINK)
+ fprintf(fp, "Deleted ");
+
+ name = (char *)(tb[IFLA_IFNAME] ? rta_getattr_str(tb[IFLA_IFNAME]) : "<nil>");
+
+ if (tb[IFLA_LINK]) {
+ SPRINT_BUF(b1);
+ int iflink = *(int*)RTA_DATA(tb[IFLA_LINK]);
+ if (iflink == 0)
+ snprintf(buf, sizeof(buf), "%s@NONE", name);
+ else {
+ snprintf(buf, sizeof(buf),
+ "%s@%s", name, ll_idx_n2a(iflink, b1));
+ m_flag = ll_index_to_flags(iflink);
+ m_flag = !(m_flag & IFF_UP);
+ }
+ } else
+ snprintf(buf, sizeof(buf), "%s", name);
+
+ fprintf(fp, "%-16s ", buf);
+
+ if (tb[IFLA_OPERSTATE])
+ print_operstate(fp, rta_getattr_u8(tb[IFLA_OPERSTATE]));
+
+ if (filter.family == AF_PACKET) {
+ SPRINT_BUF(b1);
+ if (tb[IFLA_ADDRESS]) {
+ color_fprintf(fp, COLOR_MAC, "%s ",
+ ll_addr_n2a(RTA_DATA(tb[IFLA_ADDRESS]),
+ RTA_PAYLOAD(tb[IFLA_ADDRESS]),
+ ifi->ifi_type,
+ b1, sizeof(b1)));
+ }
+ }
+
+ if (filter.family == AF_PACKET)
+ print_link_flags(fp, ifi->ifi_flags, m_flag);
+
+ if (filter.family == AF_PACKET)
+ fprintf(fp, "\n");
+ fflush(fp);
+ return 0;
+}
+
+int print_linkinfo(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ struct ifinfomsg *ifi = NLMSG_DATA(n);
+ struct rtattr * tb[IFLA_MAX+1];
+ int len = n->nlmsg_len;
+ unsigned m_flag = 0;
+
+ if (n->nlmsg_type != RTM_NEWLINK && n->nlmsg_type != RTM_DELLINK)
+ return 0;
+
+ len -= NLMSG_LENGTH(sizeof(*ifi));
+ if (len < 0)
+ return -1;
+
+ if (filter.ifindex && ifi->ifi_index != filter.ifindex)
+ return 0;
+ if (filter.up && !(ifi->ifi_flags&IFF_UP))
+ return 0;
+
+ parse_rtattr(tb, IFLA_MAX, IFLA_RTA(ifi), len);
+ if (tb[IFLA_IFNAME] == NULL) {
+ fprintf(stderr, "BUG: device with ifindex %d has nil ifname\n", ifi->ifi_index);
+ }
+ if (filter.label &&
+ (!filter.family || filter.family == AF_PACKET) &&
+ fnmatch(filter.label, RTA_DATA(tb[IFLA_IFNAME]), 0))
+ return 0;
+
+ if (tb[IFLA_GROUP]) {
+ int group = *(int*)RTA_DATA(tb[IFLA_GROUP]);
+ if (filter.group != -1 && group != filter.group)
+ return -1;
+ }
+
+ if (tb[IFLA_MASTER]) {
+ int master = *(int*)RTA_DATA(tb[IFLA_MASTER]);
+ if (filter.master > 0 && master != filter.master)
+ return -1;
+ }
+ else if (filter.master > 0)
+ return -1;
+
+ if (filter.kind) {
+ if (tb[IFLA_LINKINFO]) {
+ char *kind = parse_link_kind(tb[IFLA_LINKINFO]);
+
+ if (strcmp(kind, filter.kind))
+ return -1;
+ } else {
+ return -1;
+ }
+ }
+
+ if (n->nlmsg_type == RTM_DELLINK)
+ fprintf(fp, "Deleted ");
+
+ fprintf(fp, "%d: ", ifi->ifi_index);
+ color_fprintf(fp, COLOR_IFNAME, "%s",
+ tb[IFLA_IFNAME] ? rta_getattr_str(tb[IFLA_IFNAME]) : "<nil>");
+
+ if (tb[IFLA_LINK]) {
+ SPRINT_BUF(b1);
+ int iflink = *(int*)RTA_DATA(tb[IFLA_LINK]);
+ if (iflink == 0)
+ fprintf(fp, "@NONE: ");
+ else {
+ if (tb[IFLA_LINK_NETNSID])
+ fprintf(fp, "@if%d: ", iflink);
+ else {
+ fprintf(fp, "@%s: ", ll_idx_n2a(iflink, b1));
+ m_flag = ll_index_to_flags(iflink);
+ m_flag = !(m_flag & IFF_UP);
+ }
+ }
+ } else {
+ fprintf(fp, ": ");
+ }
+ print_link_flags(fp, ifi->ifi_flags, m_flag);
+
+ if (tb[IFLA_MTU])
+ fprintf(fp, "mtu %u ", *(int*)RTA_DATA(tb[IFLA_MTU]));
+ if (tb[IFLA_QDISC])
+ fprintf(fp, "qdisc %s ", rta_getattr_str(tb[IFLA_QDISC]));
+ if (tb[IFLA_MASTER]) {
+ SPRINT_BUF(b1);
+ fprintf(fp, "master %s ", ll_idx_n2a(*(int*)RTA_DATA(tb[IFLA_MASTER]), b1));
+ }
+
+ if (tb[IFLA_PHYS_PORT_ID]) {
+ SPRINT_BUF(b1);
+ fprintf(fp, "portid %s ",
+ hexstring_n2a(RTA_DATA(tb[IFLA_PHYS_PORT_ID]),
+ RTA_PAYLOAD(tb[IFLA_PHYS_PORT_ID]),
+ b1, sizeof(b1)));
+ }
+
+ if (tb[IFLA_PHYS_SWITCH_ID]) {
+ SPRINT_BUF(b1);
+ fprintf(fp, "switchid %s ",
+ hexstring_n2a(RTA_DATA(tb[IFLA_PHYS_SWITCH_ID]),
+ RTA_PAYLOAD(tb[IFLA_PHYS_SWITCH_ID]),
+ b1, sizeof(b1)));
+ }
+
+ if (tb[IFLA_OPERSTATE])
+ print_operstate(fp, rta_getattr_u8(tb[IFLA_OPERSTATE]));
+
+ if (do_link && tb[IFLA_LINKMODE])
+ print_linkmode(fp, tb[IFLA_LINKMODE]);
+
+ if (tb[IFLA_GROUP]) {
+ SPRINT_BUF(b1);
+ int group = *(int*)RTA_DATA(tb[IFLA_GROUP]);
+ fprintf(fp, "group %s ", rtnl_group_n2a(group, b1, sizeof(b1)));
+ }
+
+ if (filter.showqueue)
+ print_queuelen(fp, tb);
+
+ if (!filter.family || filter.family == AF_PACKET || show_details) {
+ SPRINT_BUF(b1);
+ fprintf(fp, "%s", _SL_);
+ fprintf(fp, " link/%s ", ll_type_n2a(ifi->ifi_type, b1, sizeof(b1)));
+
+ if (tb[IFLA_ADDRESS]) {
+ color_fprintf(fp, COLOR_MAC, "%s",
+ ll_addr_n2a(RTA_DATA(tb[IFLA_ADDRESS]),
+ RTA_PAYLOAD(tb[IFLA_ADDRESS]),
+ ifi->ifi_type,
+ b1, sizeof(b1)));
+ }
+ if (tb[IFLA_BROADCAST]) {
+ if (ifi->ifi_flags&IFF_POINTOPOINT)
+ fprintf(fp, " peer ");
+ else
+ fprintf(fp, " brd ");
+ fprintf(fp, "%s", ll_addr_n2a(RTA_DATA(tb[IFLA_BROADCAST]),
+ RTA_PAYLOAD(tb[IFLA_BROADCAST]),
+ ifi->ifi_type,
+ b1, sizeof(b1)));
+ }
+ }
+
+ if (tb[IFLA_LINK_NETNSID]) {
+ int id = *(int*)RTA_DATA(tb[IFLA_LINK_NETNSID]);
+
+ if (id >= 0)
+ fprintf(fp, " link-netnsid %d", id);
+ else
+ fprintf(fp, " link-netnsid unknown");
+ }
+
+ if (tb[IFLA_PROTO_DOWN]) {
+ if (rta_getattr_u8(tb[IFLA_PROTO_DOWN]))
+ fprintf(fp, " protodown on ");
+ }
+
+ if (tb[IFLA_PROMISCUITY] && show_details)
+ fprintf(fp, " promiscuity %u ",
+ *(int*)RTA_DATA(tb[IFLA_PROMISCUITY]));
+
+ if (tb[IFLA_LINKINFO] && show_details)
+ print_linktype(fp, tb[IFLA_LINKINFO]);
+
+ if (do_link && tb[IFLA_AF_SPEC] && show_details)
+ print_af_spec(fp, tb[IFLA_AF_SPEC]);
+
+ if ((do_link || show_details) && tb[IFLA_IFALIAS]) {
+ fprintf(fp, "%s alias %s", _SL_,
+ rta_getattr_str(tb[IFLA_IFALIAS]));
+ }
+
+ if (do_link && show_stats) {
+ fprintf(fp, "%s", _SL_);
+ __print_link_stats(fp, tb);
+ }
+
+ if ((do_link || show_details) && tb[IFLA_VFINFO_LIST] && tb[IFLA_NUM_VF]) {
+ struct rtattr *i, *vflist = tb[IFLA_VFINFO_LIST];
+ int rem = RTA_PAYLOAD(vflist);
+ for (i = RTA_DATA(vflist); RTA_OK(i, rem); i = RTA_NEXT(i, rem))
+ print_vfinfo(fp, i);
+ }
+
+ fprintf(fp, "\n");
+ fflush(fp);
+ return 1;
+}
+
+static int flush_update(void)
+{
+
+ /*
+ * Note that the kernel may delete multiple addresses for one
+ * delete request (e.g. if ipv4 address promotion is disabled).
+ * Since a flush operation is really a series of delete requests
+ * its possible that we may request an address delete that has
+ * already been done by the kernel. Therefore, ignore EADDRNOTAVAIL
+ * errors returned from a flush request
+ */
+ if ((rtnl_send_check(&rth, filter.flushb, filter.flushp) < 0) &&
+ (errno != EADDRNOTAVAIL)) {
+ perror("Failed to send flush request");
+ return -1;
+ }
+ filter.flushp = 0;
+ return 0;
+}
+
+static int set_lifetime(unsigned int *lifetime, char *argv)
+{
+ if (strcmp(argv, "forever") == 0)
+ *lifetime = INFINITY_LIFE_TIME;
+ else if (get_u32(lifetime, argv, 0))
+ return -1;
+
+ return 0;
+}
+
+static unsigned int get_ifa_flags(struct ifaddrmsg *ifa,
+ struct rtattr *ifa_flags_attr)
+{
+ return ifa_flags_attr ? rta_getattr_u32(ifa_flags_attr) :
+ ifa->ifa_flags;
+}
+
+int print_addrinfo(const struct sockaddr_nl *who, struct nlmsghdr *n,
+ void *arg)
+{
+ FILE *fp = arg;
+ struct ifaddrmsg *ifa = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ int deprecated = 0;
+ /* Use local copy of ifa_flags to not interfere with filtering code */
+ unsigned int ifa_flags;
+ struct rtattr * rta_tb[IFA_MAX+1];
+ char abuf[256];
+ SPRINT_BUF(b1);
+
+ if (n->nlmsg_type != RTM_NEWADDR && n->nlmsg_type != RTM_DELADDR)
+ return 0;
+ len -= NLMSG_LENGTH(sizeof(*ifa));
+ if (len < 0) {
+ fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+ return -1;
+ }
+
+ if (filter.flushb && n->nlmsg_type != RTM_NEWADDR)
+ return 0;
+
+ parse_rtattr(rta_tb, IFA_MAX, IFA_RTA(ifa),
+ n->nlmsg_len - NLMSG_LENGTH(sizeof(*ifa)));
+
+ ifa_flags = get_ifa_flags(ifa, rta_tb[IFA_FLAGS]);
+
+ if (!rta_tb[IFA_LOCAL])
+ rta_tb[IFA_LOCAL] = rta_tb[IFA_ADDRESS];
+ if (!rta_tb[IFA_ADDRESS])
+ rta_tb[IFA_ADDRESS] = rta_tb[IFA_LOCAL];
+
+ if (filter.ifindex && filter.ifindex != ifa->ifa_index)
+ return 0;
+ if ((filter.scope^ifa->ifa_scope)&filter.scopemask)
+ return 0;
+ if ((filter.flags ^ ifa_flags) & filter.flagmask)
+ return 0;
+ if (filter.label) {
+ SPRINT_BUF(b1);
+ const char *label;
+ if (rta_tb[IFA_LABEL])
+ label = RTA_DATA(rta_tb[IFA_LABEL]);
+ else
+ label = ll_idx_n2a(ifa->ifa_index, b1);
+ if (fnmatch(filter.label, label, 0) != 0)
+ return 0;
+ }
+ if (filter.pfx.family) {
+ if (rta_tb[IFA_LOCAL]) {
+ inet_prefix dst;
+ memset(&dst, 0, sizeof(dst));
+ dst.family = ifa->ifa_family;
+ memcpy(&dst.data, RTA_DATA(rta_tb[IFA_LOCAL]), RTA_PAYLOAD(rta_tb[IFA_LOCAL]));
+ if (inet_addr_match(&dst, &filter.pfx, filter.pfx.bitlen))
+ return 0;
+ }
+ }
+
+ if (filter.family && filter.family != ifa->ifa_family)
+ return 0;
+
+ if (filter.flushb) {
+ struct nlmsghdr *fn;
+ if (NLMSG_ALIGN(filter.flushp) + n->nlmsg_len > filter.flushe) {
+ if (flush_update())
+ return -1;
+ }
+ fn = (struct nlmsghdr*)(filter.flushb + NLMSG_ALIGN(filter.flushp));
+ memcpy(fn, n, n->nlmsg_len);
+ fn->nlmsg_type = RTM_DELADDR;
+ fn->nlmsg_flags = NLM_F_REQUEST;
+ fn->nlmsg_seq = ++rth.seq;
+ filter.flushp = (((char*)fn) + n->nlmsg_len) - filter.flushb;
+ filter.flushed++;
+ if (show_stats < 2)
+ return 0;
+ }
+
+ if (n->nlmsg_type == RTM_DELADDR)
+ fprintf(fp, "Deleted ");
+
+ if (!brief) {
+ if (filter.oneline || filter.flushb)
+ fprintf(fp, "%u: %s", ifa->ifa_index, ll_index_to_name(ifa->ifa_index));
+ if (ifa->ifa_family == AF_INET)
+ fprintf(fp, " inet ");
+ else if (ifa->ifa_family == AF_INET6)
+ fprintf(fp, " inet6 ");
+ else if (ifa->ifa_family == AF_DECnet)
+ fprintf(fp, " dnet ");
+ else if (ifa->ifa_family == AF_IPX)
+ fprintf(fp, " ipx ");
+ else
+ fprintf(fp, " family %d ", ifa->ifa_family);
+ }
+
+ if (rta_tb[IFA_LOCAL]) {
+ if (ifa->ifa_family == AF_INET)
+ color_fprintf(fp, COLOR_INET, "%s", format_host(ifa->ifa_family,
+ RTA_PAYLOAD(rta_tb[IFA_LOCAL]),
+ RTA_DATA(rta_tb[IFA_LOCAL]),
+ abuf, sizeof(abuf)));
+ else if (ifa->ifa_family == AF_INET6)
+ color_fprintf(fp, COLOR_INET6, "%s", format_host(ifa->ifa_family,
+ RTA_PAYLOAD(rta_tb[IFA_LOCAL]),
+ RTA_DATA(rta_tb[IFA_LOCAL]),
+ abuf, sizeof(abuf)));
+ else
+ fprintf(fp, "%s", format_host(ifa->ifa_family,
+ RTA_PAYLOAD(rta_tb[IFA_LOCAL]),
+ RTA_DATA(rta_tb[IFA_LOCAL]),
+ abuf, sizeof(abuf)));
+
+ if (rta_tb[IFA_ADDRESS] == NULL ||
+ memcmp(RTA_DATA(rta_tb[IFA_ADDRESS]), RTA_DATA(rta_tb[IFA_LOCAL]),
+ ifa->ifa_family == AF_INET ? 4 : 16) == 0) {
+ fprintf(fp, "/%d ", ifa->ifa_prefixlen);
+ } else {
+ fprintf(fp, " peer %s/%d ",
+ format_host(ifa->ifa_family,
+ RTA_PAYLOAD(rta_tb[IFA_ADDRESS]),
+ RTA_DATA(rta_tb[IFA_ADDRESS]),
+ abuf, sizeof(abuf)),
+ ifa->ifa_prefixlen);
+ }
+ }
+
+ if (brief)
+ goto brief_exit;
+
+ if (rta_tb[IFA_BROADCAST]) {
+ fprintf(fp, "brd %s ",
+ format_host(ifa->ifa_family,
+ RTA_PAYLOAD(rta_tb[IFA_BROADCAST]),
+ RTA_DATA(rta_tb[IFA_BROADCAST]),
+ abuf, sizeof(abuf)));
+ }
+ if (rta_tb[IFA_ANYCAST]) {
+ fprintf(fp, "any %s ",
+ format_host(ifa->ifa_family,
+ RTA_PAYLOAD(rta_tb[IFA_ANYCAST]),
+ RTA_DATA(rta_tb[IFA_ANYCAST]),
+ abuf, sizeof(abuf)));
+ }
+ fprintf(fp, "scope %s ", rtnl_rtscope_n2a(ifa->ifa_scope, b1, sizeof(b1)));
+ if (ifa_flags & IFA_F_SECONDARY) {
+ ifa_flags &= ~IFA_F_SECONDARY;
+ if (ifa->ifa_family == AF_INET6)
+ fprintf(fp, "temporary ");
+ else
+ fprintf(fp, "secondary ");
+ }
+ if (ifa_flags & IFA_F_TENTATIVE) {
+ ifa_flags &= ~IFA_F_TENTATIVE;
+ fprintf(fp, "tentative ");
+ }
+ if (ifa_flags & IFA_F_DEPRECATED) {
+ ifa_flags &= ~IFA_F_DEPRECATED;
+ deprecated = 1;
+ fprintf(fp, "deprecated ");
+ }
+ if (ifa_flags & IFA_F_HOMEADDRESS) {
+ ifa_flags &= ~IFA_F_HOMEADDRESS;
+ fprintf(fp, "home ");
+ }
+ if (ifa_flags & IFA_F_NODAD) {
+ ifa_flags &= ~IFA_F_NODAD;
+ fprintf(fp, "nodad ");
+ }
+ if (ifa_flags & IFA_F_MANAGETEMPADDR) {
+ ifa_flags &= ~IFA_F_MANAGETEMPADDR;
+ fprintf(fp, "mngtmpaddr ");
+ }
+ if (ifa_flags & IFA_F_NOPREFIXROUTE) {
+ ifa_flags &= ~IFA_F_NOPREFIXROUTE;
+ fprintf(fp, "noprefixroute ");
+ }
+ if (ifa_flags & IFA_F_MCAUTOJOIN) {
+ ifa_flags &= ~IFA_F_MCAUTOJOIN;
+ fprintf(fp, "autojoin ");
+ }
+ if (!(ifa_flags & IFA_F_PERMANENT)) {
+ fprintf(fp, "dynamic ");
+ } else
+ ifa_flags &= ~IFA_F_PERMANENT;
+ if (ifa_flags & IFA_F_DADFAILED) {
+ ifa_flags &= ~IFA_F_DADFAILED;
+ fprintf(fp, "dadfailed ");
+ }
+ if (ifa_flags)
+ fprintf(fp, "flags %02x ", ifa_flags);
+ if (rta_tb[IFA_LABEL])
+ fprintf(fp, "%s", rta_getattr_str(rta_tb[IFA_LABEL]));
+ if (rta_tb[IFA_CACHEINFO]) {
+ struct ifa_cacheinfo *ci = RTA_DATA(rta_tb[IFA_CACHEINFO]);
+ fprintf(fp, "%s", _SL_);
+ fprintf(fp, " valid_lft ");
+ if (ci->ifa_valid == INFINITY_LIFE_TIME)
+ fprintf(fp, "forever");
+ else
+ fprintf(fp, "%usec", ci->ifa_valid);
+ fprintf(fp, " preferred_lft ");
+ if (ci->ifa_prefered == INFINITY_LIFE_TIME)
+ fprintf(fp, "forever");
+ else {
+ if (deprecated)
+ fprintf(fp, "%dsec", ci->ifa_prefered);
+ else
+ fprintf(fp, "%usec", ci->ifa_prefered);
+ }
+ }
+ fprintf(fp, "\n");
+brief_exit:
+ fflush(fp);
+ return 0;
+}
+
+struct nlmsg_list
+{
+ struct nlmsg_list *next;
+ struct nlmsghdr h;
+};
+
+struct nlmsg_chain
+{
+ struct nlmsg_list *head;
+ struct nlmsg_list *tail;
+};
+
+static int print_selected_addrinfo(struct ifinfomsg *ifi,
+ struct nlmsg_list *ainfo, FILE *fp)
+{
+ for ( ;ainfo ; ainfo = ainfo->next) {
+ struct nlmsghdr *n = &ainfo->h;
+ struct ifaddrmsg *ifa = NLMSG_DATA(n);
+
+ if (n->nlmsg_type != RTM_NEWADDR)
+ continue;
+
+ if (n->nlmsg_len < NLMSG_LENGTH(sizeof(ifa)))
+ return -1;
+
+ if (ifa->ifa_index != ifi->ifi_index ||
+ (filter.family && filter.family != ifa->ifa_family))
+ continue;
+
+ if (filter.up && !(ifi->ifi_flags&IFF_UP))
+ continue;
+
+ print_addrinfo(NULL, n, fp);
+ }
+ if (brief) {
+ fprintf(fp, "\n");
+ fflush(fp);
+ }
+ return 0;
+}
+
+
+static int store_nlmsg(const struct sockaddr_nl *who, struct nlmsghdr *n,
+ void *arg)
+{
+ struct nlmsg_chain *lchain = (struct nlmsg_chain *)arg;
+ struct nlmsg_list *h;
+
+ h = malloc(n->nlmsg_len+sizeof(void*));
+ if (h == NULL)
+ return -1;
+
+ memcpy(&h->h, n, n->nlmsg_len);
+ h->next = NULL;
+
+ if (lchain->tail)
+ lchain->tail->next = h;
+ else
+ lchain->head = h;
+ lchain->tail = h;
+
+ ll_remember_index(who, n, NULL);
+ return 0;
+}
+
+static __u32 ipadd_dump_magic = 0x47361222;
+
+static int ipadd_save_prep(void)
+{
+ int ret;
+
+ if (isatty(STDOUT_FILENO)) {
+ fprintf(stderr, "Not sending a binary stream to stdout\n");
+ return -1;
+ }
+
+ ret = write(STDOUT_FILENO, &ipadd_dump_magic, sizeof(ipadd_dump_magic));
+ if (ret != sizeof(ipadd_dump_magic)) {
+ fprintf(stderr, "Can't write magic to dump file\n");
+ return -1;
+ }
+
+ return 0;
+}
+
+static int ipadd_dump_check_magic(void)
+{
+ int ret;
+ __u32 magic = 0;
+
+ if (isatty(STDIN_FILENO)) {
+ fprintf(stderr, "Can't restore address dump from a terminal\n");
+ return -1;
+ }
+
+ ret = fread(&magic, sizeof(magic), 1, stdin);
+ if (magic != ipadd_dump_magic) {
+ fprintf(stderr, "Magic mismatch (%d elems, %x magic)\n", ret, magic);
+ return -1;
+ }
+
+ return 0;
+}
+
+static int save_nlmsg(const struct sockaddr_nl *who, struct nlmsghdr *n,
+ void *arg)
+{
+ int ret;
+
+ ret = write(STDOUT_FILENO, n, n->nlmsg_len);
+ if ((ret > 0) && (ret != n->nlmsg_len)) {
+ fprintf(stderr, "Short write while saving nlmsg\n");
+ ret = -EIO;
+ }
+
+ return ret == n->nlmsg_len ? 0 : ret;
+}
+
+static int show_handler(const struct sockaddr_nl *nl,
+ struct rtnl_ctrl_data *ctrl,
+ struct nlmsghdr *n, void *arg)
+{
+ struct ifaddrmsg *ifa = NLMSG_DATA(n);
+
+ printf("if%d:\n", ifa->ifa_index);
+ print_addrinfo(NULL, n, stdout);
+ return 0;
+}
+
+static int ipaddr_showdump(void)
+{
+ if (ipadd_dump_check_magic())
+ exit(-1);
+
+ exit(rtnl_from_file(stdin, &show_handler, NULL));
+}
+
+static int restore_handler(const struct sockaddr_nl *nl,
+ struct rtnl_ctrl_data *ctrl,
+ struct nlmsghdr *n, void *arg)
+{
+ int ret;
+
+ n->nlmsg_flags |= NLM_F_REQUEST | NLM_F_CREATE | NLM_F_ACK;
+
+ ll_init_map(&rth);
+
+ ret = rtnl_talk(&rth, n, n, sizeof(*n));
+ if ((ret < 0) && (errno == EEXIST))
+ ret = 0;
+
+ return ret;
+}
+
+static int ipaddr_restore(void)
+{
+ if (ipadd_dump_check_magic())
+ exit(-1);
+
+ exit(rtnl_from_file(stdin, &restore_handler, NULL));
+}
+
+static void free_nlmsg_chain(struct nlmsg_chain *info)
+{
+ struct nlmsg_list *l, *n;
+
+ for (l = info->head; l; l = n) {
+ n = l->next;
+ free(l);
+ }
+}
+
+static void ipaddr_filter(struct nlmsg_chain *linfo, struct nlmsg_chain *ainfo)
+{
+ struct nlmsg_list *l, **lp;
+
+ lp = &linfo->head;
+ while ( (l = *lp) != NULL) {
+ int ok = 0;
+ int missing_net_address = 1;
+ struct ifinfomsg *ifi = NLMSG_DATA(&l->h);
+ struct nlmsg_list *a;
+
+ for (a = ainfo->head; a; a = a->next) {
+ struct nlmsghdr *n = &a->h;
+ struct ifaddrmsg *ifa = NLMSG_DATA(n);
+ struct rtattr *tb[IFA_MAX + 1];
+ unsigned int ifa_flags;
+
+ if (ifa->ifa_index != ifi->ifi_index)
+ continue;
+ missing_net_address = 0;
+ if (filter.family && filter.family != ifa->ifa_family)
+ continue;
+ if ((filter.scope^ifa->ifa_scope)&filter.scopemask)
+ continue;
+
+ parse_rtattr(tb, IFA_MAX, IFA_RTA(ifa), IFA_PAYLOAD(n));
+ ifa_flags = get_ifa_flags(ifa, tb[IFA_FLAGS]);
+
+ if ((filter.flags ^ ifa_flags) & filter.flagmask)
+ continue;
+ if (filter.pfx.family || filter.label) {
+ if (!tb[IFA_LOCAL])
+ tb[IFA_LOCAL] = tb[IFA_ADDRESS];
+
+ if (filter.pfx.family && tb[IFA_LOCAL]) {
+ inet_prefix dst;
+ memset(&dst, 0, sizeof(dst));
+ dst.family = ifa->ifa_family;
+ memcpy(&dst.data, RTA_DATA(tb[IFA_LOCAL]), RTA_PAYLOAD(tb[IFA_LOCAL]));
+ if (inet_addr_match(&dst, &filter.pfx, filter.pfx.bitlen))
+ continue;
+ }
+ if (filter.label) {
+ SPRINT_BUF(b1);
+ const char *label;
+ if (tb[IFA_LABEL])
+ label = RTA_DATA(tb[IFA_LABEL]);
+ else
+ label = ll_idx_n2a(ifa->ifa_index, b1);
+ if (fnmatch(filter.label, label, 0) != 0)
+ continue;
+ }
+ }
+
+ ok = 1;
+ break;
+ }
+ if (missing_net_address &&
+ (filter.family == AF_UNSPEC || filter.family == AF_PACKET))
+ ok = 1;
+ if (!ok) {
+ *lp = l->next;
+ free(l);
+ } else
+ lp = &l->next;
+ }
+}
+
+static int ipaddr_flush(void)
+{
+ int round = 0;
+ char flushb[4096-512];
+
+ filter.flushb = flushb;
+ filter.flushp = 0;
+ filter.flushe = sizeof(flushb);
+
+ while ((max_flush_loops == 0) || (round < max_flush_loops)) {
+ if (rtnl_wilddump_request(&rth, filter.family, RTM_GETADDR) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+ filter.flushed = 0;
+ if (rtnl_dump_filter_nc(&rth, print_addrinfo,
+ stdout, NLM_F_DUMP_INTR) < 0) {
+ fprintf(stderr, "Flush terminated\n");
+ exit(1);
+ }
+ if (filter.flushed == 0) {
+ flush_done:
+ if (show_stats) {
+ if (round == 0)
+ printf("Nothing to flush.\n");
+ else
+ printf("*** Flush is complete after %d round%s ***\n", round, round>1?"s":"");
+ }
+ fflush(stdout);
+ return 0;
+ }
+ round++;
+ if (flush_update() < 0)
+ return 1;
+
+ if (show_stats) {
+ printf("\n*** Round %d, deleting %d addresses ***\n", round, filter.flushed);
+ fflush(stdout);
+ }
+
+ /* If we are flushing, and specifying primary, then we
+ * want to flush only a single round. Otherwise, we'll
+ * start flushing secondaries that were promoted to
+ * primaries.
+ */
+ if (!(filter.flags & IFA_F_SECONDARY) && (filter.flagmask & IFA_F_SECONDARY))
+ goto flush_done;
+ }
+ fprintf(stderr, "*** Flush remains incomplete after %d rounds. ***\n", max_flush_loops);
+ fflush(stderr);
+ return 1;
+}
+
+static int ipaddr_list_flush_or_save(int argc, char **argv, int action)
+{
+ struct nlmsg_chain linfo = { NULL, NULL};
+ struct nlmsg_chain ainfo = { NULL, NULL};
+ struct nlmsg_list *l;
+ char *filter_dev = NULL;
+ int no_link = 0;
+
+ ipaddr_reset_filter(oneline, 0);
+ filter.showqueue = 1;
+ filter.family = preferred_family;
+ filter.group = -1;
+
+ if (action == IPADD_FLUSH) {
+ if (argc <= 0) {
+ fprintf(stderr, "Flush requires arguments.\n");
+
+ return -1;
+ }
+ if (filter.family == AF_PACKET) {
+ fprintf(stderr, "Cannot flush link addresses.\n");
+ return -1;
+ }
+ }
+
+ while (argc > 0) {
+ if (strcmp(*argv, "to") == 0) {
+ NEXT_ARG();
+ get_prefix(&filter.pfx, *argv, filter.family);
+ if (filter.family == AF_UNSPEC)
+ filter.family = filter.pfx.family;
+ } else if (strcmp(*argv, "scope") == 0) {
+ unsigned scope = 0;
+ NEXT_ARG();
+ filter.scopemask = -1;
+ if (rtnl_rtscope_a2n(&scope, *argv)) {
+ if (strcmp(*argv, "all") != 0)
+ invarg("invalid \"scope\"\n", *argv);
+ scope = RT_SCOPE_NOWHERE;
+ filter.scopemask = 0;
+ }
+ filter.scope = scope;
+ } else if (strcmp(*argv, "up") == 0) {
+ filter.up = 1;
+ } else if (strcmp(*argv, "dynamic") == 0) {
+ filter.flags &= ~IFA_F_PERMANENT;
+ filter.flagmask |= IFA_F_PERMANENT;
+ } else if (strcmp(*argv, "permanent") == 0) {
+ filter.flags |= IFA_F_PERMANENT;
+ filter.flagmask |= IFA_F_PERMANENT;
+ } else if (strcmp(*argv, "secondary") == 0 ||
+ strcmp(*argv, "temporary") == 0) {
+ filter.flags |= IFA_F_SECONDARY;
+ filter.flagmask |= IFA_F_SECONDARY;
+ } else if (strcmp(*argv, "primary") == 0) {
+ filter.flags &= ~IFA_F_SECONDARY;
+ filter.flagmask |= IFA_F_SECONDARY;
+ } else if (strcmp(*argv, "tentative") == 0) {
+ filter.flags |= IFA_F_TENTATIVE;
+ filter.flagmask |= IFA_F_TENTATIVE;
+ } else if (strcmp(*argv, "-tentative") == 0) {
+ filter.flags &= ~IFA_F_TENTATIVE;
+ filter.flagmask |= IFA_F_TENTATIVE;
+ } else if (strcmp(*argv, "deprecated") == 0) {
+ filter.flags |= IFA_F_DEPRECATED;
+ filter.flagmask |= IFA_F_DEPRECATED;
+ } else if (strcmp(*argv, "-deprecated") == 0) {
+ filter.flags &= ~IFA_F_DEPRECATED;
+ filter.flagmask |= IFA_F_DEPRECATED;
+ } else if (strcmp(*argv, "home") == 0) {
+ filter.flags |= IFA_F_HOMEADDRESS;
+ filter.flagmask |= IFA_F_HOMEADDRESS;
+ } else if (strcmp(*argv, "nodad") == 0) {
+ filter.flags |= IFA_F_NODAD;
+ filter.flagmask |= IFA_F_NODAD;
+ } else if (strcmp(*argv, "mngtmpaddr") == 0) {
+ filter.flags |= IFA_F_MANAGETEMPADDR;
+ filter.flagmask |= IFA_F_MANAGETEMPADDR;
+ } else if (strcmp(*argv, "noprefixroute") == 0) {
+ filter.flags |= IFA_F_NOPREFIXROUTE;
+ filter.flagmask |= IFA_F_NOPREFIXROUTE;
+ } else if (strcmp(*argv, "autojoin") == 0) {
+ filter.flags |= IFA_F_MCAUTOJOIN;
+ filter.flagmask |= IFA_F_MCAUTOJOIN;
+ } else if (strcmp(*argv, "dadfailed") == 0) {
+ filter.flags |= IFA_F_DADFAILED;
+ filter.flagmask |= IFA_F_DADFAILED;
+ } else if (strcmp(*argv, "-dadfailed") == 0) {
+ filter.flags &= ~IFA_F_DADFAILED;
+ filter.flagmask |= IFA_F_DADFAILED;
+ } else if (strcmp(*argv, "label") == 0) {
+ NEXT_ARG();
+ filter.label = *argv;
+ } else if (strcmp(*argv, "group") == 0) {
+ NEXT_ARG();
+ if (rtnl_group_a2n(&filter.group, *argv))
+ invarg("Invalid \"group\" value\n", *argv);
+ } else if (strcmp(*argv, "master") == 0) {
+ int ifindex;
+ NEXT_ARG();
+ ifindex = ll_name_to_index(*argv);
+ if (!ifindex)
+ invarg("Device does not exist\n", *argv);
+ filter.master = ifindex;
+ } else if (do_link && strcmp(*argv, "type") == 0) {
+ NEXT_ARG();
+ filter.kind = *argv;
+ } else {
+ if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ }
+ else if (matches(*argv, "help") == 0)
+ usage();
+ if (filter_dev)
+ duparg2("dev", *argv);
+ filter_dev = *argv;
+ }
+ argv++; argc--;
+ }
+
+ if (filter_dev) {
+ filter.ifindex = ll_name_to_index(filter_dev);
+ if (filter.ifindex <= 0) {
+ fprintf(stderr, "Device \"%s\" does not exist.\n", filter_dev);
+ return -1;
+ }
+ }
+
+ if (action == IPADD_FLUSH)
+ return ipaddr_flush();
+
+ if (action == IPADD_SAVE) {
+ if (ipadd_save_prep())
+ exit(1);
+
+ if (rtnl_wilddump_request(&rth, preferred_family, RTM_GETADDR) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+
+ if (rtnl_dump_filter(&rth, save_nlmsg, stdout) < 0) {
+ fprintf(stderr, "Save terminated\n");
+ exit(1);
+ }
+
+ exit(0);
+ }
+
+ /*
+ * If only filter_dev present and none of the other
+ * link filters are present, use RTM_GETLINK to get
+ * the link device
+ */
+ if (filter_dev && filter.group == -1 && do_link == 1) {
+ if (iplink_get(0, filter_dev, RTEXT_FILTER_VF) < 0) {
+ perror("Cannot send link get request");
+ exit(1);
+ }
+ exit(0);
+ }
+
+ if (rtnl_wilddump_request(&rth, preferred_family, RTM_GETLINK) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+
+ if (rtnl_dump_filter(&rth, store_nlmsg, &linfo) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ exit(1);
+ }
+
+ if (filter.family != AF_PACKET) {
+ if (filter.oneline)
+ no_link = 1;
+
+ if (rtnl_wilddump_request(&rth, filter.family, RTM_GETADDR) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+
+ if (rtnl_dump_filter(&rth, store_nlmsg, &ainfo) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ exit(1);
+ }
+
+ ipaddr_filter(&linfo, &ainfo);
+ }
+
+ for (l = linfo.head; l; l = l->next) {
+ int res = 0;
+ struct ifinfomsg *ifi = NLMSG_DATA(&l->h);
+
+ if (brief) {
+ if (print_linkinfo_brief(NULL, &l->h, stdout) == 0)
+ if (filter.family != AF_PACKET)
+ print_selected_addrinfo(ifi,
+ ainfo.head,
+ stdout);
+ } else if (no_link ||
+ (res = print_linkinfo(NULL, &l->h, stdout)) >= 0) {
+ if (filter.family != AF_PACKET)
+ print_selected_addrinfo(ifi,
+ ainfo.head, stdout);
+ if (res > 0 && !do_link && show_stats)
+ print_link_stats(stdout, &l->h);
+ }
+ }
+ fflush(stdout);
+
+ free_nlmsg_chain(&ainfo);
+ free_nlmsg_chain(&linfo);
+
+ return 0;
+}
+
+static void
+ipaddr_loop_each_vf(struct rtattr *tb[], int vfnum, int *min, int *max)
+{
+ struct rtattr *vflist = tb[IFLA_VFINFO_LIST];
+ struct rtattr *i, *vf[IFLA_VF_MAX+1];
+ struct ifla_vf_rate *vf_rate;
+ int rem;
+
+ rem = RTA_PAYLOAD(vflist);
+
+ for (i = RTA_DATA(vflist); RTA_OK(i, rem); i = RTA_NEXT(i, rem)) {
+ parse_rtattr_nested(vf, IFLA_VF_MAX, i);
+ vf_rate = RTA_DATA(vf[IFLA_VF_RATE]);
+ if (vf_rate->vf == vfnum) {
+ *min = vf_rate->min_tx_rate;
+ *max = vf_rate->max_tx_rate;
+ return;
+ }
+ }
+ fprintf(stderr, "Cannot find VF %d\n", vfnum);
+ exit(1);
+}
+
+void ipaddr_get_vf_rate(int vfnum, int *min, int *max, int idx)
+{
+ struct nlmsg_chain linfo = { NULL, NULL};
+ struct rtattr *tb[IFLA_MAX+1];
+ struct ifinfomsg *ifi;
+ struct nlmsg_list *l;
+ struct nlmsghdr *n;
+ int len;
+
+ if (rtnl_wilddump_request(&rth, AF_UNSPEC, RTM_GETLINK) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+ if (rtnl_dump_filter(&rth, store_nlmsg, &linfo) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ exit(1);
+ }
+ for (l = linfo.head; l; l = l->next) {
+ n = &l->h;
+ ifi = NLMSG_DATA(n);
+
+ len = n->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi));
+ if (len < 0 || (idx && idx != ifi->ifi_index))
+ continue;
+
+ parse_rtattr(tb, IFLA_MAX, IFLA_RTA(ifi), len);
+
+ if ((tb[IFLA_VFINFO_LIST] && tb[IFLA_NUM_VF])) {
+ ipaddr_loop_each_vf(tb, vfnum, min, max);
+ return;
+ }
+ }
+}
+
+int ipaddr_list_link(int argc, char **argv)
+{
+ preferred_family = AF_PACKET;
+ do_link = 1;
+ return ipaddr_list_flush_or_save(argc, argv, IPADD_LIST);
+}
+
+void ipaddr_reset_filter(int oneline, int ifindex)
+{
+ memset(&filter, 0, sizeof(filter));
+ filter.oneline = oneline;
+ filter.ifindex = ifindex;
+}
+
+static int default_scope(inet_prefix *lcl)
+{
+ if (lcl->family == AF_INET) {
+ if (lcl->bytelen >= 1 && *(__u8*)&lcl->data == 127)
+ return RT_SCOPE_HOST;
+ }
+ return 0;
+}
+
+static bool ipaddr_is_multicast(inet_prefix *a)
+{
+ if (a->family == AF_INET)
+ return IN_MULTICAST(ntohl(a->data[0]));
+ else if (a->family == AF_INET6)
+ return IN6_IS_ADDR_MULTICAST(a->data);
+ else
+ return false;
+}
+
+static int ipaddr_modify(int cmd, int flags, int argc, char **argv)
+{
+ struct {
+ struct nlmsghdr n;
+ struct ifaddrmsg ifa;
+ char buf[256];
+ } req;
+ char *d = NULL;
+ char *l = NULL;
+ char *lcl_arg = NULL;
+ char *valid_lftp = NULL;
+ char *preferred_lftp = NULL;
+ inet_prefix lcl;
+ inet_prefix peer;
+ int local_len = 0;
+ int peer_len = 0;
+ int brd_len = 0;
+ int any_len = 0;
+ int scoped = 0;
+ __u32 preferred_lft = INFINITY_LIFE_TIME;
+ __u32 valid_lft = INFINITY_LIFE_TIME;
+ struct ifa_cacheinfo cinfo;
+ unsigned int ifa_flags = 0;
+
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifaddrmsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST | flags;
+ req.n.nlmsg_type = cmd;
+ req.ifa.ifa_family = preferred_family;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "peer") == 0 ||
+ strcmp(*argv, "remote") == 0) {
+ NEXT_ARG();
+
+ if (peer_len)
+ duparg("peer", *argv);
+ get_prefix(&peer, *argv, req.ifa.ifa_family);
+ peer_len = peer.bytelen;
+ if (req.ifa.ifa_family == AF_UNSPEC)
+ req.ifa.ifa_family = peer.family;
+ addattr_l(&req.n, sizeof(req), IFA_ADDRESS, &peer.data, peer.bytelen);
+ req.ifa.ifa_prefixlen = peer.bitlen;
+ } else if (matches(*argv, "broadcast") == 0 ||
+ strcmp(*argv, "brd") == 0) {
+ inet_prefix addr;
+ NEXT_ARG();
+ if (brd_len)
+ duparg("broadcast", *argv);
+ if (strcmp(*argv, "+") == 0)
+ brd_len = -1;
+ else if (strcmp(*argv, "-") == 0)
+ brd_len = -2;
+ else {
+ get_addr(&addr, *argv, req.ifa.ifa_family);
+ if (req.ifa.ifa_family == AF_UNSPEC)
+ req.ifa.ifa_family = addr.family;
+ addattr_l(&req.n, sizeof(req), IFA_BROADCAST, &addr.data, addr.bytelen);
+ brd_len = addr.bytelen;
+ }
+ } else if (strcmp(*argv, "anycast") == 0) {
+ inet_prefix addr;
+ NEXT_ARG();
+ if (any_len)
+ duparg("anycast", *argv);
+ get_addr(&addr, *argv, req.ifa.ifa_family);
+ if (req.ifa.ifa_family == AF_UNSPEC)
+ req.ifa.ifa_family = addr.family;
+ addattr_l(&req.n, sizeof(req), IFA_ANYCAST, &addr.data, addr.bytelen);
+ any_len = addr.bytelen;
+ } else if (strcmp(*argv, "scope") == 0) {
+ unsigned scope = 0;
+ NEXT_ARG();
+ if (rtnl_rtscope_a2n(&scope, *argv))
+ invarg("invalid scope value.", *argv);
+ req.ifa.ifa_scope = scope;
+ scoped = 1;
+ } else if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ d = *argv;
+ } else if (strcmp(*argv, "label") == 0) {
+ NEXT_ARG();
+ l = *argv;
+ addattr_l(&req.n, sizeof(req), IFA_LABEL, l, strlen(l)+1);
+ } else if (matches(*argv, "valid_lft") == 0) {
+ if (valid_lftp)
+ duparg("valid_lft", *argv);
+ NEXT_ARG();
+ valid_lftp = *argv;
+ if (set_lifetime(&valid_lft, *argv))
+ invarg("valid_lft value", *argv);
+ } else if (matches(*argv, "preferred_lft") == 0) {
+ if (preferred_lftp)
+ duparg("preferred_lft", *argv);
+ NEXT_ARG();
+ preferred_lftp = *argv;
+ if (set_lifetime(&preferred_lft, *argv))
+ invarg("preferred_lft value", *argv);
+ } else if (strcmp(*argv, "home") == 0) {
+ ifa_flags |= IFA_F_HOMEADDRESS;
+ } else if (strcmp(*argv, "nodad") == 0) {
+ ifa_flags |= IFA_F_NODAD;
+ } else if (strcmp(*argv, "mngtmpaddr") == 0) {
+ ifa_flags |= IFA_F_MANAGETEMPADDR;
+ } else if (strcmp(*argv, "noprefixroute") == 0) {
+ ifa_flags |= IFA_F_NOPREFIXROUTE;
+ } else if (strcmp(*argv, "autojoin") == 0) {
+ ifa_flags |= IFA_F_MCAUTOJOIN;
+ } else {
+ if (strcmp(*argv, "local") == 0) {
+ NEXT_ARG();
+ }
+ if (matches(*argv, "help") == 0)
+ usage();
+ if (local_len)
+ duparg2("local", *argv);
+ lcl_arg = *argv;
+ get_prefix(&lcl, *argv, req.ifa.ifa_family);
+ if (req.ifa.ifa_family == AF_UNSPEC)
+ req.ifa.ifa_family = lcl.family;
+ addattr_l(&req.n, sizeof(req), IFA_LOCAL, &lcl.data, lcl.bytelen);
+ local_len = lcl.bytelen;
+ }
+ argc--; argv++;
+ }
+ if (ifa_flags <= 0xff)
+ req.ifa.ifa_flags = ifa_flags;
+ else
+ addattr32(&req.n, sizeof(req), IFA_FLAGS, ifa_flags);
+
+ if (d == NULL) {
+ fprintf(stderr, "Not enough information: \"dev\" argument is required.\n");
+ return -1;
+ }
+ if (l && matches(d, l) != 0) {
+ fprintf(stderr, "\"dev\" (%s) must match \"label\" (%s).\n", d, l);
+ return -1;
+ }
+
+ if (peer_len == 0 && local_len) {
+ if (cmd == RTM_DELADDR && lcl.family == AF_INET && !(lcl.flags & PREFIXLEN_SPECIFIED)) {
+ fprintf(stderr,
+ "Warning: Executing wildcard deletion to stay compatible with old scripts.\n" \
+ " Explicitly specify the prefix length (%s/%d) to avoid this warning.\n" \
+ " This special behaviour is likely to disappear in further releases,\n" \
+ " fix your scripts!\n", lcl_arg, local_len*8);
+ } else {
+ peer = lcl;
+ addattr_l(&req.n, sizeof(req), IFA_ADDRESS, &lcl.data, lcl.bytelen);
+ }
+ }
+ if (req.ifa.ifa_prefixlen == 0)
+ req.ifa.ifa_prefixlen = lcl.bitlen;
+
+ if (brd_len < 0 && cmd != RTM_DELADDR) {
+ inet_prefix brd;
+ int i;
+ if (req.ifa.ifa_family != AF_INET) {
+ fprintf(stderr, "Broadcast can be set only for IPv4 addresses\n");
+ return -1;
+ }
+ brd = peer;
+ if (brd.bitlen <= 30) {
+ for (i = 31; i >= brd.bitlen; i--) {
+ if (brd_len == -1)
+ brd.data[0] |= htonl(1<<(31-i));
+ else
+ brd.data[0] &= ~htonl(1<<(31-i));
+ }
+ addattr_l(&req.n, sizeof(req), IFA_BROADCAST, &brd.data, brd.bytelen);
+ brd_len = brd.bytelen;
+ }
+ }
+ if (!scoped && cmd != RTM_DELADDR)
+ req.ifa.ifa_scope = default_scope(&lcl);
+
+ if ((req.ifa.ifa_index = ll_name_to_index(d)) == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", d);
+ return -1;
+ }
+
+ if (valid_lftp || preferred_lftp) {
+ if (!valid_lft) {
+ fprintf(stderr, "valid_lft is zero\n");
+ return -1;
+ }
+ if (valid_lft < preferred_lft) {
+ fprintf(stderr, "preferred_lft is greater than valid_lft\n");
+ return -1;
+ }
+
+ memset(&cinfo, 0, sizeof(cinfo));
+ cinfo.ifa_prefered = preferred_lft;
+ cinfo.ifa_valid = valid_lft;
+ addattr_l(&req.n, sizeof(req), IFA_CACHEINFO, &cinfo,
+ sizeof(cinfo));
+ }
+
+ if ((ifa_flags & IFA_F_MCAUTOJOIN) && !ipaddr_is_multicast(&lcl)) {
+ fprintf(stderr, "autojoin needs multicast address\n");
+ return -1;
+ }
+
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ return -2;
+
+ return 0;
+}
+
+int do_ipaddr(int argc, char **argv)
+{
+ if (argc < 1)
+ return ipaddr_list_flush_or_save(0, NULL, IPADD_LIST);
+ if (matches(*argv, "add") == 0)
+ return ipaddr_modify(RTM_NEWADDR, NLM_F_CREATE|NLM_F_EXCL, argc-1, argv+1);
+ if (matches(*argv, "change") == 0 ||
+ strcmp(*argv, "chg") == 0)
+ return ipaddr_modify(RTM_NEWADDR, NLM_F_REPLACE, argc-1, argv+1);
+ if (matches(*argv, "replace") == 0)
+ return ipaddr_modify(RTM_NEWADDR, NLM_F_CREATE|NLM_F_REPLACE, argc-1, argv+1);
+ if (matches(*argv, "delete") == 0)
+ return ipaddr_modify(RTM_DELADDR, 0, argc-1, argv+1);
+ if (matches(*argv, "list") == 0 || matches(*argv, "show") == 0
+ || matches(*argv, "lst") == 0)
+ return ipaddr_list_flush_or_save(argc-1, argv+1, IPADD_LIST);
+ if (matches(*argv, "flush") == 0)
+ return ipaddr_list_flush_or_save(argc-1, argv+1, IPADD_FLUSH);
+ if (matches(*argv, "save") == 0)
+ return ipaddr_list_flush_or_save(argc-1, argv+1, IPADD_SAVE);
+ if (matches(*argv, "showdump") == 0)
+ return ipaddr_showdump();
+ if (matches(*argv, "restore") == 0)
+ return ipaddr_restore();
+ if (matches(*argv, "help") == 0)
+ usage();
+ fprintf(stderr, "Command \"%s\" is unknown, try \"ip address help\".\n", *argv);
+ exit(-1);
+}
diff --git a/iproute2/ip/ipaddrlabel.c b/iproute2/ip/ipaddrlabel.c
new file mode 100644
index 0000000..f01bc26
--- /dev/null
+++ b/iproute2/ip/ipaddrlabel.c
@@ -0,0 +1,265 @@
+/*
+ * ipaddrlabel.c "ip addrlabel"
+ *
+ * Copyright (C)2007 USAGI/WIDE Project
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses>.
+ *
+ *
+ * Based on iprule.c.
+ *
+ * Authors: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <linux/types.h>
+#include <linux/if_addrlabel.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+
+#define IFAL_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifaddrlblmsg))))
+#define IFAL_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifaddrlblmsg))
+
+extern struct rtnl_handle rth;
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: ip addrlabel [ list | add | del | flush ] prefix PREFIX [ dev DEV ] [ label LABEL ]\n");
+ exit(-1);
+}
+
+int print_addrlabel(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ struct ifaddrlblmsg *ifal = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr *tb[IFAL_MAX+1];
+ char abuf[256];
+
+ if (n->nlmsg_type != RTM_NEWADDRLABEL && n->nlmsg_type != RTM_DELADDRLABEL)
+ return 0;
+
+ len -= NLMSG_LENGTH(sizeof(*ifal));
+ if (len < 0)
+ return -1;
+
+ parse_rtattr(tb, IFAL_MAX, IFAL_RTA(ifal), len);
+
+ if (n->nlmsg_type == RTM_DELADDRLABEL)
+ fprintf(fp, "Deleted ");
+
+ if (tb[IFAL_ADDRESS]) {
+ fprintf(fp, "prefix %s/%u ",
+ format_host(ifal->ifal_family,
+ RTA_PAYLOAD(tb[IFAL_ADDRESS]),
+ RTA_DATA(tb[IFAL_ADDRESS]),
+ abuf, sizeof(abuf)),
+ ifal->ifal_prefixlen);
+ }
+
+ if (ifal->ifal_index)
+ fprintf(fp, "dev %s ", ll_index_to_name(ifal->ifal_index));
+
+ if (tb[IFAL_LABEL] && RTA_PAYLOAD(tb[IFAL_LABEL]) == sizeof(uint32_t)) {
+ uint32_t label;
+ memcpy(&label, RTA_DATA(tb[IFAL_LABEL]), sizeof(label));
+ fprintf(fp, "label %u ", label);
+ }
+
+ fprintf(fp, "\n");
+ fflush(fp);
+ return 0;
+}
+
+static int ipaddrlabel_list(int argc, char **argv)
+{
+ int af = preferred_family;
+
+ if (af == AF_UNSPEC)
+ af = AF_INET6;
+
+ if (argc > 0) {
+ fprintf(stderr, "\"ip addrlabel show\" does not take any arguments.\n");
+ return -1;
+ }
+
+ if (rtnl_wilddump_request(&rth, af, RTM_GETADDRLABEL) < 0) {
+ perror("Cannot send dump request");
+ return 1;
+ }
+
+ if (rtnl_dump_filter(&rth, print_addrlabel, stdout) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ return 1;
+ }
+
+ return 0;
+}
+
+
+static int ipaddrlabel_modify(int cmd, int argc, char **argv)
+{
+ struct {
+ struct nlmsghdr n;
+ struct ifaddrlblmsg ifal;
+ char buf[1024];
+ } req;
+
+ inet_prefix prefix;
+ uint32_t label = 0xffffffffUL;
+ char *p = NULL;
+ char *l = NULL;
+
+ memset(&req, 0, sizeof(req));
+ memset(&prefix, 0, sizeof(prefix));
+
+ req.n.nlmsg_type = cmd;
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifaddrlblmsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.ifal.ifal_family = preferred_family;
+ req.ifal.ifal_prefixlen = 0;
+ req.ifal.ifal_index = 0;
+
+ if (cmd == RTM_NEWADDRLABEL) {
+ req.n.nlmsg_flags |= NLM_F_CREATE|NLM_F_EXCL;
+ }
+
+ while (argc > 0) {
+ if (strcmp(*argv, "prefix") == 0) {
+ NEXT_ARG();
+ p = *argv;
+ get_prefix(&prefix, *argv, preferred_family);
+ } else if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ if ((req.ifal.ifal_index = ll_name_to_index(*argv)) == 0)
+ invarg("dev is invalid\n", *argv);
+ } else if (strcmp(*argv, "label") == 0) {
+ NEXT_ARG();
+ l = *argv;
+ if (get_u32(&label, *argv, 0) || label == 0xffffffffUL)
+ invarg("label is invalid\n", *argv);
+ }
+ argc--;
+ argv++;
+ }
+ if (p == NULL) {
+ fprintf(stderr, "Not enough information: \"prefix\" argument is required.\n");
+ return -1;
+ }
+ if (l == NULL) {
+ fprintf(stderr, "Not enough information: \"label\" argument is required.\n");
+ return -1;
+ }
+ addattr32(&req.n, sizeof(req), IFAL_LABEL, label);
+ addattr_l(&req.n, sizeof(req), IFAL_ADDRESS, &prefix.data, prefix.bytelen);
+ req.ifal.ifal_prefixlen = prefix.bitlen;
+
+ if (req.ifal.ifal_family == AF_UNSPEC)
+ req.ifal.ifal_family = AF_INET6;
+
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ return -2;
+
+ return 0;
+}
+
+
+static int flush_addrlabel(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
+{
+ struct rtnl_handle rth2;
+ struct rtmsg *r = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr * tb[IFAL_MAX+1];
+
+ len -= NLMSG_LENGTH(sizeof(*r));
+ if (len < 0)
+ return -1;
+
+ parse_rtattr(tb, IFAL_MAX, RTM_RTA(r), len);
+
+ if (tb[IFAL_ADDRESS]) {
+ n->nlmsg_type = RTM_DELADDRLABEL;
+ n->nlmsg_flags = NLM_F_REQUEST;
+
+ if (rtnl_open(&rth2, 0) < 0)
+ return -1;
+
+ if (rtnl_talk(&rth2, n, NULL, 0) < 0)
+ return -2;
+
+ rtnl_close(&rth2);
+ }
+
+ return 0;
+}
+
+static int ipaddrlabel_flush(int argc, char **argv)
+{
+ int af = preferred_family;
+
+ if (af == AF_UNSPEC)
+ af = AF_INET6;
+
+ if (argc > 0) {
+ fprintf(stderr, "\"ip addrlabel flush\" does not allow extra arguments\n");
+ return -1;
+ }
+
+ if (rtnl_wilddump_request(&rth, af, RTM_GETADDRLABEL) < 0) {
+ perror("Cannot send dump request");
+ return -1;
+ }
+
+ if (rtnl_dump_filter(&rth, flush_addrlabel, NULL) < 0) {
+ fprintf(stderr, "Flush terminated\n");
+ return -1;
+ }
+
+ return 0;
+}
+
+int do_ipaddrlabel(int argc, char **argv)
+{
+ if (argc < 1) {
+ return ipaddrlabel_list(0, NULL);
+ } else if (matches(argv[0], "list") == 0 ||
+ matches(argv[0], "lst") == 0 ||
+ matches(argv[0], "show") == 0) {
+ return ipaddrlabel_list(argc-1, argv+1);
+ } else if (matches(argv[0], "add") == 0) {
+ return ipaddrlabel_modify(RTM_NEWADDRLABEL, argc-1, argv+1);
+ } else if (matches(argv[0], "delete") == 0) {
+ return ipaddrlabel_modify(RTM_DELADDRLABEL, argc-1, argv+1);
+ } else if (matches(argv[0], "flush") == 0) {
+ return ipaddrlabel_flush(argc-1, argv+1);
+ } else if (matches(argv[0], "help") == 0)
+ usage();
+
+ fprintf(stderr, "Command \"%s\" is unknown, try \"ip addrlabel help\".\n", *argv);
+ exit(-1);
+}
diff --git a/iproute2/ip/ipfou.c b/iproute2/ip/ipfou.c
new file mode 100644
index 0000000..8a86b18
--- /dev/null
+++ b/iproute2/ip/ipfou.c
@@ -0,0 +1,158 @@
+/*
+ * ipfou.c FOU (foo over UDP) support
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Tom Herbert <therbert@google.com>
+ */
+
+#include <netdb.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <net/if.h>
+#include <linux/fou.h>
+#include <linux/genetlink.h>
+#include <linux/ip.h>
+#include <arpa/inet.h>
+
+#include "libgenl.h"
+#include "utils.h"
+#include "ip_common.h"
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: ip fou add port PORT { ipproto PROTO | gue }\n");
+ fprintf(stderr, " ip fou del port PORT\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "Where: PROTO { ipproto-name | 1..255 }\n");
+ fprintf(stderr, " PORT { 1..65535 }\n");
+
+ exit(-1);
+}
+
+/* netlink socket */
+static struct rtnl_handle genl_rth = { .fd = -1 };
+static int genl_family = -1;
+
+#define FOU_REQUEST(_req, _bufsiz, _cmd, _flags) \
+ GENL_REQUEST(_req, _bufsiz, genl_family, 0, \
+ FOU_GENL_VERSION, _cmd, _flags)
+
+static int fou_parse_opt(int argc, char **argv, struct nlmsghdr *n,
+ bool adding)
+{
+ __u16 port;
+ int port_set = 0;
+ __u8 ipproto, type;
+ bool gue_set = false;
+ int ipproto_set = 0;
+
+ while (argc > 0) {
+ if (!matches(*argv, "port")) {
+ NEXT_ARG();
+
+ if (get_u16(&port, *argv, 0) || port == 0)
+ invarg("invalid port", *argv);
+ port = htons(port);
+ port_set = 1;
+ } else if (!matches(*argv, "ipproto")) {
+ struct protoent *servptr;
+
+ NEXT_ARG();
+
+ servptr = getprotobyname(*argv);
+ if (servptr)
+ ipproto = servptr->p_proto;
+ else if (get_u8(&ipproto, *argv, 0) || ipproto == 0)
+ invarg("invalid ipproto", *argv);
+ ipproto_set = 1;
+ } else if (!matches(*argv, "gue")) {
+ gue_set = true;
+ } else {
+ fprintf(stderr, "fou: unknown command \"%s\"?\n", *argv);
+ usage();
+ return -1;
+ }
+ argc--, argv++;
+ }
+
+ if (!port_set) {
+ fprintf(stderr, "fou: missing port\n");
+ return -1;
+ }
+
+ if (!ipproto_set && !gue_set && adding) {
+ fprintf(stderr, "fou: must set ipproto or gue\n");
+ return -1;
+ }
+
+ if (ipproto_set && gue_set) {
+ fprintf(stderr, "fou: cannot set ipproto and gue\n");
+ return -1;
+ }
+
+ type = gue_set ? FOU_ENCAP_GUE : FOU_ENCAP_DIRECT;
+
+ addattr16(n, 1024, FOU_ATTR_PORT, port);
+ addattr8(n, 1024, FOU_ATTR_TYPE, type);
+
+ if (ipproto_set)
+ addattr8(n, 1024, FOU_ATTR_IPPROTO, ipproto);
+
+ return 0;
+}
+
+static int do_add(int argc, char **argv)
+{
+ FOU_REQUEST(req, 1024, FOU_CMD_ADD, NLM_F_REQUEST);
+
+ fou_parse_opt(argc, argv, &req.n, true);
+
+ if (rtnl_talk(&genl_rth, &req.n, NULL, 0) < 0)
+ return -2;
+
+ return 0;
+}
+
+static int do_del(int argc, char **argv)
+{
+ FOU_REQUEST(req, 1024, FOU_CMD_DEL, NLM_F_REQUEST);
+
+ fou_parse_opt(argc, argv, &req.n, false);
+
+ if (rtnl_talk(&genl_rth, &req.n, NULL, 0) < 0)
+ return -2;
+
+ return 0;
+}
+
+int do_ipfou(int argc, char **argv)
+{
+ if (genl_family < 0) {
+ if (rtnl_open_byproto(&genl_rth, 0, NETLINK_GENERIC) < 0) {
+ fprintf(stderr, "Cannot open generic netlink socket\n");
+ exit(1);
+ }
+
+ genl_family = genl_resolve_family(&genl_rth, FOU_GENL_NAME);
+ if (genl_family < 0)
+ exit(1);
+ }
+
+ if (argc < 1)
+ usage();
+
+ if (matches(*argv, "add") == 0)
+ return do_add(argc-1, argv+1);
+ if (matches(*argv, "delete") == 0)
+ return do_del(argc-1, argv+1);
+ if (matches(*argv, "help") == 0)
+ usage();
+
+ fprintf(stderr, "Command \"%s\" is unknown, try \"ip fou help\".\n", *argv);
+ exit(-1);
+}
diff --git a/iproute2/ip/ipl2tp.c b/iproute2/ip/ipl2tp.c
new file mode 100644
index 0000000..f050880
--- /dev/null
+++ b/iproute2/ip/ipl2tp.c
@@ -0,0 +1,750 @@
+/*
+ * ipl2tp.c "ip l2tp"
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Original Author: James Chapman <jchapman@katalix.com>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+#include <sys/ioctl.h>
+#include <linux/if.h>
+#include <linux/if_arp.h>
+#include <linux/ip.h>
+
+#include <linux/genetlink.h>
+#include <linux/l2tp.h>
+#include "libgenl.h"
+
+#include "utils.h"
+#include "ip_common.h"
+
+enum {
+ L2TP_ADD,
+ L2TP_CHG,
+ L2TP_DEL,
+ L2TP_GET
+};
+
+struct l2tp_parm {
+ uint32_t tunnel_id;
+ uint32_t peer_tunnel_id;
+ uint32_t session_id;
+ uint32_t peer_session_id;
+ uint32_t offset;
+ uint32_t peer_offset;
+ enum l2tp_encap_type encap;
+ uint16_t local_udp_port;
+ uint16_t peer_udp_port;
+ int cookie_len;
+ uint8_t cookie[8];
+ int peer_cookie_len;
+ uint8_t peer_cookie[8];
+ inet_prefix local_ip;
+ inet_prefix peer_ip;
+
+ uint16_t pw_type;
+ uint16_t mtu;
+ int udp_csum:1;
+ int recv_seq:1;
+ int send_seq:1;
+ int lns_mode:1;
+ int data_seq:2;
+ int tunnel:1;
+ int session:1;
+ int reorder_timeout;
+ const char *ifname;
+ uint8_t l2spec_type;
+ uint8_t l2spec_len;
+};
+
+struct l2tp_stats {
+ uint64_t data_rx_packets;
+ uint64_t data_rx_bytes;
+ uint64_t data_rx_errors;
+ uint64_t data_rx_oos_packets;
+ uint64_t data_rx_oos_discards;
+ uint64_t data_tx_packets;
+ uint64_t data_tx_bytes;
+ uint64_t data_tx_errors;
+};
+
+struct l2tp_data {
+ struct l2tp_parm config;
+ struct l2tp_stats stats;
+};
+
+/* netlink socket */
+static struct rtnl_handle genl_rth;
+static int genl_family = -1;
+
+/*****************************************************************************
+ * Netlink actions
+ *****************************************************************************/
+
+static int create_tunnel(struct l2tp_parm *p)
+{
+ uint32_t local_attr = L2TP_ATTR_IP_SADDR;
+ uint32_t peer_attr = L2TP_ATTR_IP_DADDR;
+
+ GENL_REQUEST(req, 1024, genl_family, 0, L2TP_GENL_VERSION,
+ L2TP_CMD_TUNNEL_CREATE, NLM_F_REQUEST | NLM_F_ACK);
+
+ addattr32(&req.n, 1024, L2TP_ATTR_CONN_ID, p->tunnel_id);
+ addattr32(&req.n, 1024, L2TP_ATTR_PEER_CONN_ID, p->peer_tunnel_id);
+ addattr8(&req.n, 1024, L2TP_ATTR_PROTO_VERSION, 3);
+ addattr16(&req.n, 1024, L2TP_ATTR_ENCAP_TYPE, p->encap);
+
+ if (p->local_ip.family == AF_INET6)
+ local_attr = L2TP_ATTR_IP6_SADDR;
+ addattr_l(&req.n, 1024, local_attr, &p->local_ip.data, p->local_ip.bytelen);
+
+ if (p->peer_ip.family == AF_INET6)
+ peer_attr = L2TP_ATTR_IP6_DADDR;
+ addattr_l(&req.n, 1024, peer_attr, &p->peer_ip.data, p->peer_ip.bytelen);
+
+ if (p->encap == L2TP_ENCAPTYPE_UDP) {
+ addattr16(&req.n, 1024, L2TP_ATTR_UDP_SPORT, p->local_udp_port);
+ addattr16(&req.n, 1024, L2TP_ATTR_UDP_DPORT, p->peer_udp_port);
+ }
+
+ if (rtnl_talk(&genl_rth, &req.n, NULL, 0) < 0)
+ return -2;
+
+ return 0;
+}
+
+static int delete_tunnel(struct l2tp_parm *p)
+{
+ GENL_REQUEST(req, 128, genl_family, 0, L2TP_GENL_VERSION,
+ L2TP_CMD_TUNNEL_DELETE, NLM_F_REQUEST | NLM_F_ACK);
+
+ addattr32(&req.n, 128, L2TP_ATTR_CONN_ID, p->tunnel_id);
+
+ if (rtnl_talk(&genl_rth, &req.n, NULL, 0) < 0)
+ return -2;
+
+ return 0;
+}
+
+static int create_session(struct l2tp_parm *p)
+{
+ GENL_REQUEST(req, 1024, genl_family, 0, L2TP_GENL_VERSION,
+ L2TP_CMD_SESSION_CREATE, NLM_F_REQUEST | NLM_F_ACK);
+
+ addattr32(&req.n, 1024, L2TP_ATTR_CONN_ID, p->tunnel_id);
+ addattr32(&req.n, 1024, L2TP_ATTR_PEER_CONN_ID, p->peer_tunnel_id);
+ addattr32(&req.n, 1024, L2TP_ATTR_SESSION_ID, p->session_id);
+ addattr32(&req.n, 1024, L2TP_ATTR_PEER_SESSION_ID, p->peer_session_id);
+ addattr16(&req.n, 1024, L2TP_ATTR_PW_TYPE, p->pw_type);
+ addattr8(&req.n, 1024, L2TP_ATTR_L2SPEC_TYPE, p->l2spec_type);
+ addattr8(&req.n, 1024, L2TP_ATTR_L2SPEC_LEN, p->l2spec_len);
+
+ if (p->mtu) addattr16(&req.n, 1024, L2TP_ATTR_MTU, p->mtu);
+ if (p->recv_seq) addattr(&req.n, 1024, L2TP_ATTR_RECV_SEQ);
+ if (p->send_seq) addattr(&req.n, 1024, L2TP_ATTR_SEND_SEQ);
+ if (p->lns_mode) addattr(&req.n, 1024, L2TP_ATTR_LNS_MODE);
+ if (p->data_seq) addattr8(&req.n, 1024, L2TP_ATTR_DATA_SEQ, p->data_seq);
+ if (p->reorder_timeout) addattr64(&req.n, 1024, L2TP_ATTR_RECV_TIMEOUT,
+ p->reorder_timeout);
+ if (p->offset) addattr16(&req.n, 1024, L2TP_ATTR_OFFSET, p->offset);
+ if (p->cookie_len) addattr_l(&req.n, 1024, L2TP_ATTR_COOKIE,
+ p->cookie, p->cookie_len);
+ if (p->peer_cookie_len) addattr_l(&req.n, 1024, L2TP_ATTR_PEER_COOKIE,
+ p->peer_cookie, p->peer_cookie_len);
+ if (p->ifname && p->ifname[0])
+ addattrstrz(&req.n, 1024, L2TP_ATTR_IFNAME, p->ifname);
+
+ if (rtnl_talk(&genl_rth, &req.n, NULL, 0) < 0)
+ return -2;
+
+ return 0;
+}
+
+static int delete_session(struct l2tp_parm *p)
+{
+ GENL_REQUEST(req, 1024, genl_family, 0, L2TP_GENL_VERSION,
+ L2TP_CMD_SESSION_DELETE, NLM_F_REQUEST | NLM_F_ACK);
+
+ addattr32(&req.n, 1024, L2TP_ATTR_CONN_ID, p->tunnel_id);
+ addattr32(&req.n, 1024, L2TP_ATTR_SESSION_ID, p->session_id);
+ if (rtnl_talk(&genl_rth, &req.n, NULL, 0) < 0)
+ return -2;
+
+ return 0;
+}
+
+static void print_cookie(char *name, const uint8_t *cookie, int len)
+{
+ printf(" %s %02x%02x%02x%02x", name,
+ cookie[0], cookie[1],
+ cookie[2], cookie[3]);
+ if (len == 8)
+ printf("%02x%02x%02x%02x",
+ cookie[4], cookie[5],
+ cookie[6], cookie[7]);
+}
+
+static void print_tunnel(const struct l2tp_data *data)
+{
+ const struct l2tp_parm *p = &data->config;
+ char buf[INET6_ADDRSTRLEN];
+
+ printf("Tunnel %u, encap %s\n",
+ p->tunnel_id,
+ p->encap == L2TP_ENCAPTYPE_UDP ? "UDP" :
+ p->encap == L2TP_ENCAPTYPE_IP ? "IP" : "??");
+ printf(" From %s ", inet_ntop(p->local_ip.family, p->local_ip.data, buf, sizeof(buf)));
+ printf("to %s\n", inet_ntop(p->peer_ip.family, p->peer_ip.data, buf, sizeof(buf)));
+ printf(" Peer tunnel %u\n",
+ p->peer_tunnel_id);
+
+ if (p->encap == L2TP_ENCAPTYPE_UDP)
+ printf(" UDP source / dest ports: %hu/%hu\n",
+ p->local_udp_port, p->peer_udp_port);
+}
+
+static void print_session(struct l2tp_data *data)
+{
+ struct l2tp_parm *p = &data->config;
+
+ printf("Session %u in tunnel %u\n",
+ p->session_id, p->tunnel_id);
+ printf(" Peer session %u, tunnel %u\n",
+ p->peer_session_id, p->peer_tunnel_id);
+
+ if (p->ifname != NULL) {
+ printf(" interface name: %s\n", p->ifname);
+ }
+ printf(" offset %u, peer offset %u\n",
+ p->offset, p->peer_offset);
+ if (p->cookie_len > 0)
+ print_cookie("cookie", p->cookie, p->cookie_len);
+ if (p->peer_cookie_len > 0)
+ print_cookie("peer cookie", p->peer_cookie, p->peer_cookie_len);
+
+ if (p->reorder_timeout != 0)
+ printf(" reorder timeout: %u\n", p->reorder_timeout);
+ else
+ printf("\n");
+}
+
+static int get_response(struct nlmsghdr *n, void *arg)
+{
+ struct genlmsghdr *ghdr;
+ struct l2tp_data *data = arg;
+ struct l2tp_parm *p = &data->config;
+ struct rtattr *attrs[L2TP_ATTR_MAX + 1];
+ struct rtattr *nla_stats;
+ int len;
+
+ /* Validate message and parse attributes */
+ if (n->nlmsg_type == NLMSG_ERROR)
+ return -EBADMSG;
+
+ ghdr = NLMSG_DATA(n);
+ len = n->nlmsg_len - NLMSG_LENGTH(sizeof(*ghdr));
+ if (len < 0)
+ return -1;
+
+ parse_rtattr(attrs, L2TP_ATTR_MAX, (void *)ghdr + GENL_HDRLEN, len);
+
+ if (attrs[L2TP_ATTR_PW_TYPE])
+ p->pw_type = rta_getattr_u16(attrs[L2TP_ATTR_PW_TYPE]);
+ if (attrs[L2TP_ATTR_ENCAP_TYPE])
+ p->encap = rta_getattr_u16(attrs[L2TP_ATTR_ENCAP_TYPE]);
+ if (attrs[L2TP_ATTR_OFFSET])
+ p->offset = rta_getattr_u16(attrs[L2TP_ATTR_OFFSET]);
+ if (attrs[L2TP_ATTR_DATA_SEQ])
+ p->data_seq = rta_getattr_u16(attrs[L2TP_ATTR_DATA_SEQ]);
+ if (attrs[L2TP_ATTR_CONN_ID])
+ p->tunnel_id = rta_getattr_u32(attrs[L2TP_ATTR_CONN_ID]);
+ if (attrs[L2TP_ATTR_PEER_CONN_ID])
+ p->peer_tunnel_id = rta_getattr_u32(attrs[L2TP_ATTR_PEER_CONN_ID]);
+ if (attrs[L2TP_ATTR_SESSION_ID])
+ p->session_id = rta_getattr_u32(attrs[L2TP_ATTR_SESSION_ID]);
+ if (attrs[L2TP_ATTR_PEER_SESSION_ID])
+ p->peer_session_id = rta_getattr_u32(attrs[L2TP_ATTR_PEER_SESSION_ID]);
+ if (attrs[L2TP_ATTR_L2SPEC_TYPE])
+ p->l2spec_type = rta_getattr_u8(attrs[L2TP_ATTR_L2SPEC_TYPE]);
+ if (attrs[L2TP_ATTR_L2SPEC_LEN])
+ p->l2spec_len = rta_getattr_u8(attrs[L2TP_ATTR_L2SPEC_LEN]);
+
+ p->udp_csum = !!attrs[L2TP_ATTR_UDP_CSUM];
+ if (attrs[L2TP_ATTR_COOKIE])
+ memcpy(p->cookie, RTA_DATA(attrs[L2TP_ATTR_COOKIE]),
+ p->cookie_len = RTA_PAYLOAD(attrs[L2TP_ATTR_COOKIE]));
+
+ if (attrs[L2TP_ATTR_PEER_COOKIE])
+ memcpy(p->peer_cookie, RTA_DATA(attrs[L2TP_ATTR_PEER_COOKIE]),
+ p->peer_cookie_len = RTA_PAYLOAD(attrs[L2TP_ATTR_PEER_COOKIE]));
+
+ p->recv_seq = !!attrs[L2TP_ATTR_RECV_SEQ];
+ p->send_seq = !!attrs[L2TP_ATTR_SEND_SEQ];
+
+ if (attrs[L2TP_ATTR_RECV_TIMEOUT])
+ p->reorder_timeout = rta_getattr_u64(attrs[L2TP_ATTR_RECV_TIMEOUT]);
+ if (attrs[L2TP_ATTR_IP_SADDR]) {
+ p->local_ip.family = AF_INET;
+ p->local_ip.data[0] = rta_getattr_u32(attrs[L2TP_ATTR_IP_SADDR]);
+ p->local_ip.bytelen = 4;
+ p->local_ip.bitlen = -1;
+ }
+ if (attrs[L2TP_ATTR_IP_DADDR]) {
+ p->peer_ip.family = AF_INET;
+ p->peer_ip.data[0] = rta_getattr_u32(attrs[L2TP_ATTR_IP_DADDR]);
+ p->peer_ip.bytelen = 4;
+ p->peer_ip.bitlen = -1;
+ }
+ if (attrs[L2TP_ATTR_IP6_SADDR]) {
+ p->local_ip.family = AF_INET6;
+ memcpy(&p->local_ip.data, RTA_DATA(attrs[L2TP_ATTR_IP6_SADDR]),
+ p->local_ip.bytelen = 16);
+ p->local_ip.bitlen = -1;
+ }
+ if (attrs[L2TP_ATTR_IP6_DADDR]) {
+ p->peer_ip.family = AF_INET6;
+ memcpy(&p->peer_ip.data, RTA_DATA(attrs[L2TP_ATTR_IP6_DADDR]),
+ p->peer_ip.bytelen = 16);
+ p->peer_ip.bitlen = -1;
+ }
+ if (attrs[L2TP_ATTR_UDP_SPORT])
+ p->local_udp_port = rta_getattr_u16(attrs[L2TP_ATTR_UDP_SPORT]);
+ if (attrs[L2TP_ATTR_UDP_DPORT])
+ p->peer_udp_port = rta_getattr_u16(attrs[L2TP_ATTR_UDP_DPORT]);
+ if (attrs[L2TP_ATTR_MTU])
+ p->mtu = rta_getattr_u16(attrs[L2TP_ATTR_MTU]);
+ if (attrs[L2TP_ATTR_IFNAME])
+ p->ifname = rta_getattr_str(attrs[L2TP_ATTR_IFNAME]);
+
+ nla_stats = attrs[L2TP_ATTR_STATS];
+ if (nla_stats) {
+ struct rtattr *tb[L2TP_ATTR_STATS_MAX + 1];
+
+ parse_rtattr_nested(tb, L2TP_ATTR_STATS_MAX, nla_stats);
+
+ if (tb[L2TP_ATTR_TX_PACKETS])
+ data->stats.data_tx_packets = rta_getattr_u64(tb[L2TP_ATTR_TX_PACKETS]);
+ if (tb[L2TP_ATTR_TX_BYTES])
+ data->stats.data_tx_bytes = rta_getattr_u64(tb[L2TP_ATTR_TX_BYTES]);
+ if (tb[L2TP_ATTR_TX_ERRORS])
+ data->stats.data_tx_errors = rta_getattr_u64(tb[L2TP_ATTR_TX_ERRORS]);
+ if (tb[L2TP_ATTR_RX_PACKETS])
+ data->stats.data_rx_packets = rta_getattr_u64(tb[L2TP_ATTR_RX_PACKETS]);
+ if (tb[L2TP_ATTR_RX_BYTES])
+ data->stats.data_rx_bytes = rta_getattr_u64(tb[L2TP_ATTR_RX_BYTES]);
+ if (tb[L2TP_ATTR_RX_ERRORS])
+ data->stats.data_rx_errors = rta_getattr_u64(tb[L2TP_ATTR_RX_ERRORS]);
+ if (tb[L2TP_ATTR_RX_SEQ_DISCARDS])
+ data->stats.data_rx_oos_discards = rta_getattr_u64(tb[L2TP_ATTR_RX_SEQ_DISCARDS]);
+ if (tb[L2TP_ATTR_RX_OOS_PACKETS])
+ data->stats.data_rx_oos_packets = rta_getattr_u64(tb[L2TP_ATTR_RX_OOS_PACKETS]);
+ }
+
+ return 0;
+}
+
+static int session_nlmsg(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
+{
+ int ret = get_response(n, arg);
+
+ if (ret == 0)
+ print_session(arg);
+
+ return ret;
+}
+
+static int get_session(struct l2tp_data *p)
+{
+ GENL_REQUEST(req, 128, genl_family, 0, L2TP_GENL_VERSION,
+ L2TP_CMD_SESSION_GET,
+ NLM_F_ROOT | NLM_F_MATCH | NLM_F_REQUEST);
+
+ req.n.nlmsg_seq = genl_rth.dump = ++genl_rth.seq;
+
+ if (p->config.tunnel_id && p->config.session_id) {
+ addattr32(&req.n, 128, L2TP_ATTR_CONN_ID, p->config.tunnel_id);
+ addattr32(&req.n, 128, L2TP_ATTR_SESSION_ID, p->config.session_id);
+ }
+
+ if (rtnl_send(&genl_rth, &req, req.n.nlmsg_len) < 0)
+ return -2;
+
+ if (rtnl_dump_filter(&genl_rth, session_nlmsg, p) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ exit(1);
+ }
+
+ return 0;
+}
+
+static int tunnel_nlmsg(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
+{
+ int ret = get_response(n, arg);
+
+ if (ret == 0)
+ print_tunnel(arg);
+
+ return ret;
+}
+
+static int get_tunnel(struct l2tp_data *p)
+{
+ GENL_REQUEST(req, 1024, genl_family, 0, L2TP_GENL_VERSION,
+ L2TP_CMD_TUNNEL_GET,
+ NLM_F_ROOT | NLM_F_MATCH | NLM_F_REQUEST);
+
+ req.n.nlmsg_seq = genl_rth.dump = ++genl_rth.seq;
+
+ if (p->config.tunnel_id)
+ addattr32(&req.n, 1024, L2TP_ATTR_CONN_ID, p->config.tunnel_id);
+
+ if (rtnl_send(&genl_rth, &req, req.n.nlmsg_len) < 0)
+ return -2;
+
+ if (rtnl_dump_filter(&genl_rth, tunnel_nlmsg, p) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ exit(1);
+ }
+
+ return 0;
+}
+
+/*****************************************************************************
+ * Command parser
+ *****************************************************************************/
+
+static int hex(char ch)
+{
+ if ((ch >= 'a') && (ch <= 'f'))
+ return ch - 'a' + 10;
+ if ((ch >= '0') && (ch <= '9'))
+ return ch - '0';
+ if ((ch >= 'A') && (ch <= 'F'))
+ return ch - 'A' + 10;
+ return -1;
+}
+
+static int hex2mem(const char *buf, uint8_t *mem, int count)
+{
+ int i, j;
+ int c;
+
+ for (i = 0, j = 0; i < count; i++, j += 2) {
+ c = hex(buf[j]);
+ if (c < 0)
+ goto err;
+
+ mem[i] = c << 4;
+
+ c = hex(buf[j + 1]);
+ if (c < 0)
+ goto err;
+
+ mem[i] |= c;
+ }
+
+ return 0;
+
+err:
+ return -1;
+}
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: ip l2tp add tunnel\n");
+ fprintf(stderr, " remote ADDR local ADDR\n");
+ fprintf(stderr, " tunnel_id ID peer_tunnel_id ID\n");
+ fprintf(stderr, " [ encap { ip | udp } ]\n");
+ fprintf(stderr, " [ udp_sport PORT ] [ udp_dport PORT ]\n");
+ fprintf(stderr, "Usage: ip l2tp add session [ name NAME ]\n");
+ fprintf(stderr, " tunnel_id ID\n");
+ fprintf(stderr, " session_id ID peer_session_id ID\n");
+ fprintf(stderr, " [ cookie HEXSTR ] [ peer_cookie HEXSTR ]\n");
+ fprintf(stderr, " [ offset OFFSET ] [ peer_offset OFFSET ]\n");
+ fprintf(stderr, " [ l2spec_type L2SPEC ]\n");
+ fprintf(stderr, " ip l2tp del tunnel tunnel_id ID\n");
+ fprintf(stderr, " ip l2tp del session tunnel_id ID session_id ID\n");
+ fprintf(stderr, " ip l2tp show tunnel [ tunnel_id ID ]\n");
+ fprintf(stderr, " ip l2tp show session [ tunnel_id ID ] [ session_id ID ]\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "Where: NAME := STRING\n");
+ fprintf(stderr, " ADDR := { IP_ADDRESS | any }\n");
+ fprintf(stderr, " PORT := { 0..65535 }\n");
+ fprintf(stderr, " ID := { 1..4294967295 }\n");
+ fprintf(stderr, " HEXSTR := { 8 or 16 hex digits (4 / 8 bytes) }\n");
+ fprintf(stderr, " L2SPEC := { none | default }\n");
+ exit(-1);
+}
+
+static int parse_args(int argc, char **argv, int cmd, struct l2tp_parm *p)
+{
+ memset(p, 0, sizeof(*p));
+
+ if (argc == 0)
+ usage();
+
+ /* Defaults */
+ p->l2spec_type = L2TP_L2SPECTYPE_DEFAULT;
+ p->l2spec_len = 4;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "encap") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "ip") == 0) {
+ p->encap = L2TP_ENCAPTYPE_IP;
+ } else if (strcmp(*argv, "udp") == 0) {
+ p->encap = L2TP_ENCAPTYPE_UDP;
+ } else {
+ fprintf(stderr, "Unknown tunnel encapsulation \"%s\"\n", *argv);
+ exit(-1);
+ }
+ } else if (strcmp(*argv, "name") == 0) {
+ NEXT_ARG();
+ p->ifname = *argv;
+ } else if (strcmp(*argv, "remote") == 0) {
+ NEXT_ARG();
+ if (get_addr(&p->peer_ip, *argv, AF_UNSPEC))
+ invarg("invalid remote address\n", *argv);
+ } else if (strcmp(*argv, "local") == 0) {
+ NEXT_ARG();
+ if (get_addr(&p->local_ip, *argv, AF_UNSPEC))
+ invarg("invalid local address\n", *argv);
+ } else if ((strcmp(*argv, "tunnel_id") == 0) ||
+ (strcmp(*argv, "tid") == 0)) {
+ __u32 uval;
+ NEXT_ARG();
+ if (get_u32(&uval, *argv, 0))
+ invarg("invalid ID\n", *argv);
+ p->tunnel_id = uval;
+ } else if ((strcmp(*argv, "peer_tunnel_id") == 0) ||
+ (strcmp(*argv, "ptid") == 0)) {
+ __u32 uval;
+ NEXT_ARG();
+ if (get_u32(&uval, *argv, 0))
+ invarg("invalid ID\n", *argv);
+ p->peer_tunnel_id = uval;
+ } else if ((strcmp(*argv, "session_id") == 0) ||
+ (strcmp(*argv, "sid") == 0)) {
+ __u32 uval;
+ NEXT_ARG();
+ if (get_u32(&uval, *argv, 0))
+ invarg("invalid ID\n", *argv);
+ p->session_id = uval;
+ } else if ((strcmp(*argv, "peer_session_id") == 0) ||
+ (strcmp(*argv, "psid") == 0)) {
+ __u32 uval;
+ NEXT_ARG();
+ if (get_u32(&uval, *argv, 0))
+ invarg("invalid ID\n", *argv);
+ p->peer_session_id = uval;
+ } else if (strcmp(*argv, "udp_sport") == 0) {
+ __u16 uval;
+ NEXT_ARG();
+ if (get_u16(&uval, *argv, 0))
+ invarg("invalid port\n", *argv);
+ p->local_udp_port = uval;
+ } else if (strcmp(*argv, "udp_dport") == 0) {
+ __u16 uval;
+ NEXT_ARG();
+ if (get_u16(&uval, *argv, 0))
+ invarg("invalid port\n", *argv);
+ p->peer_udp_port = uval;
+ } else if (strcmp(*argv, "offset") == 0) {
+ __u8 uval;
+ NEXT_ARG();
+ if (get_u8(&uval, *argv, 0))
+ invarg("invalid offset\n", *argv);
+ p->offset = uval;
+ } else if (strcmp(*argv, "peer_offset") == 0) {
+ __u8 uval;
+ NEXT_ARG();
+ if (get_u8(&uval, *argv, 0))
+ invarg("invalid offset\n", *argv);
+ p->peer_offset = uval;
+ } else if (strcmp(*argv, "cookie") == 0) {
+ int slen;
+ NEXT_ARG();
+ slen = strlen(*argv);
+ if ((slen != 8) && (slen != 16))
+ invarg("cookie must be either 8 or 16 hex digits\n", *argv);
+
+ p->cookie_len = slen / 2;
+ if (hex2mem(*argv, p->cookie, p->cookie_len) < 0)
+ invarg("cookie must be a hex string\n", *argv);
+ } else if (strcmp(*argv, "peer_cookie") == 0) {
+ int slen;
+ NEXT_ARG();
+ slen = strlen(*argv);
+ if ((slen != 8) && (slen != 16))
+ invarg("cookie must be either 8 or 16 hex digits\n", *argv);
+
+ p->peer_cookie_len = slen / 2;
+ if (hex2mem(*argv, p->peer_cookie, p->peer_cookie_len) < 0)
+ invarg("cookie must be a hex string\n", *argv);
+ } else if (strcmp(*argv, "l2spec_type") == 0) {
+ NEXT_ARG();
+ if (strcasecmp(*argv, "default") == 0) {
+ p->l2spec_type = L2TP_L2SPECTYPE_DEFAULT;
+ p->l2spec_len = 4;
+ } else if (strcasecmp(*argv, "none") == 0) {
+ p->l2spec_type = L2TP_L2SPECTYPE_NONE;
+ p->l2spec_len = 0;
+ } else {
+ fprintf(stderr, "Unknown layer2specific header type \"%s\"\n", *argv);
+ exit(-1);
+ }
+ } else if (strcmp(*argv, "tunnel") == 0) {
+ p->tunnel = 1;
+ } else if (strcmp(*argv, "session") == 0) {
+ p->session = 1;
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ } else {
+ fprintf(stderr, "Unknown command: %s\n", *argv);
+ usage();
+ }
+
+ argc--; argv++;
+ }
+
+ return 0;
+}
+
+
+static int do_add(int argc, char **argv)
+{
+ struct l2tp_parm p;
+ int ret = 0;
+
+ if (parse_args(argc, argv, L2TP_ADD, &p) < 0)
+ return -1;
+
+ if (!p.tunnel && !p.session)
+ missarg("tunnel or session");
+
+ if (p.tunnel_id == 0)
+ missarg("tunnel_id");
+
+ /* session_id and peer_session_id must be provided for sessions */
+ if ((p.session) && (p.peer_session_id == 0))
+ missarg("peer_session_id");
+ if ((p.session) && (p.session_id == 0))
+ missarg("session_id");
+
+ /* peer_tunnel_id is needed for tunnels */
+ if ((p.tunnel) && (p.peer_tunnel_id == 0))
+ missarg("peer_tunnel_id");
+
+ if (p.tunnel) {
+ if (p.local_ip.family == AF_UNSPEC)
+ missarg("local");
+
+ if (p.peer_ip.family == AF_UNSPEC)
+ missarg("remote");
+
+ if (p.encap == L2TP_ENCAPTYPE_UDP) {
+ if (p.local_udp_port == 0)
+ missarg("udp_sport");
+ if (p.peer_udp_port == 0)
+ missarg("udp_dport");
+ }
+
+ ret = create_tunnel(&p);
+ }
+
+ if (p.session) {
+ /* Only ethernet pseudowires supported */
+ p.pw_type = L2TP_PWTYPE_ETH;
+
+ ret = create_session(&p);
+ }
+
+ return ret;
+}
+
+static int do_del(int argc, char **argv)
+{
+ struct l2tp_parm p;
+
+ if (parse_args(argc, argv, L2TP_DEL, &p) < 0)
+ return -1;
+
+ if (!p.tunnel && !p.session)
+ missarg("tunnel or session");
+
+ if ((p.tunnel) && (p.tunnel_id == 0))
+ missarg("tunnel_id");
+ if ((p.session) && (p.session_id == 0))
+ missarg("session_id");
+
+ if (p.session_id)
+ return delete_session(&p);
+ else
+ return delete_tunnel(&p);
+
+ return -1;
+}
+
+static int do_show(int argc, char **argv)
+{
+ struct l2tp_data data;
+ struct l2tp_parm *p = &data.config;
+
+ if (parse_args(argc, argv, L2TP_GET, p) < 0)
+ return -1;
+
+ if (!p->tunnel && !p->session)
+ missarg("tunnel or session");
+
+ if (p->session)
+ get_session(&data);
+ else
+ get_tunnel(&data);
+
+ return 0;
+}
+
+int do_ipl2tp(int argc, char **argv)
+{
+ if (genl_family < 0) {
+ if (rtnl_open_byproto(&genl_rth, 0, NETLINK_GENERIC) < 0) {
+ fprintf(stderr, "Cannot open generic netlink socket\n");
+ exit(1);
+ }
+
+ genl_family = genl_resolve_family(&genl_rth, L2TP_GENL_NAME);
+ if (genl_family < 0)
+ exit(1);
+ }
+
+ if (argc < 1)
+ usage();
+
+ if (matches(*argv, "add") == 0)
+ return do_add(argc-1, argv+1);
+ if (matches(*argv, "delete") == 0)
+ return do_del(argc-1, argv+1);
+ if (matches(*argv, "show") == 0 ||
+ matches(*argv, "lst") == 0 ||
+ matches(*argv, "list") == 0)
+ return do_show(argc-1, argv+1);
+ if (matches(*argv, "help") == 0)
+ usage();
+
+ fprintf(stderr, "Command \"%s\" is unknown, try \"ip l2tp help\".\n", *argv);
+ exit(-1);
+}
diff --git a/iproute2/ip/iplink.c b/iproute2/ip/iplink.c
new file mode 100644
index 0000000..5ab9d61
--- /dev/null
+++ b/iproute2/ip/iplink.c
@@ -0,0 +1,1272 @@
+/*
+ * iplink.c "ip link".
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <dlfcn.h>
+#include <errno.h>
+#include <sys/socket.h>
+#include <linux/if.h>
+#include <linux/if_packet.h>
+#include <linux/if_ether.h>
+#include <linux/sockios.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <linux/sockios.h>
+#include <stdbool.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+#include "namespace.h"
+
+#define IPLINK_IOCTL_COMPAT 1
+#ifndef LIBDIR
+#define LIBDIR "/usr/lib"
+#endif
+
+static void usage(void) __attribute__((noreturn));
+static int iplink_have_newlink(void);
+
+void iplink_usage(void)
+{
+ if (iplink_have_newlink()) {
+ fprintf(stderr, "Usage: ip link add [link DEV] [ name ] NAME\n");
+ fprintf(stderr, " [ txqueuelen PACKETS ]\n");
+ fprintf(stderr, " [ address LLADDR ]\n");
+ fprintf(stderr, " [ broadcast LLADDR ]\n");
+ fprintf(stderr, " [ mtu MTU ] [index IDX ]\n");
+ fprintf(stderr, " [ numtxqueues QUEUE_COUNT ]\n");
+ fprintf(stderr, " [ numrxqueues QUEUE_COUNT ]\n");
+ fprintf(stderr, " type TYPE [ ARGS ]\n");
+ fprintf(stderr, " ip link delete { DEVICE | dev DEVICE | group DEVGROUP } type TYPE [ ARGS ]\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, " ip link set { DEVICE | dev DEVICE | group DEVGROUP } [ { up | down } ]\n");
+ } else
+ fprintf(stderr, "Usage: ip link set DEVICE [ { up | down } ]\n");
+
+ fprintf(stderr, " [ arp { on | off } ]\n");
+ fprintf(stderr, " [ dynamic { on | off } ]\n");
+ fprintf(stderr, " [ multicast { on | off } ]\n");
+ fprintf(stderr, " [ allmulticast { on | off } ]\n");
+ fprintf(stderr, " [ promisc { on | off } ]\n");
+ fprintf(stderr, " [ trailers { on | off } ]\n");
+ fprintf(stderr, " [ txqueuelen PACKETS ]\n");
+ fprintf(stderr, " [ name NEWNAME ]\n");
+ fprintf(stderr, " [ address LLADDR ]\n");
+ fprintf(stderr, " [ broadcast LLADDR ]\n");
+ fprintf(stderr, " [ mtu MTU ]\n");
+ fprintf(stderr, " [ netns PID ]\n");
+ fprintf(stderr, " [ netns NAME ]\n");
+ fprintf(stderr, " [ link-netnsid ID ]\n");
+ fprintf(stderr, " [ alias NAME ]\n");
+ fprintf(stderr, " [ vf NUM [ mac LLADDR ]\n");
+ fprintf(stderr, " [ vlan VLANID [ qos VLAN-QOS ] ]\n");
+
+ fprintf(stderr, " [ rate TXRATE ] ]\n");
+
+ fprintf(stderr, " [ spoofchk { on | off} ] ]\n");
+ fprintf(stderr, " [ query_rss { on | off} ] ]\n");
+ fprintf(stderr, " [ state { auto | enable | disable} ] ]\n");
+ fprintf(stderr, " [ master DEVICE ]\n");
+ fprintf(stderr, " [ nomaster ]\n");
+ fprintf(stderr, " [ addrgenmode { eui64 | none | stable_secret | random } ]\n");
+ fprintf(stderr, " [ protodown { on | off } ]\n");
+ fprintf(stderr, " ip link show [ DEVICE | group GROUP ] [up] [master DEV] [type TYPE]\n");
+
+ if (iplink_have_newlink()) {
+ fprintf(stderr, " ip link help [ TYPE ]\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "TYPE := { vlan | veth | vcan | dummy | ifb | macvlan | macvtap |\n");
+ fprintf(stderr, " bridge | bond | ipoib | ip6tnl | ipip | sit | vxlan |\n");
+ fprintf(stderr, " gre | gretap | ip6gre | ip6gretap | vti | nlmon |\n");
+ fprintf(stderr, " bond_slave | ipvlan | geneve | bridge_slave | vrf }\n");
+ }
+ exit(-1);
+}
+
+static void usage(void)
+{
+ iplink_usage();
+}
+
+static int on_off(const char *msg, const char *realval)
+{
+ fprintf(stderr,
+ "Error: argument of \"%s\" must be \"on\" or \"off\", not \"%s\"\n",
+ msg, realval);
+ return -1;
+}
+
+static void *BODY; /* cached dlopen(NULL) handle */
+static struct link_util *linkutil_list;
+
+static struct link_util *__get_link_kind(const char *id, bool slave)
+{
+ void *dlh;
+ char buf[256];
+ struct link_util *l;
+
+ for (l = linkutil_list; l; l = l->next)
+ if (strcmp(l->id, id) == 0 &&
+ l->slave == slave)
+ return l;
+
+ snprintf(buf, sizeof(buf), LIBDIR "/ip/link_%s.so", id);
+ dlh = dlopen(buf, RTLD_LAZY);
+ if (dlh == NULL) {
+ /* look in current binary, only open once */
+ dlh = BODY;
+ if (dlh == NULL) {
+ dlh = BODY = dlopen(NULL, RTLD_LAZY);
+ if (dlh == NULL)
+ return NULL;
+ }
+ }
+
+ if (slave)
+ snprintf(buf, sizeof(buf), "%s_slave_link_util", id);
+ else
+ snprintf(buf, sizeof(buf), "%s_link_util", id);
+ l = dlsym(dlh, buf);
+ if (l == NULL)
+ return NULL;
+
+ l->next = linkutil_list;
+ linkutil_list = l;
+ return l;
+}
+
+struct link_util *get_link_kind(const char *id)
+{
+ return __get_link_kind(id, false);
+}
+
+struct link_util *get_link_slave_kind(const char *id)
+{
+ return __get_link_kind(id, true);
+}
+
+static int get_link_mode(const char *mode)
+{
+ if (strcasecmp(mode, "default") == 0)
+ return IF_LINK_MODE_DEFAULT;
+ if (strcasecmp(mode, "dormant") == 0)
+ return IF_LINK_MODE_DORMANT;
+ return -1;
+}
+
+static int get_addr_gen_mode(const char *mode)
+{
+ if (strcasecmp(mode, "eui64") == 0)
+ return IN6_ADDR_GEN_MODE_EUI64;
+ if (strcasecmp(mode, "none") == 0)
+ return IN6_ADDR_GEN_MODE_NONE;
+ if (strcasecmp(mode, "stable_secret") == 0)
+ return IN6_ADDR_GEN_MODE_STABLE_PRIVACY;
+ if (strcasecmp(mode, "random") == 0)
+ return IN6_ADDR_GEN_MODE_RANDOM;
+ return -1;
+}
+
+#if IPLINK_IOCTL_COMPAT
+static int have_rtnl_newlink = -1;
+
+static int accept_msg(const struct sockaddr_nl *who,
+ struct rtnl_ctrl_data *ctrl,
+ struct nlmsghdr *n, void *arg)
+{
+ struct nlmsgerr *err = (struct nlmsgerr *)NLMSG_DATA(n);
+
+ if (n->nlmsg_type == NLMSG_ERROR &&
+ (err->error == -EOPNOTSUPP || err->error == -EINVAL))
+ have_rtnl_newlink = 0;
+ else
+ have_rtnl_newlink = 1;
+ return -1;
+}
+
+static int iplink_have_newlink(void)
+{
+ struct {
+ struct nlmsghdr n;
+ struct ifinfomsg i;
+ char buf[1024];
+ } req;
+
+ if (have_rtnl_newlink < 0) {
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST|NLM_F_ACK;
+ req.n.nlmsg_type = RTM_NEWLINK;
+ req.i.ifi_family = AF_UNSPEC;
+
+ if (rtnl_send(&rth, &req.n, req.n.nlmsg_len) < 0) {
+ perror("request send failed");
+ exit(1);
+ }
+ rtnl_listen(&rth, accept_msg, NULL);
+ }
+ return have_rtnl_newlink;
+}
+#else /* IPLINK_IOCTL_COMPAT */
+static int iplink_have_newlink(void)
+{
+ return 1;
+}
+#endif /* ! IPLINK_IOCTL_COMPAT */
+
+struct iplink_req {
+ struct nlmsghdr n;
+ struct ifinfomsg i;
+ char buf[1024];
+};
+
+static int iplink_parse_vf(int vf, int *argcp, char ***argvp,
+ struct iplink_req *req, int dev_index)
+{
+ char new_rate_api = 0, count = 0, override_legacy_rate = 0;
+ struct ifla_vf_rate tivt;
+ int len, argc = *argcp;
+ char **argv = *argvp;
+ struct rtattr *vfinfo;
+
+ tivt.min_tx_rate = -1;
+ tivt.max_tx_rate = -1;
+
+ vfinfo = addattr_nest(&req->n, sizeof(*req), IFLA_VF_INFO);
+
+ while (NEXT_ARG_OK()) {
+ NEXT_ARG();
+ count++;
+ if (!matches(*argv, "max_tx_rate")) {
+ /* new API in use */
+ new_rate_api = 1;
+ /* override legacy rate */
+ override_legacy_rate = 1;
+ } else if (!matches(*argv, "min_tx_rate")) {
+ /* new API in use */
+ new_rate_api = 1;
+ }
+ }
+
+ while (count--) {
+ /* rewind arg */
+ PREV_ARG();
+ }
+
+ while (NEXT_ARG_OK()) {
+ NEXT_ARG();
+ if (matches(*argv, "mac") == 0) {
+ struct ifla_vf_mac ivm;
+
+ NEXT_ARG();
+ ivm.vf = vf;
+ len = ll_addr_a2n((char *)ivm.mac, 32, *argv);
+ if (len < 0)
+ return -1;
+ addattr_l(&req->n, sizeof(*req), IFLA_VF_MAC, &ivm, sizeof(ivm));
+ } else if (matches(*argv, "vlan") == 0) {
+ struct ifla_vf_vlan ivv;
+
+ NEXT_ARG();
+ if (get_unsigned(&ivv.vlan, *argv, 0))
+ invarg("Invalid \"vlan\" value\n", *argv);
+
+ ivv.vf = vf;
+ ivv.qos = 0;
+ if (NEXT_ARG_OK()) {
+ NEXT_ARG();
+ if (matches(*argv, "qos") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&ivv.qos, *argv, 0))
+ invarg("Invalid \"qos\" value\n", *argv);
+ } else {
+ /* rewind arg */
+ PREV_ARG();
+ }
+ }
+ addattr_l(&req->n, sizeof(*req), IFLA_VF_VLAN, &ivv, sizeof(ivv));
+ } else if (matches(*argv, "rate") == 0) {
+ struct ifla_vf_tx_rate ivt;
+
+ NEXT_ARG();
+ if (get_unsigned(&ivt.rate, *argv, 0))
+ invarg("Invalid \"rate\" value\n", *argv);
+
+ ivt.vf = vf;
+ if (!new_rate_api)
+ addattr_l(&req->n, sizeof(*req),
+ IFLA_VF_TX_RATE, &ivt, sizeof(ivt));
+ else if (!override_legacy_rate)
+ tivt.max_tx_rate = ivt.rate;
+
+ } else if (matches(*argv, "max_tx_rate") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&tivt.max_tx_rate, *argv, 0))
+ invarg("Invalid \"max tx rate\" value\n",
+ *argv);
+ tivt.vf = vf;
+
+ } else if (matches(*argv, "min_tx_rate") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&tivt.min_tx_rate, *argv, 0))
+ invarg("Invalid \"min tx rate\" value\n",
+ *argv);
+ tivt.vf = vf;
+
+ } else if (matches(*argv, "spoofchk") == 0) {
+ struct ifla_vf_spoofchk ivs;
+
+ NEXT_ARG();
+ if (matches(*argv, "on") == 0)
+ ivs.setting = 1;
+ else if (matches(*argv, "off") == 0)
+ ivs.setting = 0;
+ else
+ return on_off("spoofchk", *argv);
+ ivs.vf = vf;
+ addattr_l(&req->n, sizeof(*req), IFLA_VF_SPOOFCHK, &ivs, sizeof(ivs));
+
+ } else if (matches(*argv, "query_rss") == 0) {
+ struct ifla_vf_rss_query_en ivs;
+
+ NEXT_ARG();
+ if (matches(*argv, "on") == 0)
+ ivs.setting = 1;
+ else if (matches(*argv, "off") == 0)
+ ivs.setting = 0;
+ else
+ return on_off("query_rss", *argv);
+ ivs.vf = vf;
+ addattr_l(&req->n, sizeof(*req), IFLA_VF_RSS_QUERY_EN, &ivs, sizeof(ivs));
+
+ } else if (matches(*argv, "state") == 0) {
+ struct ifla_vf_link_state ivl;
+
+ NEXT_ARG();
+ if (matches(*argv, "auto") == 0)
+ ivl.link_state = IFLA_VF_LINK_STATE_AUTO;
+ else if (matches(*argv, "enable") == 0)
+ ivl.link_state = IFLA_VF_LINK_STATE_ENABLE;
+ else if (matches(*argv, "disable") == 0)
+ ivl.link_state = IFLA_VF_LINK_STATE_DISABLE;
+ else
+ invarg("Invalid \"state\" value\n", *argv);
+ ivl.vf = vf;
+ addattr_l(&req->n, sizeof(*req), IFLA_VF_LINK_STATE, &ivl, sizeof(ivl));
+ } else {
+ /* rewind arg */
+ PREV_ARG();
+ break;
+ }
+ }
+
+ if (new_rate_api) {
+ int tmin, tmax;
+
+ if (tivt.min_tx_rate == -1 || tivt.max_tx_rate == -1) {
+ ipaddr_get_vf_rate(tivt.vf, &tmin, &tmax, dev_index);
+ if (tivt.min_tx_rate == -1)
+ tivt.min_tx_rate = tmin;
+ if (tivt.max_tx_rate == -1)
+ tivt.max_tx_rate = tmax;
+ }
+ addattr_l(&req->n, sizeof(*req), IFLA_VF_RATE, &tivt,
+ sizeof(tivt));
+ }
+
+ if (argc == *argcp)
+ incomplete_command();
+
+ addattr_nest_end(&req->n, vfinfo);
+
+ *argcp = argc;
+ *argvp = argv;
+ return 0;
+}
+
+int iplink_parse(int argc, char **argv, struct iplink_req *req,
+ char **name, char **type, char **link, char **dev,
+ int *group, int *index)
+{
+ int ret, len;
+ char abuf[32];
+ int qlen = -1;
+ int mtu = -1;
+ int netns = -1;
+ int vf = -1;
+ int numtxqueues = -1;
+ int numrxqueues = -1;
+ int dev_index = 0;
+ int link_netnsid = -1;
+
+ *group = -1;
+ ret = argc;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "up") == 0) {
+ req->i.ifi_change |= IFF_UP;
+ req->i.ifi_flags |= IFF_UP;
+ } else if (strcmp(*argv, "down") == 0) {
+ req->i.ifi_change |= IFF_UP;
+ req->i.ifi_flags &= ~IFF_UP;
+ } else if (strcmp(*argv, "name") == 0) {
+ NEXT_ARG();
+ *name = *argv;
+ } else if (strcmp(*argv, "index") == 0) {
+ NEXT_ARG();
+ *index = atoi(*argv);
+ if (*index < 0)
+ invarg("Invalid \"index\" value", *argv);
+ } else if (matches(*argv, "link") == 0) {
+ NEXT_ARG();
+ *link = *argv;
+ } else if (matches(*argv, "address") == 0) {
+ NEXT_ARG();
+ len = ll_addr_a2n(abuf, sizeof(abuf), *argv);
+ if (len < 0)
+ return -1;
+ addattr_l(&req->n, sizeof(*req), IFLA_ADDRESS, abuf, len);
+ } else if (matches(*argv, "broadcast") == 0 ||
+ strcmp(*argv, "brd") == 0) {
+ NEXT_ARG();
+ len = ll_addr_a2n(abuf, sizeof(abuf), *argv);
+ if (len < 0)
+ return -1;
+ addattr_l(&req->n, sizeof(*req), IFLA_BROADCAST, abuf, len);
+ } else if (matches(*argv, "txqueuelen") == 0 ||
+ strcmp(*argv, "qlen") == 0 ||
+ matches(*argv, "txqlen") == 0) {
+ NEXT_ARG();
+ if (qlen != -1)
+ duparg("txqueuelen", *argv);
+ if (get_integer(&qlen, *argv, 0))
+ invarg("Invalid \"txqueuelen\" value\n", *argv);
+ addattr_l(&req->n, sizeof(*req), IFLA_TXQLEN, &qlen, 4);
+ } else if (strcmp(*argv, "mtu") == 0) {
+ NEXT_ARG();
+ if (mtu != -1)
+ duparg("mtu", *argv);
+ if (get_integer(&mtu, *argv, 0))
+ invarg("Invalid \"mtu\" value\n", *argv);
+ addattr_l(&req->n, sizeof(*req), IFLA_MTU, &mtu, 4);
+ } else if (strcmp(*argv, "netns") == 0) {
+ NEXT_ARG();
+ if (netns != -1)
+ duparg("netns", *argv);
+ netns = netns_get_fd(*argv);
+ if (netns >= 0)
+ addattr_l(&req->n, sizeof(*req), IFLA_NET_NS_FD, &netns, 4);
+ else if (get_integer(&netns, *argv, 0) == 0)
+ addattr_l(&req->n, sizeof(*req), IFLA_NET_NS_PID, &netns, 4);
+ else
+ invarg("Invalid \"netns\" value\n", *argv);
+ } else if (strcmp(*argv, "multicast") == 0) {
+ NEXT_ARG();
+ req->i.ifi_change |= IFF_MULTICAST;
+
+ if (strcmp(*argv, "on") == 0)
+ req->i.ifi_flags |= IFF_MULTICAST;
+ else if (strcmp(*argv, "off") == 0)
+ req->i.ifi_flags &= ~IFF_MULTICAST;
+ else
+ return on_off("multicast", *argv);
+ } else if (strcmp(*argv, "allmulticast") == 0) {
+ NEXT_ARG();
+ req->i.ifi_change |= IFF_ALLMULTI;
+
+ if (strcmp(*argv, "on") == 0)
+ req->i.ifi_flags |= IFF_ALLMULTI;
+ else if (strcmp(*argv, "off") == 0)
+ req->i.ifi_flags &= ~IFF_ALLMULTI;
+ else
+ return on_off("allmulticast", *argv);
+ } else if (strcmp(*argv, "promisc") == 0) {
+ NEXT_ARG();
+ req->i.ifi_change |= IFF_PROMISC;
+
+ if (strcmp(*argv, "on") == 0)
+ req->i.ifi_flags |= IFF_PROMISC;
+ else if (strcmp(*argv, "off") == 0)
+ req->i.ifi_flags &= ~IFF_PROMISC;
+ else
+ return on_off("promisc", *argv);
+ } else if (strcmp(*argv, "trailers") == 0) {
+ NEXT_ARG();
+ req->i.ifi_change |= IFF_NOTRAILERS;
+
+ if (strcmp(*argv, "off") == 0)
+ req->i.ifi_flags |= IFF_NOTRAILERS;
+ else if (strcmp(*argv, "on") == 0)
+ req->i.ifi_flags &= ~IFF_NOTRAILERS;
+ else
+ return on_off("trailers", *argv);
+ } else if (strcmp(*argv, "arp") == 0) {
+ NEXT_ARG();
+ req->i.ifi_change |= IFF_NOARP;
+
+ if (strcmp(*argv, "on") == 0)
+ req->i.ifi_flags &= ~IFF_NOARP;
+ else if (strcmp(*argv, "off") == 0)
+ req->i.ifi_flags |= IFF_NOARP;
+ else
+ return on_off("arp", *argv);
+ } else if (strcmp(*argv, "vf") == 0) {
+ struct rtattr *vflist;
+
+ NEXT_ARG();
+ if (get_integer(&vf, *argv, 0))
+ invarg("Invalid \"vf\" value\n", *argv);
+
+ vflist = addattr_nest(&req->n, sizeof(*req),
+ IFLA_VFINFO_LIST);
+ if (dev_index == 0)
+ missarg("dev");
+
+ len = iplink_parse_vf(vf, &argc, &argv, req, dev_index);
+ if (len < 0)
+ return -1;
+ addattr_nest_end(&req->n, vflist);
+ } else if (matches(*argv, "master") == 0) {
+ int ifindex;
+
+ NEXT_ARG();
+ ifindex = ll_name_to_index(*argv);
+ if (!ifindex)
+ invarg("Device does not exist\n", *argv);
+ addattr_l(&req->n, sizeof(*req), IFLA_MASTER,
+ &ifindex, 4);
+ } else if (matches(*argv, "nomaster") == 0) {
+ int ifindex = 0;
+
+ addattr_l(&req->n, sizeof(*req), IFLA_MASTER,
+ &ifindex, 4);
+ } else if (matches(*argv, "dynamic") == 0) {
+ NEXT_ARG();
+ req->i.ifi_change |= IFF_DYNAMIC;
+
+ if (strcmp(*argv, "on") == 0)
+ req->i.ifi_flags |= IFF_DYNAMIC;
+ else if (strcmp(*argv, "off") == 0)
+ req->i.ifi_flags &= ~IFF_DYNAMIC;
+ else
+ return on_off("dynamic", *argv);
+ } else if (matches(*argv, "type") == 0) {
+ NEXT_ARG();
+ *type = *argv;
+ argc--; argv++;
+ break;
+ } else if (matches(*argv, "alias") == 0) {
+ NEXT_ARG();
+ addattr_l(&req->n, sizeof(*req), IFLA_IFALIAS,
+ *argv, strlen(*argv));
+ argc--; argv++;
+ break;
+ } else if (strcmp(*argv, "group") == 0) {
+ NEXT_ARG();
+ if (*group != -1)
+ duparg("group", *argv);
+ if (rtnl_group_a2n(group, *argv))
+ invarg("Invalid \"group\" value\n", *argv);
+ } else if (strcmp(*argv, "mode") == 0) {
+ int mode;
+
+ NEXT_ARG();
+ mode = get_link_mode(*argv);
+ if (mode < 0)
+ invarg("Invalid link mode\n", *argv);
+ addattr8(&req->n, sizeof(*req), IFLA_LINKMODE, mode);
+ } else if (strcmp(*argv, "state") == 0) {
+ int state;
+
+ NEXT_ARG();
+ state = get_operstate(*argv);
+ if (state < 0)
+ invarg("Invalid operstate\n", *argv);
+
+ addattr8(&req->n, sizeof(*req), IFLA_OPERSTATE, state);
+ } else if (matches(*argv, "numtxqueues") == 0) {
+ NEXT_ARG();
+ if (numtxqueues != -1)
+ duparg("numtxqueues", *argv);
+ if (get_integer(&numtxqueues, *argv, 0))
+ invarg("Invalid \"numtxqueues\" value\n", *argv);
+ addattr_l(&req->n, sizeof(*req), IFLA_NUM_TX_QUEUES,
+ &numtxqueues, 4);
+ } else if (matches(*argv, "numrxqueues") == 0) {
+ NEXT_ARG();
+ if (numrxqueues != -1)
+ duparg("numrxqueues", *argv);
+ if (get_integer(&numrxqueues, *argv, 0))
+ invarg("Invalid \"numrxqueues\" value\n", *argv);
+ addattr_l(&req->n, sizeof(*req), IFLA_NUM_RX_QUEUES,
+ &numrxqueues, 4);
+ } else if (matches(*argv, "addrgenmode") == 0) {
+ struct rtattr *afs, *afs6;
+ int mode;
+
+ NEXT_ARG();
+ mode = get_addr_gen_mode(*argv);
+ if (mode < 0)
+ invarg("Invalid address generation mode\n", *argv);
+ afs = addattr_nest(&req->n, sizeof(*req), IFLA_AF_SPEC);
+ afs6 = addattr_nest(&req->n, sizeof(*req), AF_INET6);
+ addattr8(&req->n, sizeof(*req), IFLA_INET6_ADDR_GEN_MODE, mode);
+ addattr_nest_end(&req->n, afs6);
+ addattr_nest_end(&req->n, afs);
+ } else if (matches(*argv, "link-netnsid") == 0) {
+ NEXT_ARG();
+ if (link_netnsid != -1)
+ duparg("link-netnsid", *argv);
+ if (get_integer(&link_netnsid, *argv, 0))
+ invarg("Invalid \"link-netnsid\" value\n", *argv);
+ addattr32(&req->n, sizeof(*req), IFLA_LINK_NETNSID,
+ link_netnsid);
+ } else if (strcmp(*argv, "protodown") == 0) {
+ unsigned int proto_down;
+
+ NEXT_ARG();
+ if (strcmp(*argv, "on") == 0)
+ proto_down = 1;
+ else if (strcmp(*argv, "off") == 0)
+ proto_down = 0;
+ else
+ return on_off("protodown", *argv);
+ addattr8(&req->n, sizeof(*req), IFLA_PROTO_DOWN,
+ proto_down);
+ } else {
+ if (matches(*argv, "help") == 0)
+ usage();
+
+ if (strcmp(*argv, "dev") == 0)
+ NEXT_ARG();
+ if (*dev)
+ duparg2("dev", *argv);
+ *dev = *argv;
+ dev_index = ll_name_to_index(*dev);
+ }
+ argc--; argv++;
+ }
+
+ return ret - argc;
+}
+
+static int iplink_modify(int cmd, unsigned int flags, int argc, char **argv)
+{
+ int len;
+ char *dev = NULL;
+ char *name = NULL;
+ char *link = NULL;
+ char *type = NULL;
+ int index = -1;
+ int group;
+ struct link_util *lu = NULL;
+ struct iplink_req req;
+ int ret;
+
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST|flags;
+ req.n.nlmsg_type = cmd;
+ req.i.ifi_family = preferred_family;
+
+ ret = iplink_parse(argc, argv, &req, &name, &type, &link, &dev, &group, &index);
+ if (ret < 0)
+ return ret;
+
+ argc -= ret;
+ argv += ret;
+
+ if (group != -1) {
+ if (dev)
+ addattr_l(&req.n, sizeof(req), IFLA_GROUP,
+ &group, sizeof(group));
+ else {
+ if (argc) {
+ fprintf(stderr, "Garbage instead of arguments "
+ "\"%s ...\". Try \"ip link "
+ "help\".\n", *argv);
+ return -1;
+ }
+ if (flags & NLM_F_CREATE) {
+ fprintf(stderr, "group cannot be used when "
+ "creating devices.\n");
+ return -1;
+ }
+
+ req.i.ifi_index = 0;
+ addattr32(&req.n, sizeof(req), IFLA_GROUP, group);
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ return -2;
+ return 0;
+ }
+ }
+
+ if (!(flags & NLM_F_CREATE)) {
+ if (!dev) {
+ fprintf(stderr, "Not enough information: \"dev\" "
+ "argument is required.\n");
+ exit(-1);
+ }
+ if (cmd == RTM_NEWLINK && index != -1) {
+ fprintf(stderr, "index can be used only when "
+ "creating devices.\n");
+ exit(-1);
+ }
+
+ req.i.ifi_index = ll_name_to_index(dev);
+ if (req.i.ifi_index == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", dev);
+ return -1;
+ }
+ } else {
+ /* Allow "ip link add dev" and "ip link add name" */
+ if (!name)
+ name = dev;
+
+ if (link) {
+ int ifindex;
+
+ ifindex = ll_name_to_index(link);
+ if (ifindex == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n",
+ link);
+ return -1;
+ }
+ addattr_l(&req.n, sizeof(req), IFLA_LINK, &ifindex, 4);
+ }
+
+ if (index == -1)
+ req.i.ifi_index = 0;
+ else
+ req.i.ifi_index = index;
+ }
+
+ if (name) {
+ len = strlen(name) + 1;
+ if (len == 1)
+ invarg("\"\" is not a valid device identifier\n", "name");
+ if (len > IFNAMSIZ)
+ invarg("\"name\" too long\n", name);
+ addattr_l(&req.n, sizeof(req), IFLA_IFNAME, name, len);
+ }
+
+ if (type) {
+ struct rtattr *linkinfo;
+ char slavebuf[128], *ulinep = strchr(type, '_');
+ int iflatype;
+
+ linkinfo = addattr_nest(&req.n, sizeof(req), IFLA_LINKINFO);
+ addattr_l(&req.n, sizeof(req), IFLA_INFO_KIND, type,
+ strlen(type));
+
+ if (ulinep && !strcmp(ulinep, "_slave")) {
+ strncpy(slavebuf, type, sizeof(slavebuf));
+ slavebuf[sizeof(slavebuf) - 1] = '\0';
+ ulinep = strchr(slavebuf, '_');
+ /* check in case it was after sizeof(slavebuf) - 1*/
+ if (ulinep)
+ *ulinep = '\0';
+ lu = get_link_slave_kind(slavebuf);
+ iflatype = IFLA_INFO_SLAVE_DATA;
+ } else {
+ lu = get_link_kind(type);
+ iflatype = IFLA_INFO_DATA;
+ }
+ if (lu && argc) {
+ struct rtattr *data = addattr_nest(&req.n, sizeof(req), iflatype);
+
+ if (lu->parse_opt &&
+ lu->parse_opt(lu, argc, argv, &req.n))
+ return -1;
+
+ addattr_nest_end(&req.n, data);
+ } else if (argc) {
+ if (matches(*argv, "help") == 0)
+ usage();
+ fprintf(stderr, "Garbage instead of arguments \"%s ...\". "
+ "Try \"ip link help\".\n", *argv);
+ return -1;
+ }
+ addattr_nest_end(&req.n, linkinfo);
+ } else if (flags & NLM_F_CREATE) {
+ fprintf(stderr, "Not enough information: \"type\" argument "
+ "is required\n");
+ return -1;
+ }
+
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ return -2;
+
+ return 0;
+}
+
+int iplink_get(unsigned int flags, char *name, __u32 filt_mask)
+{
+ int len;
+ struct iplink_req req;
+ struct {
+ struct nlmsghdr n;
+ char buf[16384];
+ } answer;
+
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST|flags;
+ req.n.nlmsg_type = RTM_GETLINK;
+ req.i.ifi_family = preferred_family;
+
+ if (name) {
+ len = strlen(name) + 1;
+ if (len == 1)
+ invarg("\"\" is not a valid device identifier\n",
+ "name");
+ if (len > IFNAMSIZ)
+ invarg("\"name\" too long\n", name);
+ addattr_l(&req.n, sizeof(req), IFLA_IFNAME, name, len);
+ }
+ addattr32(&req.n, sizeof(req), IFLA_EXT_MASK, filt_mask);
+
+ if (rtnl_talk(&rth, &req.n, &answer.n, sizeof(answer)) < 0)
+ return -2;
+
+ if (brief)
+ print_linkinfo_brief(NULL, &answer.n, stdout);
+ else
+ print_linkinfo(NULL, &answer.n, stdout);
+
+ return 0;
+}
+
+#if IPLINK_IOCTL_COMPAT
+static int get_ctl_fd(void)
+{
+ int s_errno;
+ int fd;
+
+ fd = socket(PF_INET, SOCK_DGRAM, 0);
+ if (fd >= 0)
+ return fd;
+ s_errno = errno;
+ fd = socket(PF_PACKET, SOCK_DGRAM, 0);
+ if (fd >= 0)
+ return fd;
+ fd = socket(PF_INET6, SOCK_DGRAM, 0);
+ if (fd >= 0)
+ return fd;
+ errno = s_errno;
+ perror("Cannot create control socket");
+ return -1;
+}
+
+static int do_chflags(const char *dev, __u32 flags, __u32 mask)
+{
+ struct ifreq ifr;
+ int fd;
+ int err;
+
+ strncpy(ifr.ifr_name, dev, IFNAMSIZ);
+ fd = get_ctl_fd();
+ if (fd < 0)
+ return -1;
+ err = ioctl(fd, SIOCGIFFLAGS, &ifr);
+ if (err) {
+ perror("SIOCGIFFLAGS");
+ close(fd);
+ return -1;
+ }
+ if ((ifr.ifr_flags^flags)&mask) {
+ ifr.ifr_flags &= ~mask;
+ ifr.ifr_flags |= mask&flags;
+ err = ioctl(fd, SIOCSIFFLAGS, &ifr);
+ if (err)
+ perror("SIOCSIFFLAGS");
+ }
+ close(fd);
+ return err;
+}
+
+static int do_changename(const char *dev, const char *newdev)
+{
+ struct ifreq ifr;
+ int fd;
+ int err;
+
+ strncpy(ifr.ifr_name, dev, IFNAMSIZ);
+ strncpy(ifr.ifr_newname, newdev, IFNAMSIZ);
+ fd = get_ctl_fd();
+ if (fd < 0)
+ return -1;
+ err = ioctl(fd, SIOCSIFNAME, &ifr);
+ if (err) {
+ perror("SIOCSIFNAME");
+ close(fd);
+ return -1;
+ }
+ close(fd);
+ return err;
+}
+
+static int set_qlen(const char *dev, int qlen)
+{
+ struct ifreq ifr;
+ int s;
+
+ s = get_ctl_fd();
+ if (s < 0)
+ return -1;
+
+ memset(&ifr, 0, sizeof(ifr));
+ strncpy(ifr.ifr_name, dev, IFNAMSIZ);
+ ifr.ifr_qlen = qlen;
+ if (ioctl(s, SIOCSIFTXQLEN, &ifr) < 0) {
+ perror("SIOCSIFXQLEN");
+ close(s);
+ return -1;
+ }
+ close(s);
+
+ return 0;
+}
+
+static int set_mtu(const char *dev, int mtu)
+{
+ struct ifreq ifr;
+ int s;
+
+ s = get_ctl_fd();
+ if (s < 0)
+ return -1;
+
+ memset(&ifr, 0, sizeof(ifr));
+ strncpy(ifr.ifr_name, dev, IFNAMSIZ);
+ ifr.ifr_mtu = mtu;
+ if (ioctl(s, SIOCSIFMTU, &ifr) < 0) {
+ perror("SIOCSIFMTU");
+ close(s);
+ return -1;
+ }
+ close(s);
+
+ return 0;
+}
+
+static int get_address(const char *dev, int *htype)
+{
+ struct ifreq ifr;
+ struct sockaddr_ll me;
+ socklen_t alen;
+ int s;
+
+ s = socket(PF_PACKET, SOCK_DGRAM, 0);
+ if (s < 0) {
+ perror("socket(PF_PACKET)");
+ return -1;
+ }
+
+ memset(&ifr, 0, sizeof(ifr));
+ strncpy(ifr.ifr_name, dev, IFNAMSIZ);
+ if (ioctl(s, SIOCGIFINDEX, &ifr) < 0) {
+ perror("SIOCGIFINDEX");
+ close(s);
+ return -1;
+ }
+
+ memset(&me, 0, sizeof(me));
+ me.sll_family = AF_PACKET;
+ me.sll_ifindex = ifr.ifr_ifindex;
+ me.sll_protocol = htons(ETH_P_LOOP);
+ if (bind(s, (struct sockaddr *)&me, sizeof(me)) == -1) {
+ perror("bind");
+ close(s);
+ return -1;
+ }
+
+ alen = sizeof(me);
+ if (getsockname(s, (struct sockaddr *)&me, &alen) == -1) {
+ perror("getsockname");
+ close(s);
+ return -1;
+ }
+ close(s);
+ *htype = me.sll_hatype;
+ return me.sll_halen;
+}
+
+static int parse_address(const char *dev, int hatype, int halen,
+ char *lla, struct ifreq *ifr)
+{
+ int alen;
+
+ memset(ifr, 0, sizeof(*ifr));
+ strncpy(ifr->ifr_name, dev, IFNAMSIZ);
+ ifr->ifr_hwaddr.sa_family = hatype;
+ alen = ll_addr_a2n(ifr->ifr_hwaddr.sa_data, 14, lla);
+ if (alen < 0)
+ return -1;
+ if (alen != halen) {
+ fprintf(stderr, "Wrong address (%s) length: expected %d bytes\n", lla, halen);
+ return -1;
+ }
+ return 0;
+}
+
+static int set_address(struct ifreq *ifr, int brd)
+{
+ int s;
+
+ s = get_ctl_fd();
+ if (s < 0)
+ return -1;
+ if (ioctl(s, brd?SIOCSIFHWBROADCAST:SIOCSIFHWADDR, ifr) < 0) {
+ perror(brd?"SIOCSIFHWBROADCAST":"SIOCSIFHWADDR");
+ close(s);
+ return -1;
+ }
+ close(s);
+ return 0;
+}
+
+static int do_set(int argc, char **argv)
+{
+ char *dev = NULL;
+ __u32 mask = 0;
+ __u32 flags = 0;
+ int qlen = -1;
+ int mtu = -1;
+ char *newaddr = NULL;
+ char *newbrd = NULL;
+ struct ifreq ifr0, ifr1;
+ char *newname = NULL;
+ int htype, halen;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "up") == 0) {
+ mask |= IFF_UP;
+ flags |= IFF_UP;
+ } else if (strcmp(*argv, "down") == 0) {
+ mask |= IFF_UP;
+ flags &= ~IFF_UP;
+ } else if (strcmp(*argv, "name") == 0) {
+ NEXT_ARG();
+ newname = *argv;
+ } else if (matches(*argv, "address") == 0) {
+ NEXT_ARG();
+ newaddr = *argv;
+ } else if (matches(*argv, "broadcast") == 0 ||
+ strcmp(*argv, "brd") == 0) {
+ NEXT_ARG();
+ newbrd = *argv;
+ } else if (matches(*argv, "txqueuelen") == 0 ||
+ strcmp(*argv, "qlen") == 0 ||
+ matches(*argv, "txqlen") == 0) {
+ NEXT_ARG();
+ if (qlen != -1)
+ duparg("txqueuelen", *argv);
+ if (get_integer(&qlen, *argv, 0))
+ invarg("Invalid \"txqueuelen\" value\n", *argv);
+ } else if (strcmp(*argv, "mtu") == 0) {
+ NEXT_ARG();
+ if (mtu != -1)
+ duparg("mtu", *argv);
+ if (get_integer(&mtu, *argv, 0))
+ invarg("Invalid \"mtu\" value\n", *argv);
+ } else if (strcmp(*argv, "multicast") == 0) {
+ NEXT_ARG();
+ mask |= IFF_MULTICAST;
+
+ if (strcmp(*argv, "on") == 0)
+ flags |= IFF_MULTICAST;
+ else if (strcmp(*argv, "off") == 0)
+ flags &= ~IFF_MULTICAST;
+ else
+ return on_off("multicast", *argv);
+ } else if (strcmp(*argv, "allmulticast") == 0) {
+ NEXT_ARG();
+ mask |= IFF_ALLMULTI;
+
+ if (strcmp(*argv, "on") == 0)
+ flags |= IFF_ALLMULTI;
+ else if (strcmp(*argv, "off") == 0)
+ flags &= ~IFF_ALLMULTI;
+ else
+ return on_off("allmulticast", *argv);
+ } else if (strcmp(*argv, "promisc") == 0) {
+ NEXT_ARG();
+ mask |= IFF_PROMISC;
+
+ if (strcmp(*argv, "on") == 0)
+ flags |= IFF_PROMISC;
+ else if (strcmp(*argv, "off") == 0)
+ flags &= ~IFF_PROMISC;
+ else
+ return on_off("promisc", *argv);
+ } else if (strcmp(*argv, "trailers") == 0) {
+ NEXT_ARG();
+ mask |= IFF_NOTRAILERS;
+
+ if (strcmp(*argv, "off") == 0)
+ flags |= IFF_NOTRAILERS;
+ else if (strcmp(*argv, "on") == 0)
+ flags &= ~IFF_NOTRAILERS;
+ else
+ return on_off("trailers", *argv);
+ } else if (strcmp(*argv, "arp") == 0) {
+ NEXT_ARG();
+ mask |= IFF_NOARP;
+
+ if (strcmp(*argv, "on") == 0)
+ flags &= ~IFF_NOARP;
+ else if (strcmp(*argv, "off") == 0)
+ flags |= IFF_NOARP;
+ else
+ return on_off("arp", *argv);
+ } else if (matches(*argv, "dynamic") == 0) {
+ NEXT_ARG();
+ mask |= IFF_DYNAMIC;
+
+ if (strcmp(*argv, "on") == 0)
+ flags |= IFF_DYNAMIC;
+ else if (strcmp(*argv, "off") == 0)
+ flags &= ~IFF_DYNAMIC;
+ else
+ return on_off("dynamic", *argv);
+ } else {
+ if (strcmp(*argv, "dev") == 0)
+ NEXT_ARG();
+ else if (matches(*argv, "help") == 0)
+ usage();
+
+ if (dev)
+ duparg2("dev", *argv);
+ dev = *argv;
+ }
+ argc--; argv++;
+ }
+
+ if (!dev) {
+ fprintf(stderr, "Not enough of information: \"dev\" argument is required.\n");
+ exit(-1);
+ }
+
+ if (newaddr || newbrd) {
+ halen = get_address(dev, &htype);
+ if (halen < 0)
+ return -1;
+ if (newaddr) {
+ if (parse_address(dev, htype, halen, newaddr, &ifr0) < 0)
+ return -1;
+ }
+ if (newbrd) {
+ if (parse_address(dev, htype, halen, newbrd, &ifr1) < 0)
+ return -1;
+ }
+ }
+
+ if (newname && strcmp(dev, newname)) {
+ if (strlen(newname) == 0)
+ invarg("\"\" is not a valid device identifier\n", "name");
+ if (do_changename(dev, newname) < 0)
+ return -1;
+ dev = newname;
+ }
+ if (qlen != -1) {
+ if (set_qlen(dev, qlen) < 0)
+ return -1;
+ }
+ if (mtu != -1) {
+ if (set_mtu(dev, mtu) < 0)
+ return -1;
+ }
+ if (newaddr || newbrd) {
+ if (newbrd) {
+ if (set_address(&ifr1, 1) < 0)
+ return -1;
+ }
+ if (newaddr) {
+ if (set_address(&ifr0, 0) < 0)
+ return -1;
+ }
+ }
+ if (mask)
+ return do_chflags(dev, flags, mask);
+ return 0;
+}
+#endif /* IPLINK_IOCTL_COMPAT */
+
+static void do_help(int argc, char **argv)
+{
+ struct link_util *lu = NULL;
+
+ if (argc <= 0) {
+ usage();
+ return;
+ }
+
+ lu = get_link_kind(*argv);
+ if (lu && lu->print_help)
+ lu->print_help(lu, argc-1, argv+1, stdout);
+ else
+ usage();
+}
+
+int do_iplink(int argc, char **argv)
+{
+ if (argc < 1)
+ return ipaddr_list_link(0, NULL);
+
+ if (iplink_have_newlink()) {
+ if (matches(*argv, "add") == 0)
+ return iplink_modify(RTM_NEWLINK,
+ NLM_F_CREATE|NLM_F_EXCL,
+ argc-1, argv+1);
+ if (matches(*argv, "set") == 0 ||
+ matches(*argv, "change") == 0)
+ return iplink_modify(RTM_NEWLINK, 0,
+ argc-1, argv+1);
+ if (matches(*argv, "replace") == 0)
+ return iplink_modify(RTM_NEWLINK,
+ NLM_F_CREATE|NLM_F_REPLACE,
+ argc-1, argv+1);
+ if (matches(*argv, "delete") == 0)
+ return iplink_modify(RTM_DELLINK, 0,
+ argc-1, argv+1);
+ } else {
+#if IPLINK_IOCTL_COMPAT
+ if (matches(*argv, "set") == 0)
+ return do_set(argc-1, argv+1);
+#endif
+ }
+
+ if (matches(*argv, "show") == 0 ||
+ matches(*argv, "lst") == 0 ||
+ matches(*argv, "list") == 0)
+ return ipaddr_list_link(argc-1, argv+1);
+
+ if (matches(*argv, "help") == 0) {
+ do_help(argc-1, argv+1);
+ return 0;
+ }
+
+ fprintf(stderr, "Command \"%s\" is unknown, try \"ip link help\".\n",
+ *argv);
+ exit(-1);
+}
diff --git a/iproute2/ip/iplink_bond.c b/iproute2/ip/iplink_bond.c
new file mode 100644
index 0000000..cb2f045
--- /dev/null
+++ b/iproute2/ip/iplink_bond.c
@@ -0,0 +1,583 @@
+/*
+ * iplink_bond.c Bonding device support
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Jiri Pirko <jiri@resnulli.us>
+ * Scott Feldman <sfeldma@cumulusnetworks.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/if_link.h>
+#include <linux/if_ether.h>
+#include <net/if.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+
+#define BOND_MAX_ARP_TARGETS 16
+
+static const char *mode_tbl[] = {
+ "balance-rr",
+ "active-backup",
+ "balance-xor",
+ "broadcast",
+ "802.3ad",
+ "balance-tlb",
+ "balance-alb",
+ NULL,
+};
+
+static const char *arp_validate_tbl[] = {
+ "none",
+ "active",
+ "backup",
+ "all",
+ NULL,
+};
+
+static const char *arp_all_targets_tbl[] = {
+ "any",
+ "all",
+ NULL,
+};
+
+static const char *primary_reselect_tbl[] = {
+ "always",
+ "better",
+ "failure",
+ NULL,
+};
+
+static const char *fail_over_mac_tbl[] = {
+ "none",
+ "active",
+ "follow",
+ NULL,
+};
+
+static const char *xmit_hash_policy_tbl[] = {
+ "layer2",
+ "layer3+4",
+ "layer2+3",
+ "encap2+3",
+ "encap3+4",
+ NULL,
+};
+
+static const char *lacp_rate_tbl[] = {
+ "slow",
+ "fast",
+ NULL,
+};
+
+static const char *ad_select_tbl[] = {
+ "stable",
+ "bandwidth",
+ "count",
+ NULL,
+};
+
+static const char *get_name(const char **tbl, int index)
+{
+ int i;
+
+ for (i = 0; tbl[i]; i++)
+ if (i == index)
+ return tbl[i];
+
+ return "UNKNOWN";
+}
+
+static int get_index(const char **tbl, char *name)
+{
+ int i, index;
+
+ /* check for integer index passed in instead of name */
+ if (get_integer(&index, name, 10) == 0)
+ for (i = 0; tbl[i]; i++)
+ if (i == index)
+ return i;
+
+ for (i = 0; tbl[i]; i++)
+ if (strcmp(tbl[i], name) == 0)
+ return i;
+
+ return -1;
+}
+
+static void print_explain(FILE *f)
+{
+ fprintf(f,
+ "Usage: ... bond [ mode BONDMODE ] [ active_slave SLAVE_DEV ]\n"
+ " [ clear_active_slave ] [ miimon MIIMON ]\n"
+ " [ updelay UPDELAY ] [ downdelay DOWNDELAY ]\n"
+ " [ use_carrier USE_CARRIER ]\n"
+ " [ arp_interval ARP_INTERVAL ]\n"
+ " [ arp_validate ARP_VALIDATE ]\n"
+ " [ arp_all_targets ARP_ALL_TARGETS ]\n"
+ " [ arp_ip_target [ ARP_IP_TARGET, ... ] ]\n"
+ " [ primary SLAVE_DEV ]\n"
+ " [ primary_reselect PRIMARY_RESELECT ]\n"
+ " [ fail_over_mac FAIL_OVER_MAC ]\n"
+ " [ xmit_hash_policy XMIT_HASH_POLICY ]\n"
+ " [ resend_igmp RESEND_IGMP ]\n"
+ " [ num_grat_arp|num_unsol_na NUM_GRAT_ARP|NUM_UNSOL_NA ]\n"
+ " [ all_slaves_active ALL_SLAVES_ACTIVE ]\n"
+ " [ min_links MIN_LINKS ]\n"
+ " [ lp_interval LP_INTERVAL ]\n"
+ " [ packets_per_slave PACKETS_PER_SLAVE ]\n"
+ " [ tlb_dynamic_lb TLB_DYNAMIC_LB ]\n"
+ " [ lacp_rate LACP_RATE ]\n"
+ " [ ad_select AD_SELECT ]\n"
+ " [ ad_user_port_key PORTKEY ]\n"
+ " [ ad_actor_sys_prio SYSPRIO ]\n"
+ " [ ad_actor_system LLADDR ]\n"
+ "\n"
+ "BONDMODE := balance-rr|active-backup|balance-xor|broadcast|802.3ad|balance-tlb|balance-alb\n"
+ "ARP_VALIDATE := none|active|backup|all\n"
+ "ARP_ALL_TARGETS := any|all\n"
+ "PRIMARY_RESELECT := always|better|failure\n"
+ "FAIL_OVER_MAC := none|active|follow\n"
+ "XMIT_HASH_POLICY := layer2|layer2+3|layer3+4|encap2+3|encap3+4\n"
+ "LACP_RATE := slow|fast\n"
+ "AD_SELECT := stable|bandwidth|count\n"
+ );
+}
+
+static void explain(void)
+{
+ print_explain(stderr);
+}
+
+static int bond_parse_opt(struct link_util *lu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ __u8 mode, use_carrier, primary_reselect, fail_over_mac;
+ __u8 xmit_hash_policy, num_peer_notif, all_slaves_active;
+ __u8 lacp_rate, ad_select, tlb_dynamic_lb;
+ __u16 ad_user_port_key, ad_actor_sys_prio;
+ __u32 miimon, updelay, downdelay, arp_interval, arp_validate;
+ __u32 arp_all_targets, resend_igmp, min_links, lp_interval;
+ __u32 packets_per_slave;
+ unsigned ifindex;
+
+ while (argc > 0) {
+ if (matches(*argv, "mode") == 0) {
+ NEXT_ARG();
+ if (get_index(mode_tbl, *argv) < 0)
+ invarg("invalid mode", *argv);
+ mode = get_index(mode_tbl, *argv);
+ addattr8(n, 1024, IFLA_BOND_MODE, mode);
+ } else if (matches(*argv, "active_slave") == 0) {
+ NEXT_ARG();
+ ifindex = if_nametoindex(*argv);
+ if (!ifindex)
+ return -1;
+ addattr32(n, 1024, IFLA_BOND_ACTIVE_SLAVE, ifindex);
+ } else if (matches(*argv, "clear_active_slave") == 0) {
+ addattr32(n, 1024, IFLA_BOND_ACTIVE_SLAVE, 0);
+ } else if (matches(*argv, "miimon") == 0) {
+ NEXT_ARG();
+ if (get_u32(&miimon, *argv, 0))
+ invarg("invalid miimon", *argv);
+ addattr32(n, 1024, IFLA_BOND_MIIMON, miimon);
+ } else if (matches(*argv, "updelay") == 0) {
+ NEXT_ARG();
+ if (get_u32(&updelay, *argv, 0))
+ invarg("invalid updelay", *argv);
+ addattr32(n, 1024, IFLA_BOND_UPDELAY, updelay);
+ } else if (matches(*argv, "downdelay") == 0) {
+ NEXT_ARG();
+ if (get_u32(&downdelay, *argv, 0))
+ invarg("invalid downdelay", *argv);
+ addattr32(n, 1024, IFLA_BOND_DOWNDELAY, downdelay);
+ } else if (matches(*argv, "use_carrier") == 0) {
+ NEXT_ARG();
+ if (get_u8(&use_carrier, *argv, 0))
+ invarg("invalid use_carrier", *argv);
+ addattr8(n, 1024, IFLA_BOND_USE_CARRIER, use_carrier);
+ } else if (matches(*argv, "arp_interval") == 0) {
+ NEXT_ARG();
+ if (get_u32(&arp_interval, *argv, 0))
+ invarg("invalid arp_interval", *argv);
+ addattr32(n, 1024, IFLA_BOND_ARP_INTERVAL, arp_interval);
+ } else if (matches(*argv, "arp_ip_target") == 0) {
+ struct rtattr * nest = addattr_nest(n, 1024,
+ IFLA_BOND_ARP_IP_TARGET);
+ if (NEXT_ARG_OK()) {
+ NEXT_ARG();
+ char *targets = strdupa(*argv);
+ char *target = strtok(targets, ",");
+ int i;
+
+ for(i = 0; target && i < BOND_MAX_ARP_TARGETS; i++) {
+ __u32 addr = get_addr32(target);
+ addattr32(n, 1024, i, addr);
+ target = strtok(NULL, ",");
+ }
+ addattr_nest_end(n, nest);
+ }
+ addattr_nest_end(n, nest);
+ } else if (matches(*argv, "arp_validate") == 0) {
+ NEXT_ARG();
+ if (get_index(arp_validate_tbl, *argv) < 0)
+ invarg("invalid arp_validate", *argv);
+ arp_validate = get_index(arp_validate_tbl, *argv);
+ addattr32(n, 1024, IFLA_BOND_ARP_VALIDATE, arp_validate);
+ } else if (matches(*argv, "arp_all_targets") == 0) {
+ NEXT_ARG();
+ if (get_index(arp_all_targets_tbl, *argv) < 0)
+ invarg("invalid arp_all_targets", *argv);
+ arp_all_targets = get_index(arp_all_targets_tbl, *argv);
+ addattr32(n, 1024, IFLA_BOND_ARP_ALL_TARGETS, arp_all_targets);
+ } else if (matches(*argv, "primary") == 0) {
+ NEXT_ARG();
+ ifindex = if_nametoindex(*argv);
+ if (!ifindex)
+ return -1;
+ addattr32(n, 1024, IFLA_BOND_PRIMARY, ifindex);
+ } else if (matches(*argv, "primary_reselect") == 0) {
+ NEXT_ARG();
+ if (get_index(primary_reselect_tbl, *argv) < 0)
+ invarg("invalid primary_reselect", *argv);
+ primary_reselect = get_index(primary_reselect_tbl, *argv);
+ addattr8(n, 1024, IFLA_BOND_PRIMARY_RESELECT,
+ primary_reselect);
+ } else if (matches(*argv, "fail_over_mac") == 0) {
+ NEXT_ARG();
+ if (get_index(fail_over_mac_tbl, *argv) < 0)
+ invarg("invalid fail_over_mac", *argv);
+ fail_over_mac = get_index(fail_over_mac_tbl, *argv);
+ addattr8(n, 1024, IFLA_BOND_FAIL_OVER_MAC,
+ fail_over_mac);
+ } else if (matches(*argv, "xmit_hash_policy") == 0) {
+ NEXT_ARG();
+ if (get_index(xmit_hash_policy_tbl, *argv) < 0)
+ invarg("invalid xmit_hash_policy", *argv);
+
+ xmit_hash_policy = get_index(xmit_hash_policy_tbl, *argv);
+ addattr8(n, 1024, IFLA_BOND_XMIT_HASH_POLICY,
+ xmit_hash_policy);
+ } else if (matches(*argv, "resend_igmp") == 0) {
+ NEXT_ARG();
+ if (get_u32(&resend_igmp, *argv, 0))
+ invarg("invalid resend_igmp", *argv);
+
+ addattr32(n, 1024, IFLA_BOND_RESEND_IGMP, resend_igmp);
+ } else if (matches(*argv, "num_grat_arp") == 0 ||
+ matches(*argv, "num_unsol_na") == 0) {
+ NEXT_ARG();
+ if (get_u8(&num_peer_notif, *argv, 0))
+ invarg("invalid num_grat_arp|num_unsol_na",
+ *argv);
+
+ addattr8(n, 1024, IFLA_BOND_NUM_PEER_NOTIF,
+ num_peer_notif);
+ } else if (matches(*argv, "all_slaves_active") == 0) {
+ NEXT_ARG();
+ if (get_u8(&all_slaves_active, *argv, 0))
+ invarg("invalid all_slaves_active", *argv);
+
+ addattr8(n, 1024, IFLA_BOND_ALL_SLAVES_ACTIVE,
+ all_slaves_active);
+ } else if (matches(*argv, "min_links") == 0) {
+ NEXT_ARG();
+ if (get_u32(&min_links, *argv, 0))
+ invarg("invalid min_links", *argv);
+
+ addattr32(n, 1024, IFLA_BOND_MIN_LINKS, min_links);
+ } else if (matches(*argv, "lp_interval") == 0) {
+ NEXT_ARG();
+ if (get_u32(&lp_interval, *argv, 0))
+ invarg("invalid lp_interval", *argv);
+
+ addattr32(n, 1024, IFLA_BOND_LP_INTERVAL, lp_interval);
+ } else if (matches(*argv, "packets_per_slave") == 0) {
+ NEXT_ARG();
+ if (get_u32(&packets_per_slave, *argv, 0))
+ invarg("invalid packets_per_slave", *argv);
+
+ addattr32(n, 1024, IFLA_BOND_PACKETS_PER_SLAVE,
+ packets_per_slave);
+ } else if (matches(*argv, "lacp_rate") == 0) {
+ NEXT_ARG();
+ if (get_index(lacp_rate_tbl, *argv) < 0)
+ invarg("invalid lacp_rate", *argv);
+
+ lacp_rate = get_index(lacp_rate_tbl, *argv);
+ addattr8(n, 1024, IFLA_BOND_AD_LACP_RATE, lacp_rate);
+ } else if (matches(*argv, "ad_select") == 0) {
+ NEXT_ARG();
+ if (get_index(ad_select_tbl, *argv) < 0)
+ invarg("invalid ad_select", *argv);
+
+ ad_select = get_index(ad_select_tbl, *argv);
+ addattr8(n, 1024, IFLA_BOND_AD_SELECT, ad_select);
+ } else if (matches(*argv, "ad_user_port_key") == 0) {
+ NEXT_ARG();
+ if (get_u16(&ad_user_port_key, *argv, 0))
+ invarg("invalid ad_user_port_key", *argv);
+
+ addattr16(n, 1024, IFLA_BOND_AD_USER_PORT_KEY,
+ ad_user_port_key);
+ } else if (matches(*argv, "ad_actor_sys_prio") == 0) {
+ NEXT_ARG();
+ if (get_u16(&ad_actor_sys_prio, *argv, 0))
+ invarg("invalid ad_actor_sys_prio", *argv);
+
+ addattr16(n, 1024, IFLA_BOND_AD_ACTOR_SYS_PRIO,
+ ad_actor_sys_prio);
+ } else if (matches(*argv, "ad_actor_system") == 0) {
+ int len;
+ char abuf[32];
+
+ NEXT_ARG();
+ len = ll_addr_a2n(abuf, sizeof(abuf), *argv);
+ if (len < 0)
+ return -1;
+ addattr_l(n, 1024, IFLA_BOND_AD_ACTOR_SYSTEM,
+ abuf, len);
+ } else if (matches(*argv, "tlb_dynamic_lb") == 0) {
+ NEXT_ARG();
+ if (get_u8(&tlb_dynamic_lb, *argv, 0)) {
+ invarg("invalid tlb_dynamic_lb", *argv);
+ return -1;
+ }
+ addattr8(n, 1024, IFLA_BOND_TLB_DYNAMIC_LB,
+ tlb_dynamic_lb);
+ } else if (matches(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "bond: unknown command \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--, argv++;
+ }
+
+ return 0;
+}
+
+static void bond_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
+{
+ unsigned ifindex;
+
+ if (!tb)
+ return;
+
+ if (tb[IFLA_BOND_MODE]) {
+ const char *mode = get_name(mode_tbl,
+ rta_getattr_u8(tb[IFLA_BOND_MODE]));
+ fprintf(f, "mode %s ", mode);
+ }
+
+ if (tb[IFLA_BOND_ACTIVE_SLAVE] &&
+ (ifindex = rta_getattr_u32(tb[IFLA_BOND_ACTIVE_SLAVE]))) {
+ char buf[IFNAMSIZ];
+ const char *n = if_indextoname(ifindex, buf);
+
+ if (n)
+ fprintf(f, "active_slave %s ", n);
+ else
+ fprintf(f, "active_slave %u ", ifindex);
+ }
+
+ if (tb[IFLA_BOND_MIIMON])
+ fprintf(f, "miimon %u ", rta_getattr_u32(tb[IFLA_BOND_MIIMON]));
+
+ if (tb[IFLA_BOND_UPDELAY])
+ fprintf(f, "updelay %u ", rta_getattr_u32(tb[IFLA_BOND_UPDELAY]));
+
+ if (tb[IFLA_BOND_DOWNDELAY])
+ fprintf(f, "downdelay %u ",
+ rta_getattr_u32(tb[IFLA_BOND_DOWNDELAY]));
+
+ if (tb[IFLA_BOND_USE_CARRIER])
+ fprintf(f, "use_carrier %u ",
+ rta_getattr_u8(tb[IFLA_BOND_USE_CARRIER]));
+
+ if (tb[IFLA_BOND_ARP_INTERVAL])
+ fprintf(f, "arp_interval %u ",
+ rta_getattr_u32(tb[IFLA_BOND_ARP_INTERVAL]));
+
+ if (tb[IFLA_BOND_ARP_IP_TARGET]) {
+ struct rtattr *iptb[BOND_MAX_ARP_TARGETS + 1];
+ char buf[INET_ADDRSTRLEN];
+ int i;
+
+ parse_rtattr_nested(iptb, BOND_MAX_ARP_TARGETS,
+ tb[IFLA_BOND_ARP_IP_TARGET]);
+
+ if (iptb[0])
+ fprintf(f, "arp_ip_target ");
+
+ for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) {
+ if (iptb[i])
+ fprintf(f, "%s",
+ rt_addr_n2a(AF_INET,
+ RTA_PAYLOAD(iptb[i]),
+ RTA_DATA(iptb[i]),
+ buf,
+ INET_ADDRSTRLEN));
+ if (i < BOND_MAX_ARP_TARGETS-1 && iptb[i+1])
+ fprintf(f, ",");
+ }
+
+ if (iptb[0])
+ fprintf(f, " ");
+ }
+
+ if (tb[IFLA_BOND_ARP_VALIDATE]) {
+ const char *arp_validate = get_name(arp_validate_tbl,
+ rta_getattr_u32(tb[IFLA_BOND_ARP_VALIDATE]));
+ fprintf(f, "arp_validate %s ", arp_validate);
+ }
+
+ if (tb[IFLA_BOND_ARP_ALL_TARGETS]) {
+ const char *arp_all_targets = get_name(arp_all_targets_tbl,
+ rta_getattr_u32(tb[IFLA_BOND_ARP_ALL_TARGETS]));
+ fprintf(f, "arp_all_targets %s ", arp_all_targets);
+ }
+
+ if (tb[IFLA_BOND_PRIMARY] &&
+ (ifindex = rta_getattr_u32(tb[IFLA_BOND_PRIMARY]))) {
+ char buf[IFNAMSIZ];
+ const char *n = if_indextoname(ifindex, buf);
+
+ if (n)
+ fprintf(f, "primary %s ", n);
+ else
+ fprintf(f, "primary %u ", ifindex);
+ }
+
+ if (tb[IFLA_BOND_PRIMARY_RESELECT]) {
+ const char *primary_reselect = get_name(primary_reselect_tbl,
+ rta_getattr_u8(tb[IFLA_BOND_PRIMARY_RESELECT]));
+ fprintf(f, "primary_reselect %s ", primary_reselect);
+ }
+
+ if (tb[IFLA_BOND_FAIL_OVER_MAC]) {
+ const char *fail_over_mac = get_name(fail_over_mac_tbl,
+ rta_getattr_u8(tb[IFLA_BOND_FAIL_OVER_MAC]));
+ fprintf(f, "fail_over_mac %s ", fail_over_mac);
+ }
+
+ if (tb[IFLA_BOND_XMIT_HASH_POLICY]) {
+ const char *xmit_hash_policy = get_name(xmit_hash_policy_tbl,
+ rta_getattr_u8(tb[IFLA_BOND_XMIT_HASH_POLICY]));
+ fprintf(f, "xmit_hash_policy %s ", xmit_hash_policy);
+ }
+
+ if (tb[IFLA_BOND_RESEND_IGMP])
+ fprintf(f, "resend_igmp %u ",
+ rta_getattr_u32(tb[IFLA_BOND_RESEND_IGMP]));
+
+ if (tb[IFLA_BOND_NUM_PEER_NOTIF])
+ fprintf(f, "num_grat_arp %u ",
+ rta_getattr_u8(tb[IFLA_BOND_NUM_PEER_NOTIF]));
+
+ if (tb[IFLA_BOND_ALL_SLAVES_ACTIVE])
+ fprintf(f, "all_slaves_active %u ",
+ rta_getattr_u8(tb[IFLA_BOND_ALL_SLAVES_ACTIVE]));
+
+ if (tb[IFLA_BOND_MIN_LINKS])
+ fprintf(f, "min_links %u ",
+ rta_getattr_u32(tb[IFLA_BOND_MIN_LINKS]));
+
+ if (tb[IFLA_BOND_LP_INTERVAL])
+ fprintf(f, "lp_interval %u ",
+ rta_getattr_u32(tb[IFLA_BOND_LP_INTERVAL]));
+
+ if (tb[IFLA_BOND_PACKETS_PER_SLAVE])
+ fprintf(f, "packets_per_slave %u ",
+ rta_getattr_u32(tb[IFLA_BOND_PACKETS_PER_SLAVE]));
+
+ if (tb[IFLA_BOND_AD_LACP_RATE]) {
+ const char *lacp_rate = get_name(lacp_rate_tbl,
+ rta_getattr_u8(tb[IFLA_BOND_AD_LACP_RATE]));
+ fprintf(f, "lacp_rate %s ", lacp_rate);
+ }
+
+ if (tb[IFLA_BOND_AD_SELECT]) {
+ const char *ad_select = get_name(ad_select_tbl,
+ rta_getattr_u8(tb[IFLA_BOND_AD_SELECT]));
+ fprintf(f, "ad_select %s ", ad_select);
+ }
+
+ if (tb[IFLA_BOND_AD_INFO]) {
+ struct rtattr *adtb[IFLA_BOND_AD_INFO_MAX + 1];
+
+ parse_rtattr_nested(adtb, IFLA_BOND_AD_INFO_MAX,
+ tb[IFLA_BOND_AD_INFO]);
+
+ if (adtb[IFLA_BOND_AD_INFO_AGGREGATOR])
+ fprintf(f, "ad_aggregator %d ",
+ rta_getattr_u16(adtb[IFLA_BOND_AD_INFO_AGGREGATOR]));
+
+ if (adtb[IFLA_BOND_AD_INFO_NUM_PORTS])
+ fprintf(f, "ad_num_ports %d ",
+ rta_getattr_u16(adtb[IFLA_BOND_AD_INFO_NUM_PORTS]));
+
+ if (adtb[IFLA_BOND_AD_INFO_ACTOR_KEY])
+ fprintf(f, "ad_actor_key %d ",
+ rta_getattr_u16(adtb[IFLA_BOND_AD_INFO_ACTOR_KEY]));
+
+ if (adtb[IFLA_BOND_AD_INFO_PARTNER_KEY])
+ fprintf(f, "ad_partner_key %d ",
+ rta_getattr_u16(adtb[IFLA_BOND_AD_INFO_PARTNER_KEY]));
+
+ if (adtb[IFLA_BOND_AD_INFO_PARTNER_MAC]) {
+ unsigned char *p =
+ RTA_DATA(adtb[IFLA_BOND_AD_INFO_PARTNER_MAC]);
+ SPRINT_BUF(b);
+ fprintf(f, "ad_partner_mac %s ",
+ ll_addr_n2a(p, ETH_ALEN, 0, b, sizeof(b)));
+ }
+ }
+
+ if (tb[IFLA_BOND_AD_ACTOR_SYS_PRIO]) {
+ fprintf(f, "ad_actor_sys_prio %u ",
+ rta_getattr_u16(tb[IFLA_BOND_AD_ACTOR_SYS_PRIO]));
+ }
+
+ if (tb[IFLA_BOND_AD_USER_PORT_KEY]) {
+ fprintf(f, "ad_user_port_key %u ",
+ rta_getattr_u16(tb[IFLA_BOND_AD_USER_PORT_KEY]));
+ }
+
+ if (tb[IFLA_BOND_AD_ACTOR_SYSTEM]) {
+ /* We assume the l2 address is an Ethernet MAC address */
+ SPRINT_BUF(b1);
+ fprintf(f, "ad_actor_system %s ",
+ ll_addr_n2a(RTA_DATA(tb[IFLA_BOND_AD_ACTOR_SYSTEM]),
+ RTA_PAYLOAD(tb[IFLA_BOND_AD_ACTOR_SYSTEM]),
+ 1 /*ARPHDR_ETHER*/, b1, sizeof(b1)));
+ }
+
+ if (tb[IFLA_BOND_TLB_DYNAMIC_LB]) {
+ fprintf(f, "tlb_dynamic_lb %u ",
+ rta_getattr_u8(tb[IFLA_BOND_TLB_DYNAMIC_LB]));
+ }
+}
+
+static void bond_print_help(struct link_util *lu, int argc, char **argv,
+ FILE *f)
+{
+ print_explain(f);
+}
+
+struct link_util bond_link_util = {
+ .id = "bond",
+ .maxattr = IFLA_BOND_MAX,
+ .parse_opt = bond_parse_opt,
+ .print_opt = bond_print_opt,
+ .print_help = bond_print_help,
+};
diff --git a/iproute2/ip/iplink_bond_slave.c b/iproute2/ip/iplink_bond_slave.c
new file mode 100644
index 0000000..9b569b1
--- /dev/null
+++ b/iproute2/ip/iplink_bond_slave.c
@@ -0,0 +1,115 @@
+/*
+ * iplink_bond_slave.c Bonding slave device support
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Jiri Pirko <jiri@resnulli.us>
+ */
+
+#include <stdio.h>
+#include <sys/socket.h>
+#include <linux/if_bonding.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+
+static const char *slave_states[] = {
+ [BOND_STATE_ACTIVE] = "ACTIVE",
+ [BOND_STATE_BACKUP] = "BACKUP",
+};
+
+static void print_slave_state(FILE *f, struct rtattr *tb)
+{
+ unsigned int state = rta_getattr_u8(tb);
+
+ if (state >= sizeof(slave_states) / sizeof(slave_states[0]))
+ fprintf(f, "state %d ", state);
+ else
+ fprintf(f, "state %s ", slave_states[state]);
+}
+
+static const char *slave_mii_status[] = {
+ [BOND_LINK_UP] = "UP",
+ [BOND_LINK_FAIL] = "GOING_DOWN",
+ [BOND_LINK_DOWN] = "DOWN",
+ [BOND_LINK_BACK] = "GOING_BACK",
+};
+
+static void print_slave_mii_status(FILE *f, struct rtattr *tb)
+{
+ unsigned int status = rta_getattr_u8(tb);
+
+ if (status >= sizeof(slave_mii_status) / sizeof(slave_mii_status[0]))
+ fprintf(f, "mii_status %d ", status);
+ else
+ fprintf(f, "mii_status %s ", slave_mii_status[status]);
+}
+
+static void bond_slave_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
+{
+ SPRINT_BUF(b1);
+ if (!tb)
+ return;
+
+ if (tb[IFLA_BOND_SLAVE_STATE])
+ print_slave_state(f, tb[IFLA_BOND_SLAVE_STATE]);
+
+ if (tb[IFLA_BOND_SLAVE_MII_STATUS])
+ print_slave_mii_status(f, tb[IFLA_BOND_SLAVE_MII_STATUS]);
+
+ if (tb[IFLA_BOND_SLAVE_LINK_FAILURE_COUNT])
+ fprintf(f, "link_failure_count %d ",
+ rta_getattr_u32(tb[IFLA_BOND_SLAVE_LINK_FAILURE_COUNT]));
+
+ if (tb[IFLA_BOND_SLAVE_PERM_HWADDR])
+ fprintf(f, "perm_hwaddr %s ",
+ ll_addr_n2a(RTA_DATA(tb[IFLA_BOND_SLAVE_PERM_HWADDR]),
+ RTA_PAYLOAD(tb[IFLA_BOND_SLAVE_PERM_HWADDR]),
+ 0, b1, sizeof(b1)));
+
+ if (tb[IFLA_BOND_SLAVE_QUEUE_ID])
+ fprintf(f, "queue_id %d ",
+ rta_getattr_u16(tb[IFLA_BOND_SLAVE_QUEUE_ID]));
+
+ if (tb[IFLA_BOND_SLAVE_AD_AGGREGATOR_ID])
+ fprintf(f, "ad_aggregator_id %d ",
+ rta_getattr_u16(tb[IFLA_BOND_SLAVE_AD_AGGREGATOR_ID]));
+
+ if (tb[IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE])
+ fprintf(f, "ad_actor_oper_port_state %d\n",
+ rta_getattr_u8(tb[IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE]));
+
+ if (tb[IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE])
+ fprintf(f, "ad_partner_oper_port_state %d\n",
+ rta_getattr_u16(tb[IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE]));
+}
+
+static int bond_slave_parse_opt(struct link_util *lu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ __u16 queue_id;
+
+ while (argc > 0) {
+ if (matches(*argv, "queue_id") == 0) {
+ NEXT_ARG();
+ if (get_u16(&queue_id, *argv, 0))
+ invarg("queue_id is invalid", *argv);
+ addattr16(n, 1024, IFLA_BOND_SLAVE_QUEUE_ID, queue_id);
+ }
+ argc--, argv++;
+ }
+
+ return 0;
+}
+
+struct link_util bond_slave_link_util = {
+ .id = "bond",
+ .maxattr = IFLA_BOND_SLAVE_MAX,
+ .print_opt = bond_slave_print_opt,
+ .parse_opt = bond_slave_parse_opt,
+ .slave = true,
+};
diff --git a/iproute2/ip/iplink_bridge.c b/iproute2/ip/iplink_bridge.c
new file mode 100644
index 0000000..0080409
--- /dev/null
+++ b/iproute2/ip/iplink_bridge.c
@@ -0,0 +1,172 @@
+/*
+ * iplink_bridge.c Bridge device support
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Jiri Pirko <jiri@resnulli.us>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/if_link.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+
+static void print_explain(FILE *f)
+{
+ fprintf(f,
+ "Usage: ... bridge [ forward_delay FORWARD_DELAY ]\n"
+ " [ hello_time HELLO_TIME ]\n"
+ " [ max_age MAX_AGE ]\n"
+ " [ ageing_time AGEING_TIME ]\n"
+ " [ stp_state STP_STATE ]\n"
+ " [ priority PRIORITY ]\n"
+ " [ vlan_filtering VLAN_FILTERING ]\n"
+ " [ vlan_protocol VLAN_PROTOCOL ]\n"
+ "\n"
+ "Where: VLAN_PROTOCOL := { 802.1Q | 802.1ad }\n"
+ );
+}
+
+static void explain(void)
+{
+ print_explain(stderr);
+}
+
+static int bridge_parse_opt(struct link_util *lu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ __u32 val;
+
+ while (argc > 0) {
+ if (matches(*argv, "forward_delay") == 0) {
+ NEXT_ARG();
+ if (get_u32(&val, *argv, 0))
+ invarg("invalid forward_delay", *argv);
+
+ addattr32(n, 1024, IFLA_BR_FORWARD_DELAY, val);
+ } else if (matches(*argv, "hello_time") == 0) {
+ NEXT_ARG();
+ if (get_u32(&val, *argv, 0))
+ invarg("invalid hello_time", *argv);
+
+ addattr32(n, 1024, IFLA_BR_HELLO_TIME, val);
+ } else if (matches(*argv, "max_age") == 0) {
+ NEXT_ARG();
+ if (get_u32(&val, *argv, 0))
+ invarg("invalid max_age", *argv);
+
+ addattr32(n, 1024, IFLA_BR_MAX_AGE, val);
+ } else if (matches(*argv, "ageing_time") == 0) {
+ NEXT_ARG();
+ if (get_u32(&val, *argv, 0))
+ invarg("invalid ageing_time", *argv);
+
+ addattr32(n, 1024, IFLA_BR_AGEING_TIME, val);
+ } else if (matches(*argv, "stp_state") == 0) {
+ NEXT_ARG();
+ if (get_u32(&val, *argv, 0))
+ invarg("invalid stp_state", *argv);
+
+ addattr32(n, 1024, IFLA_BR_STP_STATE, val);
+ } else if (matches(*argv, "priority") == 0) {
+ __u16 prio;
+
+ NEXT_ARG();
+ if (get_u16(&prio, *argv, 0))
+ invarg("invalid priority", *argv);
+
+ addattr16(n, 1024, IFLA_BR_PRIORITY, prio);
+ } else if (matches(*argv, "vlan_filtering") == 0) {
+ __u8 vlan_filter;
+
+ NEXT_ARG();
+ if (get_u8(&vlan_filter, *argv, 0)) {
+ invarg("invalid vlan_filtering", *argv);
+ return -1;
+ }
+ addattr8(n, 1024, IFLA_BR_VLAN_FILTERING, vlan_filter);
+ } else if (matches(*argv, "vlan_protocol") == 0) {
+ __u16 vlan_proto;
+
+ NEXT_ARG();
+ if (ll_proto_a2n(&vlan_proto, *argv)) {
+ invarg("invalid vlan_protocol", *argv);
+ return -1;
+ }
+ addattr16(n, 1024, IFLA_BR_VLAN_PROTOCOL, vlan_proto);
+ } else if (matches(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "bridge: unknown command \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--, argv++;
+ }
+
+ return 0;
+}
+
+static void bridge_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
+{
+ if (!tb)
+ return;
+
+ if (tb[IFLA_BR_FORWARD_DELAY])
+ fprintf(f, "forward_delay %u ",
+ rta_getattr_u32(tb[IFLA_BR_FORWARD_DELAY]));
+
+ if (tb[IFLA_BR_HELLO_TIME])
+ fprintf(f, "hello_time %u ",
+ rta_getattr_u32(tb[IFLA_BR_HELLO_TIME]));
+
+ if (tb[IFLA_BR_MAX_AGE])
+ fprintf(f, "max_age %u ",
+ rta_getattr_u32(tb[IFLA_BR_MAX_AGE]));
+
+ if (tb[IFLA_BR_AGEING_TIME])
+ fprintf(f, "ageing_time %u ",
+ rta_getattr_u32(tb[IFLA_BR_AGEING_TIME]));
+
+ if (tb[IFLA_BR_STP_STATE])
+ fprintf(f, "stp_state %u ",
+ rta_getattr_u32(tb[IFLA_BR_STP_STATE]));
+
+ if (tb[IFLA_BR_PRIORITY])
+ fprintf(f, "priority %u ",
+ rta_getattr_u16(tb[IFLA_BR_PRIORITY]));
+
+ if (tb[IFLA_BR_VLAN_FILTERING])
+ fprintf(f, "vlan_filtering %u ",
+ rta_getattr_u8(tb[IFLA_BR_VLAN_FILTERING]));
+
+ if (tb[IFLA_BR_VLAN_PROTOCOL]) {
+ SPRINT_BUF(b1);
+
+ fprintf(f, "vlan_protocol %s ",
+ ll_proto_n2a(rta_getattr_u16(tb[IFLA_BR_VLAN_PROTOCOL]),
+ b1, sizeof(b1)));
+ }
+}
+
+static void bridge_print_help(struct link_util *lu, int argc, char **argv,
+ FILE *f)
+{
+ print_explain(f);
+}
+
+struct link_util bridge_link_util = {
+ .id = "bridge",
+ .maxattr = IFLA_BR_MAX,
+ .parse_opt = bridge_parse_opt,
+ .print_opt = bridge_print_opt,
+ .print_help = bridge_print_help,
+};
diff --git a/iproute2/ip/iplink_bridge_slave.c b/iproute2/ip/iplink_bridge_slave.c
new file mode 100644
index 0000000..4593872
--- /dev/null
+++ b/iproute2/ip/iplink_bridge_slave.c
@@ -0,0 +1,193 @@
+/*
+ * iplink_bridge_slave.c Bridge slave device support
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Jiri Pirko <jiri@resnulli.us>
+ */
+
+#include <stdio.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <linux/if_link.h>
+#include <linux/if_bridge.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+
+static void print_explain(FILE *f)
+{
+ fprintf(f,
+ "Usage: ... bridge_slave [ state STATE ] [ priority PRIO ] [cost COST ]\n"
+ " [ guard {on | off} ]\n"
+ " [ hairpin {on | off} ] \n"
+ " [ fastleave {on | off} ]\n"
+ " [ root_block {on | off} ]\n"
+ " [ learning {on | off} ]\n"
+ " [ flood {on | off} ]\n"
+ );
+}
+
+static void explain(void)
+{
+ print_explain(stderr);
+}
+
+static const char *port_states[] = {
+ [BR_STATE_DISABLED] = "disabled",
+ [BR_STATE_LISTENING] = "listening",
+ [BR_STATE_LEARNING] = "learning",
+ [BR_STATE_FORWARDING] = "forwarding",
+ [BR_STATE_BLOCKING] = "blocking",
+};
+
+static void print_portstate(FILE *f, __u8 state)
+{
+ if (state <= BR_STATE_BLOCKING)
+ fprintf(f, "state %s ", port_states[state]);
+ else
+ fprintf(f, "state (%d) ", state);
+}
+
+static void print_onoff(FILE *f, char *flag, __u8 val)
+{
+ fprintf(f, "%s %s ", flag, val ? "on" : "off");
+}
+
+static void bridge_slave_print_opt(struct link_util *lu, FILE *f,
+ struct rtattr *tb[])
+{
+ if (!tb)
+ return;
+
+ if (tb[IFLA_BRPORT_STATE])
+ print_portstate(f, rta_getattr_u8(tb[IFLA_BRPORT_STATE]));
+
+ if (tb[IFLA_BRPORT_PRIORITY])
+ fprintf(f, "priority %d ",
+ rta_getattr_u16(tb[IFLA_BRPORT_PRIORITY]));
+
+ if (tb[IFLA_BRPORT_COST])
+ fprintf(f, "cost %d ",
+ rta_getattr_u32(tb[IFLA_BRPORT_COST]));
+
+ if (tb[IFLA_BRPORT_MODE])
+ print_onoff(f, "hairpin",
+ rta_getattr_u8(tb[IFLA_BRPORT_MODE]));
+
+ if (tb[IFLA_BRPORT_GUARD])
+ print_onoff(f, "guard",
+ rta_getattr_u8(tb[IFLA_BRPORT_GUARD]));
+
+ if (tb[IFLA_BRPORT_PROTECT])
+ print_onoff(f, "root_block",
+ rta_getattr_u8(tb[IFLA_BRPORT_PROTECT]));
+
+ if (tb[IFLA_BRPORT_FAST_LEAVE])
+ print_onoff(f, "fastleave",
+ rta_getattr_u8(tb[IFLA_BRPORT_FAST_LEAVE]));
+
+ if (tb[IFLA_BRPORT_LEARNING])
+ print_onoff(f, "learning",
+ rta_getattr_u8(tb[IFLA_BRPORT_LEARNING]));
+
+ if (tb[IFLA_BRPORT_UNICAST_FLOOD])
+ print_onoff(f, "flood",
+ rta_getattr_u8(tb[IFLA_BRPORT_UNICAST_FLOOD]));
+}
+
+static void bridge_slave_parse_on_off(char *arg_name, char *arg_val,
+ struct nlmsghdr *n, int type)
+{
+ __u8 val;
+
+ if (strcmp(arg_val, "on") == 0)
+ val = 1;
+ else if (strcmp(arg_val, "off") == 0)
+ val = 0;
+ else
+ invarg("should be \"on\" or \"off\"", arg_name);
+
+ addattr8(n, 1024, type, val);
+}
+
+static int bridge_slave_parse_opt(struct link_util *lu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ __u8 state;
+ __u16 priority;
+ __u32 cost;
+
+ while (argc > 0) {
+ if (matches(*argv, "state") == 0) {
+ NEXT_ARG();
+ if (get_u8(&state, *argv, 0))
+ invarg("state is invalid", *argv);
+ addattr8(n, 1024, IFLA_BRPORT_STATE, state);
+ } else if (matches(*argv, "priority") == 0) {
+ NEXT_ARG();
+ if (get_u16(&priority, *argv, 0))
+ invarg("priority is invalid", *argv);
+ addattr16(n, 1024, IFLA_BRPORT_PRIORITY, priority);
+ } else if (matches(*argv, "cost") == 0) {
+ NEXT_ARG();
+ if (get_u32(&cost, *argv, 0))
+ invarg("cost is invalid", *argv);
+ addattr32(n, 1024, IFLA_BRPORT_COST, cost);
+ } else if (matches(*argv, "hairpin") == 0) {
+ NEXT_ARG();
+ bridge_slave_parse_on_off("hairpin", *argv, n,
+ IFLA_BRPORT_MODE);
+ } else if (matches(*argv, "guard") == 0) {
+ NEXT_ARG();
+ bridge_slave_parse_on_off("guard", *argv, n,
+ IFLA_BRPORT_GUARD);
+ } else if (matches(*argv, "root_block") == 0) {
+ NEXT_ARG();
+ bridge_slave_parse_on_off("root_block", *argv, n,
+ IFLA_BRPORT_PROTECT);
+ } else if (matches(*argv, "fastleave") == 0) {
+ NEXT_ARG();
+ bridge_slave_parse_on_off("fastleave", *argv, n,
+ IFLA_BRPORT_FAST_LEAVE);
+ } else if (matches(*argv, "learning") == 0) {
+ NEXT_ARG();
+ bridge_slave_parse_on_off("learning", *argv, n,
+ IFLA_BRPORT_LEARNING);
+ } else if (matches(*argv, "flood") == 0) {
+ NEXT_ARG();
+ bridge_slave_parse_on_off("flood", *argv, n,
+ IFLA_BRPORT_UNICAST_FLOOD);
+ } else if (matches(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "bridge_slave: unknown option \"%s\"?\n",
+ *argv);
+ explain();
+ return -1;
+ }
+ argc--, argv++;
+ }
+
+ return 0;
+}
+
+static void bridge_slave_print_help(struct link_util *lu, int argc, char **argv,
+ FILE *f)
+{
+ print_explain(f);
+}
+
+struct link_util bridge_slave_link_util = {
+ .id = "bridge",
+ .maxattr = IFLA_BRPORT_MAX,
+ .print_opt = bridge_slave_print_opt,
+ .parse_opt = bridge_slave_parse_opt,
+ .print_help = bridge_slave_print_help,
+ .slave = true,
+};
diff --git a/iproute2/ip/iplink_can.c b/iproute2/ip/iplink_can.c
new file mode 100644
index 0000000..f1b089d
--- /dev/null
+++ b/iproute2/ip/iplink_can.c
@@ -0,0 +1,377 @@
+/*
+ * iplink_can.c CAN device support
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Wolfgang Grandegger <wg@grandegger.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <linux/can/netlink.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+
+static void print_usage(FILE *f)
+{
+ fprintf(f,
+ "Usage: ip link set DEVICE type can\n"
+ "\t[ bitrate BITRATE [ sample-point SAMPLE-POINT] ] | \n"
+ "\t[ tq TQ prop-seg PROP_SEG phase-seg1 PHASE-SEG1\n "
+ "\t phase-seg2 PHASE-SEG2 [ sjw SJW ] ]\n"
+ "\n"
+ "\t[ dbitrate BITRATE [ dsample-point SAMPLE-POINT] ] | \n"
+ "\t[ dtq TQ dprop-seg PROP_SEG dphase-seg1 PHASE-SEG1\n "
+ "\t dphase-seg2 PHASE-SEG2 [ dsjw SJW ] ]\n"
+ "\n"
+ "\t[ loopback { on | off } ]\n"
+ "\t[ listen-only { on | off } ]\n"
+ "\t[ triple-sampling { on | off } ]\n"
+ "\t[ one-shot { on | off } ]\n"
+ "\t[ berr-reporting { on | off } ]\n"
+ "\t[ fd { on | off } ]\n"
+ "\t[ fd-non-iso { on | off } ]\n"
+ "\t[ presume-ack { on | off } ]\n"
+ "\n"
+ "\t[ restart-ms TIME-MS ]\n"
+ "\t[ restart ]\n"
+ "\n"
+ "\tWhere: BITRATE := { 1..1000000 }\n"
+ "\t SAMPLE-POINT := { 0.000..0.999 }\n"
+ "\t TQ := { NUMBER }\n"
+ "\t PROP-SEG := { 1..8 }\n"
+ "\t PHASE-SEG1 := { 1..8 }\n"
+ "\t PHASE-SEG2 := { 1..8 }\n"
+ "\t SJW := { 1..4 }\n"
+ "\t RESTART-MS := { 0 | NUMBER }\n"
+ );
+}
+
+static void usage(void)
+{
+ print_usage(stderr);
+}
+
+static int get_float(float *val, const char *arg)
+{
+ float res;
+ char *ptr;
+
+ if (!arg || !*arg)
+ return -1;
+ res = strtof(arg, &ptr);
+ if (!ptr || ptr == arg || *ptr)
+ return -1;
+ *val = res;
+ return 0;
+}
+
+static void set_ctrlmode(char* name, char *arg,
+ struct can_ctrlmode *cm, __u32 flags)
+{
+ if (strcmp(arg, "on") == 0) {
+ cm->flags |= flags;
+ } else if (strcmp(arg, "off") != 0) {
+ fprintf(stderr,
+ "Error: argument of \"%s\" must be \"on\" or \"off\", not \"%s\"\n",
+ name, arg);
+ exit(-1);
+ }
+ cm->mask |= flags;
+}
+
+static void print_ctrlmode(FILE *f, __u32 cm)
+{
+ fprintf(f, "<");
+#define _PF(cmflag, cmname) \
+ if (cm & cmflag) { \
+ cm &= ~cmflag; \
+ fprintf(f, "%s%s", cmname, cm ? "," : ""); \
+ }
+ _PF(CAN_CTRLMODE_LOOPBACK, "LOOPBACK");
+ _PF(CAN_CTRLMODE_LISTENONLY, "LISTEN-ONLY");
+ _PF(CAN_CTRLMODE_3_SAMPLES, "TRIPLE-SAMPLING");
+ _PF(CAN_CTRLMODE_ONE_SHOT, "ONE-SHOT");
+ _PF(CAN_CTRLMODE_BERR_REPORTING, "BERR-REPORTING");
+ _PF(CAN_CTRLMODE_FD, "FD");
+ _PF(CAN_CTRLMODE_FD_NON_ISO, "FD-NON-ISO");
+ _PF(CAN_CTRLMODE_PRESUME_ACK, "PRESUME-ACK");
+#undef _PF
+ if (cm)
+ fprintf(f, "%x", cm);
+ fprintf(f, "> ");
+}
+
+static int can_parse_opt(struct link_util *lu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ struct can_bittiming bt, dbt;
+ struct can_ctrlmode cm = {0, 0};
+
+ memset(&bt, 0, sizeof(bt));
+ memset(&dbt, 0, sizeof(dbt));
+ while (argc > 0) {
+ if (matches(*argv, "bitrate") == 0) {
+ NEXT_ARG();
+ if (get_u32(&bt.bitrate, *argv, 0))
+ invarg("invalid \"bitrate\" value\n", *argv);
+ } else if (matches(*argv, "sample-point") == 0) {
+ float sp;
+
+ NEXT_ARG();
+ if (get_float(&sp, *argv))
+ invarg("invalid \"sample-point\" value\n",
+ *argv);
+ bt.sample_point = (__u32)(sp * 1000);
+ } else if (matches(*argv, "tq") == 0) {
+ NEXT_ARG();
+ if (get_u32(&bt.tq, *argv, 0))
+ invarg("invalid \"tq\" value\n", *argv);
+ } else if (matches(*argv, "prop-seg") == 0) {
+ NEXT_ARG();
+ if (get_u32(&bt.prop_seg, *argv, 0))
+ invarg("invalid \"prop-seg\" value\n", *argv);
+ } else if (matches(*argv, "phase-seg1") == 0) {
+ NEXT_ARG();
+ if (get_u32(&bt.phase_seg1, *argv, 0))
+ invarg("invalid \"phase-seg1\" value\n", *argv);
+ } else if (matches(*argv, "phase-seg2") == 0) {
+ NEXT_ARG();
+ if (get_u32(&bt.phase_seg2, *argv, 0))
+ invarg("invalid \"phase-seg2\" value\n", *argv);
+ } else if (matches(*argv, "sjw") == 0) {
+ NEXT_ARG();
+ if (get_u32(&bt.sjw, *argv, 0))
+ invarg("invalid \"sjw\" value\n", *argv);
+ } else if (matches(*argv, "dbitrate") == 0) {
+ NEXT_ARG();
+ if (get_u32(&dbt.bitrate, *argv, 0))
+ invarg("invalid \"dbitrate\" value\n", *argv);
+ } else if (matches(*argv, "dsample-point") == 0) {
+ float sp;
+
+ NEXT_ARG();
+ if (get_float(&sp, *argv))
+ invarg("invalid \"dsample-point\" value\n", *argv);
+ dbt.sample_point = (__u32)(sp * 1000);
+ } else if (matches(*argv, "dtq") == 0) {
+ NEXT_ARG();
+ if (get_u32(&dbt.tq, *argv, 0))
+ invarg("invalid \"dtq\" value\n", *argv);
+ } else if (matches(*argv, "dprop-seg") == 0) {
+ NEXT_ARG();
+ if (get_u32(&dbt.prop_seg, *argv, 0))
+ invarg("invalid \"dprop-seg\" value\n", *argv);
+ } else if (matches(*argv, "dphase-seg1") == 0) {
+ NEXT_ARG();
+ if (get_u32(&dbt.phase_seg1, *argv, 0))
+ invarg("invalid \"dphase-seg1\" value\n", *argv);
+ } else if (matches(*argv, "dphase-seg2") == 0) {
+ NEXT_ARG();
+ if (get_u32(&dbt.phase_seg2, *argv, 0))
+ invarg("invalid \"dphase-seg2\" value\n", *argv);
+ } else if (matches(*argv, "dsjw") == 0) {
+ NEXT_ARG();
+ if (get_u32(&dbt.sjw, *argv, 0))
+ invarg("invalid \"dsjw\" value\n", *argv);
+ } else if (matches(*argv, "loopback") == 0) {
+ NEXT_ARG();
+ set_ctrlmode("loopback", *argv, &cm,
+ CAN_CTRLMODE_LOOPBACK);
+ } else if (matches(*argv, "listen-only") == 0) {
+ NEXT_ARG();
+ set_ctrlmode("listen-only", *argv, &cm,
+ CAN_CTRLMODE_LISTENONLY);
+ } else if (matches(*argv, "triple-sampling") == 0) {
+ NEXT_ARG();
+ set_ctrlmode("triple-sampling", *argv, &cm,
+ CAN_CTRLMODE_3_SAMPLES);
+ } else if (matches(*argv, "one-shot") == 0) {
+ NEXT_ARG();
+ set_ctrlmode("one-shot", *argv, &cm,
+ CAN_CTRLMODE_ONE_SHOT);
+ } else if (matches(*argv, "berr-reporting") == 0) {
+ NEXT_ARG();
+ set_ctrlmode("berr-reporting", *argv, &cm,
+ CAN_CTRLMODE_BERR_REPORTING);
+ } else if (matches(*argv, "fd") == 0) {
+ NEXT_ARG();
+ set_ctrlmode("fd", *argv, &cm,
+ CAN_CTRLMODE_FD);
+ } else if (matches(*argv, "fd-non-iso") == 0) {
+ NEXT_ARG();
+ set_ctrlmode("fd-non-iso", *argv, &cm,
+ CAN_CTRLMODE_FD_NON_ISO);
+ } else if (matches(*argv, "presume-ack") == 0) {
+ NEXT_ARG();
+ set_ctrlmode("presume-ack", *argv, &cm,
+ CAN_CTRLMODE_PRESUME_ACK);
+ } else if (matches(*argv, "restart") == 0) {
+ __u32 val = 1;
+
+ addattr32(n, 1024, IFLA_CAN_RESTART, val);
+ } else if (matches(*argv, "restart-ms") == 0) {
+ __u32 val;
+
+ NEXT_ARG();
+ if (get_u32(&val, *argv, 0))
+ invarg("invalid \"restart-ms\" value\n", *argv);
+ addattr32(n, 1024, IFLA_CAN_RESTART_MS, val);
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ return -1;
+ } else {
+ fprintf(stderr, "can: unknown option \"%s\"\n", *argv);
+ usage();
+ return -1;
+ }
+ argc--, argv++;
+ }
+
+ if (bt.bitrate || bt.tq)
+ addattr_l(n, 1024, IFLA_CAN_BITTIMING, &bt, sizeof(bt));
+ if (dbt.bitrate || dbt.tq)
+ addattr_l(n, 1024, IFLA_CAN_DATA_BITTIMING, &dbt, sizeof(dbt));
+ if (cm.mask)
+ addattr_l(n, 1024, IFLA_CAN_CTRLMODE, &cm, sizeof(cm));
+
+ return 0;
+}
+
+static const char *can_state_names[] = {
+ [CAN_STATE_ERROR_ACTIVE] = "ERROR-ACTIVE",
+ [CAN_STATE_ERROR_WARNING] = "ERROR-WARNING",
+ [CAN_STATE_ERROR_PASSIVE] = "ERROR-PASSIVE",
+ [CAN_STATE_BUS_OFF] = "BUS-OFF",
+ [CAN_STATE_STOPPED] = "STOPPED",
+ [CAN_STATE_SLEEPING] = "SLEEPING"
+};
+
+static void can_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
+{
+ if (!tb)
+ return;
+
+ if (tb[IFLA_CAN_CTRLMODE]) {
+ struct can_ctrlmode *cm = RTA_DATA(tb[IFLA_CAN_CTRLMODE]);
+
+ if (cm->flags)
+ print_ctrlmode(f, cm->flags);
+ }
+
+ if (tb[IFLA_CAN_STATE]) {
+ int *state = RTA_DATA(tb[IFLA_CAN_STATE]);
+
+ fprintf(f, "state %s ", *state <= CAN_STATE_MAX ?
+ can_state_names[*state] : "UNKNOWN");
+ }
+
+ if (tb[IFLA_CAN_BERR_COUNTER]) {
+ struct can_berr_counter *bc =
+ RTA_DATA(tb[IFLA_CAN_BERR_COUNTER]);
+
+ fprintf(f, "(berr-counter tx %d rx %d) ", bc->txerr, bc->rxerr);
+ }
+
+ if (tb[IFLA_CAN_RESTART_MS]) {
+ __u32 *restart_ms = RTA_DATA(tb[IFLA_CAN_RESTART_MS]);
+
+ fprintf(f, "restart-ms %d ", *restart_ms);
+ }
+
+ if (tb[IFLA_CAN_BITTIMING]) {
+ struct can_bittiming *bt = RTA_DATA(tb[IFLA_CAN_BITTIMING]);
+
+ fprintf(f, "\n "
+ "bitrate %d sample-point %.3f ",
+ bt->bitrate, (float)bt->sample_point / 1000.);
+ fprintf(f, "\n "
+ "tq %d prop-seg %d phase-seg1 %d phase-seg2 %d sjw %d",
+ bt->tq, bt->prop_seg, bt->phase_seg1, bt->phase_seg2,
+ bt->sjw);
+ }
+
+ if (tb[IFLA_CAN_BITTIMING_CONST]) {
+ struct can_bittiming_const *btc =
+ RTA_DATA(tb[IFLA_CAN_BITTIMING_CONST]);
+
+ fprintf(f, "\n "
+ "%s: tseg1 %d..%d tseg2 %d..%d "
+ "sjw 1..%d brp %d..%d brp-inc %d",
+ btc->name, btc->tseg1_min, btc->tseg1_max,
+ btc->tseg2_min, btc->tseg2_max, btc->sjw_max,
+ btc->brp_min, btc->brp_max, btc->brp_inc);
+ }
+
+ if (tb[IFLA_CAN_DATA_BITTIMING]) {
+ struct can_bittiming *dbt =
+ RTA_DATA(tb[IFLA_CAN_DATA_BITTIMING]);
+
+ fprintf(f, "\n "
+ "dbitrate %d dsample-point %.3f ",
+ dbt->bitrate, (float)dbt->sample_point / 1000.);
+ fprintf(f, "\n "
+ "dtq %d dprop-seg %d dphase-seg1 %d "
+ "dphase-seg2 %d dsjw %d",
+ dbt->tq, dbt->prop_seg, dbt->phase_seg1,
+ dbt->phase_seg2, dbt->sjw);
+ }
+
+ if (tb[IFLA_CAN_DATA_BITTIMING_CONST]) {
+ struct can_bittiming_const *dbtc =
+ RTA_DATA(tb[IFLA_CAN_DATA_BITTIMING_CONST]);
+
+ fprintf(f, "\n "
+ "%s: dtseg1 %d..%d dtseg2 %d..%d "
+ "dsjw 1..%d dbrp %d..%d dbrp-inc %d",
+ dbtc->name, dbtc->tseg1_min, dbtc->tseg1_max,
+ dbtc->tseg2_min, dbtc->tseg2_max, dbtc->sjw_max,
+ dbtc->brp_min, dbtc->brp_max, dbtc->brp_inc);
+ }
+
+ if (tb[IFLA_CAN_CLOCK]) {
+ struct can_clock *clock = RTA_DATA(tb[IFLA_CAN_CLOCK]);
+
+ fprintf(f, "\n clock %d", clock->freq);
+ }
+
+}
+
+static void can_print_xstats(struct link_util *lu,
+ FILE *f, struct rtattr *xstats)
+{
+ struct can_device_stats *stats;
+
+ if (xstats && RTA_PAYLOAD(xstats) == sizeof(*stats)) {
+ stats = RTA_DATA(xstats);
+ fprintf(f, "\n "
+ "re-started bus-errors arbit-lost "
+ "error-warn error-pass bus-off");
+ fprintf(f, "\n %-10d %-10d %-10d %-10d %-10d %-10d",
+ stats->restarts, stats->bus_error,
+ stats->arbitration_lost, stats->error_warning,
+ stats->error_passive, stats->bus_off);
+ }
+}
+
+static void can_print_help(struct link_util *lu, int argc, char **argv,
+ FILE *f)
+{
+ print_usage(f);
+}
+
+struct link_util can_link_util = {
+ .id = "can",
+ .maxattr = IFLA_CAN_MAX,
+ .parse_opt = can_parse_opt,
+ .print_opt = can_print_opt,
+ .print_xstats = can_print_xstats,
+ .print_help = can_print_help,
+};
diff --git a/iproute2/ip/iplink_geneve.c b/iproute2/ip/iplink_geneve.c
new file mode 100644
index 0000000..1345479
--- /dev/null
+++ b/iproute2/ip/iplink_geneve.c
@@ -0,0 +1,173 @@
+/*
+ * iplink_geneve.c GENEVE device support
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: John W. Linville <linville@tuxdriver.com>
+ */
+
+#include <stdio.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+
+static void print_explain(FILE *f)
+{
+ fprintf(f, "Usage: ... geneve id VNI remote ADDR\n");
+ fprintf(f, " [ ttl TTL ] [ tos TOS ]\n");
+ fprintf(f, "\n");
+ fprintf(f, "Where: VNI := 0-16777215\n");
+ fprintf(f, " ADDR := IP_ADDRESS\n");
+ fprintf(f, " TOS := { NUMBER | inherit }\n");
+ fprintf(f, " TTL := { 1..255 | inherit }\n");
+}
+
+static void explain(void)
+{
+ print_explain(stderr);
+}
+
+static int geneve_parse_opt(struct link_util *lu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ __u32 vni = 0;
+ int vni_set = 0;
+ __u32 daddr = 0;
+ struct in6_addr daddr6 = IN6ADDR_ANY_INIT;
+ __u8 ttl = 0;
+ __u8 tos = 0;
+
+ while (argc > 0) {
+ if (!matches(*argv, "id") ||
+ !matches(*argv, "vni")) {
+ NEXT_ARG();
+ if (get_u32(&vni, *argv, 0) ||
+ vni >= 1u << 24)
+ invarg("invalid id", *argv);
+ vni_set = 1;
+ } else if (!matches(*argv, "remote")) {
+ NEXT_ARG();
+ if (!inet_get_addr(*argv, &daddr, &daddr6)) {
+ fprintf(stderr, "Invalid address \"%s\"\n", *argv);
+ return -1;
+ }
+ if (IN6_IS_ADDR_MULTICAST(&daddr6) || IN_MULTICAST(ntohl(daddr)))
+ invarg("invalid remote address", *argv);
+ } else if (!matches(*argv, "ttl") ||
+ !matches(*argv, "hoplimit")) {
+ unsigned uval;
+
+ NEXT_ARG();
+ if (strcmp(*argv, "inherit") != 0) {
+ if (get_unsigned(&uval, *argv, 0))
+ invarg("invalid TTL", *argv);
+ if (uval > 255)
+ invarg("TTL must be <= 255", *argv);
+ ttl = uval;
+ }
+ } else if (!matches(*argv, "tos") ||
+ !matches(*argv, "dsfield")) {
+ __u32 uval;
+
+ NEXT_ARG();
+ if (strcmp(*argv, "inherit") != 0) {
+ if (rtnl_dsfield_a2n(&uval, *argv))
+ invarg("bad TOS value", *argv);
+ tos = uval;
+ } else
+ tos = 1;
+ } else if (matches(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "geneve: unknown command \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--, argv++;
+ }
+
+ if (!vni_set) {
+ fprintf(stderr, "geneve: missing virtual network identifier\n");
+ return -1;
+ }
+
+ if (!daddr && memcmp(&daddr6, &in6addr_any, sizeof(daddr6)) == 0) {
+ fprintf(stderr, "geneve: remote link partner not specified\n");
+ return -1;
+ }
+
+ addattr32(n, 1024, IFLA_GENEVE_ID, vni);
+ if (daddr)
+ addattr_l(n, 1024, IFLA_GENEVE_REMOTE, &daddr, 4);
+ if (memcmp(&daddr6, &in6addr_any, sizeof(daddr6)) != 0)
+ addattr_l(n, 1024, IFLA_GENEVE_REMOTE6, &daddr6, sizeof(struct in6_addr));
+ addattr8(n, 1024, IFLA_GENEVE_TTL, ttl);
+ addattr8(n, 1024, IFLA_GENEVE_TOS, tos);
+
+ return 0;
+}
+
+static void geneve_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
+{
+ __u32 vni;
+ char s1[1024];
+ __u8 tos;
+
+ if (!tb)
+ return;
+
+ if (!tb[IFLA_GENEVE_ID] ||
+ RTA_PAYLOAD(tb[IFLA_GENEVE_ID]) < sizeof(__u32))
+ return;
+
+ vni = rta_getattr_u32(tb[IFLA_GENEVE_ID]);
+ fprintf(f, "id %u ", vni);
+
+ if (tb[IFLA_GENEVE_REMOTE]) {
+ __be32 addr = rta_getattr_u32(tb[IFLA_GENEVE_REMOTE]);
+ if (addr)
+ fprintf(f, "remote %s ",
+ format_host(AF_INET, 4, &addr, s1, sizeof(s1)));
+ } else if (tb[IFLA_GENEVE_REMOTE6]) {
+ struct in6_addr addr;
+ memcpy(&addr, RTA_DATA(tb[IFLA_GENEVE_REMOTE6]), sizeof(struct in6_addr));
+ if (memcmp(&addr, &in6addr_any, sizeof(addr)) != 0) {
+ if (IN6_IS_ADDR_MULTICAST(&addr))
+ fprintf(f, "remote %s ",
+ format_host(AF_INET6, sizeof(struct in6_addr), &addr, s1, sizeof(s1)));
+ }
+ }
+
+ if (tb[IFLA_GENEVE_TTL]) {
+ __u8 ttl = rta_getattr_u8(tb[IFLA_GENEVE_TTL]);
+ if (ttl)
+ fprintf(f, "ttl %d ", ttl);
+ }
+
+ if (tb[IFLA_GENEVE_TOS] &&
+ (tos = rta_getattr_u8(tb[IFLA_GENEVE_TOS]))) {
+ if (tos == 1)
+ fprintf(f, "tos inherit ");
+ else
+ fprintf(f, "tos %#x ", tos);
+ }
+}
+
+static void geneve_print_help(struct link_util *lu, int argc, char **argv,
+ FILE *f)
+{
+ print_explain(f);
+}
+
+struct link_util geneve_link_util = {
+ .id = "geneve",
+ .maxattr = IFLA_GENEVE_MAX,
+ .parse_opt = geneve_parse_opt,
+ .print_opt = geneve_print_opt,
+ .print_help = geneve_print_help,
+};
diff --git a/iproute2/ip/iplink_hsr.c b/iproute2/ip/iplink_hsr.c
new file mode 100644
index 0000000..65fbec8
--- /dev/null
+++ b/iproute2/ip/iplink_hsr.c
@@ -0,0 +1,141 @@
+/*
+ * iplink_hsr.c HSR device support
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Arvid Brodin <arvid.brodin@alten.se>
+ *
+ * Based on iplink_vlan.c by Patrick McHardy <kaber@trash.net>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h> /* Needed by linux/if.h for some reason */
+#include <linux/if.h>
+#include <linux/if_arp.h>
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+
+static void print_usage(FILE *f)
+{
+ fprintf(f,
+"Usage:\tip link add name NAME type hsr slave1 SLAVE1-IF slave2 SLAVE2-IF\n"
+"\t[ supervision ADDR-BYTE ]\n"
+"\n"
+"NAME\n"
+" name of new hsr device (e.g. hsr0)\n"
+"SLAVE1-IF, SLAVE2-IF\n"
+" the two slave devices bound to the HSR device\n"
+"ADDR-BYTE\n"
+" 0-255; the last byte of the multicast address used for HSR supervision\n"
+" frames (default = 0)\n");
+}
+
+static void usage(void)
+{
+ print_usage(stderr);
+}
+
+static int hsr_parse_opt(struct link_util *lu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ int ifindex;
+ unsigned char multicast_spec;
+
+ while (argc > 0) {
+ if (matches(*argv, "supervision") == 0) {
+ NEXT_ARG();
+ if (get_u8(&multicast_spec, *argv, 0))
+ invarg("ADDR-BYTE is invalid", *argv);
+ addattr_l(n, 1024, IFLA_HSR_MULTICAST_SPEC,
+ &multicast_spec, 1);
+ } else if (matches(*argv, "slave1") == 0) {
+ NEXT_ARG();
+ ifindex = ll_name_to_index(*argv);
+ if (ifindex == 0)
+ invarg("No such interface", *argv);
+ addattr_l(n, 1024, IFLA_HSR_SLAVE1, &ifindex, 4);
+ } else if (matches(*argv, "slave2") == 0) {
+ NEXT_ARG();
+ ifindex = ll_name_to_index(*argv);
+ if (ifindex == 0)
+ invarg("No such interface", *argv);
+ addattr_l(n, 1024, IFLA_HSR_SLAVE2, &ifindex, 4);
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ return -1;
+ } else {
+ fprintf(stderr, "hsr: what is \"%s\"?\n", *argv);
+ usage();
+ return -1;
+ }
+ argc--, argv++;
+ }
+
+ return 0;
+}
+
+static void hsr_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
+{
+ SPRINT_BUF(b1);
+
+ if (!tb)
+ return;
+
+ if (tb[IFLA_HSR_SLAVE1] &&
+ RTA_PAYLOAD(tb[IFLA_HSR_SLAVE1]) < sizeof(__u32))
+ return;
+ if (tb[IFLA_HSR_SLAVE2] &&
+ RTA_PAYLOAD(tb[IFLA_HSR_SLAVE2]) < sizeof(__u32))
+ return;
+ if (tb[IFLA_HSR_SEQ_NR] &&
+ RTA_PAYLOAD(tb[IFLA_HSR_SEQ_NR]) < sizeof(__u16))
+ return;
+ if (tb[IFLA_HSR_SUPERVISION_ADDR] &&
+ RTA_PAYLOAD(tb[IFLA_HSR_SUPERVISION_ADDR]) < ETH_ALEN)
+ return;
+
+ fprintf(f, "slave1 ");
+ if (tb[IFLA_HSR_SLAVE1])
+ fprintf(f, "%s ",
+ ll_index_to_name(rta_getattr_u32(tb[IFLA_HSR_SLAVE1])));
+ else
+ fprintf(f, "<none> ");
+
+ fprintf(f, "slave2 ");
+ if (tb[IFLA_HSR_SLAVE2])
+ fprintf(f, "%s ",
+ ll_index_to_name(rta_getattr_u32(tb[IFLA_HSR_SLAVE2])));
+ else
+ fprintf(f, "<none> ");
+
+ if (tb[IFLA_HSR_SEQ_NR])
+ fprintf(f, "sequence %d ",
+ rta_getattr_u16(tb[IFLA_HSR_SEQ_NR]));
+
+ if (tb[IFLA_HSR_SUPERVISION_ADDR])
+ fprintf(f, "supervision %s ",
+ ll_addr_n2a(RTA_DATA(tb[IFLA_HSR_SUPERVISION_ADDR]),
+ RTA_PAYLOAD(tb[IFLA_HSR_SUPERVISION_ADDR]),
+ ARPHRD_VOID,
+ b1, sizeof(b1)));
+}
+
+static void hsr_print_help(struct link_util *lu, int argc, char **argv,
+ FILE *f)
+{
+ print_usage(f);
+}
+
+struct link_util hsr_link_util = {
+ .id = "hsr",
+ .maxattr = IFLA_VLAN_MAX,
+ .parse_opt = hsr_parse_opt,
+ .print_opt = hsr_print_opt,
+ .print_help = hsr_print_help,
+};
diff --git a/iproute2/ip/iplink_ipoib.c b/iproute2/ip/iplink_ipoib.c
new file mode 100644
index 0000000..6087cbe
--- /dev/null
+++ b/iproute2/ip/iplink_ipoib.c
@@ -0,0 +1,125 @@
+/*
+ * iplink_ipoib.c IPoIB device support
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Or Gerlitz <ogerlitz@mellanox.com>
+ * copied iflink_vlan.c authored by Patrick McHardy <kaber@trash.net>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/if_link.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+
+static void print_explain(FILE *f)
+{
+ fprintf(f,
+ "Usage: ... ipoib [pkey PKEY] [mode {datagram | connected}]"
+ "[umcast {0|1}]\n"
+ "\n"
+ "PKEY := 0x8001-0xffff\n"
+ );
+}
+
+static void explain(void)
+{
+ print_explain(stderr);
+}
+
+static int mode_arg(void)
+{
+ fprintf(stderr, "Error: argument of \"mode\" must be \"datagram\""
+ "or \"connected\"\n");
+ return -1;
+}
+
+static int ipoib_parse_opt(struct link_util *lu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ __u16 pkey, mode, umcast;
+
+ while (argc > 0) {
+ if (matches(*argv, "pkey") == 0) {
+ NEXT_ARG();
+ if (get_u16(&pkey, *argv, 0))
+ invarg("pkey is invalid", *argv);
+ addattr_l(n, 1024, IFLA_IPOIB_PKEY, &pkey, 2);
+ } else if (matches(*argv, "mode") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "datagram") == 0)
+ mode = IPOIB_MODE_DATAGRAM;
+ else if (strcmp(*argv, "connected") == 0)
+ mode = IPOIB_MODE_CONNECTED;
+ else
+ return mode_arg();
+ addattr_l(n, 1024, IFLA_IPOIB_MODE, &mode, 2);
+ } else if (matches(*argv, "umcast") == 0) {
+ NEXT_ARG();
+ if (get_u16(&umcast, *argv, 0))
+ invarg("umcast is invalid", *argv);
+ addattr_l(n, 1024, IFLA_IPOIB_UMCAST, &umcast, 2);
+ } else if (matches(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "ipoib: unknown option \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--, argv++;
+ }
+
+ return 0;
+}
+
+static void ipoib_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
+{
+ __u16 mode;
+
+ if (!tb)
+ return;
+
+ if (!tb[IFLA_IPOIB_PKEY] ||
+ RTA_PAYLOAD(tb[IFLA_IPOIB_PKEY]) < sizeof(__u16))
+ return;
+
+ fprintf(f, "pkey %#.4x ", rta_getattr_u16(tb[IFLA_IPOIB_PKEY]));
+
+ if (!tb[IFLA_IPOIB_MODE] ||
+ RTA_PAYLOAD(tb[IFLA_IPOIB_MODE]) < sizeof(__u16))
+ return;
+
+ mode = rta_getattr_u16(tb[IFLA_IPOIB_MODE]);
+ fprintf(f, "mode %s ",
+ mode == IPOIB_MODE_DATAGRAM ? "datagram" :
+ mode == IPOIB_MODE_CONNECTED ? "connected" :
+ "unknown");
+
+ if (!tb[IFLA_IPOIB_UMCAST] ||
+ RTA_PAYLOAD(tb[IFLA_IPOIB_UMCAST]) < sizeof(__u16))
+ return;
+
+ fprintf(f, "umcast %.4x ", rta_getattr_u16(tb[IFLA_IPOIB_UMCAST]));
+}
+
+static void ipoib_print_help(struct link_util *lu, int argc, char **argv,
+ FILE *f)
+{
+ print_explain(f);
+}
+
+struct link_util ipoib_link_util = {
+ .id = "ipoib",
+ .maxattr = IFLA_IPOIB_MAX,
+ .parse_opt = ipoib_parse_opt,
+ .print_opt = ipoib_print_opt,
+ .print_help = ipoib_print_help,
+};
diff --git a/iproute2/ip/iplink_ipvlan.c b/iproute2/ip/iplink_ipvlan.c
new file mode 100644
index 0000000..e08fc39
--- /dev/null
+++ b/iproute2/ip/iplink_ipvlan.c
@@ -0,0 +1,98 @@
+/* iplink_ipvlan.c IPVLAN device support
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Mahesh Bandewar <maheshb@google.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <linux/if_link.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+
+static void ipvlan_explain(FILE *f)
+{
+ fprintf(f, "Usage: ... ipvlan [ mode { l2 | l3 } ]\n");
+}
+
+static void explain(void)
+{
+ ipvlan_explain(stderr);
+}
+
+static int mode_arg(void)
+{
+ fprintf(stderr, "Error: argument of \"mode\" must be either \"l2\", "
+ "or \"l3\"\n");
+ return -1;
+}
+
+static int ipvlan_parse_opt(struct link_util *lu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ while (argc > 0) {
+ if (matches(*argv, "mode") == 0) {
+ __u16 mode = 0;
+ NEXT_ARG();
+
+ if (strcmp(*argv, "l2") == 0)
+ mode = IPVLAN_MODE_L2;
+ else if (strcmp(*argv, "l3") == 0)
+ mode = IPVLAN_MODE_L3;
+ else
+ return mode_arg();
+
+ addattr16(n, 1024, IFLA_IPVLAN_MODE, mode);
+ } else if (matches(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "ipvlan: unknown option \"%s\"?\n",
+ *argv);
+ explain();
+ return -1;
+ }
+ argc--, argv++;
+ }
+
+ return 0;
+}
+
+static void ipvlan_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
+{
+
+ if (!tb)
+ return;
+
+ if (tb[IFLA_IPVLAN_MODE]) {
+ if (RTA_PAYLOAD(tb[IFLA_IPVLAN_MODE]) == sizeof(__u16)) {
+ __u16 mode = rta_getattr_u16(tb[IFLA_IPVLAN_MODE]);
+
+ fprintf(f, " mode %s ",
+ mode == IPVLAN_MODE_L2 ? "l2" :
+ mode == IPVLAN_MODE_L3 ? "l3" : "unknown");
+ }
+ }
+}
+
+static void ipvlan_print_help(struct link_util *lu, int argc, char **argv,
+ FILE *f)
+{
+ ipvlan_explain(f);
+}
+
+struct link_util ipvlan_link_util = {
+ .id = "ipvlan",
+ .maxattr = IFLA_IPVLAN_MAX,
+ .parse_opt = ipvlan_parse_opt,
+ .print_opt = ipvlan_print_opt,
+ .print_help = ipvlan_print_help,
+};
diff --git a/iproute2/ip/iplink_macvlan.c b/iproute2/ip/iplink_macvlan.c
new file mode 100644
index 0000000..f195e81
--- /dev/null
+++ b/iproute2/ip/iplink_macvlan.c
@@ -0,0 +1,146 @@
+/*
+ * iplink_macvlan.c macvlan/macvtap device support
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Patrick McHardy <kaber@trash.net>
+ * Arnd Bergmann <arnd@arndb.de>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <linux/if_link.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+
+#define pfx_err(lu, ...) { \
+ fprintf(stderr, "%s: ", lu->id); \
+ fprintf(stderr, __VA_ARGS__); \
+ fprintf(stderr, "\n"); \
+}
+
+static void print_explain(struct link_util *lu, FILE *f)
+{
+ fprintf(f,
+ "Usage: ... %s mode { private | vepa | bridge | passthru [nopromisc] }\n",
+ lu->id
+ );
+}
+
+static void explain(struct link_util *lu)
+{
+ print_explain(lu, stderr);
+}
+
+static int mode_arg(const char *arg)
+{
+ fprintf(stderr, "Error: argument of \"mode\" must be \"private\", "
+ "\"vepa\", \"bridge\" or \"passthru\", not \"%s\"\n", arg);
+ return -1;
+}
+
+static int macvlan_parse_opt(struct link_util *lu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ __u32 mode = 0;
+ __u16 flags = 0;
+
+ while (argc > 0) {
+ if (matches(*argv, "mode") == 0) {
+ NEXT_ARG();
+
+ if (strcmp(*argv, "private") == 0)
+ mode = MACVLAN_MODE_PRIVATE;
+ else if (strcmp(*argv, "vepa") == 0)
+ mode = MACVLAN_MODE_VEPA;
+ else if (strcmp(*argv, "bridge") == 0)
+ mode = MACVLAN_MODE_BRIDGE;
+ else if (strcmp(*argv, "passthru") == 0)
+ mode = MACVLAN_MODE_PASSTHRU;
+ else
+ return mode_arg(*argv);
+ } else if (matches(*argv, "nopromisc") == 0) {
+ flags |= MACVLAN_FLAG_NOPROMISC;
+ } else if (matches(*argv, "help") == 0) {
+ explain(lu);
+ return -1;
+ } else {
+ pfx_err(lu, "unknown option \"%s\"?", *argv);
+ explain(lu);
+ return -1;
+ }
+ argc--, argv++;
+ }
+
+ if (mode)
+ addattr32(n, 1024, IFLA_MACVLAN_MODE, mode);
+
+ if (flags) {
+ if (flags & MACVLAN_FLAG_NOPROMISC &&
+ mode != MACVLAN_MODE_PASSTHRU) {
+ pfx_err(lu, "nopromisc flag only valid in passthru mode");
+ explain(lu);
+ return -1;
+ }
+ addattr16(n, 1024, IFLA_MACVLAN_FLAGS, flags);
+ }
+ return 0;
+}
+
+static void macvlan_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
+{
+ __u32 mode;
+ __u16 flags;
+
+ if (!tb)
+ return;
+
+ if (!tb[IFLA_MACVLAN_MODE] ||
+ RTA_PAYLOAD(tb[IFLA_MACVLAN_MODE]) < sizeof(__u32))
+ return;
+
+ mode = rta_getattr_u32(tb[IFLA_MACVLAN_MODE]);
+ fprintf(f, " mode %s ",
+ mode == MACVLAN_MODE_PRIVATE ? "private"
+ : mode == MACVLAN_MODE_VEPA ? "vepa"
+ : mode == MACVLAN_MODE_BRIDGE ? "bridge"
+ : mode == MACVLAN_MODE_PASSTHRU ? "passthru"
+ : "unknown");
+
+ if (!tb[IFLA_MACVLAN_FLAGS] ||
+ RTA_PAYLOAD(tb[IFLA_MACVLAN_FLAGS]) < sizeof(__u16))
+ return;
+
+ flags = rta_getattr_u16(tb[IFLA_MACVLAN_FLAGS]);
+ if (flags & MACVLAN_FLAG_NOPROMISC)
+ fprintf(f, "nopromisc ");
+}
+
+static void macvlan_print_help(struct link_util *lu, int argc, char **argv,
+ FILE *f)
+{
+ print_explain(lu, f);
+}
+
+struct link_util macvlan_link_util = {
+ .id = "macvlan",
+ .maxattr = IFLA_MACVLAN_MAX,
+ .parse_opt = macvlan_parse_opt,
+ .print_opt = macvlan_print_opt,
+ .print_help = macvlan_print_help,
+};
+
+struct link_util macvtap_link_util = {
+ .id = "macvtap",
+ .maxattr = IFLA_MACVLAN_MAX,
+ .parse_opt = macvlan_parse_opt,
+ .print_opt = macvlan_print_opt,
+ .print_help = macvlan_print_help,
+};
diff --git a/iproute2/ip/iplink_vlan.c b/iproute2/ip/iplink_vlan.c
new file mode 100644
index 0000000..5bd766f
--- /dev/null
+++ b/iproute2/ip/iplink_vlan.c
@@ -0,0 +1,246 @@
+/*
+ * iplink_vlan.c VLAN device support
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Patrick McHardy <kaber@trash.net>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/if_vlan.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+
+static void print_explain(FILE *f)
+{
+ fprintf(f,
+ "Usage: ... vlan [ protocol VLANPROTO ] id VLANID"
+ " [ FLAG-LIST ]\n"
+ " [ ingress-qos-map QOS-MAP ] [ egress-qos-map QOS-MAP ]\n"
+ "\n"
+ "VLANPROTO: [ 802.1Q / 802.1ad ]\n"
+ "VLANID := 0-4095\n"
+ "FLAG-LIST := [ FLAG-LIST ] FLAG\n"
+ "FLAG := [ reorder_hdr { on | off } ] [ gvrp { on | off } ] [ mvrp { on | off } ]\n"
+ " [ loose_binding { on | off } ]\n"
+ "QOS-MAP := [ QOS-MAP ] QOS-MAPPING\n"
+ "QOS-MAPPING := FROM:TO\n"
+ );
+}
+
+static void explain(void)
+{
+ print_explain(stderr);
+}
+
+static int on_off(const char *msg, const char *arg)
+{
+ fprintf(stderr, "Error: argument of \"%s\" must be \"on\" or \"off\", not \"%s\"\n", msg, arg);
+ return -1;
+}
+
+static int vlan_parse_qos_map(int *argcp, char ***argvp, struct nlmsghdr *n,
+ int attrtype)
+{
+ int argc = *argcp;
+ char **argv = *argvp;
+ struct ifla_vlan_qos_mapping m;
+ struct rtattr *tail;
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 1024, attrtype, NULL, 0);
+
+ while (argc > 0) {
+ char *colon = strchr(*argv, ':');
+
+ if (!colon)
+ break;
+ *colon = '\0';
+
+ if (get_u32(&m.from, *argv, 0))
+ return 1;
+ if (get_u32(&m.to, colon + 1, 0))
+ return 1;
+ argc--, argv++;
+
+ addattr_l(n, 1024, IFLA_VLAN_QOS_MAPPING, &m, sizeof(m));
+ }
+
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *)tail;
+
+ *argcp = argc;
+ *argvp = argv;
+ return 0;
+}
+
+static int vlan_parse_opt(struct link_util *lu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ struct ifla_vlan_flags flags = { 0 };
+ __u16 id, proto;
+
+ while (argc > 0) {
+ if (matches(*argv, "protocol") == 0) {
+ NEXT_ARG();
+ if (ll_proto_a2n(&proto, *argv))
+ invarg("protocol is invalid", *argv);
+ addattr_l(n, 1024, IFLA_VLAN_PROTOCOL, &proto, 2);
+ } else if (matches(*argv, "id") == 0) {
+ NEXT_ARG();
+ if (get_u16(&id, *argv, 0))
+ invarg("id is invalid", *argv);
+ addattr_l(n, 1024, IFLA_VLAN_ID, &id, 2);
+ } else if (matches(*argv, "reorder_hdr") == 0) {
+ NEXT_ARG();
+ flags.mask |= VLAN_FLAG_REORDER_HDR;
+ if (strcmp(*argv, "on") == 0)
+ flags.flags |= VLAN_FLAG_REORDER_HDR;
+ else if (strcmp(*argv, "off") == 0)
+ flags.flags &= ~VLAN_FLAG_REORDER_HDR;
+ else
+ return on_off("reorder_hdr", *argv);
+ } else if (matches(*argv, "gvrp") == 0) {
+ NEXT_ARG();
+ flags.mask |= VLAN_FLAG_GVRP;
+ if (strcmp(*argv, "on") == 0)
+ flags.flags |= VLAN_FLAG_GVRP;
+ else if (strcmp(*argv, "off") == 0)
+ flags.flags &= ~VLAN_FLAG_GVRP;
+ else
+ return on_off("gvrp", *argv);
+ } else if (matches(*argv, "mvrp") == 0) {
+ NEXT_ARG();
+ flags.mask |= VLAN_FLAG_MVRP;
+ if (strcmp(*argv, "on") == 0)
+ flags.flags |= VLAN_FLAG_MVRP;
+ else if (strcmp(*argv, "off") == 0)
+ flags.flags &= ~VLAN_FLAG_MVRP;
+ else
+ return on_off("mvrp", *argv);
+ } else if (matches(*argv, "loose_binding") == 0) {
+ NEXT_ARG();
+ flags.mask |= VLAN_FLAG_LOOSE_BINDING;
+ if (strcmp(*argv, "on") == 0)
+ flags.flags |= VLAN_FLAG_LOOSE_BINDING;
+ else if (strcmp(*argv, "off") == 0)
+ flags.flags &= ~VLAN_FLAG_LOOSE_BINDING;
+ else
+ return on_off("loose_binding", *argv);
+ } else if (matches(*argv, "ingress-qos-map") == 0) {
+ NEXT_ARG();
+ if (vlan_parse_qos_map(&argc, &argv, n,
+ IFLA_VLAN_INGRESS_QOS))
+ invarg("invalid ingress-qos-map", *argv);
+ continue;
+ } else if (matches(*argv, "egress-qos-map") == 0) {
+ NEXT_ARG();
+ if (vlan_parse_qos_map(&argc, &argv, n,
+ IFLA_VLAN_EGRESS_QOS))
+ invarg("invalid egress-qos-map", *argv);
+ continue;
+ } else if (matches(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "vlan: unknown command \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--, argv++;
+ }
+
+ if (flags.mask)
+ addattr_l(n, 1024, IFLA_VLAN_FLAGS, &flags, sizeof(flags));
+
+ return 0;
+}
+
+static void vlan_print_map(FILE *f, char *name, struct rtattr *attr)
+{
+ struct ifla_vlan_qos_mapping *m;
+ struct rtattr *i;
+ int rem;
+
+ fprintf(f, "\n %s { ", name);
+
+ rem = RTA_PAYLOAD(attr);
+ for (i = RTA_DATA(attr); RTA_OK(i, rem); i = RTA_NEXT(i, rem)) {
+ m = RTA_DATA(i);
+ fprintf(f, "%u:%u ", m->from, m->to);
+ }
+ fprintf(f, "} ");
+}
+
+static void vlan_print_flags(FILE *fp, __u32 flags)
+{
+ fprintf(fp, "<");
+#define _PF(f) if (flags & VLAN_FLAG_##f) { \
+ flags &= ~ VLAN_FLAG_##f; \
+ fprintf(fp, #f "%s", flags ? "," : ""); \
+ }
+ _PF(REORDER_HDR);
+ _PF(GVRP);
+ _PF(MVRP);
+ _PF(LOOSE_BINDING);
+#undef _PF
+ if (flags)
+ fprintf(fp, "%x", flags);
+ fprintf(fp, "> ");
+}
+
+static void vlan_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
+{
+ struct ifla_vlan_flags *flags;
+ SPRINT_BUF(b1);
+
+ if (!tb)
+ return;
+
+ if (tb[IFLA_VLAN_PROTOCOL] &&
+ RTA_PAYLOAD(tb[IFLA_VLAN_PROTOCOL]) < sizeof(__u16))
+ return;
+ if (!tb[IFLA_VLAN_ID] ||
+ RTA_PAYLOAD(tb[IFLA_VLAN_ID]) < sizeof(__u16))
+ return;
+
+ if (tb[IFLA_VLAN_PROTOCOL])
+ fprintf(f, "protocol %s ",
+ ll_proto_n2a(rta_getattr_u16(tb[IFLA_VLAN_PROTOCOL]),
+ b1, sizeof(b1)));
+ else
+ fprintf(f, "protocol 802.1q ");
+
+ fprintf(f, "id %u ", rta_getattr_u16(tb[IFLA_VLAN_ID]));
+
+ if (tb[IFLA_VLAN_FLAGS]) {
+ if (RTA_PAYLOAD(tb[IFLA_VLAN_FLAGS]) < sizeof(*flags))
+ return;
+ flags = RTA_DATA(tb[IFLA_VLAN_FLAGS]);
+ vlan_print_flags(f, flags->flags);
+ }
+ if (tb[IFLA_VLAN_INGRESS_QOS])
+ vlan_print_map(f, "ingress-qos-map", tb[IFLA_VLAN_INGRESS_QOS]);
+ if (tb[IFLA_VLAN_EGRESS_QOS])
+ vlan_print_map(f, "egress-qos-map", tb[IFLA_VLAN_EGRESS_QOS]);
+}
+
+static void vlan_print_help(struct link_util *lu, int argc, char **argv,
+ FILE *f)
+{
+ print_explain(f);
+}
+
+struct link_util vlan_link_util = {
+ .id = "vlan",
+ .maxattr = IFLA_VLAN_MAX,
+ .parse_opt = vlan_parse_opt,
+ .print_opt = vlan_print_opt,
+ .print_help = vlan_print_help,
+};
diff --git a/iproute2/ip/iplink_vrf.c b/iproute2/ip/iplink_vrf.c
new file mode 100644
index 0000000..9b4b772
--- /dev/null
+++ b/iproute2/ip/iplink_vrf.c
@@ -0,0 +1,79 @@
+/* iplink_vrf.c VRF device support
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Shrijeet Mukherjee <shm@cumulusnetworks.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <linux/if_link.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+
+static void vrf_explain(FILE *f)
+{
+ fprintf(f, "Usage: ... vrf table TABLEID \n");
+}
+
+static void explain(void)
+{
+ vrf_explain(stderr);
+}
+
+static int vrf_parse_opt(struct link_util *lu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ while (argc > 0) {
+ if (matches(*argv, "table") == 0) {
+ __u32 table;
+
+ NEXT_ARG();
+
+ if (rtnl_rttable_a2n(&table, *argv))
+ invarg("invalid table ID\n", *argv);
+ addattr32(n, 1024, IFLA_VRF_TABLE, table);
+ } else if (matches(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "vrf: unknown option \"%s\"?\n",
+ *argv);
+ explain();
+ return -1;
+ }
+ argc--, argv++;
+ }
+
+ return 0;
+}
+
+static void vrf_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
+{
+ if (!tb)
+ return;
+
+ if (tb[IFLA_VRF_TABLE])
+ fprintf(f, "table %u ", rta_getattr_u32(tb[IFLA_VRF_TABLE]));
+}
+
+static void vrf_print_help(struct link_util *lu, int argc, char **argv,
+ FILE *f)
+{
+ vrf_explain(f);
+}
+
+struct link_util vrf_link_util = {
+ .id = "vrf",
+ .maxattr = IFLA_VRF_MAX,
+ .parse_opt = vrf_parse_opt,
+ .print_opt = vrf_print_opt,
+ .print_help = vrf_print_help,
+};
diff --git a/iproute2/ip/iplink_vxlan.c b/iproute2/ip/iplink_vxlan.c
new file mode 100644
index 0000000..ede8482
--- /dev/null
+++ b/iproute2/ip/iplink_vxlan.c
@@ -0,0 +1,462 @@
+/*
+ * iplink_vxlan.c VXLAN device support
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Stephen Hemminger <shemminger@vyatta.com
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <net/if.h>
+#include <linux/ip.h>
+#include <linux/if_link.h>
+#include <arpa/inet.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+
+static void print_explain(FILE *f)
+{
+ fprintf(f, "Usage: ... vxlan id VNI [ { group | remote } IP_ADDRESS ] [ local ADDR ]\n");
+ fprintf(f, " [ ttl TTL ] [ tos TOS ] [ dev PHYS_DEV ]\n");
+ fprintf(f, " [ dstport PORT ] [ srcport MIN MAX ]\n");
+ fprintf(f, " [ [no]learning ] [ [no]proxy ] [ [no]rsc ]\n");
+ fprintf(f, " [ [no]l2miss ] [ [no]l3miss ]\n");
+ fprintf(f, " [ ageing SECONDS ] [ maxaddress NUMBER ]\n");
+ fprintf(f, " [ [no]udpcsum ] [ [no]udp6zerocsumtx ] [ [no]udp6zerocsumrx ]\n");
+ fprintf(f, " [ [no]remcsumtx ] [ [no]remcsumrx ]\n");
+ fprintf(f, " [ [no]external ] [ gbp ]\n");
+ fprintf(f, "\n");
+ fprintf(f, "Where: VNI := 0-16777215\n");
+ fprintf(f, " ADDR := { IP_ADDRESS | any }\n");
+ fprintf(f, " TOS := { NUMBER | inherit }\n");
+ fprintf(f, " TTL := { 1..255 | inherit }\n");
+}
+
+static void explain(void)
+{
+ print_explain(stderr);
+}
+
+static int vxlan_parse_opt(struct link_util *lu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ __u32 vni = 0;
+ int vni_set = 0;
+ __u32 saddr = 0;
+ __u32 gaddr = 0;
+ __u32 daddr = 0;
+ struct in6_addr saddr6 = IN6ADDR_ANY_INIT;
+ struct in6_addr gaddr6 = IN6ADDR_ANY_INIT;
+ struct in6_addr daddr6 = IN6ADDR_ANY_INIT;
+ unsigned link = 0;
+ __u8 tos = 0;
+ __u8 ttl = 0;
+ __u8 learning = 1;
+ __u8 proxy = 0;
+ __u8 rsc = 0;
+ __u8 l2miss = 0;
+ __u8 l3miss = 0;
+ __u8 noage = 0;
+ __u32 age = 0;
+ __u32 maxaddr = 0;
+ __u16 dstport = 0;
+ __u8 udpcsum = 0;
+ __u8 udp6zerocsumtx = 0;
+ __u8 udp6zerocsumrx = 0;
+ __u8 remcsumtx = 0;
+ __u8 remcsumrx = 0;
+ __u8 metadata = 0;
+ __u8 gbp = 0;
+ int dst_port_set = 0;
+ struct ifla_vxlan_port_range range = { 0, 0 };
+
+ while (argc > 0) {
+ if (!matches(*argv, "id") ||
+ !matches(*argv, "vni")) {
+ NEXT_ARG();
+ if (get_u32(&vni, *argv, 0) ||
+ vni >= 1u << 24)
+ invarg("invalid id", *argv);
+ vni_set = 1;
+ } else if (!matches(*argv, "group")) {
+ NEXT_ARG();
+ if (!inet_get_addr(*argv, &gaddr, &gaddr6)) {
+ fprintf(stderr, "Invalid address \"%s\"\n", *argv);
+ return -1;
+ }
+ if (!IN6_IS_ADDR_MULTICAST(&gaddr6) && !IN_MULTICAST(ntohl(gaddr)))
+ invarg("invalid group address", *argv);
+ } else if (!matches(*argv, "remote")) {
+ NEXT_ARG();
+ if (!inet_get_addr(*argv, &daddr, &daddr6)) {
+ fprintf(stderr, "Invalid address \"%s\"\n", *argv);
+ return -1;
+ }
+ if (IN6_IS_ADDR_MULTICAST(&daddr6) || IN_MULTICAST(ntohl(daddr)))
+ invarg("invalid remote address", *argv);
+ } else if (!matches(*argv, "local")) {
+ NEXT_ARG();
+ if (strcmp(*argv, "any")) {
+ if (!inet_get_addr(*argv, &saddr, &saddr6)) {
+ fprintf(stderr, "Invalid address \"%s\"\n", *argv);
+ return -1;
+ }
+ }
+
+ if (IN_MULTICAST(ntohl(saddr)) || IN6_IS_ADDR_MULTICAST(&saddr6))
+ invarg("invalid local address", *argv);
+ } else if (!matches(*argv, "dev")) {
+ NEXT_ARG();
+ link = if_nametoindex(*argv);
+ if (link == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n",
+ *argv);
+ exit(-1);
+ }
+ } else if (!matches(*argv, "ttl") ||
+ !matches(*argv, "hoplimit")) {
+ unsigned uval;
+
+ NEXT_ARG();
+ if (strcmp(*argv, "inherit") != 0) {
+ if (get_unsigned(&uval, *argv, 0))
+ invarg("invalid TTL", *argv);
+ if (uval > 255)
+ invarg("TTL must be <= 255", *argv);
+ ttl = uval;
+ }
+ } else if (!matches(*argv, "tos") ||
+ !matches(*argv, "dsfield")) {
+ __u32 uval;
+
+ NEXT_ARG();
+ if (strcmp(*argv, "inherit") != 0) {
+ if (rtnl_dsfield_a2n(&uval, *argv))
+ invarg("bad TOS value", *argv);
+ tos = uval;
+ } else
+ tos = 1;
+ } else if (!matches(*argv, "ageing")) {
+ NEXT_ARG();
+ if (strcmp(*argv, "none") == 0)
+ noage = 1;
+ else if (get_u32(&age, *argv, 0))
+ invarg("ageing timer", *argv);
+ } else if (!matches(*argv, "maxaddress")) {
+ NEXT_ARG();
+ if (strcmp(*argv, "unlimited") == 0)
+ maxaddr = 0;
+ else if (get_u32(&maxaddr, *argv, 0))
+ invarg("max addresses", *argv);
+ } else if (!matches(*argv, "port") ||
+ !matches(*argv, "srcport")) {
+ __u16 minport, maxport;
+ NEXT_ARG();
+ if (get_u16(&minport, *argv, 0))
+ invarg("min port", *argv);
+ NEXT_ARG();
+ if (get_u16(&maxport, *argv, 0))
+ invarg("max port", *argv);
+ range.low = htons(minport);
+ range.high = htons(maxport);
+ } else if (!matches(*argv, "dstport")){
+ NEXT_ARG();
+ if (get_u16(&dstport, *argv, 0))
+ invarg("dst port", *argv);
+ dst_port_set = 1;
+ } else if (!matches(*argv, "nolearning")) {
+ learning = 0;
+ } else if (!matches(*argv, "learning")) {
+ learning = 1;
+ } else if (!matches(*argv, "noproxy")) {
+ proxy = 0;
+ } else if (!matches(*argv, "proxy")) {
+ proxy = 1;
+ } else if (!matches(*argv, "norsc")) {
+ rsc = 0;
+ } else if (!matches(*argv, "rsc")) {
+ rsc = 1;
+ } else if (!matches(*argv, "nol2miss")) {
+ l2miss = 0;
+ } else if (!matches(*argv, "l2miss")) {
+ l2miss = 1;
+ } else if (!matches(*argv, "nol3miss")) {
+ l3miss = 0;
+ } else if (!matches(*argv, "l3miss")) {
+ l3miss = 1;
+ } else if (!matches(*argv, "udpcsum")) {
+ udpcsum = 1;
+ } else if (!matches(*argv, "noudpcsum")) {
+ udpcsum = 0;
+ } else if (!matches(*argv, "udp6zerocsumtx")) {
+ udp6zerocsumtx = 1;
+ } else if (!matches(*argv, "noudp6zerocsumtx")) {
+ udp6zerocsumtx = 0;
+ } else if (!matches(*argv, "udp6zerocsumrx")) {
+ udp6zerocsumrx = 1;
+ } else if (!matches(*argv, "noudp6zerocsumrx")) {
+ udp6zerocsumrx = 0;
+ } else if (!matches(*argv, "remcsumtx")) {
+ remcsumtx = 1;
+ } else if (!matches(*argv, "noremcsumtx")) {
+ remcsumtx = 0;
+ } else if (!matches(*argv, "remcsumrx")) {
+ remcsumrx = 1;
+ } else if (!matches(*argv, "noremcsumrx")) {
+ remcsumrx = 0;
+ } else if (!matches(*argv, "external")) {
+ metadata = 1;
+ } else if (!matches(*argv, "noexternal")) {
+ metadata = 0;
+ } else if (!matches(*argv, "gbp")) {
+ gbp = 1;
+ } else if (matches(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "vxlan: unknown command \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--, argv++;
+ }
+
+ if (metadata && vni_set) {
+ fprintf(stderr, "vxlan: both 'external' and vni cannot be specified\n");
+ return -1;
+ }
+
+ if (!metadata && !vni_set) {
+ fprintf(stderr, "vxlan: missing virtual network identifier\n");
+ return -1;
+ }
+
+ if ((gaddr && daddr) ||
+ (memcmp(&gaddr6, &in6addr_any, sizeof(gaddr6)) &&
+ memcmp(&daddr6, &in6addr_any, sizeof(daddr6)))) {
+ fprintf(stderr, "vxlan: both group and remote cannot be specified\n");
+ return -1;
+ }
+
+ if (!dst_port_set) {
+ fprintf(stderr, "vxlan: destination port not specified\n"
+ "Will use Linux kernel default (non-standard value)\n");
+ fprintf(stderr,
+ "Use 'dstport 4789' to get the IANA assigned value\n"
+ "Use 'dstport 0' to get default and quiet this message\n");
+ }
+
+ addattr32(n, 1024, IFLA_VXLAN_ID, vni);
+ if (gaddr)
+ addattr_l(n, 1024, IFLA_VXLAN_GROUP, &gaddr, 4);
+ else if (daddr)
+ addattr_l(n, 1024, IFLA_VXLAN_GROUP, &daddr, 4);
+ if (memcmp(&gaddr6, &in6addr_any, sizeof(gaddr6)) != 0)
+ addattr_l(n, 1024, IFLA_VXLAN_GROUP6, &gaddr6, sizeof(struct in6_addr));
+ else if (memcmp(&daddr6, &in6addr_any, sizeof(daddr6)) != 0)
+ addattr_l(n, 1024, IFLA_VXLAN_GROUP6, &daddr6, sizeof(struct in6_addr));
+
+ if (saddr)
+ addattr_l(n, 1024, IFLA_VXLAN_LOCAL, &saddr, 4);
+ else if (memcmp(&saddr6, &in6addr_any, sizeof(saddr6)) != 0)
+ addattr_l(n, 1024, IFLA_VXLAN_LOCAL6, &saddr6, sizeof(struct in6_addr));
+
+ if (link)
+ addattr32(n, 1024, IFLA_VXLAN_LINK, link);
+ addattr8(n, 1024, IFLA_VXLAN_TTL, ttl);
+ addattr8(n, 1024, IFLA_VXLAN_TOS, tos);
+ addattr8(n, 1024, IFLA_VXLAN_LEARNING, learning);
+ addattr8(n, 1024, IFLA_VXLAN_PROXY, proxy);
+ addattr8(n, 1024, IFLA_VXLAN_RSC, rsc);
+ addattr8(n, 1024, IFLA_VXLAN_L2MISS, l2miss);
+ addattr8(n, 1024, IFLA_VXLAN_L3MISS, l3miss);
+ addattr8(n, 1024, IFLA_VXLAN_UDP_CSUM, udpcsum);
+ addattr8(n, 1024, IFLA_VXLAN_UDP_ZERO_CSUM6_TX, udp6zerocsumtx);
+ addattr8(n, 1024, IFLA_VXLAN_UDP_ZERO_CSUM6_RX, udp6zerocsumrx);
+ addattr8(n, 1024, IFLA_VXLAN_REMCSUM_TX, remcsumtx);
+ addattr8(n, 1024, IFLA_VXLAN_REMCSUM_RX, remcsumrx);
+ addattr8(n, 1024, IFLA_VXLAN_COLLECT_METADATA, metadata);
+
+ if (noage)
+ addattr32(n, 1024, IFLA_VXLAN_AGEING, 0);
+ else if (age)
+ addattr32(n, 1024, IFLA_VXLAN_AGEING, age);
+ if (maxaddr)
+ addattr32(n, 1024, IFLA_VXLAN_LIMIT, maxaddr);
+ if (range.low || range.high)
+ addattr_l(n, 1024, IFLA_VXLAN_PORT_RANGE,
+ &range, sizeof(range));
+ if (dstport)
+ addattr16(n, 1024, IFLA_VXLAN_PORT, htons(dstport));
+
+ if (gbp)
+ addattr_l(n, 1024, IFLA_VXLAN_GBP, NULL, 0);
+
+
+ return 0;
+}
+
+static void vxlan_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
+{
+ __u32 vni;
+ unsigned link;
+ __u8 tos;
+ __u32 maxaddr;
+ char s1[1024];
+ char s2[64];
+
+ if (!tb)
+ return;
+
+ if (!tb[IFLA_VXLAN_ID] ||
+ RTA_PAYLOAD(tb[IFLA_VXLAN_ID]) < sizeof(__u32))
+ return;
+
+ vni = rta_getattr_u32(tb[IFLA_VXLAN_ID]);
+ fprintf(f, "id %u ", vni);
+
+ if (tb[IFLA_VXLAN_GROUP]) {
+ __be32 addr = rta_getattr_u32(tb[IFLA_VXLAN_GROUP]);
+ if (addr) {
+ if (IN_MULTICAST(ntohl(addr)))
+ fprintf(f, "group %s ",
+ format_host(AF_INET, 4, &addr, s1, sizeof(s1)));
+ else
+ fprintf(f, "remote %s ",
+ format_host(AF_INET, 4, &addr, s1, sizeof(s1)));
+ }
+ } else if (tb[IFLA_VXLAN_GROUP6]) {
+ struct in6_addr addr;
+ memcpy(&addr, RTA_DATA(tb[IFLA_VXLAN_GROUP6]), sizeof(struct in6_addr));
+ if (memcmp(&addr, &in6addr_any, sizeof(addr)) != 0) {
+ if (IN6_IS_ADDR_MULTICAST(&addr))
+ fprintf(f, "group %s ",
+ format_host(AF_INET6, sizeof(struct in6_addr), &addr, s1, sizeof(s1)));
+ else
+ fprintf(f, "remote %s ",
+ format_host(AF_INET6, sizeof(struct in6_addr), &addr, s1, sizeof(s1)));
+ }
+ }
+
+ if (tb[IFLA_VXLAN_LOCAL]) {
+ __be32 addr = rta_getattr_u32(tb[IFLA_VXLAN_LOCAL]);
+ if (addr)
+ fprintf(f, "local %s ",
+ format_host(AF_INET, 4, &addr, s1, sizeof(s1)));
+ } else if (tb[IFLA_VXLAN_LOCAL6]) {
+ struct in6_addr addr;
+ memcpy(&addr, RTA_DATA(tb[IFLA_VXLAN_LOCAL6]), sizeof(struct in6_addr));
+ if (memcmp(&addr, &in6addr_any, sizeof(addr)) != 0)
+ fprintf(f, "local %s ",
+ format_host(AF_INET6, sizeof(struct in6_addr), &addr, s1, sizeof(s1)));
+ }
+
+ if (tb[IFLA_VXLAN_LINK] &&
+ (link = rta_getattr_u32(tb[IFLA_VXLAN_LINK]))) {
+ const char *n = if_indextoname(link, s2);
+
+ if (n)
+ fprintf(f, "dev %s ", n);
+ else
+ fprintf(f, "dev %u ", link);
+ }
+
+ if (tb[IFLA_VXLAN_PORT_RANGE]) {
+ const struct ifla_vxlan_port_range *r
+ = RTA_DATA(tb[IFLA_VXLAN_PORT_RANGE]);
+ fprintf(f, "srcport %u %u ", ntohs(r->low), ntohs(r->high));
+ }
+
+ if (tb[IFLA_VXLAN_PORT])
+ fprintf(f, "dstport %u ",
+ ntohs(rta_getattr_u16(tb[IFLA_VXLAN_PORT])));
+
+ if (tb[IFLA_VXLAN_LEARNING] &&
+ !rta_getattr_u8(tb[IFLA_VXLAN_LEARNING]))
+ fputs("nolearning ", f);
+
+ if (tb[IFLA_VXLAN_PROXY] && rta_getattr_u8(tb[IFLA_VXLAN_PROXY]))
+ fputs("proxy ", f);
+
+ if (tb[IFLA_VXLAN_RSC] && rta_getattr_u8(tb[IFLA_VXLAN_RSC]))
+ fputs("rsc ", f);
+
+ if (tb[IFLA_VXLAN_L2MISS] && rta_getattr_u8(tb[IFLA_VXLAN_L2MISS]))
+ fputs("l2miss ", f);
+
+ if (tb[IFLA_VXLAN_L3MISS] && rta_getattr_u8(tb[IFLA_VXLAN_L3MISS]))
+ fputs("l3miss ", f);
+
+ if (tb[IFLA_VXLAN_TOS] &&
+ (tos = rta_getattr_u8(tb[IFLA_VXLAN_TOS]))) {
+ if (tos == 1)
+ fprintf(f, "tos inherit ");
+ else
+ fprintf(f, "tos %#x ", tos);
+ }
+
+ if (tb[IFLA_VXLAN_TTL]) {
+ __u8 ttl = rta_getattr_u8(tb[IFLA_VXLAN_TTL]);
+ if (ttl)
+ fprintf(f, "ttl %d ", ttl);
+ }
+
+ if (tb[IFLA_VXLAN_AGEING]) {
+ __u32 age = rta_getattr_u32(tb[IFLA_VXLAN_AGEING]);
+ if (age == 0)
+ fprintf(f, "ageing none ");
+ else
+ fprintf(f, "ageing %u ", age);
+ }
+
+ if (tb[IFLA_VXLAN_LIMIT] &&
+ ((maxaddr = rta_getattr_u32(tb[IFLA_VXLAN_LIMIT])) != 0))
+ fprintf(f, "maxaddr %u ", maxaddr);
+
+ if (tb[IFLA_VXLAN_UDP_CSUM] && rta_getattr_u8(tb[IFLA_VXLAN_UDP_CSUM]))
+ fputs("udpcsum ", f);
+
+ if (tb[IFLA_VXLAN_UDP_ZERO_CSUM6_TX] &&
+ rta_getattr_u8(tb[IFLA_VXLAN_UDP_ZERO_CSUM6_TX]))
+ fputs("udp6zerocsumtx ", f);
+
+ if (tb[IFLA_VXLAN_UDP_ZERO_CSUM6_RX] &&
+ rta_getattr_u8(tb[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]))
+ fputs("udp6zerocsumrx ", f);
+
+ if (tb[IFLA_VXLAN_REMCSUM_TX] &&
+ rta_getattr_u8(tb[IFLA_VXLAN_REMCSUM_TX]))
+ fputs("remcsumtx ", f);
+
+ if (tb[IFLA_VXLAN_REMCSUM_RX] &&
+ rta_getattr_u8(tb[IFLA_VXLAN_REMCSUM_RX]))
+ fputs("remcsumrx ", f);
+
+ if (tb[IFLA_VXLAN_COLLECT_METADATA] &&
+ rta_getattr_u8(tb[IFLA_VXLAN_COLLECT_METADATA]))
+ fputs("external ", f);
+
+ if (tb[IFLA_VXLAN_GBP])
+ fputs("gbp ", f);
+}
+
+static void vxlan_print_help(struct link_util *lu, int argc, char **argv,
+ FILE *f)
+{
+ print_explain(f);
+}
+
+struct link_util vxlan_link_util = {
+ .id = "vxlan",
+ .maxattr = IFLA_VXLAN_MAX,
+ .parse_opt = vxlan_parse_opt,
+ .print_opt = vxlan_print_opt,
+ .print_help = vxlan_print_help,
+};
diff --git a/iproute2/ip/ipmaddr.c b/iproute2/ip/ipmaddr.c
new file mode 100644
index 0000000..cbd6d11
--- /dev/null
+++ b/iproute2/ip/ipmaddr.c
@@ -0,0 +1,348 @@
+/*
+ * ipmaddr.c "ip maddress".
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include <linux/netdevice.h>
+#include <linux/if.h>
+#include <linux/if_arp.h>
+#include <linux/sockios.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+
+static struct {
+ char *dev;
+ int family;
+} filter;
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: ip maddr [ add | del ] MULTIADDR dev STRING\n");
+ fprintf(stderr, " ip maddr show [ dev STRING ]\n");
+ exit(-1);
+}
+
+static int parse_hex(char *str, unsigned char *addr, size_t size)
+{
+ int len = 0;
+
+ while (*str && (len < 2 * size)) {
+ int tmp;
+ if (str[1] == 0)
+ return -1;
+ if (sscanf(str, "%02x", &tmp) != 1)
+ return -1;
+ addr[len] = tmp;
+ len++;
+ str += 2;
+ }
+ return len;
+}
+
+struct ma_info
+{
+ struct ma_info *next;
+ int index;
+ int users;
+ char *features;
+ char name[IFNAMSIZ];
+ inet_prefix addr;
+};
+
+static void maddr_ins(struct ma_info **lst, struct ma_info *m)
+{
+ struct ma_info *mp;
+
+ for (; (mp = *lst) != NULL; lst = &mp->next) {
+ if (mp->index > m->index)
+ break;
+ }
+ m->next = *lst;
+ *lst = m;
+}
+
+static void read_dev_mcast(struct ma_info **result_p)
+{
+ char buf[256];
+ FILE *fp = fopen("/proc/net/dev_mcast", "r");
+
+ if (!fp)
+ return;
+
+ while (fgets(buf, sizeof(buf), fp)) {
+ char hexa[256];
+ struct ma_info m;
+ int len;
+ int st;
+
+ memset(&m, 0, sizeof(m));
+ sscanf(buf, "%d%s%d%d%s", &m.index, m.name, &m.users, &st,
+ hexa);
+ if (filter.dev && strcmp(filter.dev, m.name))
+ continue;
+
+ m.addr.family = AF_PACKET;
+
+ len = parse_hex(hexa, (unsigned char*)&m.addr.data, sizeof (m.addr.data));
+ if (len >= 0) {
+ struct ma_info *ma = malloc(sizeof(m));
+
+ memcpy(ma, &m, sizeof(m));
+ ma->addr.bytelen = len;
+ ma->addr.bitlen = len<<3;
+ if (st)
+ ma->features = "static";
+ maddr_ins(result_p, ma);
+ }
+ }
+ fclose(fp);
+}
+
+static void read_igmp(struct ma_info **result_p)
+{
+ struct ma_info m;
+ char buf[256];
+ FILE *fp = fopen("/proc/net/igmp", "r");
+
+ if (!fp)
+ return;
+ memset(&m, 0, sizeof(m));
+ if (!fgets(buf, sizeof(buf), fp)) {
+ fclose(fp);
+ return;
+ }
+
+ m.addr.family = AF_INET;
+ m.addr.bitlen = 32;
+ m.addr.bytelen = 4;
+
+ while (fgets(buf, sizeof(buf), fp)) {
+ struct ma_info *ma;
+
+ if (buf[0] != '\t') {
+ sscanf(buf, "%d%s", &m.index, m.name);
+ continue;
+ }
+
+ if (filter.dev && strcmp(filter.dev, m.name))
+ continue;
+
+ sscanf(buf, "%08x%d", (__u32*)&m.addr.data, &m.users);
+
+ ma = malloc(sizeof(m));
+ memcpy(ma, &m, sizeof(m));
+ maddr_ins(result_p, ma);
+ }
+ fclose(fp);
+}
+
+
+static void read_igmp6(struct ma_info **result_p)
+{
+ char buf[256];
+ FILE *fp = fopen("/proc/net/igmp6", "r");
+
+ if (!fp)
+ return;
+
+ while (fgets(buf, sizeof(buf), fp)) {
+ char hexa[256];
+ struct ma_info m;
+ int len;
+
+ memset(&m, 0, sizeof(m));
+ sscanf(buf, "%d%s%s%d", &m.index, m.name, hexa, &m.users);
+
+ if (filter.dev && strcmp(filter.dev, m.name))
+ continue;
+
+ m.addr.family = AF_INET6;
+
+ len = parse_hex(hexa, (unsigned char*)&m.addr.data, sizeof (m.addr.data));
+ if (len >= 0) {
+ struct ma_info *ma = malloc(sizeof(m));
+
+ memcpy(ma, &m, sizeof(m));
+
+ ma->addr.bytelen = len;
+ ma->addr.bitlen = len<<3;
+ maddr_ins(result_p, ma);
+ }
+ }
+ fclose(fp);
+}
+
+static void print_maddr(FILE *fp, struct ma_info *list)
+{
+ fprintf(fp, "\t");
+
+ if (list->addr.family == AF_PACKET) {
+ SPRINT_BUF(b1);
+ fprintf(fp, "link %s", ll_addr_n2a((unsigned char*)list->addr.data,
+ list->addr.bytelen, 0,
+ b1, sizeof(b1)));
+ } else {
+ char abuf[256];
+ switch(list->addr.family) {
+ case AF_INET:
+ fprintf(fp, "inet ");
+ break;
+ case AF_INET6:
+ fprintf(fp, "inet6 ");
+ break;
+ default:
+ fprintf(fp, "family %d ", list->addr.family);
+ break;
+ }
+ fprintf(fp, "%s",
+ format_host(list->addr.family,
+ -1,
+ list->addr.data,
+ abuf, sizeof(abuf)));
+ }
+ if (list->users != 1)
+ fprintf(fp, " users %d", list->users);
+ if (list->features)
+ fprintf(fp, " %s", list->features);
+ fprintf(fp, "\n");
+}
+
+static void print_mlist(FILE *fp, struct ma_info *list)
+{
+ int cur_index = 0;
+
+ for (; list; list = list->next) {
+ if (oneline) {
+ cur_index = list->index;
+ fprintf(fp, "%d:\t%s%s", cur_index, list->name, _SL_);
+ } else if (cur_index != list->index) {
+ cur_index = list->index;
+ fprintf(fp, "%d:\t%s\n", cur_index, list->name);
+ }
+ print_maddr(fp, list);
+ }
+}
+
+static int multiaddr_list(int argc, char **argv)
+{
+ struct ma_info *list = NULL;
+
+ if (!filter.family)
+ filter.family = preferred_family;
+
+ while (argc > 0) {
+ if (1) {
+ if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ }
+ else if (matches(*argv, "help") == 0)
+ usage();
+ if (filter.dev)
+ duparg2("dev", *argv);
+ filter.dev = *argv;
+ }
+ argv++; argc--;
+ }
+
+ if (!filter.family || filter.family == AF_PACKET)
+ read_dev_mcast(&list);
+ if (!filter.family || filter.family == AF_INET)
+ read_igmp(&list);
+ if (!filter.family || filter.family == AF_INET6)
+ read_igmp6(&list);
+ print_mlist(stdout, list);
+ return 0;
+}
+
+static int multiaddr_modify(int cmd, int argc, char **argv)
+{
+ struct ifreq ifr;
+ int fd;
+
+ memset(&ifr, 0, sizeof(ifr));
+
+ if (cmd == RTM_NEWADDR)
+ cmd = SIOCADDMULTI;
+ else
+ cmd = SIOCDELMULTI;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ if (ifr.ifr_name[0])
+ duparg("dev", *argv);
+ strncpy(ifr.ifr_name, *argv, IFNAMSIZ);
+ } else {
+ if (matches(*argv, "address") == 0) {
+ NEXT_ARG();
+ }
+ if (matches(*argv, "help") == 0)
+ usage();
+ if (ifr.ifr_hwaddr.sa_data[0])
+ duparg("address", *argv);
+ if (ll_addr_a2n(ifr.ifr_hwaddr.sa_data,
+ 14, *argv) < 0) {
+ fprintf(stderr, "Error: \"%s\" is not a legal ll address.\n", *argv);
+ exit(1);
+ }
+ }
+ argc--; argv++;
+ }
+ if (ifr.ifr_name[0] == 0) {
+ fprintf(stderr, "Not enough information: \"dev\" is required.\n");
+ exit(-1);
+ }
+
+ fd = socket(AF_INET, SOCK_DGRAM, 0);
+ if (fd < 0) {
+ perror("Cannot create socket");
+ exit(1);
+ }
+ if (ioctl(fd, cmd, (char*)&ifr) != 0) {
+ perror("ioctl");
+ exit(1);
+ }
+ close(fd);
+
+ exit(0);
+}
+
+
+int do_multiaddr(int argc, char **argv)
+{
+ if (argc < 1)
+ return multiaddr_list(0, NULL);
+ if (matches(*argv, "add") == 0)
+ return multiaddr_modify(RTM_NEWADDR, argc-1, argv+1);
+ if (matches(*argv, "delete") == 0)
+ return multiaddr_modify(RTM_DELADDR, argc-1, argv+1);
+ if (matches(*argv, "list") == 0 || matches(*argv, "show") == 0
+ || matches(*argv, "lst") == 0)
+ return multiaddr_list(argc-1, argv+1);
+ if (matches(*argv, "help") == 0)
+ usage();
+ fprintf(stderr, "Command \"%s\" is unknown, try \"ip maddr help\".\n", *argv);
+ exit(-1);
+}
diff --git a/iproute2/ip/ipmonitor.c b/iproute2/ip/ipmonitor.c
new file mode 100644
index 0000000..99a237f
--- /dev/null
+++ b/iproute2/ip/ipmonitor.c
@@ -0,0 +1,311 @@
+/*
+ * ipmonitor.c "ip monitor".
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <time.h>
+
+#include "utils.h"
+#include "ip_common.h"
+
+static void usage(void) __attribute__((noreturn));
+int prefix_banner;
+int listen_all_nsid;
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: ip monitor [ all | LISTofOBJECTS ] [ FILE ] "
+ "[ label ] [all-nsid] [dev DEVICE]\n");
+ fprintf(stderr, "LISTofOBJECTS := link | address | route | mroute | prefix |\n");
+ fprintf(stderr, " neigh | netconf | rule | nsid\n");
+ fprintf(stderr, "FILE := file FILENAME\n");
+ exit(-1);
+}
+
+static void print_headers(FILE *fp, char *label, struct rtnl_ctrl_data *ctrl)
+{
+ if (timestamp)
+ print_timestamp(fp);
+
+ if (listen_all_nsid) {
+ if (ctrl == NULL || ctrl->nsid < 0)
+ fprintf(fp, "[nsid current]");
+ else
+ fprintf(fp, "[nsid %d]", ctrl->nsid);
+ }
+
+ if (prefix_banner)
+ fprintf(fp, "%s", label);
+}
+
+static int accept_msg(const struct sockaddr_nl *who,
+ struct rtnl_ctrl_data *ctrl,
+ struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+
+ if (n->nlmsg_type == RTM_NEWROUTE || n->nlmsg_type == RTM_DELROUTE) {
+ struct rtmsg *r = NLMSG_DATA(n);
+ int len = n->nlmsg_len - NLMSG_LENGTH(sizeof(*r));
+
+ if (len < 0) {
+ fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+ return -1;
+ }
+
+ if (r->rtm_flags & RTM_F_CLONED)
+ return 0;
+
+ if (r->rtm_family == RTNL_FAMILY_IPMR ||
+ r->rtm_family == RTNL_FAMILY_IP6MR) {
+ print_headers(fp, "[MROUTE]", ctrl);
+ print_mroute(who, n, arg);
+ return 0;
+ } else {
+ print_headers(fp, "[ROUTE]", ctrl);
+ print_route(who, n, arg);
+ return 0;
+ }
+ }
+
+ if (n->nlmsg_type == RTM_NEWLINK || n->nlmsg_type == RTM_DELLINK) {
+ ll_remember_index(who, n, NULL);
+ print_headers(fp, "[LINK]", ctrl);
+ print_linkinfo(who, n, arg);
+ return 0;
+ }
+ if (n->nlmsg_type == RTM_NEWADDR || n->nlmsg_type == RTM_DELADDR) {
+ print_headers(fp, "[ADDR]", ctrl);
+ print_addrinfo(who, n, arg);
+ return 0;
+ }
+ if (n->nlmsg_type == RTM_NEWADDRLABEL || n->nlmsg_type == RTM_DELADDRLABEL) {
+ print_headers(fp, "[ADDRLABEL]", ctrl);
+ print_addrlabel(who, n, arg);
+ return 0;
+ }
+ if (n->nlmsg_type == RTM_NEWNEIGH || n->nlmsg_type == RTM_DELNEIGH ||
+ n->nlmsg_type == RTM_GETNEIGH) {
+ if (preferred_family) {
+ struct ndmsg *r = NLMSG_DATA(n);
+
+ if (r->ndm_family != preferred_family)
+ return 0;
+ }
+
+ print_headers(fp, "[NEIGH]", ctrl);
+ print_neigh(who, n, arg);
+ return 0;
+ }
+ if (n->nlmsg_type == RTM_NEWPREFIX) {
+ print_headers(fp, "[PREFIX]", ctrl);
+ print_prefix(who, n, arg);
+ return 0;
+ }
+ if (n->nlmsg_type == RTM_NEWRULE || n->nlmsg_type == RTM_DELRULE) {
+ print_headers(fp, "[RULE]", ctrl);
+ print_rule(who, n, arg);
+ return 0;
+ }
+ if (n->nlmsg_type == RTM_NEWNETCONF) {
+ print_headers(fp, "[NETCONF]", ctrl);
+ print_netconf(who, ctrl, n, arg);
+ return 0;
+ }
+ if (n->nlmsg_type == NLMSG_TSTAMP) {
+ print_nlmsg_timestamp(fp, n);
+ return 0;
+ }
+ if (n->nlmsg_type == RTM_NEWNSID || n->nlmsg_type == RTM_DELNSID) {
+ print_headers(fp, "[NSID]", ctrl);
+ print_nsid(who, n, arg);
+ return 0;
+ }
+ if (n->nlmsg_type != NLMSG_ERROR && n->nlmsg_type != NLMSG_NOOP &&
+ n->nlmsg_type != NLMSG_DONE) {
+ fprintf(fp, "Unknown message: type=0x%08x(%d) flags=0x%08x(%d)"
+ "len=0x%08x(%d)\n", n->nlmsg_type, n->nlmsg_type,
+ n->nlmsg_flags, n->nlmsg_flags, n->nlmsg_len,
+ n->nlmsg_len);
+ }
+ return 0;
+}
+
+int do_ipmonitor(int argc, char **argv)
+{
+ char *file = NULL;
+ unsigned groups = 0;
+ int llink=0;
+ int laddr=0;
+ int lroute=0;
+ int lmroute=0;
+ int lprefix=0;
+ int lneigh=0;
+ int lnetconf=0;
+ int lrule=0;
+ int lnsid=0;
+ int ifindex=0;
+
+ groups |= nl_mgrp(RTNLGRP_LINK);
+ groups |= nl_mgrp(RTNLGRP_IPV4_IFADDR);
+ groups |= nl_mgrp(RTNLGRP_IPV6_IFADDR);
+ groups |= nl_mgrp(RTNLGRP_IPV4_ROUTE);
+ groups |= nl_mgrp(RTNLGRP_IPV6_ROUTE);
+ groups |= nl_mgrp(RTNLGRP_MPLS_ROUTE);
+ groups |= nl_mgrp(RTNLGRP_IPV4_MROUTE);
+ groups |= nl_mgrp(RTNLGRP_IPV6_MROUTE);
+ groups |= nl_mgrp(RTNLGRP_IPV6_PREFIX);
+ groups |= nl_mgrp(RTNLGRP_NEIGH);
+ groups |= nl_mgrp(RTNLGRP_IPV4_NETCONF);
+ groups |= nl_mgrp(RTNLGRP_IPV6_NETCONF);
+ groups |= nl_mgrp(RTNLGRP_IPV4_RULE);
+ groups |= nl_mgrp(RTNLGRP_IPV6_RULE);
+ groups |= nl_mgrp(RTNLGRP_NSID);
+
+ rtnl_close(&rth);
+
+ while (argc > 0) {
+ if (matches(*argv, "file") == 0) {
+ NEXT_ARG();
+ file = *argv;
+ } else if (matches(*argv, "label") == 0) {
+ prefix_banner = 1;
+ } else if (matches(*argv, "all-nsid") == 0) {
+ listen_all_nsid = 1;
+ } else if (matches(*argv, "link") == 0) {
+ llink=1;
+ groups = 0;
+ } else if (matches(*argv, "address") == 0) {
+ laddr=1;
+ groups = 0;
+ } else if (matches(*argv, "route") == 0) {
+ lroute=1;
+ groups = 0;
+ } else if (matches(*argv, "mroute") == 0) {
+ lmroute=1;
+ groups = 0;
+ } else if (matches(*argv, "prefix") == 0) {
+ lprefix=1;
+ groups = 0;
+ } else if (matches(*argv, "neigh") == 0) {
+ lneigh = 1;
+ groups = 0;
+ } else if (matches(*argv, "netconf") == 0) {
+ lnetconf = 1;
+ groups = 0;
+ } else if (matches(*argv, "rule") == 0) {
+ lrule = 1;
+ groups = 0;
+ } else if (matches(*argv, "nsid") == 0) {
+ lnsid = 1;
+ groups = 0;
+ } else if (strcmp(*argv, "all") == 0) {
+ prefix_banner=1;
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ } else if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+
+ ifindex = ll_name_to_index(*argv);
+ if (!ifindex)
+ invarg("Device does not exist\n", *argv);
+ } else {
+ fprintf(stderr, "Argument \"%s\" is unknown, try \"ip monitor help\".\n", *argv);
+ exit(-1);
+ }
+ argc--; argv++;
+ }
+
+ ipaddr_reset_filter(1, ifindex);
+ iproute_reset_filter(ifindex);
+ ipmroute_reset_filter(ifindex);
+ ipneigh_reset_filter(ifindex);
+ ipnetconf_reset_filter(ifindex);
+
+ if (llink)
+ groups |= nl_mgrp(RTNLGRP_LINK);
+ if (laddr) {
+ if (!preferred_family || preferred_family == AF_INET)
+ groups |= nl_mgrp(RTNLGRP_IPV4_IFADDR);
+ if (!preferred_family || preferred_family == AF_INET6)
+ groups |= nl_mgrp(RTNLGRP_IPV6_IFADDR);
+ }
+ if (lroute) {
+ if (!preferred_family || preferred_family == AF_INET)
+ groups |= nl_mgrp(RTNLGRP_IPV4_ROUTE);
+ if (!preferred_family || preferred_family == AF_INET6)
+ groups |= nl_mgrp(RTNLGRP_IPV6_ROUTE);
+ if (!preferred_family || preferred_family == AF_MPLS)
+ groups |= nl_mgrp(RTNLGRP_MPLS_ROUTE);
+ }
+ if (lmroute) {
+ if (!preferred_family || preferred_family == AF_INET)
+ groups |= nl_mgrp(RTNLGRP_IPV4_MROUTE);
+ if (!preferred_family || preferred_family == AF_INET6)
+ groups |= nl_mgrp(RTNLGRP_IPV6_MROUTE);
+ }
+ if (lprefix) {
+ if (!preferred_family || preferred_family == AF_INET6)
+ groups |= nl_mgrp(RTNLGRP_IPV6_PREFIX);
+ }
+ if (lneigh) {
+ groups |= nl_mgrp(RTNLGRP_NEIGH);
+ }
+ if (lnetconf) {
+ if (!preferred_family || preferred_family == AF_INET)
+ groups |= nl_mgrp(RTNLGRP_IPV4_NETCONF);
+ if (!preferred_family || preferred_family == AF_INET6)
+ groups |= nl_mgrp(RTNLGRP_IPV6_NETCONF);
+ }
+ if (lrule) {
+ if (!preferred_family || preferred_family == AF_INET)
+ groups |= nl_mgrp(RTNLGRP_IPV4_RULE);
+ if (!preferred_family || preferred_family == AF_INET6)
+ groups |= nl_mgrp(RTNLGRP_IPV6_RULE);
+ }
+ if (lnsid) {
+ groups |= nl_mgrp(RTNLGRP_NSID);
+ }
+ if (file) {
+ FILE *fp;
+ int err;
+
+ fp = fopen(file, "r");
+ if (fp == NULL) {
+ perror("Cannot fopen");
+ exit(-1);
+ }
+ err = rtnl_from_file(fp, accept_msg, stdout);
+ fclose(fp);
+ return err;
+ }
+
+ if (rtnl_open(&rth, groups) < 0)
+ exit(1);
+ if (listen_all_nsid && rtnl_listen_all_nsid(&rth) < 0)
+ exit(1);
+
+ ll_init_map(&rth);
+ netns_map_init();
+
+ if (rtnl_listen(&rth, accept_msg, stdout) < 0)
+ exit(2);
+
+ return 0;
+}
diff --git a/iproute2/ip/ipmroute.c b/iproute2/ip/ipmroute.c
new file mode 100644
index 0000000..fffa9e2
--- /dev/null
+++ b/iproute2/ip/ipmroute.c
@@ -0,0 +1,287 @@
+/*
+ * ipmroute.c "ip mroute".
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <inttypes.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include <linux/netdevice.h>
+#include <linux/if.h>
+#include <linux/if_arp.h>
+#include <linux/sockios.h>
+
+#include <rt_names.h>
+#include "utils.h"
+#include "ip_common.h"
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: ip mroute show [ [ to ] PREFIX ] [ from PREFIX ] [ iif DEVICE ]\n");
+ fprintf(stderr, " [ table TABLE_ID ]\n");
+ fprintf(stderr, "TABLE_ID := [ local | main | default | all | NUMBER ]\n");
+#if 0
+ fprintf(stderr, "Usage: ip mroute [ add | del ] DESTINATION from SOURCE [ iif DEVICE ] [ oif DEVICE ]\n");
+#endif
+ exit(-1);
+}
+
+struct rtfilter
+{
+ int tb;
+ int af;
+ int iif;
+ inet_prefix mdst;
+ inet_prefix msrc;
+} filter;
+
+int print_mroute(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ struct rtmsg *r = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr * tb[RTA_MAX+1];
+ char abuf[256];
+ char obuf[256];
+ SPRINT_BUF(b1);
+ __u32 table;
+ int iif = 0;
+ int family;
+
+ if ((n->nlmsg_type != RTM_NEWROUTE &&
+ n->nlmsg_type != RTM_DELROUTE)) {
+ fprintf(stderr, "Not a multicast route: %08x %08x %08x\n",
+ n->nlmsg_len, n->nlmsg_type, n->nlmsg_flags);
+ return 0;
+ }
+ len -= NLMSG_LENGTH(sizeof(*r));
+ if (len < 0) {
+ fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+ return -1;
+ }
+ if (r->rtm_type != RTN_MULTICAST) {
+ fprintf(stderr, "Not a multicast route (type: %s)\n",
+ rtnl_rtntype_n2a(r->rtm_type, b1, sizeof(b1)));
+ return 0;
+ }
+
+ parse_rtattr(tb, RTA_MAX, RTM_RTA(r), len);
+ table = rtm_get_table(r, tb);
+
+ if (filter.tb > 0 && filter.tb != table)
+ return 0;
+
+ if (tb[RTA_IIF])
+ iif = *(int*)RTA_DATA(tb[RTA_IIF]);
+ if (filter.iif && filter.iif != iif)
+ return 0;
+
+ if (filter.af && filter.af != r->rtm_family)
+ return 0;
+
+ if (tb[RTA_DST] && filter.mdst.bitlen > 0) {
+ inet_prefix dst;
+
+ memset(&dst, 0, sizeof(dst));
+ dst.family = r->rtm_family;
+ memcpy(&dst.data, RTA_DATA(tb[RTA_DST]), RTA_PAYLOAD(tb[RTA_DST]));
+ if (inet_addr_match(&dst, &filter.mdst, filter.mdst.bitlen))
+ return 0;
+ }
+
+ if (tb[RTA_SRC] && filter.msrc.bitlen > 0) {
+ inet_prefix src;
+
+ memset(&src, 0, sizeof(src));
+ src.family = r->rtm_family;
+ memcpy(&src.data, RTA_DATA(tb[RTA_SRC]), RTA_PAYLOAD(tb[RTA_SRC]));
+ if (inet_addr_match(&src, &filter.msrc, filter.msrc.bitlen))
+ return 0;
+ }
+
+ family = r->rtm_family == RTNL_FAMILY_IPMR ? AF_INET : AF_INET6;
+
+ if (n->nlmsg_type == RTM_DELROUTE)
+ fprintf(fp, "Deleted ");
+
+ if (tb[RTA_SRC])
+ len = snprintf(obuf, sizeof(obuf),
+ "(%s, ", rt_addr_n2a(family,
+ RTA_PAYLOAD(tb[RTA_SRC]),
+ RTA_DATA(tb[RTA_SRC]),
+ abuf, sizeof(abuf)));
+ else
+ len = sprintf(obuf, "(unknown, ");
+ if (tb[RTA_DST])
+ snprintf(obuf + len, sizeof(obuf) - len,
+ "%s)", rt_addr_n2a(family,
+ RTA_PAYLOAD(tb[RTA_DST]),
+ RTA_DATA(tb[RTA_DST]),
+ abuf, sizeof(abuf)));
+ else
+ snprintf(obuf + len, sizeof(obuf) - len, "unknown) ");
+
+ fprintf(fp, "%-32s Iif: ", obuf);
+ if (iif)
+ fprintf(fp, "%-10s ", ll_index_to_name(iif));
+ else
+ fprintf(fp, "unresolved ");
+
+ if (tb[RTA_MULTIPATH]) {
+ struct rtnexthop *nh = RTA_DATA(tb[RTA_MULTIPATH]);
+ int first = 1;
+
+ len = RTA_PAYLOAD(tb[RTA_MULTIPATH]);
+
+ for (;;) {
+ if (len < sizeof(*nh))
+ break;
+ if (nh->rtnh_len > len)
+ break;
+
+ if (first) {
+ fprintf(fp, "Oifs: ");
+ first = 0;
+ }
+ fprintf(fp, "%s", ll_index_to_name(nh->rtnh_ifindex));
+ if (nh->rtnh_hops > 1)
+ fprintf(fp, "(ttl %d) ", nh->rtnh_hops);
+ else
+ fprintf(fp, " ");
+ len -= NLMSG_ALIGN(nh->rtnh_len);
+ nh = RTNH_NEXT(nh);
+ }
+ }
+ if (show_stats && tb[RTA_MFC_STATS]) {
+ struct rta_mfc_stats *mfcs = RTA_DATA(tb[RTA_MFC_STATS]);
+
+ fprintf(fp, "%s %"PRIu64" packets, %"PRIu64" bytes", _SL_,
+ (uint64_t)mfcs->mfcs_packets,
+ (uint64_t)mfcs->mfcs_bytes);
+ if (mfcs->mfcs_wrong_if)
+ fprintf(fp, ", %"PRIu64" arrived on wrong iif.",
+ (uint64_t)mfcs->mfcs_wrong_if);
+ }
+ fprintf(fp, "\n");
+ fflush(fp);
+ return 0;
+}
+
+void ipmroute_reset_filter(int ifindex)
+{
+ memset(&filter, 0, sizeof(filter));
+ filter.mdst.bitlen = -1;
+ filter.msrc.bitlen = -1;
+ filter.iif = ifindex;
+}
+
+static int mroute_list(int argc, char **argv)
+{
+ char *id = NULL;
+ int family;
+
+ ipmroute_reset_filter(0);
+ if (preferred_family == AF_UNSPEC)
+ family = AF_INET;
+ else
+ family = AF_INET6;
+ if (family == AF_INET) {
+ filter.af = RTNL_FAMILY_IPMR;
+ filter.tb = RT_TABLE_DEFAULT; /* for backward compatibility */
+ } else
+ filter.af = RTNL_FAMILY_IP6MR;
+
+ while (argc > 0) {
+ if (matches(*argv, "table") == 0) {
+ __u32 tid;
+ NEXT_ARG();
+ if (rtnl_rttable_a2n(&tid, *argv)) {
+ if (strcmp(*argv, "all") == 0) {
+ filter.tb = 0;
+ } else if (strcmp(*argv, "help") == 0) {
+ usage();
+ } else {
+ invarg("table id value is invalid\n", *argv);
+ }
+ } else
+ filter.tb = tid;
+ } else if (strcmp(*argv, "iif") == 0) {
+ NEXT_ARG();
+ id = *argv;
+ } else if (matches(*argv, "from") == 0) {
+ NEXT_ARG();
+ get_prefix(&filter.msrc, *argv, family);
+ } else {
+ if (strcmp(*argv, "to") == 0) {
+ NEXT_ARG();
+ }
+ if (matches(*argv, "help") == 0)
+ usage();
+ get_prefix(&filter.mdst, *argv, family);
+ }
+ argc--; argv++;
+ }
+
+ ll_init_map(&rth);
+
+ if (id) {
+ int idx;
+
+ if ((idx = ll_name_to_index(id)) == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", id);
+ return -1;
+ }
+ filter.iif = idx;
+ }
+
+ if (rtnl_wilddump_request(&rth, filter.af, RTM_GETROUTE) < 0) {
+ perror("Cannot send dump request");
+ return 1;
+ }
+
+ if (rtnl_dump_filter(&rth, print_mroute, stdout) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ exit(1);
+ }
+
+ exit(0);
+}
+
+int do_multiroute(int argc, char **argv)
+{
+ if (argc < 1)
+ return mroute_list(0, NULL);
+#if 0
+ if (matches(*argv, "add") == 0)
+ return mroute_modify(RTM_NEWADDR, argc-1, argv+1);
+ if (matches(*argv, "delete") == 0)
+ return mroute_modify(RTM_DELADDR, argc-1, argv+1);
+ if (matches(*argv, "get") == 0)
+ return mroute_get(argc-1, argv+1);
+#endif
+ if (matches(*argv, "list") == 0 || matches(*argv, "show") == 0
+ || matches(*argv, "lst") == 0)
+ return mroute_list(argc-1, argv+1);
+ if (matches(*argv, "help") == 0)
+ usage();
+ fprintf(stderr, "Command \"%s\" is unknown, try \"ip mroute help\".\n", *argv);
+ exit(-1);
+}
diff --git a/iproute2/ip/ipneigh.c b/iproute2/ip/ipneigh.c
new file mode 100644
index 0000000..92b7cd6
--- /dev/null
+++ b/iproute2/ip/ipneigh.c
@@ -0,0 +1,514 @@
+/*
+ * ipneigh.c "ip neigh".
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <string.h>
+#include <sys/time.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+
+#define NUD_VALID (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE|NUD_PROBE|NUD_STALE|NUD_DELAY)
+#define MAX_ROUNDS 10
+
+static struct
+{
+ int family;
+ int index;
+ int state;
+ int unused_only;
+ inet_prefix pfx;
+ int flushed;
+ char *flushb;
+ int flushp;
+ int flushe;
+ int master;
+} filter;
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: ip neigh { add | del | change | replace } { ADDR [ lladdr LLADDR ]\n"
+ " [ nud { permanent | noarp | stale | reachable } ]\n"
+ " | proxy ADDR } [ dev DEV ]\n");
+ fprintf(stderr, " ip neigh {show|flush} [ to PREFIX ] [ dev DEV ] [ nud STATE ]\n");
+ exit(-1);
+}
+
+static int nud_state_a2n(unsigned *state, const char *arg)
+{
+ if (matches(arg, "permanent") == 0)
+ *state = NUD_PERMANENT;
+ else if (matches(arg, "reachable") == 0)
+ *state = NUD_REACHABLE;
+ else if (strcmp(arg, "noarp") == 0)
+ *state = NUD_NOARP;
+ else if (strcmp(arg, "none") == 0)
+ *state = NUD_NONE;
+ else if (strcmp(arg, "stale") == 0)
+ *state = NUD_STALE;
+ else if (strcmp(arg, "incomplete") == 0)
+ *state = NUD_INCOMPLETE;
+ else if (strcmp(arg, "delay") == 0)
+ *state = NUD_DELAY;
+ else if (strcmp(arg, "probe") == 0)
+ *state = NUD_PROBE;
+ else if (matches(arg, "failed") == 0)
+ *state = NUD_FAILED;
+ else {
+ if (get_unsigned(state, arg, 0))
+ return -1;
+ if (*state>=0x100 || (*state&((*state)-1)))
+ return -1;
+ }
+ return 0;
+}
+
+static int flush_update(void)
+{
+ if (rtnl_send_check(&rth, filter.flushb, filter.flushp) < 0) {
+ perror("Failed to send flush request");
+ return -1;
+ }
+ filter.flushp = 0;
+ return 0;
+}
+
+
+static int ipneigh_modify(int cmd, int flags, int argc, char **argv)
+{
+ struct {
+ struct nlmsghdr n;
+ struct ndmsg ndm;
+ char buf[256];
+ } req;
+ char *dev = NULL;
+ int dst_ok = 0;
+ int dev_ok = 0;
+ int lladdr_ok = 0;
+ char * lla = NULL;
+ inet_prefix dst;
+
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ndmsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST|flags;
+ req.n.nlmsg_type = cmd;
+ req.ndm.ndm_family = preferred_family;
+ req.ndm.ndm_state = NUD_PERMANENT;
+
+ while (argc > 0) {
+ if (matches(*argv, "lladdr") == 0) {
+ NEXT_ARG();
+ if (lladdr_ok)
+ duparg("lladdr", *argv);
+ lla = *argv;
+ lladdr_ok = 1;
+ } else if (strcmp(*argv, "nud") == 0) {
+ unsigned state;
+ NEXT_ARG();
+ if (nud_state_a2n(&state, *argv))
+ invarg("nud state is bad", *argv);
+ req.ndm.ndm_state = state;
+ } else if (matches(*argv, "proxy") == 0) {
+ NEXT_ARG();
+ if (matches(*argv, "help") == 0)
+ usage();
+ if (dst_ok)
+ duparg("address", *argv);
+ get_addr(&dst, *argv, preferred_family);
+ dst_ok = 1;
+ dev_ok = 1;
+ req.ndm.ndm_flags |= NTF_PROXY;
+ } else if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ dev = *argv;
+ dev_ok = 1;
+ } else {
+ if (strcmp(*argv, "to") == 0) {
+ NEXT_ARG();
+ }
+ if (matches(*argv, "help") == 0) {
+ NEXT_ARG();
+ }
+ if (dst_ok)
+ duparg2("to", *argv);
+ get_addr(&dst, *argv, preferred_family);
+ dst_ok = 1;
+ }
+ argc--; argv++;
+ }
+ if (!dev_ok || !dst_ok || dst.family == AF_UNSPEC) {
+ fprintf(stderr, "Device and destination are required arguments.\n");
+ exit(-1);
+ }
+ req.ndm.ndm_family = dst.family;
+ if (addattr_l(&req.n, sizeof(req), NDA_DST, &dst.data, dst.bytelen) < 0)
+ return -1;
+
+ if (lla && strcmp(lla, "null")) {
+ char llabuf[20];
+ int l;
+
+ l = ll_addr_a2n(llabuf, sizeof(llabuf), lla);
+ if (l < 0)
+ return -1;
+
+ if (addattr_l(&req.n, sizeof(req), NDA_LLADDR, llabuf, l) < 0)
+ return -1;
+ }
+
+ ll_init_map(&rth);
+
+ if (dev && (req.ndm.ndm_ifindex = ll_name_to_index(dev)) == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", dev);
+ return -1;
+ }
+
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ exit(2);
+
+ return 0;
+}
+
+
+int print_neigh(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ struct ndmsg *r = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr * tb[NDA_MAX+1];
+ char abuf[256];
+ static int logit = 1;
+
+ if (n->nlmsg_type != RTM_NEWNEIGH && n->nlmsg_type != RTM_DELNEIGH &&
+ n->nlmsg_type != RTM_GETNEIGH) {
+ fprintf(stderr, "Not RTM_NEWNEIGH: %08x %08x %08x\n",
+ n->nlmsg_len, n->nlmsg_type, n->nlmsg_flags);
+
+ return 0;
+ }
+ len -= NLMSG_LENGTH(sizeof(*r));
+ if (len < 0) {
+ fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+ return -1;
+ }
+
+ if (filter.flushb && n->nlmsg_type != RTM_NEWNEIGH)
+ return 0;
+
+ if (filter.family && filter.family != r->ndm_family)
+ return 0;
+ if (filter.index && filter.index != r->ndm_ifindex)
+ return 0;
+ if (!(filter.state&r->ndm_state) &&
+ !(r->ndm_flags & NTF_PROXY) &&
+ (r->ndm_state || !(filter.state&0x100)) &&
+ (r->ndm_family != AF_DECnet))
+ return 0;
+
+ if (filter.master && !(n->nlmsg_flags & NLM_F_DUMP_FILTERED)) {
+ if (logit) {
+ logit = 0;
+ fprintf(fp,
+ "\nWARNING: Kernel does not support filtering by master device\n\n");
+ }
+ }
+
+ parse_rtattr(tb, NDA_MAX, NDA_RTA(r), n->nlmsg_len - NLMSG_LENGTH(sizeof(*r)));
+
+ if (tb[NDA_DST]) {
+ if (filter.pfx.family) {
+ inet_prefix dst;
+ memset(&dst, 0, sizeof(dst));
+ dst.family = r->ndm_family;
+ memcpy(&dst.data, RTA_DATA(tb[NDA_DST]), RTA_PAYLOAD(tb[NDA_DST]));
+ if (inet_addr_match(&dst, &filter.pfx, filter.pfx.bitlen))
+ return 0;
+ }
+ }
+ if (filter.unused_only && tb[NDA_CACHEINFO]) {
+ struct nda_cacheinfo *ci = RTA_DATA(tb[NDA_CACHEINFO]);
+ if (ci->ndm_refcnt)
+ return 0;
+ }
+
+ if (filter.flushb) {
+ struct nlmsghdr *fn;
+ if (NLMSG_ALIGN(filter.flushp) + n->nlmsg_len > filter.flushe) {
+ if (flush_update())
+ return -1;
+ }
+ fn = (struct nlmsghdr*)(filter.flushb + NLMSG_ALIGN(filter.flushp));
+ memcpy(fn, n, n->nlmsg_len);
+ fn->nlmsg_type = RTM_DELNEIGH;
+ fn->nlmsg_flags = NLM_F_REQUEST;
+ fn->nlmsg_seq = ++rth.seq;
+ filter.flushp = (((char*)fn) + n->nlmsg_len) - filter.flushb;
+ filter.flushed++;
+ if (show_stats < 2)
+ return 0;
+ }
+
+ if (n->nlmsg_type == RTM_DELNEIGH)
+ fprintf(fp, "Deleted ");
+ else if (n->nlmsg_type == RTM_GETNEIGH)
+ fprintf(fp, "miss ");
+ if (tb[NDA_DST]) {
+ fprintf(fp, "%s ",
+ format_host(r->ndm_family,
+ RTA_PAYLOAD(tb[NDA_DST]),
+ RTA_DATA(tb[NDA_DST]),
+ abuf, sizeof(abuf)));
+ }
+ if (!filter.index && r->ndm_ifindex)
+ fprintf(fp, "dev %s ", ll_index_to_name(r->ndm_ifindex));
+ if (tb[NDA_LLADDR]) {
+ SPRINT_BUF(b1);
+ fprintf(fp, "lladdr %s", ll_addr_n2a(RTA_DATA(tb[NDA_LLADDR]),
+ RTA_PAYLOAD(tb[NDA_LLADDR]),
+ ll_index_to_type(r->ndm_ifindex),
+ b1, sizeof(b1)));
+ }
+ if (r->ndm_flags & NTF_ROUTER) {
+ fprintf(fp, " router");
+ }
+ if (r->ndm_flags & NTF_PROXY) {
+ fprintf(fp, " proxy");
+ }
+ if (tb[NDA_CACHEINFO] && show_stats) {
+ struct nda_cacheinfo *ci = RTA_DATA(tb[NDA_CACHEINFO]);
+ int hz = get_user_hz();
+
+ if (ci->ndm_refcnt)
+ printf(" ref %d", ci->ndm_refcnt);
+ fprintf(fp, " used %d/%d/%d", ci->ndm_used/hz,
+ ci->ndm_confirmed/hz, ci->ndm_updated/hz);
+ }
+
+ if (tb[NDA_PROBES] && show_stats) {
+ __u32 p = rta_getattr_u32(tb[NDA_PROBES]);
+ fprintf(fp, " probes %u", p);
+ }
+
+ if (r->ndm_state) {
+ int nud = r->ndm_state;
+ fprintf(fp, " ");
+
+#define PRINT_FLAG(f) if (nud & NUD_##f) { \
+ nud &= ~NUD_##f; fprintf(fp, #f "%s", nud ? "," : ""); }
+ PRINT_FLAG(INCOMPLETE);
+ PRINT_FLAG(REACHABLE);
+ PRINT_FLAG(STALE);
+ PRINT_FLAG(DELAY);
+ PRINT_FLAG(PROBE);
+ PRINT_FLAG(FAILED);
+ PRINT_FLAG(NOARP);
+ PRINT_FLAG(PERMANENT);
+#undef PRINT_FLAG
+ }
+ fprintf(fp, "\n");
+
+ fflush(fp);
+ return 0;
+}
+
+void ipneigh_reset_filter(int ifindex)
+{
+ memset(&filter, 0, sizeof(filter));
+ filter.state = ~0;
+ filter.index = ifindex;
+}
+
+static int do_show_or_flush(int argc, char **argv, int flush)
+{
+ struct {
+ struct nlmsghdr n;
+ struct ndmsg ndm;
+ char buf[256];
+ } req;
+ char *filter_dev = NULL;
+ int state_given = 0;
+
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_type = RTM_GETNEIGH;
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ndmsg));
+
+ ipneigh_reset_filter(0);
+
+ if (!filter.family)
+ filter.family = preferred_family;
+
+ if (flush) {
+ if (argc <= 0) {
+ fprintf(stderr, "Flush requires arguments.\n");
+ return -1;
+ }
+ filter.state = ~(NUD_PERMANENT|NUD_NOARP);
+ } else
+ filter.state = 0xFF & ~NUD_NOARP;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ if (filter_dev)
+ duparg("dev", *argv);
+ filter_dev = *argv;
+ } else if (strcmp(*argv, "master") == 0) {
+ int ifindex;
+ NEXT_ARG();
+ ifindex = ll_name_to_index(*argv);
+ if (!ifindex)
+ invarg("Device does not exist\n", *argv);
+ addattr32(&req.n, sizeof(req), NDA_MASTER, ifindex);
+ filter.master = ifindex;
+ } else if (strcmp(*argv, "unused") == 0) {
+ filter.unused_only = 1;
+ } else if (strcmp(*argv, "nud") == 0) {
+ unsigned state;
+ NEXT_ARG();
+ if (!state_given) {
+ state_given = 1;
+ filter.state = 0;
+ }
+ if (nud_state_a2n(&state, *argv)) {
+ if (strcmp(*argv, "all") != 0)
+ invarg("nud state is bad", *argv);
+ state = ~0;
+ if (flush)
+ state &= ~NUD_NOARP;
+ }
+ if (state == 0)
+ state = 0x100;
+ filter.state |= state;
+ } else if (strcmp(*argv, "proxy") == 0)
+ req.ndm.ndm_flags = NTF_PROXY;
+ else {
+ if (strcmp(*argv, "to") == 0) {
+ NEXT_ARG();
+ }
+ if (matches(*argv, "help") == 0)
+ usage();
+ get_prefix(&filter.pfx, *argv, filter.family);
+ if (filter.family == AF_UNSPEC)
+ filter.family = filter.pfx.family;
+ }
+ argc--; argv++;
+ }
+
+ ll_init_map(&rth);
+
+ if (filter_dev) {
+ if ((filter.index = ll_name_to_index(filter_dev)) == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", filter_dev);
+ return -1;
+ }
+ addattr32(&req.n, sizeof(req), NDA_IFINDEX, filter.index);
+ }
+
+ if (flush) {
+ int round = 0;
+ char flushb[4096-512];
+
+ filter.flushb = flushb;
+ filter.flushp = 0;
+ filter.flushe = sizeof(flushb);
+ filter.state &= ~NUD_FAILED;
+
+ while (round < MAX_ROUNDS) {
+ if (rtnl_wilddump_request(&rth, filter.family, RTM_GETNEIGH) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+ filter.flushed = 0;
+ if (rtnl_dump_filter(&rth, print_neigh, stdout) < 0) {
+ fprintf(stderr, "Flush terminated\n");
+ exit(1);
+ }
+ if (filter.flushed == 0) {
+ if (show_stats) {
+ if (round == 0)
+ printf("Nothing to flush.\n");
+ else
+ printf("*** Flush is complete after %d round%s ***\n", round, round>1?"s":"");
+ }
+ fflush(stdout);
+ return 0;
+ }
+ round++;
+ if (flush_update() < 0)
+ exit(1);
+ if (show_stats) {
+ printf("\n*** Round %d, deleting %d entries ***\n", round, filter.flushed);
+ fflush(stdout);
+ }
+ }
+ printf("*** Flush not complete bailing out after %d rounds\n",
+ MAX_ROUNDS);
+ return 1;
+ }
+
+ req.ndm.ndm_family = filter.family;
+
+ if (rtnl_dump_request_n(&rth, &req.n) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+
+ if (rtnl_dump_filter(&rth, print_neigh, stdout) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ exit(1);
+ }
+
+ return 0;
+}
+
+int do_ipneigh(int argc, char **argv)
+{
+ if (argc > 0) {
+ if (matches(*argv, "add") == 0)
+ return ipneigh_modify(RTM_NEWNEIGH, NLM_F_CREATE|NLM_F_EXCL, argc-1, argv+1);
+ if (matches(*argv, "change") == 0 ||
+ strcmp(*argv, "chg") == 0)
+ return ipneigh_modify(RTM_NEWNEIGH, NLM_F_REPLACE, argc-1, argv+1);
+ if (matches(*argv, "replace") == 0)
+ return ipneigh_modify(RTM_NEWNEIGH, NLM_F_CREATE|NLM_F_REPLACE, argc-1, argv+1);
+ if (matches(*argv, "delete") == 0)
+ return ipneigh_modify(RTM_DELNEIGH, 0, argc-1, argv+1);
+ if (matches(*argv, "get") == 0) {
+ fprintf(stderr, "Sorry, \"neigh get\" is not implemented :-(\n");
+ return -1;
+ }
+ if (matches(*argv, "show") == 0 ||
+ matches(*argv, "lst") == 0 ||
+ matches(*argv, "list") == 0)
+ return do_show_or_flush(argc-1, argv+1, 0);
+ if (matches(*argv, "flush") == 0)
+ return do_show_or_flush(argc-1, argv+1, 1);
+ if (matches(*argv, "help") == 0)
+ usage();
+ } else
+ return do_show_or_flush(0, NULL, 0);
+
+ fprintf(stderr, "Command \"%s\" is unknown, try \"ip neigh help\".\n", *argv);
+ exit(-1);
+}
diff --git a/iproute2/ip/ipnetconf.c b/iproute2/ip/ipnetconf.c
new file mode 100644
index 0000000..eca6eee
--- /dev/null
+++ b/iproute2/ip/ipnetconf.c
@@ -0,0 +1,214 @@
+/*
+ * ipnetconf.c "ip netconf".
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Nicolas Dichtel, <nicolas.dichtel@6wind.com>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <string.h>
+#include <sys/time.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+
+static struct
+{
+ int family;
+ int ifindex;
+} filter;
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: ip netconf show [ dev STRING ]\n");
+ exit(-1);
+}
+
+#define NETCONF_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct netconfmsg))))
+
+int print_netconf(const struct sockaddr_nl *who, struct rtnl_ctrl_data *ctrl,
+ struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ struct netconfmsg *ncm = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr *tb[NETCONFA_MAX+1];
+
+ if (n->nlmsg_type == NLMSG_ERROR)
+ return -1;
+ if (n->nlmsg_type != RTM_NEWNETCONF) {
+ fprintf(stderr, "Not RTM_NEWNETCONF: %08x %08x %08x\n",
+ n->nlmsg_len, n->nlmsg_type, n->nlmsg_flags);
+
+ return -1;
+ }
+ len -= NLMSG_SPACE(sizeof(*ncm));
+ if (len < 0) {
+ fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+ return -1;
+ }
+
+ if (filter.family && filter.family != ncm->ncm_family)
+ return 0;
+
+ parse_rtattr(tb, NETCONFA_MAX, NETCONF_RTA(ncm),
+ NLMSG_PAYLOAD(n, sizeof(*ncm)));
+
+ switch (ncm->ncm_family) {
+ case AF_INET:
+ fprintf(fp, "ipv4 ");
+ break;
+ case AF_INET6:
+ fprintf(fp, "ipv6 ");
+ break;
+ default:
+ fprintf(fp, "unknown ");
+ break;
+ }
+
+ if (tb[NETCONFA_IFINDEX]) {
+ int *ifindex = (int *)RTA_DATA(tb[NETCONFA_IFINDEX]);
+
+ switch (*ifindex) {
+ case NETCONFA_IFINDEX_ALL:
+ fprintf(fp, "all ");
+ break;
+ case NETCONFA_IFINDEX_DEFAULT:
+ fprintf(fp, "default ");
+ break;
+ default:
+ fprintf(fp, "dev %s ", ll_index_to_name(*ifindex));
+ break;
+ }
+ }
+
+ if (tb[NETCONFA_FORWARDING])
+ fprintf(fp, "forwarding %s ",
+ *(int *)RTA_DATA(tb[NETCONFA_FORWARDING])?"on":"off");
+ if (tb[NETCONFA_RP_FILTER]) {
+ int rp_filter = *(int *)RTA_DATA(tb[NETCONFA_RP_FILTER]);
+
+ if (rp_filter == 0)
+ fprintf(fp, "rp_filter off ");
+ else if (rp_filter == 1)
+ fprintf(fp, "rp_filter strict ");
+ else if (rp_filter == 2)
+ fprintf(fp, "rp_filter loose ");
+ else
+ fprintf(fp, "rp_filter unknown mode ");
+ }
+ if (tb[NETCONFA_MC_FORWARDING])
+ fprintf(fp, "mc_forwarding %d ",
+ *(int *)RTA_DATA(tb[NETCONFA_MC_FORWARDING]));
+
+ if (tb[NETCONFA_PROXY_NEIGH])
+ fprintf(fp, "proxy_neigh %s ",
+ *(int *)RTA_DATA(tb[NETCONFA_PROXY_NEIGH])?"on":"off");
+
+ fprintf(fp, "\n");
+ fflush(fp);
+ return 0;
+}
+
+static int print_netconf2(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg)
+{
+ return print_netconf(who, NULL, n, arg);
+}
+
+void ipnetconf_reset_filter(int ifindex)
+{
+ memset(&filter, 0, sizeof(filter));
+ filter.ifindex = ifindex;
+}
+
+static int do_show(int argc, char **argv)
+{
+ struct {
+ struct nlmsghdr n;
+ struct netconfmsg ncm;
+ char buf[1024];
+ } req;
+
+ ipnetconf_reset_filter(0);
+ filter.family = preferred_family;
+ if (filter.family == AF_UNSPEC)
+ filter.family = AF_INET;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ filter.ifindex = ll_name_to_index(*argv);
+ if (filter.ifindex <= 0) {
+ fprintf(stderr, "Device \"%s\" does not exist.\n",
+ *argv);
+ return -1;
+ }
+ }
+ argv++; argc--;
+ }
+
+ ll_init_map(&rth);
+ if (filter.ifindex) {
+ memset(&req, 0, sizeof(req));
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct netconfmsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST|NLM_F_ACK;
+ req.n.nlmsg_type = RTM_GETNETCONF;
+ req.ncm.ncm_family = filter.family;
+ if (filter.ifindex)
+ addattr_l(&req.n, sizeof(req), NETCONFA_IFINDEX,
+ &filter.ifindex, sizeof(filter.ifindex));
+
+ if (rtnl_send(&rth, &req.n, req.n.nlmsg_len) < 0) {
+ perror("Can not send request");
+ exit(1);
+ }
+ rtnl_listen(&rth, print_netconf, stdout);
+ } else {
+dump:
+ if (rtnl_wilddump_request(&rth, filter.family, RTM_GETNETCONF) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+ if (rtnl_dump_filter(&rth, print_netconf2, stdout) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ exit(1);
+ }
+ if (preferred_family == AF_UNSPEC) {
+ preferred_family = AF_INET6;
+ filter.family = AF_INET6;
+ goto dump;
+ }
+ }
+ return 0;
+}
+
+int do_ipnetconf(int argc, char **argv)
+{
+ if (argc > 0) {
+ if (matches(*argv, "show") == 0 ||
+ matches(*argv, "lst") == 0 ||
+ matches(*argv, "list") == 0)
+ return do_show(argc-1, argv+1);
+ if (matches(*argv, "help") == 0)
+ usage();
+ } else
+ return do_show(0, NULL);
+
+ fprintf(stderr, "Command \"%s\" is unknown, try \"ip netconf help\".\n", *argv);
+ exit(-1);
+}
diff --git a/iproute2/ip/ipnetns.c b/iproute2/ip/ipnetns.c
new file mode 100644
index 0000000..088096f
--- /dev/null
+++ b/iproute2/ip/ipnetns.c
@@ -0,0 +1,814 @@
+#define _ATFILE_SOURCE
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/wait.h>
+#include <sys/inotify.h>
+#include <sys/mount.h>
+#include <sys/syscall.h>
+#include <stdio.h>
+#include <string.h>
+#include <sched.h>
+#include <fcntl.h>
+#include <dirent.h>
+#include <errno.h>
+#include <unistd.h>
+#include <ctype.h>
+#include <linux/limits.h>
+
+#include <linux/net_namespace.h>
+
+#include "utils.h"
+#include "hlist.h"
+#include "ip_common.h"
+#include "namespace.h"
+
+static int usage(void)
+{
+ fprintf(stderr, "Usage: ip netns list\n");
+ fprintf(stderr, " ip netns add NAME\n");
+ fprintf(stderr, " ip netns set NAME NETNSID\n");
+ fprintf(stderr, " ip [-all] netns delete [NAME]\n");
+ fprintf(stderr, " ip netns identify [PID]\n");
+ fprintf(stderr, " ip netns pids NAME\n");
+ fprintf(stderr, " ip [-all] netns exec [NAME] cmd ...\n");
+ fprintf(stderr, " ip netns monitor\n");
+ fprintf(stderr, " ip netns list-id\n");
+ exit(-1);
+}
+
+/* This socket is used to get nsid */
+static struct rtnl_handle rtnsh = { .fd = -1 };
+
+static int have_rtnl_getnsid = -1;
+
+static int ipnetns_accept_msg(const struct sockaddr_nl *who,
+ struct rtnl_ctrl_data *ctrl,
+ struct nlmsghdr *n, void *arg)
+{
+ struct nlmsgerr *err = (struct nlmsgerr *)NLMSG_DATA(n);
+
+ if (n->nlmsg_type == NLMSG_ERROR &&
+ (err->error == -EOPNOTSUPP || err->error == -EINVAL))
+ have_rtnl_getnsid = 0;
+ else
+ have_rtnl_getnsid = 1;
+ return -1;
+}
+
+static int ipnetns_have_nsid(void)
+{
+ struct {
+ struct nlmsghdr n;
+ struct rtgenmsg g;
+ char buf[1024];
+ } req;
+ int fd;
+
+ if (have_rtnl_getnsid < 0) {
+ memset(&req, 0, sizeof(req));
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct rtgenmsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = RTM_GETNSID;
+ req.g.rtgen_family = AF_UNSPEC;
+
+ fd = open("/proc/self/ns/net", O_RDONLY);
+ if (fd < 0) {
+ perror("open(\"/proc/self/ns/net\")");
+ exit(1);
+ }
+
+ addattr32(&req.n, 1024, NETNSA_FD, fd);
+
+ if (rtnl_send(&rth, &req.n, req.n.nlmsg_len) < 0) {
+ perror("request send failed");
+ exit(1);
+ }
+ rtnl_listen(&rth, ipnetns_accept_msg, NULL);
+ close(fd);
+ }
+
+ return have_rtnl_getnsid;
+}
+
+static int get_netnsid_from_name(const char *name)
+{
+ struct {
+ struct nlmsghdr n;
+ struct rtgenmsg g;
+ char buf[1024];
+ } req, answer;
+ struct rtattr *tb[NETNSA_MAX + 1];
+ struct rtgenmsg *rthdr;
+ int len, fd;
+
+ memset(&req, 0, sizeof(req));
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct rtgenmsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = RTM_GETNSID;
+ req.g.rtgen_family = AF_UNSPEC;
+
+ fd = netns_get_fd(name);
+ if (fd < 0)
+ return fd;
+
+ addattr32(&req.n, 1024, NETNSA_FD, fd);
+ if (rtnl_talk(&rtnsh, &req.n, &answer.n, sizeof(answer)) < 0) {
+ close(fd);
+ return -2;
+ }
+ close(fd);
+
+ /* Validate message and parse attributes */
+ if (answer.n.nlmsg_type == NLMSG_ERROR)
+ return -1;
+
+ rthdr = NLMSG_DATA(&answer.n);
+ len = answer.n.nlmsg_len - NLMSG_SPACE(sizeof(*rthdr));
+ if (len < 0)
+ return -1;
+
+ parse_rtattr(tb, NETNSA_MAX, NETNS_RTA(rthdr), len);
+
+ if (tb[NETNSA_NSID])
+ return rta_getattr_u32(tb[NETNSA_NSID]);
+
+ return -1;
+}
+
+struct nsid_cache {
+ struct hlist_node nsid_hash;
+ struct hlist_node name_hash;
+ int nsid;
+ char name[0];
+};
+
+#define NSIDMAP_SIZE 128
+#define NSID_HASH_NSID(nsid) (nsid & (NSIDMAP_SIZE - 1))
+#define NSID_HASH_NAME(name) (namehash(name) & (NSIDMAP_SIZE - 1))
+
+static struct hlist_head nsid_head[NSIDMAP_SIZE];
+static struct hlist_head name_head[NSIDMAP_SIZE];
+
+static struct nsid_cache *netns_map_get_by_nsid(int nsid)
+{
+ uint32_t h = NSID_HASH_NSID(nsid);
+ struct hlist_node *n;
+
+ hlist_for_each(n, &nsid_head[h]) {
+ struct nsid_cache *c = container_of(n, struct nsid_cache,
+ nsid_hash);
+ if (c->nsid == nsid)
+ return c;
+ }
+
+ return NULL;
+}
+
+static int netns_map_add(int nsid, const char *name)
+{
+ struct nsid_cache *c;
+ uint32_t h;
+
+ if (netns_map_get_by_nsid(nsid) != NULL)
+ return -EEXIST;
+
+ c = malloc(sizeof(*c) + strlen(name));
+ if (c == NULL) {
+ perror("malloc");
+ return -ENOMEM;
+ }
+ c->nsid = nsid;
+ strcpy(c->name, name);
+
+ h = NSID_HASH_NSID(nsid);
+ hlist_add_head(&c->nsid_hash, &nsid_head[h]);
+
+ h = NSID_HASH_NAME(name);
+ hlist_add_head(&c->name_hash, &name_head[h]);
+
+ return 0;
+}
+
+static void netns_map_del(struct nsid_cache *c)
+{
+ hlist_del(&c->name_hash);
+ hlist_del(&c->nsid_hash);
+ free(c);
+}
+
+void netns_map_init(void)
+{
+ static int initialized;
+ struct dirent *entry;
+ DIR *dir;
+ int nsid;
+
+ if (initialized || !ipnetns_have_nsid())
+ return;
+
+ if (rtnl_open(&rtnsh, 0) < 0) {
+ fprintf(stderr, "Cannot open rtnetlink\n");
+ exit(1);
+ }
+
+ dir = opendir(NETNS_RUN_DIR);
+ if (!dir)
+ return;
+
+ while ((entry = readdir(dir)) != NULL) {
+ if (strcmp(entry->d_name, ".") == 0)
+ continue;
+ if (strcmp(entry->d_name, "..") == 0)
+ continue;
+ nsid = get_netnsid_from_name(entry->d_name);
+
+ if (nsid >= 0)
+ netns_map_add(nsid, entry->d_name);
+ }
+ closedir(dir);
+ initialized = 1;
+}
+
+static int netns_get_name(int nsid, char *name)
+{
+ struct dirent *entry;
+ DIR *dir;
+ int id;
+
+ dir = opendir(NETNS_RUN_DIR);
+ if (!dir)
+ return -ENOENT;
+
+ while ((entry = readdir(dir)) != NULL) {
+ if (strcmp(entry->d_name, ".") == 0)
+ continue;
+ if (strcmp(entry->d_name, "..") == 0)
+ continue;
+ id = get_netnsid_from_name(entry->d_name);
+
+ if (nsid == id) {
+ strcpy(name, entry->d_name);
+ closedir(dir);
+ return 0;
+ }
+ }
+ closedir(dir);
+ return -ENOENT;
+}
+
+int print_nsid(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
+{
+ struct rtgenmsg *rthdr = NLMSG_DATA(n);
+ struct rtattr *tb[NETNSA_MAX+1];
+ int len = n->nlmsg_len;
+ FILE *fp = (FILE *)arg;
+ struct nsid_cache *c;
+ char name[NAME_MAX];
+ int nsid;
+
+ if (n->nlmsg_type != RTM_NEWNSID && n->nlmsg_type != RTM_DELNSID)
+ return 0;
+
+ len -= NLMSG_SPACE(sizeof(*rthdr));
+ if (len < 0) {
+ fprintf(stderr, "BUG: wrong nlmsg len %d in %s\n", len,
+ __func__);
+ return -1;
+ }
+
+ parse_rtattr(tb, NETNSA_MAX, NETNS_RTA(rthdr), len);
+ if (tb[NETNSA_NSID] == NULL) {
+ fprintf(stderr, "BUG: NETNSA_NSID is missing %s\n", __func__);
+ return -1;
+ }
+
+ if (n->nlmsg_type == RTM_DELNSID)
+ fprintf(fp, "Deleted ");
+
+ nsid = rta_getattr_u32(tb[NETNSA_NSID]);
+ fprintf(fp, "nsid %u ", nsid);
+
+ c = netns_map_get_by_nsid(nsid);
+ if (c != NULL) {
+ fprintf(fp, "(iproute2 netns name: %s)", c->name);
+ netns_map_del(c);
+ }
+
+ /* During 'ip monitor nsid', no chance to have new nsid in cache. */
+ if (c == NULL && n->nlmsg_type == RTM_NEWNSID)
+ if (netns_get_name(nsid, name) == 0) {
+ fprintf(fp, "(iproute2 netns name: %s)", name);
+ netns_map_add(nsid, name);
+ }
+
+ fprintf(fp, "\n");
+ fflush(fp);
+ return 0;
+}
+
+static int netns_list_id(int argc, char **argv)
+{
+ if (!ipnetns_have_nsid()) {
+ fprintf(stderr,
+ "RTM_GETNSID is not supported by the kernel.\n");
+ return -ENOTSUP;
+ }
+
+ if (rtnl_wilddump_request(&rth, AF_UNSPEC, RTM_GETNSID) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+ if (rtnl_dump_filter(&rth, print_nsid, stdout) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ exit(1);
+ }
+ return 0;
+}
+
+static int netns_list(int argc, char **argv)
+{
+ struct dirent *entry;
+ DIR *dir;
+ int id;
+
+ dir = opendir(NETNS_RUN_DIR);
+ if (!dir)
+ return 0;
+
+ while ((entry = readdir(dir)) != NULL) {
+ if (strcmp(entry->d_name, ".") == 0)
+ continue;
+ if (strcmp(entry->d_name, "..") == 0)
+ continue;
+ printf("%s", entry->d_name);
+ if (ipnetns_have_nsid()) {
+ id = get_netnsid_from_name(entry->d_name);
+ if (id >= 0)
+ printf(" (id: %d)", id);
+ }
+ printf("\n");
+ }
+ closedir(dir);
+ return 0;
+}
+
+static int cmd_exec(const char *cmd, char **argv, bool do_fork)
+{
+ fflush(stdout);
+ if (do_fork) {
+ int status;
+ pid_t pid;
+
+ pid = fork();
+ if (pid < 0) {
+ perror("fork");
+ exit(1);
+ }
+
+ if (pid != 0) {
+ /* Parent */
+ if (waitpid(pid, &status, 0) < 0) {
+ perror("waitpid");
+ exit(1);
+ }
+
+ if (WIFEXITED(status)) {
+ return WEXITSTATUS(status);
+ }
+
+ exit(1);
+ }
+ }
+
+ if (execvp(cmd, argv) < 0)
+ fprintf(stderr, "exec of \"%s\" failed: %s\n",
+ cmd, strerror(errno));
+ _exit(1);
+}
+
+static int on_netns_exec(char *nsname, void *arg)
+{
+ char **argv = arg;
+ cmd_exec(argv[1], argv + 1, true);
+ return 0;
+}
+
+static int netns_exec(int argc, char **argv)
+{
+ /* Setup the proper environment for apps that are not netns
+ * aware, and execute a program in that environment.
+ */
+ const char *cmd;
+
+ if (argc < 1 && !do_all) {
+ fprintf(stderr, "No netns name specified\n");
+ return -1;
+ }
+ if ((argc < 2 && !do_all) || (argc < 1 && do_all)) {
+ fprintf(stderr, "No command specified\n");
+ return -1;
+ }
+
+ if (do_all)
+ return do_each_netns(on_netns_exec, --argv, 1);
+
+ if (netns_switch(argv[0]))
+ return -1;
+
+ /* ip must return the status of the child,
+ * but do_cmd() will add a minus to this,
+ * so let's add another one here to cancel it.
+ */
+ cmd = argv[1];
+ return -cmd_exec(cmd, argv + 1, !!batch_mode);
+}
+
+static int is_pid(const char *str)
+{
+ int ch;
+ for (; (ch = *str); str++) {
+ if (!isdigit(ch))
+ return 0;
+ }
+ return 1;
+}
+
+static int netns_pids(int argc, char **argv)
+{
+ const char *name;
+ char net_path[PATH_MAX];
+ int netns;
+ struct stat netst;
+ DIR *dir;
+ struct dirent *entry;
+
+ if (argc < 1) {
+ fprintf(stderr, "No netns name specified\n");
+ return -1;
+ }
+ if (argc > 1) {
+ fprintf(stderr, "extra arguments specified\n");
+ return -1;
+ }
+
+ name = argv[0];
+ snprintf(net_path, sizeof(net_path), "%s/%s", NETNS_RUN_DIR, name);
+ netns = open(net_path, O_RDONLY);
+ if (netns < 0) {
+ fprintf(stderr, "Cannot open network namespace: %s\n",
+ strerror(errno));
+ return -1;
+ }
+ if (fstat(netns, &netst) < 0) {
+ fprintf(stderr, "Stat of netns failed: %s\n",
+ strerror(errno));
+ return -1;
+ }
+ dir = opendir("/proc/");
+ if (!dir) {
+ fprintf(stderr, "Open of /proc failed: %s\n",
+ strerror(errno));
+ return -1;
+ }
+ while((entry = readdir(dir))) {
+ char pid_net_path[PATH_MAX];
+ struct stat st;
+ if (!is_pid(entry->d_name))
+ continue;
+ snprintf(pid_net_path, sizeof(pid_net_path), "/proc/%s/ns/net",
+ entry->d_name);
+ if (stat(pid_net_path, &st) != 0)
+ continue;
+ if ((st.st_dev == netst.st_dev) &&
+ (st.st_ino == netst.st_ino)) {
+ printf("%s\n", entry->d_name);
+ }
+ }
+ closedir(dir);
+ return 0;
+
+}
+
+static int netns_identify(int argc, char **argv)
+{
+ const char *pidstr;
+ char net_path[PATH_MAX];
+ int netns;
+ struct stat netst;
+ DIR *dir;
+ struct dirent *entry;
+
+ if (argc < 1) {
+ pidstr = "self";
+ } else if (argc > 1) {
+ fprintf(stderr, "extra arguments specified\n");
+ return -1;
+ } else {
+ pidstr = argv[0];
+ if (!is_pid(pidstr)) {
+ fprintf(stderr, "Specified string '%s' is not a pid\n",
+ pidstr);
+ return -1;
+ }
+ }
+
+ snprintf(net_path, sizeof(net_path), "/proc/%s/ns/net", pidstr);
+ netns = open(net_path, O_RDONLY);
+ if (netns < 0) {
+ fprintf(stderr, "Cannot open network namespace: %s\n",
+ strerror(errno));
+ return -1;
+ }
+ if (fstat(netns, &netst) < 0) {
+ fprintf(stderr, "Stat of netns failed: %s\n",
+ strerror(errno));
+ return -1;
+ }
+ dir = opendir(NETNS_RUN_DIR);
+ if (!dir) {
+ /* Succeed treat a missing directory as an empty directory */
+ if (errno == ENOENT)
+ return 0;
+
+ fprintf(stderr, "Failed to open directory %s:%s\n",
+ NETNS_RUN_DIR, strerror(errno));
+ return -1;
+ }
+
+ while((entry = readdir(dir))) {
+ char name_path[PATH_MAX];
+ struct stat st;
+
+ if (strcmp(entry->d_name, ".") == 0)
+ continue;
+ if (strcmp(entry->d_name, "..") == 0)
+ continue;
+
+ snprintf(name_path, sizeof(name_path), "%s/%s", NETNS_RUN_DIR,
+ entry->d_name);
+
+ if (stat(name_path, &st) != 0)
+ continue;
+
+ if ((st.st_dev == netst.st_dev) &&
+ (st.st_ino == netst.st_ino)) {
+ printf("%s\n", entry->d_name);
+ }
+ }
+ closedir(dir);
+ return 0;
+
+}
+
+static int on_netns_del(char *nsname, void *arg)
+{
+ char netns_path[PATH_MAX];
+
+ snprintf(netns_path, sizeof(netns_path), "%s/%s", NETNS_RUN_DIR, nsname);
+ umount2(netns_path, MNT_DETACH);
+ if (unlink(netns_path) < 0) {
+ fprintf(stderr, "Cannot remove namespace file \"%s\": %s\n",
+ netns_path, strerror(errno));
+ return -1;
+ }
+ return 0;
+}
+
+static int netns_delete(int argc, char **argv)
+{
+ if (argc < 1 && !do_all) {
+ fprintf(stderr, "No netns name specified\n");
+ return -1;
+ }
+
+ if (do_all)
+ return netns_foreach(on_netns_del, NULL);
+
+ return on_netns_del(argv[0], NULL);
+}
+
+static int create_netns_dir(void)
+{
+ /* Create the base netns directory if it doesn't exist */
+ if (mkdir(NETNS_RUN_DIR, S_IRWXU|S_IRGRP|S_IXGRP|S_IROTH|S_IXOTH)) {
+ if (errno != EEXIST) {
+ fprintf(stderr, "mkdir %s failed: %s\n",
+ NETNS_RUN_DIR, strerror(errno));
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+static int netns_add(int argc, char **argv)
+{
+ /* This function creates a new network namespace and
+ * a new mount namespace and bind them into a well known
+ * location in the filesystem based on the name provided.
+ *
+ * The mount namespace is created so that any necessary
+ * userspace tweaks like remounting /sys, or bind mounting
+ * a new /etc/resolv.conf can be shared between uers.
+ */
+ char netns_path[PATH_MAX];
+ const char *name;
+ int fd;
+ int made_netns_run_dir_mount = 0;
+
+ if (argc < 1) {
+ fprintf(stderr, "No netns name specified\n");
+ return -1;
+ }
+ name = argv[0];
+
+ snprintf(netns_path, sizeof(netns_path), "%s/%s", NETNS_RUN_DIR, name);
+
+ if (create_netns_dir())
+ return -1;
+
+ /* Make it possible for network namespace mounts to propagate between
+ * mount namespaces. This makes it likely that a unmounting a network
+ * namespace file in one namespace will unmount the network namespace
+ * file in all namespaces allowing the network namespace to be freed
+ * sooner.
+ */
+ while (mount("", NETNS_RUN_DIR, "none", MS_SHARED | MS_REC, NULL)) {
+ /* Fail unless we need to make the mount point */
+ if (errno != EINVAL || made_netns_run_dir_mount) {
+ fprintf(stderr, "mount --make-shared %s failed: %s\n",
+ NETNS_RUN_DIR, strerror(errno));
+ return -1;
+ }
+
+ /* Upgrade NETNS_RUN_DIR to a mount point */
+ if (mount(NETNS_RUN_DIR, NETNS_RUN_DIR, "none", MS_BIND, NULL)) {
+ fprintf(stderr, "mount --bind %s %s failed: %s\n",
+ NETNS_RUN_DIR, NETNS_RUN_DIR, strerror(errno));
+ return -1;
+ }
+ made_netns_run_dir_mount = 1;
+ }
+
+ /* Create the filesystem state */
+ fd = open(netns_path, O_RDONLY|O_CREAT|O_EXCL, 0);
+ if (fd < 0) {
+ fprintf(stderr, "Cannot create namespace file \"%s\": %s\n",
+ netns_path, strerror(errno));
+ return -1;
+ }
+ close(fd);
+ if (unshare(CLONE_NEWNET) < 0) {
+ fprintf(stderr, "Failed to create a new network namespace \"%s\": %s\n",
+ name, strerror(errno));
+ goto out_delete;
+ }
+
+ /* Bind the netns last so I can watch for it */
+ if (mount("/proc/self/ns/net", netns_path, "none", MS_BIND, NULL) < 0) {
+ fprintf(stderr, "Bind /proc/self/ns/net -> %s failed: %s\n",
+ netns_path, strerror(errno));
+ goto out_delete;
+ }
+ return 0;
+out_delete:
+ netns_delete(argc, argv);
+ return -1;
+}
+
+static int set_netnsid_from_name(const char *name, int nsid)
+{
+ struct {
+ struct nlmsghdr n;
+ struct rtgenmsg g;
+ char buf[1024];
+ } req;
+ int fd, err = 0;
+
+ memset(&req, 0, sizeof(req));
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct rtgenmsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = RTM_NEWNSID;
+ req.g.rtgen_family = AF_UNSPEC;
+
+ fd = netns_get_fd(name);
+ if (fd < 0)
+ return fd;
+
+ addattr32(&req.n, 1024, NETNSA_FD, fd);
+ addattr32(&req.n, 1024, NETNSA_NSID, nsid);
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ err = -2;
+
+ close(fd);
+ return err;
+}
+
+static int netns_set(int argc, char **argv)
+{
+ char netns_path[PATH_MAX];
+ const char *name;
+ int netns, nsid;
+
+ if (argc < 1) {
+ fprintf(stderr, "No netns name specified\n");
+ return -1;
+ }
+ if (argc < 2) {
+ fprintf(stderr, "No nsid specified\n");
+ return -1;
+ }
+ name = argv[0];
+ nsid = atoi(argv[1]);
+
+ snprintf(netns_path, sizeof(netns_path), "%s/%s", NETNS_RUN_DIR, name);
+ netns = open(netns_path, O_RDONLY | O_CLOEXEC);
+ if (netns < 0) {
+ fprintf(stderr, "Cannot open network namespace \"%s\": %s\n",
+ name, strerror(errno));
+ return -1;
+ }
+
+ return set_netnsid_from_name(name, nsid);
+}
+
+static int netns_monitor(int argc, char **argv)
+{
+ char buf[4096];
+ struct inotify_event *event;
+ int fd;
+ fd = inotify_init();
+ if (fd < 0) {
+ fprintf(stderr, "inotify_init failed: %s\n",
+ strerror(errno));
+ return -1;
+ }
+
+ if (create_netns_dir())
+ return -1;
+
+ if (inotify_add_watch(fd, NETNS_RUN_DIR, IN_CREATE | IN_DELETE) < 0) {
+ fprintf(stderr, "inotify_add_watch failed: %s\n",
+ strerror(errno));
+ return -1;
+ }
+ for(;;) {
+ ssize_t len = read(fd, buf, sizeof(buf));
+ if (len < 0) {
+ fprintf(stderr, "read failed: %s\n",
+ strerror(errno));
+ return -1;
+ }
+ for (event = (struct inotify_event *)buf;
+ (char *)event < &buf[len];
+ event = (struct inotify_event *)((char *)event + sizeof(*event) + event->len)) {
+ if (event->mask & IN_CREATE)
+ printf("add %s\n", event->name);
+ if (event->mask & IN_DELETE)
+ printf("delete %s\n", event->name);
+ }
+ }
+ return 0;
+}
+
+int do_netns(int argc, char **argv)
+{
+ netns_map_init();
+
+ if (argc < 1)
+ return netns_list(0, NULL);
+
+ if ((matches(*argv, "list") == 0) || (matches(*argv, "show") == 0) ||
+ (matches(*argv, "lst") == 0))
+ return netns_list(argc-1, argv+1);
+
+ if ((matches(*argv, "list-id") == 0))
+ return netns_list_id(argc-1, argv+1);
+
+ if (matches(*argv, "help") == 0)
+ return usage();
+
+ if (matches(*argv, "add") == 0)
+ return netns_add(argc-1, argv+1);
+
+ if (matches(*argv, "set") == 0)
+ return netns_set(argc-1, argv+1);
+
+ if (matches(*argv, "delete") == 0)
+ return netns_delete(argc-1, argv+1);
+
+ if (matches(*argv, "identify") == 0)
+ return netns_identify(argc-1, argv+1);
+
+ if (matches(*argv, "pids") == 0)
+ return netns_pids(argc-1, argv+1);
+
+ if (matches(*argv, "exec") == 0)
+ return netns_exec(argc-1, argv+1);
+
+ if (matches(*argv, "monitor") == 0)
+ return netns_monitor(argc-1, argv+1);
+
+ fprintf(stderr, "Command \"%s\" is unknown, try \"ip netns help\".\n", *argv);
+ exit(-1);
+}
diff --git a/iproute2/ip/ipntable.c b/iproute2/ip/ipntable.c
new file mode 100644
index 0000000..6eb84e7
--- /dev/null
+++ b/iproute2/ip/ipntable.c
@@ -0,0 +1,667 @@
+/*
+ * Copyright (C)2006 USAGI/WIDE Project
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses>.
+ */
+/*
+ * based on ipneigh.c
+ */
+/*
+ * Authors:
+ * Masahide NAKAMURA @USAGI
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/time.h>
+#include <sys/socket.h>
+#include <time.h>
+
+#include "utils.h"
+#include "ip_common.h"
+
+static struct
+{
+ int family;
+ int index;
+#define NONE_DEV (-1)
+ char name[1024];
+} filter;
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr,
+ "Usage: ip ntable change name NAME [ dev DEV ]\n"
+ " [ thresh1 VAL ] [ thresh2 VAL ] [ thresh3 VAL ] [ gc_int MSEC ]\n"
+ " [ PARMS ]\n"
+ "Usage: ip ntable show [ dev DEV ] [ name NAME ]\n"
+
+ "PARMS := [ base_reachable MSEC ] [ retrans MSEC ] [ gc_stale MSEC ]\n"
+ " [ delay_probe MSEC ] [ queue LEN ]\n"
+ " [ app_probs VAL ] [ ucast_probes VAL ] [ mcast_probes VAL ]\n"
+ " [ anycast_delay MSEC ] [ proxy_delay MSEC ] [ proxy_queue LEN ]\n"
+ " [ locktime MSEC ]\n"
+ );
+
+ exit(-1);
+}
+
+static int ipntable_modify(int cmd, int flags, int argc, char **argv)
+{
+ struct {
+ struct nlmsghdr n;
+ struct ndtmsg ndtm;
+ char buf[1024];
+ } req;
+ char *namep = NULL;
+ char *threshsp = NULL;
+ char *gc_intp = NULL;
+ char parms_buf[1024];
+ struct rtattr *parms_rta = (struct rtattr *)parms_buf;
+ int parms_change = 0;
+
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ndtmsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST|flags;
+ req.n.nlmsg_type = cmd;
+
+ req.ndtm.ndtm_family = preferred_family;
+ req.ndtm.ndtm_pad1 = 0;
+ req.ndtm.ndtm_pad2 = 0;
+
+ memset(&parms_buf, 0, sizeof(parms_buf));
+
+ parms_rta->rta_type = NDTA_PARMS;
+ parms_rta->rta_len = RTA_LENGTH(0);
+
+ while (argc > 0) {
+ if (strcmp(*argv, "name") == 0) {
+ int len;
+
+ NEXT_ARG();
+ if (namep)
+ duparg("NAME", *argv);
+
+ namep = *argv;
+ len = strlen(namep) + 1;
+ addattr_l(&req.n, sizeof(req), NDTA_NAME, namep, len);
+ } else if (strcmp(*argv, "thresh1") == 0) {
+ __u32 thresh1;
+
+ NEXT_ARG();
+ threshsp = *argv;
+
+ if (get_u32(&thresh1, *argv, 0))
+ invarg("\"thresh1\" value is invalid", *argv);
+
+ addattr32(&req.n, sizeof(req), NDTA_THRESH1, thresh1);
+ } else if (strcmp(*argv, "thresh2") == 0) {
+ __u32 thresh2;
+
+ NEXT_ARG();
+ threshsp = *argv;
+
+ if (get_u32(&thresh2, *argv, 0))
+ invarg("\"thresh2\" value is invalid", *argv);
+
+ addattr32(&req.n, sizeof(req), NDTA_THRESH2, thresh2);
+ } else if (strcmp(*argv, "thresh3") == 0) {
+ __u32 thresh3;
+
+ NEXT_ARG();
+ threshsp = *argv;
+
+ if (get_u32(&thresh3, *argv, 0))
+ invarg("\"thresh3\" value is invalid", *argv);
+
+ addattr32(&req.n, sizeof(req), NDTA_THRESH3, thresh3);
+ } else if (strcmp(*argv, "gc_int") == 0) {
+ __u64 gc_int;
+
+ NEXT_ARG();
+ gc_intp = *argv;
+
+ if (get_u64(&gc_int, *argv, 0))
+ invarg("\"gc_int\" value is invalid", *argv);
+
+ addattr_l(&req.n, sizeof(req), NDTA_GC_INTERVAL,
+ &gc_int, sizeof(gc_int));
+ } else if (strcmp(*argv, "dev") == 0) {
+ __u32 ifindex;
+
+ NEXT_ARG();
+ ifindex = ll_name_to_index(*argv);
+ if (ifindex == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", *argv);
+ return -1;
+ }
+
+ rta_addattr32(parms_rta, sizeof(parms_buf),
+ NDTPA_IFINDEX, ifindex);
+ } else if (strcmp(*argv, "base_reachable") == 0) {
+ __u64 breachable;
+
+ NEXT_ARG();
+
+ if (get_u64(&breachable, *argv, 0))
+ invarg("\"base_reachable\" value is invalid", *argv);
+
+ rta_addattr_l(parms_rta, sizeof(parms_buf),
+ NDTPA_BASE_REACHABLE_TIME,
+ &breachable, sizeof(breachable));
+ parms_change = 1;
+ } else if (strcmp(*argv, "retrans") == 0) {
+ __u64 retrans;
+
+ NEXT_ARG();
+
+ if (get_u64(&retrans, *argv, 0))
+ invarg("\"retrans\" value is invalid", *argv);
+
+ rta_addattr_l(parms_rta, sizeof(parms_buf),
+ NDTPA_RETRANS_TIME,
+ &retrans, sizeof(retrans));
+ parms_change = 1;
+ } else if (strcmp(*argv, "gc_stale") == 0) {
+ __u64 gc_stale;
+
+ NEXT_ARG();
+
+ if (get_u64(&gc_stale, *argv, 0))
+ invarg("\"gc_stale\" value is invalid", *argv);
+
+ rta_addattr_l(parms_rta, sizeof(parms_buf),
+ NDTPA_GC_STALETIME,
+ &gc_stale, sizeof(gc_stale));
+ parms_change = 1;
+ } else if (strcmp(*argv, "delay_probe") == 0) {
+ __u64 delay_probe;
+
+ NEXT_ARG();
+
+ if (get_u64(&delay_probe, *argv, 0))
+ invarg("\"delay_probe\" value is invalid", *argv);
+
+ rta_addattr_l(parms_rta, sizeof(parms_buf),
+ NDTPA_DELAY_PROBE_TIME,
+ &delay_probe, sizeof(delay_probe));
+ parms_change = 1;
+ } else if (strcmp(*argv, "queue") == 0) {
+ __u32 queue;
+
+ NEXT_ARG();
+
+ if (get_u32(&queue, *argv, 0))
+ invarg("\"queue\" value is invalid", *argv);
+
+ if (!parms_rta)
+ parms_rta = (struct rtattr *)&parms_buf;
+ rta_addattr32(parms_rta, sizeof(parms_buf),
+ NDTPA_QUEUE_LEN, queue);
+ parms_change = 1;
+ } else if (strcmp(*argv, "app_probes") == 0) {
+ __u32 aprobe;
+
+ NEXT_ARG();
+
+ if (get_u32(&aprobe, *argv, 0))
+ invarg("\"app_probes\" value is invalid", *argv);
+
+ rta_addattr32(parms_rta, sizeof(parms_buf),
+ NDTPA_APP_PROBES, aprobe);
+ parms_change = 1;
+ } else if (strcmp(*argv, "ucast_probes") == 0) {
+ __u32 uprobe;
+
+ NEXT_ARG();
+
+ if (get_u32(&uprobe, *argv, 0))
+ invarg("\"ucast_probes\" value is invalid", *argv);
+
+ rta_addattr32(parms_rta, sizeof(parms_buf),
+ NDTPA_UCAST_PROBES, uprobe);
+ parms_change = 1;
+ } else if (strcmp(*argv, "mcast_probes") == 0) {
+ __u32 mprobe;
+
+ NEXT_ARG();
+
+ if (get_u32(&mprobe, *argv, 0))
+ invarg("\"mcast_probes\" value is invalid", *argv);
+
+ rta_addattr32(parms_rta, sizeof(parms_buf),
+ NDTPA_MCAST_PROBES, mprobe);
+ parms_change = 1;
+ } else if (strcmp(*argv, "anycast_delay") == 0) {
+ __u64 anycast_delay;
+
+ NEXT_ARG();
+
+ if (get_u64(&anycast_delay, *argv, 0))
+ invarg("\"anycast_delay\" value is invalid", *argv);
+
+ rta_addattr_l(parms_rta, sizeof(parms_buf),
+ NDTPA_ANYCAST_DELAY,
+ &anycast_delay, sizeof(anycast_delay));
+ parms_change = 1;
+ } else if (strcmp(*argv, "proxy_delay") == 0) {
+ __u64 proxy_delay;
+
+ NEXT_ARG();
+
+ if (get_u64(&proxy_delay, *argv, 0))
+ invarg("\"proxy_delay\" value is invalid", *argv);
+
+ rta_addattr_l(parms_rta, sizeof(parms_buf),
+ NDTPA_PROXY_DELAY,
+ &proxy_delay, sizeof(proxy_delay));
+ parms_change = 1;
+ } else if (strcmp(*argv, "proxy_queue") == 0) {
+ __u32 pqueue;
+
+ NEXT_ARG();
+
+ if (get_u32(&pqueue, *argv, 0))
+ invarg("\"proxy_queue\" value is invalid", *argv);
+
+ rta_addattr32(parms_rta, sizeof(parms_buf),
+ NDTPA_PROXY_QLEN, pqueue);
+ parms_change = 1;
+ } else if (strcmp(*argv, "locktime") == 0) {
+ __u64 locktime;
+
+ NEXT_ARG();
+
+ if (get_u64(&locktime, *argv, 0))
+ invarg("\"locktime\" value is invalid", *argv);
+
+ rta_addattr_l(parms_rta, sizeof(parms_buf),
+ NDTPA_LOCKTIME,
+ &locktime, sizeof(locktime));
+ parms_change = 1;
+ } else {
+ invarg("unknown", *argv);
+ }
+
+ argc--; argv++;
+ }
+
+ if (!namep)
+ missarg("NAME");
+ if (!threshsp && !gc_intp && !parms_change) {
+ fprintf(stderr, "Not enough information: changeable attributes required.\n");
+ exit(-1);
+ }
+
+ if (parms_rta->rta_len > RTA_LENGTH(0)) {
+ addattr_l(&req.n, sizeof(req), NDTA_PARMS, RTA_DATA(parms_rta),
+ RTA_PAYLOAD(parms_rta));
+ }
+
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ exit(2);
+
+ return 0;
+}
+
+static const char *ntable_strtime_delta(__u32 msec)
+{
+ static char str[32];
+ struct timeval now;
+ time_t t;
+ struct tm *tp;
+
+ if (msec == 0)
+ goto error;
+
+ memset(&now, 0, sizeof(now));
+
+ if (gettimeofday(&now, NULL) < 0) {
+ perror("gettimeofday");
+ goto error;
+ }
+
+ t = now.tv_sec - (msec / 1000);
+ tp = localtime(&t);
+ if (!tp)
+ goto error;
+
+ strftime(str, sizeof(str), "%Y-%m-%d %T", tp);
+
+ return str;
+ error:
+ strcpy(str, "(error)");
+ return str;
+}
+
+static int print_ntable(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ struct ndtmsg *ndtm = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr *tb[NDTA_MAX+1];
+ struct rtattr *tpb[NDTPA_MAX+1];
+ int ret;
+
+ if (n->nlmsg_type != RTM_NEWNEIGHTBL) {
+ fprintf(stderr, "Not NEIGHTBL: %08x %08x %08x\n",
+ n->nlmsg_len, n->nlmsg_type, n->nlmsg_flags);
+ return 0;
+ }
+ len -= NLMSG_LENGTH(sizeof(*ndtm));
+ if (len < 0) {
+ fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+ return -1;
+ }
+
+ if (preferred_family && preferred_family != ndtm->ndtm_family)
+ return 0;
+
+ parse_rtattr(tb, NDTA_MAX, NDTA_RTA(ndtm),
+ n->nlmsg_len - NLMSG_LENGTH(sizeof(*ndtm)));
+
+ if (tb[NDTA_NAME]) {
+ const char *name = rta_getattr_str(tb[NDTA_NAME]);
+
+ if (strlen(filter.name) > 0 && strcmp(filter.name, name))
+ return 0;
+ }
+ if (tb[NDTA_PARMS]) {
+ parse_rtattr(tpb, NDTPA_MAX, RTA_DATA(tb[NDTA_PARMS]),
+ RTA_PAYLOAD(tb[NDTA_PARMS]));
+
+ if (tpb[NDTPA_IFINDEX]) {
+ __u32 ifindex = rta_getattr_u32(tpb[NDTPA_IFINDEX]);
+
+ if (filter.index && filter.index != ifindex)
+ return 0;
+ } else {
+ if (filter.index && filter.index != NONE_DEV)
+ return 0;
+ }
+ }
+
+ if (ndtm->ndtm_family == AF_INET)
+ fprintf(fp, "inet ");
+ else if (ndtm->ndtm_family == AF_INET6)
+ fprintf(fp, "inet6 ");
+ else if (ndtm->ndtm_family == AF_DECnet)
+ fprintf(fp, "dnet ");
+ else
+ fprintf(fp, "(%d) ", ndtm->ndtm_family);
+
+ if (tb[NDTA_NAME]) {
+ const char *name = rta_getattr_str(tb[NDTA_NAME]);
+ fprintf(fp, "%s ", name);
+ }
+
+ fprintf(fp, "%s", _SL_);
+
+ ret = (tb[NDTA_THRESH1] || tb[NDTA_THRESH2] || tb[NDTA_THRESH3] ||
+ tb[NDTA_GC_INTERVAL]);
+ if (ret)
+ fprintf(fp, " ");
+
+ if (tb[NDTA_THRESH1]) {
+ __u32 thresh1 = rta_getattr_u32(tb[NDTA_THRESH1]);
+ fprintf(fp, "thresh1 %u ", thresh1);
+ }
+ if (tb[NDTA_THRESH2]) {
+ __u32 thresh2 = rta_getattr_u32(tb[NDTA_THRESH2]);
+ fprintf(fp, "thresh2 %u ", thresh2);
+ }
+ if (tb[NDTA_THRESH3]) {
+ __u32 thresh3 = rta_getattr_u32(tb[NDTA_THRESH3]);
+ fprintf(fp, "thresh3 %u ", thresh3);
+ }
+ if (tb[NDTA_GC_INTERVAL]) {
+ unsigned long long gc_int = rta_getattr_u64(tb[NDTA_GC_INTERVAL]);
+ fprintf(fp, "gc_int %llu ", gc_int);
+ }
+
+ if (ret)
+ fprintf(fp, "%s", _SL_);
+
+ if (tb[NDTA_CONFIG] && show_stats) {
+ struct ndt_config *ndtc = RTA_DATA(tb[NDTA_CONFIG]);
+
+ fprintf(fp, " ");
+ fprintf(fp, "config ");
+
+ fprintf(fp, "key_len %u ", ndtc->ndtc_key_len);
+ fprintf(fp, "entry_size %u ", ndtc->ndtc_entry_size);
+ fprintf(fp, "entries %u ", ndtc->ndtc_entries);
+
+ fprintf(fp, "%s", _SL_);
+ fprintf(fp, " ");
+
+ fprintf(fp, "last_flush %s ",
+ ntable_strtime_delta(ndtc->ndtc_last_flush));
+ fprintf(fp, "last_rand %s ",
+ ntable_strtime_delta(ndtc->ndtc_last_rand));
+
+ fprintf(fp, "%s", _SL_);
+ fprintf(fp, " ");
+
+ fprintf(fp, "hash_rnd %u ", ndtc->ndtc_hash_rnd);
+ fprintf(fp, "hash_mask %08x ", ndtc->ndtc_hash_mask);
+
+ fprintf(fp, "hash_chain_gc %u ", ndtc->ndtc_hash_chain_gc);
+ fprintf(fp, "proxy_qlen %u ", ndtc->ndtc_proxy_qlen);
+
+ fprintf(fp, "%s", _SL_);
+ }
+
+ if (tb[NDTA_PARMS]) {
+ if (tpb[NDTPA_IFINDEX]) {
+ __u32 ifindex = rta_getattr_u32(tpb[NDTPA_IFINDEX]);
+
+ fprintf(fp, " ");
+ fprintf(fp, "dev %s ", ll_index_to_name(ifindex));
+ fprintf(fp, "%s", _SL_);
+ }
+
+ fprintf(fp, " ");
+
+ if (tpb[NDTPA_REFCNT]) {
+ __u32 refcnt = rta_getattr_u32(tpb[NDTPA_REFCNT]);
+ fprintf(fp, "refcnt %u ", refcnt);
+ }
+ if (tpb[NDTPA_REACHABLE_TIME]) {
+ unsigned long long reachable = rta_getattr_u64(tpb[NDTPA_REACHABLE_TIME]);
+ fprintf(fp, "reachable %llu ", reachable);
+ }
+ if (tpb[NDTPA_BASE_REACHABLE_TIME]) {
+ unsigned long long breachable = rta_getattr_u64(tpb[NDTPA_BASE_REACHABLE_TIME]);
+ fprintf(fp, "base_reachable %llu ", breachable);
+ }
+ if (tpb[NDTPA_RETRANS_TIME]) {
+ unsigned long long retrans = rta_getattr_u64(tpb[NDTPA_RETRANS_TIME]);
+ fprintf(fp, "retrans %llu ", retrans);
+ }
+
+ fprintf(fp, "%s", _SL_);
+
+ fprintf(fp, " ");
+
+ if (tpb[NDTPA_GC_STALETIME]) {
+ unsigned long long gc_stale = rta_getattr_u64(tpb[NDTPA_GC_STALETIME]);
+ fprintf(fp, "gc_stale %llu ", gc_stale);
+ }
+ if (tpb[NDTPA_DELAY_PROBE_TIME]) {
+ unsigned long long delay_probe = rta_getattr_u64(tpb[NDTPA_DELAY_PROBE_TIME]);
+ fprintf(fp, "delay_probe %llu ", delay_probe);
+ }
+ if (tpb[NDTPA_QUEUE_LEN]) {
+ __u32 queue = rta_getattr_u32(tpb[NDTPA_QUEUE_LEN]);
+ fprintf(fp, "queue %u ", queue);
+ }
+
+ fprintf(fp, "%s", _SL_);
+
+ fprintf(fp, " ");
+
+ if (tpb[NDTPA_APP_PROBES]) {
+ __u32 aprobe = rta_getattr_u32(tpb[NDTPA_APP_PROBES]);
+ fprintf(fp, "app_probes %u ", aprobe);
+ }
+ if (tpb[NDTPA_UCAST_PROBES]) {
+ __u32 uprobe = rta_getattr_u32(tpb[NDTPA_UCAST_PROBES]);
+ fprintf(fp, "ucast_probes %u ", uprobe);
+ }
+ if (tpb[NDTPA_MCAST_PROBES]) {
+ __u32 mprobe = rta_getattr_u32(tpb[NDTPA_MCAST_PROBES]);
+ fprintf(fp, "mcast_probes %u ", mprobe);
+ }
+
+ fprintf(fp, "%s", _SL_);
+
+ fprintf(fp, " ");
+
+ if (tpb[NDTPA_ANYCAST_DELAY]) {
+ unsigned long long anycast_delay = rta_getattr_u64(tpb[NDTPA_ANYCAST_DELAY]);
+ fprintf(fp, "anycast_delay %llu ", anycast_delay);
+ }
+ if (tpb[NDTPA_PROXY_DELAY]) {
+ unsigned long long proxy_delay = rta_getattr_u64(tpb[NDTPA_PROXY_DELAY]);
+ fprintf(fp, "proxy_delay %llu ", proxy_delay);
+ }
+ if (tpb[NDTPA_PROXY_QLEN]) {
+ __u32 pqueue = rta_getattr_u32(tpb[NDTPA_PROXY_QLEN]);
+ fprintf(fp, "proxy_queue %u ", pqueue);
+ }
+ if (tpb[NDTPA_LOCKTIME]) {
+ unsigned long long locktime = rta_getattr_u64(tpb[NDTPA_LOCKTIME]);
+ fprintf(fp, "locktime %llu ", locktime);
+ }
+
+ fprintf(fp, "%s", _SL_);
+ }
+
+ if (tb[NDTA_STATS] && show_stats) {
+ struct ndt_stats *ndts = RTA_DATA(tb[NDTA_STATS]);
+
+ fprintf(fp, " ");
+ fprintf(fp, "stats ");
+
+ fprintf(fp, "allocs %llu ",
+ (unsigned long long) ndts->ndts_allocs);
+ fprintf(fp, "destroys %llu ",
+ (unsigned long long) ndts->ndts_destroys);
+ fprintf(fp, "hash_grows %llu ",
+ (unsigned long long) ndts->ndts_hash_grows);
+
+ fprintf(fp, "%s", _SL_);
+ fprintf(fp, " ");
+
+ fprintf(fp, "res_failed %llu ",
+ (unsigned long long) ndts->ndts_res_failed);
+ fprintf(fp, "lookups %llu ",
+ (unsigned long long) ndts->ndts_lookups);
+ fprintf(fp, "hits %llu ",
+ (unsigned long long) ndts->ndts_hits);
+
+ fprintf(fp, "%s", _SL_);
+ fprintf(fp, " ");
+
+ fprintf(fp, "rcv_probes_mcast %llu ",
+ (unsigned long long) ndts->ndts_rcv_probes_mcast);
+ fprintf(fp, "rcv_probes_ucast %llu ",
+ (unsigned long long) ndts->ndts_rcv_probes_ucast);
+
+ fprintf(fp, "%s", _SL_);
+ fprintf(fp, " ");
+
+ fprintf(fp, "periodic_gc_runs %llu ",
+ (unsigned long long) ndts->ndts_periodic_gc_runs);
+ fprintf(fp, "forced_gc_runs %llu ",
+ (unsigned long long) ndts->ndts_forced_gc_runs);
+
+ fprintf(fp, "%s", _SL_);
+ }
+
+ fprintf(fp, "\n");
+
+ fflush(fp);
+ return 0;
+}
+
+static void ipntable_reset_filter(void)
+{
+ memset(&filter, 0, sizeof(filter));
+}
+
+static int ipntable_show(int argc, char **argv)
+{
+ ipntable_reset_filter();
+
+ filter.family = preferred_family;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+
+ if (strcmp("none", *argv) == 0)
+ filter.index = NONE_DEV;
+ else if ((filter.index = ll_name_to_index(*argv)) == 0)
+ invarg("\"DEV\" is invalid", *argv);
+ } else if (strcmp(*argv, "name") == 0) {
+ NEXT_ARG();
+
+ strncpy(filter.name, *argv, sizeof(filter.name));
+ } else
+ invarg("unknown", *argv);
+
+ argc--; argv++;
+ }
+
+ if (rtnl_wilddump_request(&rth, preferred_family, RTM_GETNEIGHTBL) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+
+ if (rtnl_dump_filter(&rth, print_ntable, stdout) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ exit(1);
+ }
+
+ return 0;
+}
+
+int do_ipntable(int argc, char **argv)
+{
+ ll_init_map(&rth);
+
+ if (argc > 0) {
+ if (matches(*argv, "change") == 0 ||
+ matches(*argv, "chg") == 0)
+ return ipntable_modify(RTM_SETNEIGHTBL,
+ NLM_F_REPLACE,
+ argc-1, argv+1);
+ if (matches(*argv, "show") == 0 ||
+ matches(*argv, "lst") == 0 ||
+ matches(*argv, "list") == 0)
+ return ipntable_show(argc-1, argv+1);
+ if (matches(*argv, "help") == 0)
+ usage();
+ } else
+ return ipntable_show(0, NULL);
+
+ fprintf(stderr, "Command \"%s\" is unknown, try \"ip ntable help\".\n", *argv);
+ exit(-1);
+}
diff --git a/iproute2/ip/ipprefix.c b/iproute2/ip/ipprefix.c
new file mode 100644
index 0000000..ee51f04
--- /dev/null
+++ b/iproute2/ip/ipprefix.c
@@ -0,0 +1,109 @@
+/*
+ * Copyright (C)2005 USAGI/WIDE Project
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses>.
+ */
+/*
+ * based on ip.c, iproute.c
+ */
+/*
+ * Authors:
+ * Masahide NAKAMURA @USAGI
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <netinet/icmp6.h>
+
+#include "utils.h"
+#include "ip_common.h"
+
+/* prefix flags; see kernel's net/ipv6/addrconf.c and include/net/if_inet6.h */
+#define IF_PREFIX_ONLINK 0x01
+#define IF_PREFIX_AUTOCONF 0x02
+
+int print_prefix(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ struct prefixmsg *prefix = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr * tb[RTA_MAX+1];
+ int family = preferred_family;
+
+ if (n->nlmsg_type != RTM_NEWPREFIX) {
+ fprintf(stderr, "Not a prefix: %08x %08x %08x\n",
+ n->nlmsg_len, n->nlmsg_type, n->nlmsg_flags);
+ return 0;
+ }
+
+ len -= NLMSG_LENGTH(sizeof(*prefix));
+ if (len < 0) {
+ fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+ return -1;
+ }
+
+ if (family == AF_UNSPEC)
+ family = AF_INET6;
+ if (family != AF_INET6)
+ return 0;
+
+ if (prefix->prefix_family != AF_INET6) {
+ fprintf(stderr, "incorrect protocol family: %d\n", prefix->prefix_family);
+ return 0;
+ }
+ if (prefix->prefix_type != ND_OPT_PREFIX_INFORMATION) {
+ fprintf(stderr, "wrong ND type %d\n", prefix->prefix_type);
+ return 0;
+ }
+
+ parse_rtattr(tb, RTA_MAX, RTM_RTA(prefix), len);
+
+ fprintf(fp, "prefix ");
+
+ if (tb[PREFIX_ADDRESS]) {
+ struct in6_addr *pfx;
+ char abuf[256];
+
+ pfx = (struct in6_addr *)RTA_DATA(tb[PREFIX_ADDRESS]);
+
+ memset(abuf, '\0', sizeof(abuf));
+ fprintf(fp, "%s", rt_addr_n2a(family,
+ RTA_PAYLOAD(tb[PREFIX_ADDRESS]),
+ pfx,
+ abuf, sizeof(abuf)));
+ }
+ fprintf(fp, "/%u ", prefix->prefix_len);
+
+ fprintf(fp, "dev %s ", ll_index_to_name(prefix->prefix_ifindex));
+
+ if (prefix->prefix_flags & IF_PREFIX_ONLINK)
+ fprintf(fp, "onlink ");
+ if (prefix->prefix_flags & IF_PREFIX_AUTOCONF)
+ fprintf(fp, "autoconf ");
+
+ if (tb[PREFIX_CACHEINFO]) {
+ struct prefix_cacheinfo *pc;
+ pc = (struct prefix_cacheinfo *)RTA_DATA(tb[PREFIX_CACHEINFO]);
+
+ fprintf(fp, "valid %u ", pc->valid_time);
+ fprintf(fp, "preferred %u ", pc->preferred_time);
+ }
+
+ fprintf(fp, "\n");
+ fflush(fp);
+
+ return 0;
+}
diff --git a/iproute2/ip/iproute.c b/iproute2/ip/iproute.c
new file mode 100644
index 0000000..381c3dd
--- /dev/null
+++ b/iproute2/ip/iproute.c
@@ -0,0 +1,1861 @@
+/*
+ * iproute.c "ip route".
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <string.h>
+#include <time.h>
+#include <sys/time.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+#include <arpa/inet.h>
+#include <linux/in_route.h>
+#include <linux/icmpv6.h>
+#include <errno.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+#include "iproute_lwtunnel.h"
+
+#ifndef RTAX_RTTVAR
+#define RTAX_RTTVAR RTAX_HOPS
+#endif
+
+enum list_action {
+ IPROUTE_LIST,
+ IPROUTE_FLUSH,
+ IPROUTE_SAVE,
+};
+static const char *mx_names[RTAX_MAX+1] = {
+ [RTAX_MTU] = "mtu",
+ [RTAX_WINDOW] = "window",
+ [RTAX_RTT] = "rtt",
+ [RTAX_RTTVAR] = "rttvar",
+ [RTAX_SSTHRESH] = "ssthresh",
+ [RTAX_CWND] = "cwnd",
+ [RTAX_ADVMSS] = "advmss",
+ [RTAX_REORDERING]="reordering",
+ [RTAX_HOPLIMIT] = "hoplimit",
+ [RTAX_INITCWND] = "initcwnd",
+ [RTAX_FEATURES] = "features",
+ [RTAX_RTO_MIN] = "rto_min",
+ [RTAX_INITRWND] = "initrwnd",
+ [RTAX_QUICKACK] = "quickack",
+ [RTAX_CC_ALGO] = "congctl",
+};
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: ip route { list | flush } SELECTOR\n");
+ fprintf(stderr, " ip route save SELECTOR\n");
+ fprintf(stderr, " ip route restore\n");
+ fprintf(stderr, " ip route showdump\n");
+ fprintf(stderr, " ip route get ADDRESS [ from ADDRESS iif STRING ]\n");
+ fprintf(stderr, " [ oif STRING ] [ tos TOS ]\n");
+ fprintf(stderr, " [ mark NUMBER ] [ uid NUMBER ]\n");
+ fprintf(stderr, " ip route { add | del | change | append | replace } ROUTE\n");
+ fprintf(stderr, "SELECTOR := [ root PREFIX ] [ match PREFIX ] [ exact PREFIX ]\n");
+ fprintf(stderr, " [ table TABLE_ID ] [ proto RTPROTO ]\n");
+ fprintf(stderr, " [ type TYPE ] [ scope SCOPE ]\n");
+ fprintf(stderr, "ROUTE := NODE_SPEC [ INFO_SPEC ]\n");
+ fprintf(stderr, "NODE_SPEC := [ TYPE ] PREFIX [ tos TOS ]\n");
+ fprintf(stderr, " [ table TABLE_ID ] [ proto RTPROTO ]\n");
+ fprintf(stderr, " [ scope SCOPE ] [ metric METRIC ]\n");
+ fprintf(stderr, "INFO_SPEC := NH OPTIONS FLAGS [ nexthop NH ]...\n");
+ fprintf(stderr, "NH := [ encap ENCAPTYPE ENCAPHDR ] [ via [ FAMILY ] ADDRESS ]\n");
+ fprintf(stderr, " [ dev STRING ] [ weight NUMBER ] NHFLAGS\n");
+ fprintf(stderr, "FAMILY := [ inet | inet6 | ipx | dnet | mpls | bridge | link ]\n");
+ fprintf(stderr, "OPTIONS := FLAGS [ mtu NUMBER ] [ advmss NUMBER ] [ as [ to ] ADDRESS ]\n");
+ fprintf(stderr, " [ rtt TIME ] [ rttvar TIME ] [ reordering NUMBER ]\n");
+ fprintf(stderr, " [ window NUMBER] [ cwnd NUMBER ] [ initcwnd NUMBER ]\n");
+ fprintf(stderr, " [ ssthresh NUMBER ] [ realms REALM ] [ src ADDRESS ]\n");
+ fprintf(stderr, " [ rto_min TIME ] [ hoplimit NUMBER ] [ initrwnd NUMBER ]\n");
+ fprintf(stderr, " [ features FEATURES ] [ quickack BOOL ] [ congctl NAME ]\n");
+ fprintf(stderr, " [ pref PREF ] [ expires TIME ]\n");
+ fprintf(stderr, "TYPE := [ unicast | local | broadcast | multicast | throw |\n");
+ fprintf(stderr, " unreachable | prohibit | blackhole | nat ]\n");
+ fprintf(stderr, "TABLE_ID := [ local | main | default | all | NUMBER ]\n");
+ fprintf(stderr, "SCOPE := [ host | link | global | NUMBER ]\n");
+ fprintf(stderr, "NHFLAGS := [ onlink | pervasive ]\n");
+ fprintf(stderr, "RTPROTO := [ kernel | boot | static | NUMBER ]\n");
+ fprintf(stderr, "PREF := [ low | medium | high ]\n");
+ fprintf(stderr, "TIME := NUMBER[s|ms]\n");
+ fprintf(stderr, "BOOL := [1|0]\n");
+ fprintf(stderr, "FEATURES := ecn\n");
+ fprintf(stderr, "ENCAPTYPE := [ mpls | ip | ip6 ]\n");
+ fprintf(stderr, "ENCAPHDR := [ MPLSLABEL ]\n");
+ exit(-1);
+}
+
+
+static struct
+{
+ unsigned int tb;
+ int cloned;
+ int flushed;
+ char *flushb;
+ int flushp;
+ int flushe;
+ int protocol, protocolmask;
+ int scope, scopemask;
+ int type, typemask;
+ int tos, tosmask;
+ int iif, iifmask;
+ int oif, oifmask;
+ int mark, markmask;
+ int realm, realmmask;
+ inet_prefix rprefsrc;
+ inet_prefix rvia;
+ inet_prefix rdst;
+ inet_prefix mdst;
+ inet_prefix rsrc;
+ inet_prefix msrc;
+} filter;
+
+static int flush_update(void)
+{
+ if (rtnl_send_check(&rth, filter.flushb, filter.flushp) < 0) {
+ perror("Failed to send flush request");
+ return -1;
+ }
+ filter.flushp = 0;
+ return 0;
+}
+
+static int filter_nlmsg(struct nlmsghdr *n, struct rtattr **tb, int host_len)
+{
+ struct rtmsg *r = NLMSG_DATA(n);
+ inet_prefix dst;
+ inet_prefix src;
+ inet_prefix via;
+ inet_prefix prefsrc;
+ __u32 table;
+ static int ip6_multiple_tables;
+
+ table = rtm_get_table(r, tb);
+
+ if (preferred_family != AF_UNSPEC && r->rtm_family != preferred_family)
+ return 0;
+
+ if (r->rtm_family == AF_INET6 && table != RT_TABLE_MAIN)
+ ip6_multiple_tables = 1;
+
+ if (filter.cloned == !(r->rtm_flags&RTM_F_CLONED))
+ return 0;
+
+ if (r->rtm_family == AF_INET6 && !ip6_multiple_tables) {
+ if (filter.tb) {
+ if (filter.tb == RT_TABLE_LOCAL) {
+ if (r->rtm_type != RTN_LOCAL)
+ return 0;
+ } else if (filter.tb == RT_TABLE_MAIN) {
+ if (r->rtm_type == RTN_LOCAL)
+ return 0;
+ } else {
+ return 0;
+ }
+ }
+ } else {
+ if (filter.tb > 0 && filter.tb != table)
+ return 0;
+ }
+ if ((filter.protocol^r->rtm_protocol)&filter.protocolmask)
+ return 0;
+ if ((filter.scope^r->rtm_scope)&filter.scopemask)
+ return 0;
+ if ((filter.type^r->rtm_type)&filter.typemask)
+ return 0;
+ if ((filter.tos^r->rtm_tos)&filter.tosmask)
+ return 0;
+ if (filter.rdst.family &&
+ (r->rtm_family != filter.rdst.family || filter.rdst.bitlen > r->rtm_dst_len))
+ return 0;
+ if (filter.mdst.family &&
+ (r->rtm_family != filter.mdst.family ||
+ (filter.mdst.bitlen >= 0 && filter.mdst.bitlen < r->rtm_dst_len)))
+ return 0;
+ if (filter.rsrc.family &&
+ (r->rtm_family != filter.rsrc.family || filter.rsrc.bitlen > r->rtm_src_len))
+ return 0;
+ if (filter.msrc.family &&
+ (r->rtm_family != filter.msrc.family ||
+ (filter.msrc.bitlen >= 0 && filter.msrc.bitlen < r->rtm_src_len)))
+ return 0;
+ if (filter.rvia.family) {
+ int family = r->rtm_family;
+ if (tb[RTA_VIA]) {
+ struct rtvia *via = RTA_DATA(tb[RTA_VIA]);
+ family = via->rtvia_family;
+ }
+ if (family != filter.rvia.family)
+ return 0;
+ }
+ if (filter.rprefsrc.family && r->rtm_family != filter.rprefsrc.family)
+ return 0;
+
+ memset(&dst, 0, sizeof(dst));
+ dst.family = r->rtm_family;
+ if (tb[RTA_DST])
+ memcpy(&dst.data, RTA_DATA(tb[RTA_DST]), (r->rtm_dst_len+7)/8);
+ if (filter.rsrc.family || filter.msrc.family) {
+ memset(&src, 0, sizeof(src));
+ src.family = r->rtm_family;
+ if (tb[RTA_SRC])
+ memcpy(&src.data, RTA_DATA(tb[RTA_SRC]), (r->rtm_src_len+7)/8);
+ }
+ if (filter.rvia.bitlen>0) {
+ memset(&via, 0, sizeof(via));
+ via.family = r->rtm_family;
+ if (tb[RTA_GATEWAY])
+ memcpy(&via.data, RTA_DATA(tb[RTA_GATEWAY]), host_len/8);
+ if (tb[RTA_VIA]) {
+ size_t len = RTA_PAYLOAD(tb[RTA_VIA]) - 2;
+ struct rtvia *rtvia = RTA_DATA(tb[RTA_VIA]);
+ via.family = rtvia->rtvia_family;
+ memcpy(&via.data, rtvia->rtvia_addr, len);
+ }
+ }
+ if (filter.rprefsrc.bitlen>0) {
+ memset(&prefsrc, 0, sizeof(prefsrc));
+ prefsrc.family = r->rtm_family;
+ if (tb[RTA_PREFSRC])
+ memcpy(&prefsrc.data, RTA_DATA(tb[RTA_PREFSRC]), host_len/8);
+ }
+
+ if (filter.rdst.family && inet_addr_match(&dst, &filter.rdst, filter.rdst.bitlen))
+ return 0;
+ if (filter.mdst.family && filter.mdst.bitlen >= 0 &&
+ inet_addr_match(&dst, &filter.mdst, r->rtm_dst_len))
+ return 0;
+
+ if (filter.rsrc.family && inet_addr_match(&src, &filter.rsrc, filter.rsrc.bitlen))
+ return 0;
+ if (filter.msrc.family && filter.msrc.bitlen >= 0 &&
+ inet_addr_match(&src, &filter.msrc, r->rtm_src_len))
+ return 0;
+
+ if (filter.rvia.family && inet_addr_match(&via, &filter.rvia, filter.rvia.bitlen))
+ return 0;
+ if (filter.rprefsrc.family && inet_addr_match(&prefsrc, &filter.rprefsrc, filter.rprefsrc.bitlen))
+ return 0;
+ if (filter.realmmask) {
+ __u32 realms = 0;
+ if (tb[RTA_FLOW])
+ realms = rta_getattr_u32(tb[RTA_FLOW]);
+ if ((realms^filter.realm)&filter.realmmask)
+ return 0;
+ }
+ if (filter.iifmask) {
+ int iif = 0;
+ if (tb[RTA_IIF])
+ iif = *(int*)RTA_DATA(tb[RTA_IIF]);
+ if ((iif^filter.iif)&filter.iifmask)
+ return 0;
+ }
+ if (filter.oifmask) {
+ int oif = 0;
+ if (tb[RTA_OIF])
+ oif = *(int*)RTA_DATA(tb[RTA_OIF]);
+ if ((oif^filter.oif)&filter.oifmask)
+ return 0;
+ }
+ if (filter.markmask) {
+ int mark = 0;
+ if (tb[RTA_MARK])
+ mark = *(int *)RTA_DATA(tb[RTA_MARK]);
+ if ((mark ^ filter.mark) & filter.markmask)
+ return 0;
+ }
+ if (filter.flushb &&
+ r->rtm_family == AF_INET6 &&
+ r->rtm_dst_len == 0 &&
+ r->rtm_type == RTN_UNREACHABLE &&
+ tb[RTA_PRIORITY] &&
+ *(int*)RTA_DATA(tb[RTA_PRIORITY]) == -1)
+ return 0;
+
+ return 1;
+}
+
+static void print_rtax_features(FILE *fp, unsigned int features)
+{
+ unsigned int of = features;
+
+ if (features & RTAX_FEATURE_ECN) {
+ fprintf(fp, " ecn");
+ features &= ~RTAX_FEATURE_ECN;
+ }
+
+ if (features)
+ fprintf(fp, " 0x%x", of);
+}
+
+int print_route(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ struct rtmsg *r = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr * tb[RTA_MAX+1];
+ char abuf[256];
+ int host_len;
+ __u32 table;
+ SPRINT_BUF(b1);
+ static int hz;
+
+ if (n->nlmsg_type != RTM_NEWROUTE && n->nlmsg_type != RTM_DELROUTE) {
+ fprintf(stderr, "Not a route: %08x %08x %08x\n",
+ n->nlmsg_len, n->nlmsg_type, n->nlmsg_flags);
+ return 0;
+ }
+ if (filter.flushb && n->nlmsg_type != RTM_NEWROUTE)
+ return 0;
+ len -= NLMSG_LENGTH(sizeof(*r));
+ if (len < 0) {
+ fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+ return -1;
+ }
+
+ host_len = af_bit_len(r->rtm_family);
+
+ parse_rtattr(tb, RTA_MAX, RTM_RTA(r), len);
+ table = rtm_get_table(r, tb);
+
+ if (!filter_nlmsg(n, tb, host_len))
+ return 0;
+
+ if (filter.flushb) {
+ struct nlmsghdr *fn;
+ if (NLMSG_ALIGN(filter.flushp) + n->nlmsg_len > filter.flushe) {
+ if (flush_update())
+ return -1;
+ }
+ fn = (struct nlmsghdr*)(filter.flushb + NLMSG_ALIGN(filter.flushp));
+ memcpy(fn, n, n->nlmsg_len);
+ fn->nlmsg_type = RTM_DELROUTE;
+ fn->nlmsg_flags = NLM_F_REQUEST;
+ fn->nlmsg_seq = ++rth.seq;
+ filter.flushp = (((char*)fn) + n->nlmsg_len) - filter.flushb;
+ filter.flushed++;
+ if (show_stats < 2)
+ return 0;
+ }
+
+ if (n->nlmsg_type == RTM_DELROUTE)
+ fprintf(fp, "Deleted ");
+ if ((r->rtm_type != RTN_UNICAST || show_details > 0) && !filter.type)
+ fprintf(fp, "%s ", rtnl_rtntype_n2a(r->rtm_type, b1, sizeof(b1)));
+
+ if (tb[RTA_DST]) {
+ if (r->rtm_dst_len != host_len) {
+ fprintf(fp, "%s/%u ", rt_addr_n2a(r->rtm_family,
+ RTA_PAYLOAD(tb[RTA_DST]),
+ RTA_DATA(tb[RTA_DST]),
+ abuf, sizeof(abuf)),
+ r->rtm_dst_len
+ );
+ } else {
+ fprintf(fp, "%s ", format_host(r->rtm_family,
+ RTA_PAYLOAD(tb[RTA_DST]),
+ RTA_DATA(tb[RTA_DST]),
+ abuf, sizeof(abuf))
+ );
+ }
+ } else if (r->rtm_dst_len) {
+ fprintf(fp, "0/%d ", r->rtm_dst_len);
+ } else {
+ fprintf(fp, "default ");
+ }
+ if (tb[RTA_SRC]) {
+ if (r->rtm_src_len != host_len) {
+ fprintf(fp, "from %s/%u ", rt_addr_n2a(r->rtm_family,
+ RTA_PAYLOAD(tb[RTA_SRC]),
+ RTA_DATA(tb[RTA_SRC]),
+ abuf, sizeof(abuf)),
+ r->rtm_src_len
+ );
+ } else {
+ fprintf(fp, "from %s ", format_host(r->rtm_family,
+ RTA_PAYLOAD(tb[RTA_SRC]),
+ RTA_DATA(tb[RTA_SRC]),
+ abuf, sizeof(abuf))
+ );
+ }
+ } else if (r->rtm_src_len) {
+ fprintf(fp, "from 0/%u ", r->rtm_src_len);
+ }
+ if (tb[RTA_NEWDST]) {
+ fprintf(fp, "as to %s ", format_host(r->rtm_family,
+ RTA_PAYLOAD(tb[RTA_NEWDST]),
+ RTA_DATA(tb[RTA_NEWDST]),
+ abuf, sizeof(abuf))
+ );
+ }
+
+ if (tb[RTA_ENCAP])
+ lwt_print_encap(fp, tb[RTA_ENCAP_TYPE], tb[RTA_ENCAP]);
+
+ if (r->rtm_tos && filter.tosmask != -1) {
+ SPRINT_BUF(b1);
+ fprintf(fp, "tos %s ", rtnl_dsfield_n2a(r->rtm_tos, b1, sizeof(b1)));
+ }
+
+ if (tb[RTA_GATEWAY] && filter.rvia.bitlen != host_len) {
+ fprintf(fp, "via %s ",
+ format_host(r->rtm_family,
+ RTA_PAYLOAD(tb[RTA_GATEWAY]),
+ RTA_DATA(tb[RTA_GATEWAY]),
+ abuf, sizeof(abuf)));
+ }
+ if (tb[RTA_VIA]) {
+ size_t len = RTA_PAYLOAD(tb[RTA_VIA]) - 2;
+ struct rtvia *via = RTA_DATA(tb[RTA_VIA]);
+ fprintf(fp, "via %s %s ",
+ family_name(via->rtvia_family),
+ format_host(via->rtvia_family, len, via->rtvia_addr,
+ abuf, sizeof(abuf)));
+ }
+ if (tb[RTA_OIF] && filter.oifmask != -1)
+ fprintf(fp, "dev %s ", ll_index_to_name(*(int*)RTA_DATA(tb[RTA_OIF])));
+
+ if (table && (table != RT_TABLE_MAIN || show_details > 0) && !filter.tb)
+ fprintf(fp, " table %s ", rtnl_rttable_n2a(table, b1, sizeof(b1)));
+ if (!(r->rtm_flags&RTM_F_CLONED)) {
+ if ((r->rtm_protocol != RTPROT_BOOT || show_details > 0) && filter.protocolmask != -1)
+ fprintf(fp, " proto %s ", rtnl_rtprot_n2a(r->rtm_protocol, b1, sizeof(b1)));
+ if ((r->rtm_scope != RT_SCOPE_UNIVERSE || show_details > 0) && filter.scopemask != -1)
+ fprintf(fp, " scope %s ", rtnl_rtscope_n2a(r->rtm_scope, b1, sizeof(b1)));
+ }
+ if (tb[RTA_PREFSRC] && filter.rprefsrc.bitlen != host_len) {
+ /* Do not use format_host(). It is our local addr
+ and symbolic name will not be useful.
+ */
+ fprintf(fp, " src %s ",
+ rt_addr_n2a(r->rtm_family,
+ RTA_PAYLOAD(tb[RTA_PREFSRC]),
+ RTA_DATA(tb[RTA_PREFSRC]),
+ abuf, sizeof(abuf)));
+ }
+ if (tb[RTA_PRIORITY])
+ fprintf(fp, " metric %u ", rta_getattr_u32(tb[RTA_PRIORITY]));
+ if (r->rtm_flags & RTNH_F_DEAD)
+ fprintf(fp, "dead ");
+ if (r->rtm_flags & RTNH_F_ONLINK)
+ fprintf(fp, "onlink ");
+ if (r->rtm_flags & RTNH_F_PERVASIVE)
+ fprintf(fp, "pervasive ");
+ if (r->rtm_flags & RTNH_F_OFFLOAD)
+ fprintf(fp, "offload ");
+ if (r->rtm_flags & RTM_F_NOTIFY)
+ fprintf(fp, "notify ");
+ if (r->rtm_flags & RTNH_F_LINKDOWN)
+ fprintf(fp, "linkdown ");
+ if (tb[RTA_MARK]) {
+ unsigned int mark = *(unsigned int*)RTA_DATA(tb[RTA_MARK]);
+ if (mark) {
+ if (mark >= 16)
+ fprintf(fp, " mark 0x%x", mark);
+ else
+ fprintf(fp, " mark %u", mark);
+ }
+ }
+
+ if (tb[RTA_UID])
+ fprintf(fp, " uid %u ", rta_getattr_u32(tb[RTA_UID]));
+
+ if (tb[RTA_FLOW] && filter.realmmask != ~0U) {
+ __u32 to = rta_getattr_u32(tb[RTA_FLOW]);
+ __u32 from = to>>16;
+ to &= 0xFFFF;
+ fprintf(fp, "realm%s ", from ? "s" : "");
+ if (from) {
+ fprintf(fp, "%s/",
+ rtnl_rtrealm_n2a(from, b1, sizeof(b1)));
+ }
+ fprintf(fp, "%s ",
+ rtnl_rtrealm_n2a(to, b1, sizeof(b1)));
+ }
+ if ((r->rtm_flags&RTM_F_CLONED) && r->rtm_family == AF_INET) {
+ __u32 flags = r->rtm_flags&~0xFFFF;
+ int first = 1;
+
+ fprintf(fp, "%s cache ", _SL_);
+
+#define PRTFL(fl,flname) if (flags&RTCF_##fl) { \
+ flags &= ~RTCF_##fl; \
+ fprintf(fp, "%s" flname "%s", first ? "<" : "", flags ? "," : "> "); \
+ first = 0; }
+ PRTFL(LOCAL, "local");
+ PRTFL(REJECT, "reject");
+ PRTFL(MULTICAST, "mc");
+ PRTFL(BROADCAST, "brd");
+ PRTFL(DNAT, "dst-nat");
+ PRTFL(SNAT, "src-nat");
+ PRTFL(MASQ, "masq");
+ PRTFL(DIRECTDST, "dst-direct");
+ PRTFL(DIRECTSRC, "src-direct");
+ PRTFL(REDIRECTED, "redirected");
+ PRTFL(DOREDIRECT, "redirect");
+ PRTFL(FAST, "fastroute");
+ PRTFL(NOTIFY, "notify");
+ PRTFL(TPROXY, "proxy");
+
+ if (flags)
+ fprintf(fp, "%s%x> ", first ? "<" : "", flags);
+ if (tb[RTA_CACHEINFO]) {
+ struct rta_cacheinfo *ci = RTA_DATA(tb[RTA_CACHEINFO]);
+ if (!hz)
+ hz = get_user_hz();
+ if (ci->rta_expires != 0)
+ fprintf(fp, " expires %dsec", ci->rta_expires/hz);
+ if (ci->rta_error != 0)
+ fprintf(fp, " error %d", ci->rta_error);
+ if (show_stats) {
+ if (ci->rta_clntref)
+ fprintf(fp, " users %d", ci->rta_clntref);
+ if (ci->rta_used != 0)
+ fprintf(fp, " used %d", ci->rta_used);
+ if (ci->rta_lastuse != 0)
+ fprintf(fp, " age %dsec", ci->rta_lastuse/hz);
+ }
+ if (ci->rta_id)
+ fprintf(fp, " ipid 0x%04x", ci->rta_id);
+ if (ci->rta_ts || ci->rta_tsage)
+ fprintf(fp, " ts 0x%x tsage %dsec",
+ ci->rta_ts, ci->rta_tsage);
+ }
+ } else if (r->rtm_family == AF_INET6) {
+ struct rta_cacheinfo *ci = NULL;
+ if (tb[RTA_CACHEINFO])
+ ci = RTA_DATA(tb[RTA_CACHEINFO]);
+ if ((r->rtm_flags & RTM_F_CLONED) || (ci && ci->rta_expires)) {
+ if (!hz)
+ hz = get_user_hz();
+ if (r->rtm_flags & RTM_F_CLONED)
+ fprintf(fp, "%s cache ", _SL_);
+ if (ci->rta_expires)
+ fprintf(fp, " expires %dsec", ci->rta_expires/hz);
+ if (ci->rta_error != 0)
+ fprintf(fp, " error %d", ci->rta_error);
+ if (show_stats) {
+ if (ci->rta_clntref)
+ fprintf(fp, " users %d", ci->rta_clntref);
+ if (ci->rta_used != 0)
+ fprintf(fp, " used %d", ci->rta_used);
+ if (ci->rta_lastuse != 0)
+ fprintf(fp, " age %dsec", ci->rta_lastuse/hz);
+ }
+ } else if (ci) {
+ if (ci->rta_error != 0)
+ fprintf(fp, " error %d", ci->rta_error);
+ }
+ }
+ if (tb[RTA_METRICS]) {
+ int i;
+ unsigned mxlock = 0;
+ struct rtattr *mxrta[RTAX_MAX+1];
+
+ parse_rtattr(mxrta, RTAX_MAX, RTA_DATA(tb[RTA_METRICS]),
+ RTA_PAYLOAD(tb[RTA_METRICS]));
+ if (mxrta[RTAX_LOCK])
+ mxlock = *(unsigned*)RTA_DATA(mxrta[RTAX_LOCK]);
+
+ for (i=2; i<= RTAX_MAX; i++) {
+ __u32 val;
+
+ if (mxrta[i] == NULL)
+ continue;
+
+ if (i != RTAX_CC_ALGO)
+ val = rta_getattr_u32(mxrta[i]);
+
+ if (i == RTAX_HOPLIMIT && (int)val == -1)
+ continue;
+
+ if (i < sizeof(mx_names)/sizeof(char*) && mx_names[i])
+ fprintf(fp, " %s", mx_names[i]);
+ else
+ fprintf(fp, " metric %d", i);
+
+ if (mxlock & (1<<i))
+ fprintf(fp, " lock");
+
+ switch (i) {
+ case RTAX_FEATURES:
+ print_rtax_features(fp, val);
+ break;
+ default:
+ fprintf(fp, " %u", val);
+ break;
+
+ case RTAX_RTT:
+ case RTAX_RTTVAR:
+ case RTAX_RTO_MIN:
+ if (i == RTAX_RTT)
+ val /= 8;
+ else if (i == RTAX_RTTVAR)
+ val /= 4;
+
+ if (val >= 1000)
+ fprintf(fp, " %gs", val/1e3);
+ else
+ fprintf(fp, " %ums", val);
+ break;
+ case RTAX_CC_ALGO:
+ fprintf(fp, " %s", rta_getattr_str(mxrta[i]));
+ break;
+ }
+ }
+ }
+ if (tb[RTA_IIF] && filter.iifmask != -1) {
+ fprintf(fp, " iif %s", ll_index_to_name(*(int*)RTA_DATA(tb[RTA_IIF])));
+ }
+ if (tb[RTA_MULTIPATH]) {
+ struct rtnexthop *nh = RTA_DATA(tb[RTA_MULTIPATH]);
+ int first = 0;
+
+ len = RTA_PAYLOAD(tb[RTA_MULTIPATH]);
+
+ for (;;) {
+ if (len < sizeof(*nh))
+ break;
+ if (nh->rtnh_len > len)
+ break;
+ if (r->rtm_flags&RTM_F_CLONED && r->rtm_type == RTN_MULTICAST) {
+ if (first)
+ fprintf(fp, " Oifs:");
+ else
+ fprintf(fp, " ");
+ } else
+ fprintf(fp, "%s\tnexthop", _SL_);
+ if (nh->rtnh_len > sizeof(*nh)) {
+ parse_rtattr(tb, RTA_MAX, RTNH_DATA(nh), nh->rtnh_len - sizeof(*nh));
+
+ if (tb[RTA_ENCAP])
+ lwt_print_encap(fp,
+ tb[RTA_ENCAP_TYPE],
+ tb[RTA_ENCAP]);
+
+ if (tb[RTA_GATEWAY]) {
+ fprintf(fp, " via %s ",
+ format_host(r->rtm_family,
+ RTA_PAYLOAD(tb[RTA_GATEWAY]),
+ RTA_DATA(tb[RTA_GATEWAY]),
+ abuf, sizeof(abuf)));
+ }
+ if (tb[RTA_VIA]) {
+ size_t len = RTA_PAYLOAD(tb[RTA_VIA]) - 2;
+ struct rtvia *via = RTA_DATA(tb[RTA_VIA]);
+ fprintf(fp, "via %s %s ",
+ family_name(via->rtvia_family),
+ format_host(via->rtvia_family, len, via->rtvia_addr,
+ abuf, sizeof(abuf)));
+ }
+ if (tb[RTA_FLOW]) {
+ __u32 to = rta_getattr_u32(tb[RTA_FLOW]);
+ __u32 from = to>>16;
+ to &= 0xFFFF;
+ fprintf(fp, " realm%s ", from ? "s" : "");
+ if (from) {
+ fprintf(fp, "%s/",
+ rtnl_rtrealm_n2a(from, b1, sizeof(b1)));
+ }
+ fprintf(fp, "%s",
+ rtnl_rtrealm_n2a(to, b1, sizeof(b1)));
+ }
+ }
+ if (r->rtm_flags&RTM_F_CLONED && r->rtm_type == RTN_MULTICAST) {
+ fprintf(fp, " %s", ll_index_to_name(nh->rtnh_ifindex));
+ if (nh->rtnh_hops != 1)
+ fprintf(fp, "(ttl>%d)", nh->rtnh_hops);
+ } else {
+ fprintf(fp, " dev %s", ll_index_to_name(nh->rtnh_ifindex));
+ fprintf(fp, " weight %d", nh->rtnh_hops+1);
+ }
+ if (nh->rtnh_flags & RTNH_F_DEAD)
+ fprintf(fp, " dead");
+ if (nh->rtnh_flags & RTNH_F_ONLINK)
+ fprintf(fp, " onlink");
+ if (nh->rtnh_flags & RTNH_F_PERVASIVE)
+ fprintf(fp, " pervasive");
+ if (nh->rtnh_flags & RTNH_F_LINKDOWN)
+ fprintf(fp, " linkdown");
+ len -= NLMSG_ALIGN(nh->rtnh_len);
+ nh = RTNH_NEXT(nh);
+ }
+ }
+ if (tb[RTA_PREF]) {
+ unsigned int pref = rta_getattr_u8(tb[RTA_PREF]);
+ fprintf(fp, " pref ");
+
+ switch (pref) {
+ case ICMPV6_ROUTER_PREF_LOW:
+ fprintf(fp, "low");
+ break;
+ case ICMPV6_ROUTER_PREF_MEDIUM:
+ fprintf(fp, "medium");
+ break;
+ case ICMPV6_ROUTER_PREF_HIGH:
+ fprintf(fp, "high");
+ break;
+ default:
+ fprintf(fp, "%u", pref);
+ }
+ }
+ fprintf(fp, "\n");
+ fflush(fp);
+ return 0;
+}
+
+static int parse_one_nh(struct nlmsghdr *n, struct rtmsg *r,
+ struct rtattr *rta, struct rtnexthop *rtnh,
+ int *argcp, char ***argvp)
+{
+ int argc = *argcp;
+ char **argv = *argvp;
+
+ while (++argv, --argc > 0) {
+ if (strcmp(*argv, "via") == 0) {
+ inet_prefix addr;
+ int family;
+ NEXT_ARG();
+ family = read_family(*argv);
+ if (family == AF_UNSPEC)
+ family = r->rtm_family;
+ else
+ NEXT_ARG();
+ get_addr(&addr, *argv, family);
+ if (r->rtm_family == AF_UNSPEC)
+ r->rtm_family = addr.family;
+ if (addr.family == r->rtm_family) {
+ rta_addattr_l(rta, 4096, RTA_GATEWAY, &addr.data, addr.bytelen);
+ rtnh->rtnh_len += sizeof(struct rtattr) + addr.bytelen;
+ } else {
+ rta_addattr_l(rta, 4096, RTA_VIA, &addr.family, addr.bytelen+2);
+ rtnh->rtnh_len += sizeof(struct rtattr) + addr.bytelen+2;
+ }
+ } else if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ if ((rtnh->rtnh_ifindex = ll_name_to_index(*argv)) == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", *argv);
+ exit(1);
+ }
+ } else if (strcmp(*argv, "weight") == 0) {
+ unsigned w;
+ NEXT_ARG();
+ if (get_unsigned(&w, *argv, 0) || w == 0 || w > 256)
+ invarg("\"weight\" is invalid\n", *argv);
+ rtnh->rtnh_hops = w - 1;
+ } else if (strcmp(*argv, "onlink") == 0) {
+ rtnh->rtnh_flags |= RTNH_F_ONLINK;
+ } else if (matches(*argv, "realms") == 0) {
+ __u32 realm;
+ NEXT_ARG();
+ if (get_rt_realms_or_raw(&realm, *argv))
+ invarg("\"realm\" value is invalid\n", *argv);
+ rta_addattr32(rta, 4096, RTA_FLOW, realm);
+ rtnh->rtnh_len += sizeof(struct rtattr) + 4;
+ } else if (strcmp(*argv, "encap") == 0) {
+ int len = rta->rta_len;
+
+ lwt_parse_encap(rta, 4096, &argc, &argv);
+ rtnh->rtnh_len += rta->rta_len - len;
+ } else
+ break;
+ }
+ *argcp = argc;
+ *argvp = argv;
+ return 0;
+}
+
+static int parse_nexthops(struct nlmsghdr *n, struct rtmsg *r,
+ int argc, char **argv)
+{
+ char buf[1024];
+ struct rtattr *rta = (void*)buf;
+ struct rtnexthop *rtnh;
+
+ rta->rta_type = RTA_MULTIPATH;
+ rta->rta_len = RTA_LENGTH(0);
+ rtnh = RTA_DATA(rta);
+
+ while (argc > 0) {
+ if (strcmp(*argv, "nexthop") != 0) {
+ fprintf(stderr, "Error: \"nexthop\" or end of line is expected instead of \"%s\"\n", *argv);
+ exit(-1);
+ }
+ if (argc <= 1) {
+ fprintf(stderr, "Error: unexpected end of line after \"nexthop\"\n");
+ exit(-1);
+ }
+ memset(rtnh, 0, sizeof(*rtnh));
+ rtnh->rtnh_len = sizeof(*rtnh);
+ rta->rta_len += rtnh->rtnh_len;
+ parse_one_nh(n, r, rta, rtnh, &argc, &argv);
+ rtnh = RTNH_NEXT(rtnh);
+ }
+
+ if (rta->rta_len > RTA_LENGTH(0))
+ addattr_l(n, 1024, RTA_MULTIPATH, RTA_DATA(rta), RTA_PAYLOAD(rta));
+ return 0;
+}
+
+static int iproute_modify(int cmd, unsigned flags, int argc, char **argv)
+{
+ struct {
+ struct nlmsghdr n;
+ struct rtmsg r;
+ char buf[1024];
+ } req;
+ char mxbuf[256];
+ struct rtattr * mxrta = (void*)mxbuf;
+ unsigned mxlock = 0;
+ char *d = NULL;
+ int gw_ok = 0;
+ int dst_ok = 0;
+ int nhs_ok = 0;
+ int scope_ok = 0;
+ int table_ok = 0;
+ int raw = 0;
+ int type_ok = 0;
+ static int hz;
+
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct rtmsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST|flags;
+ req.n.nlmsg_type = cmd;
+ req.r.rtm_family = preferred_family;
+ req.r.rtm_table = RT_TABLE_MAIN;
+ req.r.rtm_scope = RT_SCOPE_NOWHERE;
+
+ if (cmd != RTM_DELROUTE) {
+ req.r.rtm_protocol = RTPROT_BOOT;
+ req.r.rtm_scope = RT_SCOPE_UNIVERSE;
+ req.r.rtm_type = RTN_UNICAST;
+ }
+
+ mxrta->rta_type = RTA_METRICS;
+ mxrta->rta_len = RTA_LENGTH(0);
+
+ while (argc > 0) {
+ if (strcmp(*argv, "src") == 0) {
+ inet_prefix addr;
+ NEXT_ARG();
+ get_addr(&addr, *argv, req.r.rtm_family);
+ if (req.r.rtm_family == AF_UNSPEC)
+ req.r.rtm_family = addr.family;
+ addattr_l(&req.n, sizeof(req), RTA_PREFSRC, &addr.data, addr.bytelen);
+ } else if (strcmp(*argv, "as") == 0) {
+ inet_prefix addr;
+ NEXT_ARG();
+ if (strcmp(*argv, "to") == 0) {
+ NEXT_ARG();
+ }
+ get_addr(&addr, *argv, req.r.rtm_family);
+ if (req.r.rtm_family == AF_UNSPEC)
+ req.r.rtm_family = addr.family;
+ addattr_l(&req.n, sizeof(req), RTA_NEWDST, &addr.data, addr.bytelen);
+ } else if (strcmp(*argv, "via") == 0) {
+ inet_prefix addr;
+ int family;
+ gw_ok = 1;
+ NEXT_ARG();
+ family = read_family(*argv);
+ if (family == AF_UNSPEC)
+ family = req.r.rtm_family;
+ else
+ NEXT_ARG();
+ get_addr(&addr, *argv, family);
+ if (req.r.rtm_family == AF_UNSPEC)
+ req.r.rtm_family = addr.family;
+ if (addr.family == req.r.rtm_family)
+ addattr_l(&req.n, sizeof(req), RTA_GATEWAY, &addr.data, addr.bytelen);
+ else
+ addattr_l(&req.n, sizeof(req), RTA_VIA, &addr.family, addr.bytelen+2);
+ } else if (strcmp(*argv, "from") == 0) {
+ inet_prefix addr;
+ NEXT_ARG();
+ get_prefix(&addr, *argv, req.r.rtm_family);
+ if (req.r.rtm_family == AF_UNSPEC)
+ req.r.rtm_family = addr.family;
+ if (addr.bytelen)
+ addattr_l(&req.n, sizeof(req), RTA_SRC, &addr.data, addr.bytelen);
+ req.r.rtm_src_len = addr.bitlen;
+ } else if (strcmp(*argv, "tos") == 0 ||
+ matches(*argv, "dsfield") == 0) {
+ __u32 tos;
+ NEXT_ARG();
+ if (rtnl_dsfield_a2n(&tos, *argv))
+ invarg("\"tos\" value is invalid\n", *argv);
+ req.r.rtm_tos = tos;
+ } else if (strcmp(*argv, "expires") == 0 ) {
+ __u32 expires;
+ NEXT_ARG();
+ if (get_u32(&expires, *argv, 0))
+ invarg("\"expires\" value is invalid\n", *argv);
+ if (!hz)
+ hz = get_user_hz();
+ addattr32(&req.n, sizeof(req), RTA_EXPIRES, expires*hz);
+ } else if (matches(*argv, "metric") == 0 ||
+ matches(*argv, "priority") == 0 ||
+ strcmp(*argv, "preference") == 0) {
+ __u32 metric;
+ NEXT_ARG();
+ if (get_u32(&metric, *argv, 0))
+ invarg("\"metric\" value is invalid\n", *argv);
+ addattr32(&req.n, sizeof(req), RTA_PRIORITY, metric);
+ } else if (strcmp(*argv, "scope") == 0) {
+ __u32 scope = 0;
+ NEXT_ARG();
+ if (rtnl_rtscope_a2n(&scope, *argv))
+ invarg("invalid \"scope\" value\n", *argv);
+ req.r.rtm_scope = scope;
+ scope_ok = 1;
+ } else if (strcmp(*argv, "mtu") == 0) {
+ unsigned mtu;
+ NEXT_ARG();
+ if (strcmp(*argv, "lock") == 0) {
+ mxlock |= (1<<RTAX_MTU);
+ NEXT_ARG();
+ }
+ if (get_unsigned(&mtu, *argv, 0))
+ invarg("\"mtu\" value is invalid\n", *argv);
+ rta_addattr32(mxrta, sizeof(mxbuf), RTAX_MTU, mtu);
+ } else if (strcmp(*argv, "hoplimit") == 0) {
+ unsigned hoplimit;
+ NEXT_ARG();
+ if (strcmp(*argv, "lock") == 0) {
+ mxlock |= (1<<RTAX_HOPLIMIT);
+ NEXT_ARG();
+ }
+ if (get_unsigned(&hoplimit, *argv, 0) || hoplimit > 255)
+ invarg("\"hoplimit\" value is invalid\n", *argv);
+ rta_addattr32(mxrta, sizeof(mxbuf), RTAX_HOPLIMIT, hoplimit);
+ } else if (strcmp(*argv, "advmss") == 0) {
+ unsigned mss;
+ NEXT_ARG();
+ if (strcmp(*argv, "lock") == 0) {
+ mxlock |= (1<<RTAX_ADVMSS);
+ NEXT_ARG();
+ }
+ if (get_unsigned(&mss, *argv, 0))
+ invarg("\"mss\" value is invalid\n", *argv);
+ rta_addattr32(mxrta, sizeof(mxbuf), RTAX_ADVMSS, mss);
+ } else if (matches(*argv, "reordering") == 0) {
+ unsigned reord;
+ NEXT_ARG();
+ if (strcmp(*argv, "lock") == 0) {
+ mxlock |= (1<<RTAX_REORDERING);
+ NEXT_ARG();
+ }
+ if (get_unsigned(&reord, *argv, 0))
+ invarg("\"reordering\" value is invalid\n", *argv);
+ rta_addattr32(mxrta, sizeof(mxbuf), RTAX_REORDERING, reord);
+ } else if (strcmp(*argv, "rtt") == 0) {
+ unsigned rtt;
+ NEXT_ARG();
+ if (strcmp(*argv, "lock") == 0) {
+ mxlock |= (1<<RTAX_RTT);
+ NEXT_ARG();
+ }
+ if (get_time_rtt(&rtt, *argv, &raw))
+ invarg("\"rtt\" value is invalid\n", *argv);
+ rta_addattr32(mxrta, sizeof(mxbuf), RTAX_RTT,
+ (raw) ? rtt : rtt * 8);
+ } else if (strcmp(*argv, "rto_min") == 0) {
+ unsigned rto_min;
+ NEXT_ARG();
+ mxlock |= (1<<RTAX_RTO_MIN);
+ if (get_time_rtt(&rto_min, *argv, &raw))
+ invarg("\"rto_min\" value is invalid\n",
+ *argv);
+ rta_addattr32(mxrta, sizeof(mxbuf), RTAX_RTO_MIN,
+ rto_min);
+ } else if (matches(*argv, "window") == 0) {
+ unsigned win;
+ NEXT_ARG();
+ if (strcmp(*argv, "lock") == 0) {
+ mxlock |= (1<<RTAX_WINDOW);
+ NEXT_ARG();
+ }
+ if (get_unsigned(&win, *argv, 0))
+ invarg("\"window\" value is invalid\n", *argv);
+ rta_addattr32(mxrta, sizeof(mxbuf), RTAX_WINDOW, win);
+ } else if (matches(*argv, "cwnd") == 0) {
+ unsigned win;
+ NEXT_ARG();
+ if (strcmp(*argv, "lock") == 0) {
+ mxlock |= (1<<RTAX_CWND);
+ NEXT_ARG();
+ }
+ if (get_unsigned(&win, *argv, 0))
+ invarg("\"cwnd\" value is invalid\n", *argv);
+ rta_addattr32(mxrta, sizeof(mxbuf), RTAX_CWND, win);
+ } else if (matches(*argv, "initcwnd") == 0) {
+ unsigned win;
+ NEXT_ARG();
+ if (strcmp(*argv, "lock") == 0) {
+ mxlock |= (1<<RTAX_INITCWND);
+ NEXT_ARG();
+ }
+ if (get_unsigned(&win, *argv, 0))
+ invarg("\"initcwnd\" value is invalid\n", *argv);
+ rta_addattr32(mxrta, sizeof(mxbuf), RTAX_INITCWND, win);
+ } else if (matches(*argv, "initrwnd") == 0) {
+ unsigned win;
+ NEXT_ARG();
+ if (strcmp(*argv, "lock") == 0) {
+ mxlock |= (1<<RTAX_INITRWND);
+ NEXT_ARG();
+ }
+ if (get_unsigned(&win, *argv, 0))
+ invarg("\"initrwnd\" value is invalid\n", *argv);
+ rta_addattr32(mxrta, sizeof(mxbuf), RTAX_INITRWND, win);
+ } else if (matches(*argv, "features") == 0) {
+ unsigned int features = 0;
+
+ while (argc > 0) {
+ NEXT_ARG();
+
+ if (strcmp(*argv, "ecn") == 0)
+ features |= RTAX_FEATURE_ECN;
+ else
+ invarg("\"features\" value not valid\n", *argv);
+ break;
+ }
+
+ rta_addattr32(mxrta, sizeof(mxbuf), RTAX_FEATURES, features);
+ } else if (matches(*argv, "quickack") == 0) {
+ unsigned quickack;
+ NEXT_ARG();
+ if (get_unsigned(&quickack, *argv, 0))
+ invarg("\"quickack\" value is invalid\n", *argv);
+ if (quickack != 1 && quickack != 0)
+ invarg("\"quickack\" value should be 0 or 1\n", *argv);
+ rta_addattr32(mxrta, sizeof(mxbuf), RTAX_QUICKACK, quickack);
+ } else if (matches(*argv, "congctl") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "lock") == 0) {
+ mxlock |= 1 << RTAX_CC_ALGO;
+ NEXT_ARG();
+ }
+ rta_addattr_l(mxrta, sizeof(mxbuf), RTAX_CC_ALGO, *argv,
+ strlen(*argv));
+ } else if (matches(*argv, "rttvar") == 0) {
+ unsigned win;
+ NEXT_ARG();
+ if (strcmp(*argv, "lock") == 0) {
+ mxlock |= (1<<RTAX_RTTVAR);
+ NEXT_ARG();
+ }
+ if (get_time_rtt(&win, *argv, &raw))
+ invarg("\"rttvar\" value is invalid\n", *argv);
+ rta_addattr32(mxrta, sizeof(mxbuf), RTAX_RTTVAR,
+ (raw) ? win : win * 4);
+ } else if (matches(*argv, "ssthresh") == 0) {
+ unsigned win;
+ NEXT_ARG();
+ if (strcmp(*argv, "lock") == 0) {
+ mxlock |= (1<<RTAX_SSTHRESH);
+ NEXT_ARG();
+ }
+ if (get_unsigned(&win, *argv, 0))
+ invarg("\"ssthresh\" value is invalid\n", *argv);
+ rta_addattr32(mxrta, sizeof(mxbuf), RTAX_SSTHRESH, win);
+ } else if (matches(*argv, "realms") == 0) {
+ __u32 realm;
+ NEXT_ARG();
+ if (get_rt_realms_or_raw(&realm, *argv))
+ invarg("\"realm\" value is invalid\n", *argv);
+ addattr32(&req.n, sizeof(req), RTA_FLOW, realm);
+ } else if (strcmp(*argv, "onlink") == 0) {
+ req.r.rtm_flags |= RTNH_F_ONLINK;
+ } else if (strcmp(*argv, "nexthop") == 0) {
+ nhs_ok = 1;
+ break;
+ } else if (matches(*argv, "protocol") == 0) {
+ __u32 prot;
+ NEXT_ARG();
+ if (rtnl_rtprot_a2n(&prot, *argv))
+ invarg("\"protocol\" value is invalid\n", *argv);
+ req.r.rtm_protocol = prot;
+ } else if (matches(*argv, "table") == 0) {
+ __u32 tid;
+ NEXT_ARG();
+ if (rtnl_rttable_a2n(&tid, *argv))
+ invarg("\"table\" value is invalid\n", *argv);
+ if (tid < 256)
+ req.r.rtm_table = tid;
+ else {
+ req.r.rtm_table = RT_TABLE_UNSPEC;
+ addattr32(&req.n, sizeof(req), RTA_TABLE, tid);
+ }
+ table_ok = 1;
+ } else if (strcmp(*argv, "dev") == 0 ||
+ strcmp(*argv, "oif") == 0) {
+ NEXT_ARG();
+ d = *argv;
+ } else if (matches(*argv, "pref") == 0) {
+ __u8 pref;
+ NEXT_ARG();
+ if (strcmp(*argv, "low") == 0)
+ pref = ICMPV6_ROUTER_PREF_LOW;
+ else if (strcmp(*argv, "medium") == 0)
+ pref = ICMPV6_ROUTER_PREF_MEDIUM;
+ else if (strcmp(*argv, "high") == 0)
+ pref = ICMPV6_ROUTER_PREF_HIGH;
+ else if (get_u8(&pref, *argv, 0))
+ invarg("\"pref\" value is invalid\n", *argv);
+ addattr8(&req.n, sizeof(req), RTA_PREF, pref);
+ } else if (strcmp(*argv, "encap") == 0) {
+ char buf[1024];
+ struct rtattr *rta = (void*)buf;
+
+ rta->rta_type = RTA_ENCAP;
+ rta->rta_len = RTA_LENGTH(0);
+
+ lwt_parse_encap(rta, sizeof(buf), &argc, &argv);
+
+ if (rta->rta_len > RTA_LENGTH(0))
+ addraw_l(&req.n, 1024, RTA_DATA(rta), RTA_PAYLOAD(rta));
+ } else {
+ int type;
+ inet_prefix dst;
+
+ if (strcmp(*argv, "to") == 0) {
+ NEXT_ARG();
+ }
+ if ((**argv < '0' || **argv > '9') &&
+ rtnl_rtntype_a2n(&type, *argv) == 0) {
+ NEXT_ARG();
+ req.r.rtm_type = type;
+ type_ok = 1;
+ }
+
+ if (matches(*argv, "help") == 0)
+ usage();
+ if (dst_ok)
+ duparg2("to", *argv);
+ get_prefix(&dst, *argv, req.r.rtm_family);
+ if (req.r.rtm_family == AF_UNSPEC)
+ req.r.rtm_family = dst.family;
+ req.r.rtm_dst_len = dst.bitlen;
+ dst_ok = 1;
+ if (dst.bytelen)
+ addattr_l(&req.n, sizeof(req), RTA_DST, &dst.data, dst.bytelen);
+ }
+ argc--; argv++;
+ }
+
+ if (!dst_ok)
+ usage();
+
+ if (d || nhs_ok) {
+ int idx;
+
+ if (d) {
+ if ((idx = ll_name_to_index(d)) == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", d);
+ return -1;
+ }
+ addattr32(&req.n, sizeof(req), RTA_OIF, idx);
+ }
+ }
+
+ if (mxrta->rta_len > RTA_LENGTH(0)) {
+ if (mxlock)
+ rta_addattr32(mxrta, sizeof(mxbuf), RTAX_LOCK, mxlock);
+ addattr_l(&req.n, sizeof(req), RTA_METRICS, RTA_DATA(mxrta), RTA_PAYLOAD(mxrta));
+ }
+
+ if (nhs_ok)
+ parse_nexthops(&req.n, &req.r, argc, argv);
+
+ if (req.r.rtm_family == AF_UNSPEC)
+ req.r.rtm_family = AF_INET;
+
+ if (!table_ok) {
+ if (req.r.rtm_type == RTN_LOCAL ||
+ req.r.rtm_type == RTN_BROADCAST ||
+ req.r.rtm_type == RTN_NAT ||
+ req.r.rtm_type == RTN_ANYCAST)
+ req.r.rtm_table = RT_TABLE_LOCAL;
+ }
+ if (!scope_ok) {
+ if (req.r.rtm_family == AF_INET6 ||
+ req.r.rtm_family == AF_MPLS)
+ req.r.rtm_scope = RT_SCOPE_UNIVERSE;
+ else if (req.r.rtm_type == RTN_LOCAL ||
+ req.r.rtm_type == RTN_NAT)
+ req.r.rtm_scope = RT_SCOPE_HOST;
+ else if (req.r.rtm_type == RTN_BROADCAST ||
+ req.r.rtm_type == RTN_MULTICAST ||
+ req.r.rtm_type == RTN_ANYCAST)
+ req.r.rtm_scope = RT_SCOPE_LINK;
+ else if (req.r.rtm_type == RTN_UNICAST ||
+ req.r.rtm_type == RTN_UNSPEC) {
+ if (cmd == RTM_DELROUTE)
+ req.r.rtm_scope = RT_SCOPE_NOWHERE;
+ else if (!gw_ok && !nhs_ok)
+ req.r.rtm_scope = RT_SCOPE_LINK;
+ }
+ }
+
+ if (!type_ok && req.r.rtm_family == AF_MPLS)
+ req.r.rtm_type = RTN_UNICAST;
+
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ return -2;
+
+ return 0;
+}
+
+static int rtnl_rtcache_request(struct rtnl_handle *rth, int family)
+{
+ struct {
+ struct nlmsghdr nlh;
+ struct rtmsg rtm;
+ } req;
+ struct sockaddr_nl nladdr;
+
+ memset(&nladdr, 0, sizeof(nladdr));
+ memset(&req, 0, sizeof(req));
+ nladdr.nl_family = AF_NETLINK;
+
+ req.nlh.nlmsg_len = sizeof(req);
+ req.nlh.nlmsg_type = RTM_GETROUTE;
+ req.nlh.nlmsg_flags = NLM_F_ROOT|NLM_F_REQUEST;
+ req.nlh.nlmsg_pid = 0;
+ req.nlh.nlmsg_seq = rth->dump = ++rth->seq;
+ req.rtm.rtm_family = family;
+ req.rtm.rtm_flags |= RTM_F_CLONED;
+
+ return sendto(rth->fd, (void*)&req, sizeof(req), 0, (struct sockaddr*)&nladdr, sizeof(nladdr));
+}
+
+static int iproute_flush_cache(void)
+{
+#define ROUTE_FLUSH_PATH "/proc/sys/net/ipv4/route/flush"
+
+ int len;
+ int flush_fd = open (ROUTE_FLUSH_PATH, O_WRONLY);
+ char *buffer = "-1";
+
+ if (flush_fd < 0) {
+ fprintf (stderr, "Cannot open \"%s\": %s\n",
+ ROUTE_FLUSH_PATH, strerror(errno));
+ return -1;
+ }
+
+ len = strlen (buffer);
+
+ if ((write (flush_fd, (void *)buffer, len)) < len) {
+ fprintf (stderr, "Cannot flush routing cache\n");
+ close(flush_fd);
+ return -1;
+ }
+ close(flush_fd);
+ return 0;
+}
+
+static __u32 route_dump_magic = 0x45311224;
+
+static int save_route(const struct sockaddr_nl *who, struct nlmsghdr *n,
+ void *arg)
+{
+ int ret;
+ int len = n->nlmsg_len;
+ struct rtmsg *r = NLMSG_DATA(n);
+ struct rtattr *tb[RTA_MAX+1];
+ int host_len;
+
+ host_len = af_bit_len(r->rtm_family);
+ len -= NLMSG_LENGTH(sizeof(*r));
+ parse_rtattr(tb, RTA_MAX, RTM_RTA(r), len);
+
+ if (!filter_nlmsg(n, tb, host_len))
+ return 0;
+
+ ret = write(STDOUT_FILENO, n, n->nlmsg_len);
+ if ((ret > 0) && (ret != n->nlmsg_len)) {
+ fprintf(stderr, "Short write while saving nlmsg\n");
+ ret = -EIO;
+ }
+
+ return ret == n->nlmsg_len ? 0 : ret;
+}
+
+static int save_route_prep(void)
+{
+ int ret;
+
+ if (isatty(STDOUT_FILENO)) {
+ fprintf(stderr, "Not sending a binary stream to stdout\n");
+ return -1;
+ }
+
+ ret = write(STDOUT_FILENO, &route_dump_magic, sizeof(route_dump_magic));
+ if (ret != sizeof(route_dump_magic)) {
+ fprintf(stderr, "Can't write magic to dump file\n");
+ return -1;
+ }
+
+ return 0;
+}
+
+static int iproute_list_flush_or_save(int argc, char **argv, int action)
+{
+ int do_ipv6 = preferred_family;
+ char *id = NULL;
+ char *od = NULL;
+ unsigned int mark = 0;
+ rtnl_filter_t filter_fn;
+
+ if (action == IPROUTE_SAVE) {
+ if (save_route_prep())
+ return -1;
+
+ filter_fn = save_route;
+ } else
+ filter_fn = print_route;
+
+ iproute_reset_filter(0);
+ filter.tb = RT_TABLE_MAIN;
+
+ if ((action == IPROUTE_FLUSH) && argc <= 0) {
+ fprintf(stderr, "\"ip route flush\" requires arguments.\n");
+ return -1;
+ }
+
+ while (argc > 0) {
+ if (matches(*argv, "table") == 0) {
+ __u32 tid;
+ NEXT_ARG();
+ if (rtnl_rttable_a2n(&tid, *argv)) {
+ if (strcmp(*argv, "all") == 0) {
+ filter.tb = 0;
+ } else if (strcmp(*argv, "cache") == 0) {
+ filter.cloned = 1;
+ } else if (strcmp(*argv, "help") == 0) {
+ usage();
+ } else {
+ invarg("table id value is invalid\n", *argv);
+ }
+ } else
+ filter.tb = tid;
+ } else if (matches(*argv, "cached") == 0 ||
+ matches(*argv, "cloned") == 0) {
+ filter.cloned = 1;
+ } else if (strcmp(*argv, "tos") == 0 ||
+ matches(*argv, "dsfield") == 0) {
+ __u32 tos;
+ NEXT_ARG();
+ if (rtnl_dsfield_a2n(&tos, *argv))
+ invarg("TOS value is invalid\n", *argv);
+ filter.tos = tos;
+ filter.tosmask = -1;
+ } else if (matches(*argv, "protocol") == 0) {
+ __u32 prot = 0;
+ NEXT_ARG();
+ filter.protocolmask = -1;
+ if (rtnl_rtprot_a2n(&prot, *argv)) {
+ if (strcmp(*argv, "all") != 0)
+ invarg("invalid \"protocol\"\n", *argv);
+ prot = 0;
+ filter.protocolmask = 0;
+ }
+ filter.protocol = prot;
+ } else if (matches(*argv, "scope") == 0) {
+ __u32 scope = 0;
+ NEXT_ARG();
+ filter.scopemask = -1;
+ if (rtnl_rtscope_a2n(&scope, *argv)) {
+ if (strcmp(*argv, "all") != 0)
+ invarg("invalid \"scope\"\n", *argv);
+ scope = RT_SCOPE_NOWHERE;
+ filter.scopemask = 0;
+ }
+ filter.scope = scope;
+ } else if (matches(*argv, "type") == 0) {
+ int type;
+ NEXT_ARG();
+ filter.typemask = -1;
+ if (rtnl_rtntype_a2n(&type, *argv))
+ invarg("node type value is invalid\n", *argv);
+ filter.type = type;
+ } else if (strcmp(*argv, "dev") == 0 ||
+ strcmp(*argv, "oif") == 0) {
+ NEXT_ARG();
+ od = *argv;
+ } else if (strcmp(*argv, "iif") == 0) {
+ NEXT_ARG();
+ id = *argv;
+ } else if (strcmp(*argv, "mark") == 0) {
+ NEXT_ARG();
+ get_unsigned(&mark, *argv, 0);
+ filter.markmask = -1;
+ } else if (strcmp(*argv, "via") == 0) {
+ int family;
+ NEXT_ARG();
+ family = read_family(*argv);
+ if (family == AF_UNSPEC)
+ family = do_ipv6;
+ else
+ NEXT_ARG();
+ get_prefix(&filter.rvia, *argv, family);
+ } else if (strcmp(*argv, "src") == 0) {
+ NEXT_ARG();
+ get_prefix(&filter.rprefsrc, *argv, do_ipv6);
+ } else if (matches(*argv, "realms") == 0) {
+ __u32 realm;
+ NEXT_ARG();
+ if (get_rt_realms_or_raw(&realm, *argv))
+ invarg("invalid realms\n", *argv);
+ filter.realm = realm;
+ filter.realmmask = ~0U;
+ if ((filter.realm&0xFFFF) == 0 &&
+ (*argv)[strlen(*argv) - 1] == '/')
+ filter.realmmask &= ~0xFFFF;
+ if ((filter.realm&0xFFFF0000U) == 0 &&
+ (strchr(*argv, '/') == NULL ||
+ (*argv)[0] == '/'))
+ filter.realmmask &= ~0xFFFF0000U;
+ } else if (matches(*argv, "from") == 0) {
+ NEXT_ARG();
+ if (matches(*argv, "root") == 0) {
+ NEXT_ARG();
+ get_prefix(&filter.rsrc, *argv, do_ipv6);
+ } else if (matches(*argv, "match") == 0) {
+ NEXT_ARG();
+ get_prefix(&filter.msrc, *argv, do_ipv6);
+ } else {
+ if (matches(*argv, "exact") == 0) {
+ NEXT_ARG();
+ }
+ get_prefix(&filter.msrc, *argv, do_ipv6);
+ filter.rsrc = filter.msrc;
+ }
+ } else {
+ if (matches(*argv, "to") == 0) {
+ NEXT_ARG();
+ }
+ if (matches(*argv, "root") == 0) {
+ NEXT_ARG();
+ get_prefix(&filter.rdst, *argv, do_ipv6);
+ } else if (matches(*argv, "match") == 0) {
+ NEXT_ARG();
+ get_prefix(&filter.mdst, *argv, do_ipv6);
+ } else {
+ if (matches(*argv, "exact") == 0) {
+ NEXT_ARG();
+ }
+ get_prefix(&filter.mdst, *argv, do_ipv6);
+ filter.rdst = filter.mdst;
+ }
+ }
+ argc--; argv++;
+ }
+
+ if (do_ipv6 == AF_UNSPEC && filter.tb)
+ do_ipv6 = AF_INET;
+
+ if (id || od) {
+ int idx;
+
+ if (id) {
+ if ((idx = ll_name_to_index(id)) == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", id);
+ return -1;
+ }
+ filter.iif = idx;
+ filter.iifmask = -1;
+ }
+ if (od) {
+ if ((idx = ll_name_to_index(od)) == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", od);
+ return -1;
+ }
+ filter.oif = idx;
+ filter.oifmask = -1;
+ }
+ }
+ filter.mark = mark;
+
+ if (action == IPROUTE_FLUSH) {
+ int round = 0;
+ char flushb[4096-512];
+ time_t start = time(0);
+
+ if (filter.cloned) {
+ if (do_ipv6 != AF_INET6) {
+ iproute_flush_cache();
+ if (show_stats)
+ printf("*** IPv4 routing cache is flushed.\n");
+ }
+ if (do_ipv6 == AF_INET)
+ return 0;
+ }
+
+ filter.flushb = flushb;
+ filter.flushp = 0;
+ filter.flushe = sizeof(flushb);
+
+ for (;;) {
+ if (rtnl_wilddump_request(&rth, do_ipv6, RTM_GETROUTE) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+ filter.flushed = 0;
+ if (rtnl_dump_filter(&rth, filter_fn, stdout) < 0) {
+ fprintf(stderr, "Flush terminated\n");
+ exit(1);
+ }
+ if (filter.flushed == 0) {
+ if (show_stats) {
+ if (round == 0 && (!filter.cloned || do_ipv6 == AF_INET6))
+ printf("Nothing to flush.\n");
+ else
+ printf("*** Flush is complete after %d round%s ***\n", round, round>1?"s":"");
+ }
+ fflush(stdout);
+ return 0;
+ }
+ round++;
+ if (flush_update() < 0)
+ exit(1);
+
+ if (time(0) - start > 30) {
+ printf("\n*** Flush not completed after %ld seconds, %d entries remain ***\n",
+ (long)(time(0) - start), filter.flushed);
+ exit(1);
+ }
+
+ if (show_stats) {
+ printf("\n*** Round %d, deleting %d entries ***\n", round, filter.flushed);
+ fflush(stdout);
+ }
+ }
+ }
+
+ if (!filter.cloned) {
+ if (rtnl_wilddump_request(&rth, do_ipv6, RTM_GETROUTE) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+ } else {
+ if (rtnl_rtcache_request(&rth, do_ipv6) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+ }
+
+ if (rtnl_dump_filter(&rth, filter_fn, stdout) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ exit(1);
+ }
+
+ exit(0);
+}
+
+
+static int iproute_get(int argc, char **argv)
+{
+ struct {
+ struct nlmsghdr n;
+ struct rtmsg r;
+ char buf[1024];
+ } req;
+ char *idev = NULL;
+ char *odev = NULL;
+ int connected = 0;
+ int from_ok = 0;
+ unsigned int mark = 0;
+
+ memset(&req, 0, sizeof(req));
+
+ iproute_reset_filter(0);
+ filter.cloned = 2;
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct rtmsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = RTM_GETROUTE;
+ req.r.rtm_family = preferred_family;
+ req.r.rtm_table = 0;
+ req.r.rtm_protocol = 0;
+ req.r.rtm_scope = 0;
+ req.r.rtm_type = 0;
+ req.r.rtm_src_len = 0;
+ req.r.rtm_dst_len = 0;
+ req.r.rtm_tos = 0;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "tos") == 0 ||
+ matches(*argv, "dsfield") == 0) {
+ __u32 tos;
+ NEXT_ARG();
+ if (rtnl_dsfield_a2n(&tos, *argv))
+ invarg("TOS value is invalid\n", *argv);
+ req.r.rtm_tos = tos;
+ } else if (matches(*argv, "from") == 0) {
+ inet_prefix addr;
+ NEXT_ARG();
+ if (matches(*argv, "help") == 0)
+ usage();
+ from_ok = 1;
+ get_prefix(&addr, *argv, req.r.rtm_family);
+ if (req.r.rtm_family == AF_UNSPEC)
+ req.r.rtm_family = addr.family;
+ if (addr.bytelen)
+ addattr_l(&req.n, sizeof(req), RTA_SRC, &addr.data, addr.bytelen);
+ req.r.rtm_src_len = addr.bitlen;
+ } else if (matches(*argv, "iif") == 0) {
+ NEXT_ARG();
+ idev = *argv;
+ } else if (matches(*argv, "mark") == 0) {
+ NEXT_ARG();
+ get_unsigned(&mark, *argv, 0);
+ } else if (matches(*argv, "oif") == 0 ||
+ strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ odev = *argv;
+ } else if (matches(*argv, "uid") == 0) {
+ uid_t uid;
+ NEXT_ARG();
+ get_unsigned(&uid, *argv, 0);
+ addattr32(&req.n, sizeof(req), RTA_UID, uid);
+ } else if (matches(*argv, "notify") == 0) {
+ req.r.rtm_flags |= RTM_F_NOTIFY;
+ } else if (matches(*argv, "connected") == 0) {
+ connected = 1;
+ } else {
+ inet_prefix addr;
+ if (strcmp(*argv, "to") == 0) {
+ NEXT_ARG();
+ }
+ if (matches(*argv, "help") == 0)
+ usage();
+ get_prefix(&addr, *argv, req.r.rtm_family);
+ if (req.r.rtm_family == AF_UNSPEC)
+ req.r.rtm_family = addr.family;
+ if (addr.bytelen)
+ addattr_l(&req.n, sizeof(req), RTA_DST, &addr.data, addr.bytelen);
+ req.r.rtm_dst_len = addr.bitlen;
+ }
+ argc--; argv++;
+ }
+
+ if (req.r.rtm_dst_len == 0) {
+ fprintf(stderr, "need at least a destination address\n");
+ exit(1);
+ }
+
+ if (idev || odev) {
+ int idx;
+
+ if (idev) {
+ if ((idx = ll_name_to_index(idev)) == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", idev);
+ return -1;
+ }
+ addattr32(&req.n, sizeof(req), RTA_IIF, idx);
+ }
+ if (odev) {
+ if ((idx = ll_name_to_index(odev)) == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", odev);
+ return -1;
+ }
+ addattr32(&req.n, sizeof(req), RTA_OIF, idx);
+ }
+ }
+ if (mark)
+ addattr32(&req.n, sizeof(req), RTA_MARK, mark);
+
+ if (req.r.rtm_family == AF_UNSPEC)
+ req.r.rtm_family = AF_INET;
+
+ req.r.rtm_flags |= RTM_F_LOOKUP_TABLE;
+
+ if (rtnl_talk(&rth, &req.n, &req.n, sizeof(req)) < 0)
+ return -2;
+
+ if (connected && !from_ok) {
+ struct rtmsg *r = NLMSG_DATA(&req.n);
+ int len = req.n.nlmsg_len;
+ struct rtattr * tb[RTA_MAX+1];
+
+ if (print_route(NULL, &req.n, (void*)stdout) < 0) {
+ fprintf(stderr, "An error :-)\n");
+ exit(1);
+ }
+
+ if (req.n.nlmsg_type != RTM_NEWROUTE) {
+ fprintf(stderr, "Not a route?\n");
+ return -1;
+ }
+ len -= NLMSG_LENGTH(sizeof(*r));
+ if (len < 0) {
+ fprintf(stderr, "Wrong len %d\n", len);
+ return -1;
+ }
+
+ parse_rtattr(tb, RTA_MAX, RTM_RTA(r), len);
+
+ if (tb[RTA_PREFSRC]) {
+ tb[RTA_PREFSRC]->rta_type = RTA_SRC;
+ r->rtm_src_len = 8*RTA_PAYLOAD(tb[RTA_PREFSRC]);
+ } else if (!tb[RTA_SRC]) {
+ fprintf(stderr, "Failed to connect the route\n");
+ return -1;
+ }
+ if (!odev && tb[RTA_OIF])
+ tb[RTA_OIF]->rta_type = 0;
+ if (tb[RTA_GATEWAY])
+ tb[RTA_GATEWAY]->rta_type = 0;
+ if (tb[RTA_VIA])
+ tb[RTA_VIA]->rta_type = 0;
+ if (!idev && tb[RTA_IIF])
+ tb[RTA_IIF]->rta_type = 0;
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = RTM_GETROUTE;
+
+ if (rtnl_talk(&rth, &req.n, &req.n, sizeof(req)) < 0)
+ return -2;
+ }
+
+ if (print_route(NULL, &req.n, (void*)stdout) < 0) {
+ fprintf(stderr, "An error :-)\n");
+ return -1;
+ }
+
+ return 0;
+}
+
+static int restore_handler(const struct sockaddr_nl *nl,
+ struct rtnl_ctrl_data *ctrl,
+ struct nlmsghdr *n, void *arg)
+{
+ int ret;
+
+ n->nlmsg_flags |= NLM_F_REQUEST | NLM_F_CREATE | NLM_F_ACK;
+
+ ll_init_map(&rth);
+
+ ret = rtnl_talk(&rth, n, n, sizeof(*n));
+ if ((ret < 0) && (errno == EEXIST))
+ ret = 0;
+
+ return ret;
+}
+
+static int route_dump_check_magic(void)
+{
+ int ret;
+ __u32 magic = 0;
+
+ if (isatty(STDIN_FILENO)) {
+ fprintf(stderr, "Can't restore route dump from a terminal\n");
+ return -1;
+ }
+
+ ret = fread(&magic, sizeof(magic), 1, stdin);
+ if (magic != route_dump_magic) {
+ fprintf(stderr, "Magic mismatch (%d elems, %x magic)\n", ret, magic);
+ return -1;
+ }
+
+ return 0;
+}
+
+static int iproute_restore(void)
+{
+ if (route_dump_check_magic())
+ exit(-1);
+
+ exit(rtnl_from_file(stdin, &restore_handler, NULL));
+}
+
+static int show_handler(const struct sockaddr_nl *nl,
+ struct rtnl_ctrl_data *ctrl,
+ struct nlmsghdr *n, void *arg)
+{
+ print_route(nl, n, stdout);
+ return 0;
+}
+
+static int iproute_showdump(void)
+{
+ if (route_dump_check_magic())
+ exit(-1);
+
+ exit(rtnl_from_file(stdin, &show_handler, NULL));
+}
+
+void iproute_reset_filter(int ifindex)
+{
+ memset(&filter, 0, sizeof(filter));
+ filter.mdst.bitlen = -1;
+ filter.msrc.bitlen = -1;
+ filter.oif = ifindex;
+ if (filter.oif > 0)
+ filter.oifmask = -1;
+}
+
+int do_iproute(int argc, char **argv)
+{
+ if (argc < 1)
+ return iproute_list_flush_or_save(0, NULL, IPROUTE_LIST);
+
+ if (matches(*argv, "add") == 0)
+ return iproute_modify(RTM_NEWROUTE, NLM_F_CREATE|NLM_F_EXCL,
+ argc-1, argv+1);
+ if (matches(*argv, "change") == 0 || strcmp(*argv, "chg") == 0)
+ return iproute_modify(RTM_NEWROUTE, NLM_F_REPLACE,
+ argc-1, argv+1);
+ if (matches(*argv, "replace") == 0)
+ return iproute_modify(RTM_NEWROUTE, NLM_F_CREATE|NLM_F_REPLACE,
+ argc-1, argv+1);
+ if (matches(*argv, "prepend") == 0)
+ return iproute_modify(RTM_NEWROUTE, NLM_F_CREATE,
+ argc-1, argv+1);
+ if (matches(*argv, "append") == 0)
+ return iproute_modify(RTM_NEWROUTE, NLM_F_CREATE|NLM_F_APPEND,
+ argc-1, argv+1);
+ if (matches(*argv, "test") == 0)
+ return iproute_modify(RTM_NEWROUTE, NLM_F_EXCL,
+ argc-1, argv+1);
+ if (matches(*argv, "delete") == 0)
+ return iproute_modify(RTM_DELROUTE, 0,
+ argc-1, argv+1);
+ if (matches(*argv, "list") == 0 || matches(*argv, "show") == 0
+ || matches(*argv, "lst") == 0)
+ return iproute_list_flush_or_save(argc-1, argv+1, IPROUTE_LIST);
+ if (matches(*argv, "get") == 0)
+ return iproute_get(argc-1, argv+1);
+ if (matches(*argv, "flush") == 0)
+ return iproute_list_flush_or_save(argc-1, argv+1, IPROUTE_FLUSH);
+ if (matches(*argv, "save") == 0)
+ return iproute_list_flush_or_save(argc-1, argv+1, IPROUTE_SAVE);
+ if (matches(*argv, "restore") == 0)
+ return iproute_restore();
+ if (matches(*argv, "showdump") == 0)
+ return iproute_showdump();
+ if (matches(*argv, "help") == 0)
+ usage();
+ fprintf(stderr, "Command \"%s\" is unknown, try \"ip route help\".\n", *argv);
+ exit(-1);
+}
diff --git a/iproute2/ip/iproute_lwtunnel.c b/iproute2/ip/iproute_lwtunnel.c
new file mode 100644
index 0000000..7074906
--- /dev/null
+++ b/iproute2/ip/iproute_lwtunnel.c
@@ -0,0 +1,367 @@
+/*
+ * iproute_lwtunnel.c
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Roopa Prabhu, <roopa@cumulusnetworks.com>
+ * Thomas Graf <tgraf@suug.ch>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <string.h>
+#include <linux/ila.h>
+#include <linux/lwtunnel.h>
+#include <linux/mpls_iptunnel.h>
+#include <errno.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "iproute_lwtunnel.h"
+
+static int read_encap_type(const char *name)
+{
+ if (strcmp(name, "mpls") == 0)
+ return LWTUNNEL_ENCAP_MPLS;
+ else if (strcmp(name, "ip") == 0)
+ return LWTUNNEL_ENCAP_IP;
+ else if (strcmp(name, "ip6") == 0)
+ return LWTUNNEL_ENCAP_IP6;
+ else if (strcmp(name, "ila") == 0)
+ return LWTUNNEL_ENCAP_ILA;
+ else
+ return LWTUNNEL_ENCAP_NONE;
+}
+
+static const char *format_encap_type(int type)
+{
+ switch (type) {
+ case LWTUNNEL_ENCAP_MPLS:
+ return "mpls";
+ case LWTUNNEL_ENCAP_IP:
+ return "ip";
+ case LWTUNNEL_ENCAP_IP6:
+ return "ip6";
+ case LWTUNNEL_ENCAP_ILA:
+ return "ila";
+ default:
+ return "unknown";
+ }
+}
+
+static void print_encap_mpls(FILE *fp, struct rtattr *encap)
+{
+ struct rtattr *tb[MPLS_IPTUNNEL_MAX+1];
+ char abuf[256];
+
+ parse_rtattr_nested(tb, MPLS_IPTUNNEL_MAX, encap);
+
+ if (tb[MPLS_IPTUNNEL_DST])
+ fprintf(fp, " %s ", format_host(AF_MPLS,
+ RTA_PAYLOAD(tb[MPLS_IPTUNNEL_DST]),
+ RTA_DATA(tb[MPLS_IPTUNNEL_DST]),
+ abuf, sizeof(abuf)));
+}
+
+static void print_encap_ip(FILE *fp, struct rtattr *encap)
+{
+ struct rtattr *tb[LWTUNNEL_IP_MAX+1];
+ char abuf[256];
+
+ parse_rtattr_nested(tb, LWTUNNEL_IP_MAX, encap);
+
+ if (tb[LWTUNNEL_IP_ID])
+ fprintf(fp, "id %llu ", ntohll(rta_getattr_u64(tb[LWTUNNEL_IP_ID])));
+
+ if (tb[LWTUNNEL_IP_SRC])
+ fprintf(fp, "src %s ",
+ rt_addr_n2a(AF_INET,
+ RTA_PAYLOAD(tb[LWTUNNEL_IP_SRC]),
+ RTA_DATA(tb[LWTUNNEL_IP_SRC]),
+ abuf, sizeof(abuf)));
+
+ if (tb[LWTUNNEL_IP_DST])
+ fprintf(fp, "dst %s ",
+ rt_addr_n2a(AF_INET,
+ RTA_PAYLOAD(tb[LWTUNNEL_IP_DST]),
+ RTA_DATA(tb[LWTUNNEL_IP_DST]),
+ abuf, sizeof(abuf)));
+
+ if (tb[LWTUNNEL_IP_TTL])
+ fprintf(fp, "ttl %d ", rta_getattr_u8(tb[LWTUNNEL_IP_TTL]));
+
+ if (tb[LWTUNNEL_IP_TOS])
+ fprintf(fp, "tos %d ", rta_getattr_u8(tb[LWTUNNEL_IP_TOS]));
+}
+
+static void print_encap_ila(FILE *fp, struct rtattr *encap)
+{
+ struct rtattr *tb[ILA_ATTR_MAX+1];
+
+ parse_rtattr_nested(tb, ILA_ATTR_MAX, encap);
+
+ if (tb[ILA_ATTR_LOCATOR]) {
+ char abuf[ADDR64_BUF_SIZE];
+
+ addr64_n2a(*(__u64 *)RTA_DATA(tb[ILA_ATTR_LOCATOR]),
+ abuf, sizeof(abuf));
+ fprintf(fp, " %s ", abuf);
+ }
+}
+
+static void print_encap_ip6(FILE *fp, struct rtattr *encap)
+{
+ struct rtattr *tb[LWTUNNEL_IP6_MAX+1];
+ char abuf[256];
+
+ parse_rtattr_nested(tb, LWTUNNEL_IP6_MAX, encap);
+
+ if (tb[LWTUNNEL_IP6_ID])
+ fprintf(fp, "id %llu ", ntohll(rta_getattr_u64(tb[LWTUNNEL_IP6_ID])));
+
+ if (tb[LWTUNNEL_IP6_SRC])
+ fprintf(fp, "src %s ",
+ rt_addr_n2a(AF_INET6,
+ RTA_PAYLOAD(tb[LWTUNNEL_IP6_SRC]),
+ RTA_DATA(tb[LWTUNNEL_IP6_SRC]),
+ abuf, sizeof(abuf)));
+
+ if (tb[LWTUNNEL_IP6_DST])
+ fprintf(fp, "dst %s ",
+ rt_addr_n2a(AF_INET6,
+ RTA_PAYLOAD(tb[LWTUNNEL_IP6_DST]),
+ RTA_DATA(tb[LWTUNNEL_IP6_DST]),
+ abuf, sizeof(abuf)));
+
+ if (tb[LWTUNNEL_IP6_HOPLIMIT])
+ fprintf(fp, "hoplimit %d ", rta_getattr_u8(tb[LWTUNNEL_IP6_HOPLIMIT]));
+
+ if (tb[LWTUNNEL_IP6_TC])
+ fprintf(fp, "tc %d ", rta_getattr_u8(tb[LWTUNNEL_IP6_TC]));
+}
+
+void lwt_print_encap(FILE *fp, struct rtattr *encap_type,
+ struct rtattr *encap)
+{
+ int et;
+
+ if (!encap_type)
+ return;
+
+ et = rta_getattr_u16(encap_type);
+
+ fprintf(fp, " encap %s ", format_encap_type(et));
+
+ switch (et) {
+ case LWTUNNEL_ENCAP_MPLS:
+ print_encap_mpls(fp, encap);
+ break;
+ case LWTUNNEL_ENCAP_IP:
+ print_encap_ip(fp, encap);
+ break;
+ case LWTUNNEL_ENCAP_ILA:
+ print_encap_ila(fp, encap);
+ break;
+ case LWTUNNEL_ENCAP_IP6:
+ print_encap_ip6(fp, encap);
+ break;
+ }
+}
+
+static int parse_encap_mpls(struct rtattr *rta, size_t len, int *argcp, char ***argvp)
+{
+ inet_prefix addr;
+ int argc = *argcp;
+ char **argv = *argvp;
+
+ if (get_addr(&addr, *argv, AF_MPLS)) {
+ fprintf(stderr, "Error: an inet address is expected rather than \"%s\".\n", *argv);
+ exit(1);
+ }
+
+ rta_addattr_l(rta, len, MPLS_IPTUNNEL_DST, &addr.data,
+ addr.bytelen);
+
+ *argcp = argc;
+ *argvp = argv;
+
+ return 0;
+}
+
+static int parse_encap_ip(struct rtattr *rta, size_t len, int *argcp, char ***argvp)
+{
+ int id_ok = 0, dst_ok = 0, tos_ok = 0, ttl_ok = 0;
+ char **argv = *argvp;
+ int argc = *argcp;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "id") == 0) {
+ __u64 id;
+ NEXT_ARG();
+ if (id_ok++)
+ duparg2("id", *argv);
+ if (get_u64(&id, *argv, 0))
+ invarg("\"id\" value is invalid\n", *argv);
+ rta_addattr64(rta, len, LWTUNNEL_IP_ID, htonll(id));
+ } else if (strcmp(*argv, "dst") == 0) {
+ inet_prefix addr;
+ NEXT_ARG();
+ if (dst_ok++)
+ duparg2("dst", *argv);
+ get_addr(&addr, *argv, AF_INET);
+ rta_addattr_l(rta, len, LWTUNNEL_IP_DST, &addr.data, addr.bytelen);
+ } else if (strcmp(*argv, "tos") == 0) {
+ __u32 tos;
+ NEXT_ARG();
+ if (tos_ok++)
+ duparg2("tos", *argv);
+ if (rtnl_dsfield_a2n(&tos, *argv))
+ invarg("\"tos\" value is invalid\n", *argv);
+ rta_addattr8(rta, len, LWTUNNEL_IP_TOS, tos);
+ } else if (strcmp(*argv, "ttl") == 0) {
+ __u8 ttl;
+ NEXT_ARG();
+ if (ttl_ok++)
+ duparg2("ttl", *argv);
+ if (get_u8(&ttl, *argv, 0))
+ invarg("\"ttl\" value is invalid\n", *argv);
+ rta_addattr8(rta, len, LWTUNNEL_IP_TTL, ttl);
+ } else {
+ break;
+ }
+ argc--; argv++;
+ }
+
+ /* argv is currently the first unparsed argument,
+ * but the lwt_parse_encap() caller will move to the next,
+ * so step back */
+ *argcp = argc + 1;
+ *argvp = argv - 1;
+
+ return 0;
+}
+
+static int parse_encap_ila(struct rtattr *rta, size_t len,
+ int *argcp, char ***argvp)
+{
+ __u64 locator;
+ int argc = *argcp;
+ char **argv = *argvp;
+
+ if (get_addr64(&locator, *argv) < 0) {
+ fprintf(stderr, "Bad locator: %s\n", *argv);
+ exit(1);
+ }
+
+ rta_addattr64(rta, 1024, ILA_ATTR_LOCATOR, locator);
+
+ *argcp = argc;
+ *argvp = argv;
+
+ return 0;
+}
+
+static int parse_encap_ip6(struct rtattr *rta, size_t len, int *argcp, char ***argvp)
+{
+ int id_ok = 0, dst_ok = 0, tos_ok = 0, ttl_ok = 0;
+ char **argv = *argvp;
+ int argc = *argcp;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "id") == 0) {
+ __u64 id;
+ NEXT_ARG();
+ if (id_ok++)
+ duparg2("id", *argv);
+ if (get_u64(&id, *argv, 0))
+ invarg("\"id\" value is invalid\n", *argv);
+ rta_addattr64(rta, len, LWTUNNEL_IP6_ID, htonll(id));
+ } else if (strcmp(*argv, "dst") == 0) {
+ inet_prefix addr;
+ NEXT_ARG();
+ if (dst_ok++)
+ duparg2("dst", *argv);
+ get_addr(&addr, *argv, AF_INET6);
+ rta_addattr_l(rta, len, LWTUNNEL_IP6_DST, &addr.data, addr.bytelen);
+ } else if (strcmp(*argv, "tc") == 0) {
+ __u32 tc;
+ NEXT_ARG();
+ if (tos_ok++)
+ duparg2("tc", *argv);
+ if (rtnl_dsfield_a2n(&tc, *argv))
+ invarg("\"tc\" value is invalid\n", *argv);
+ rta_addattr8(rta, len, LWTUNNEL_IP6_TC, tc);
+ } else if (strcmp(*argv, "hoplimit") == 0) {
+ __u8 hoplimit;
+ NEXT_ARG();
+ if (ttl_ok++)
+ duparg2("hoplimit", *argv);
+ if (get_u8(&hoplimit, *argv, 0))
+ invarg("\"hoplimit\" value is invalid\n", *argv);
+ rta_addattr8(rta, len, LWTUNNEL_IP6_HOPLIMIT, hoplimit);
+ } else {
+ break;
+ }
+ argc--; argv++;
+ }
+
+ /* argv is currently the first unparsed argument,
+ * but the lwt_parse_encap() caller will move to the next,
+ * so step back */
+ *argcp = argc + 1;
+ *argvp = argv - 1;
+
+ return 0;
+}
+
+int lwt_parse_encap(struct rtattr *rta, size_t len, int *argcp, char ***argvp)
+{
+ struct rtattr *nest;
+ int argc = *argcp;
+ char **argv = *argvp;
+ __u16 type;
+
+ NEXT_ARG();
+ type = read_encap_type(*argv);
+ if (!type)
+ invarg("\"encap type\" value is invalid\n", *argv);
+
+ NEXT_ARG();
+ if (argc <= 1) {
+ fprintf(stderr, "Error: unexpected end of line after \"encap\"\n");
+ exit(-1);
+ }
+
+ nest = rta_nest(rta, 1024, RTA_ENCAP);
+ switch (type) {
+ case LWTUNNEL_ENCAP_MPLS:
+ parse_encap_mpls(rta, len, &argc, &argv);
+ break;
+ case LWTUNNEL_ENCAP_IP:
+ parse_encap_ip(rta, len, &argc, &argv);
+ break;
+ case LWTUNNEL_ENCAP_ILA:
+ parse_encap_ila(rta, len, &argc, &argv);
+ break;
+ case LWTUNNEL_ENCAP_IP6:
+ parse_encap_ip6(rta, len, &argc, &argv);
+ break;
+ default:
+ fprintf(stderr, "Error: unsupported encap type\n");
+ break;
+ }
+ rta_nest_end(rta, nest);
+
+ rta_addattr16(rta, 1024, RTA_ENCAP_TYPE, type);
+
+ *argcp = argc;
+ *argvp = argv;
+
+ return 0;
+}
diff --git a/iproute2/ip/iproute_lwtunnel.h b/iproute2/ip/iproute_lwtunnel.h
new file mode 100644
index 0000000..b82b58a
--- /dev/null
+++ b/iproute2/ip/iproute_lwtunnel.h
@@ -0,0 +1,8 @@
+#ifndef __LWTUNNEL_H__
+#define __LETUNNEL_H__ 1
+
+int lwt_parse_encap(struct rtattr *rta, size_t len, int *argcp, char ***argvp);
+void lwt_print_encap(FILE *fp, struct rtattr *encap_type,
+ struct rtattr *encap);
+
+#endif
diff --git a/iproute2/ip/iprule.c b/iproute2/ip/iprule.c
new file mode 100644
index 0000000..c363ccc
--- /dev/null
+++ b/iproute2/ip/iprule.c
@@ -0,0 +1,595 @@
+/*
+ * iprule.c "ip rule".
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <linux/fib_rules.h>
+#include <errno.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+
+extern struct rtnl_handle rth;
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: ip rule [ list | add | del | flush | save ] SELECTOR ACTION\n");
+ fprintf(stderr, " ip rule restore\n");
+ fprintf(stderr, "SELECTOR := [ not ] [ from PREFIX ] [ to PREFIX ] [ tos TOS ] [ fwmark FWMARK[/MASK] ]\n");
+ fprintf(stderr, " [ iif STRING ] [ oif STRING ] [ pref NUMBER ] [ uidrange UID1-UID2 ]\n");
+ fprintf(stderr, "ACTION := [ table TABLE_ID ]\n");
+ fprintf(stderr, " [ realms [SRCREALM/]DSTREALM ]\n");
+ fprintf(stderr, " [ goto NUMBER ]\n");
+ fprintf(stderr, " SUPPRESSOR\n");
+ fprintf(stderr, "SUPPRESSOR := [ suppress_prefixlength NUMBER ]\n");
+ fprintf(stderr, " [ suppress_ifgroup DEVGROUP ]\n");
+ fprintf(stderr, "TABLE_ID := [ local | main | default | NUMBER ]\n");
+ exit(-1);
+}
+
+int print_rule(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ struct rtmsg *r = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ int host_len = -1;
+ __u32 table;
+ struct rtattr * tb[FRA_MAX+1];
+ char abuf[256];
+ SPRINT_BUF(b1);
+
+ if (n->nlmsg_type != RTM_NEWRULE && n->nlmsg_type != RTM_DELRULE)
+ return 0;
+
+ len -= NLMSG_LENGTH(sizeof(*r));
+ if (len < 0)
+ return -1;
+
+ parse_rtattr(tb, FRA_MAX, RTM_RTA(r), len);
+
+ host_len = af_bit_len(r->rtm_family);
+
+ if (n->nlmsg_type == RTM_DELRULE)
+ fprintf(fp, "Deleted ");
+
+ if (tb[FRA_PRIORITY])
+ fprintf(fp, "%u:\t", *(unsigned*)RTA_DATA(tb[FRA_PRIORITY]));
+ else
+ fprintf(fp, "0:\t");
+
+ if (r->rtm_flags & FIB_RULE_INVERT)
+ fprintf(fp, "not ");
+
+ if (tb[FRA_SRC]) {
+ if (r->rtm_src_len != host_len) {
+ fprintf(fp, "from %s/%u ", rt_addr_n2a(r->rtm_family,
+ RTA_PAYLOAD(tb[FRA_SRC]),
+ RTA_DATA(tb[FRA_SRC]),
+ abuf, sizeof(abuf)),
+ r->rtm_src_len
+ );
+ } else {
+ fprintf(fp, "from %s ", format_host(r->rtm_family,
+ RTA_PAYLOAD(tb[FRA_SRC]),
+ RTA_DATA(tb[FRA_SRC]),
+ abuf, sizeof(abuf))
+ );
+ }
+ } else if (r->rtm_src_len) {
+ fprintf(fp, "from 0/%d ", r->rtm_src_len);
+ } else {
+ fprintf(fp, "from all ");
+ }
+
+ if (tb[FRA_DST]) {
+ if (r->rtm_dst_len != host_len) {
+ fprintf(fp, "to %s/%u ", rt_addr_n2a(r->rtm_family,
+ RTA_PAYLOAD(tb[FRA_DST]),
+ RTA_DATA(tb[FRA_DST]),
+ abuf, sizeof(abuf)),
+ r->rtm_dst_len
+ );
+ } else {
+ fprintf(fp, "to %s ", format_host(r->rtm_family,
+ RTA_PAYLOAD(tb[FRA_DST]),
+ RTA_DATA(tb[FRA_DST]),
+ abuf, sizeof(abuf)));
+ }
+ } else if (r->rtm_dst_len) {
+ fprintf(fp, "to 0/%d ", r->rtm_dst_len);
+ }
+
+ if (r->rtm_tos) {
+ SPRINT_BUF(b1);
+ fprintf(fp, "tos %s ", rtnl_dsfield_n2a(r->rtm_tos, b1, sizeof(b1)));
+ }
+
+ if (tb[FRA_FWMARK] || tb[FRA_FWMASK]) {
+ __u32 mark = 0, mask = 0;
+
+ if (tb[FRA_FWMARK])
+ mark = rta_getattr_u32(tb[FRA_FWMARK]);
+
+ if (tb[FRA_FWMASK] &&
+ (mask = rta_getattr_u32(tb[FRA_FWMASK])) != 0xFFFFFFFF)
+ fprintf(fp, "fwmark 0x%x/0x%x ", mark, mask);
+ else
+ fprintf(fp, "fwmark 0x%x ", mark);
+ }
+
+ if (tb[FRA_IFNAME]) {
+ fprintf(fp, "iif %s ", rta_getattr_str(tb[FRA_IFNAME]));
+ if (r->rtm_flags & FIB_RULE_IIF_DETACHED)
+ fprintf(fp, "[detached] ");
+ }
+
+ if (tb[FRA_OIFNAME]) {
+ fprintf(fp, "oif %s ", rta_getattr_str(tb[FRA_OIFNAME]));
+ if (r->rtm_flags & FIB_RULE_OIF_DETACHED)
+ fprintf(fp, "[detached] ");
+ }
+
+ if (tb[FRA_UID_START] || tb[FRA_UID_END]) {
+ fprintf(fp, "uidrange ");
+ if (tb[FRA_UID_START])
+ fprintf(fp, "%u", rta_getattr_u32(tb[FRA_UID_START]));
+ else
+ fprintf(fp, "???");
+
+ if (tb[FRA_UID_END])
+ fprintf(fp, "-%u ", rta_getattr_u32(tb[FRA_UID_END]));
+ else
+ fprintf(fp, "-??? ");
+ }
+
+ table = rtm_get_table(r, tb);
+ if (table) {
+ fprintf(fp, "lookup %s ", rtnl_rttable_n2a(table, b1, sizeof(b1)));
+
+ if (tb[FRA_SUPPRESS_PREFIXLEN]) {
+ int pl = rta_getattr_u32(tb[FRA_SUPPRESS_PREFIXLEN]);
+ if (pl != -1) {
+ fprintf(fp, "suppress_prefixlength %d ", pl);
+ }
+ }
+ if (tb[FRA_SUPPRESS_IFGROUP]) {
+ int group = rta_getattr_u32(tb[FRA_SUPPRESS_IFGROUP]);
+ if (group != -1) {
+ SPRINT_BUF(b1);
+ fprintf(fp, "suppress_ifgroup %s ", rtnl_group_n2a(group, b1, sizeof(b1)));
+ }
+ }
+ }
+
+ if (tb[FRA_FLOW]) {
+ __u32 to = rta_getattr_u32(tb[FRA_FLOW]);
+ __u32 from = to>>16;
+ to &= 0xFFFF;
+ if (from) {
+ fprintf(fp, "realms %s/",
+ rtnl_rtrealm_n2a(from, b1, sizeof(b1)));
+ }
+ fprintf(fp, "%s ",
+ rtnl_rtrealm_n2a(to, b1, sizeof(b1)));
+ }
+
+ if (r->rtm_type == RTN_NAT) {
+ if (tb[RTA_GATEWAY]) {
+ fprintf(fp, "map-to %s ",
+ format_host(r->rtm_family,
+ RTA_PAYLOAD(tb[RTA_GATEWAY]),
+ RTA_DATA(tb[RTA_GATEWAY]),
+ abuf, sizeof(abuf)));
+ } else
+ fprintf(fp, "masquerade");
+ } else if (r->rtm_type == FR_ACT_GOTO) {
+ fprintf(fp, "goto ");
+ if (tb[FRA_GOTO])
+ fprintf(fp, "%u", rta_getattr_u32(tb[FRA_GOTO]));
+ else
+ fprintf(fp, "none");
+ if (r->rtm_flags & FIB_RULE_UNRESOLVED)
+ fprintf(fp, " [unresolved]");
+ } else if (r->rtm_type == FR_ACT_NOP)
+ fprintf(fp, "nop");
+ else if (r->rtm_type != RTN_UNICAST)
+ fprintf(fp, "%s", rtnl_rtntype_n2a(r->rtm_type, b1, sizeof(b1)));
+
+ fprintf(fp, "\n");
+ fflush(fp);
+ return 0;
+}
+
+static __u32 rule_dump_magic = 0x71706986;
+
+static int save_rule_prep(void)
+{
+ int ret;
+
+ if (isatty(STDOUT_FILENO)) {
+ fprintf(stderr, "Not sending a binary stream to stdout\n");
+ return -1;
+ }
+
+ ret = write(STDOUT_FILENO, &rule_dump_magic, sizeof(rule_dump_magic));
+ if (ret != sizeof(rule_dump_magic)) {
+ fprintf(stderr, "Can't write magic to dump file\n");
+ return -1;
+ }
+
+ return 0;
+}
+
+static int save_rule(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
+{
+ int ret;
+
+ ret = write(STDOUT_FILENO, n, n->nlmsg_len);
+ if ((ret > 0) && (ret != n->nlmsg_len)) {
+ fprintf(stderr, "Short write while saving nlmsg\n");
+ ret = -EIO;
+ }
+
+ return ret == n->nlmsg_len ? 0 : ret;
+}
+
+static int iprule_list_or_save(int argc, char **argv, int save)
+{
+ rtnl_filter_t filter = print_rule;
+ int af = preferred_family;
+
+ if (af == AF_UNSPEC)
+ af = AF_INET;
+
+ if (argc > 0) {
+ fprintf(stderr, "\"ip rule %s\" does not take any arguments.\n",
+ save ? "save" : "show");
+ return -1;
+ }
+
+ if (save) {
+ if (save_rule_prep())
+ return -1;
+ filter = save_rule;
+ }
+
+ if (rtnl_wilddump_request(&rth, af, RTM_GETRULE) < 0) {
+ perror("Cannot send dump request");
+ return 1;
+ }
+
+ if (rtnl_dump_filter(&rth, filter, stdout) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ return 1;
+ }
+
+ return 0;
+}
+
+static int rule_dump_check_magic(void)
+{
+ int ret;
+ __u32 magic = 0;
+
+ if (isatty(STDIN_FILENO)) {
+ fprintf(stderr, "Can't restore rule dump from a terminal\n");
+ return -1;
+ }
+
+ ret = fread(&magic, sizeof(magic), 1, stdin);
+ if (magic != rule_dump_magic) {
+ fprintf(stderr, "Magic mismatch (%d elems, %x magic)\n", ret, magic);
+ return -1;
+ }
+
+ return 0;
+}
+
+static int restore_handler(const struct sockaddr_nl *nl,
+ struct rtnl_ctrl_data *ctrl,
+ struct nlmsghdr *n, void *arg)
+{
+ int ret;
+
+ n->nlmsg_flags |= NLM_F_REQUEST | NLM_F_CREATE | NLM_F_ACK;
+
+ ll_init_map(&rth);
+
+ ret = rtnl_talk(&rth, n, n, sizeof(*n));
+ if ((ret < 0) && (errno == EEXIST))
+ ret = 0;
+
+ return ret;
+}
+
+
+static int iprule_restore(void)
+{
+ if (rule_dump_check_magic())
+ exit(-1);
+
+ exit(rtnl_from_file(stdin, &restore_handler, NULL));
+}
+
+static int iprule_modify(int cmd, int argc, char **argv)
+{
+ int table_ok = 0;
+ struct {
+ struct nlmsghdr n;
+ struct rtmsg r;
+ char buf[1024];
+ } req;
+
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_type = cmd;
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct rtmsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.r.rtm_family = preferred_family;
+ req.r.rtm_protocol = RTPROT_BOOT;
+ req.r.rtm_scope = RT_SCOPE_UNIVERSE;
+ req.r.rtm_table = 0;
+ req.r.rtm_type = RTN_UNSPEC;
+ req.r.rtm_flags = 0;
+
+ if (cmd == RTM_NEWRULE) {
+ req.n.nlmsg_flags |= NLM_F_CREATE|NLM_F_EXCL;
+ req.r.rtm_type = RTN_UNICAST;
+ }
+
+ while (argc > 0) {
+ if (strcmp(*argv, "not") == 0) {
+ req.r.rtm_flags |= FIB_RULE_INVERT;
+ } else if (strcmp(*argv, "from") == 0) {
+ inet_prefix dst;
+ NEXT_ARG();
+ get_prefix(&dst, *argv, req.r.rtm_family);
+ req.r.rtm_src_len = dst.bitlen;
+ addattr_l(&req.n, sizeof(req), FRA_SRC, &dst.data, dst.bytelen);
+ } else if (strcmp(*argv, "to") == 0) {
+ inet_prefix dst;
+ NEXT_ARG();
+ get_prefix(&dst, *argv, req.r.rtm_family);
+ req.r.rtm_dst_len = dst.bitlen;
+ addattr_l(&req.n, sizeof(req), FRA_DST, &dst.data, dst.bytelen);
+ } else if (matches(*argv, "preference") == 0 ||
+ matches(*argv, "order") == 0 ||
+ matches(*argv, "priority") == 0) {
+ __u32 pref;
+ NEXT_ARG();
+ if (get_u32(&pref, *argv, 0))
+ invarg("preference value is invalid\n", *argv);
+ addattr32(&req.n, sizeof(req), FRA_PRIORITY, pref);
+ } else if (strcmp(*argv, "tos") == 0 ||
+ matches(*argv, "dsfield") == 0) {
+ __u32 tos;
+ NEXT_ARG();
+ if (rtnl_dsfield_a2n(&tos, *argv))
+ invarg("TOS value is invalid\n", *argv);
+ req.r.rtm_tos = tos;
+ } else if (strcmp(*argv, "fwmark") == 0) {
+ char *slash;
+ __u32 fwmark, fwmask;
+ NEXT_ARG();
+ if ((slash = strchr(*argv, '/')) != NULL)
+ *slash = '\0';
+ if (get_u32(&fwmark, *argv, 0))
+ invarg("fwmark value is invalid\n", *argv);
+ addattr32(&req.n, sizeof(req), FRA_FWMARK, fwmark);
+ if (slash) {
+ if (get_u32(&fwmask, slash+1, 0))
+ invarg("fwmask value is invalid\n", slash+1);
+ addattr32(&req.n, sizeof(req), FRA_FWMASK, fwmask);
+ }
+ } else if (matches(*argv, "realms") == 0) {
+ __u32 realm;
+ NEXT_ARG();
+ if (get_rt_realms_or_raw(&realm, *argv))
+ invarg("invalid realms\n", *argv);
+ addattr32(&req.n, sizeof(req), FRA_FLOW, realm);
+ } else if (matches(*argv, "table") == 0 ||
+ strcmp(*argv, "lookup") == 0) {
+ __u32 tid;
+ NEXT_ARG();
+ if (rtnl_rttable_a2n(&tid, *argv))
+ invarg("invalid table ID\n", *argv);
+ if (tid < 256)
+ req.r.rtm_table = tid;
+ else {
+ req.r.rtm_table = RT_TABLE_UNSPEC;
+ addattr32(&req.n, sizeof(req), FRA_TABLE, tid);
+ }
+ table_ok = 1;
+ } else if (matches(*argv, "suppress_prefixlength") == 0 ||
+ strcmp(*argv, "sup_pl") == 0) {
+ int pl;
+ NEXT_ARG();
+ if (get_s32(&pl, *argv, 0) || pl < 0)
+ invarg("suppress_prefixlength value is invalid\n", *argv);
+ addattr32(&req.n, sizeof(req), FRA_SUPPRESS_PREFIXLEN, pl);
+ } else if (matches(*argv, "suppress_ifgroup") == 0 ||
+ strcmp(*argv, "sup_group") == 0) {
+ NEXT_ARG();
+ int group;
+ if (rtnl_group_a2n(&group, *argv))
+ invarg("Invalid \"suppress_ifgroup\" value\n", *argv);
+ addattr32(&req.n, sizeof(req), FRA_SUPPRESS_IFGROUP, group);
+ } else if (strcmp(*argv, "dev") == 0 ||
+ strcmp(*argv, "iif") == 0) {
+ NEXT_ARG();
+ addattr_l(&req.n, sizeof(req), FRA_IFNAME, *argv, strlen(*argv)+1);
+ } else if (strcmp(*argv, "oif") == 0) {
+ NEXT_ARG();
+ addattr_l(&req.n, sizeof(req), FRA_OIFNAME, *argv, strlen(*argv)+1);
+ } else if (strcmp(*argv, "nat") == 0 ||
+ matches(*argv, "map-to") == 0) {
+ NEXT_ARG();
+ fprintf(stderr, "Warning: route NAT is deprecated\n");
+ addattr32(&req.n, sizeof(req), RTA_GATEWAY, get_addr32(*argv));
+ req.r.rtm_type = RTN_NAT;
+ } else if (strcmp(*argv, "uidrange") == 0) {
+ __u32 uid_start, uid_end;
+ NEXT_ARG();
+ if (sscanf(*argv, "%u-%u", &uid_start, &uid_end) != 2)
+ invarg("UID range is invalid\n", *argv);
+ addattr32(&req.n, sizeof(req), FRA_UID_START, uid_start);
+ addattr32(&req.n, sizeof(req), FRA_UID_END, uid_end);
+ } else {
+ int type;
+
+ if (strcmp(*argv, "type") == 0) {
+ NEXT_ARG();
+ }
+ if (matches(*argv, "help") == 0)
+ usage();
+ else if (matches(*argv, "goto") == 0) {
+ __u32 target;
+ type = FR_ACT_GOTO;
+ NEXT_ARG();
+ if (get_u32(&target, *argv, 0))
+ invarg("invalid target\n", *argv);
+ addattr32(&req.n, sizeof(req), FRA_GOTO, target);
+ } else if (matches(*argv, "nop") == 0)
+ type = FR_ACT_NOP;
+ else if (rtnl_rtntype_a2n(&type, *argv))
+ invarg("Failed to parse rule type", *argv);
+ req.r.rtm_type = type;
+ table_ok = 1;
+ }
+ argc--;
+ argv++;
+ }
+
+ if (req.r.rtm_family == AF_UNSPEC)
+ req.r.rtm_family = AF_INET;
+
+ if (!table_ok && cmd == RTM_NEWRULE)
+ req.r.rtm_table = RT_TABLE_MAIN;
+
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ return -2;
+
+ return 0;
+}
+
+
+static int flush_rule(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
+{
+ struct rtnl_handle rth2;
+ struct rtmsg *r = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr * tb[FRA_MAX+1];
+
+ len -= NLMSG_LENGTH(sizeof(*r));
+ if (len < 0)
+ return -1;
+
+ parse_rtattr(tb, FRA_MAX, RTM_RTA(r), len);
+
+ if (tb[FRA_PRIORITY]) {
+ n->nlmsg_type = RTM_DELRULE;
+ n->nlmsg_flags = NLM_F_REQUEST;
+
+ if (rtnl_open(&rth2, 0) < 0)
+ return -1;
+
+ if (rtnl_talk(&rth2, n, NULL, 0) < 0)
+ return -2;
+
+ rtnl_close(&rth2);
+ }
+
+ return 0;
+}
+
+static int iprule_flush(int argc, char **argv)
+{
+ int af = preferred_family;
+
+ if (af == AF_UNSPEC)
+ af = AF_INET;
+
+ if (argc > 0) {
+ fprintf(stderr, "\"ip rule flush\" does not allow arguments\n");
+ return -1;
+ }
+
+ if (rtnl_wilddump_request(&rth, af, RTM_GETRULE) < 0) {
+ perror("Cannot send dump request");
+ return 1;
+ }
+
+ if (rtnl_dump_filter(&rth, flush_rule, NULL) < 0) {
+ fprintf(stderr, "Flush terminated\n");
+ return 1;
+ }
+
+ return 0;
+}
+
+int do_iprule(int argc, char **argv)
+{
+ if (argc < 1) {
+ return iprule_list_or_save(0, NULL, 0);
+ } else if (matches(argv[0], "list") == 0 ||
+ matches(argv[0], "lst") == 0 ||
+ matches(argv[0], "show") == 0) {
+ return iprule_list_or_save(argc-1, argv+1, 0);
+ } else if (matches(argv[0], "save") == 0) {
+ return iprule_list_or_save(argc-1, argv+1, 1);
+ } else if (matches(argv[0], "restore") == 0) {
+ return iprule_restore();
+ } else if (matches(argv[0], "add") == 0) {
+ return iprule_modify(RTM_NEWRULE, argc-1, argv+1);
+ } else if (matches(argv[0], "delete") == 0) {
+ return iprule_modify(RTM_DELRULE, argc-1, argv+1);
+ } else if (matches(argv[0], "flush") == 0) {
+ return iprule_flush(argc-1, argv+1);
+ } else if (matches(argv[0], "help") == 0)
+ usage();
+
+ fprintf(stderr, "Command \"%s\" is unknown, try \"ip rule help\".\n", *argv);
+ exit(-1);
+}
+
+int do_multirule(int argc, char **argv)
+{
+ switch (preferred_family) {
+ case AF_UNSPEC:
+ case AF_INET:
+ preferred_family = RTNL_FAMILY_IPMR;
+ break;
+ case AF_INET6:
+ preferred_family = RTNL_FAMILY_IP6MR;
+ break;
+ case RTNL_FAMILY_IPMR:
+ case RTNL_FAMILY_IP6MR:
+ break;
+ default:
+ fprintf(stderr, "Multicast rules are only supported for IPv4/IPv6, was: %i\n",
+ preferred_family);
+ exit(-1);
+ }
+
+ return do_iprule(argc, argv);
+}
diff --git a/iproute2/ip/iptoken.c b/iproute2/ip/iptoken.c
new file mode 100644
index 0000000..428f133
--- /dev/null
+++ b/iproute2/ip/iptoken.c
@@ -0,0 +1,207 @@
+/*
+ * iptoken.c "ip token"
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Daniel Borkmann, <borkmann@redhat.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+#include <arpa/inet.h>
+#include <linux/types.h>
+#include <linux/if.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+
+extern struct rtnl_handle rth;
+
+struct rtnl_dump_args {
+ FILE *fp;
+ int ifindex;
+};
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: ip token [ list | set | get ] [ TOKEN ] [ dev DEV ]\n");
+ exit(-1);
+}
+
+static int print_token(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
+{
+ struct rtnl_dump_args *args = arg;
+ FILE *fp = args->fp;
+ int ifindex = args->ifindex;
+ struct ifinfomsg *ifi = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr *tb[IFLA_MAX + 1];
+ struct rtattr *ltb[IFLA_INET6_MAX + 1];
+ char abuf[256];
+
+ if (n->nlmsg_type != RTM_NEWLINK)
+ return -1;
+
+ len -= NLMSG_LENGTH(sizeof(*ifi));
+ if (len < 0)
+ return -1;
+
+ if (ifi->ifi_family != AF_INET6)
+ return -1;
+ if (ifi->ifi_index == 0)
+ return -1;
+ if (ifindex > 0 && ifi->ifi_index != ifindex)
+ return 0;
+ if (ifi->ifi_flags & (IFF_LOOPBACK | IFF_NOARP))
+ return 0;
+
+ parse_rtattr(tb, IFLA_MAX, IFLA_RTA(ifi), len);
+ if (!tb[IFLA_PROTINFO])
+ return -1;
+
+ parse_rtattr_nested(ltb, IFLA_INET6_MAX, tb[IFLA_PROTINFO]);
+ if (!ltb[IFLA_INET6_TOKEN]) {
+ fprintf(stderr, "Seems there's no support for IPv6 token!\n");
+ return -1;
+ }
+
+ fprintf(fp, "token %s ",
+ format_host(ifi->ifi_family,
+ RTA_PAYLOAD(ltb[IFLA_INET6_TOKEN]),
+ RTA_DATA(ltb[IFLA_INET6_TOKEN]),
+ abuf, sizeof(abuf)));
+ fprintf(fp, "dev %s ", ll_index_to_name(ifi->ifi_index));
+ fprintf(fp, "\n");
+ fflush(fp);
+
+ return 0;
+}
+
+static int iptoken_list(int argc, char **argv)
+{
+ int af = AF_INET6;
+ struct rtnl_dump_args da;
+
+ memset(&da, 0, sizeof(da));
+ da.fp = stdout;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ if ((da.ifindex = ll_name_to_index(*argv)) == 0)
+ invarg("dev is invalid\n", *argv);
+ break;
+ }
+ argc--; argv++;
+ }
+
+ if (rtnl_wilddump_request(&rth, af, RTM_GETLINK) < 0) {
+ perror("Cannot send dump request");
+ return -1;
+ }
+
+ if (rtnl_dump_filter(&rth, print_token, &da) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ return -1;
+ }
+
+ return 0;
+}
+
+static int iptoken_set(int argc, char **argv)
+{
+ struct {
+ struct nlmsghdr n;
+ struct ifinfomsg ifi;
+ char buf[512];
+ } req;
+ struct rtattr *afs, *afs6;
+ bool have_token = false, have_dev = false;
+ inet_prefix addr;
+
+ memset(&addr, 0, sizeof(addr));
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = RTM_SETLINK;
+ req.ifi.ifi_family = AF_INET6;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ if (!have_dev) {
+ if ((req.ifi.ifi_index =
+ ll_name_to_index(*argv)) == 0)
+ invarg("dev is invalid\n", *argv);
+ have_dev = true;
+ }
+ } else {
+ if (matches(*argv, "help") == 0)
+ usage();
+ if (!have_token) {
+ afs = addattr_nest(&req.n, sizeof(req), IFLA_AF_SPEC);
+ afs6 = addattr_nest(&req.n, sizeof(req), AF_INET6);
+ get_prefix(&addr, *argv, req.ifi.ifi_family);
+ addattr_l(&req.n, sizeof(req), IFLA_INET6_TOKEN,
+ &addr.data, addr.bytelen);
+ addattr_nest_end(&req.n, afs6);
+ addattr_nest_end(&req.n, afs);
+ have_token = true;
+ }
+ }
+ argc--; argv++;
+ }
+
+ if (!have_token) {
+ fprintf(stderr, "Not enough information: token "
+ "is required.\n");
+ return -1;
+ }
+ if (!have_dev) {
+ fprintf(stderr, "Not enough information: \"dev\" "
+ "argument is required.\n");
+ return -1;
+ }
+
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ return -2;
+
+ return 0;
+}
+
+int do_iptoken(int argc, char **argv)
+{
+ ll_init_map(&rth);
+
+ if (argc < 1) {
+ return iptoken_list(0, NULL);
+ } else if (matches(argv[0], "list") == 0 ||
+ matches(argv[0], "lst") == 0 ||
+ matches(argv[0], "show") == 0) {
+ return iptoken_list(argc - 1, argv + 1);
+ } else if (matches(argv[0], "set") == 0 ||
+ matches(argv[0], "add") == 0) {
+ return iptoken_set(argc - 1, argv + 1);
+ } else if (matches(argv[0], "get") == 0) {
+ return iptoken_list(argc - 1, argv + 1);
+ } else if (matches(argv[0], "help") == 0)
+ usage();
+
+ fprintf(stderr, "Command \"%s\" is unknown, try \"ip token help\".\n", *argv);
+ exit(-1);
+}
diff --git a/iproute2/ip/iptunnel.c b/iproute2/ip/iptunnel.c
new file mode 100644
index 0000000..65a4e6e
--- /dev/null
+++ b/iproute2/ip/iptunnel.c
@@ -0,0 +1,639 @@
+/*
+ * iptunnel.c "ip tunnel"
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+#include <sys/ioctl.h>
+#include <net/if.h>
+#include <net/if_arp.h>
+#include <linux/ip.h>
+#include <linux/if_tunnel.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+#include "tunnel.h"
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: ip tunnel { add | change | del | show | prl | 6rd } [ NAME ]\n");
+ fprintf(stderr, " [ mode { ipip | gre | sit | isatap | vti } ] [ remote ADDR ] [ local ADDR ]\n");
+ fprintf(stderr, " [ [i|o]seq ] [ [i|o]key KEY ] [ [i|o]csum ]\n");
+ fprintf(stderr, " [ prl-default ADDR ] [ prl-nodefault ADDR ] [ prl-delete ADDR ]\n");
+ fprintf(stderr, " [ 6rd-prefix ADDR ] [ 6rd-relay_prefix ADDR ] [ 6rd-reset ]\n");
+ fprintf(stderr, " [ ttl TTL ] [ tos TOS ] [ [no]pmtudisc ] [ dev PHYS_DEV ]\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "Where: NAME := STRING\n");
+ fprintf(stderr, " ADDR := { IP_ADDRESS | any }\n");
+ fprintf(stderr, " TOS := { STRING | 00..ff | inherit | inherit/STRING | inherit/00..ff }\n");
+ fprintf(stderr, " TTL := { 1..255 | inherit }\n");
+ fprintf(stderr, " KEY := { DOTTED_QUAD | NUMBER }\n");
+ exit(-1);
+}
+
+static void set_tunnel_proto(struct ip_tunnel_parm *p, int proto)
+{
+ if (p->iph.protocol && p->iph.protocol != proto) {
+ fprintf(stderr,
+ "You managed to ask for more than one tunnel mode.\n");
+ exit(-1);
+ }
+ p->iph.protocol = proto;
+}
+
+static int parse_args(int argc, char **argv, int cmd, struct ip_tunnel_parm *p)
+{
+ int count = 0;
+ char medium[IFNAMSIZ];
+ int isatap = 0;
+
+ memset(p, 0, sizeof(*p));
+ memset(&medium, 0, sizeof(medium));
+
+ p->iph.version = 4;
+ p->iph.ihl = 5;
+#ifndef IP_DF
+#define IP_DF 0x4000 /* Flag: "Don't Fragment" */
+#endif
+ p->iph.frag_off = htons(IP_DF);
+
+ while (argc > 0) {
+ if (strcmp(*argv, "mode") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "ipip") == 0 ||
+ strcmp(*argv, "ip/ip") == 0) {
+ set_tunnel_proto(p, IPPROTO_IPIP);
+ } else if (strcmp(*argv, "gre") == 0 ||
+ strcmp(*argv, "gre/ip") == 0) {
+ set_tunnel_proto(p, IPPROTO_GRE);
+ } else if (strcmp(*argv, "sit") == 0 ||
+ strcmp(*argv, "ipv6/ip") == 0) {
+ set_tunnel_proto(p, IPPROTO_IPV6);
+ } else if (strcmp(*argv, "isatap") == 0) {
+ set_tunnel_proto(p, IPPROTO_IPV6);
+ isatap++;
+ } else if (strcmp(*argv, "vti") == 0) {
+ set_tunnel_proto(p, IPPROTO_IPIP);
+ p->i_flags |= VTI_ISVTI;
+ } else {
+ fprintf(stderr,
+ "Unknown tunnel mode \"%s\"\n", *argv);
+ exit(-1);
+ }
+ } else if (strcmp(*argv, "key") == 0) {
+ NEXT_ARG();
+ p->i_flags |= GRE_KEY;
+ p->o_flags |= GRE_KEY;
+ p->i_key = p->o_key = tnl_parse_key("key", *argv);
+ } else if (strcmp(*argv, "ikey") == 0) {
+ NEXT_ARG();
+ p->i_flags |= GRE_KEY;
+ p->i_key = tnl_parse_key("ikey", *argv);
+ } else if (strcmp(*argv, "okey") == 0) {
+ NEXT_ARG();
+ p->o_flags |= GRE_KEY;
+ p->o_key = tnl_parse_key("okey", *argv);
+ } else if (strcmp(*argv, "seq") == 0) {
+ p->i_flags |= GRE_SEQ;
+ p->o_flags |= GRE_SEQ;
+ } else if (strcmp(*argv, "iseq") == 0) {
+ p->i_flags |= GRE_SEQ;
+ } else if (strcmp(*argv, "oseq") == 0) {
+ p->o_flags |= GRE_SEQ;
+ } else if (strcmp(*argv, "csum") == 0) {
+ p->i_flags |= GRE_CSUM;
+ p->o_flags |= GRE_CSUM;
+ } else if (strcmp(*argv, "icsum") == 0) {
+ p->i_flags |= GRE_CSUM;
+ } else if (strcmp(*argv, "ocsum") == 0) {
+ p->o_flags |= GRE_CSUM;
+ } else if (strcmp(*argv, "nopmtudisc") == 0) {
+ p->iph.frag_off = 0;
+ } else if (strcmp(*argv, "pmtudisc") == 0) {
+ p->iph.frag_off = htons(IP_DF);
+ } else if (strcmp(*argv, "remote") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "any"))
+ p->iph.daddr = get_addr32(*argv);
+ else
+ p->iph.daddr = htonl(INADDR_ANY);
+ } else if (strcmp(*argv, "local") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "any"))
+ p->iph.saddr = get_addr32(*argv);
+ else
+ p->iph.saddr = htonl(INADDR_ANY);
+ } else if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ strncpy(medium, *argv, IFNAMSIZ - 1);
+ } else if (strcmp(*argv, "ttl") == 0 ||
+ strcmp(*argv, "hoplimit") == 0 ||
+ strcmp(*argv, "hlim") == 0) {
+ __u8 uval;
+
+ NEXT_ARG();
+ if (strcmp(*argv, "inherit") != 0) {
+ if (get_u8(&uval, *argv, 0))
+ invarg("invalid TTL\n", *argv);
+ p->iph.ttl = uval;
+ }
+ } else if (strcmp(*argv, "tos") == 0 ||
+ strcmp(*argv, "tclass") == 0 ||
+ matches(*argv, "dsfield") == 0) {
+ char *dsfield;
+ __u32 uval;
+
+ NEXT_ARG();
+ dsfield = *argv;
+ strsep(&dsfield, "/");
+ if (strcmp(*argv, "inherit") != 0) {
+ dsfield = *argv;
+ p->iph.tos = 0;
+ } else
+ p->iph.tos = 1;
+ if (dsfield) {
+ if (rtnl_dsfield_a2n(&uval, dsfield))
+ invarg("bad TOS value", *argv);
+ p->iph.tos |= uval;
+ }
+ } else {
+ if (strcmp(*argv, "name") == 0)
+ NEXT_ARG();
+ else if (matches(*argv, "help") == 0)
+ usage();
+
+ if (p->name[0])
+ duparg2("name", *argv);
+ strncpy(p->name, *argv, IFNAMSIZ - 1);
+ if (cmd == SIOCCHGTUNNEL && count == 0) {
+ struct ip_tunnel_parm old_p;
+
+ memset(&old_p, 0, sizeof(old_p));
+ if (tnl_get_ioctl(*argv, &old_p))
+ return -1;
+ *p = old_p;
+ }
+ }
+ count++;
+ argc--; argv++;
+ }
+
+
+ if (p->iph.protocol == 0) {
+ if (memcmp(p->name, "gre", 3) == 0)
+ p->iph.protocol = IPPROTO_GRE;
+ else if (memcmp(p->name, "ipip", 4) == 0)
+ p->iph.protocol = IPPROTO_IPIP;
+ else if (memcmp(p->name, "sit", 3) == 0)
+ p->iph.protocol = IPPROTO_IPV6;
+ else if (memcmp(p->name, "isatap", 6) == 0) {
+ p->iph.protocol = IPPROTO_IPV6;
+ isatap++;
+ } else if (memcmp(p->name, "vti", 3) == 0) {
+ p->iph.protocol = IPPROTO_IPIP;
+ p->i_flags |= VTI_ISVTI;
+ }
+ }
+
+ if ((p->i_flags & GRE_KEY) || (p->o_flags & GRE_KEY)) {
+ if (!(p->i_flags & VTI_ISVTI) &&
+ (p->iph.protocol != IPPROTO_GRE)) {
+ fprintf(stderr, "Keys are not allowed with ipip and sit tunnels\n");
+ return -1;
+ }
+ }
+
+ if (medium[0]) {
+ p->link = ll_name_to_index(medium);
+ if (p->link == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", medium);
+ return -1;
+ }
+ }
+
+ if (p->i_key == 0 && IN_MULTICAST(ntohl(p->iph.daddr))) {
+ p->i_key = p->iph.daddr;
+ p->i_flags |= GRE_KEY;
+ }
+ if (p->o_key == 0 && IN_MULTICAST(ntohl(p->iph.daddr))) {
+ p->o_key = p->iph.daddr;
+ p->o_flags |= GRE_KEY;
+ }
+ if (IN_MULTICAST(ntohl(p->iph.daddr)) && !p->iph.saddr) {
+ fprintf(stderr, "A broadcast tunnel requires a source address\n");
+ return -1;
+ }
+ if (isatap)
+ p->i_flags |= SIT_ISATAP;
+
+ return 0;
+}
+
+static const char *tnl_defname(const struct ip_tunnel_parm *p)
+{
+ switch (p->iph.protocol) {
+ case IPPROTO_IPIP:
+ if (p->i_flags & VTI_ISVTI)
+ return "ip_vti0";
+ else
+ return "tunl0";
+ case IPPROTO_GRE:
+ return "gre0";
+ case IPPROTO_IPV6:
+ return "sit0";
+ }
+ return NULL;
+}
+
+static int do_add(int cmd, int argc, char **argv)
+{
+ struct ip_tunnel_parm p;
+ const char *basedev;
+
+ if (parse_args(argc, argv, cmd, &p) < 0)
+ return -1;
+
+ if (p.iph.ttl && p.iph.frag_off == 0) {
+ fprintf(stderr, "ttl != 0 and nopmtudisc are incompatible\n");
+ return -1;
+ }
+
+ basedev = tnl_defname(&p);
+ if (!basedev) {
+ fprintf(stderr,
+ "cannot determine tunnel mode (ipip, gre, vti or sit)\n");
+ return -1;
+ }
+
+ return tnl_add_ioctl(cmd, basedev, p.name, &p);
+}
+
+static int do_del(int argc, char **argv)
+{
+ struct ip_tunnel_parm p;
+
+ if (parse_args(argc, argv, SIOCDELTUNNEL, &p) < 0)
+ return -1;
+
+ return tnl_del_ioctl(tnl_defname(&p) ? : p.name, p.name, &p);
+}
+
+static void print_tunnel(struct ip_tunnel_parm *p)
+{
+ struct ip_tunnel_6rd ip6rd;
+ char s1[1024];
+ char s2[1024];
+
+ memset(&ip6rd, 0, sizeof(ip6rd));
+
+ /* Do not use format_host() for local addr,
+ * symbolic name will not be useful.
+ */
+ printf("%s: %s/ip remote %s local %s",
+ p->name,
+ tnl_strproto(p->iph.protocol),
+ p->iph.daddr ? format_host(AF_INET, 4, &p->iph.daddr, s1, sizeof(s1)) : "any",
+ p->iph.saddr ? rt_addr_n2a(AF_INET, 4, &p->iph.saddr, s2, sizeof(s2)) : "any");
+
+ if (p->iph.protocol == IPPROTO_IPV6 && (p->i_flags & SIT_ISATAP)) {
+ struct ip_tunnel_prl prl[16];
+ int i;
+
+ memset(prl, 0, sizeof(prl));
+ prl[0].datalen = sizeof(prl) - sizeof(prl[0]);
+ prl[0].addr = htonl(INADDR_ANY);
+
+ if (!tnl_prl_ioctl(SIOCGETPRL, p->name, prl))
+ for (i = 1; i < ARRAY_SIZE(prl); i++) {
+ if (prl[i].addr != htonl(INADDR_ANY)) {
+ printf(" %s %s ",
+ (prl[i].flags & PRL_DEFAULT) ? "pdr" : "pr",
+ format_host(AF_INET, 4, &prl[i].addr, s1, sizeof(s1)));
+ }
+ }
+ }
+
+ if (p->link) {
+ const char *n = ll_index_to_name(p->link);
+
+ if (n)
+ printf(" dev %s", n);
+ }
+
+ if (p->iph.ttl)
+ printf(" ttl %d", p->iph.ttl);
+ else
+ printf(" ttl inherit");
+
+ if (p->iph.tos) {
+ SPRINT_BUF(b1);
+ printf(" tos");
+ if (p->iph.tos & 1)
+ printf(" inherit");
+ if (p->iph.tos & ~1)
+ printf("%c%s ", p->iph.tos & 1 ? '/' : ' ',
+ rtnl_dsfield_n2a(p->iph.tos & ~1, b1, sizeof(b1)));
+ }
+
+ if (!(p->iph.frag_off & htons(IP_DF)))
+ printf(" nopmtudisc");
+
+ if (p->iph.protocol == IPPROTO_IPV6 && !tnl_ioctl_get_6rd(p->name, &ip6rd) && ip6rd.prefixlen) {
+ printf(" 6rd-prefix %s/%u",
+ inet_ntop(AF_INET6, &ip6rd.prefix, s1, sizeof(s1)),
+ ip6rd.prefixlen);
+ if (ip6rd.relay_prefix) {
+ printf(" 6rd-relay_prefix %s/%u",
+ format_host(AF_INET, 4, &ip6rd.relay_prefix, s1, sizeof(s1)),
+ ip6rd.relay_prefixlen);
+ }
+ }
+
+ if ((p->i_flags & GRE_KEY) && (p->o_flags & GRE_KEY) && p->o_key == p->i_key)
+ printf(" key %u", ntohl(p->i_key));
+ else if ((p->i_flags | p->o_flags) & GRE_KEY) {
+ if (p->i_flags & GRE_KEY)
+ printf(" ikey %u", ntohl(p->i_key));
+ if (p->o_flags & GRE_KEY)
+ printf(" okey %u", ntohl(p->o_key));
+ }
+
+ if (p->i_flags & GRE_SEQ)
+ printf("%s Drop packets out of sequence.", _SL_);
+ if (p->i_flags & GRE_CSUM)
+ printf("%s Checksum in received packet is required.", _SL_);
+ if (p->o_flags & GRE_SEQ)
+ printf("%s Sequence packets on output.", _SL_);
+ if (p->o_flags & GRE_CSUM)
+ printf("%s Checksum output packets.", _SL_);
+}
+
+static int do_tunnels_list(struct ip_tunnel_parm *p)
+{
+ char buf[512];
+ int err = -1;
+ FILE *fp = fopen("/proc/net/dev", "r");
+
+ if (fp == NULL) {
+ perror("fopen");
+ return -1;
+ }
+
+ /* skip header lines */
+ if (!fgets(buf, sizeof(buf), fp) ||
+ !fgets(buf, sizeof(buf), fp)) {
+ fprintf(stderr, "/proc/net/dev read error\n");
+ goto end;
+ }
+
+ while (fgets(buf, sizeof(buf), fp) != NULL) {
+ char name[IFNAMSIZ];
+ int index, type;
+ struct ip_tunnel_parm p1;
+ char *ptr;
+
+ buf[sizeof(buf) - 1] = 0;
+ ptr = strchr(buf, ':');
+ if (ptr == NULL ||
+ (*ptr++ = 0, sscanf(buf, "%s", name) != 1)) {
+ fprintf(stderr, "Wrong format for /proc/net/dev. Giving up.\n");
+ goto end;
+ }
+ if (p->name[0] && strcmp(p->name, name))
+ continue;
+ index = ll_name_to_index(name);
+ if (index == 0)
+ continue;
+ type = ll_index_to_type(index);
+ if (type == -1) {
+ fprintf(stderr, "Failed to get type of \"%s\"\n", name);
+ continue;
+ }
+ if (type != ARPHRD_TUNNEL && type != ARPHRD_IPGRE && type != ARPHRD_SIT)
+ continue;
+ memset(&p1, 0, sizeof(p1));
+ if (tnl_get_ioctl(name, &p1))
+ continue;
+ if ((p->link && p1.link != p->link) ||
+ (p->name[0] && strcmp(p1.name, p->name)) ||
+ (p->iph.daddr && p1.iph.daddr != p->iph.daddr) ||
+ (p->iph.saddr && p1.iph.saddr != p->iph.saddr) ||
+ (p->i_key && p1.i_key != p->i_key))
+ continue;
+ print_tunnel(&p1);
+ if (show_stats)
+ tnl_print_stats(ptr);
+ printf("\n");
+ }
+ err = 0;
+ end:
+ fclose(fp);
+ return err;
+}
+
+static int do_show(int argc, char **argv)
+{
+ struct ip_tunnel_parm p;
+ const char *basedev;
+
+ ll_init_map(&rth);
+ if (parse_args(argc, argv, SIOCGETTUNNEL, &p) < 0)
+ return -1;
+
+ basedev = tnl_defname(&p);
+ if (!basedev)
+ return do_tunnels_list(&p);
+
+ if (tnl_get_ioctl(p.name[0] ? p.name : basedev, &p))
+ return -1;
+
+ print_tunnel(&p);
+ printf("\n");
+ return 0;
+}
+
+static int do_prl(int argc, char **argv)
+{
+ struct ip_tunnel_prl p;
+ int count = 0;
+ int devname = 0;
+ int cmd = 0;
+ char medium[IFNAMSIZ];
+
+ memset(&p, 0, sizeof(p));
+ memset(&medium, 0, sizeof(medium));
+
+ while (argc > 0) {
+ if (strcmp(*argv, "prl-default") == 0) {
+ NEXT_ARG();
+ cmd = SIOCADDPRL;
+ p.addr = get_addr32(*argv);
+ p.flags |= PRL_DEFAULT;
+ count++;
+ } else if (strcmp(*argv, "prl-nodefault") == 0) {
+ NEXT_ARG();
+ cmd = SIOCADDPRL;
+ p.addr = get_addr32(*argv);
+ count++;
+ } else if (strcmp(*argv, "prl-delete") == 0) {
+ NEXT_ARG();
+ cmd = SIOCDELPRL;
+ p.addr = get_addr32(*argv);
+ count++;
+ } else if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ strncpy(medium, *argv, IFNAMSIZ-1);
+ devname++;
+ } else {
+ fprintf(stderr,
+ "Invalid PRL parameter \"%s\"\n", *argv);
+ exit(-1);
+ }
+ if (count > 1) {
+ fprintf(stderr,
+ "One PRL entry at a time\n");
+ exit(-1);
+ }
+ argc--; argv++;
+ }
+ if (devname == 0) {
+ fprintf(stderr, "Must specify device\n");
+ exit(-1);
+ }
+
+ return tnl_prl_ioctl(cmd, medium, &p);
+}
+
+static int do_6rd(int argc, char **argv)
+{
+ struct ip_tunnel_6rd ip6rd;
+ int devname = 0;
+ int cmd = 0;
+ char medium[IFNAMSIZ];
+ inet_prefix prefix;
+
+ memset(&ip6rd, 0, sizeof(ip6rd));
+ memset(&medium, 0, sizeof(medium));
+
+ while (argc > 0) {
+ if (strcmp(*argv, "6rd-prefix") == 0) {
+ NEXT_ARG();
+ if (get_prefix(&prefix, *argv, AF_INET6))
+ invarg("invalid 6rd_prefix\n", *argv);
+ cmd = SIOCADD6RD;
+ memcpy(&ip6rd.prefix, prefix.data, 16);
+ ip6rd.prefixlen = prefix.bitlen;
+ } else if (strcmp(*argv, "6rd-relay_prefix") == 0) {
+ NEXT_ARG();
+ if (get_prefix(&prefix, *argv, AF_INET))
+ invarg("invalid 6rd-relay_prefix\n", *argv);
+ cmd = SIOCADD6RD;
+ memcpy(&ip6rd.relay_prefix, prefix.data, 4);
+ ip6rd.relay_prefixlen = prefix.bitlen;
+ } else if (strcmp(*argv, "6rd-reset") == 0) {
+ cmd = SIOCDEL6RD;
+ } else if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ strncpy(medium, *argv, IFNAMSIZ-1);
+ devname++;
+ } else {
+ fprintf(stderr,
+ "Invalid 6RD parameter \"%s\"\n", *argv);
+ exit(-1);
+ }
+ argc--; argv++;
+ }
+ if (devname == 0) {
+ fprintf(stderr, "Must specify device\n");
+ exit(-1);
+ }
+
+ return tnl_6rd_ioctl(cmd, medium, &ip6rd);
+}
+
+static int tunnel_mode_is_ipv6(char *tunnel_mode)
+{
+ static const char * const ipv6_modes[] = {
+ "ipv6/ipv6", "ip6ip6",
+ "vti6",
+ "ip/ipv6", "ipv4/ipv6", "ipip6", "ip4ip6",
+ "ip6gre", "gre/ipv6",
+ "any/ipv6", "any"
+ };
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(ipv6_modes); i++) {
+ if (strcmp(ipv6_modes[i], tunnel_mode) == 0)
+ return 1;
+ }
+ return 0;
+}
+
+int do_iptunnel(int argc, char **argv)
+{
+ int i;
+
+ for (i = 0; i < argc - 1; i++) {
+ if (strcmp(argv[i], "mode") == 0) {
+ if (tunnel_mode_is_ipv6(argv[i + 1]))
+ preferred_family = AF_INET6;
+ break;
+ }
+ }
+ switch (preferred_family) {
+ case AF_UNSPEC:
+ preferred_family = AF_INET;
+ break;
+ case AF_INET:
+ break;
+ /*
+ * This is silly enough but we have no easy way to make it
+ * protocol-independent because of unarranged structure between
+ * IPv4 and IPv6.
+ */
+ case AF_INET6:
+ return do_ip6tunnel(argc, argv);
+ default:
+ fprintf(stderr, "Unsupported protocol family: %d\n", preferred_family);
+ exit(-1);
+ }
+
+ if (argc > 0) {
+ if (matches(*argv, "add") == 0)
+ return do_add(SIOCADDTUNNEL, argc - 1, argv + 1);
+ if (matches(*argv, "change") == 0)
+ return do_add(SIOCCHGTUNNEL, argc - 1, argv + 1);
+ if (matches(*argv, "delete") == 0)
+ return do_del(argc - 1, argv + 1);
+ if (matches(*argv, "show") == 0 ||
+ matches(*argv, "lst") == 0 ||
+ matches(*argv, "list") == 0)
+ return do_show(argc - 1, argv + 1);
+ if (matches(*argv, "prl") == 0)
+ return do_prl(argc - 1, argv + 1);
+ if (matches(*argv, "6rd") == 0)
+ return do_6rd(argc - 1, argv + 1);
+ if (matches(*argv, "help") == 0)
+ usage();
+ } else
+ return do_show(0, NULL);
+
+ fprintf(stderr, "Command \"%s\" is unknown, try \"ip tunnel help\"\n", *argv);
+ exit(-1);
+}
diff --git a/iproute2/ip/iptuntap.c b/iproute2/ip/iptuntap.c
new file mode 100644
index 0000000..b9b28a1
--- /dev/null
+++ b/iproute2/ip/iptuntap.c
@@ -0,0 +1,327 @@
+/*
+ * iptunnel.c "ip tuntap"
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: David Woodhouse <David.Woodhouse@intel.com>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+#include <sys/ioctl.h>
+#include <linux/if.h>
+#include <linux/if_tun.h>
+#include <pwd.h>
+#include <grp.h>
+#include <fcntl.h>
+#include <dirent.h>
+#include <errno.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+
+#define TUNDEV "/dev/net/tun"
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: ip tuntap { add | del | show | list | lst | help } [ dev PHYS_DEV ] \n");
+ fprintf(stderr, " [ mode { tun | tap } ] [ user USER ] [ group GROUP ]\n");
+ fprintf(stderr, " [ one_queue ] [ pi ] [ vnet_hdr ] [ multi_queue ]\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "Where: USER := { STRING | NUMBER }\n");
+ fprintf(stderr, " GROUP := { STRING | NUMBER }\n");
+ exit(-1);
+}
+
+static int tap_add_ioctl(struct ifreq *ifr, uid_t uid, gid_t gid)
+{
+ int fd;
+ int ret = -1;
+
+#ifdef IFF_TUN_EXCL
+ ifr->ifr_flags |= IFF_TUN_EXCL;
+#endif
+
+ fd = open(TUNDEV, O_RDWR);
+ if (fd < 0) {
+ perror("open");
+ return -1;
+ }
+ if (ioctl(fd, TUNSETIFF, ifr)) {
+ perror("ioctl(TUNSETIFF)");
+ goto out;
+ }
+ if (uid != -1 && ioctl(fd, TUNSETOWNER, uid)) {
+ perror("ioctl(TUNSETOWNER)");
+ goto out;
+ }
+ if (gid != -1 && ioctl(fd, TUNSETGROUP, gid)) {
+ perror("ioctl(TUNSETGROUP)");
+ goto out;
+ }
+ if (ioctl(fd, TUNSETPERSIST, 1)) {
+ perror("ioctl(TUNSETPERSIST)");
+ goto out;
+ }
+ ret = 0;
+ out:
+ close(fd);
+ return ret;
+}
+
+static int tap_del_ioctl(struct ifreq *ifr)
+{
+ int fd = open(TUNDEV, O_RDWR);
+ int ret = -1;
+
+ if (fd < 0) {
+ perror("open");
+ return -1;
+ }
+ if (ioctl(fd, TUNSETIFF, ifr)) {
+ perror("ioctl(TUNSETIFF)");
+ goto out;
+ }
+ if (ioctl(fd, TUNSETPERSIST, 0)) {
+ perror("ioctl(TUNSETPERSIST)");
+ goto out;
+ }
+ ret = 0;
+ out:
+ close(fd);
+ return ret;
+
+}
+static int parse_args(int argc, char **argv, struct ifreq *ifr, uid_t *uid, gid_t *gid)
+{
+ int count = 0;
+
+ memset(ifr, 0, sizeof(*ifr));
+
+ ifr->ifr_flags |= IFF_NO_PI;
+
+ while (argc > 0) {
+ if (matches(*argv, "mode") == 0) {
+ NEXT_ARG();
+ if (matches(*argv, "tun") == 0) {
+ if (ifr->ifr_flags & IFF_TAP) {
+ fprintf(stderr,"You managed to ask for more than one tunnel mode.\n");
+ exit(-1);
+ }
+ ifr->ifr_flags |= IFF_TUN;
+ } else if (matches(*argv, "tap") == 0) {
+ if (ifr->ifr_flags & IFF_TUN) {
+ fprintf(stderr,"You managed to ask for more than one tunnel mode.\n");
+ exit(-1);
+ }
+ ifr->ifr_flags |= IFF_TAP;
+ } else {
+ fprintf(stderr,"Unknown tunnel mode \"%s\"\n", *argv);
+ exit(-1);
+ }
+ } else if (uid && matches(*argv, "user") == 0) {
+ char *end;
+ unsigned long user;
+
+ NEXT_ARG();
+ if (**argv && ((user = strtol(*argv, &end, 10)), !*end))
+ *uid = user;
+ else {
+ struct passwd *pw = getpwnam(*argv);
+ if (!pw) {
+ fprintf(stderr, "invalid user \"%s\"\n", *argv);
+ exit(-1);
+ }
+ *uid = pw->pw_uid;
+ }
+ } else if (gid && matches(*argv, "group") == 0) {
+ char *end;
+ unsigned long group;
+
+ NEXT_ARG();
+
+ if (**argv && ((group = strtol(*argv, &end, 10)), !*end))
+ *gid = group;
+ else {
+ struct group *gr = getgrnam(*argv);
+ if (!gr) {
+ fprintf(stderr, "invalid group \"%s\"\n", *argv);
+ exit(-1);
+ }
+ *gid = gr->gr_gid;
+ }
+ } else if (matches(*argv, "pi") == 0) {
+ ifr->ifr_flags &= ~IFF_NO_PI;
+ } else if (matches(*argv, "one_queue") == 0) {
+ ifr->ifr_flags |= IFF_ONE_QUEUE;
+ } else if (matches(*argv, "vnet_hdr") == 0) {
+ ifr->ifr_flags |= IFF_VNET_HDR;
+ } else if (matches(*argv, "multi_queue") == 0) {
+ ifr->ifr_flags |= IFF_MULTI_QUEUE;
+ } else if (matches(*argv, "dev") == 0) {
+ NEXT_ARG();
+ strncpy(ifr->ifr_name, *argv, IFNAMSIZ-1);
+ } else {
+ if (matches(*argv, "name") == 0) {
+ NEXT_ARG();
+ } else if (matches(*argv, "help") == 0)
+ usage();
+ if (ifr->ifr_name[0])
+ duparg2("name", *argv);
+ strncpy(ifr->ifr_name, *argv, IFNAMSIZ);
+ }
+ count++;
+ argc--; argv++;
+ }
+
+ if (!(ifr->ifr_flags & TUN_TYPE_MASK)) {
+ fprintf(stderr, "You failed to specify a tunnel mode\n");
+ return -1;
+ }
+
+ return 0;
+}
+
+
+static int do_add(int argc, char **argv)
+{
+ struct ifreq ifr;
+ uid_t uid = -1;
+ gid_t gid = -1;
+
+ if (parse_args(argc, argv, &ifr, &uid, &gid) < 0)
+ return -1;
+
+ return tap_add_ioctl(&ifr, uid, gid);
+}
+
+static int do_del(int argc, char **argv)
+{
+ struct ifreq ifr;
+
+ if (parse_args(argc, argv, &ifr, NULL, NULL) < 0)
+ return -1;
+
+ return tap_del_ioctl(&ifr);
+}
+
+static int read_prop(char *dev, char *prop, long *value)
+{
+ char fname[IFNAMSIZ+25], buf[80], *endp;
+ ssize_t len;
+ int fd;
+ long result;
+
+ sprintf(fname, "/sys/class/net/%s/%s", dev, prop);
+ fd = open(fname, O_RDONLY);
+ if (fd < 0) {
+ if (strcmp(prop, "tun_flags"))
+ fprintf(stderr, "open %s: %s\n", fname,
+ strerror(errno));
+ return -1;
+ }
+ len = read(fd, buf, sizeof(buf)-1);
+ close(fd);
+ if (len < 0) {
+ fprintf(stderr, "read %s: %s", fname, strerror(errno));
+ return -1;
+ }
+
+ buf[len] = 0;
+ result = strtol(buf, &endp, 0);
+ if (*endp != '\n') {
+ fprintf(stderr, "Failed to parse %s\n", fname);
+ return -1;
+ }
+ *value = result;
+ return 0;
+}
+
+static void print_flags(long flags)
+{
+ if (flags & IFF_TUN)
+ printf(" tun");
+
+ if (flags & IFF_TAP)
+ printf(" tap");
+
+ if (!(flags & IFF_NO_PI))
+ printf(" pi");
+
+ if (flags & IFF_ONE_QUEUE)
+ printf(" one_queue");
+
+ if (flags & IFF_VNET_HDR)
+ printf(" vnet_hdr");
+
+ flags &= ~(IFF_TUN|IFF_TAP|IFF_NO_PI|IFF_ONE_QUEUE|IFF_VNET_HDR);
+ if (flags)
+ printf(" UNKNOWN_FLAGS:%lx", flags);
+}
+
+static int do_show(int argc, char **argv)
+{
+ DIR *dir;
+ struct dirent *d;
+ long flags, owner = -1, group = -1;
+
+ dir = opendir("/sys/class/net");
+ if (!dir) {
+ perror("opendir");
+ return -1;
+ }
+ while ((d = readdir(dir))) {
+ if (d->d_name[0] == '.' &&
+ (d->d_name[1] == 0 || d->d_name[1] == '.'))
+ continue;
+
+ if (read_prop(d->d_name, "tun_flags", &flags))
+ continue;
+
+ read_prop(d->d_name, "owner", &owner);
+ read_prop(d->d_name, "group", &group);
+
+ printf("%s:", d->d_name);
+ print_flags(flags);
+ if (owner != -1)
+ printf(" user %ld", owner);
+ if (group != -1)
+ printf(" group %ld", group);
+ printf("\n");
+ }
+ closedir(dir);
+ return 0;
+}
+
+int do_iptuntap(int argc, char **argv)
+{
+ if (argc > 0) {
+ if (matches(*argv, "add") == 0)
+ return do_add(argc-1, argv+1);
+ if (matches(*argv, "delete") == 0)
+ return do_del(argc-1, argv+1);
+ if (matches(*argv, "show") == 0 ||
+ matches(*argv, "lst") == 0 ||
+ matches(*argv, "list") == 0)
+ return do_show(argc-1, argv+1);
+ if (matches(*argv, "help") == 0)
+ usage();
+ } else
+ return do_show(0, NULL);
+
+ fprintf(stderr, "Command \"%s\" is unknown, try \"ip tuntap help\".\n",
+ *argv);
+ exit(-1);
+}
diff --git a/iproute2/ip/ipxfrm.c b/iproute2/ip/ipxfrm.c
new file mode 100644
index 0000000..e583abf
--- /dev/null
+++ b/iproute2/ip/ipxfrm.c
@@ -0,0 +1,1538 @@
+/* $USAGI: $ */
+
+/*
+ * Copyright (C)2004 USAGI/WIDE Project
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses>.
+ */
+/*
+ * based on ip.c, iproute.c
+ */
+/*
+ * Authors:
+ * Masahide NAKAMURA @USAGI
+ */
+
+#include <alloca.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <time.h>
+#include <netdb.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+
+#include "utils.h"
+#include "xfrm.h"
+#include "ip_common.h"
+
+#define STRBUF_SIZE (128)
+#define STRBUF_CAT(buf, str) \
+ do { \
+ int rest = sizeof(buf) - 1 - strlen(buf); \
+ if (rest > 0) { \
+ int len = strlen(str); \
+ if (len > rest) \
+ len = rest; \
+ strncat(buf, str, len); \
+ buf[sizeof(buf) - 1] = '\0'; \
+ } \
+ } while(0);
+
+struct xfrm_filter filter;
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr,
+ "Usage: ip xfrm XFRM-OBJECT { COMMAND | help }\n"
+ "where XFRM-OBJECT := state | policy | monitor\n");
+ exit(-1);
+}
+
+/* This is based on utils.c(inet_addr_match) */
+int xfrm_addr_match(xfrm_address_t *x1, xfrm_address_t *x2, int bits)
+{
+ __u32 *a1 = (__u32 *)x1;
+ __u32 *a2 = (__u32 *)x2;
+ int words = bits >> 0x05;
+
+ bits &= 0x1f;
+
+ if (words)
+ if (memcmp(a1, a2, words << 2))
+ return -1;
+
+ if (bits) {
+ __u32 w1, w2;
+ __u32 mask;
+
+ w1 = a1[words];
+ w2 = a2[words];
+
+ mask = htonl((0xffffffff) << (0x20 - bits));
+
+ if ((w1 ^ w2) & mask)
+ return 1;
+ }
+
+ return 0;
+}
+
+int xfrm_xfrmproto_is_ipsec(__u8 proto)
+{
+ return (proto == IPPROTO_ESP ||
+ proto == IPPROTO_AH ||
+ proto == IPPROTO_COMP);
+}
+
+int xfrm_xfrmproto_is_ro(__u8 proto)
+{
+ return (proto == IPPROTO_ROUTING ||
+ proto == IPPROTO_DSTOPTS);
+}
+
+struct typeent {
+ const char *t_name;
+ int t_type;
+};
+
+static const struct typeent xfrmproto_types[]= {
+ { "esp", IPPROTO_ESP }, { "ah", IPPROTO_AH }, { "comp", IPPROTO_COMP },
+ { "route2", IPPROTO_ROUTING }, { "hao", IPPROTO_DSTOPTS },
+ { "ipsec-any", IPSEC_PROTO_ANY },
+ { NULL, -1 }
+};
+
+int xfrm_xfrmproto_getbyname(char *name)
+{
+ int i;
+
+ for (i = 0; ; i++) {
+ const struct typeent *t = &xfrmproto_types[i];
+ if (!t->t_name || t->t_type == -1)
+ break;
+
+ if (strcmp(t->t_name, name) == 0)
+ return t->t_type;
+ }
+
+ return -1;
+}
+
+const char *strxf_xfrmproto(__u8 proto)
+{
+ static char str[16];
+ int i;
+
+ for (i = 0; ; i++) {
+ const struct typeent *t = &xfrmproto_types[i];
+ if (!t->t_name || t->t_type == -1)
+ break;
+
+ if (t->t_type == proto)
+ return t->t_name;
+ }
+
+ sprintf(str, "%u", proto);
+ return str;
+}
+
+static const struct typeent algo_types[]= {
+ { "enc", XFRMA_ALG_CRYPT }, { "auth", XFRMA_ALG_AUTH },
+ { "comp", XFRMA_ALG_COMP }, { "aead", XFRMA_ALG_AEAD },
+ { "auth-trunc", XFRMA_ALG_AUTH_TRUNC },
+ { NULL, -1 }
+};
+
+int xfrm_algotype_getbyname(char *name)
+{
+ int i;
+
+ for (i = 0; ; i++) {
+ const struct typeent *t = &algo_types[i];
+ if (!t->t_name || t->t_type == -1)
+ break;
+
+ if (strcmp(t->t_name, name) == 0)
+ return t->t_type;
+ }
+
+ return -1;
+}
+
+const char *strxf_algotype(int type)
+{
+ static char str[32];
+ int i;
+
+ for (i = 0; ; i++) {
+ const struct typeent *t = &algo_types[i];
+ if (!t->t_name || t->t_type == -1)
+ break;
+
+ if (t->t_type == type)
+ return t->t_name;
+ }
+
+ sprintf(str, "%d", type);
+ return str;
+}
+
+const char *strxf_mask8(__u8 mask)
+{
+ static char str[16];
+ const int sn = sizeof(mask) * 8 - 1;
+ __u8 b;
+ int i = 0;
+
+ for (b = (1 << sn); b > 0; b >>= 1)
+ str[i++] = ((b & mask) ? '1' : '0');
+ str[i] = '\0';
+
+ return str;
+}
+
+const char *strxf_mask32(__u32 mask)
+{
+ static char str[16];
+
+ sprintf(str, "%.8x", mask);
+
+ return str;
+}
+
+const char *strxf_share(__u8 share)
+{
+ static char str[32];
+
+ switch (share) {
+ case XFRM_SHARE_ANY:
+ strcpy(str, "any");
+ break;
+ case XFRM_SHARE_SESSION:
+ strcpy(str, "session");
+ break;
+ case XFRM_SHARE_USER:
+ strcpy(str, "user");
+ break;
+ case XFRM_SHARE_UNIQUE:
+ strcpy(str, "unique");
+ break;
+ default:
+ sprintf(str, "%u", share);
+ break;
+ }
+
+ return str;
+}
+
+const char *strxf_proto(__u8 proto)
+{
+ static char buf[32];
+ struct protoent *pp;
+ const char *p;
+
+ pp = getprotobynumber(proto);
+ if (pp)
+ p = pp->p_name;
+ else {
+ sprintf(buf, "%u", proto);
+ p = buf;
+ }
+
+ return p;
+}
+
+const char *strxf_ptype(__u8 ptype)
+{
+ static char str[16];
+
+ switch (ptype) {
+ case XFRM_POLICY_TYPE_MAIN:
+ strcpy(str, "main");
+ break;
+ case XFRM_POLICY_TYPE_SUB:
+ strcpy(str, "sub");
+ break;
+ default:
+ sprintf(str, "%u", ptype);
+ break;
+ }
+
+ return str;
+}
+
+void xfrm_id_info_print(xfrm_address_t *saddr, struct xfrm_id *id,
+ __u8 mode, __u32 reqid, __u16 family, int force_spi,
+ FILE *fp, const char *prefix, const char *title)
+{
+ char abuf[256];
+
+ if (title)
+ fputs(title, fp);
+
+ memset(abuf, '\0', sizeof(abuf));
+ fprintf(fp, "src %s ", rt_addr_n2a(family, sizeof(*saddr),
+ saddr, abuf, sizeof(abuf)));
+ memset(abuf, '\0', sizeof(abuf));
+ fprintf(fp, "dst %s", rt_addr_n2a(family, sizeof(id->daddr),
+ &id->daddr, abuf, sizeof(abuf)));
+ fprintf(fp, "%s", _SL_);
+
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, "\t");
+
+ fprintf(fp, "proto %s ", strxf_xfrmproto(id->proto));
+
+ if (show_stats > 0 || force_spi || id->spi) {
+ __u32 spi = ntohl(id->spi);
+ fprintf(fp, "spi 0x%08x", spi);
+ if (show_stats > 0)
+ fprintf(fp, "(%u)", spi);
+ fprintf(fp, " ");
+ }
+
+ fprintf(fp, "reqid %u", reqid);
+ if (show_stats > 0)
+ fprintf(fp, "(0x%08x)", reqid);
+ fprintf(fp, " ");
+
+ fprintf(fp, "mode ");
+ switch (mode) {
+ case XFRM_MODE_TRANSPORT:
+ fprintf(fp, "transport");
+ break;
+ case XFRM_MODE_TUNNEL:
+ fprintf(fp, "tunnel");
+ break;
+ case XFRM_MODE_ROUTEOPTIMIZATION:
+ fprintf(fp, "ro");
+ break;
+ case XFRM_MODE_IN_TRIGGER:
+ fprintf(fp, "in_trigger");
+ break;
+ case XFRM_MODE_BEET:
+ fprintf(fp, "beet");
+ break;
+ default:
+ fprintf(fp, "%u", mode);
+ break;
+ }
+ fprintf(fp, "%s", _SL_);
+}
+
+static const char *strxf_limit(__u64 limit)
+{
+ static char str[32];
+ if (limit == XFRM_INF)
+ strcpy(str, "(INF)");
+ else
+ sprintf(str, "%llu", (unsigned long long) limit);
+
+ return str;
+}
+
+void xfrm_stats_print(struct xfrm_stats *s, FILE *fp, const char *prefix)
+{
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, "stats:%s", _SL_);
+
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, " replay-window %u replay %u failed %u%s",
+ s->replay_window, s->replay, s->integrity_failed, _SL_);
+}
+
+static const char *strxf_time(__u64 time)
+{
+ static char str[32];
+
+ if (time == 0)
+ strcpy(str, "-");
+ else {
+ time_t t;
+ struct tm *tp;
+
+ /* XXX: treat time in the same manner of kernel's
+ * net/xfrm/xfrm_{user,state}.c
+ */
+ t = (long)time;
+ tp = localtime(&t);
+
+ strftime(str, sizeof(str), "%Y-%m-%d %T", tp);
+ }
+
+ return str;
+}
+
+void xfrm_lifetime_print(struct xfrm_lifetime_cfg *cfg,
+ struct xfrm_lifetime_cur *cur,
+ FILE *fp, const char *prefix)
+{
+ if (cfg) {
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, "lifetime config:%s",_SL_);
+
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, " limit: soft %s(bytes),",
+ strxf_limit(cfg->soft_byte_limit));
+ fprintf(fp, " hard %s(bytes)%s",
+ strxf_limit(cfg->hard_byte_limit), _SL_);
+
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, " limit: soft %s(packets),",
+ strxf_limit(cfg->soft_packet_limit));
+ fprintf(fp, " hard %s(packets)%s",
+ strxf_limit(cfg->hard_packet_limit), _SL_);
+
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, " expire add: soft %llu(sec), hard %llu(sec)%s",
+ (unsigned long long) cfg->soft_add_expires_seconds,
+ (unsigned long long) cfg->hard_add_expires_seconds,
+ _SL_);
+
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, " expire use: soft %llu(sec), hard %llu(sec)%s",
+ (unsigned long long) cfg->soft_use_expires_seconds,
+ (unsigned long long) cfg->hard_use_expires_seconds,
+ _SL_);
+ }
+ if (cur) {
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, "lifetime current:%s", _SL_);
+
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, " %llu(bytes), %llu(packets)%s",
+ (unsigned long long) cur->bytes,
+ (unsigned long long) cur->packets,
+ _SL_);
+
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, " add %s ", strxf_time(cur->add_time));
+ fprintf(fp, "use %s%s", strxf_time(cur->use_time), _SL_);
+ }
+}
+
+void xfrm_selector_print(struct xfrm_selector *sel, __u16 family,
+ FILE *fp, const char *prefix)
+{
+ char abuf[256];
+ __u16 f;
+
+ f = sel->family;
+ if (f == AF_UNSPEC)
+ f = family;
+ if (f == AF_UNSPEC)
+ f = preferred_family;
+
+ if (prefix)
+ fputs(prefix, fp);
+
+ memset(abuf, '\0', sizeof(abuf));
+ fprintf(fp, "src %s/%u ",
+ rt_addr_n2a(f, sizeof(sel->saddr), &sel->saddr,
+ abuf, sizeof(abuf)),
+ sel->prefixlen_s);
+
+ memset(abuf, '\0', sizeof(abuf));
+ fprintf(fp, "dst %s/%u ",
+ rt_addr_n2a(f, sizeof(sel->daddr), &sel->daddr,
+ abuf, sizeof(abuf)),
+ sel->prefixlen_d);
+
+ if (sel->proto)
+ fprintf(fp, "proto %s ", strxf_proto(sel->proto));
+ switch (sel->proto) {
+ case IPPROTO_TCP:
+ case IPPROTO_UDP:
+ case IPPROTO_SCTP:
+ case IPPROTO_DCCP:
+ default: /* XXX */
+ if (sel->sport_mask)
+ fprintf(fp, "sport %u ", ntohs(sel->sport));
+ if (sel->dport_mask)
+ fprintf(fp, "dport %u ", ntohs(sel->dport));
+ break;
+ case IPPROTO_ICMP:
+ case IPPROTO_ICMPV6:
+ /* type/code is stored at sport/dport in selector */
+ if (sel->sport_mask)
+ fprintf(fp, "type %u ", ntohs(sel->sport));
+ if (sel->dport_mask)
+ fprintf(fp, "code %u ", ntohs(sel->dport));
+ break;
+ case IPPROTO_GRE:
+ if (sel->sport_mask || sel->dport_mask)
+ fprintf(fp, "key %u ",
+ (((__u32)ntohs(sel->sport)) << 16) +
+ ntohs(sel->dport));
+ break;
+ case IPPROTO_MH:
+ if (sel->sport_mask)
+ fprintf(fp, "type %u ", ntohs(sel->sport));
+ if (sel->dport_mask) {
+ if (show_stats > 0)
+ fprintf(fp, "(dport) 0x%.4x ", sel->dport);
+ }
+ break;
+ }
+
+ if (sel->ifindex > 0)
+ fprintf(fp, "dev %s ", ll_index_to_name(sel->ifindex));
+
+ if (show_stats > 0)
+ fprintf(fp, "uid %u", sel->user);
+
+ fprintf(fp, "%s", _SL_);
+}
+
+static void __xfrm_algo_print(struct xfrm_algo *algo, int type, int len,
+ FILE *fp, const char *prefix, int newline)
+{
+ int keylen;
+ int i;
+
+ if (prefix)
+ fputs(prefix, fp);
+
+ fprintf(fp, "%s ", strxf_algotype(type));
+
+ if (len < sizeof(*algo)) {
+ fprintf(fp, "(ERROR truncated)");
+ goto fin;
+ }
+ len -= sizeof(*algo);
+
+ fprintf(fp, "%s ", algo->alg_name);
+
+ keylen = algo->alg_key_len / 8;
+ if (len < keylen) {
+ fprintf(fp, "(ERROR truncated)");
+ goto fin;
+ }
+
+ if (keylen > 0) {
+ fprintf(fp, "0x");
+ for (i = 0; i < keylen; i ++)
+ fprintf(fp, "%.2x", (unsigned char)algo->alg_key[i]);
+
+ if (show_stats > 0)
+ fprintf(fp, " (%d bits)", algo->alg_key_len);
+ }
+
+ fin:
+ if (newline)
+ fprintf(fp, "%s", _SL_);
+}
+
+static inline void xfrm_algo_print(struct xfrm_algo *algo, int type, int len,
+ FILE *fp, const char *prefix)
+{
+ return __xfrm_algo_print(algo, type, len, fp, prefix, 1);
+}
+
+static void xfrm_aead_print(struct xfrm_algo_aead *algo, int len,
+ FILE *fp, const char *prefix)
+{
+ struct xfrm_algo *base_algo = alloca(sizeof(*base_algo) + algo->alg_key_len / 8);
+
+ memcpy(base_algo->alg_name, algo->alg_name, sizeof(base_algo->alg_name));
+ base_algo->alg_key_len = algo->alg_key_len;
+ memcpy(base_algo->alg_key, algo->alg_key, algo->alg_key_len / 8);
+
+ __xfrm_algo_print(base_algo, XFRMA_ALG_AEAD, len, fp, prefix, 0);
+
+ fprintf(fp, " %d", algo->alg_icv_len);
+
+ fprintf(fp, "%s", _SL_);
+}
+
+static void xfrm_auth_trunc_print(struct xfrm_algo_auth *algo, int len,
+ FILE *fp, const char *prefix)
+{
+ struct xfrm_algo *base_algo = alloca(sizeof(*base_algo) + algo->alg_key_len / 8);
+
+ memcpy(base_algo->alg_name, algo->alg_name, sizeof(base_algo->alg_name));
+ base_algo->alg_key_len = algo->alg_key_len;
+ memcpy(base_algo->alg_key, algo->alg_key, algo->alg_key_len / 8);
+
+ __xfrm_algo_print(base_algo, XFRMA_ALG_AUTH_TRUNC, len, fp, prefix, 0);
+
+ fprintf(fp, " %d", algo->alg_trunc_len);
+
+ fprintf(fp, "%s", _SL_);
+}
+
+static void xfrm_tmpl_print(struct xfrm_user_tmpl *tmpls, int len,
+ FILE *fp, const char *prefix)
+{
+ int ntmpls = len / sizeof(struct xfrm_user_tmpl);
+ int i;
+
+ if (ntmpls <= 0) {
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, "(ERROR \"tmpl\" truncated)");
+ fprintf(fp, "%s", _SL_);
+ return;
+ }
+
+ for (i = 0; i < ntmpls; i++) {
+ struct xfrm_user_tmpl *tmpl = &tmpls[i];
+
+ if (prefix)
+ fputs(prefix, fp);
+
+ xfrm_id_info_print(&tmpl->saddr, &tmpl->id, tmpl->mode,
+ tmpl->reqid, tmpl->family, 0, fp, prefix, "tmpl ");
+
+ if (show_stats > 0 || tmpl->optional) {
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, "\t");
+ switch (tmpl->optional) {
+ case 0:
+ if (show_stats > 0)
+ fprintf(fp, "level required ");
+ break;
+ case 1:
+ fprintf(fp, "level use ");
+ break;
+ default:
+ fprintf(fp, "level %u ", tmpl->optional);
+ break;
+ }
+
+ if (show_stats > 0)
+ fprintf(fp, "share %s ", strxf_share(tmpl->share));
+
+ fprintf(fp, "%s", _SL_);
+ }
+
+ if (show_stats > 0) {
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, "\t");
+ fprintf(fp, "%s-mask %s ",
+ strxf_algotype(XFRMA_ALG_CRYPT),
+ strxf_mask32(tmpl->ealgos));
+ fprintf(fp, "%s-mask %s ",
+ strxf_algotype(XFRMA_ALG_AUTH),
+ strxf_mask32(tmpl->aalgos));
+ fprintf(fp, "%s-mask %s",
+ strxf_algotype(XFRMA_ALG_COMP),
+ strxf_mask32(tmpl->calgos));
+
+ fprintf(fp, "%s", _SL_);
+ }
+ }
+}
+
+int xfrm_parse_mark(struct xfrm_mark *mark, int *argcp, char ***argvp)
+{
+ int argc = *argcp;
+ char **argv = *argvp;
+
+ NEXT_ARG();
+ if (get_u32(&mark->v, *argv, 0)) {
+ invarg("MARK value is invalid\n", *argv);
+ }
+ if (argc > 1)
+ NEXT_ARG();
+ else { /* last entry on parse line */
+ mark->m = 0xffffffff;
+ goto done;
+ }
+
+ if (strcmp(*argv, "mask") == 0) {
+ NEXT_ARG();
+ if (get_u32(&mark->m, *argv, 0)) {
+ invarg("MASK value is invalid\n", *argv);
+ }
+ } else {
+ mark->m = 0xffffffff;
+ PREV_ARG();
+ }
+
+done:
+ *argcp = argc;
+ *argvp = argv;
+
+ return 0;
+}
+
+void xfrm_xfrma_print(struct rtattr *tb[], __u16 family,
+ FILE *fp, const char *prefix)
+{
+ if (tb[XFRMA_MARK]) {
+ struct rtattr *rta = tb[XFRMA_MARK];
+ struct xfrm_mark *m = (struct xfrm_mark *) RTA_DATA(rta);
+ fprintf(fp, "\tmark %#x/%#x", m->v, m->m);
+ fprintf(fp, "%s", _SL_);
+ }
+
+ if (tb[XFRMA_ALG_AUTH] && !tb[XFRMA_ALG_AUTH_TRUNC]) {
+ struct rtattr *rta = tb[XFRMA_ALG_AUTH];
+ xfrm_algo_print((struct xfrm_algo *) RTA_DATA(rta),
+ XFRMA_ALG_AUTH, RTA_PAYLOAD(rta), fp, prefix);
+ }
+
+ if (tb[XFRMA_ALG_AUTH_TRUNC]) {
+ struct rtattr *rta = tb[XFRMA_ALG_AUTH_TRUNC];
+ xfrm_auth_trunc_print((struct xfrm_algo_auth *) RTA_DATA(rta),
+ RTA_PAYLOAD(rta), fp, prefix);
+ }
+
+ if (tb[XFRMA_ALG_AEAD]) {
+ struct rtattr *rta = tb[XFRMA_ALG_AEAD];
+ xfrm_aead_print((struct xfrm_algo_aead *)RTA_DATA(rta),
+ RTA_PAYLOAD(rta), fp, prefix);
+ }
+
+ if (tb[XFRMA_ALG_CRYPT]) {
+ struct rtattr *rta = tb[XFRMA_ALG_CRYPT];
+ xfrm_algo_print((struct xfrm_algo *) RTA_DATA(rta),
+ XFRMA_ALG_CRYPT, RTA_PAYLOAD(rta), fp, prefix);
+ }
+
+ if (tb[XFRMA_ALG_COMP]) {
+ struct rtattr *rta = tb[XFRMA_ALG_COMP];
+ xfrm_algo_print((struct xfrm_algo *) RTA_DATA(rta),
+ XFRMA_ALG_COMP, RTA_PAYLOAD(rta), fp, prefix);
+ }
+
+ if (tb[XFRMA_ENCAP]) {
+ struct xfrm_encap_tmpl *e;
+ char abuf[256];
+
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, "encap ");
+
+ if (RTA_PAYLOAD(tb[XFRMA_ENCAP]) < sizeof(*e)) {
+ fprintf(fp, "(ERROR truncated)");
+ fprintf(fp, "%s", _SL_);
+ return;
+ }
+ e = (struct xfrm_encap_tmpl *) RTA_DATA(tb[XFRMA_ENCAP]);
+
+ fprintf(fp, "type ");
+ switch (e->encap_type) {
+ case 1:
+ fprintf(fp, "espinudp-nonike ");
+ break;
+ case 2:
+ fprintf(fp, "espinudp ");
+ break;
+ default:
+ fprintf(fp, "%u ", e->encap_type);
+ break;
+ }
+ fprintf(fp, "sport %u ", ntohs(e->encap_sport));
+ fprintf(fp, "dport %u ", ntohs(e->encap_dport));
+
+ memset(abuf, '\0', sizeof(abuf));
+ fprintf(fp, "addr %s",
+ rt_addr_n2a(family, sizeof(e->encap_oa), &e->encap_oa,
+ abuf, sizeof(abuf)));
+ fprintf(fp, "%s", _SL_);
+ }
+
+ if (tb[XFRMA_TMPL]) {
+ struct rtattr *rta = tb[XFRMA_TMPL];
+ xfrm_tmpl_print((struct xfrm_user_tmpl *) RTA_DATA(rta),
+ RTA_PAYLOAD(rta), fp, prefix);
+ }
+
+ if (tb[XFRMA_COADDR]) {
+ char abuf[256];
+ xfrm_address_t *coa;
+
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, "coa ");
+
+ coa = (xfrm_address_t *)RTA_DATA(tb[XFRMA_COADDR]);
+
+ if (RTA_PAYLOAD(tb[XFRMA_COADDR]) < sizeof(*coa)) {
+ fprintf(fp, "(ERROR truncated)");
+ fprintf(fp, "%s", _SL_);
+ return;
+ }
+
+ memset(abuf, '\0', sizeof(abuf));
+ fprintf(fp, "%s",
+ rt_addr_n2a(family, sizeof(*coa), coa,
+ abuf, sizeof(abuf)));
+ fprintf(fp, "%s", _SL_);
+ }
+
+ if (tb[XFRMA_LASTUSED]) {
+ __u64 lastused;
+
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, "lastused ");
+
+ if (RTA_PAYLOAD(tb[XFRMA_LASTUSED]) < sizeof(lastused)) {
+ fprintf(fp, "(ERROR truncated)");
+ fprintf(fp, "%s", _SL_);
+ return;
+ }
+
+ lastused = rta_getattr_u64(tb[XFRMA_LASTUSED]);
+
+ fprintf(fp, "%s", strxf_time(lastused));
+ fprintf(fp, "%s", _SL_);
+ }
+
+ if (tb[XFRMA_REPLAY_VAL]) {
+ struct xfrm_replay_state *replay;
+
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, "anti-replay context: ");
+
+ if (RTA_PAYLOAD(tb[XFRMA_REPLAY_VAL]) < sizeof(*replay)) {
+ fprintf(fp, "(ERROR truncated)");
+ fprintf(fp, "%s", _SL_);
+ return;
+ }
+
+ replay = (struct xfrm_replay_state *)RTA_DATA(tb[XFRMA_REPLAY_VAL]);
+ fprintf(fp, "seq 0x%x, oseq 0x%x, bitmap 0x%08x",
+ replay->seq, replay->oseq, replay->bitmap);
+ fprintf(fp, "%s", _SL_);
+ }
+
+ if (tb[XFRMA_REPLAY_ESN_VAL]) {
+ struct xfrm_replay_state_esn *replay;
+ unsigned int i, j;
+
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, "anti-replay esn context:");
+
+ if (RTA_PAYLOAD(tb[XFRMA_REPLAY_ESN_VAL]) < sizeof(*replay)) {
+ fprintf(fp, "(ERROR truncated)");
+ fprintf(fp, "%s", _SL_);
+ return;
+ }
+ fprintf(fp, "%s", _SL_);
+
+ replay = (struct xfrm_replay_state_esn *)RTA_DATA(tb[XFRMA_REPLAY_ESN_VAL]);
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, " seq-hi 0x%x, seq 0x%x, oseq-hi 0x%0x, oseq 0x%0x",
+ replay->seq_hi, replay->seq, replay->oseq_hi,
+ replay->oseq);
+ fprintf(fp, "%s", _SL_);
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, " replay_window %u, bitmap-length %u",
+ replay->replay_window, replay->bmp_len);
+ for (i = replay->bmp_len, j = 0; i; i--) {
+ if (j++ % 8 == 0) {
+ fprintf(fp, "%s", _SL_);
+ if (prefix)
+ fputs(prefix, fp);
+ fprintf(fp, " ");
+ }
+ fprintf(fp, "%08x ", replay->bmp[i - 1]);
+ }
+ fprintf(fp, "%s", _SL_);
+ }
+}
+
+static int xfrm_selector_iszero(struct xfrm_selector *s)
+{
+ struct xfrm_selector s0;
+
+ memset(&s0, 0, sizeof(s0));
+
+ return (memcmp(&s0, s, sizeof(s0)) == 0);
+}
+
+void xfrm_state_info_print(struct xfrm_usersa_info *xsinfo,
+ struct rtattr *tb[], FILE *fp, const char *prefix,
+ const char *title)
+{
+ char buf[STRBUF_SIZE];
+ int force_spi = xfrm_xfrmproto_is_ipsec(xsinfo->id.proto);
+
+ memset(buf, '\0', sizeof(buf));
+
+ xfrm_id_info_print(&xsinfo->saddr, &xsinfo->id, xsinfo->mode,
+ xsinfo->reqid, xsinfo->family, force_spi, fp,
+ prefix, title);
+
+ if (prefix)
+ STRBUF_CAT(buf, prefix);
+ STRBUF_CAT(buf, "\t");
+
+ fputs(buf, fp);
+ fprintf(fp, "replay-window %u ", xsinfo->replay_window);
+ if (show_stats > 0)
+ fprintf(fp, "seq 0x%08u ", xsinfo->seq);
+ if (show_stats > 0 || xsinfo->flags) {
+ __u8 flags = xsinfo->flags;
+
+ fprintf(fp, "flag ");
+ XFRM_FLAG_PRINT(fp, flags, XFRM_STATE_NOECN, "noecn");
+ XFRM_FLAG_PRINT(fp, flags, XFRM_STATE_DECAP_DSCP, "decap-dscp");
+ XFRM_FLAG_PRINT(fp, flags, XFRM_STATE_NOPMTUDISC, "nopmtudisc");
+ XFRM_FLAG_PRINT(fp, flags, XFRM_STATE_WILDRECV, "wildrecv");
+ XFRM_FLAG_PRINT(fp, flags, XFRM_STATE_ICMP, "icmp");
+ XFRM_FLAG_PRINT(fp, flags, XFRM_STATE_AF_UNSPEC, "af-unspec");
+ XFRM_FLAG_PRINT(fp, flags, XFRM_STATE_ALIGN4, "align4");
+ XFRM_FLAG_PRINT(fp, flags, XFRM_STATE_ESN, "esn");
+ if (flags)
+ fprintf(fp, "%x", flags);
+ }
+ if (show_stats > 0 && tb[XFRMA_SA_EXTRA_FLAGS]) {
+ __u32 extra_flags = *(__u32 *)RTA_DATA(tb[XFRMA_SA_EXTRA_FLAGS]);
+
+ fprintf(fp, "extra_flag ");
+ XFRM_FLAG_PRINT(fp, extra_flags,
+ XFRM_SA_XFLAG_DONT_ENCAP_DSCP,
+ "dont-encap-dscp");
+ if (extra_flags)
+ fprintf(fp, "%x", extra_flags);
+ }
+ if (show_stats > 0)
+ fprintf(fp, " (0x%s)", strxf_mask8(xsinfo->flags));
+ fprintf(fp, "%s", _SL_);
+
+ xfrm_xfrma_print(tb, xsinfo->family, fp, buf);
+
+ if (!xfrm_selector_iszero(&xsinfo->sel)) {
+ char sbuf[STRBUF_SIZE];
+
+ memcpy(sbuf, buf, sizeof(sbuf));
+ STRBUF_CAT(sbuf, "sel ");
+
+ xfrm_selector_print(&xsinfo->sel, xsinfo->family, fp, sbuf);
+ }
+
+ if (show_stats > 0) {
+ xfrm_lifetime_print(&xsinfo->lft, &xsinfo->curlft, fp, buf);
+ xfrm_stats_print(&xsinfo->stats, fp, buf);
+ }
+
+ if (tb[XFRMA_SEC_CTX]) {
+ struct xfrm_user_sec_ctx *sctx;
+
+ fprintf(fp, "\tsecurity context ");
+
+ if (RTA_PAYLOAD(tb[XFRMA_SEC_CTX]) < sizeof(*sctx))
+ fprintf(fp, "(ERROR truncated)");
+
+ sctx = (struct xfrm_user_sec_ctx *)RTA_DATA(tb[XFRMA_SEC_CTX]);
+
+ fprintf(fp, "%s %s", (char *)(sctx + 1), _SL_);
+ }
+
+}
+
+void xfrm_policy_info_print(struct xfrm_userpolicy_info *xpinfo,
+ struct rtattr *tb[], FILE *fp, const char *prefix,
+ const char *title)
+{
+ char buf[STRBUF_SIZE];
+
+ memset(buf, '\0', sizeof(buf));
+
+ xfrm_selector_print(&xpinfo->sel, preferred_family, fp, title);
+
+ if (tb[XFRMA_SEC_CTX]) {
+ struct xfrm_user_sec_ctx *sctx;
+
+ fprintf(fp, "\tsecurity context ");
+
+ if (RTA_PAYLOAD(tb[XFRMA_SEC_CTX]) < sizeof(*sctx))
+ fprintf(fp, "(ERROR truncated)");
+
+ sctx = (struct xfrm_user_sec_ctx *)RTA_DATA(tb[XFRMA_SEC_CTX]);
+
+ fprintf(fp, "%s ", (char *)(sctx + 1));
+ fprintf(fp, "%s", _SL_);
+ }
+
+ if (prefix)
+ STRBUF_CAT(buf, prefix);
+ STRBUF_CAT(buf, "\t");
+
+ fputs(buf, fp);
+ if (xpinfo->dir >= XFRM_POLICY_MAX) {
+ xpinfo->dir -= XFRM_POLICY_MAX;
+ fprintf(fp, "socket ");
+ } else
+ fprintf(fp, "dir ");
+
+ switch (xpinfo->dir) {
+ case XFRM_POLICY_IN:
+ fprintf(fp, "in");
+ break;
+ case XFRM_POLICY_OUT:
+ fprintf(fp, "out");
+ break;
+ case XFRM_POLICY_FWD:
+ fprintf(fp, "fwd");
+ break;
+ default:
+ fprintf(fp, "%u", xpinfo->dir);
+ break;
+ }
+ fprintf(fp, " ");
+
+ switch (xpinfo->action) {
+ case XFRM_POLICY_ALLOW:
+ if (show_stats > 0)
+ fprintf(fp, "action allow ");
+ break;
+ case XFRM_POLICY_BLOCK:
+ fprintf(fp, "action block ");
+ break;
+ default:
+ fprintf(fp, "action %u ", xpinfo->action);
+ break;
+ }
+
+ if (show_stats)
+ fprintf(fp, "index %u ", xpinfo->index);
+ fprintf(fp, "priority %u ", xpinfo->priority);
+
+ if (tb[XFRMA_POLICY_TYPE]) {
+ struct xfrm_userpolicy_type *upt;
+
+ fprintf(fp, "ptype ");
+
+ if (RTA_PAYLOAD(tb[XFRMA_POLICY_TYPE]) < sizeof(*upt))
+ fprintf(fp, "(ERROR truncated)");
+
+ upt = (struct xfrm_userpolicy_type *)RTA_DATA(tb[XFRMA_POLICY_TYPE]);
+ fprintf(fp, "%s ", strxf_ptype(upt->type));
+ }
+
+ if (show_stats > 0)
+ fprintf(fp, "share %s ", strxf_share(xpinfo->share));
+
+ if (show_stats > 0 || xpinfo->flags) {
+ __u8 flags = xpinfo->flags;
+
+ fprintf(fp, "flag ");
+ XFRM_FLAG_PRINT(fp, flags, XFRM_POLICY_LOCALOK, "localok");
+ XFRM_FLAG_PRINT(fp, flags, XFRM_POLICY_ICMP, "icmp");
+ if (flags)
+ fprintf(fp, "%x", flags);
+ }
+ if (show_stats > 0)
+ fprintf(fp, " (0x%s)", strxf_mask8(xpinfo->flags));
+ fprintf(fp, "%s", _SL_);
+
+ if (show_stats > 0)
+ xfrm_lifetime_print(&xpinfo->lft, &xpinfo->curlft, fp, buf);
+
+ xfrm_xfrma_print(tb, xpinfo->sel.family, fp, buf);
+}
+
+int xfrm_id_parse(xfrm_address_t *saddr, struct xfrm_id *id, __u16 *family,
+ int loose, int *argcp, char ***argvp)
+{
+ int argc = *argcp;
+ char **argv = *argvp;
+ inet_prefix dst;
+ inet_prefix src;
+
+ memset(&dst, 0, sizeof(dst));
+ memset(&src, 0, sizeof(src));
+
+ while (1) {
+ if (strcmp(*argv, "src") == 0) {
+ NEXT_ARG();
+
+ get_prefix(&src, *argv, preferred_family);
+ if (src.family == AF_UNSPEC)
+ invarg("value after \"src\" has an unrecognized address family", *argv);
+ if (family)
+ *family = src.family;
+
+ memcpy(saddr, &src.data, sizeof(*saddr));
+
+ filter.id_src_mask = src.bitlen;
+
+ } else if (strcmp(*argv, "dst") == 0) {
+ NEXT_ARG();
+
+ get_prefix(&dst, *argv, preferred_family);
+ if (dst.family == AF_UNSPEC)
+ invarg("value after \"dst\" has an unrecognized address family", *argv);
+ if (family)
+ *family = dst.family;
+
+ memcpy(&id->daddr, &dst.data, sizeof(id->daddr));
+
+ filter.id_dst_mask = dst.bitlen;
+
+ } else if (strcmp(*argv, "proto") == 0) {
+ int ret;
+
+ NEXT_ARG();
+
+ ret = xfrm_xfrmproto_getbyname(*argv);
+ if (ret < 0)
+ invarg("XFRM-PROTO value is invalid", *argv);
+
+ id->proto = (__u8)ret;
+
+ filter.id_proto_mask = XFRM_FILTER_MASK_FULL;
+
+ } else if (strcmp(*argv, "spi") == 0) {
+ __u32 spi;
+
+ NEXT_ARG();
+ if (get_u32(&spi, *argv, 0))
+ invarg("SPI value is invalid", *argv);
+
+ spi = htonl(spi);
+ id->spi = spi;
+
+ filter.id_spi_mask = XFRM_FILTER_MASK_FULL;
+
+ } else {
+ PREV_ARG(); /* back track */
+ break;
+ }
+
+ if (!NEXT_ARG_OK())
+ break;
+ NEXT_ARG();
+ }
+
+ if (src.family && dst.family && (src.family != dst.family))
+ invarg("the same address family is required between values after \"src\" and \"dst\"", *argv);
+
+ if (id->spi && id->proto) {
+ if (xfrm_xfrmproto_is_ro(id->proto)) {
+ fprintf(stderr, "\"spi\" is invalid with XFRM-PROTO value \"%s\"\n",
+ strxf_xfrmproto(id->proto));
+ exit(1);
+ } else if (id->proto == IPPROTO_COMP && ntohl(id->spi) >= 0x10000) {
+ fprintf(stderr, "SPI value is too large with XFRM-PROTO value \"%s\"\n",
+ strxf_xfrmproto(id->proto));
+ exit(1);
+ }
+ }
+
+ if (loose == 0 && id->proto == 0)
+ missarg("XFRM-PROTO");
+ if (argc == *argcp)
+ missarg("ID");
+
+ *argcp = argc;
+ *argvp = argv;
+
+ return 0;
+}
+
+int xfrm_mode_parse(__u8 *mode, int *argcp, char ***argvp)
+{
+ int argc = *argcp;
+ char **argv = *argvp;
+
+ if (matches(*argv, "transport") == 0)
+ *mode = XFRM_MODE_TRANSPORT;
+ else if (matches(*argv, "tunnel") == 0)
+ *mode = XFRM_MODE_TUNNEL;
+ else if (matches(*argv, "ro") == 0)
+ *mode = XFRM_MODE_ROUTEOPTIMIZATION;
+ else if (matches(*argv, "in_trigger") == 0)
+ *mode = XFRM_MODE_IN_TRIGGER;
+ else if (matches(*argv, "beet") == 0)
+ *mode = XFRM_MODE_BEET;
+ else
+ invarg("MODE value is invalid", *argv);
+
+ *argcp = argc;
+ *argvp = argv;
+
+ return 0;
+}
+
+int xfrm_encap_type_parse(__u16 *type, int *argcp, char ***argvp)
+{
+ int argc = *argcp;
+ char **argv = *argvp;
+
+ if (strcmp(*argv, "espinudp-nonike") == 0)
+ *type = 1;
+ else if (strcmp(*argv, "espinudp") == 0)
+ *type = 2;
+ else
+ invarg("ENCAP-TYPE value is invalid", *argv);
+
+ *argcp = argc;
+ *argvp = argv;
+
+ return 0;
+}
+
+/* NOTE: reqid is used by host-byte order */
+int xfrm_reqid_parse(__u32 *reqid, int *argcp, char ***argvp)
+{
+ int argc = *argcp;
+ char **argv = *argvp;
+
+ if (get_u32(reqid, *argv, 0))
+ invarg("REQID value is invalid", *argv);
+
+ *argcp = argc;
+ *argvp = argv;
+
+ return 0;
+}
+
+static int xfrm_selector_upspec_parse(struct xfrm_selector *sel,
+ int *argcp, char ***argvp)
+{
+ int argc = *argcp;
+ char **argv = *argvp;
+ char *sportp = NULL;
+ char *dportp = NULL;
+ char *typep = NULL;
+ char *codep = NULL;
+ char *grekey = NULL;
+
+ while (1) {
+ if (strcmp(*argv, "proto") == 0) {
+ __u8 upspec;
+
+ NEXT_ARG();
+
+ if (strcmp(*argv, "any") == 0)
+ upspec = 0;
+ else {
+ struct protoent *pp;
+ pp = getprotobyname(*argv);
+ if (pp)
+ upspec = pp->p_proto;
+ else {
+ if (get_u8(&upspec, *argv, 0))
+ invarg("PROTO value is invalid", *argv);
+ }
+ }
+ sel->proto = upspec;
+
+ filter.upspec_proto_mask = XFRM_FILTER_MASK_FULL;
+
+ } else if (strcmp(*argv, "sport") == 0) {
+ sportp = *argv;
+
+ NEXT_ARG();
+
+ if (get_u16(&sel->sport, *argv, 0))
+ invarg("value after \"sport\" is invalid", *argv);
+ sel->sport = htons(sel->sport);
+ if (sel->sport)
+ sel->sport_mask = ~((__u16)0);
+
+ filter.upspec_sport_mask = XFRM_FILTER_MASK_FULL;
+
+ } else if (strcmp(*argv, "dport") == 0) {
+ dportp = *argv;
+
+ NEXT_ARG();
+
+ if (get_u16(&sel->dport, *argv, 0))
+ invarg("value after \"dport\" is invalid", *argv);
+ sel->dport = htons(sel->dport);
+ if (sel->dport)
+ sel->dport_mask = ~((__u16)0);
+
+ filter.upspec_dport_mask = XFRM_FILTER_MASK_FULL;
+
+ } else if (strcmp(*argv, "type") == 0) {
+ typep = *argv;
+
+ NEXT_ARG();
+
+ if (get_u16(&sel->sport, *argv, 0) ||
+ (sel->sport & ~((__u16)0xff)))
+ invarg("value after \"type\" is invalid", *argv);
+ sel->sport = htons(sel->sport);
+ sel->sport_mask = ~((__u16)0);
+
+ filter.upspec_sport_mask = XFRM_FILTER_MASK_FULL;
+
+
+ } else if (strcmp(*argv, "code") == 0) {
+ codep = *argv;
+
+ NEXT_ARG();
+
+ if (get_u16(&sel->dport, *argv, 0) ||
+ (sel->dport & ~((__u16)0xff)))
+ invarg("value after \"code\" is invalid", *argv);
+ sel->dport = htons(sel->dport);
+ sel->dport_mask = ~((__u16)0);
+
+ filter.upspec_dport_mask = XFRM_FILTER_MASK_FULL;
+
+ } else if (strcmp(*argv, "key") == 0) {
+ unsigned uval;
+
+ grekey = *argv;
+
+ NEXT_ARG();
+
+ if (strchr(*argv, '.'))
+ uval = htonl(get_addr32(*argv));
+ else {
+ if (get_unsigned(&uval, *argv, 0)<0) {
+ fprintf(stderr, "value after \"key\" is invalid\n");
+ exit(-1);
+ }
+ }
+
+ sel->sport = htons(uval >> 16);
+ sel->dport = htons(uval & 0xffff);
+ sel->sport_mask = ~((__u16)0);
+ sel->dport_mask = ~((__u16)0);
+
+ filter.upspec_dport_mask = XFRM_FILTER_MASK_FULL;
+
+ } else {
+ PREV_ARG(); /* back track */
+ break;
+ }
+
+ if (!NEXT_ARG_OK())
+ break;
+ NEXT_ARG();
+ }
+ if (argc == *argcp)
+ missarg("UPSPEC");
+ if (sportp || dportp) {
+ switch (sel->proto) {
+ case IPPROTO_TCP:
+ case IPPROTO_UDP:
+ case IPPROTO_SCTP:
+ case IPPROTO_DCCP:
+ case IPPROTO_IP: /* to allow shared SA for different protocols */
+ break;
+ default:
+ fprintf(stderr, "\"sport\" and \"dport\" are invalid with PROTO value \"%s\"\n", strxf_proto(sel->proto));
+ exit(1);
+ }
+ }
+ if (typep || codep) {
+ switch (sel->proto) {
+ case IPPROTO_ICMP:
+ case IPPROTO_ICMPV6:
+ case IPPROTO_MH:
+ break;
+ default:
+ fprintf(stderr, "\"type\" and \"code\" are invalid with PROTO value \"%s\"\n", strxf_proto(sel->proto));
+ exit(1);
+ }
+ }
+ if (grekey) {
+ switch (sel->proto) {
+ case IPPROTO_GRE:
+ break;
+ default:
+ fprintf(stderr, "\"key\" is invalid with PROTO value \"%s\"\n", strxf_proto(sel->proto));
+ exit(1);
+ }
+ }
+
+ *argcp = argc;
+ *argvp = argv;
+
+ return 0;
+}
+
+int xfrm_selector_parse(struct xfrm_selector *sel, int *argcp, char ***argvp)
+{
+ int argc = *argcp;
+ char **argv = *argvp;
+ inet_prefix dst;
+ inet_prefix src;
+ char *upspecp = NULL;
+
+ memset(&dst, 0, sizeof(dst));
+ memset(&src, 0, sizeof(src));
+
+ while (1) {
+ if (strcmp(*argv, "src") == 0) {
+ NEXT_ARG();
+
+ get_prefix(&src, *argv, preferred_family);
+ if (src.family == AF_UNSPEC)
+ invarg("value after \"src\" has an unrecognized address family", *argv);
+ sel->family = src.family;
+
+ memcpy(&sel->saddr, &src.data, sizeof(sel->saddr));
+ sel->prefixlen_s = src.bitlen;
+
+ filter.sel_src_mask = src.bitlen;
+
+ } else if (strcmp(*argv, "dst") == 0) {
+ NEXT_ARG();
+
+ get_prefix(&dst, *argv, preferred_family);
+ if (dst.family == AF_UNSPEC)
+ invarg("value after \"dst\" has an unrecognized address family", *argv);
+ sel->family = dst.family;
+
+ memcpy(&sel->daddr, &dst.data, sizeof(sel->daddr));
+ sel->prefixlen_d = dst.bitlen;
+
+ filter.sel_dst_mask = dst.bitlen;
+
+ } else if (strcmp(*argv, "dev") == 0) {
+ int ifindex;
+
+ NEXT_ARG();
+
+ if (strcmp(*argv, "none") == 0)
+ ifindex = 0;
+ else {
+ ifindex = ll_name_to_index(*argv);
+ if (ifindex <= 0)
+ invarg("DEV value is invalid", *argv);
+ }
+ sel->ifindex = ifindex;
+
+ filter.sel_dev_mask = XFRM_FILTER_MASK_FULL;
+
+ } else {
+ if (upspecp) {
+ PREV_ARG(); /* back track */
+ break;
+ } else {
+ upspecp = *argv;
+ xfrm_selector_upspec_parse(sel, &argc, &argv);
+ }
+ }
+
+ if (!NEXT_ARG_OK())
+ break;
+
+ NEXT_ARG();
+ }
+
+ if (src.family && dst.family && (src.family != dst.family))
+ invarg("the same address family is required between values after \"src\" and \"dst\"", *argv);
+
+ if (argc == *argcp)
+ missarg("SELECTOR");
+
+ *argcp = argc;
+ *argvp = argv;
+
+ return 0;
+}
+
+int xfrm_lifetime_cfg_parse(struct xfrm_lifetime_cfg *lft,
+ int *argcp, char ***argvp)
+{
+ int argc = *argcp;
+ char **argv = *argvp;
+ int ret;
+
+ if (strcmp(*argv, "time-soft") == 0) {
+ NEXT_ARG();
+ ret = get_u64(&lft->soft_add_expires_seconds, *argv, 0);
+ if (ret)
+ invarg("value after \"time-soft\" is invalid", *argv);
+ } else if (strcmp(*argv, "time-hard") == 0) {
+ NEXT_ARG();
+ ret = get_u64(&lft->hard_add_expires_seconds, *argv, 0);
+ if (ret)
+ invarg("value after \"time-hard\" is invalid", *argv);
+ } else if (strcmp(*argv, "time-use-soft") == 0) {
+ NEXT_ARG();
+ ret = get_u64(&lft->soft_use_expires_seconds, *argv, 0);
+ if (ret)
+ invarg("value after \"time-use-soft\" is invalid", *argv);
+ } else if (strcmp(*argv, "time-use-hard") == 0) {
+ NEXT_ARG();
+ ret = get_u64(&lft->hard_use_expires_seconds, *argv, 0);
+ if (ret)
+ invarg("value after \"time-use-hard\" is invalid", *argv);
+ } else if (strcmp(*argv, "byte-soft") == 0) {
+ NEXT_ARG();
+ ret = get_u64(&lft->soft_byte_limit, *argv, 0);
+ if (ret)
+ invarg("value after \"byte-soft\" is invalid", *argv);
+ } else if (strcmp(*argv, "byte-hard") == 0) {
+ NEXT_ARG();
+ ret = get_u64(&lft->hard_byte_limit, *argv, 0);
+ if (ret)
+ invarg("value after \"byte-hard\" is invalid", *argv);
+ } else if (strcmp(*argv, "packet-soft") == 0) {
+ NEXT_ARG();
+ ret = get_u64(&lft->soft_packet_limit, *argv, 0);
+ if (ret)
+ invarg("value after \"packet-soft\" is invalid", *argv);
+ } else if (strcmp(*argv, "packet-hard") == 0) {
+ NEXT_ARG();
+ ret = get_u64(&lft->hard_packet_limit, *argv, 0);
+ if (ret)
+ invarg("value after \"packet-hard\" is invalid", *argv);
+ } else
+ invarg("LIMIT value is invalid", *argv);
+
+ *argcp = argc;
+ *argvp = argv;
+
+ return 0;
+}
+
+int do_xfrm(int argc, char **argv)
+{
+ memset(&filter, 0, sizeof(filter));
+
+ if (argc < 1)
+ usage();
+
+ if (matches(*argv, "state") == 0 ||
+ matches(*argv, "sa") == 0)
+ return do_xfrm_state(argc-1, argv+1);
+ else if (matches(*argv, "policy") == 0)
+ return do_xfrm_policy(argc-1, argv+1);
+ else if (matches(*argv, "monitor") == 0)
+ return do_xfrm_monitor(argc-1, argv+1);
+ else if (matches(*argv, "help") == 0) {
+ usage();
+ fprintf(stderr, "xfrm Object \"%s\" is unknown.\n", *argv);
+ exit(-1);
+ }
+ usage();
+}
diff --git a/iproute2/ip/link_gre.c b/iproute2/ip/link_gre.c
new file mode 100644
index 0000000..c85741f
--- /dev/null
+++ b/iproute2/ip/link_gre.c
@@ -0,0 +1,491 @@
+/*
+ * link_gre.c gre driver module
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Herbert Xu <herbert@gondor.apana.org.au>
+ *
+ */
+
+#include <string.h>
+#include <net/if.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+
+#include <linux/ip.h>
+#include <linux/if_tunnel.h>
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+#include "tunnel.h"
+
+static void print_usage(FILE *f)
+{
+ fprintf(f, "Usage: ip link { add | set | change | replace | del } NAME\n");
+ fprintf(f, " type { gre | gretap } [ remote ADDR ] [ local ADDR ]\n");
+ fprintf(f, " [ [i|o]seq ] [ [i|o]key KEY ] [ [i|o]csum ]\n");
+ fprintf(f, " [ ttl TTL ] [ tos TOS ] [ [no]pmtudisc ] [ dev PHYS_DEV ]\n");
+ fprintf(f, " [ noencap ] [ encap { fou | gue | none } ]\n");
+ fprintf(f, " [ encap-sport PORT ] [ encap-dport PORT ]\n");
+ fprintf(f, " [ [no]encap-csum ] [ [no]encap-csum6 ] [ [no]encap-remcsum ]\n");
+ fprintf(f, "\n");
+ fprintf(f, "Where: NAME := STRING\n");
+ fprintf(f, " ADDR := { IP_ADDRESS | any }\n");
+ fprintf(f, " TOS := { NUMBER | inherit }\n");
+ fprintf(f, " TTL := { 1..255 | inherit }\n");
+ fprintf(f, " KEY := { DOTTED_QUAD | NUMBER }\n");
+}
+
+static void usage(void) __attribute__((noreturn));
+static void usage(void)
+{
+ print_usage(stderr);
+ exit(-1);
+}
+
+static int gre_parse_opt(struct link_util *lu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ struct {
+ struct nlmsghdr n;
+ struct ifinfomsg i;
+ char buf[16384];
+ } req;
+ struct ifinfomsg *ifi = (struct ifinfomsg *)(n + 1);
+ struct rtattr *tb[IFLA_MAX + 1];
+ struct rtattr *linkinfo[IFLA_INFO_MAX+1];
+ struct rtattr *greinfo[IFLA_GRE_MAX + 1];
+ __u16 iflags = 0;
+ __u16 oflags = 0;
+ unsigned ikey = 0;
+ unsigned okey = 0;
+ unsigned saddr = 0;
+ unsigned daddr = 0;
+ unsigned link = 0;
+ __u8 pmtudisc = 1;
+ __u8 ttl = 0;
+ __u8 tos = 0;
+ int len;
+ __u16 encaptype = 0;
+ __u16 encapflags = 0;
+ __u16 encapsport = 0;
+ __u16 encapdport = 0;
+ __u8 metadata = 0;
+
+ if (!(n->nlmsg_flags & NLM_F_CREATE)) {
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(*ifi));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = RTM_GETLINK;
+ req.i.ifi_family = preferred_family;
+ req.i.ifi_index = ifi->ifi_index;
+
+ if (rtnl_talk(&rth, &req.n, &req.n, sizeof(req)) < 0) {
+get_failed:
+ fprintf(stderr,
+ "Failed to get existing tunnel info.\n");
+ return -1;
+ }
+
+ len = req.n.nlmsg_len;
+ len -= NLMSG_LENGTH(sizeof(*ifi));
+ if (len < 0)
+ goto get_failed;
+
+ parse_rtattr(tb, IFLA_MAX, IFLA_RTA(&req.i), len);
+
+ if (!tb[IFLA_LINKINFO])
+ goto get_failed;
+
+ parse_rtattr_nested(linkinfo, IFLA_INFO_MAX, tb[IFLA_LINKINFO]);
+
+ if (!linkinfo[IFLA_INFO_DATA])
+ goto get_failed;
+
+ parse_rtattr_nested(greinfo, IFLA_GRE_MAX,
+ linkinfo[IFLA_INFO_DATA]);
+
+ if (greinfo[IFLA_GRE_IKEY])
+ ikey = rta_getattr_u32(greinfo[IFLA_GRE_IKEY]);
+
+ if (greinfo[IFLA_GRE_OKEY])
+ okey = rta_getattr_u32(greinfo[IFLA_GRE_OKEY]);
+
+ if (greinfo[IFLA_GRE_IFLAGS])
+ iflags = rta_getattr_u16(greinfo[IFLA_GRE_IFLAGS]);
+
+ if (greinfo[IFLA_GRE_OFLAGS])
+ oflags = rta_getattr_u16(greinfo[IFLA_GRE_OFLAGS]);
+
+ if (greinfo[IFLA_GRE_LOCAL])
+ saddr = rta_getattr_u32(greinfo[IFLA_GRE_LOCAL]);
+
+ if (greinfo[IFLA_GRE_REMOTE])
+ daddr = rta_getattr_u32(greinfo[IFLA_GRE_REMOTE]);
+
+ if (greinfo[IFLA_GRE_PMTUDISC])
+ pmtudisc = rta_getattr_u8(
+ greinfo[IFLA_GRE_PMTUDISC]);
+
+ if (greinfo[IFLA_GRE_TTL])
+ ttl = rta_getattr_u8(greinfo[IFLA_GRE_TTL]);
+
+ if (greinfo[IFLA_GRE_TOS])
+ tos = rta_getattr_u8(greinfo[IFLA_GRE_TOS]);
+
+ if (greinfo[IFLA_GRE_LINK])
+ link = rta_getattr_u8(greinfo[IFLA_GRE_LINK]);
+
+ if (greinfo[IFLA_GRE_ENCAP_TYPE])
+ encaptype = rta_getattr_u16(greinfo[IFLA_GRE_ENCAP_TYPE]);
+ if (greinfo[IFLA_GRE_ENCAP_FLAGS])
+ encapflags = rta_getattr_u16(greinfo[IFLA_GRE_ENCAP_FLAGS]);
+ if (greinfo[IFLA_GRE_ENCAP_SPORT])
+ encapsport = rta_getattr_u16(greinfo[IFLA_GRE_ENCAP_SPORT]);
+ if (greinfo[IFLA_GRE_ENCAP_DPORT])
+ encapdport = rta_getattr_u16(greinfo[IFLA_GRE_ENCAP_DPORT]);
+
+ if (greinfo[IFLA_GRE_COLLECT_METADATA])
+ metadata = 1;
+ }
+
+ while (argc > 0) {
+ if (!matches(*argv, "key")) {
+ unsigned uval;
+
+ NEXT_ARG();
+ iflags |= GRE_KEY;
+ oflags |= GRE_KEY;
+ if (strchr(*argv, '.'))
+ uval = get_addr32(*argv);
+ else {
+ if (get_unsigned(&uval, *argv, 0) < 0) {
+ fprintf(stderr,
+ "Invalid value for \"key\": \"%s\"; it should be an unsigned integer\n", *argv);
+ exit(-1);
+ }
+ uval = htonl(uval);
+ }
+
+ ikey = okey = uval;
+ } else if (!matches(*argv, "ikey")) {
+ unsigned uval;
+
+ NEXT_ARG();
+ iflags |= GRE_KEY;
+ if (strchr(*argv, '.'))
+ uval = get_addr32(*argv);
+ else {
+ if (get_unsigned(&uval, *argv, 0)<0) {
+ fprintf(stderr, "invalid value for \"ikey\": \"%s\"; it should be an unsigned integer\n", *argv);
+ exit(-1);
+ }
+ uval = htonl(uval);
+ }
+ ikey = uval;
+ } else if (!matches(*argv, "okey")) {
+ unsigned uval;
+
+ NEXT_ARG();
+ oflags |= GRE_KEY;
+ if (strchr(*argv, '.'))
+ uval = get_addr32(*argv);
+ else {
+ if (get_unsigned(&uval, *argv, 0)<0) {
+ fprintf(stderr, "invalid value for \"okey\": \"%s\"; it should be an unsigned integer\n", *argv);
+ exit(-1);
+ }
+ uval = htonl(uval);
+ }
+ okey = uval;
+ } else if (!matches(*argv, "seq")) {
+ iflags |= GRE_SEQ;
+ oflags |= GRE_SEQ;
+ } else if (!matches(*argv, "iseq")) {
+ iflags |= GRE_SEQ;
+ } else if (!matches(*argv, "oseq")) {
+ oflags |= GRE_SEQ;
+ } else if (!matches(*argv, "csum")) {
+ iflags |= GRE_CSUM;
+ oflags |= GRE_CSUM;
+ } else if (!matches(*argv, "icsum")) {
+ iflags |= GRE_CSUM;
+ } else if (!matches(*argv, "ocsum")) {
+ oflags |= GRE_CSUM;
+ } else if (!matches(*argv, "nopmtudisc")) {
+ pmtudisc = 0;
+ } else if (!matches(*argv, "pmtudisc")) {
+ pmtudisc = 1;
+ } else if (!matches(*argv, "remote")) {
+ NEXT_ARG();
+ if (strcmp(*argv, "any"))
+ daddr = get_addr32(*argv);
+ } else if (!matches(*argv, "local")) {
+ NEXT_ARG();
+ if (strcmp(*argv, "any"))
+ saddr = get_addr32(*argv);
+ } else if (!matches(*argv, "dev")) {
+ NEXT_ARG();
+ link = if_nametoindex(*argv);
+ if (link == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n",
+ *argv);
+ exit(-1);
+ }
+ } else if (!matches(*argv, "ttl") ||
+ !matches(*argv, "hoplimit")) {
+ unsigned uval;
+
+ NEXT_ARG();
+ if (strcmp(*argv, "inherit") != 0) {
+ if (get_unsigned(&uval, *argv, 0))
+ invarg("invalid TTL\n", *argv);
+ if (uval > 255)
+ invarg("TTL must be <= 255\n", *argv);
+ ttl = uval;
+ }
+ } else if (!matches(*argv, "tos") ||
+ !matches(*argv, "tclass") ||
+ !matches(*argv, "dsfield")) {
+ __u32 uval;
+
+ NEXT_ARG();
+ if (strcmp(*argv, "inherit") != 0) {
+ if (rtnl_dsfield_a2n(&uval, *argv))
+ invarg("bad TOS value", *argv);
+ tos = uval;
+ } else
+ tos = 1;
+ } else if (strcmp(*argv, "noencap") == 0) {
+ encaptype = TUNNEL_ENCAP_NONE;
+ } else if (strcmp(*argv, "encap") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "fou") == 0)
+ encaptype = TUNNEL_ENCAP_FOU;
+ else if (strcmp(*argv, "gue") == 0)
+ encaptype = TUNNEL_ENCAP_GUE;
+ else if (strcmp(*argv, "none") == 0)
+ encaptype = TUNNEL_ENCAP_NONE;
+ else
+ invarg("Invalid encap type.", *argv);
+ } else if (strcmp(*argv, "encap-sport") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "auto") == 0)
+ encapsport = 0;
+ else if (get_u16(&encapsport, *argv, 0))
+ invarg("Invalid source port.", *argv);
+ } else if (strcmp(*argv, "encap-dport") == 0) {
+ NEXT_ARG();
+ if (get_u16(&encapdport, *argv, 0))
+ invarg("Invalid destination port.", *argv);
+ } else if (strcmp(*argv, "encap-csum") == 0) {
+ encapflags |= TUNNEL_ENCAP_FLAG_CSUM;
+ } else if (strcmp(*argv, "noencap-csum") == 0) {
+ encapflags &= ~TUNNEL_ENCAP_FLAG_CSUM;
+ } else if (strcmp(*argv, "encap-udp6-csum") == 0) {
+ encapflags |= TUNNEL_ENCAP_FLAG_CSUM6;
+ } else if (strcmp(*argv, "noencap-udp6-csum") == 0) {
+ encapflags |= ~TUNNEL_ENCAP_FLAG_CSUM6;
+ } else if (strcmp(*argv, "encap-remcsum") == 0) {
+ encapflags |= TUNNEL_ENCAP_FLAG_REMCSUM;
+ } else if (strcmp(*argv, "noencap-remcsum") == 0) {
+ encapflags |= ~TUNNEL_ENCAP_FLAG_REMCSUM;
+ } else if (strcmp(*argv, "external") == 0) {
+ metadata = 1;
+ } else
+ usage();
+ argc--; argv++;
+ }
+
+ if (!ikey && IN_MULTICAST(ntohl(daddr))) {
+ ikey = daddr;
+ iflags |= GRE_KEY;
+ }
+ if (!okey && IN_MULTICAST(ntohl(daddr))) {
+ okey = daddr;
+ oflags |= GRE_KEY;
+ }
+ if (IN_MULTICAST(ntohl(daddr)) && !saddr) {
+ fprintf(stderr, "A broadcast tunnel requires a source address.\n");
+ return -1;
+ }
+
+ addattr32(n, 1024, IFLA_GRE_IKEY, ikey);
+ addattr32(n, 1024, IFLA_GRE_OKEY, okey);
+ addattr_l(n, 1024, IFLA_GRE_IFLAGS, &iflags, 2);
+ addattr_l(n, 1024, IFLA_GRE_OFLAGS, &oflags, 2);
+ addattr_l(n, 1024, IFLA_GRE_LOCAL, &saddr, 4);
+ addattr_l(n, 1024, IFLA_GRE_REMOTE, &daddr, 4);
+ addattr_l(n, 1024, IFLA_GRE_PMTUDISC, &pmtudisc, 1);
+ if (link)
+ addattr32(n, 1024, IFLA_GRE_LINK, link);
+ addattr_l(n, 1024, IFLA_GRE_TTL, &ttl, 1);
+ addattr_l(n, 1024, IFLA_GRE_TOS, &tos, 1);
+
+ addattr16(n, 1024, IFLA_GRE_ENCAP_TYPE, encaptype);
+ addattr16(n, 1024, IFLA_GRE_ENCAP_FLAGS, encapflags);
+ addattr16(n, 1024, IFLA_GRE_ENCAP_SPORT, htons(encapsport));
+ addattr16(n, 1024, IFLA_GRE_ENCAP_DPORT, htons(encapdport));
+ if (metadata)
+ addattr_l(n, 1024, IFLA_GRE_COLLECT_METADATA, NULL, 0);
+
+ return 0;
+}
+
+static void gre_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
+{
+ char s1[1024];
+ char s2[64];
+ const char *local = "any";
+ const char *remote = "any";
+ unsigned iflags = 0;
+ unsigned oflags = 0;
+
+ if (!tb)
+ return;
+
+ if (tb[IFLA_GRE_REMOTE]) {
+ unsigned addr = rta_getattr_u32(tb[IFLA_GRE_REMOTE]);
+
+ if (addr)
+ remote = format_host(AF_INET, 4, &addr, s1, sizeof(s1));
+ }
+
+ fprintf(f, "remote %s ", remote);
+
+ if (tb[IFLA_GRE_LOCAL]) {
+ unsigned addr = rta_getattr_u32(tb[IFLA_GRE_LOCAL]);
+
+ if (addr)
+ local = format_host(AF_INET, 4, &addr, s1, sizeof(s1));
+ }
+
+ fprintf(f, "local %s ", local);
+
+ if (tb[IFLA_GRE_LINK] && rta_getattr_u32(tb[IFLA_GRE_LINK])) {
+ unsigned link = rta_getattr_u32(tb[IFLA_GRE_LINK]);
+ const char *n = if_indextoname(link, s2);
+
+ if (n)
+ fprintf(f, "dev %s ", n);
+ else
+ fprintf(f, "dev %u ", link);
+ }
+
+ if (tb[IFLA_GRE_TTL] && rta_getattr_u8(tb[IFLA_GRE_TTL]))
+ fprintf(f, "ttl %d ", rta_getattr_u8(tb[IFLA_GRE_TTL]));
+ else
+ fprintf(f, "ttl inherit ");
+
+ if (tb[IFLA_GRE_TOS] && rta_getattr_u8(tb[IFLA_GRE_TOS])) {
+ int tos = rta_getattr_u8(tb[IFLA_GRE_TOS]);
+
+ fputs("tos ", f);
+ if (tos == 1)
+ fputs("inherit ", f);
+ else
+ fprintf(f, "0x%x ", tos);
+ }
+
+ if (tb[IFLA_GRE_PMTUDISC] &&
+ !rta_getattr_u8(tb[IFLA_GRE_PMTUDISC]))
+ fputs("nopmtudisc ", f);
+
+ if (tb[IFLA_GRE_IFLAGS])
+ iflags = rta_getattr_u16(tb[IFLA_GRE_IFLAGS]);
+
+ if (tb[IFLA_GRE_OFLAGS])
+ oflags = rta_getattr_u16(tb[IFLA_GRE_OFLAGS]);
+
+ if ((iflags & GRE_KEY) && tb[IFLA_GRE_IKEY]) {
+ inet_ntop(AF_INET, RTA_DATA(tb[IFLA_GRE_IKEY]), s2, sizeof(s2));
+ fprintf(f, "ikey %s ", s2);
+ }
+
+ if ((oflags & GRE_KEY) && tb[IFLA_GRE_OKEY]) {
+ inet_ntop(AF_INET, RTA_DATA(tb[IFLA_GRE_OKEY]), s2, sizeof(s2));
+ fprintf(f, "okey %s ", s2);
+ }
+
+ if (iflags & GRE_SEQ)
+ fputs("iseq ", f);
+ if (oflags & GRE_SEQ)
+ fputs("oseq ", f);
+ if (iflags & GRE_CSUM)
+ fputs("icsum ", f);
+ if (oflags & GRE_CSUM)
+ fputs("ocsum ", f);
+
+ if (tb[IFLA_GRE_COLLECT_METADATA])
+ fputs("external ", f);
+
+ if (tb[IFLA_GRE_ENCAP_TYPE] &&
+ *(__u16 *)RTA_DATA(tb[IFLA_GRE_ENCAP_TYPE]) != TUNNEL_ENCAP_NONE) {
+ __u16 type = rta_getattr_u16(tb[IFLA_GRE_ENCAP_TYPE]);
+ __u16 flags = rta_getattr_u16(tb[IFLA_GRE_ENCAP_FLAGS]);
+ __u16 sport = rta_getattr_u16(tb[IFLA_GRE_ENCAP_SPORT]);
+ __u16 dport = rta_getattr_u16(tb[IFLA_GRE_ENCAP_DPORT]);
+
+ fputs("encap ", f);
+ switch (type) {
+ case TUNNEL_ENCAP_FOU:
+ fputs("fou ", f);
+ break;
+ case TUNNEL_ENCAP_GUE:
+ fputs("gue ", f);
+ break;
+ default:
+ fputs("unknown ", f);
+ break;
+ }
+
+ if (sport == 0)
+ fputs("encap-sport auto ", f);
+ else
+ fprintf(f, "encap-sport %u", ntohs(sport));
+
+ fprintf(f, "encap-dport %u ", ntohs(dport));
+
+ if (flags & TUNNEL_ENCAP_FLAG_CSUM)
+ fputs("encap-csum ", f);
+ else
+ fputs("noencap-csum ", f);
+
+ if (flags & TUNNEL_ENCAP_FLAG_CSUM6)
+ fputs("encap-csum6 ", f);
+ else
+ fputs("noencap-csum6 ", f);
+
+ if (flags & TUNNEL_ENCAP_FLAG_REMCSUM)
+ fputs("encap-remcsum ", f);
+ else
+ fputs("noencap-remcsum ", f);
+ }
+}
+
+static void gre_print_help(struct link_util *lu, int argc, char **argv,
+ FILE *f)
+{
+ print_usage(f);
+}
+
+struct link_util gre_link_util = {
+ .id = "gre",
+ .maxattr = IFLA_GRE_MAX,
+ .parse_opt = gre_parse_opt,
+ .print_opt = gre_print_opt,
+ .print_help = gre_print_help,
+};
+
+struct link_util gretap_link_util = {
+ .id = "gretap",
+ .maxattr = IFLA_GRE_MAX,
+ .parse_opt = gre_parse_opt,
+ .print_opt = gre_print_opt,
+ .print_help = gre_print_help,
+};
diff --git a/iproute2/ip/link_gre6.c b/iproute2/ip/link_gre6.c
new file mode 100644
index 0000000..e00ea09
--- /dev/null
+++ b/iproute2/ip/link_gre6.c
@@ -0,0 +1,414 @@
+/*
+ * link_gre6.c gre driver module
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Dmitry Kozlov <xeb@mail.ru>
+ *
+ */
+
+#include <string.h>
+#include <net/if.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+
+#include <linux/ip.h>
+#include <linux/if_tunnel.h>
+#include <linux/ip6_tunnel.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+#include "tunnel.h"
+
+#define IP6_FLOWINFO_TCLASS htonl(0x0FF00000)
+#define IP6_FLOWINFO_FLOWLABEL htonl(0x000FFFFF)
+
+#define DEFAULT_TNL_HOP_LIMIT (64)
+
+static void print_usage(FILE *f)
+{
+ fprintf(f, "Usage: ip link { add | set | change | replace | del } NAME\n");
+ fprintf(f, " type { ip6gre | ip6gretap } [ remote ADDR ] [ local ADDR ]\n");
+ fprintf(f, " [ [i|o]seq ] [ [i|o]key KEY ] [ [i|o]csum ]\n");
+ fprintf(f, " [ hoplimit TTL ] [ encaplimit ELIM ]\n");
+ fprintf(f, " [ tclass TCLASS ] [ flowlabel FLOWLABEL ]\n");
+ fprintf(f, " [ dscp inherit ] [ dev PHYS_DEV ]\n");
+ fprintf(f, "\n");
+ fprintf(f, "Where: NAME := STRING\n");
+ fprintf(f, " ADDR := IPV6_ADDRESS\n");
+ fprintf(f, " TTL := { 0..255 } (default=%d)\n",
+ DEFAULT_TNL_HOP_LIMIT);
+ fprintf(f, " KEY := { DOTTED_QUAD | NUMBER }\n");
+ fprintf(f, " ELIM := { none | 0..255 }(default=%d)\n",
+ IPV6_DEFAULT_TNL_ENCAP_LIMIT);
+ fprintf(f, " TCLASS := { 0x0..0xff | inherit }\n");
+ fprintf(f, " FLOWLABEL := { 0x0..0xfffff | inherit }\n");
+}
+
+static void usage(void) __attribute__((noreturn));
+static void usage(void)
+{
+ print_usage(stderr);
+ exit(-1);
+}
+
+static int gre_parse_opt(struct link_util *lu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ struct {
+ struct nlmsghdr n;
+ struct ifinfomsg i;
+ char buf[1024];
+ } req;
+ struct ifinfomsg *ifi = (struct ifinfomsg *)(n + 1);
+ struct rtattr *tb[IFLA_MAX + 1];
+ struct rtattr *linkinfo[IFLA_INFO_MAX+1];
+ struct rtattr *greinfo[IFLA_GRE_MAX + 1];
+ __u16 iflags = 0;
+ __u16 oflags = 0;
+ unsigned ikey = 0;
+ unsigned okey = 0;
+ struct in6_addr raddr = IN6ADDR_ANY_INIT;
+ struct in6_addr laddr = IN6ADDR_ANY_INIT;
+ unsigned link = 0;
+ unsigned flowinfo = 0;
+ unsigned flags = 0;
+ __u8 hop_limit = DEFAULT_TNL_HOP_LIMIT;
+ __u8 encap_limit = IPV6_DEFAULT_TNL_ENCAP_LIMIT;
+ int len;
+
+ if (!(n->nlmsg_flags & NLM_F_CREATE)) {
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(*ifi));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = RTM_GETLINK;
+ req.i.ifi_family = preferred_family;
+ req.i.ifi_index = ifi->ifi_index;
+
+ if (rtnl_talk(&rth, &req.n, &req.n, sizeof(req)) < 0) {
+get_failed:
+ fprintf(stderr,
+ "Failed to get existing tunnel info.\n");
+ return -1;
+ }
+
+ len = req.n.nlmsg_len;
+ len -= NLMSG_LENGTH(sizeof(*ifi));
+ if (len < 0)
+ goto get_failed;
+
+ parse_rtattr(tb, IFLA_MAX, IFLA_RTA(&req.i), len);
+
+ if (!tb[IFLA_LINKINFO])
+ goto get_failed;
+
+ parse_rtattr_nested(linkinfo, IFLA_INFO_MAX, tb[IFLA_LINKINFO]);
+
+ if (!linkinfo[IFLA_INFO_DATA])
+ goto get_failed;
+
+ parse_rtattr_nested(greinfo, IFLA_GRE_MAX,
+ linkinfo[IFLA_INFO_DATA]);
+
+ if (greinfo[IFLA_GRE_IKEY])
+ ikey = rta_getattr_u32(greinfo[IFLA_GRE_IKEY]);
+
+ if (greinfo[IFLA_GRE_OKEY])
+ okey = rta_getattr_u32(greinfo[IFLA_GRE_OKEY]);
+
+ if (greinfo[IFLA_GRE_IFLAGS])
+ iflags = rta_getattr_u16(greinfo[IFLA_GRE_IFLAGS]);
+
+ if (greinfo[IFLA_GRE_OFLAGS])
+ oflags = rta_getattr_u16(greinfo[IFLA_GRE_OFLAGS]);
+
+ if (greinfo[IFLA_GRE_LOCAL])
+ memcpy(&laddr, RTA_DATA(greinfo[IFLA_GRE_LOCAL]), sizeof(laddr));
+
+ if (greinfo[IFLA_GRE_REMOTE])
+ memcpy(&raddr, RTA_DATA(greinfo[IFLA_GRE_REMOTE]), sizeof(raddr));
+
+ if (greinfo[IFLA_GRE_TTL])
+ hop_limit = rta_getattr_u8(greinfo[IFLA_GRE_TTL]);
+
+ if (greinfo[IFLA_GRE_LINK])
+ link = rta_getattr_u32(greinfo[IFLA_GRE_LINK]);
+
+ if (greinfo[IFLA_GRE_ENCAP_LIMIT])
+ encap_limit = rta_getattr_u8(greinfo[IFLA_GRE_ENCAP_LIMIT]);
+
+ if (greinfo[IFLA_GRE_FLOWINFO])
+ flowinfo = rta_getattr_u32(greinfo[IFLA_GRE_FLOWINFO]);
+
+ if (greinfo[IFLA_GRE_FLAGS])
+ flags = rta_getattr_u32(greinfo[IFLA_GRE_FLAGS]);
+ }
+
+ while (argc > 0) {
+ if (!matches(*argv, "key")) {
+ unsigned uval;
+
+ NEXT_ARG();
+ iflags |= GRE_KEY;
+ oflags |= GRE_KEY;
+ if (strchr(*argv, '.'))
+ uval = get_addr32(*argv);
+ else {
+ if (get_unsigned(&uval, *argv, 0) < 0) {
+ fprintf(stderr,
+ "Invalid value for \"key\"\n");
+ exit(-1);
+ }
+ uval = htonl(uval);
+ }
+
+ ikey = okey = uval;
+ } else if (!matches(*argv, "ikey")) {
+ unsigned uval;
+
+ NEXT_ARG();
+ iflags |= GRE_KEY;
+ if (strchr(*argv, '.'))
+ uval = get_addr32(*argv);
+ else {
+ if (get_unsigned(&uval, *argv, 0)<0) {
+ fprintf(stderr, "invalid value of \"ikey\"\n");
+ exit(-1);
+ }
+ uval = htonl(uval);
+ }
+ ikey = uval;
+ } else if (!matches(*argv, "okey")) {
+ unsigned uval;
+
+ NEXT_ARG();
+ oflags |= GRE_KEY;
+ if (strchr(*argv, '.'))
+ uval = get_addr32(*argv);
+ else {
+ if (get_unsigned(&uval, *argv, 0)<0) {
+ fprintf(stderr, "invalid value of \"okey\"\n");
+ exit(-1);
+ }
+ uval = htonl(uval);
+ }
+ okey = uval;
+ } else if (!matches(*argv, "seq")) {
+ iflags |= GRE_SEQ;
+ oflags |= GRE_SEQ;
+ } else if (!matches(*argv, "iseq")) {
+ iflags |= GRE_SEQ;
+ } else if (!matches(*argv, "oseq")) {
+ oflags |= GRE_SEQ;
+ } else if (!matches(*argv, "csum")) {
+ iflags |= GRE_CSUM;
+ oflags |= GRE_CSUM;
+ } else if (!matches(*argv, "icsum")) {
+ iflags |= GRE_CSUM;
+ } else if (!matches(*argv, "ocsum")) {
+ oflags |= GRE_CSUM;
+ } else if (!matches(*argv, "remote")) {
+ inet_prefix addr;
+ NEXT_ARG();
+ get_prefix(&addr, *argv, preferred_family);
+ if (addr.family == AF_UNSPEC)
+ invarg("\"remote\" address family is AF_UNSPEC", *argv);
+ memcpy(&raddr, &addr.data, sizeof(raddr));
+ } else if (!matches(*argv, "local")) {
+ inet_prefix addr;
+ NEXT_ARG();
+ get_prefix(&addr, *argv, preferred_family);
+ if (addr.family == AF_UNSPEC)
+ invarg("\"local\" address family is AF_UNSPEC", *argv);
+ memcpy(&laddr, &addr.data, sizeof(laddr));
+ } else if (!matches(*argv, "dev")) {
+ NEXT_ARG();
+ link = if_nametoindex(*argv);
+ if (link == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n",
+ *argv);
+ exit(-1);
+ }
+ } else if (!matches(*argv, "ttl") ||
+ !matches(*argv, "hoplimit")) {
+ __u8 uval;
+ NEXT_ARG();
+ if (get_u8(&uval, *argv, 0))
+ invarg("invalid TTL", *argv);
+ hop_limit = uval;
+ } else if (!matches(*argv, "tos") ||
+ !matches(*argv, "tclass") ||
+ !matches(*argv, "dsfield")) {
+ __u8 uval;
+ NEXT_ARG();
+ if (strcmp(*argv, "inherit") == 0)
+ flags |= IP6_TNL_F_USE_ORIG_TCLASS;
+ else {
+ if (get_u8(&uval, *argv, 16))
+ invarg("invalid TClass", *argv);
+ flowinfo |= htonl((__u32)uval << 20) & IP6_FLOWINFO_TCLASS;
+ flags &= ~IP6_TNL_F_USE_ORIG_TCLASS;
+ }
+ } else if (strcmp(*argv, "flowlabel") == 0 ||
+ strcmp(*argv, "fl") == 0) {
+ __u32 uval;
+ NEXT_ARG();
+ if (strcmp(*argv, "inherit") == 0)
+ flags |= IP6_TNL_F_USE_ORIG_FLOWLABEL;
+ else {
+ if (get_u32(&uval, *argv, 16))
+ invarg("invalid Flowlabel", *argv);
+ if (uval > 0xFFFFF)
+ invarg("invalid Flowlabel", *argv);
+ flowinfo |= htonl(uval) & IP6_FLOWINFO_FLOWLABEL;
+ flags &= ~IP6_TNL_F_USE_ORIG_FLOWLABEL;
+ }
+ } else if (strcmp(*argv, "dscp") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "inherit") != 0)
+ invarg("not inherit", *argv);
+ flags |= IP6_TNL_F_RCV_DSCP_COPY;
+ } else
+ usage();
+ argc--; argv++;
+ }
+
+ addattr32(n, 1024, IFLA_GRE_IKEY, ikey);
+ addattr32(n, 1024, IFLA_GRE_OKEY, okey);
+ addattr_l(n, 1024, IFLA_GRE_IFLAGS, &iflags, 2);
+ addattr_l(n, 1024, IFLA_GRE_OFLAGS, &oflags, 2);
+ addattr_l(n, 1024, IFLA_GRE_LOCAL, &laddr, sizeof(laddr));
+ addattr_l(n, 1024, IFLA_GRE_REMOTE, &raddr, sizeof(raddr));
+ if (link)
+ addattr32(n, 1024, IFLA_GRE_LINK, link);
+ addattr_l(n, 1024, IFLA_GRE_TTL, &hop_limit, 1);
+ addattr_l(n, 1024, IFLA_GRE_ENCAP_LIMIT, &encap_limit, 1);
+ addattr_l(n, 1024, IFLA_GRE_FLOWINFO, &flowinfo, 4);
+ addattr_l(n, 1024, IFLA_GRE_FLAGS, &flowinfo, 4);
+
+ return 0;
+}
+
+static void gre_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
+{
+ char s1[1024];
+ char s2[64];
+ const char *local = "any";
+ const char *remote = "any";
+ unsigned iflags = 0;
+ unsigned oflags = 0;
+ unsigned flags = 0;
+ unsigned flowinfo = 0;
+ struct in6_addr in6_addr_any = IN6ADDR_ANY_INIT;
+
+ if (!tb)
+ return;
+
+ if (tb[IFLA_GRE_FLAGS])
+ flags = rta_getattr_u32(tb[IFLA_GRE_FLAGS]);
+
+ if (tb[IFLA_GRE_FLOWINFO])
+ flags = rta_getattr_u32(tb[IFLA_GRE_FLOWINFO]);
+
+ if (tb[IFLA_GRE_REMOTE]) {
+ struct in6_addr addr;
+ memcpy(&addr, RTA_DATA(tb[IFLA_GRE_REMOTE]), sizeof(addr));
+
+ if (memcmp(&addr, &in6_addr_any, sizeof(addr)))
+ remote = format_host(AF_INET6, sizeof(addr), &addr, s1, sizeof(s1));
+ }
+
+ fprintf(f, "remote %s ", remote);
+
+ if (tb[IFLA_GRE_LOCAL]) {
+ struct in6_addr addr;
+ memcpy(&addr, RTA_DATA(tb[IFLA_GRE_LOCAL]), sizeof(addr));
+
+ if (memcmp(&addr, &in6_addr_any, sizeof(addr)))
+ local = format_host(AF_INET6, sizeof(addr), &addr, s1, sizeof(s1));
+ }
+
+ fprintf(f, "local %s ", local);
+
+ if (tb[IFLA_GRE_LINK] && rta_getattr_u32(tb[IFLA_GRE_LINK])) {
+ unsigned link = rta_getattr_u32(tb[IFLA_GRE_LINK]);
+ const char *n = if_indextoname(link, s2);
+
+ if (n)
+ fprintf(f, "dev %s ", n);
+ else
+ fprintf(f, "dev %u ", link);
+ }
+
+ if (tb[IFLA_GRE_TTL] && rta_getattr_u8(tb[IFLA_GRE_TTL]))
+ fprintf(f, "hoplimit %d ", rta_getattr_u8(tb[IFLA_GRE_TTL]));
+
+ if (flags & IP6_TNL_F_IGN_ENCAP_LIMIT)
+ fprintf(f, "encaplimit none ");
+ else if (tb[IFLA_GRE_ENCAP_LIMIT]) {
+ int encap_limit = rta_getattr_u8(tb[IFLA_GRE_ENCAP_LIMIT]);
+
+ fprintf(f, "encaplimit %d ", encap_limit);
+ }
+
+ if (flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)
+ fprintf(f, "flowlabel inherit ");
+ else
+ fprintf(f, "flowlabel 0x%05x ", ntohl(flowinfo & IP6_FLOWINFO_FLOWLABEL));
+
+ if (flags & IP6_TNL_F_RCV_DSCP_COPY)
+ fprintf(f, "dscp inherit ");
+
+ if (tb[IFLA_GRE_IFLAGS])
+ iflags = rta_getattr_u16(tb[IFLA_GRE_IFLAGS]);
+
+ if (tb[IFLA_GRE_OFLAGS])
+ oflags = rta_getattr_u16(tb[IFLA_GRE_OFLAGS]);
+
+ if ((iflags & GRE_KEY) && tb[IFLA_GRE_IKEY]) {
+ inet_ntop(AF_INET, RTA_DATA(tb[IFLA_GRE_IKEY]), s2, sizeof(s2));
+ fprintf(f, "ikey %s ", s2);
+ }
+
+ if ((oflags & GRE_KEY) && tb[IFLA_GRE_OKEY]) {
+ inet_ntop(AF_INET, RTA_DATA(tb[IFLA_GRE_OKEY]), s2, sizeof(s2));
+ fprintf(f, "okey %s ", s2);
+ }
+
+ if (iflags & GRE_SEQ)
+ fputs("iseq ", f);
+ if (oflags & GRE_SEQ)
+ fputs("oseq ", f);
+ if (iflags & GRE_CSUM)
+ fputs("icsum ", f);
+ if (oflags & GRE_CSUM)
+ fputs("ocsum ", f);
+}
+
+static void gre_print_help(struct link_util *lu, int argc, char **argv,
+ FILE *f)
+{
+ print_usage(f);
+}
+
+struct link_util ip6gre_link_util = {
+ .id = "ip6gre",
+ .maxattr = IFLA_GRE_MAX,
+ .parse_opt = gre_parse_opt,
+ .print_opt = gre_print_opt,
+ .print_help = gre_print_help,
+};
+
+struct link_util ip6gretap_link_util = {
+ .id = "ip6gretap",
+ .maxattr = IFLA_GRE_MAX,
+ .parse_opt = gre_parse_opt,
+ .print_opt = gre_print_opt,
+ .print_help = gre_print_help,
+};
diff --git a/iproute2/ip/link_ip6tnl.c b/iproute2/ip/link_ip6tnl.c
new file mode 100644
index 0000000..f771c75
--- /dev/null
+++ b/iproute2/ip/link_ip6tnl.c
@@ -0,0 +1,357 @@
+/*
+ * link_ip6tnl.c ip6tnl driver module
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Nicolas Dichtel <nicolas.dichtel@6wind.com>
+ *
+ */
+
+#include <string.h>
+#include <net/if.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+
+#include <linux/ip.h>
+#include <linux/if_tunnel.h>
+#include <linux/ip6_tunnel.h>
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+#include "tunnel.h"
+
+#define IP6_FLOWINFO_TCLASS htonl(0x0FF00000)
+#define IP6_FLOWINFO_FLOWLABEL htonl(0x000FFFFF)
+
+#define DEFAULT_TNL_HOP_LIMIT (64)
+
+static void print_usage(FILE *f)
+{
+ fprintf(f, "Usage: ip link { add | set | change | replace | del } NAME\n");
+ fprintf(f, " [ mode { ip6ip6 | ipip6 | any } ]\n");
+ fprintf(f, " type ip6tnl [ remote ADDR ] [ local ADDR ]\n");
+ fprintf(f, " [ dev PHYS_DEV ] [ encaplimit ELIM ]\n");
+ fprintf(f ," [ hoplimit HLIM ] [ tclass TCLASS ] [ flowlabel FLOWLABEL ]\n");
+ fprintf(f, " [ dscp inherit ] [ fwmark inherit ]\n");
+ fprintf(f, "\n");
+ fprintf(f, "Where: NAME := STRING\n");
+ fprintf(f, " ADDR := IPV6_ADDRESS\n");
+ fprintf(f, " ELIM := { none | 0..255 }(default=%d)\n",
+ IPV6_DEFAULT_TNL_ENCAP_LIMIT);
+ fprintf(f, " HLIM := 0..255 (default=%d)\n",
+ DEFAULT_TNL_HOP_LIMIT);
+ fprintf(f, " TCLASS := { 0x0..0xff | inherit }\n");
+ fprintf(f, " FLOWLABEL := { 0x0..0xfffff | inherit }\n");
+}
+
+static void usage(void) __attribute__((noreturn));
+static void usage(void)
+{
+ print_usage(stderr);
+ exit(-1);
+}
+
+static int ip6tunnel_parse_opt(struct link_util *lu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ struct {
+ struct nlmsghdr n;
+ struct ifinfomsg i;
+ char buf[2048];
+ } req;
+ struct ifinfomsg *ifi = (struct ifinfomsg *)(n + 1);
+ struct rtattr *tb[IFLA_MAX + 1];
+ struct rtattr *linkinfo[IFLA_INFO_MAX+1];
+ struct rtattr *iptuninfo[IFLA_IPTUN_MAX + 1];
+ int len;
+ struct in6_addr laddr;
+ struct in6_addr raddr;
+ __u8 hop_limit = DEFAULT_TNL_HOP_LIMIT;
+ __u8 encap_limit = IPV6_DEFAULT_TNL_ENCAP_LIMIT;
+ __u32 flowinfo = 0;
+ __u32 flags = 0;
+ __u32 link = 0;
+ __u8 proto = 0;
+
+ memset(&laddr, 0, sizeof(laddr));
+ memset(&raddr, 0, sizeof(raddr));
+
+ if (!(n->nlmsg_flags & NLM_F_CREATE)) {
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(*ifi));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = RTM_GETLINK;
+ req.i.ifi_family = preferred_family;
+ req.i.ifi_index = ifi->ifi_index;
+
+ if (rtnl_talk(&rth, &req.n, &req.n, sizeof(req)) < 0) {
+get_failed:
+ fprintf(stderr,
+ "Failed to get existing tunnel info.\n");
+ return -1;
+ }
+
+ len = req.n.nlmsg_len;
+ len -= NLMSG_LENGTH(sizeof(*ifi));
+ if (len < 0)
+ goto get_failed;
+
+ parse_rtattr(tb, IFLA_MAX, IFLA_RTA(&req.i), len);
+
+ if (!tb[IFLA_LINKINFO])
+ goto get_failed;
+
+ parse_rtattr_nested(linkinfo, IFLA_INFO_MAX, tb[IFLA_LINKINFO]);
+
+ if (!linkinfo[IFLA_INFO_DATA])
+ goto get_failed;
+
+ parse_rtattr_nested(iptuninfo, IFLA_IPTUN_MAX,
+ linkinfo[IFLA_INFO_DATA]);
+
+ if (iptuninfo[IFLA_IPTUN_LOCAL])
+ memcpy(&laddr, RTA_DATA(iptuninfo[IFLA_IPTUN_LOCAL]),
+ sizeof(laddr));
+
+ if (iptuninfo[IFLA_IPTUN_REMOTE])
+ memcpy(&raddr, RTA_DATA(iptuninfo[IFLA_IPTUN_REMOTE]),
+ sizeof(raddr));
+
+ if (iptuninfo[IFLA_IPTUN_TTL])
+ hop_limit = rta_getattr_u8(iptuninfo[IFLA_IPTUN_TTL]);
+
+ if (iptuninfo[IFLA_IPTUN_ENCAP_LIMIT])
+ encap_limit = rta_getattr_u8(iptuninfo[IFLA_IPTUN_ENCAP_LIMIT]);
+
+ if (iptuninfo[IFLA_IPTUN_FLOWINFO])
+ flowinfo = rta_getattr_u32(iptuninfo[IFLA_IPTUN_FLOWINFO]);
+
+ if (iptuninfo[IFLA_IPTUN_FLAGS])
+ flags = rta_getattr_u32(iptuninfo[IFLA_IPTUN_FLAGS]);
+
+ if (iptuninfo[IFLA_IPTUN_LINK])
+ link = rta_getattr_u32(iptuninfo[IFLA_IPTUN_LINK]);
+
+ if (iptuninfo[IFLA_IPTUN_PROTO])
+ proto = rta_getattr_u8(iptuninfo[IFLA_IPTUN_PROTO]);
+ }
+
+ while (argc > 0) {
+ if (matches(*argv, "mode") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "ipv6/ipv6") == 0 ||
+ strcmp(*argv, "ip6ip6") == 0)
+ proto = IPPROTO_IPV6;
+ else if (strcmp(*argv, "ip/ipv6") == 0 ||
+ strcmp(*argv, "ipv4/ipv6") == 0 ||
+ strcmp(*argv, "ipip6") == 0 ||
+ strcmp(*argv, "ip4ip6") == 0)
+ proto = IPPROTO_IPIP;
+ else if (strcmp(*argv, "any/ipv6") == 0 ||
+ strcmp(*argv, "any") == 0)
+ proto = 0;
+ else
+ invarg("Cannot guess tunnel mode.", *argv);
+ } else if (strcmp(*argv, "remote") == 0) {
+ inet_prefix addr;
+ NEXT_ARG();
+ get_prefix(&addr, *argv, preferred_family);
+ if (addr.family == AF_UNSPEC)
+ invarg("\"remote\" address family is AF_UNSPEC", *argv);
+ memcpy(&raddr, addr.data, addr.bytelen);
+ } else if (strcmp(*argv, "local") == 0) {
+ inet_prefix addr;
+ NEXT_ARG();
+ get_prefix(&addr, *argv, preferred_family);
+ if (addr.family == AF_UNSPEC)
+ invarg("\"local\" address family is AF_UNSPEC", *argv);
+ memcpy(&laddr, addr.data, addr.bytelen);
+ } else if (matches(*argv, "dev") == 0) {
+ NEXT_ARG();
+ link = if_nametoindex(*argv);
+ if (link == 0)
+ invarg("\"dev\" is invalid", *argv);
+ } else if (strcmp(*argv, "hoplimit") == 0 ||
+ strcmp(*argv, "ttl") == 0 ||
+ strcmp(*argv, "hlim") == 0) {
+ __u8 uval;
+ NEXT_ARG();
+ if (get_u8(&uval, *argv, 0))
+ invarg("invalid HLIM", *argv);
+ hop_limit = uval;
+ } else if (matches(*argv, "encaplimit") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "none") == 0) {
+ flags |= IP6_TNL_F_IGN_ENCAP_LIMIT;
+ } else {
+ __u8 uval;
+ if (get_u8(&uval, *argv, 0) < -1)
+ invarg("invalid ELIM", *argv);
+ encap_limit = uval;
+ flags &= ~IP6_TNL_F_IGN_ENCAP_LIMIT;
+ }
+ } else if (strcmp(*argv, "tclass") == 0 ||
+ strcmp(*argv, "tc") == 0 ||
+ strcmp(*argv, "tos") == 0 ||
+ matches(*argv, "dsfield") == 0) {
+ __u8 uval;
+ NEXT_ARG();
+ flowinfo &= ~IP6_FLOWINFO_TCLASS;
+ if (strcmp(*argv, "inherit") == 0)
+ flags |= IP6_TNL_F_USE_ORIG_TCLASS;
+ else {
+ if (get_u8(&uval, *argv, 16))
+ invarg("invalid TClass", *argv);
+ flowinfo |= htonl((__u32)uval << 20) & IP6_FLOWINFO_TCLASS;
+ flags &= ~IP6_TNL_F_USE_ORIG_TCLASS;
+ }
+ } else if (strcmp(*argv, "flowlabel") == 0 ||
+ strcmp(*argv, "fl") == 0) {
+ __u32 uval;
+ NEXT_ARG();
+ flowinfo &= ~IP6_FLOWINFO_FLOWLABEL;
+ if (strcmp(*argv, "inherit") == 0)
+ flags |= IP6_TNL_F_USE_ORIG_FLOWLABEL;
+ else {
+ if (get_u32(&uval, *argv, 16))
+ invarg("invalid Flowlabel", *argv);
+ if (uval > 0xFFFFF)
+ invarg("invalid Flowlabel", *argv);
+ flowinfo |= htonl(uval) & IP6_FLOWINFO_FLOWLABEL;
+ flags &= ~IP6_TNL_F_USE_ORIG_FLOWLABEL;
+ }
+ } else if (strcmp(*argv, "dscp") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "inherit") != 0)
+ invarg("not inherit", *argv);
+ flags |= IP6_TNL_F_RCV_DSCP_COPY;
+ } else if (strcmp(*argv, "fwmark") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "inherit") != 0)
+ invarg("not inherit", *argv);
+ flags |= IP6_TNL_F_USE_ORIG_FWMARK;
+ } else
+ usage();
+ argc--, argv++;
+ }
+
+ addattr8(n, 1024, IFLA_IPTUN_PROTO, proto);
+ addattr_l(n, 1024, IFLA_IPTUN_LOCAL, &laddr, sizeof(laddr));
+ addattr_l(n, 1024, IFLA_IPTUN_REMOTE, &raddr, sizeof(raddr));
+ addattr8(n, 1024, IFLA_IPTUN_TTL, hop_limit);
+ addattr8(n, 1024, IFLA_IPTUN_ENCAP_LIMIT, encap_limit);
+ addattr32(n, 1024, IFLA_IPTUN_FLOWINFO, flowinfo);
+ addattr32(n, 1024, IFLA_IPTUN_FLAGS, flags);
+ addattr32(n, 1024, IFLA_IPTUN_LINK, link);
+
+ return 0;
+}
+
+static void ip6tunnel_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
+{
+ char s1[256];
+ char s2[64];
+ int flags = 0;
+ __u32 flowinfo = 0;
+
+ if (!tb)
+ return;
+
+ if (tb[IFLA_IPTUN_FLAGS])
+ flags = rta_getattr_u32(tb[IFLA_IPTUN_FLAGS]);
+
+ if (tb[IFLA_IPTUN_FLOWINFO])
+ flowinfo = rta_getattr_u32(tb[IFLA_IPTUN_FLOWINFO]);
+
+ if (tb[IFLA_IPTUN_PROTO]) {
+ switch (rta_getattr_u8(tb[IFLA_IPTUN_PROTO])) {
+ case IPPROTO_IPIP:
+ fprintf(f, "ipip6 ");
+ break;
+ case IPPROTO_IPV6:
+ fprintf(f, "ip6ip6 ");
+ break;
+ case 0:
+ fprintf(f, "any ");
+ break;
+ }
+ }
+
+ if (tb[IFLA_IPTUN_REMOTE]) {
+ fprintf(f, "remote %s ",
+ rt_addr_n2a(AF_INET6,
+ RTA_PAYLOAD(tb[IFLA_IPTUN_REMOTE]),
+ RTA_DATA(tb[IFLA_IPTUN_REMOTE]),
+ s1, sizeof(s1)));
+ }
+
+ if (tb[IFLA_IPTUN_LOCAL]) {
+ fprintf(f, "local %s ",
+ rt_addr_n2a(AF_INET6,
+ RTA_PAYLOAD(tb[IFLA_IPTUN_LOCAL]),
+ RTA_DATA(tb[IFLA_IPTUN_LOCAL]),
+ s1, sizeof(s1)));
+ }
+
+ if (tb[IFLA_IPTUN_LINK] && rta_getattr_u32(tb[IFLA_IPTUN_LINK])) {
+ unsigned link = rta_getattr_u32(tb[IFLA_IPTUN_LINK]);
+ const char *n = if_indextoname(link, s2);
+
+ if (n)
+ fprintf(f, "dev %s ", n);
+ else
+ fprintf(f, "dev %u ", link);
+ }
+
+ if (flags & IP6_TNL_F_IGN_ENCAP_LIMIT)
+ printf("encaplimit none ");
+ else if (tb[IFLA_IPTUN_ENCAP_LIMIT])
+ fprintf(f, "encaplimit %u ",
+ rta_getattr_u8(tb[IFLA_IPTUN_ENCAP_LIMIT]));
+
+ if (tb[IFLA_IPTUN_TTL])
+ fprintf(f, "hoplimit %u ", rta_getattr_u8(tb[IFLA_IPTUN_TTL]));
+
+ if (flags & IP6_TNL_F_USE_ORIG_TCLASS)
+ printf("tclass inherit ");
+ else if (tb[IFLA_IPTUN_FLOWINFO]) {
+ __u32 val = ntohl(flowinfo & IP6_FLOWINFO_TCLASS);
+
+ printf("tclass 0x%02x ", (__u8)(val >> 20));
+ }
+
+ if (flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)
+ printf("flowlabel inherit ");
+ else
+ printf("flowlabel 0x%05x ", ntohl(flowinfo & IP6_FLOWINFO_FLOWLABEL));
+
+ printf("(flowinfo 0x%08x) ", ntohl(flowinfo));
+
+ if (flags & IP6_TNL_F_RCV_DSCP_COPY)
+ printf("dscp inherit ");
+
+ if (flags & IP6_TNL_F_MIP6_DEV)
+ fprintf(f, "mip6 ");
+
+ if (flags & IP6_TNL_F_USE_ORIG_FWMARK)
+ fprintf(f, "fwmark inherit ");
+}
+
+static void ip6tunnel_print_help(struct link_util *lu, int argc, char **argv,
+ FILE *f)
+{
+ print_usage(f);
+}
+
+struct link_util ip6tnl_link_util = {
+ .id = "ip6tnl",
+ .maxattr = IFLA_IPTUN_MAX,
+ .parse_opt = ip6tunnel_parse_opt,
+ .print_opt = ip6tunnel_print_opt,
+ .print_help = ip6tunnel_print_help,
+};
diff --git a/iproute2/ip/link_iptnl.c b/iproute2/ip/link_iptnl.c
new file mode 100644
index 0000000..9d6bc98
--- /dev/null
+++ b/iproute2/ip/link_iptnl.c
@@ -0,0 +1,473 @@
+/*
+ * link_iptnl.c ipip and sit driver module
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Nicolas Dichtel <nicolas.dichtel@6wind.com>
+ *
+ */
+
+#include <string.h>
+#include <net/if.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+
+#include <linux/ip.h>
+#include <linux/if_tunnel.h>
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+#include "tunnel.h"
+
+static void print_usage(FILE *f, int sit)
+{
+ fprintf(f, "Usage: ip link { add | set | change | replace | del } NAME\n");
+ fprintf(f, " type { ipip | sit } [ remote ADDR ] [ local ADDR ]\n");
+ fprintf(f, " [ ttl TTL ] [ tos TOS ] [ [no]pmtudisc ] [ dev PHYS_DEV ]\n");
+ fprintf(f, " [ 6rd-prefix ADDR ] [ 6rd-relay_prefix ADDR ] [ 6rd-reset ]\n");
+ fprintf(f, " [ noencap ] [ encap { fou | gue | none } ]\n");
+ fprintf(f, " [ encap-sport PORT ] [ encap-dport PORT ]\n");
+ fprintf(f, " [ [no]encap-csum ] [ [no]encap-csum6 ] [ [no]encap-remcsum ]\n");
+ if (sit) {
+ fprintf(f, " [ mode { ip6ip | ipip | any } ]\n");
+ fprintf(f, " [ isatap ]\n");
+ }
+ fprintf(f, "\n");
+ fprintf(f, "Where: NAME := STRING\n");
+ fprintf(f, " ADDR := { IP_ADDRESS | any }\n");
+ fprintf(f, " TOS := { NUMBER | inherit }\n");
+ fprintf(f, " TTL := { 1..255 | inherit }\n");
+}
+
+static void usage(int sit) __attribute__((noreturn));
+static void usage(int sit)
+{
+ print_usage(stderr, sit);
+ exit(-1);
+}
+
+static int iptunnel_parse_opt(struct link_util *lu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ struct {
+ struct nlmsghdr n;
+ struct ifinfomsg i;
+ char buf[2048];
+ } req;
+ struct ifinfomsg *ifi = (struct ifinfomsg *)(n + 1);
+ struct rtattr *tb[IFLA_MAX + 1];
+ struct rtattr *linkinfo[IFLA_INFO_MAX+1];
+ struct rtattr *iptuninfo[IFLA_IPTUN_MAX + 1];
+ int len;
+ __u32 link = 0;
+ __u32 laddr = 0;
+ __u32 raddr = 0;
+ __u8 ttl = 0;
+ __u8 tos = 0;
+ __u8 pmtudisc = 1;
+ __u16 iflags = 0;
+ __u8 proto = 0;
+ struct in6_addr ip6rdprefix;
+ __u16 ip6rdprefixlen = 0;
+ __u32 ip6rdrelayprefix = 0;
+ __u16 ip6rdrelayprefixlen = 0;
+ __u16 encaptype = 0;
+ __u16 encapflags = 0;
+ __u16 encapsport = 0;
+ __u16 encapdport = 0;
+
+ memset(&ip6rdprefix, 0, sizeof(ip6rdprefix));
+
+ if (!(n->nlmsg_flags & NLM_F_CREATE)) {
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(*ifi));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = RTM_GETLINK;
+ req.i.ifi_family = preferred_family;
+ req.i.ifi_index = ifi->ifi_index;
+
+ if (rtnl_talk(&rth, &req.n, &req.n, sizeof(req)) < 0) {
+get_failed:
+ fprintf(stderr,
+ "Failed to get existing tunnel info.\n");
+ return -1;
+ }
+
+ len = req.n.nlmsg_len;
+ len -= NLMSG_LENGTH(sizeof(*ifi));
+ if (len < 0)
+ goto get_failed;
+
+ parse_rtattr(tb, IFLA_MAX, IFLA_RTA(&req.i), len);
+
+ if (!tb[IFLA_LINKINFO])
+ goto get_failed;
+
+ parse_rtattr_nested(linkinfo, IFLA_INFO_MAX, tb[IFLA_LINKINFO]);
+
+ if (!linkinfo[IFLA_INFO_DATA])
+ goto get_failed;
+
+ parse_rtattr_nested(iptuninfo, IFLA_IPTUN_MAX,
+ linkinfo[IFLA_INFO_DATA]);
+
+ if (iptuninfo[IFLA_IPTUN_LOCAL])
+ laddr = rta_getattr_u32(iptuninfo[IFLA_IPTUN_LOCAL]);
+
+ if (iptuninfo[IFLA_IPTUN_REMOTE])
+ raddr = rta_getattr_u32(iptuninfo[IFLA_IPTUN_REMOTE]);
+
+ if (iptuninfo[IFLA_IPTUN_TTL])
+ ttl = rta_getattr_u8(iptuninfo[IFLA_IPTUN_TTL]);
+
+ if (iptuninfo[IFLA_IPTUN_TOS])
+ tos = rta_getattr_u8(iptuninfo[IFLA_IPTUN_TOS]);
+
+ if (iptuninfo[IFLA_IPTUN_PMTUDISC])
+ pmtudisc =
+ rta_getattr_u8(iptuninfo[IFLA_IPTUN_PMTUDISC]);
+
+ if (iptuninfo[IFLA_IPTUN_FLAGS])
+ iflags = rta_getattr_u16(iptuninfo[IFLA_IPTUN_FLAGS]);
+
+ if (iptuninfo[IFLA_IPTUN_LINK])
+ link = rta_getattr_u32(iptuninfo[IFLA_IPTUN_LINK]);
+
+ if (iptuninfo[IFLA_IPTUN_PROTO])
+ proto = rta_getattr_u8(iptuninfo[IFLA_IPTUN_PROTO]);
+
+ if (iptuninfo[IFLA_IPTUN_ENCAP_TYPE])
+ encaptype = rta_getattr_u16(iptuninfo[IFLA_IPTUN_ENCAP_TYPE]);
+ if (iptuninfo[IFLA_IPTUN_ENCAP_FLAGS])
+ encapflags = rta_getattr_u16(iptuninfo[IFLA_IPTUN_ENCAP_FLAGS]);
+ if (iptuninfo[IFLA_IPTUN_ENCAP_SPORT])
+ encapsport = rta_getattr_u16(iptuninfo[IFLA_IPTUN_ENCAP_SPORT]);
+ if (iptuninfo[IFLA_IPTUN_ENCAP_DPORT])
+ encapdport = rta_getattr_u16(iptuninfo[IFLA_IPTUN_ENCAP_DPORT]);
+ if (iptuninfo[IFLA_IPTUN_6RD_PREFIX])
+ memcpy(&ip6rdprefix,
+ RTA_DATA(iptuninfo[IFLA_IPTUN_6RD_PREFIX]),
+ sizeof(laddr));
+
+ if (iptuninfo[IFLA_IPTUN_6RD_PREFIXLEN])
+ ip6rdprefixlen =
+ rta_getattr_u16(iptuninfo[IFLA_IPTUN_6RD_PREFIXLEN]);
+
+ if (iptuninfo[IFLA_IPTUN_6RD_RELAY_PREFIX])
+ ip6rdrelayprefix =
+ rta_getattr_u32(iptuninfo[IFLA_IPTUN_6RD_RELAY_PREFIX]);
+
+ if (iptuninfo[IFLA_IPTUN_6RD_RELAY_PREFIXLEN])
+ ip6rdrelayprefixlen =
+ rta_getattr_u16(iptuninfo[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]);
+ }
+
+ while (argc > 0) {
+ if (strcmp(*argv, "remote") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "any"))
+ raddr = get_addr32(*argv);
+ else
+ raddr = 0;
+ } else if (strcmp(*argv, "local") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "any"))
+ laddr = get_addr32(*argv);
+ else
+ laddr = 0;
+ } else if (matches(*argv, "dev") == 0) {
+ NEXT_ARG();
+ link = if_nametoindex(*argv);
+ if (link == 0)
+ invarg("\"dev\" is invalid", *argv);
+ } else if (strcmp(*argv, "ttl") == 0 ||
+ strcmp(*argv, "hoplimit") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "inherit") != 0) {
+ if (get_u8(&ttl, *argv, 0))
+ invarg("invalid TTL\n", *argv);
+ } else
+ ttl = 0;
+ } else if (strcmp(*argv, "tos") == 0 ||
+ strcmp(*argv, "tclass") == 0 ||
+ matches(*argv, "dsfield") == 0) {
+ __u32 uval;
+ NEXT_ARG();
+ if (strcmp(*argv, "inherit") != 0) {
+ if (rtnl_dsfield_a2n(&uval, *argv))
+ invarg("bad TOS value", *argv);
+ tos = uval;
+ } else
+ tos = 1;
+ } else if (strcmp(*argv, "nopmtudisc") == 0) {
+ pmtudisc = 0;
+ } else if (strcmp(*argv, "pmtudisc") == 0) {
+ pmtudisc = 1;
+ } else if (strcmp(lu->id, "sit") == 0 &&
+ strcmp(*argv, "isatap") == 0) {
+ iflags |= SIT_ISATAP;
+ } else if (strcmp(lu->id, "sit") == 0 &&
+ strcmp(*argv, "mode") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "ipv6/ipv4") == 0 ||
+ strcmp(*argv, "ip6ip") == 0)
+ proto = IPPROTO_IPV6;
+ else if (strcmp(*argv, "ipv4/ipv4") == 0 ||
+ strcmp(*argv, "ipip") == 0 ||
+ strcmp(*argv, "ip4ip4") == 0)
+ proto = IPPROTO_IPIP;
+ else if (strcmp(*argv, "any/ipv4") == 0 ||
+ strcmp(*argv, "any") == 0)
+ proto = 0;
+ else
+ invarg("Cannot guess tunnel mode.", *argv);
+ } else if (strcmp(*argv, "noencap") == 0) {
+ encaptype = TUNNEL_ENCAP_NONE;
+ } else if (strcmp(*argv, "encap") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "fou") == 0)
+ encaptype = TUNNEL_ENCAP_FOU;
+ else if (strcmp(*argv, "gue") == 0)
+ encaptype = TUNNEL_ENCAP_GUE;
+ else if (strcmp(*argv, "none") == 0)
+ encaptype = TUNNEL_ENCAP_NONE;
+ else
+ invarg("Invalid encap type.", *argv);
+ } else if (strcmp(*argv, "encap-sport") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "auto") == 0)
+ encapsport = 0;
+ else if (get_u16(&encapsport, *argv, 0))
+ invarg("Invalid source port.", *argv);
+ } else if (strcmp(*argv, "encap-dport") == 0) {
+ NEXT_ARG();
+ if (get_u16(&encapdport, *argv, 0))
+ invarg("Invalid destination port.", *argv);
+ } else if (strcmp(*argv, "encap-csum") == 0) {
+ encapflags |= TUNNEL_ENCAP_FLAG_CSUM;
+ } else if (strcmp(*argv, "noencap-csum") == 0) {
+ encapflags &= ~TUNNEL_ENCAP_FLAG_CSUM;
+ } else if (strcmp(*argv, "encap-udp6-csum") == 0) {
+ encapflags |= TUNNEL_ENCAP_FLAG_CSUM6;
+ } else if (strcmp(*argv, "noencap-udp6-csum") == 0) {
+ encapflags &= ~TUNNEL_ENCAP_FLAG_CSUM6;
+ } else if (strcmp(*argv, "encap-remcsum") == 0) {
+ encapflags |= TUNNEL_ENCAP_FLAG_REMCSUM;
+ } else if (strcmp(*argv, "noencap-remcsum") == 0) {
+ encapflags &= ~TUNNEL_ENCAP_FLAG_REMCSUM;
+ } else if (strcmp(*argv, "6rd-prefix") == 0) {
+ inet_prefix prefix;
+ NEXT_ARG();
+ if (get_prefix(&prefix, *argv, AF_INET6))
+ invarg("invalid 6rd_prefix\n", *argv);
+ memcpy(&ip6rdprefix, prefix.data, 16);
+ ip6rdprefixlen = prefix.bitlen;
+ } else if (strcmp(*argv, "6rd-relay_prefix") == 0) {
+ inet_prefix prefix;
+ NEXT_ARG();
+ if (get_prefix(&prefix, *argv, AF_INET))
+ invarg("invalid 6rd-relay_prefix\n", *argv);
+ memcpy(&ip6rdrelayprefix, prefix.data, 4);
+ ip6rdrelayprefixlen = prefix.bitlen;
+ } else if (strcmp(*argv, "6rd-reset") == 0) {
+ inet_prefix prefix;
+ get_prefix(&prefix, "2002::", AF_INET6);
+ memcpy(&ip6rdprefix, prefix.data, 16);
+ ip6rdprefixlen = 16;
+ ip6rdrelayprefix = 0;
+ ip6rdrelayprefixlen = 0;
+ } else
+ usage(strcmp(lu->id, "sit") == 0);
+ argc--, argv++;
+ }
+
+ if (ttl && pmtudisc == 0) {
+ fprintf(stderr, "ttl != 0 and nopmtudisc are incompatible\n");
+ exit(-1);
+ }
+
+ addattr32(n, 1024, IFLA_IPTUN_LINK, link);
+ addattr32(n, 1024, IFLA_IPTUN_LOCAL, laddr);
+ addattr32(n, 1024, IFLA_IPTUN_REMOTE, raddr);
+ addattr8(n, 1024, IFLA_IPTUN_TTL, ttl);
+ addattr8(n, 1024, IFLA_IPTUN_TOS, tos);
+ addattr8(n, 1024, IFLA_IPTUN_PMTUDISC, pmtudisc);
+
+ addattr16(n, 1024, IFLA_IPTUN_ENCAP_TYPE, encaptype);
+ addattr16(n, 1024, IFLA_IPTUN_ENCAP_FLAGS, encapflags);
+ addattr16(n, 1024, IFLA_IPTUN_ENCAP_SPORT, htons(encapsport));
+ addattr16(n, 1024, IFLA_IPTUN_ENCAP_DPORT, htons(encapdport));
+
+ if (strcmp(lu->id, "sit") == 0) {
+ addattr16(n, 1024, IFLA_IPTUN_FLAGS, iflags);
+ addattr8(n, 1024, IFLA_IPTUN_PROTO, proto);
+ if (ip6rdprefixlen) {
+ addattr_l(n, 1024, IFLA_IPTUN_6RD_PREFIX,
+ &ip6rdprefix, sizeof(ip6rdprefix));
+ addattr16(n, 1024, IFLA_IPTUN_6RD_PREFIXLEN,
+ ip6rdprefixlen);
+ addattr32(n, 1024, IFLA_IPTUN_6RD_RELAY_PREFIX,
+ ip6rdrelayprefix);
+ addattr16(n, 1024, IFLA_IPTUN_6RD_RELAY_PREFIXLEN,
+ ip6rdrelayprefixlen);
+ }
+ }
+
+ return 0;
+}
+
+static void iptunnel_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
+{
+ char s1[1024];
+ char s2[64];
+ const char *local = "any";
+ const char *remote = "any";
+
+ if (!tb)
+ return;
+
+ if (tb[IFLA_IPTUN_REMOTE]) {
+ unsigned addr = rta_getattr_u32(tb[IFLA_IPTUN_REMOTE]);
+
+ if (addr)
+ remote = format_host(AF_INET, 4, &addr, s1, sizeof(s1));
+ }
+
+ fprintf(f, "remote %s ", remote);
+
+ if (tb[IFLA_IPTUN_LOCAL]) {
+ unsigned addr = rta_getattr_u32(tb[IFLA_IPTUN_LOCAL]);
+
+ if (addr)
+ local = format_host(AF_INET, 4, &addr, s1, sizeof(s1));
+ }
+
+ fprintf(f, "local %s ", local);
+
+ if (tb[IFLA_IPTUN_LINK] && rta_getattr_u32(tb[IFLA_IPTUN_LINK])) {
+ unsigned link = rta_getattr_u32(tb[IFLA_IPTUN_LINK]);
+ const char *n = if_indextoname(link, s2);
+
+ if (n)
+ fprintf(f, "dev %s ", n);
+ else
+ fprintf(f, "dev %u ", link);
+ }
+
+ if (tb[IFLA_IPTUN_TTL] && rta_getattr_u8(tb[IFLA_IPTUN_TTL]))
+ fprintf(f, "ttl %d ", rta_getattr_u8(tb[IFLA_IPTUN_TTL]));
+ else
+ fprintf(f, "ttl inherit ");
+
+ if (tb[IFLA_IPTUN_TOS] && rta_getattr_u8(tb[IFLA_IPTUN_TOS])) {
+ int tos = rta_getattr_u8(tb[IFLA_IPTUN_TOS]);
+
+ fputs("tos ", f);
+ if (tos == 1)
+ fputs("inherit ", f);
+ else
+ fprintf(f, "0x%x ", tos);
+ }
+
+ if (tb[IFLA_IPTUN_PMTUDISC] && rta_getattr_u8(tb[IFLA_IPTUN_PMTUDISC]))
+ fprintf(f, "pmtudisc ");
+ else
+ fprintf(f, "nopmtudisc ");
+
+ if (tb[IFLA_IPTUN_FLAGS]) {
+ __u16 iflags = rta_getattr_u16(tb[IFLA_IPTUN_FLAGS]);
+
+ if (iflags & SIT_ISATAP)
+ fprintf(f, "isatap ");
+ }
+
+ if (tb[IFLA_IPTUN_6RD_PREFIXLEN] &&
+ *(__u16 *)RTA_DATA(tb[IFLA_IPTUN_6RD_PREFIXLEN])) {
+ __u16 prefixlen = rta_getattr_u16(tb[IFLA_IPTUN_6RD_PREFIXLEN]);
+ __u16 relayprefixlen =
+ rta_getattr_u16(tb[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]);
+ __u32 relayprefix =
+ rta_getattr_u32(tb[IFLA_IPTUN_6RD_RELAY_PREFIX]);
+
+ printf("6rd-prefix %s/%u ",
+ inet_ntop(AF_INET6, RTA_DATA(tb[IFLA_IPTUN_6RD_PREFIX]),
+ s1, sizeof(s1)),
+ prefixlen);
+ if (relayprefix) {
+ printf("6rd-relay_prefix %s/%u ",
+ format_host(AF_INET, 4, &relayprefix, s1,
+ sizeof(s1)),
+ relayprefixlen);
+ }
+ }
+
+ if (tb[IFLA_IPTUN_ENCAP_TYPE] &&
+ *(__u16 *)RTA_DATA(tb[IFLA_IPTUN_ENCAP_TYPE]) != TUNNEL_ENCAP_NONE) {
+ __u16 type = rta_getattr_u16(tb[IFLA_IPTUN_ENCAP_TYPE]);
+ __u16 flags = rta_getattr_u16(tb[IFLA_IPTUN_ENCAP_FLAGS]);
+ __u16 sport = rta_getattr_u16(tb[IFLA_IPTUN_ENCAP_SPORT]);
+ __u16 dport = rta_getattr_u16(tb[IFLA_IPTUN_ENCAP_DPORT]);
+
+ fputs("encap ", f);
+ switch (type) {
+ case TUNNEL_ENCAP_FOU:
+ fputs("fou ", f);
+ break;
+ case TUNNEL_ENCAP_GUE:
+ fputs("gue ", f);
+ break;
+ default:
+ fputs("unknown ", f);
+ break;
+ }
+
+ if (sport == 0)
+ fputs("encap-sport auto ", f);
+ else
+ fprintf(f, "encap-sport %u", ntohs(sport));
+
+ fprintf(f, "encap-dport %u ", ntohs(dport));
+
+ if (flags & TUNNEL_ENCAP_FLAG_CSUM)
+ fputs("encap-csum ", f);
+ else
+ fputs("noencap-csum ", f);
+
+ if (flags & TUNNEL_ENCAP_FLAG_CSUM6)
+ fputs("encap-csum6 ", f);
+ else
+ fputs("noencap-csum6 ", f);
+
+ if (flags & TUNNEL_ENCAP_FLAG_REMCSUM)
+ fputs("encap-remcsum ", f);
+ else
+ fputs("noencap-remcsum ", f);
+ }
+}
+
+static void iptunnel_print_help(struct link_util *lu, int argc, char **argv,
+ FILE *f)
+{
+ print_usage(f, strcmp(lu->id, "sit") == 0);
+}
+
+struct link_util ipip_link_util = {
+ .id = "ipip",
+ .maxattr = IFLA_IPTUN_MAX,
+ .parse_opt = iptunnel_parse_opt,
+ .print_opt = iptunnel_print_opt,
+ .print_help = iptunnel_print_help,
+};
+
+struct link_util sit_link_util = {
+ .id = "sit",
+ .maxattr = IFLA_IPTUN_MAX,
+ .parse_opt = iptunnel_parse_opt,
+ .print_opt = iptunnel_print_opt,
+ .print_help = iptunnel_print_help,
+};
diff --git a/iproute2/ip/link_veth.c b/iproute2/ip/link_veth.c
new file mode 100644
index 0000000..314216c
--- /dev/null
+++ b/iproute2/ip/link_veth.c
@@ -0,0 +1,97 @@
+/*
+ * link_veth.c veth driver module
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Pavel Emelianov <xemul@openvz.org>
+ *
+ */
+
+#include <string.h>
+#include <net/if.h>
+#include <linux/veth.h>
+
+#include "utils.h"
+#include "ip_common.h"
+
+static void print_usage(FILE *f)
+{
+ printf("Usage: ip link <options> type veth [peer <options>]\n"
+ "To get <options> type 'ip link add help'\n");
+}
+
+static void usage(void)
+{
+ print_usage(stderr);
+}
+
+static int veth_parse_opt(struct link_util *lu, int argc, char **argv,
+ struct nlmsghdr *hdr)
+{
+ char *dev = NULL;
+ char *name = NULL;
+ char *link = NULL;
+ char *type = NULL;
+ int index = 0;
+ int err, len;
+ struct rtattr * data;
+ int group;
+ struct ifinfomsg *ifm, *peer_ifm;
+ unsigned int ifi_flags, ifi_change;
+
+ if (strcmp(argv[0], "peer") != 0) {
+ usage();
+ return -1;
+ }
+
+ ifm = NLMSG_DATA(hdr);
+ ifi_flags = ifm->ifi_flags;
+ ifi_change = ifm->ifi_change;
+ ifm->ifi_flags = 0;
+ ifm->ifi_change = 0;
+
+ data = NLMSG_TAIL(hdr);
+ addattr_l(hdr, 1024, VETH_INFO_PEER, NULL, 0);
+
+ hdr->nlmsg_len += sizeof(struct ifinfomsg);
+
+ err = iplink_parse(argc - 1, argv + 1, (struct iplink_req *)hdr,
+ &name, &type, &link, &dev, &group, &index);
+ if (err < 0)
+ return err;
+
+ if (name) {
+ len = strlen(name) + 1;
+ if (len > IFNAMSIZ)
+ invarg("\"name\" too long\n", *argv);
+ addattr_l(hdr, 1024, IFLA_IFNAME, name, len);
+ }
+
+ peer_ifm = RTA_DATA(data);
+ peer_ifm->ifi_index = index;
+ peer_ifm->ifi_flags = ifm->ifi_flags;
+ peer_ifm->ifi_change = ifm->ifi_change;
+ ifm->ifi_flags = ifi_flags;
+ ifm->ifi_change = ifi_change;
+
+ if (group != -1)
+ addattr32(hdr, 1024, IFLA_GROUP, group);
+
+ data->rta_len = (void *)NLMSG_TAIL(hdr) - (void *)data;
+ return argc - 1 - err;
+}
+
+static void veth_print_help(struct link_util *lu, int argc, char **argv,
+ FILE *f)
+{
+ print_usage(f);
+}
+
+struct link_util veth_link_util = {
+ .id = "veth",
+ .parse_opt = veth_parse_opt,
+ .print_help = veth_print_help,
+};
diff --git a/iproute2/ip/link_vti.c b/iproute2/ip/link_vti.c
new file mode 100644
index 0000000..f3fea33
--- /dev/null
+++ b/iproute2/ip/link_vti.c
@@ -0,0 +1,260 @@
+/*
+ * link_vti.c VTI driver module
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Herbert Xu <herbert@gondor.apana.org.au>
+ * Saurabh Mohan <saurabh.mohan@vyatta.com> Modified link_gre.c for VTI
+ */
+
+#include <string.h>
+#include <net/if.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+
+#include <linux/ip.h>
+#include <linux/if_tunnel.h>
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+#include "tunnel.h"
+
+
+static void print_usage(FILE *f)
+{
+ fprintf(f, "Usage: ip link { add | set | change | replace | del } NAME\n");
+ fprintf(f, " type { vti } [ remote ADDR ] [ local ADDR ]\n");
+ fprintf(f, " [ [i|o]key KEY ]\n");
+ fprintf(f, " [ dev PHYS_DEV ]\n");
+ fprintf(f, "\n");
+ fprintf(f, "Where: NAME := STRING\n");
+ fprintf(f, " ADDR := { IP_ADDRESS }\n");
+ fprintf(f, " KEY := { DOTTED_QUAD | NUMBER }\n");
+}
+
+static void usage(void) __attribute__((noreturn));
+static void usage(void)
+{
+ print_usage(stderr);
+ exit(-1);
+}
+
+static int vti_parse_opt(struct link_util *lu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ struct {
+ struct nlmsghdr n;
+ struct ifinfomsg i;
+ char buf[1024];
+ } req;
+ struct ifinfomsg *ifi = (struct ifinfomsg *)(n + 1);
+ struct rtattr *tb[IFLA_MAX + 1];
+ struct rtattr *linkinfo[IFLA_INFO_MAX+1];
+ struct rtattr *vtiinfo[IFLA_VTI_MAX + 1];
+ unsigned ikey = 0;
+ unsigned okey = 0;
+ unsigned saddr = 0;
+ unsigned daddr = 0;
+ unsigned link = 0;
+ int len;
+
+ if (!(n->nlmsg_flags & NLM_F_CREATE)) {
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(*ifi));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = RTM_GETLINK;
+ req.i.ifi_family = preferred_family;
+ req.i.ifi_index = ifi->ifi_index;
+
+ if (rtnl_talk(&rth, &req.n, &req.n, sizeof(req)) < 0) {
+get_failed:
+ fprintf(stderr,
+ "Failed to get existing tunnel info.\n");
+ return -1;
+ }
+
+ len = req.n.nlmsg_len;
+ len -= NLMSG_LENGTH(sizeof(*ifi));
+ if (len < 0)
+ goto get_failed;
+
+ parse_rtattr(tb, IFLA_MAX, IFLA_RTA(&req.i), len);
+
+ if (!tb[IFLA_LINKINFO])
+ goto get_failed;
+
+ parse_rtattr_nested(linkinfo, IFLA_INFO_MAX, tb[IFLA_LINKINFO]);
+
+ if (!linkinfo[IFLA_INFO_DATA])
+ goto get_failed;
+
+ parse_rtattr_nested(vtiinfo, IFLA_VTI_MAX,
+ linkinfo[IFLA_INFO_DATA]);
+
+ if (vtiinfo[IFLA_VTI_IKEY])
+ ikey = *(__u32 *)RTA_DATA(vtiinfo[IFLA_VTI_IKEY]);
+
+ if (vtiinfo[IFLA_VTI_OKEY])
+ okey = *(__u32 *)RTA_DATA(vtiinfo[IFLA_VTI_OKEY]);
+
+ if (vtiinfo[IFLA_VTI_LOCAL])
+ saddr = *(__u32 *)RTA_DATA(vtiinfo[IFLA_VTI_LOCAL]);
+
+ if (vtiinfo[IFLA_VTI_REMOTE])
+ daddr = *(__u32 *)RTA_DATA(vtiinfo[IFLA_VTI_REMOTE]);
+
+ if (vtiinfo[IFLA_VTI_LINK])
+ link = *(__u8 *)RTA_DATA(vtiinfo[IFLA_VTI_LINK]);
+ }
+
+ while (argc > 0) {
+ if (!matches(*argv, "key")) {
+ unsigned uval;
+
+ NEXT_ARG();
+ if (strchr(*argv, '.'))
+ uval = get_addr32(*argv);
+ else {
+ if (get_unsigned(&uval, *argv, 0) < 0) {
+ fprintf(stderr,
+ "Invalid value for \"key\": \"%s\"; it should be an unsigned integer\n", *argv);
+ exit(-1);
+ }
+ uval = htonl(uval);
+ }
+
+ ikey = okey = uval;
+ } else if (!matches(*argv, "ikey")) {
+ unsigned uval;
+
+ NEXT_ARG();
+ if (strchr(*argv, '.'))
+ uval = get_addr32(*argv);
+ else {
+ if (get_unsigned(&uval, *argv, 0) < 0) {
+ fprintf(stderr, "invalid value for \"ikey\": \"%s\"; it should be an unsigned integer\n", *argv);
+ exit(-1);
+ }
+ uval = htonl(uval);
+ }
+ ikey = uval;
+ } else if (!matches(*argv, "okey")) {
+ unsigned uval;
+
+ NEXT_ARG();
+ if (strchr(*argv, '.'))
+ uval = get_addr32(*argv);
+ else {
+ if (get_unsigned(&uval, *argv, 0) < 0) {
+ fprintf(stderr, "invalid value for \"okey\": \"%s\"; it should be an unsigned integer\n", *argv);
+ exit(-1);
+ }
+ uval = htonl(uval);
+ }
+ okey = uval;
+ } else if (!matches(*argv, "remote")) {
+ NEXT_ARG();
+ if (!strcmp(*argv, "any")) {
+ fprintf(stderr, "invalid value for \"remote\": \"%s\"\n", *argv);
+ exit(-1);
+ } else {
+ daddr = get_addr32(*argv);
+ }
+ } else if (!matches(*argv, "local")) {
+ NEXT_ARG();
+ if (!strcmp(*argv, "any")) {
+ fprintf(stderr, "invalid value for \"local\": \"%s\"\n", *argv);
+ exit(-1);
+ } else {
+ saddr = get_addr32(*argv);
+ }
+ } else if (!matches(*argv, "dev")) {
+ NEXT_ARG();
+ link = if_nametoindex(*argv);
+ if (link == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n",
+ *argv);
+ exit(-1);
+ }
+ } else
+ usage();
+ argc--; argv++;
+ }
+
+ addattr32(n, 1024, IFLA_VTI_IKEY, ikey);
+ addattr32(n, 1024, IFLA_VTI_OKEY, okey);
+ addattr_l(n, 1024, IFLA_VTI_LOCAL, &saddr, 4);
+ addattr_l(n, 1024, IFLA_VTI_REMOTE, &daddr, 4);
+ if (link)
+ addattr32(n, 1024, IFLA_VTI_LINK, link);
+
+ return 0;
+}
+
+static void vti_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
+{
+ char s1[1024];
+ char s2[64];
+ const char *local = "any";
+ const char *remote = "any";
+
+ if (!tb)
+ return;
+
+ if (tb[IFLA_VTI_REMOTE]) {
+ unsigned addr = *(__u32 *)RTA_DATA(tb[IFLA_VTI_REMOTE]);
+
+ if (addr)
+ remote = format_host(AF_INET, 4, &addr, s1, sizeof(s1));
+ }
+
+ fprintf(f, "remote %s ", remote);
+
+ if (tb[IFLA_VTI_LOCAL]) {
+ unsigned addr = *(__u32 *)RTA_DATA(tb[IFLA_VTI_LOCAL]);
+
+ if (addr)
+ local = format_host(AF_INET, 4, &addr, s1, sizeof(s1));
+ }
+
+ fprintf(f, "local %s ", local);
+
+ if (tb[IFLA_VTI_LINK] && *(__u32 *)RTA_DATA(tb[IFLA_VTI_LINK])) {
+ unsigned link = *(__u32 *)RTA_DATA(tb[IFLA_VTI_LINK]);
+ const char *n = if_indextoname(link, s2);
+
+ if (n)
+ fprintf(f, "dev %s ", n);
+ else
+ fprintf(f, "dev %u ", link);
+ }
+
+ if (tb[IFLA_VTI_IKEY]) {
+ inet_ntop(AF_INET, RTA_DATA(tb[IFLA_VTI_IKEY]), s2, sizeof(s2));
+ fprintf(f, "ikey %s ", s2);
+ }
+
+ if (tb[IFLA_VTI_OKEY]) {
+ inet_ntop(AF_INET, RTA_DATA(tb[IFLA_VTI_OKEY]), s2, sizeof(s2));
+ fprintf(f, "okey %s ", s2);
+ }
+}
+
+static void vti_print_help(struct link_util *lu, int argc, char **argv,
+ FILE *f)
+{
+ print_usage(f);
+}
+
+struct link_util vti_link_util = {
+ .id = "vti",
+ .maxattr = IFLA_VTI_MAX,
+ .parse_opt = vti_parse_opt,
+ .print_opt = vti_print_opt,
+ .print_help = vti_print_help,
+};
diff --git a/iproute2/ip/link_vti6.c b/iproute2/ip/link_vti6.c
new file mode 100644
index 0000000..c146f79
--- /dev/null
+++ b/iproute2/ip/link_vti6.c
@@ -0,0 +1,250 @@
+/*
+ * link_vti6.c VTI driver module
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Herbert Xu <herbert@gondor.apana.org.au>
+ * Saurabh Mohan <saurabh.mohan@vyatta.com> Modified link_gre.c for VTI
+ * Steffen Klassert <steffen.klassert@secunet.com> Modified link_vti.c for IPv6
+ */
+
+#include <string.h>
+#include <net/if.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+
+#include <linux/ip.h>
+#include <linux/if_tunnel.h>
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+#include "tunnel.h"
+
+
+static void usage(void) __attribute__((noreturn));
+static void usage(void)
+{
+ fprintf(stderr, "Usage: ip link { add | set | change | replace | del } NAME\n");
+ fprintf(stderr, " type { vti6 } [ remote ADDR ] [ local ADDR ]\n");
+ fprintf(stderr, " [ [i|o]key KEY ]\n");
+ fprintf(stderr, " [ dev PHYS_DEV ]\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "Where: NAME := STRING\n");
+ fprintf(stderr, " ADDR := { IPV6_ADDRESS }\n");
+ fprintf(stderr, " KEY := { DOTTED_QUAD | NUMBER }\n");
+ exit(-1);
+}
+
+static int vti6_parse_opt(struct link_util *lu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ struct {
+ struct nlmsghdr n;
+ struct ifinfomsg i;
+ char buf[1024];
+ } req;
+ struct ifinfomsg *ifi = (struct ifinfomsg *)(n + 1);
+ struct rtattr *tb[IFLA_MAX + 1];
+ struct rtattr *linkinfo[IFLA_INFO_MAX+1];
+ struct rtattr *vtiinfo[IFLA_VTI_MAX + 1];
+ struct in6_addr saddr;
+ struct in6_addr daddr;
+ unsigned ikey = 0;
+ unsigned okey = 0;
+ unsigned link = 0;
+ int len;
+
+ if (!(n->nlmsg_flags & NLM_F_CREATE)) {
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(*ifi));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = RTM_GETLINK;
+ req.i.ifi_family = preferred_family;
+ req.i.ifi_index = ifi->ifi_index;
+
+ if (rtnl_talk(&rth, &req.n, &req.n, sizeof(req)) < 0) {
+get_failed:
+ fprintf(stderr,
+ "Failed to get existing tunnel info.\n");
+ return -1;
+ }
+
+ len = req.n.nlmsg_len;
+ len -= NLMSG_LENGTH(sizeof(*ifi));
+ if (len < 0)
+ goto get_failed;
+
+ parse_rtattr(tb, IFLA_MAX, IFLA_RTA(&req.i), len);
+
+ if (!tb[IFLA_LINKINFO])
+ goto get_failed;
+
+ parse_rtattr_nested(linkinfo, IFLA_INFO_MAX, tb[IFLA_LINKINFO]);
+
+ if (!linkinfo[IFLA_INFO_DATA])
+ goto get_failed;
+
+ parse_rtattr_nested(vtiinfo, IFLA_VTI_MAX,
+ linkinfo[IFLA_INFO_DATA]);
+
+ if (vtiinfo[IFLA_VTI_IKEY])
+ ikey = rta_getattr_u32(vtiinfo[IFLA_VTI_IKEY]);
+
+ if (vtiinfo[IFLA_VTI_OKEY])
+ okey = rta_getattr_u32(vtiinfo[IFLA_VTI_OKEY]);
+
+ if (vtiinfo[IFLA_VTI_LOCAL])
+ memcpy(&saddr, RTA_DATA(vtiinfo[IFLA_VTI_LOCAL]), sizeof(saddr));
+
+ if (vtiinfo[IFLA_VTI_REMOTE])
+ memcpy(&daddr, RTA_DATA(vtiinfo[IFLA_VTI_REMOTE]), sizeof(daddr));
+
+ if (vtiinfo[IFLA_VTI_LINK])
+ link = rta_getattr_u8(vtiinfo[IFLA_VTI_LINK]);
+ }
+
+ while (argc > 0) {
+ if (!matches(*argv, "key")) {
+ unsigned uval;
+
+ NEXT_ARG();
+ if (strchr(*argv, '.'))
+ uval = get_addr32(*argv);
+ else {
+ if (get_unsigned(&uval, *argv, 0) < 0) {
+ fprintf(stderr,
+ "Invalid value for \"key\": \"%s\"; it should be an unsigned integer\n", *argv);
+ exit(-1);
+ }
+ uval = htonl(uval);
+ }
+
+ ikey = okey = uval;
+ } else if (!matches(*argv, "ikey")) {
+ unsigned uval;
+
+ NEXT_ARG();
+ if (strchr(*argv, '.'))
+ uval = get_addr32(*argv);
+ else {
+ if (get_unsigned(&uval, *argv, 0) < 0) {
+ fprintf(stderr, "invalid value for \"ikey\": \"%s\"; it should be an unsigned integer\n", *argv);
+ exit(-1);
+ }
+ uval = htonl(uval);
+ }
+ ikey = uval;
+ } else if (!matches(*argv, "okey")) {
+ unsigned uval;
+
+ NEXT_ARG();
+ if (strchr(*argv, '.'))
+ uval = get_addr32(*argv);
+ else {
+ if (get_unsigned(&uval, *argv, 0) < 0) {
+ fprintf(stderr, "invalid value for \"okey\": \"%s\"; it should be an unsigned integer\n", *argv);
+ exit(-1);
+ }
+ uval = htonl(uval);
+ }
+ okey = uval;
+ } else if (!matches(*argv, "remote")) {
+ NEXT_ARG();
+ if (!strcmp(*argv, "any")) {
+ fprintf(stderr, "invalid value for \"remote\": \"%s\"\n", *argv);
+ exit(-1);
+ } else {
+ inet_prefix addr;
+ get_prefix(&addr, *argv, AF_INET6);
+ memcpy(&daddr, addr.data, addr.bytelen);
+ }
+ } else if (!matches(*argv, "local")) {
+ NEXT_ARG();
+ if (!strcmp(*argv, "any")) {
+ fprintf(stderr, "invalid value for \"local\": \"%s\"\n", *argv);
+ exit(-1);
+ } else {
+ inet_prefix addr;
+ get_prefix(&addr, *argv, AF_INET6);
+ memcpy(&saddr, addr.data, addr.bytelen);
+ }
+ } else if (!matches(*argv, "dev")) {
+ NEXT_ARG();
+ link = if_nametoindex(*argv);
+ if (link == 0)
+ exit(-1);
+ } else
+ usage();
+ argc--; argv++;
+ }
+
+ addattr32(n, 1024, IFLA_VTI_IKEY, ikey);
+ addattr32(n, 1024, IFLA_VTI_OKEY, okey);
+ addattr_l(n, 1024, IFLA_VTI_LOCAL, &saddr, sizeof(saddr));
+ addattr_l(n, 1024, IFLA_VTI_REMOTE, &daddr, sizeof(daddr));
+ if (link)
+ addattr32(n, 1024, IFLA_VTI_LINK, link);
+
+ return 0;
+}
+
+static void vti6_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
+{
+ char s1[1024];
+ char s2[64];
+ const char *local = "any";
+ const char *remote = "any";
+ struct in6_addr saddr;
+ struct in6_addr daddr;
+
+ if (!tb)
+ return;
+
+ if (tb[IFLA_VTI_REMOTE]) {
+ memcpy(&daddr, RTA_DATA(tb[IFLA_VTI_REMOTE]), sizeof(daddr));
+
+ remote = format_host(AF_INET6, 16, &daddr, s1, sizeof(s1));
+ }
+
+ fprintf(f, "remote %s ", remote);
+
+ if (tb[IFLA_VTI_LOCAL]) {
+ memcpy(&saddr, RTA_DATA(tb[IFLA_VTI_LOCAL]), sizeof(saddr));
+
+ local = format_host(AF_INET6, 16, &saddr, s1, sizeof(s1));
+ }
+
+ fprintf(f, "local %s ", local);
+
+ if (tb[IFLA_VTI_LINK] && *(__u32 *)RTA_DATA(tb[IFLA_VTI_LINK])) {
+ unsigned link = *(__u32 *)RTA_DATA(tb[IFLA_VTI_LINK]);
+ const char *n = if_indextoname(link, s2);
+
+ if (n)
+ fprintf(f, "dev %s ", n);
+ else
+ fprintf(f, "dev %u ", link);
+ }
+
+ if (tb[IFLA_VTI_IKEY]) {
+ inet_ntop(AF_INET, RTA_DATA(tb[IFLA_VTI_IKEY]), s2, sizeof(s2));
+ fprintf(f, "ikey %s ", s2);
+ }
+
+ if (tb[IFLA_VTI_OKEY]) {
+ inet_ntop(AF_INET, RTA_DATA(tb[IFLA_VTI_OKEY]), s2, sizeof(s2));
+ fprintf(f, "okey %s ", s2);
+ }
+}
+
+struct link_util vti6_link_util = {
+ .id = "vti6",
+ .maxattr = IFLA_VTI_MAX,
+ .parse_opt = vti6_parse_opt,
+ .print_opt = vti6_print_opt,
+};
diff --git a/iproute2/ip/routef b/iproute2/ip/routef
new file mode 100644
index 0000000..d266e2d
--- /dev/null
+++ b/iproute2/ip/routef
@@ -0,0 +1,9 @@
+#! /bin/sh
+
+if [ -z "$*" ] ; then
+ exec ip -4 ro flush scope global type unicast
+else
+ echo "Usage: routef"
+ echo
+ echo "This script will flush the IPv4 routing table"
+fi
diff --git a/iproute2/ip/routel b/iproute2/ip/routel
new file mode 100644
index 0000000..8d1d352
--- /dev/null
+++ b/iproute2/ip/routel
@@ -0,0 +1,60 @@
+#!/bin/sh
+#$Id$
+
+#
+# Script created by: Stephen R. van den Berg <srb@cuci.nl>, 1999/04/18
+# Donated to the public domain.
+#
+# This script transforms the output of "ip" into more readable text.
+# "ip" is the Linux-advanced-routing configuration tool part of the
+# iproute package.
+#
+
+test "X-h" = "X$1" && echo "Usage: $0 [tablenr [raw ip args...]]" && exit 64
+
+test -z "$*" && set 0
+
+ip route list table "$@" |
+ while read network rest
+ do set xx $rest
+ shift
+ proto=""
+ via=""
+ dev=""
+ scope=""
+ src=""
+ table=""
+ case $network in
+ broadcast|local|unreachable) via=$network
+ network=$1
+ shift
+ ;;
+ esac
+ while test $# != 0
+ do
+ key=$1
+ val=$2
+ eval "$key=$val"
+ shift 2
+ done
+ echo "$network $via $src $proto $scope $dev $table"
+ done | awk -F ' ' '
+BEGIN {
+ format="%15s%-3s %15s %15s %8s %8s%7s %s\n";
+ printf(format,"target","","gateway","source","proto","scope","dev","tbl");
+ }
+ { network=$1;
+ mask="";
+ if(match(network,"/"))
+ { mask=" "substr(network,RSTART+1);
+ network=substr(network,0,RSTART);
+ }
+ via=$2;
+ src=$3;
+ proto=$4;
+ scope=$5;
+ dev=$6;
+ table=$7;
+ printf(format,network,mask,via,src,proto,scope,dev,table);
+ }
+'
diff --git a/iproute2/ip/rtm_map.c b/iproute2/ip/rtm_map.c
new file mode 100644
index 0000000..1d7d2c7
--- /dev/null
+++ b/iproute2/ip/rtm_map.c
@@ -0,0 +1,124 @@
+/*
+ * rtm_map.c
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+#include "rt_names.h"
+#include "utils.h"
+
+char *rtnl_rtntype_n2a(int id, char *buf, int len)
+{
+ switch (id) {
+ case RTN_UNSPEC:
+ return "none";
+ case RTN_UNICAST:
+ return "unicast";
+ case RTN_LOCAL:
+ return "local";
+ case RTN_BROADCAST:
+ return "broadcast";
+ case RTN_ANYCAST:
+ return "anycast";
+ case RTN_MULTICAST:
+ return "multicast";
+ case RTN_BLACKHOLE:
+ return "blackhole";
+ case RTN_UNREACHABLE:
+ return "unreachable";
+ case RTN_PROHIBIT:
+ return "prohibit";
+ case RTN_THROW:
+ return "throw";
+ case RTN_NAT:
+ return "nat";
+ case RTN_XRESOLVE:
+ return "xresolve";
+ default:
+ snprintf(buf, len, "%d", id);
+ return buf;
+ }
+}
+
+
+int rtnl_rtntype_a2n(int *id, char *arg)
+{
+ char *end;
+ unsigned long res;
+
+ if (strcmp(arg, "local") == 0)
+ res = RTN_LOCAL;
+ else if (strcmp(arg, "nat") == 0)
+ res = RTN_NAT;
+ else if (matches(arg, "broadcast") == 0 ||
+ strcmp(arg, "brd") == 0)
+ res = RTN_BROADCAST;
+ else if (matches(arg, "anycast") == 0)
+ res = RTN_ANYCAST;
+ else if (matches(arg, "multicast") == 0)
+ res = RTN_MULTICAST;
+ else if (matches(arg, "prohibit") == 0)
+ res = RTN_PROHIBIT;
+ else if (matches(arg, "unreachable") == 0)
+ res = RTN_UNREACHABLE;
+ else if (matches(arg, "blackhole") == 0)
+ res = RTN_BLACKHOLE;
+ else if (matches(arg, "xresolve") == 0)
+ res = RTN_XRESOLVE;
+ else if (matches(arg, "unicast") == 0)
+ res = RTN_UNICAST;
+ else if (strcmp(arg, "throw") == 0)
+ res = RTN_THROW;
+ else {
+ res = strtoul(arg, &end, 0);
+ if (!end || end == arg || *end || res > 255)
+ return -1;
+ }
+ *id = res;
+ return 0;
+}
+
+static int get_rt_realms(__u32 *realms, char *arg)
+{
+ __u32 realm = 0;
+ char *p = strchr(arg, '/');
+
+ *realms = 0;
+ if (p) {
+ *p = 0;
+ if (rtnl_rtrealm_a2n(realms, arg)) {
+ *p = '/';
+ return -1;
+ }
+ *realms <<= 16;
+ *p = '/';
+ arg = p+1;
+ }
+ if (*arg && rtnl_rtrealm_a2n(&realm, arg))
+ return -1;
+ *realms |= realm;
+ return 0;
+}
+
+int get_rt_realms_or_raw(__u32 *realms, char *arg)
+{
+ if (!get_rt_realms(realms, arg))
+ return 0;
+
+ return get_unsigned(realms, arg, 0);
+}
diff --git a/iproute2/ip/rtmon.c b/iproute2/ip/rtmon.c
new file mode 100644
index 0000000..42b24fb
--- /dev/null
+++ b/iproute2/ip/rtmon.c
@@ -0,0 +1,183 @@
+/*
+ * rtmon.c RTnetlink listener.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <netinet/in.h>
+#include <string.h>
+
+#include "SNAPSHOT.h"
+
+#include "utils.h"
+#include "libnetlink.h"
+
+int resolve_hosts = 0;
+static int init_phase = 1;
+
+static void write_stamp(FILE *fp)
+{
+ char buf[128];
+ struct nlmsghdr *n1 = (void*)buf;
+ struct timeval tv;
+
+ n1->nlmsg_type = NLMSG_TSTAMP;
+ n1->nlmsg_flags = 0;
+ n1->nlmsg_seq = 0;
+ n1->nlmsg_pid = 0;
+ n1->nlmsg_len = NLMSG_LENGTH(4*2);
+ gettimeofday(&tv, NULL);
+ ((__u32*)NLMSG_DATA(n1))[0] = tv.tv_sec;
+ ((__u32*)NLMSG_DATA(n1))[1] = tv.tv_usec;
+ fwrite((void*)n1, 1, NLMSG_ALIGN(n1->nlmsg_len), fp);
+}
+
+static int dump_msg(const struct sockaddr_nl *who, struct rtnl_ctrl_data *ctrl,
+ struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ if (!init_phase)
+ write_stamp(fp);
+ fwrite((void*)n, 1, NLMSG_ALIGN(n->nlmsg_len), fp);
+ fflush(fp);
+ return 0;
+}
+
+static int dump_msg2(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg)
+{
+ return dump_msg(who, NULL, n, arg);
+}
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: rtmon file FILE [ all | LISTofOBJECTS]\n");
+ fprintf(stderr, "LISTofOBJECTS := [ link ] [ address ] [ route ]\n");
+ exit(-1);
+}
+
+int
+main(int argc, char **argv)
+{
+ FILE *fp;
+ struct rtnl_handle rth;
+ int family = AF_UNSPEC;
+ unsigned groups = ~0U;
+ int llink = 0;
+ int laddr = 0;
+ int lroute = 0;
+ char *file = NULL;
+
+ while (argc > 1) {
+ if (matches(argv[1], "-family") == 0) {
+ argc--;
+ argv++;
+ if (argc <= 1)
+ usage();
+ if (strcmp(argv[1], "inet") == 0)
+ family = AF_INET;
+ else if (strcmp(argv[1], "inet6") == 0)
+ family = AF_INET6;
+ else if (strcmp(argv[1], "link") == 0)
+ family = AF_INET6;
+ else if (strcmp(argv[1], "help") == 0)
+ usage();
+ else {
+ fprintf(stderr, "Protocol ID \"%s\" is unknown, try \"rtmon help\".\n", argv[1]);
+ exit(-1);
+ }
+ } else if (strcmp(argv[1], "-4") == 0) {
+ family = AF_INET;
+ } else if (strcmp(argv[1], "-6") == 0) {
+ family = AF_INET6;
+ } else if (strcmp(argv[1], "-0") == 0) {
+ family = AF_PACKET;
+ } else if (matches(argv[1], "-Version") == 0) {
+ printf("rtmon utility, iproute2-ss%s\n", SNAPSHOT);
+ exit(0);
+ } else if (matches(argv[1], "file") == 0) {
+ argc--;
+ argv++;
+ if (argc <= 1)
+ usage();
+ file = argv[1];
+ } else if (matches(argv[1], "link") == 0) {
+ llink=1;
+ groups = 0;
+ } else if (matches(argv[1], "address") == 0) {
+ laddr=1;
+ groups = 0;
+ } else if (matches(argv[1], "route") == 0) {
+ lroute=1;
+ groups = 0;
+ } else if (strcmp(argv[1], "all") == 0) {
+ groups = ~0U;
+ } else if (matches(argv[1], "help") == 0) {
+ usage();
+ } else {
+ fprintf(stderr, "Argument \"%s\" is unknown, try \"rtmon help\".\n", argv[1]);
+ exit(-1);
+ }
+ argc--; argv++;
+ }
+
+ if (file == NULL) {
+ fprintf(stderr, "Not enough information: argument \"file\" is required\n");
+ exit(-1);
+ }
+ if (llink)
+ groups |= nl_mgrp(RTNLGRP_LINK);
+ if (laddr) {
+ if (!family || family == AF_INET)
+ groups |= nl_mgrp(RTNLGRP_IPV4_IFADDR);
+ if (!family || family == AF_INET6)
+ groups |= nl_mgrp(RTNLGRP_IPV6_IFADDR);
+ }
+ if (lroute) {
+ if (!family || family == AF_INET)
+ groups |= nl_mgrp(RTNLGRP_IPV4_ROUTE);
+ if (!family || family == AF_INET6)
+ groups |= nl_mgrp(RTNLGRP_IPV6_ROUTE);
+ }
+
+ fp = fopen(file, "w");
+ if (fp == NULL) {
+ perror("Cannot fopen");
+ exit(-1);
+ }
+
+ if (rtnl_open(&rth, groups) < 0)
+ exit(1);
+
+ if (rtnl_wilddump_request(&rth, AF_UNSPEC, RTM_GETLINK) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+
+ write_stamp(fp);
+
+ if (rtnl_dump_filter(&rth, dump_msg2, fp) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ return 1;
+ }
+
+ init_phase = 0;
+
+ if (rtnl_listen(&rth, dump_msg, (void*)fp) < 0)
+ exit(2);
+
+ exit(0);
+}
diff --git a/iproute2/ip/rtpr b/iproute2/ip/rtpr
new file mode 100644
index 0000000..c3629fd
--- /dev/null
+++ b/iproute2/ip/rtpr
@@ -0,0 +1,4 @@
+#! /bin/bash
+
+exec tr "[\\\\]" "[
+]"
diff --git a/iproute2/ip/static-syms.c b/iproute2/ip/static-syms.c
new file mode 100644
index 0000000..0bc8074
--- /dev/null
+++ b/iproute2/ip/static-syms.c
@@ -0,0 +1,14 @@
+/*
+ * This file creates a dummy version of dynamic loading
+ * for environments where dynamic linking
+ * is not used or available.
+ */
+
+#include <string.h>
+#include "dlfcn.h"
+
+void *_dlsym(const char *sym)
+{
+#include "static-syms.h"
+ return NULL;
+}
diff --git a/iproute2/ip/tcp_metrics.c b/iproute2/ip/tcp_metrics.c
new file mode 100644
index 0000000..57b605f
--- /dev/null
+++ b/iproute2/ip/tcp_metrics.c
@@ -0,0 +1,510 @@
+/*
+ * tcp_metrics.c "ip tcp_metrics/tcpmetrics"
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation;
+ *
+ * Authors: Julian Anastasov <ja@ssi.bg>, August 2012
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+#include <sys/ioctl.h>
+#include <linux/if.h>
+
+#include <linux/genetlink.h>
+#include <linux/tcp_metrics.h>
+
+#include "utils.h"
+#include "ip_common.h"
+#include "libgenl.h"
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: ip tcp_metrics/tcpmetrics { COMMAND | help }\n");
+ fprintf(stderr, " ip tcp_metrics { show | flush } SELECTOR\n");
+ fprintf(stderr, " ip tcp_metrics delete [ address ] ADDRESS\n");
+ fprintf(stderr, "SELECTOR := [ [ address ] PREFIX ]\n");
+ exit(-1);
+}
+
+/* netlink socket */
+static struct rtnl_handle grth = { .fd = -1 };
+static int genl_family = -1;
+
+#define TCPM_REQUEST(_req, _bufsiz, _cmd, _flags) \
+ GENL_REQUEST(_req, _bufsiz, genl_family, 0, \
+ TCP_METRICS_GENL_VERSION, _cmd, _flags)
+
+#define CMD_LIST 0x0001 /* list, lst, show */
+#define CMD_DEL 0x0002 /* delete, remove */
+#define CMD_FLUSH 0x0004 /* flush */
+
+static struct {
+ char *name;
+ int code;
+} cmds[] = {
+ { "list", CMD_LIST },
+ { "lst", CMD_LIST },
+ { "show", CMD_LIST },
+ { "delete", CMD_DEL },
+ { "remove", CMD_DEL },
+ { "flush", CMD_FLUSH },
+};
+
+static char *metric_name[TCP_METRIC_MAX + 1] = {
+ [TCP_METRIC_RTT] = "rtt",
+ [TCP_METRIC_RTTVAR] = "rttvar",
+ [TCP_METRIC_SSTHRESH] = "ssthresh",
+ [TCP_METRIC_CWND] = "cwnd",
+ [TCP_METRIC_REORDERING] = "reordering",
+};
+
+static struct
+{
+ int flushed;
+ char *flushb;
+ int flushp;
+ int flushe;
+ int cmd;
+ inet_prefix daddr;
+ inet_prefix saddr;
+} f;
+
+static int flush_update(void)
+{
+ if (rtnl_send_check(&grth, f.flushb, f.flushp) < 0) {
+ perror("Failed to send flush request\n");
+ return -1;
+ }
+ f.flushp = 0;
+ return 0;
+}
+
+static int process_msg(const struct sockaddr_nl *who, struct nlmsghdr *n,
+ void *arg)
+{
+ FILE *fp = (FILE *) arg;
+ struct genlmsghdr *ghdr;
+ struct rtattr *attrs[TCP_METRICS_ATTR_MAX + 1], *a;
+ int len = n->nlmsg_len;
+ char abuf[256];
+ inet_prefix daddr, saddr;
+ int family, i, atype, stype, dlen = 0, slen = 0;
+
+ if (n->nlmsg_type != genl_family)
+ return -1;
+
+ len -= NLMSG_LENGTH(GENL_HDRLEN);
+ if (len < 0)
+ return -1;
+
+ ghdr = NLMSG_DATA(n);
+ if (ghdr->cmd != TCP_METRICS_CMD_GET)
+ return 0;
+
+ parse_rtattr(attrs, TCP_METRICS_ATTR_MAX, (void *) ghdr + GENL_HDRLEN,
+ len);
+
+ a = attrs[TCP_METRICS_ATTR_ADDR_IPV4];
+ if (a) {
+ if (f.daddr.family && f.daddr.family != AF_INET)
+ return 0;
+ memcpy(&daddr.data, RTA_DATA(a), 4);
+ daddr.bytelen = 4;
+ family = AF_INET;
+ atype = TCP_METRICS_ATTR_ADDR_IPV4;
+ dlen = RTA_PAYLOAD(a);
+ } else {
+ a = attrs[TCP_METRICS_ATTR_ADDR_IPV6];
+ if (a) {
+ if (f.daddr.family && f.daddr.family != AF_INET6)
+ return 0;
+ memcpy(&daddr.data, RTA_DATA(a), 16);
+ daddr.bytelen = 16;
+ family = AF_INET6;
+ atype = TCP_METRICS_ATTR_ADDR_IPV6;
+ dlen = RTA_PAYLOAD(a);
+ } else
+ return 0;
+ }
+
+ a = attrs[TCP_METRICS_ATTR_SADDR_IPV4];
+ if (a) {
+ if (f.saddr.family && f.saddr.family != AF_INET)
+ return 0;
+ memcpy(&saddr.data, RTA_DATA(a), 4);
+ saddr.bytelen = 4;
+ stype = TCP_METRICS_ATTR_SADDR_IPV4;
+ slen = RTA_PAYLOAD(a);
+ } else {
+ a = attrs[TCP_METRICS_ATTR_SADDR_IPV6];
+ if (a) {
+ if (f.saddr.family && f.saddr.family != AF_INET6)
+ return 0;
+ memcpy(&saddr.data, RTA_DATA(a), 16);
+ saddr.bytelen = 16;
+ stype = TCP_METRICS_ATTR_SADDR_IPV6;
+ slen = RTA_PAYLOAD(a);
+ }
+ }
+
+ if (f.daddr.family && f.daddr.bitlen >= 0 &&
+ inet_addr_match(&daddr, &f.daddr, f.daddr.bitlen))
+ return 0;
+ /* Only check for the source-address if the kernel supports it,
+ * meaning slen != 0.
+ */
+ if (slen && f.saddr.family && f.saddr.bitlen >= 0 &&
+ inet_addr_match(&saddr, &f.saddr, f.saddr.bitlen))
+ return 0;
+
+ if (f.flushb) {
+ struct nlmsghdr *fn;
+ TCPM_REQUEST(req2, 128, TCP_METRICS_CMD_DEL, NLM_F_REQUEST);
+
+ addattr_l(&req2.n, sizeof(req2), atype, &daddr.data,
+ daddr.bytelen);
+ if (slen)
+ addattr_l(&req2.n, sizeof(req2), stype, &saddr.data,
+ saddr.bytelen);
+
+ if (NLMSG_ALIGN(f.flushp) + req2.n.nlmsg_len > f.flushe) {
+ if (flush_update())
+ return -1;
+ }
+ fn = (struct nlmsghdr *) (f.flushb + NLMSG_ALIGN(f.flushp));
+ memcpy(fn, &req2.n, req2.n.nlmsg_len);
+ fn->nlmsg_seq = ++grth.seq;
+ f.flushp = (((char *) fn) + req2.n.nlmsg_len) - f.flushb;
+ f.flushed++;
+ if (show_stats < 2)
+ return 0;
+ }
+
+ if (f.cmd & (CMD_DEL | CMD_FLUSH))
+ fprintf(fp, "Deleted ");
+
+ fprintf(fp, "%s",
+ format_host(family, dlen, &daddr.data, abuf, sizeof(abuf)));
+
+ a = attrs[TCP_METRICS_ATTR_AGE];
+ if (a) {
+ unsigned long long val = rta_getattr_u64(a);
+
+ fprintf(fp, " age %llu.%03llusec",
+ val / 1000, val % 1000);
+ }
+
+ a = attrs[TCP_METRICS_ATTR_TW_TS_STAMP];
+ if (a) {
+ __s32 val = (__s32) rta_getattr_u32(a);
+ __u32 tsval;
+
+ a = attrs[TCP_METRICS_ATTR_TW_TSVAL];
+ tsval = a ? rta_getattr_u32(a) : 0;
+ fprintf(fp, " tw_ts %u/%dsec ago", tsval, val);
+ }
+
+ a = attrs[TCP_METRICS_ATTR_VALS];
+ if (a) {
+ struct rtattr *m[TCP_METRIC_MAX + 1 + 1];
+ unsigned long rtt = 0, rttvar = 0;
+
+ parse_rtattr_nested(m, TCP_METRIC_MAX + 1, a);
+
+ for (i = 0; i < TCP_METRIC_MAX + 1; i++) {
+ unsigned long val;
+
+ a = m[i + 1];
+ if (!a)
+ continue;
+ if (i != TCP_METRIC_RTT &&
+ i != TCP_METRIC_RTT_US &&
+ i != TCP_METRIC_RTTVAR &&
+ i != TCP_METRIC_RTTVAR_US) {
+ if (metric_name[i])
+ fprintf(fp, " %s ", metric_name[i]);
+ else
+ fprintf(fp, " metric_%d ", i);
+ }
+ val = rta_getattr_u32(a);
+ switch (i) {
+ case TCP_METRIC_RTT:
+ if (!rtt)
+ rtt = (val * 1000UL) >> 3;
+ break;
+ case TCP_METRIC_RTTVAR:
+ if (!rttvar)
+ rttvar = (val * 1000UL) >> 2;
+ break;
+ case TCP_METRIC_RTT_US:
+ rtt = val >> 3;
+ break;
+ case TCP_METRIC_RTTVAR_US:
+ rttvar = val >> 2;
+ break;
+ case TCP_METRIC_SSTHRESH:
+ case TCP_METRIC_CWND:
+ case TCP_METRIC_REORDERING:
+ default:
+ fprintf(fp, "%lu", val);
+ break;
+ }
+ }
+ if (rtt)
+ fprintf(fp, " rtt %luus", rtt);
+ if (rttvar)
+ fprintf(fp, " rttvar %luus", rttvar);
+ }
+
+ a = attrs[TCP_METRICS_ATTR_FOPEN_MSS];
+ if (a)
+ fprintf(fp, " fo_mss %u", rta_getattr_u16(a));
+
+ a = attrs[TCP_METRICS_ATTR_FOPEN_SYN_DROPS];
+ if (a) {
+ __u16 syn_loss = rta_getattr_u16(a);
+ unsigned long long ts;
+
+ a = attrs[TCP_METRICS_ATTR_FOPEN_SYN_DROP_TS];
+ ts = a ? rta_getattr_u64(a) : 0;
+
+ fprintf(fp, " fo_syn_drops %u/%llu.%03llusec ago",
+ syn_loss, ts / 1000, ts % 1000);
+ }
+
+ a = attrs[TCP_METRICS_ATTR_FOPEN_COOKIE];
+ if (a) {
+ char cookie[32 + 1];
+ unsigned char *ptr = RTA_DATA(a);
+ int i, max = RTA_PAYLOAD(a);
+
+ if (max > 16)
+ max = 16;
+ cookie[0] = 0;
+ for (i = 0; i < max; i++)
+ sprintf(cookie + i + i, "%02x", ptr[i]);
+ fprintf(fp, " fo_cookie %s", cookie);
+ }
+
+ if (slen) {
+ fprintf(fp, " source %s",
+ format_host(family, slen, &saddr.data, abuf,
+ sizeof(abuf)));
+ }
+
+ fprintf(fp, "\n");
+
+ fflush(fp);
+ return 0;
+}
+
+static int tcpm_do_cmd(int cmd, int argc, char **argv)
+{
+ TCPM_REQUEST(req, 1024, TCP_METRICS_CMD_GET, NLM_F_REQUEST);
+ int atype = -1, stype = -1;
+ int ack;
+
+ memset(&f, 0, sizeof(f));
+ f.daddr.bitlen = -1;
+ f.daddr.family = preferred_family;
+ f.saddr.bitlen = -1;
+ f.saddr.family = preferred_family;
+
+ switch (preferred_family) {
+ case AF_UNSPEC:
+ case AF_INET:
+ case AF_INET6:
+ break;
+ default:
+ fprintf(stderr, "Unsupported protocol family: %d\n", preferred_family);
+ return -1;
+ }
+
+ for (; argc > 0; argc--, argv++) {
+ if (strcmp(*argv, "src") == 0 ||
+ strcmp(*argv, "source") == 0) {
+ char *who = *argv;
+ NEXT_ARG();
+ if (matches(*argv, "help") == 0)
+ usage();
+ if (f.saddr.bitlen >= 0)
+ duparg2(who, *argv);
+
+ get_prefix(&f.saddr, *argv, preferred_family);
+ if (f.saddr.bytelen && f.saddr.bytelen * 8 == f.saddr.bitlen) {
+ if (f.saddr.family == AF_INET)
+ stype = TCP_METRICS_ATTR_SADDR_IPV4;
+ else if (f.saddr.family == AF_INET6)
+ stype = TCP_METRICS_ATTR_SADDR_IPV6;
+ }
+
+ if (stype < 0) {
+ fprintf(stderr, "Error: a specific IP address is expected rather than \"%s\"\n",
+ *argv);
+ return -1;
+ }
+ } else {
+ char *who = "address";
+ if (strcmp(*argv, "addr") == 0 ||
+ strcmp(*argv, "address") == 0) {
+ who = *argv;
+ NEXT_ARG();
+ }
+ if (matches(*argv, "help") == 0)
+ usage();
+ if (f.daddr.bitlen >= 0)
+ duparg2(who, *argv);
+
+ get_prefix(&f.daddr, *argv, preferred_family);
+ if (f.daddr.bytelen && f.daddr.bytelen * 8 == f.daddr.bitlen) {
+ if (f.daddr.family == AF_INET)
+ atype = TCP_METRICS_ATTR_ADDR_IPV4;
+ else if (f.daddr.family == AF_INET6)
+ atype = TCP_METRICS_ATTR_ADDR_IPV6;
+ }
+ if ((CMD_DEL & cmd) && atype < 0) {
+ fprintf(stderr, "Error: a specific IP address is expected rather than \"%s\"\n",
+ *argv);
+ return -1;
+ }
+ }
+ argc--; argv++;
+ }
+
+ if (cmd == CMD_DEL && atype < 0)
+ missarg("address");
+
+ /* flush for exact address ? Single del */
+ if (cmd == CMD_FLUSH && atype >= 0)
+ cmd = CMD_DEL;
+
+ /* flush for all addresses ? Single del without address */
+ if (cmd == CMD_FLUSH && f.daddr.bitlen <= 0 &&
+ f.saddr.bitlen <= 0 && preferred_family == AF_UNSPEC) {
+ cmd = CMD_DEL;
+ req.g.cmd = TCP_METRICS_CMD_DEL;
+ ack = 1;
+ } else if (cmd == CMD_DEL) {
+ req.g.cmd = TCP_METRICS_CMD_DEL;
+ ack = 1;
+ } else { /* CMD_FLUSH, CMD_LIST */
+ ack = 0;
+ }
+
+ if (genl_family < 0) {
+ if (rtnl_open_byproto(&grth, 0, NETLINK_GENERIC) < 0) {
+ fprintf(stderr, "Cannot open generic netlink socket\n");
+ exit(1);
+ }
+ genl_family = genl_resolve_family(&grth,
+ TCP_METRICS_GENL_NAME);
+ if (genl_family < 0)
+ exit(1);
+ req.n.nlmsg_type = genl_family;
+ }
+
+ if (!(cmd & CMD_FLUSH) && (atype >= 0 || (cmd & CMD_DEL))) {
+ if (ack)
+ req.n.nlmsg_flags |= NLM_F_ACK;
+ if (atype >= 0)
+ addattr_l(&req.n, sizeof(req), atype, &f.daddr.data,
+ f.daddr.bytelen);
+ if (stype >= 0)
+ addattr_l(&req.n, sizeof(req), stype, &f.saddr.data,
+ f.saddr.bytelen);
+ } else {
+ req.n.nlmsg_flags |= NLM_F_DUMP;
+ }
+
+ f.cmd = cmd;
+ if (cmd & CMD_FLUSH) {
+ int round = 0;
+ char flushb[4096-512];
+
+ f.flushb = flushb;
+ f.flushp = 0;
+ f.flushe = sizeof(flushb);
+
+ for (;;) {
+ req.n.nlmsg_seq = grth.dump = ++grth.seq;
+ if (rtnl_send(&grth, &req, req.n.nlmsg_len) < 0) {
+ perror("Failed to send flush request");
+ exit(1);
+ }
+ f.flushed = 0;
+ if (rtnl_dump_filter(&grth, process_msg, stdout) < 0) {
+ fprintf(stderr, "Flush terminated\n");
+ exit(1);
+ }
+ if (f.flushed == 0) {
+ if (round == 0) {
+ fprintf(stderr, "Nothing to flush.\n");
+ } else if (show_stats)
+ printf("*** Flush is complete after %d round%s ***\n",
+ round, round > 1 ? "s" : "");
+ fflush(stdout);
+ return 0;
+ }
+ round++;
+ if (flush_update() < 0)
+ exit(1);
+ if (show_stats) {
+ printf("\n*** Round %d, deleting %d entries ***\n",
+ round, f.flushed);
+ fflush(stdout);
+ }
+ }
+ return 0;
+ }
+
+ if (ack) {
+ if (rtnl_talk(&grth, &req.n, NULL, 0) < 0)
+ return -2;
+ } else if (atype >= 0) {
+ if (rtnl_talk(&grth, &req.n, &req.n, sizeof(req)) < 0)
+ return -2;
+ if (process_msg(NULL, &req.n, stdout) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ exit(1);
+ }
+ } else {
+ req.n.nlmsg_seq = grth.dump = ++grth.seq;
+ if (rtnl_send(&grth, &req, req.n.nlmsg_len) < 0) {
+ perror("Failed to send dump request");
+ exit(1);
+ }
+
+ if (rtnl_dump_filter(&grth, process_msg, stdout) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ exit(1);
+ }
+ }
+ return 0;
+}
+
+int do_tcp_metrics(int argc, char **argv)
+{
+ int i;
+
+ if (argc < 1)
+ return tcpm_do_cmd(CMD_LIST, 0, NULL);
+ for (i = 0; i < ARRAY_SIZE(cmds); i++) {
+ if (matches(argv[0], cmds[i].name) == 0)
+ return tcpm_do_cmd(cmds[i].code, argc-1, argv+1);
+ }
+ if (matches(argv[0], "help") == 0)
+ usage();
+
+ fprintf(stderr, "Command \"%s\" is unknown, "
+ "try \"ip tcp_metrics help\".\n", *argv);
+ exit(-1);
+}
diff --git a/iproute2/ip/tunnel.c b/iproute2/ip/tunnel.c
new file mode 100644
index 0000000..39f825b
--- /dev/null
+++ b/iproute2/ip/tunnel.c
@@ -0,0 +1,225 @@
+/*
+ * Copyright (C)2006 USAGI/WIDE Project
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses>.
+ */
+/*
+ * split from ip_tunnel.c
+ */
+/*
+ * Author:
+ * Masahide NAKAMURA @USAGI
+ */
+
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <netinet/in.h>
+#include <linux/if.h>
+#include <linux/ip.h>
+#include <linux/if_tunnel.h>
+
+#include "utils.h"
+#include "tunnel.h"
+
+const char *tnl_strproto(__u8 proto)
+{
+ static char buf[16];
+
+ switch (proto) {
+ case IPPROTO_IPIP:
+ strcpy(buf, "ip");
+ break;
+ case IPPROTO_GRE:
+ strcpy(buf, "gre");
+ break;
+ case IPPROTO_IPV6:
+ strcpy(buf, "ipv6");
+ break;
+ case IPPROTO_ESP:
+ strcpy(buf, "esp");
+ break;
+ case 0:
+ strcpy(buf, "any");
+ break;
+ default:
+ strcpy(buf, "unknown");
+ break;
+ }
+
+ return buf;
+}
+
+int tnl_get_ioctl(const char *basedev, void *p)
+{
+ struct ifreq ifr;
+ int fd;
+ int err;
+
+ strncpy(ifr.ifr_name, basedev, IFNAMSIZ);
+ ifr.ifr_ifru.ifru_data = (void*)p;
+
+ fd = socket(preferred_family, SOCK_DGRAM, 0);
+ if (fd < 0) {
+ fprintf(stderr, "create socket failed: %s\n", strerror(errno));
+ return -1;
+ }
+
+ err = ioctl(fd, SIOCGETTUNNEL, &ifr);
+ if (err)
+ fprintf(stderr, "get tunnel \"%s\" failed: %s\n", basedev,
+ strerror(errno));
+
+ close(fd);
+ return err;
+}
+
+int tnl_add_ioctl(int cmd, const char *basedev, const char *name, void *p)
+{
+ struct ifreq ifr;
+ int fd;
+ int err;
+
+ if (cmd == SIOCCHGTUNNEL && name[0])
+ strncpy(ifr.ifr_name, name, IFNAMSIZ);
+ else
+ strncpy(ifr.ifr_name, basedev, IFNAMSIZ);
+ ifr.ifr_ifru.ifru_data = p;
+
+ fd = socket(preferred_family, SOCK_DGRAM, 0);
+ if (fd < 0) {
+ fprintf(stderr, "create socket failed: %s\n", strerror(errno));
+ return -1;
+ }
+
+ err = ioctl(fd, cmd, &ifr);
+ if (err)
+ fprintf(stderr, "add tunnel \"%s\" failed: %s\n", ifr.ifr_name,
+ strerror(errno));
+ close(fd);
+ return err;
+}
+
+int tnl_del_ioctl(const char *basedev, const char *name, void *p)
+{
+ struct ifreq ifr;
+ int fd;
+ int err;
+
+ if (name[0])
+ strncpy(ifr.ifr_name, name, IFNAMSIZ);
+ else
+ strncpy(ifr.ifr_name, basedev, IFNAMSIZ);
+
+ ifr.ifr_ifru.ifru_data = p;
+
+ fd = socket(preferred_family, SOCK_DGRAM, 0);
+ if (fd < 0) {
+ fprintf(stderr, "create socket failed: %s\n", strerror(errno));
+ return -1;
+ }
+
+ err = ioctl(fd, SIOCDELTUNNEL, &ifr);
+ if (err)
+ fprintf(stderr, "delete tunnel \"%s\" failed: %s\n",
+ ifr.ifr_name, strerror(errno));
+ close(fd);
+ return err;
+}
+
+static int tnl_gen_ioctl(int cmd, const char *name,
+ void *p, int skiperr)
+{
+ struct ifreq ifr;
+ int fd;
+ int err;
+
+ strncpy(ifr.ifr_name, name, IFNAMSIZ);
+ ifr.ifr_ifru.ifru_data = p;
+
+ fd = socket(preferred_family, SOCK_DGRAM, 0);
+ if (fd < 0) {
+ fprintf(stderr, "create socket failed: %s\n", strerror(errno));
+ return -1;
+ }
+
+ err = ioctl(fd, cmd, &ifr);
+ if (err && errno != skiperr)
+ fprintf(stderr, "%s: ioctl %x failed: %s\n", name,
+ cmd, strerror(errno));
+ close(fd);
+ return err;
+}
+
+int tnl_prl_ioctl(int cmd, const char *name, void *p)
+{
+ return tnl_gen_ioctl(cmd, name, p, -1);
+}
+
+int tnl_6rd_ioctl(int cmd, const char *name, void *p)
+{
+ return tnl_gen_ioctl(cmd, name, p, -1);
+}
+
+int tnl_ioctl_get_6rd(const char *name, void *p)
+{
+ return tnl_gen_ioctl(SIOCGET6RD, name, p, EINVAL);
+}
+
+__be32 tnl_parse_key(const char *name, const char *key)
+{
+ unsigned uval;
+
+ if (strchr(key, '.'))
+ return get_addr32(key);
+
+ if (get_unsigned(&uval, key, 0) < 0) {
+ fprintf(stderr, "invalid value for \"%s\": \"%s\";", name, key);
+ fprintf(stderr, " it should be an unsigned integer\n");
+ exit(-1);
+ }
+ return htonl(uval);
+}
+
+/* tnl_print_stats - print tunnel statistics
+ *
+ * @buf - tunnel interface's line in /proc/net/dev,
+ * starting past the interface name and following colon
+ */
+void tnl_print_stats(const char *buf)
+{
+ unsigned long rx_bytes, rx_packets, rx_errs, rx_drops,
+ rx_fifo, rx_frame,
+ tx_bytes, tx_packets, tx_errs, tx_drops,
+ tx_fifo, tx_colls, tx_carrier, rx_multi;
+
+ if (sscanf(buf, "%lu%lu%lu%lu%lu%lu%lu%*d%lu%lu%lu%lu%lu%lu%lu",
+ &rx_bytes, &rx_packets, &rx_errs, &rx_drops,
+ &rx_fifo, &rx_frame, &rx_multi,
+ &tx_bytes, &tx_packets, &tx_errs, &tx_drops,
+ &tx_fifo, &tx_colls, &tx_carrier) != 14)
+ return;
+
+ printf("%s", _SL_);
+ printf("RX: Packets Bytes Errors CsumErrs OutOfSeq Mcasts%s", _SL_);
+ printf(" %-10ld %-12ld %-6ld %-8ld %-8ld %-8ld%s",
+ rx_packets, rx_bytes, rx_errs, rx_frame, rx_fifo, rx_multi, _SL_);
+ printf("TX: Packets Bytes Errors DeadLoop NoRoute NoBufs%s", _SL_);
+ printf(" %-10ld %-12ld %-6ld %-8ld %-8ld %-6ld",
+ tx_packets, tx_bytes, tx_errs, tx_colls, tx_carrier, tx_drops);
+}
diff --git a/iproute2/ip/tunnel.h b/iproute2/ip/tunnel.h
new file mode 100644
index 0000000..9a03c0d
--- /dev/null
+++ b/iproute2/ip/tunnel.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright (C)2006 USAGI/WIDE Project
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses>.
+ */
+/*
+ * Author:
+ * Masahide NAKAMURA @USAGI
+ */
+#ifndef __TUNNEL_H__
+#define __TUNNEL_H__ 1
+
+#include <linux/types.h>
+
+const char *tnl_strproto(__u8 proto);
+
+int tnl_get_ioctl(const char *basedev, void *p);
+int tnl_add_ioctl(int cmd, const char *basedev, const char *name, void *p);
+int tnl_del_ioctl(const char *basedev, const char *name, void *p);
+int tnl_prl_ioctl(int cmd, const char *name, void *p);
+int tnl_6rd_ioctl(int cmd, const char *name, void *p);
+int tnl_ioctl_get_6rd(const char *name, void *p);
+__be32 tnl_parse_key(const char *name, const char *key);
+void tnl_print_stats(const char *buf);
+
+#endif
diff --git a/iproute2/ip/xfrm.h b/iproute2/ip/xfrm.h
new file mode 100644
index 0000000..773c92e
--- /dev/null
+++ b/iproute2/ip/xfrm.h
@@ -0,0 +1,158 @@
+/* $USAGI: $ */
+
+/*
+ * Copyright (C)2004 USAGI/WIDE Project
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses>.
+ */
+/*
+ * Authors:
+ * Masahide NAKAMURA @USAGI
+ */
+
+#ifndef __XFRM_H__
+#define __XFRM_H__ 1
+
+#include <stdio.h>
+#include <sys/socket.h>
+#include <linux/xfrm.h>
+
+#ifndef IPPROTO_SCTP
+# define IPPROTO_SCTP 132
+#endif
+#ifndef IPPROTO_DCCP
+# define IPPROTO_DCCP 33
+#endif
+#ifndef IPPROTO_MH
+# define IPPROTO_MH 135
+#endif
+
+#define XFRMS_RTA(x) ((struct rtattr*)(((char*)(x)) + NLMSG_ALIGN(sizeof(struct xfrm_usersa_info))))
+#define XFRMS_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct xfrm_usersa_info))
+
+#define XFRMP_RTA(x) ((struct rtattr*)(((char*)(x)) + NLMSG_ALIGN(sizeof(struct xfrm_userpolicy_info))))
+#define XFRMP_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct xfrm_userpoilcy_info))
+
+#define XFRMSID_RTA(x) ((struct rtattr*)(((char*)(x)) + NLMSG_ALIGN(sizeof(struct xfrm_usersa_id))))
+#define XFRMSID_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct xfrm_usersa_id))
+
+#define XFRMPID_RTA(x) ((struct rtattr*)(((char*)(x)) + NLMSG_ALIGN(sizeof(struct xfrm_userpolicy_id))))
+#define XFRMPID_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct xfrm_userpoilcy_id))
+
+#define XFRMACQ_RTA(x) ((struct rtattr*)(((char*)(x)) + NLMSG_ALIGN(sizeof(struct xfrm_user_acquire))))
+#define XFRMEXP_RTA(x) ((struct rtattr*)(((char*)(x)) + NLMSG_ALIGN(sizeof(struct xfrm_user_expire))))
+#define XFRMPEXP_RTA(x) ((struct rtattr*)(((char*)(x)) + NLMSG_ALIGN(sizeof(struct xfrm_user_polexpire))))
+
+#define XFRMREP_RTA(x) ((struct rtattr*)(((char*)(x)) + NLMSG_ALIGN(sizeof(struct xfrm_user_report))))
+
+#define XFRMSAPD_RTA(x) ((struct rtattr*)(((char*)(x)) + NLMSG_ALIGN(sizeof(__u32))))
+#define XFRM_FLAG_PRINT(fp, flags, f, s) \
+ do { \
+ if (flags & f) { \
+ flags &= ~f; \
+ fprintf(fp, s "%s", (flags ? " " : "")); \
+ } \
+ } while(0)
+
+struct xfrm_buffer {
+ char *buf;
+ int size;
+ int offset;
+
+ int nlmsg_count;
+ struct rtnl_handle *rth;
+};
+
+struct xfrm_filter {
+ int use;
+
+ struct xfrm_usersa_info xsinfo;
+ __u8 id_src_mask;
+ __u8 id_dst_mask;
+ __u8 id_proto_mask;
+ __u32 id_spi_mask;
+ __u8 mode_mask;
+ __u32 reqid_mask;
+ __u8 state_flags_mask;
+
+ struct xfrm_userpolicy_info xpinfo;
+ __u8 dir_mask;
+ __u8 sel_src_mask;
+ __u8 sel_dst_mask;
+ __u32 sel_dev_mask;
+ __u8 upspec_proto_mask;
+ __u16 upspec_sport_mask;
+ __u16 upspec_dport_mask;
+ __u32 index_mask;
+ __u8 action_mask;
+ __u32 priority_mask;
+ __u8 policy_flags_mask;
+
+ __u8 ptype;
+ __u8 ptype_mask;
+
+};
+#define XFRM_FILTER_MASK_FULL (~0)
+
+extern struct xfrm_filter filter;
+
+int xfrm_state_print(const struct sockaddr_nl *who, struct nlmsghdr *n,
+ void *arg);
+int xfrm_policy_print(const struct sockaddr_nl *who, struct nlmsghdr *n,
+ void *arg);
+int do_xfrm_state(int argc, char **argv);
+int do_xfrm_policy(int argc, char **argv);
+int do_xfrm_monitor(int argc, char **argv);
+
+int xfrm_addr_match(xfrm_address_t *x1, xfrm_address_t *x2, int bits);
+int xfrm_xfrmproto_is_ipsec(__u8 proto);
+int xfrm_xfrmproto_is_ro(__u8 proto);
+int xfrm_xfrmproto_getbyname(char *name);
+int xfrm_algotype_getbyname(char *name);
+int xfrm_parse_mark(struct xfrm_mark *mark, int *argcp, char ***argvp);
+const char *strxf_xfrmproto(__u8 proto);
+const char *strxf_algotype(int type);
+const char *strxf_mask8(__u8 mask);
+const char *strxf_mask32(__u32 mask);
+const char *strxf_share(__u8 share);
+const char *strxf_proto(__u8 proto);
+const char *strxf_ptype(__u8 ptype);
+void xfrm_id_info_print(xfrm_address_t *saddr, struct xfrm_id *id,
+ __u8 mode, __u32 reqid, __u16 family, int force_spi,
+ FILE *fp, const char *prefix, const char *title);
+void xfrm_stats_print(struct xfrm_stats *s, FILE *fp, const char *prefix);
+void xfrm_lifetime_print(struct xfrm_lifetime_cfg *cfg,
+ struct xfrm_lifetime_cur *cur,
+ FILE *fp, const char *prefix);
+void xfrm_selector_print(struct xfrm_selector *sel, __u16 family,
+ FILE *fp, const char *prefix);
+void xfrm_xfrma_print(struct rtattr *tb[], __u16 family,
+ FILE *fp, const char *prefix);
+void xfrm_state_info_print(struct xfrm_usersa_info *xsinfo,
+ struct rtattr *tb[], FILE *fp, const char *prefix,
+ const char *title);
+void xfrm_policy_info_print(struct xfrm_userpolicy_info *xpinfo,
+ struct rtattr *tb[], FILE *fp, const char *prefix,
+ const char *title);
+int xfrm_id_parse(xfrm_address_t *saddr, struct xfrm_id *id, __u16 *family,
+ int loose, int *argcp, char ***argvp);
+int xfrm_mode_parse(__u8 *mode, int *argcp, char ***argvp);
+int xfrm_encap_type_parse(__u16 *type, int *argcp, char ***argvp);
+int xfrm_reqid_parse(__u32 *reqid, int *argcp, char ***argvp);
+int xfrm_selector_parse(struct xfrm_selector *sel, int *argcp, char ***argvp);
+int xfrm_lifetime_cfg_parse(struct xfrm_lifetime_cfg *lft,
+ int *argcp, char ***argvp);
+int xfrm_sctx_parse(char *ctxstr, char *context,
+ struct xfrm_user_sec_ctx *sctx);
+#endif
diff --git a/iproute2/ip/xfrm_monitor.c b/iproute2/ip/xfrm_monitor.c
new file mode 100644
index 0000000..e6e991a
--- /dev/null
+++ b/iproute2/ip/xfrm_monitor.c
@@ -0,0 +1,435 @@
+/* $USAGI: $ */
+
+/*
+ * Copyright (C)2005 USAGI/WIDE Project
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses>.
+ */
+/*
+ * based on ipmonitor.c
+ */
+/*
+ * Authors:
+ * Masahide NAKAMURA @USAGI
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <netinet/in.h>
+
+#include "utils.h"
+#include "xfrm.h"
+#include "ip_common.h"
+
+static void usage(void) __attribute__((noreturn));
+int listen_all_nsid;
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: ip xfrm monitor [all-nsid] [ all | OBJECTS | help ]\n");
+ fprintf(stderr, "OBJECTS := { acquire | expire | SA | aevent | policy | report }\n");
+ exit(-1);
+}
+
+static int xfrm_acquire_print(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ struct xfrm_user_acquire *xacq = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr * tb[XFRMA_MAX+1];
+ __u16 family;
+
+ len -= NLMSG_LENGTH(sizeof(*xacq));
+ if (len < 0) {
+ fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+ return -1;
+ }
+
+ parse_rtattr(tb, XFRMA_MAX, XFRMACQ_RTA(xacq), len);
+
+ family = xacq->sel.family;
+ if (family == AF_UNSPEC)
+ family = xacq->policy.sel.family;
+ if (family == AF_UNSPEC)
+ family = preferred_family;
+
+ fprintf(fp, "acquire ");
+
+ fprintf(fp, "proto %s ", strxf_xfrmproto(xacq->id.proto));
+ if (show_stats > 0 || xacq->id.spi) {
+ __u32 spi = ntohl(xacq->id.spi);
+ fprintf(fp, "spi 0x%08x", spi);
+ if (show_stats > 0)
+ fprintf(fp, "(%u)", spi);
+ fprintf(fp, " ");
+ }
+ fprintf(fp, "%s", _SL_);
+
+ xfrm_selector_print(&xacq->sel, family, fp, " sel ");
+
+ xfrm_policy_info_print(&xacq->policy, tb, fp, " ", " policy ");
+
+ if (show_stats > 0)
+ fprintf(fp, " seq 0x%08u ", xacq->seq);
+ if (show_stats > 0) {
+ fprintf(fp, "%s-mask %s ",
+ strxf_algotype(XFRMA_ALG_CRYPT),
+ strxf_mask32(xacq->ealgos));
+ fprintf(fp, "%s-mask %s ",
+ strxf_algotype(XFRMA_ALG_AUTH),
+ strxf_mask32(xacq->aalgos));
+ fprintf(fp, "%s-mask %s",
+ strxf_algotype(XFRMA_ALG_COMP),
+ strxf_mask32(xacq->calgos));
+ }
+ fprintf(fp, "%s", _SL_);
+
+ if (oneline)
+ fprintf(fp, "\n");
+ fflush(fp);
+
+ return 0;
+}
+
+static int xfrm_state_flush_print(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ struct xfrm_usersa_flush *xsf = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ const char *str;
+
+ len -= NLMSG_SPACE(sizeof(*xsf));
+ if (len < 0) {
+ fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+ return -1;
+ }
+
+ fprintf(fp, "Flushed state ");
+
+ str = strxf_xfrmproto(xsf->proto);
+ if (str)
+ fprintf(fp, "proto %s", str);
+ else
+ fprintf(fp, "proto %u", xsf->proto);
+ fprintf(fp, "%s", _SL_);
+
+ if (oneline)
+ fprintf(fp, "\n");
+ fflush(fp);
+
+ return 0;
+}
+
+static int xfrm_policy_flush_print(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg)
+{
+ struct rtattr * tb[XFRMA_MAX+1];
+ FILE *fp = (FILE*)arg;
+ int len = n->nlmsg_len;
+
+ len -= NLMSG_SPACE(0);
+ if (len < 0) {
+ fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+ return -1;
+ }
+
+ fprintf(fp, "Flushed policy ");
+
+ parse_rtattr(tb, XFRMA_MAX, NLMSG_DATA(n), len);
+
+ if (tb[XFRMA_POLICY_TYPE]) {
+ struct xfrm_userpolicy_type *upt;
+
+ fprintf(fp, "ptype ");
+
+ if (RTA_PAYLOAD(tb[XFRMA_POLICY_TYPE]) < sizeof(*upt))
+ fprintf(fp, "(ERROR truncated)");
+
+ upt = (struct xfrm_userpolicy_type *)RTA_DATA(tb[XFRMA_POLICY_TYPE]);
+ fprintf(fp, "%s ", strxf_ptype(upt->type));
+ }
+
+ fprintf(fp, "%s", _SL_);
+
+ if (oneline)
+ fprintf(fp, "\n");
+ fflush(fp);
+
+ return 0;
+}
+
+static int xfrm_report_print(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ struct xfrm_user_report *xrep = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr * tb[XFRMA_MAX+1];
+ __u16 family;
+
+ len -= NLMSG_LENGTH(sizeof(*xrep));
+ if (len < 0) {
+ fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+ return -1;
+ }
+
+ family = xrep->sel.family;
+ if (family == AF_UNSPEC)
+ family = preferred_family;
+
+ fprintf(fp, "report ");
+
+ fprintf(fp, "proto %s ", strxf_xfrmproto(xrep->proto));
+ fprintf(fp, "%s", _SL_);
+
+ xfrm_selector_print(&xrep->sel, family, fp, " sel ");
+
+ parse_rtattr(tb, XFRMA_MAX, XFRMREP_RTA(xrep), len);
+
+ xfrm_xfrma_print(tb, family, fp, " ");
+
+ if (oneline)
+ fprintf(fp, "\n");
+
+ return 0;
+}
+
+static void xfrm_ae_flags_print(__u32 flags, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ fprintf(fp, " (0x%x) ", flags);
+ if (!flags)
+ return;
+ if (flags & XFRM_AE_CR)
+ fprintf(fp, " replay update ");
+ if (flags & XFRM_AE_CE)
+ fprintf(fp, " timer expired ");
+ if (flags & XFRM_AE_CU)
+ fprintf(fp, " policy updated ");
+
+}
+
+static void xfrm_usersa_print(const struct xfrm_usersa_id *sa_id, __u32 reqid, FILE *fp)
+{
+ char buf[256];
+
+ buf[0] = 0;
+ fprintf(fp, "dst %s ",
+ rt_addr_n2a(sa_id->family, sizeof(sa_id->daddr), &sa_id->daddr,
+ buf, sizeof(buf)));
+
+ fprintf(fp, " reqid 0x%x", reqid);
+
+ fprintf(fp, " protocol %s ", strxf_proto(sa_id->proto));
+ fprintf(fp, " SPI 0x%x", ntohl(sa_id->spi));
+}
+
+static int xfrm_ae_print(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ struct xfrm_aevent_id *id = NLMSG_DATA(n);
+ char abuf[256];
+
+ fprintf(fp, "Async event ");
+ xfrm_ae_flags_print(id->flags, arg);
+ fprintf(fp,"\n\t");
+ memset(abuf, '\0', sizeof(abuf));
+ fprintf(fp, "src %s ", rt_addr_n2a(id->sa_id.family,
+ sizeof(id->saddr), &id->saddr,
+ abuf, sizeof(abuf)));
+
+ xfrm_usersa_print(&id->sa_id, id->reqid, fp);
+
+ fprintf(fp, "\n");
+ fflush(fp);
+
+ return 0;
+}
+
+static void xfrm_print_addr(FILE *fp, int family, xfrm_address_t *a)
+{
+ char buf[256];
+
+ buf[0] = 0;
+ fprintf(fp, "%s", rt_addr_n2a(family, sizeof(*a), a, buf, sizeof(buf)));
+}
+
+static int xfrm_mapping_print(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ struct xfrm_user_mapping *map = NLMSG_DATA(n);
+
+ fprintf(fp, "Mapping change ");
+ xfrm_print_addr(fp, map->id.family, &map->old_saddr);
+
+ fprintf(fp, ":%d -> ", ntohs(map->old_sport));
+ xfrm_print_addr(fp, map->id.family, &map->new_saddr);
+ fprintf(fp, ":%d\n\t", ntohs(map->new_sport));
+
+ xfrm_usersa_print(&map->id, map->reqid, fp);
+
+ fprintf(fp, "\n");
+ fflush(fp);
+ return 0;
+}
+
+static int xfrm_accept_msg(const struct sockaddr_nl *who,
+ struct rtnl_ctrl_data *ctrl,
+ struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+
+ if (timestamp)
+ print_timestamp(fp);
+
+ if (listen_all_nsid) {
+ if (ctrl == NULL || ctrl->nsid < 0)
+ fprintf(fp, "[nsid current]");
+ else
+ fprintf(fp, "[nsid %d]", ctrl->nsid);
+ }
+
+ switch (n->nlmsg_type) {
+ case XFRM_MSG_NEWSA:
+ case XFRM_MSG_DELSA:
+ case XFRM_MSG_UPDSA:
+ case XFRM_MSG_EXPIRE:
+ xfrm_state_print(who, n, arg);
+ return 0;
+ case XFRM_MSG_NEWPOLICY:
+ case XFRM_MSG_DELPOLICY:
+ case XFRM_MSG_UPDPOLICY:
+ case XFRM_MSG_POLEXPIRE:
+ xfrm_policy_print(who, n, arg);
+ return 0;
+ case XFRM_MSG_ACQUIRE:
+ xfrm_acquire_print(who, n, arg);
+ return 0;
+ case XFRM_MSG_FLUSHSA:
+ xfrm_state_flush_print(who, n, arg);
+ return 0;
+ case XFRM_MSG_FLUSHPOLICY:
+ xfrm_policy_flush_print(who, n, arg);
+ return 0;
+ case XFRM_MSG_REPORT:
+ xfrm_report_print(who, n, arg);
+ return 0;
+ case XFRM_MSG_NEWAE:
+ xfrm_ae_print(who, n, arg);
+ return 0;
+ case XFRM_MSG_MAPPING:
+ xfrm_mapping_print(who, n, arg);
+ return 0;
+ default:
+ break;
+ }
+
+ if (n->nlmsg_type != NLMSG_ERROR && n->nlmsg_type != NLMSG_NOOP &&
+ n->nlmsg_type != NLMSG_DONE) {
+ fprintf(fp, "Unknown message: %08d 0x%08x 0x%08x\n",
+ n->nlmsg_len, n->nlmsg_type, n->nlmsg_flags);
+ }
+ return 0;
+}
+
+extern struct rtnl_handle rth;
+
+int do_xfrm_monitor(int argc, char **argv)
+{
+ char *file = NULL;
+ unsigned groups = ~((unsigned)0); /* XXX */
+ int lacquire=0;
+ int lexpire=0;
+ int laevent=0;
+ int lpolicy=0;
+ int lsa=0;
+ int lreport=0;
+
+ rtnl_close(&rth);
+
+ while (argc > 0) {
+ if (matches(*argv, "file") == 0) {
+ NEXT_ARG();
+ file = *argv;
+ } else if (matches(*argv, "all-nsid") == 0) {
+ listen_all_nsid = 1;
+ } else if (matches(*argv, "acquire") == 0) {
+ lacquire=1;
+ groups = 0;
+ } else if (matches(*argv, "expire") == 0) {
+ lexpire=1;
+ groups = 0;
+ } else if (matches(*argv, "SA") == 0) {
+ lsa=1;
+ groups = 0;
+ } else if (matches(*argv, "aevent") == 0) {
+ laevent=1;
+ groups = 0;
+ } else if (matches(*argv, "policy") == 0) {
+ lpolicy=1;
+ groups = 0;
+ } else if (matches(*argv, "report") == 0) {
+ lreport=1;
+ groups = 0;
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ } else if (strcmp(*argv, "all")) {
+ fprintf(stderr, "Argument \"%s\" is unknown, try \"ip xfrm monitor help\".\n", *argv);
+ exit(-1);
+ }
+ argc--; argv++;
+ }
+
+ if (lacquire)
+ groups |= nl_mgrp(XFRMNLGRP_ACQUIRE);
+ if (lexpire)
+ groups |= nl_mgrp(XFRMNLGRP_EXPIRE);
+ if (lsa)
+ groups |= nl_mgrp(XFRMNLGRP_SA);
+ if (lpolicy)
+ groups |= nl_mgrp(XFRMNLGRP_POLICY);
+ if (laevent)
+ groups |= nl_mgrp(XFRMNLGRP_AEVENTS);
+ if (lreport)
+ groups |= nl_mgrp(XFRMNLGRP_REPORT);
+
+ if (file) {
+ FILE *fp;
+ int err;
+
+ fp = fopen(file, "r");
+ if (fp == NULL) {
+ perror("Cannot fopen");
+ exit(-1);
+ }
+ err = rtnl_from_file(fp, xfrm_accept_msg, stdout);
+ fclose(fp);
+ return err;
+ }
+
+ if (rtnl_open_byproto(&rth, groups, NETLINK_XFRM) < 0)
+ exit(1);
+ if (listen_all_nsid && rtnl_listen_all_nsid(&rth) < 0)
+ exit(1);
+
+ if (rtnl_listen(&rth, xfrm_accept_msg, (void*)stdout) < 0)
+ exit(2);
+
+ return 0;
+}
diff --git a/iproute2/ip/xfrm_policy.c b/iproute2/ip/xfrm_policy.c
new file mode 100644
index 0000000..efea1e8
--- /dev/null
+++ b/iproute2/ip/xfrm_policy.c
@@ -0,0 +1,1183 @@
+/* $USAGI: $ */
+
+/*
+ * Copyright (C)2004 USAGI/WIDE Project
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses>.
+ */
+/*
+ * based on iproute.c
+ */
+/*
+ * Authors:
+ * Masahide NAKAMURA @USAGI
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <netdb.h>
+#include <linux/netlink.h>
+#include "utils.h"
+#include "xfrm.h"
+#include "ip_common.h"
+
+//#define NLMSG_DELETEALL_BUF_SIZE (4096-512)
+#define NLMSG_DELETEALL_BUF_SIZE 8192
+
+/*
+ * Receiving buffer defines:
+ * nlmsg
+ * data = struct xfrm_userpolicy_info
+ * rtattr
+ * data = struct xfrm_user_tmpl[]
+ */
+#define NLMSG_BUF_SIZE 4096
+#define RTA_BUF_SIZE 2048
+#define XFRM_TMPLS_BUF_SIZE 1024
+#define CTX_BUF_SIZE 256
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: ip xfrm policy { add | update } SELECTOR dir DIR [ ctx CTX ]\n");
+ fprintf(stderr, " [ mark MARK [ mask MASK ] ] [ index INDEX ] [ ptype PTYPE ]\n");
+ fprintf(stderr, " [ action ACTION ] [ priority PRIORITY ] [ flag FLAG-LIST ]\n");
+ fprintf(stderr, " [ LIMIT-LIST ] [ TMPL-LIST ]\n");
+ fprintf(stderr, "Usage: ip xfrm policy { delete | get } { SELECTOR | index INDEX } dir DIR\n");
+ fprintf(stderr, " [ ctx CTX ] [ mark MARK [ mask MASK ] ] [ ptype PTYPE ]\n");
+ fprintf(stderr, "Usage: ip xfrm policy { deleteall | list } [ SELECTOR ] [ dir DIR ]\n");
+ fprintf(stderr, " [ index INDEX ] [ ptype PTYPE ] [ action ACTION ] [ priority PRIORITY ]\n");
+ fprintf(stderr, " [ flag FLAG-LIST ]\n");
+ fprintf(stderr, "Usage: ip xfrm policy flush [ ptype PTYPE ]\n");
+ fprintf(stderr, "Usage: ip xfrm policy count\n");
+ fprintf(stderr, "Usage: ip xfrm policy set [ hthresh4 LBITS RBITS ] [ hthresh6 LBITS RBITS ]\n");
+ fprintf(stderr, "SELECTOR := [ src ADDR[/PLEN] ] [ dst ADDR[/PLEN] ] [ dev DEV ] [ UPSPEC ]\n");
+ fprintf(stderr, "UPSPEC := proto { { ");
+ fprintf(stderr, "%s | ", strxf_proto(IPPROTO_TCP));
+ fprintf(stderr, "%s | ", strxf_proto(IPPROTO_UDP));
+ fprintf(stderr, "%s | ", strxf_proto(IPPROTO_SCTP));
+ fprintf(stderr, "%s", strxf_proto(IPPROTO_DCCP));
+ fprintf(stderr, " } [ sport PORT ] [ dport PORT ] |\n");
+ fprintf(stderr, " { ");
+ fprintf(stderr, "%s | ", strxf_proto(IPPROTO_ICMP));
+ fprintf(stderr, "%s | ", strxf_proto(IPPROTO_ICMPV6));
+ fprintf(stderr, "%s", strxf_proto(IPPROTO_MH));
+ fprintf(stderr, " } [ type NUMBER ] [ code NUMBER ] |\n");
+ fprintf(stderr, " %s", strxf_proto(IPPROTO_GRE));
+ fprintf(stderr, " [ key { DOTTED-QUAD | NUMBER } ] | PROTO }\n");
+ fprintf(stderr, "DIR := in | out | fwd\n");
+ fprintf(stderr, "PTYPE := main | sub\n");
+ fprintf(stderr, "ACTION := allow | block\n");
+ fprintf(stderr, "FLAG-LIST := [ FLAG-LIST ] FLAG\n");
+ fprintf(stderr, "FLAG := localok | icmp\n");
+ fprintf(stderr, "LIMIT-LIST := [ LIMIT-LIST ] limit LIMIT\n");
+ fprintf(stderr, "LIMIT := { time-soft | time-hard | time-use-soft | time-use-hard } SECONDS |\n");
+ fprintf(stderr, " { byte-soft | byte-hard } SIZE | { packet-soft | packet-hard } COUNT\n");
+ fprintf(stderr, "TMPL-LIST := [ TMPL-LIST ] tmpl TMPL\n");
+ fprintf(stderr, "TMPL := ID [ mode MODE ] [ reqid REQID ] [ level LEVEL ]\n");
+ fprintf(stderr, "ID := [ src ADDR ] [ dst ADDR ] [ proto XFRM-PROTO ] [ spi SPI ]\n");
+ fprintf(stderr, "XFRM-PROTO := ");
+ fprintf(stderr, "%s | ", strxf_xfrmproto(IPPROTO_ESP));
+ fprintf(stderr, "%s | ", strxf_xfrmproto(IPPROTO_AH));
+ fprintf(stderr, "%s | ", strxf_xfrmproto(IPPROTO_COMP));
+ fprintf(stderr, "%s | ", strxf_xfrmproto(IPPROTO_ROUTING));
+ fprintf(stderr, "%s\n", strxf_xfrmproto(IPPROTO_DSTOPTS));
+ fprintf(stderr, "MODE := transport | tunnel | beet | ro | in_trigger\n");
+ fprintf(stderr, "LEVEL := required | use\n");
+
+ exit(-1);
+}
+
+static int xfrm_policy_dir_parse(__u8 *dir, int *argcp, char ***argvp)
+{
+ int argc = *argcp;
+ char **argv = *argvp;
+
+ if (strcmp(*argv, "in") == 0)
+ *dir = XFRM_POLICY_IN;
+ else if (strcmp(*argv, "out") == 0)
+ *dir = XFRM_POLICY_OUT;
+ else if (strcmp(*argv, "fwd") == 0)
+ *dir = XFRM_POLICY_FWD;
+ else
+ invarg("DIR value is invalid", *argv);
+
+ *argcp = argc;
+ *argvp = argv;
+
+ return 0;
+}
+
+static int xfrm_policy_ptype_parse(__u8 *ptype, int *argcp, char ***argvp)
+{
+ int argc = *argcp;
+ char **argv = *argvp;
+
+ if (strcmp(*argv, "main") == 0)
+ *ptype = XFRM_POLICY_TYPE_MAIN;
+ else if (strcmp(*argv, "sub") == 0)
+ *ptype = XFRM_POLICY_TYPE_SUB;
+ else
+ invarg("PTYPE value is invalid", *argv);
+
+ *argcp = argc;
+ *argvp = argv;
+
+ return 0;
+}
+
+static int xfrm_policy_flag_parse(__u8 *flags, int *argcp, char ***argvp)
+{
+ int argc = *argcp;
+ char **argv = *argvp;
+ int len = strlen(*argv);
+
+ if (len > 2 && strncmp(*argv, "0x", 2) == 0) {
+ __u8 val = 0;
+
+ if (get_u8(&val, *argv, 16))
+ invarg("FLAG value is invalid", *argv);
+ *flags = val;
+ } else {
+ while (1) {
+ if (strcmp(*argv, "localok") == 0)
+ *flags |= XFRM_POLICY_LOCALOK;
+ else if (strcmp(*argv, "icmp") == 0)
+ *flags |= XFRM_POLICY_ICMP;
+ else {
+ PREV_ARG(); /* back track */
+ break;
+ }
+
+ if (!NEXT_ARG_OK())
+ break;
+ NEXT_ARG();
+ }
+ }
+
+ *argcp = argc;
+ *argvp = argv;
+
+ return 0;
+}
+
+static int xfrm_tmpl_parse(struct xfrm_user_tmpl *tmpl,
+ int *argcp, char ***argvp)
+{
+ int argc = *argcp;
+ char **argv = *argvp;
+ char *idp = NULL;
+
+ while (1) {
+ if (strcmp(*argv, "mode") == 0) {
+ NEXT_ARG();
+ xfrm_mode_parse(&tmpl->mode, &argc, &argv);
+ } else if (strcmp(*argv, "reqid") == 0) {
+ NEXT_ARG();
+ xfrm_reqid_parse(&tmpl->reqid, &argc, &argv);
+ } else if (strcmp(*argv, "level") == 0) {
+ NEXT_ARG();
+
+ if (strcmp(*argv, "required") == 0)
+ tmpl->optional = 0;
+ else if (strcmp(*argv, "use") == 0)
+ tmpl->optional = 1;
+ else
+ invarg("LEVEL value is invalid\n", *argv);
+
+ } else {
+ if (idp) {
+ PREV_ARG(); /* back track */
+ break;
+ }
+ idp = *argv;
+ preferred_family = AF_UNSPEC;
+ xfrm_id_parse(&tmpl->saddr, &tmpl->id, &tmpl->family,
+ 0, &argc, &argv);
+ preferred_family = tmpl->family;
+ }
+
+ if (!NEXT_ARG_OK())
+ break;
+
+ NEXT_ARG();
+ }
+ if (argc == *argcp)
+ missarg("TMPL");
+
+ *argcp = argc;
+ *argvp = argv;
+
+ return 0;
+}
+
+int xfrm_sctx_parse(char *ctxstr, char *s,
+ struct xfrm_user_sec_ctx *sctx)
+{
+ int slen;
+
+ slen = strlen(s) + 1;
+
+ sctx->exttype = XFRMA_SEC_CTX;
+ sctx->ctx_doi = 1;
+ sctx->ctx_alg = 1;
+ sctx->ctx_len = slen;
+ sctx->len = sizeof(struct xfrm_user_sec_ctx) + slen;
+ memcpy(ctxstr, s, slen);
+
+ return 0;
+}
+
+static int xfrm_policy_modify(int cmd, unsigned flags, int argc, char **argv)
+{
+ struct rtnl_handle rth;
+ struct {
+ struct nlmsghdr n;
+ struct xfrm_userpolicy_info xpinfo;
+ char buf[RTA_BUF_SIZE];
+ } req;
+ char *dirp = NULL;
+ char *selp = NULL;
+ char *ptypep = NULL;
+ char *sctxp = NULL;
+ struct xfrm_userpolicy_type upt;
+ char tmpls_buf[XFRM_TMPLS_BUF_SIZE];
+ int tmpls_len = 0;
+ struct xfrm_mark mark = {0, 0};
+ struct {
+ struct xfrm_user_sec_ctx sctx;
+ char str[CTX_BUF_SIZE];
+ } ctx;
+
+ memset(&req, 0, sizeof(req));
+ memset(&upt, 0, sizeof(upt));
+ memset(&tmpls_buf, 0, sizeof(tmpls_buf));
+ memset(&ctx, 0, sizeof(ctx));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(req.xpinfo));
+ req.n.nlmsg_flags = NLM_F_REQUEST|flags;
+ req.n.nlmsg_type = cmd;
+ req.xpinfo.sel.family = preferred_family;
+
+ req.xpinfo.lft.soft_byte_limit = XFRM_INF;
+ req.xpinfo.lft.hard_byte_limit = XFRM_INF;
+ req.xpinfo.lft.soft_packet_limit = XFRM_INF;
+ req.xpinfo.lft.hard_packet_limit = XFRM_INF;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dir") == 0) {
+ if (dirp)
+ duparg("dir", *argv);
+ dirp = *argv;
+
+ NEXT_ARG();
+ xfrm_policy_dir_parse(&req.xpinfo.dir, &argc, &argv);
+ } else if (strcmp(*argv, "ctx") == 0) {
+ char *context;
+
+ if (sctxp)
+ duparg("ctx", *argv);
+ sctxp = *argv;
+ NEXT_ARG();
+ context = *argv;
+ xfrm_sctx_parse((char *)&ctx.str, context, &ctx.sctx);
+ } else if (strcmp(*argv, "mark") == 0) {
+ xfrm_parse_mark(&mark, &argc, &argv);
+ } else if (strcmp(*argv, "index") == 0) {
+ NEXT_ARG();
+ if (get_u32(&req.xpinfo.index, *argv, 0))
+ invarg("INDEX value is invalid", *argv);
+ } else if (strcmp(*argv, "ptype") == 0) {
+ if (ptypep)
+ duparg("ptype", *argv);
+ ptypep = *argv;
+
+ NEXT_ARG();
+ xfrm_policy_ptype_parse(&upt.type, &argc, &argv);
+ } else if (strcmp(*argv, "action") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "allow") == 0)
+ req.xpinfo.action = XFRM_POLICY_ALLOW;
+ else if (strcmp(*argv, "block") == 0)
+ req.xpinfo.action = XFRM_POLICY_BLOCK;
+ else
+ invarg("ACTION value is invalid\n", *argv);
+ } else if (strcmp(*argv, "priority") == 0) {
+ NEXT_ARG();
+ if (get_u32(&req.xpinfo.priority, *argv, 0))
+ invarg("PRIORITY value is invalid", *argv);
+ } else if (strcmp(*argv, "flag") == 0) {
+ NEXT_ARG();
+ xfrm_policy_flag_parse(&req.xpinfo.flags, &argc,
+ &argv);
+ } else if (strcmp(*argv, "limit") == 0) {
+ NEXT_ARG();
+ xfrm_lifetime_cfg_parse(&req.xpinfo.lft, &argc, &argv);
+ } else if (strcmp(*argv, "tmpl") == 0) {
+ struct xfrm_user_tmpl *tmpl;
+
+ if (tmpls_len + sizeof(*tmpl) > sizeof(tmpls_buf)) {
+ fprintf(stderr, "Too many tmpls: buffer overflow\n");
+ exit(1);
+ }
+ tmpl = (struct xfrm_user_tmpl *)((char *)tmpls_buf + tmpls_len);
+
+ tmpl->family = preferred_family;
+ tmpl->aalgos = (~(__u32)0);
+ tmpl->ealgos = (~(__u32)0);
+ tmpl->calgos = (~(__u32)0);
+
+ NEXT_ARG();
+ xfrm_tmpl_parse(tmpl, &argc, &argv);
+
+ tmpls_len += sizeof(*tmpl);
+ } else {
+ if (selp)
+ duparg("unknown", *argv);
+ selp = *argv;
+
+ xfrm_selector_parse(&req.xpinfo.sel, &argc, &argv);
+ if (preferred_family == AF_UNSPEC)
+ preferred_family = req.xpinfo.sel.family;
+ }
+
+ argc--; argv++;
+ }
+
+ if (!dirp) {
+ fprintf(stderr, "Not enough information: DIR is required.\n");
+ exit(1);
+ }
+
+ if (ptypep) {
+ addattr_l(&req.n, sizeof(req), XFRMA_POLICY_TYPE,
+ (void *)&upt, sizeof(upt));
+ }
+
+ if (tmpls_len > 0) {
+ addattr_l(&req.n, sizeof(req), XFRMA_TMPL,
+ (void *)tmpls_buf, tmpls_len);
+ }
+
+ if (mark.m) {
+ int r = addattr_l(&req.n, sizeof(req.buf), XFRMA_MARK,
+ (void *)&mark, sizeof(mark));
+ if (r < 0) {
+ fprintf(stderr, "%s: XFRMA_MARK failed\n",__func__);
+ exit(1);
+ }
+ }
+
+ if (sctxp) {
+ addattr_l(&req.n, sizeof(req), XFRMA_SEC_CTX,
+ (void *)&ctx, ctx.sctx.len);
+ }
+
+ if (rtnl_open_byproto(&rth, 0, NETLINK_XFRM) < 0)
+ exit(1);
+
+ if (req.xpinfo.sel.family == AF_UNSPEC)
+ req.xpinfo.sel.family = AF_INET;
+
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ exit(2);
+
+ rtnl_close(&rth);
+
+ return 0;
+}
+
+static int xfrm_policy_filter_match(struct xfrm_userpolicy_info *xpinfo,
+ __u8 ptype)
+{
+ if (!filter.use)
+ return 1;
+
+ if ((xpinfo->dir^filter.xpinfo.dir)&filter.dir_mask)
+ return 0;
+
+ if ((ptype^filter.ptype)&filter.ptype_mask)
+ return 0;
+
+ if (filter.sel_src_mask) {
+ if (xfrm_addr_match(&xpinfo->sel.saddr, &filter.xpinfo.sel.saddr,
+ filter.sel_src_mask))
+ return 0;
+ }
+
+ if (filter.sel_dst_mask) {
+ if (xfrm_addr_match(&xpinfo->sel.daddr, &filter.xpinfo.sel.daddr,
+ filter.sel_dst_mask))
+ return 0;
+ }
+
+ if ((xpinfo->sel.ifindex^filter.xpinfo.sel.ifindex)&filter.sel_dev_mask)
+ return 0;
+
+ if ((xpinfo->sel.proto^filter.xpinfo.sel.proto)&filter.upspec_proto_mask)
+ return 0;
+
+ if (filter.upspec_sport_mask) {
+ if ((xpinfo->sel.sport^filter.xpinfo.sel.sport)&filter.upspec_sport_mask)
+ return 0;
+ }
+
+ if (filter.upspec_dport_mask) {
+ if ((xpinfo->sel.dport^filter.xpinfo.sel.dport)&filter.upspec_dport_mask)
+ return 0;
+ }
+
+ if ((xpinfo->index^filter.xpinfo.index)&filter.index_mask)
+ return 0;
+
+ if ((xpinfo->action^filter.xpinfo.action)&filter.action_mask)
+ return 0;
+
+ if ((xpinfo->priority^filter.xpinfo.priority)&filter.priority_mask)
+ return 0;
+
+ if (filter.policy_flags_mask)
+ if ((xpinfo->flags & filter.xpinfo.flags) == 0)
+ return 0;
+
+ return 1;
+}
+
+int xfrm_policy_print(const struct sockaddr_nl *who, struct nlmsghdr *n,
+ void *arg)
+{
+ struct rtattr * tb[XFRMA_MAX+1];
+ struct rtattr * rta;
+ struct xfrm_userpolicy_info *xpinfo = NULL;
+ struct xfrm_user_polexpire *xpexp = NULL;
+ struct xfrm_userpolicy_id *xpid = NULL;
+ __u8 ptype = XFRM_POLICY_TYPE_MAIN;
+ FILE *fp = (FILE*)arg;
+ int len = n->nlmsg_len;
+
+ if (n->nlmsg_type != XFRM_MSG_NEWPOLICY &&
+ n->nlmsg_type != XFRM_MSG_DELPOLICY &&
+ n->nlmsg_type != XFRM_MSG_UPDPOLICY &&
+ n->nlmsg_type != XFRM_MSG_POLEXPIRE) {
+ fprintf(stderr, "Not a policy: %08x %08x %08x\n",
+ n->nlmsg_len, n->nlmsg_type, n->nlmsg_flags);
+ return 0;
+ }
+
+ if (n->nlmsg_type == XFRM_MSG_DELPOLICY) {
+ xpid = NLMSG_DATA(n);
+ len -= NLMSG_SPACE(sizeof(*xpid));
+ } else if (n->nlmsg_type == XFRM_MSG_POLEXPIRE) {
+ xpexp = NLMSG_DATA(n);
+ xpinfo = &xpexp->pol;
+ len -= NLMSG_SPACE(sizeof(*xpexp));
+ } else {
+ xpexp = NULL;
+ xpinfo = NLMSG_DATA(n);
+ len -= NLMSG_SPACE(sizeof(*xpinfo));
+ }
+
+ if (len < 0) {
+ fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+ return -1;
+ }
+
+ if (n->nlmsg_type == XFRM_MSG_DELPOLICY)
+ rta = XFRMPID_RTA(xpid);
+ else if (n->nlmsg_type == XFRM_MSG_POLEXPIRE)
+ rta = XFRMPEXP_RTA(xpexp);
+ else
+ rta = XFRMP_RTA(xpinfo);
+
+ parse_rtattr(tb, XFRMA_MAX, rta, len);
+
+ if (tb[XFRMA_POLICY_TYPE]) {
+ struct xfrm_userpolicy_type *upt;
+
+ if (RTA_PAYLOAD(tb[XFRMA_POLICY_TYPE]) < sizeof(*upt)) {
+ fprintf(stderr, "too short XFRMA_POLICY_TYPE len\n");
+ return -1;
+ }
+ upt = (struct xfrm_userpolicy_type *)RTA_DATA(tb[XFRMA_POLICY_TYPE]);
+ ptype = upt->type;
+ }
+
+ if (xpinfo && !xfrm_policy_filter_match(xpinfo, ptype))
+ return 0;
+
+ if (n->nlmsg_type == XFRM_MSG_DELPOLICY)
+ fprintf(fp, "Deleted ");
+ else if (n->nlmsg_type == XFRM_MSG_UPDPOLICY)
+ fprintf(fp, "Updated ");
+ else if (n->nlmsg_type == XFRM_MSG_POLEXPIRE)
+ fprintf(fp, "Expired ");
+
+ if (n->nlmsg_type == XFRM_MSG_DELPOLICY) {
+ //xfrm_policy_id_print();
+ if (!tb[XFRMA_POLICY]) {
+ fprintf(stderr, "Buggy XFRM_MSG_DELPOLICY: no XFRMA_POLICY\n");
+ return -1;
+ }
+ if (RTA_PAYLOAD(tb[XFRMA_POLICY]) < sizeof(*xpinfo)) {
+ fprintf(stderr, "Buggy XFRM_MSG_DELPOLICY: too short XFRMA_POLICY len\n");
+ return -1;
+ }
+ xpinfo = (struct xfrm_userpolicy_info *)RTA_DATA(tb[XFRMA_POLICY]);
+ }
+
+ xfrm_policy_info_print(xpinfo, tb, fp, NULL, NULL);
+
+ if (n->nlmsg_type == XFRM_MSG_POLEXPIRE) {
+ fprintf(fp, "\t");
+ fprintf(fp, "hard %u", xpexp->hard);
+ fprintf(fp, "%s", _SL_);
+ }
+
+ if (oneline)
+ fprintf(fp, "\n");
+ fflush(fp);
+
+ return 0;
+}
+
+static int xfrm_policy_get_or_delete(int argc, char **argv, int delete,
+ void *res_nlbuf, size_t res_size)
+{
+ struct rtnl_handle rth;
+ struct {
+ struct nlmsghdr n;
+ struct xfrm_userpolicy_id xpid;
+ char buf[RTA_BUF_SIZE];
+ } req;
+ char *dirp = NULL;
+ char *selp = NULL;
+ char *indexp = NULL;
+ char *ptypep = NULL;
+ char *sctxp = NULL;
+ struct xfrm_userpolicy_type upt;
+ struct xfrm_mark mark = {0, 0};
+ struct {
+ struct xfrm_user_sec_ctx sctx;
+ char str[CTX_BUF_SIZE];
+ } ctx;
+
+
+ memset(&req, 0, sizeof(req));
+ memset(&upt, 0, sizeof(upt));
+ memset(&ctx, 0, sizeof(ctx));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(req.xpid));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = delete ? XFRM_MSG_DELPOLICY : XFRM_MSG_GETPOLICY;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dir") == 0) {
+ if (dirp)
+ duparg("dir", *argv);
+ dirp = *argv;
+
+ NEXT_ARG();
+ xfrm_policy_dir_parse(&req.xpid.dir, &argc, &argv);
+
+ } else if (strcmp(*argv, "ctx") == 0) {
+ char *context;
+
+ if (sctxp)
+ duparg("ctx", *argv);
+ sctxp = *argv;
+ NEXT_ARG();
+ context = *argv;
+ xfrm_sctx_parse((char *)&ctx.str, context, &ctx.sctx);
+ } else if (strcmp(*argv, "mark") == 0) {
+ xfrm_parse_mark(&mark, &argc, &argv);
+ } else if (strcmp(*argv, "index") == 0) {
+ if (indexp)
+ duparg("index", *argv);
+ indexp = *argv;
+
+ NEXT_ARG();
+ if (get_u32(&req.xpid.index, *argv, 0))
+ invarg("INDEX value is invalid", *argv);
+
+ } else if (strcmp(*argv, "ptype") == 0) {
+ if (ptypep)
+ duparg("ptype", *argv);
+ ptypep = *argv;
+
+ NEXT_ARG();
+ xfrm_policy_ptype_parse(&upt.type, &argc, &argv);
+
+ } else {
+ if (selp)
+ invarg("unknown", *argv);
+ selp = *argv;
+
+ xfrm_selector_parse(&req.xpid.sel, &argc, &argv);
+ if (preferred_family == AF_UNSPEC)
+ preferred_family = req.xpid.sel.family;
+
+ }
+
+ argc--; argv++;
+ }
+
+ if (!dirp) {
+ fprintf(stderr, "Not enough information: DIR is required.\n");
+ exit(1);
+ }
+ if (ptypep) {
+ addattr_l(&req.n, sizeof(req), XFRMA_POLICY_TYPE,
+ (void *)&upt, sizeof(upt));
+ }
+ if (!selp && !indexp) {
+ fprintf(stderr, "Not enough information: either SELECTOR or INDEX is required.\n");
+ exit(1);
+ }
+ if (selp && indexp)
+ duparg2("SELECTOR", "INDEX");
+
+ if (rtnl_open_byproto(&rth, 0, NETLINK_XFRM) < 0)
+ exit(1);
+
+ if (req.xpid.sel.family == AF_UNSPEC)
+ req.xpid.sel.family = AF_INET;
+
+ if (mark.m & mark.v) {
+ int r = addattr_l(&req.n, sizeof(req.buf), XFRMA_MARK,
+ (void *)&mark, sizeof(mark));
+ if (r < 0) {
+ fprintf(stderr, "%s: XFRMA_MARK failed\n",__func__);
+ exit(1);
+ }
+ }
+
+ if (sctxp) {
+ addattr_l(&req.n, sizeof(req), XFRMA_SEC_CTX,
+ (void *)&ctx, ctx.sctx.len);
+ }
+
+ if (rtnl_talk(&rth, &req.n, res_nlbuf, res_size) < 0)
+ exit(2);
+
+ rtnl_close(&rth);
+
+ return 0;
+}
+
+static int xfrm_policy_delete(int argc, char **argv)
+{
+ return xfrm_policy_get_or_delete(argc, argv, 1, NULL, 0);
+}
+
+static int xfrm_policy_get(int argc, char **argv)
+{
+ char buf[NLMSG_BUF_SIZE];
+ struct nlmsghdr *n = (struct nlmsghdr *)buf;
+
+ memset(buf, 0, sizeof(buf));
+
+ xfrm_policy_get_or_delete(argc, argv, 0, n, sizeof(buf));
+
+ if (xfrm_policy_print(NULL, n, (void*)stdout) < 0) {
+ fprintf(stderr, "An error :-)\n");
+ exit(1);
+ }
+
+ return 0;
+}
+
+/*
+ * With an existing policy of nlmsg, make new nlmsg for deleting the policy
+ * and store it to buffer.
+ */
+static int xfrm_policy_keep(const struct sockaddr_nl *who,
+ struct nlmsghdr *n,
+ void *arg)
+{
+ struct xfrm_buffer *xb = (struct xfrm_buffer *)arg;
+ struct rtnl_handle *rth = xb->rth;
+ struct xfrm_userpolicy_info *xpinfo = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr *tb[XFRMA_MAX+1];
+ __u8 ptype = XFRM_POLICY_TYPE_MAIN;
+ struct nlmsghdr *new_n;
+ struct xfrm_userpolicy_id *xpid;
+
+ if (n->nlmsg_type != XFRM_MSG_NEWPOLICY) {
+ fprintf(stderr, "Not a policy: %08x %08x %08x\n",
+ n->nlmsg_len, n->nlmsg_type, n->nlmsg_flags);
+ return 0;
+ }
+
+ len -= NLMSG_LENGTH(sizeof(*xpinfo));
+ if (len < 0) {
+ fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+ return -1;
+ }
+
+ parse_rtattr(tb, XFRMA_MAX, XFRMP_RTA(xpinfo), len);
+
+ if (tb[XFRMA_POLICY_TYPE]) {
+ struct xfrm_userpolicy_type *upt;
+
+ if (RTA_PAYLOAD(tb[XFRMA_POLICY_TYPE]) < sizeof(*upt)) {
+ fprintf(stderr, "too short XFRMA_POLICY_TYPE len\n");
+ return -1;
+ }
+ upt = (struct xfrm_userpolicy_type *)RTA_DATA(tb[XFRMA_POLICY_TYPE]);
+ ptype = upt->type;
+ }
+
+ if (!xfrm_policy_filter_match(xpinfo, ptype))
+ return 0;
+
+ if (xb->offset > xb->size) {
+ fprintf(stderr, "Policy buffer overflow\n");
+ return -1;
+ }
+
+ new_n = (struct nlmsghdr *)(xb->buf + xb->offset);
+ new_n->nlmsg_len = NLMSG_LENGTH(sizeof(*xpid));
+ new_n->nlmsg_flags = NLM_F_REQUEST;
+ new_n->nlmsg_type = XFRM_MSG_DELPOLICY;
+ new_n->nlmsg_seq = ++rth->seq;
+
+ xpid = NLMSG_DATA(new_n);
+ memcpy(&xpid->sel, &xpinfo->sel, sizeof(xpid->sel));
+ xpid->dir = xpinfo->dir;
+ xpid->index = xpinfo->index;
+
+ xb->offset += new_n->nlmsg_len;
+ xb->nlmsg_count ++;
+
+ return 0;
+}
+
+static int xfrm_policy_list_or_deleteall(int argc, char **argv, int deleteall)
+{
+ char *selp = NULL;
+ struct rtnl_handle rth;
+
+ if (argc > 0)
+ filter.use = 1;
+ filter.xpinfo.sel.family = preferred_family;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dir") == 0) {
+ NEXT_ARG();
+ xfrm_policy_dir_parse(&filter.xpinfo.dir, &argc, &argv);
+
+ filter.dir_mask = XFRM_FILTER_MASK_FULL;
+
+ } else if (strcmp(*argv, "index") == 0) {
+ NEXT_ARG();
+ if (get_u32(&filter.xpinfo.index, *argv, 0))
+ invarg("INDEX value is invalid", *argv);
+
+ filter.index_mask = XFRM_FILTER_MASK_FULL;
+
+ } else if (strcmp(*argv, "ptype") == 0) {
+ NEXT_ARG();
+ xfrm_policy_ptype_parse(&filter.ptype, &argc, &argv);
+
+ filter.ptype_mask = XFRM_FILTER_MASK_FULL;
+
+ } else if (strcmp(*argv, "action") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "allow") == 0)
+ filter.xpinfo.action = XFRM_POLICY_ALLOW;
+ else if (strcmp(*argv, "block") == 0)
+ filter.xpinfo.action = XFRM_POLICY_BLOCK;
+ else
+ invarg("ACTION value is invalid\n", *argv);
+
+ filter.action_mask = XFRM_FILTER_MASK_FULL;
+
+ } else if (strcmp(*argv, "priority") == 0) {
+ NEXT_ARG();
+ if (get_u32(&filter.xpinfo.priority, *argv, 0))
+ invarg("PRIORITY value is invalid", *argv);
+
+ filter.priority_mask = XFRM_FILTER_MASK_FULL;
+
+ } else if (strcmp(*argv, "flag") == 0) {
+ NEXT_ARG();
+ xfrm_policy_flag_parse(&filter.xpinfo.flags, &argc,
+ &argv);
+
+ filter.policy_flags_mask = XFRM_FILTER_MASK_FULL;
+
+ } else {
+ if (selp)
+ invarg("unknown", *argv);
+ selp = *argv;
+
+ xfrm_selector_parse(&filter.xpinfo.sel, &argc, &argv);
+ if (preferred_family == AF_UNSPEC)
+ preferred_family = filter.xpinfo.sel.family;
+
+ }
+
+ argc--; argv++;
+ }
+
+ if (rtnl_open_byproto(&rth, 0, NETLINK_XFRM) < 0)
+ exit(1);
+
+ if (deleteall) {
+ struct xfrm_buffer xb;
+ char buf[NLMSG_DELETEALL_BUF_SIZE];
+ int i;
+
+ xb.buf = buf;
+ xb.size = sizeof(buf);
+ xb.rth = &rth;
+
+ for (i = 0; ; i++) {
+ struct {
+ struct nlmsghdr n;
+ char buf[NLMSG_BUF_SIZE];
+ } req = {
+ .n.nlmsg_len = NLMSG_HDRLEN,
+ .n.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
+ .n.nlmsg_type = XFRM_MSG_GETPOLICY,
+ .n.nlmsg_seq = rth.dump = ++rth.seq,
+ };
+
+ xb.offset = 0;
+ xb.nlmsg_count = 0;
+
+ if (show_stats > 1)
+ fprintf(stderr, "Delete-all round = %d\n", i);
+
+ if (rtnl_send(&rth, (void *)&req, req.n.nlmsg_len) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+
+ if (rtnl_dump_filter(&rth, xfrm_policy_keep, &xb) < 0) {
+ fprintf(stderr, "Delete-all terminated\n");
+ exit(1);
+ }
+ if (xb.nlmsg_count == 0) {
+ if (show_stats > 1)
+ fprintf(stderr, "Delete-all completed\n");
+ break;
+ }
+
+ if (rtnl_send_check(&rth, xb.buf, xb.offset) < 0) {
+ perror("Failed to send delete-all request");
+ exit(1);
+ }
+ if (show_stats > 1)
+ fprintf(stderr, "Delete-all nlmsg count = %d\n", xb.nlmsg_count);
+
+ xb.offset = 0;
+ xb.nlmsg_count = 0;
+ }
+ } else {
+ struct {
+ struct nlmsghdr n;
+ char buf[NLMSG_BUF_SIZE];
+ } req = {
+ .n.nlmsg_len = NLMSG_HDRLEN,
+ .n.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
+ .n.nlmsg_type = XFRM_MSG_GETPOLICY,
+ .n.nlmsg_seq = rth.dump = ++rth.seq,
+ };
+
+ if (rtnl_send(&rth, (void *)&req, req.n.nlmsg_len) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+
+ if (rtnl_dump_filter(&rth, xfrm_policy_print, stdout) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ exit(1);
+ }
+ }
+
+ rtnl_close(&rth);
+
+ exit(0);
+}
+
+static int print_spdinfo( struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ __u32 *f = NLMSG_DATA(n);
+ struct rtattr * tb[XFRMA_SPD_MAX+1];
+ struct rtattr * rta;
+
+ int len = n->nlmsg_len;
+
+ len -= NLMSG_LENGTH(sizeof(__u32));
+ if (len < 0) {
+ fprintf(stderr, "SPDinfo: Wrong len %d\n", len);
+ return -1;
+ }
+
+ rta = XFRMSAPD_RTA(f);
+ parse_rtattr(tb, XFRMA_SPD_MAX, rta, len);
+
+ fprintf(fp,"\t SPD");
+ if (tb[XFRMA_SPD_INFO]) {
+ struct xfrmu_spdinfo *si;
+
+ if (RTA_PAYLOAD(tb[XFRMA_SPD_INFO]) < sizeof(*si)) {
+ fprintf(stderr, "SPDinfo: Wrong len %d\n", len);
+ return -1;
+ }
+ si = RTA_DATA(tb[XFRMA_SPD_INFO]);
+ fprintf(fp," IN %d", si->incnt);
+ fprintf(fp," OUT %d", si->outcnt);
+ fprintf(fp," FWD %d", si->fwdcnt);
+
+ if (show_stats) {
+ fprintf(fp," (Sock:");
+ fprintf(fp," IN %d", si->inscnt);
+ fprintf(fp," OUT %d", si->outscnt);
+ fprintf(fp," FWD %d", si->fwdscnt);
+ fprintf(fp,")");
+ }
+
+ fprintf(fp, "%s", _SL_);
+ }
+ if (show_stats > 1) {
+ struct xfrmu_spdhinfo *sh;
+
+ if (tb[XFRMA_SPD_HINFO]) {
+ if (RTA_PAYLOAD(tb[XFRMA_SPD_HINFO]) < sizeof(*sh)) {
+ fprintf(stderr, "SPDinfo: Wrong len %d\n", len);
+ return -1;
+ }
+ sh = RTA_DATA(tb[XFRMA_SPD_HINFO]);
+ fprintf(fp,"\t SPD buckets:");
+ fprintf(fp," count %d", sh->spdhcnt);
+ fprintf(fp," Max %d", sh->spdhmcnt);
+ fprintf(fp, "%s", _SL_);
+ }
+ if (tb[XFRMA_SPD_IPV4_HTHRESH]) {
+ struct xfrmu_spdhthresh *th;
+ if (RTA_PAYLOAD(tb[XFRMA_SPD_IPV4_HTHRESH]) < sizeof(*th)) {
+ fprintf(stderr, "SPDinfo: Wrong len %d\n", len);
+ return -1;
+ }
+ th = RTA_DATA(tb[XFRMA_SPD_IPV4_HTHRESH]);
+ fprintf(fp,"\t SPD IPv4 thresholds:");
+ fprintf(fp," local %d", th->lbits);
+ fprintf(fp," remote %d", th->rbits);
+ fprintf(fp, "%s", _SL_);
+
+ }
+ if (tb[XFRMA_SPD_IPV6_HTHRESH]) {
+ struct xfrmu_spdhthresh *th;
+ if (RTA_PAYLOAD(tb[XFRMA_SPD_IPV6_HTHRESH]) < sizeof(*th)) {
+ fprintf(stderr, "SPDinfo: Wrong len %d\n", len);
+ return -1;
+ }
+ th = RTA_DATA(tb[XFRMA_SPD_IPV6_HTHRESH]);
+ fprintf(fp,"\t SPD IPv6 thresholds:");
+ fprintf(fp," local %d", th->lbits);
+ fprintf(fp," remote %d", th->rbits);
+ fprintf(fp, "%s", _SL_);
+ }
+ }
+
+ if (oneline)
+ fprintf(fp, "\n");
+
+ return 0;
+}
+
+static int xfrm_spd_setinfo(int argc, char **argv)
+{
+ struct rtnl_handle rth;
+ struct {
+ struct nlmsghdr n;
+ __u32 flags;
+ char buf[RTA_BUF_SIZE];
+ } req;
+
+ char *thr4 = NULL;
+ char *thr6 = NULL;
+
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(__u32));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = XFRM_MSG_NEWSPDINFO;
+ req.flags = 0XFFFFFFFF;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "hthresh4") == 0) {
+ struct xfrmu_spdhthresh thr;
+
+ if (thr4)
+ duparg("hthresh4", *argv);
+ thr4 = *argv;
+ NEXT_ARG();
+ if (get_u8(&thr.lbits, *argv, 0) || thr.lbits > 32)
+ invarg("hthresh4 LBITS value is invalid", *argv);
+ NEXT_ARG();
+ if (get_u8(&thr.rbits, *argv, 0) || thr.rbits > 32)
+ invarg("hthresh4 RBITS value is invalid", *argv);
+
+ addattr_l(&req.n, sizeof(req), XFRMA_SPD_IPV4_HTHRESH,
+ (void *)&thr, sizeof(thr));
+ } else if (strcmp(*argv, "hthresh6") == 0) {
+ struct xfrmu_spdhthresh thr;
+
+ if (thr6)
+ duparg("hthresh6", *argv);
+ thr6 = *argv;
+ NEXT_ARG();
+ if (get_u8(&thr.lbits, *argv, 0) || thr.lbits > 128)
+ invarg("hthresh6 LBITS value is invalid", *argv);
+ NEXT_ARG();
+ if (get_u8(&thr.rbits, *argv, 0) || thr.rbits > 128)
+ invarg("hthresh6 RBITS value is invalid", *argv);
+
+ addattr_l(&req.n, sizeof(req), XFRMA_SPD_IPV6_HTHRESH,
+ (void *)&thr, sizeof(thr));
+ } else {
+ invarg("unknown", *argv);
+ }
+
+ argc--; argv++;
+ }
+
+ if (rtnl_open_byproto(&rth, 0, NETLINK_XFRM) < 0)
+ exit(1);
+
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ exit(2);
+
+ rtnl_close(&rth);
+
+ return 0;
+}
+
+static int xfrm_spd_getinfo(int argc, char **argv)
+{
+ struct rtnl_handle rth;
+ struct {
+ struct nlmsghdr n;
+ __u32 flags;
+ char ans[128];
+ } req;
+
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(__u32));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = XFRM_MSG_GETSPDINFO;
+ req.flags = 0XFFFFFFFF;
+
+ if (rtnl_open_byproto(&rth, 0, NETLINK_XFRM) < 0)
+ exit(1);
+
+ if (rtnl_talk(&rth, &req.n, &req.n, sizeof(req)) < 0)
+ exit(2);
+
+ print_spdinfo(&req.n, (void*)stdout);
+
+ rtnl_close(&rth);
+
+ return 0;
+}
+
+static int xfrm_policy_flush(int argc, char **argv)
+{
+ struct rtnl_handle rth;
+ struct {
+ struct nlmsghdr n;
+ char buf[RTA_BUF_SIZE];
+ } req;
+ char *ptypep = NULL;
+ struct xfrm_userpolicy_type upt;
+
+ memset(&req, 0, sizeof(req));
+ memset(&upt, 0, sizeof(upt));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(0); /* nlmsg data is nothing */
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = XFRM_MSG_FLUSHPOLICY;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "ptype") == 0) {
+ if (ptypep)
+ duparg("ptype", *argv);
+ ptypep = *argv;
+
+ NEXT_ARG();
+ xfrm_policy_ptype_parse(&upt.type, &argc, &argv);
+ } else
+ invarg("unknown", *argv);
+
+ argc--; argv++;
+ }
+
+ if (ptypep) {
+ addattr_l(&req.n, sizeof(req), XFRMA_POLICY_TYPE,
+ (void *)&upt, sizeof(upt));
+ }
+
+ if (rtnl_open_byproto(&rth, 0, NETLINK_XFRM) < 0)
+ exit(1);
+
+ if (show_stats > 1)
+ fprintf(stderr, "Flush policy\n");
+
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ exit(2);
+
+ rtnl_close(&rth);
+
+ return 0;
+}
+
+int do_xfrm_policy(int argc, char **argv)
+{
+ if (argc < 1)
+ return xfrm_policy_list_or_deleteall(0, NULL, 0);
+
+ if (matches(*argv, "add") == 0)
+ return xfrm_policy_modify(XFRM_MSG_NEWPOLICY, 0,
+ argc-1, argv+1);
+ if (matches(*argv, "update") == 0)
+ return xfrm_policy_modify(XFRM_MSG_UPDPOLICY, 0,
+ argc-1, argv+1);
+ if (matches(*argv, "delete") == 0)
+ return xfrm_policy_delete(argc-1, argv+1);
+ if (matches(*argv, "deleteall") == 0 || matches(*argv, "delall") == 0)
+ return xfrm_policy_list_or_deleteall(argc-1, argv+1, 1);
+ if (matches(*argv, "list") == 0 || matches(*argv, "show") == 0
+ || matches(*argv, "lst") == 0)
+ return xfrm_policy_list_or_deleteall(argc-1, argv+1, 0);
+ if (matches(*argv, "get") == 0)
+ return xfrm_policy_get(argc-1, argv+1);
+ if (matches(*argv, "flush") == 0)
+ return xfrm_policy_flush(argc-1, argv+1);
+ if (matches(*argv, "count") == 0)
+ return xfrm_spd_getinfo(argc, argv);
+ if (matches(*argv, "set") == 0)
+ return xfrm_spd_setinfo(argc-1, argv+1);
+ if (matches(*argv, "help") == 0)
+ usage();
+ fprintf(stderr, "Command \"%s\" is unknown, try \"ip xfrm policy help\".\n", *argv);
+ exit(-1);
+}
diff --git a/iproute2/ip/xfrm_state.c b/iproute2/ip/xfrm_state.c
new file mode 100644
index 0000000..b5734da
--- /dev/null
+++ b/iproute2/ip/xfrm_state.c
@@ -0,0 +1,1392 @@
+/* $USAGI: $ */
+
+/*
+ * Copyright (C)2004 USAGI/WIDE Project
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses>.
+ */
+/*
+ * based on iproute.c
+ */
+/*
+ * Authors:
+ * Masahide NAKAMURA @USAGI
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <netdb.h>
+#include "utils.h"
+#include "xfrm.h"
+#include "ip_common.h"
+
+//#define NLMSG_DELETEALL_BUF_SIZE (4096-512)
+#define NLMSG_DELETEALL_BUF_SIZE 8192
+
+/*
+ * Receiving buffer defines:
+ * nlmsg
+ * data = struct xfrm_usersa_info
+ * rtattr
+ * rtattr
+ * ... (max count of rtattr is XFRM_MAX+1
+ *
+ * each rtattr data = struct xfrm_algo(dynamic size) or xfrm_address_t
+ */
+#define NLMSG_BUF_SIZE 4096
+#define RTA_BUF_SIZE 2048
+#define XFRM_ALGO_KEY_BUF_SIZE 512
+#define CTX_BUF_SIZE 256
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: ip xfrm state { add | update } ID [ ALGO-LIST ] [ mode MODE ]\n");
+ fprintf(stderr, " [ mark MARK [ mask MASK ] ] [ reqid REQID ] [ seq SEQ ]\n");
+ fprintf(stderr, " [ replay-window SIZE ] [ replay-seq SEQ ] [ replay-oseq SEQ ]\n");
+ fprintf(stderr, " [ replay-seq-hi SEQ ] [ replay-oseq-hi SEQ ]\n");
+ fprintf(stderr, " [ flag FLAG-LIST ] [ sel SELECTOR ] [ LIMIT-LIST ] [ encap ENCAP ]\n");
+ fprintf(stderr, " [ coa ADDR[/PLEN] ] [ ctx CTX ] [ extra-flag EXTRA-FLAG-LIST ]\n");
+ fprintf(stderr, "Usage: ip xfrm state allocspi ID [ mode MODE ] [ mark MARK [ mask MASK ] ]\n");
+ fprintf(stderr, " [ reqid REQID ] [ seq SEQ ] [ min SPI max SPI ]\n");
+ fprintf(stderr, "Usage: ip xfrm state { delete | get } ID [ mark MARK [ mask MASK ] ]\n");
+ fprintf(stderr, "Usage: ip xfrm state { deleteall | list } [ ID ] [ mode MODE ] [ reqid REQID ]\n");
+ fprintf(stderr, " [ flag FLAG-LIST ]\n");
+ fprintf(stderr, "Usage: ip xfrm state flush [ proto XFRM-PROTO ]\n");
+ fprintf(stderr, "Usage: ip xfrm state count\n");
+ fprintf(stderr, "ID := [ src ADDR ] [ dst ADDR ] [ proto XFRM-PROTO ] [ spi SPI ]\n");
+ fprintf(stderr, "XFRM-PROTO := ");
+ fprintf(stderr, "%s | ", strxf_xfrmproto(IPPROTO_ESP));
+ fprintf(stderr, "%s | ", strxf_xfrmproto(IPPROTO_AH));
+ fprintf(stderr, "%s | ", strxf_xfrmproto(IPPROTO_COMP));
+ fprintf(stderr, "%s | ", strxf_xfrmproto(IPPROTO_ROUTING));
+ fprintf(stderr, "%s\n", strxf_xfrmproto(IPPROTO_DSTOPTS));
+ fprintf(stderr, "ALGO-LIST := [ ALGO-LIST ] ALGO\n");
+ fprintf(stderr, "ALGO := { ");
+ fprintf(stderr, "%s | ", strxf_algotype(XFRMA_ALG_CRYPT));
+ fprintf(stderr, "%s", strxf_algotype(XFRMA_ALG_AUTH));
+ fprintf(stderr, " } ALGO-NAME ALGO-KEYMAT |\n");
+ fprintf(stderr, " %s", strxf_algotype(XFRMA_ALG_AUTH_TRUNC));
+ fprintf(stderr, " ALGO-NAME ALGO-KEYMAT ALGO-TRUNC-LEN |\n");
+ fprintf(stderr, " %s", strxf_algotype(XFRMA_ALG_AEAD));
+ fprintf(stderr, " ALGO-NAME ALGO-KEYMAT ALGO-ICV-LEN |\n");
+ fprintf(stderr, " %s", strxf_algotype(XFRMA_ALG_COMP));
+ fprintf(stderr, " ALGO-NAME\n");
+ fprintf(stderr, "MODE := transport | tunnel | beet | ro | in_trigger\n");
+ fprintf(stderr, "FLAG-LIST := [ FLAG-LIST ] FLAG\n");
+ fprintf(stderr, "FLAG := noecn | decap-dscp | nopmtudisc | wildrecv | icmp | af-unspec | align4 | esn\n");
+ fprintf(stderr, "EXTRA-FLAG-LIST := [ EXTRA-FLAG-LIST ] EXTRA-FLAG\n");
+ fprintf(stderr, "EXTRA-FLAG := dont-encap-dscp\n");
+ fprintf(stderr, "SELECTOR := [ src ADDR[/PLEN] ] [ dst ADDR[/PLEN] ] [ dev DEV ] [ UPSPEC ]\n");
+ fprintf(stderr, "UPSPEC := proto { { ");
+ fprintf(stderr, "%s | ", strxf_proto(IPPROTO_TCP));
+ fprintf(stderr, "%s | ", strxf_proto(IPPROTO_UDP));
+ fprintf(stderr, "%s | ", strxf_proto(IPPROTO_SCTP));
+ fprintf(stderr, "%s", strxf_proto(IPPROTO_DCCP));
+ fprintf(stderr, " } [ sport PORT ] [ dport PORT ] |\n");
+ fprintf(stderr, " { ");
+ fprintf(stderr, "%s | ", strxf_proto(IPPROTO_ICMP));
+ fprintf(stderr, "%s | ", strxf_proto(IPPROTO_ICMPV6));
+ fprintf(stderr, "%s", strxf_proto(IPPROTO_MH));
+ fprintf(stderr, " } [ type NUMBER ] [ code NUMBER ] |\n");
+ fprintf(stderr, " %s", strxf_proto(IPPROTO_GRE));
+ fprintf(stderr, " [ key { DOTTED-QUAD | NUMBER } ] | PROTO }\n");
+ fprintf(stderr, "LIMIT-LIST := [ LIMIT-LIST ] limit LIMIT\n");
+ fprintf(stderr, "LIMIT := { time-soft | time-hard | time-use-soft | time-use-hard } SECONDS |\n");
+ fprintf(stderr, " { byte-soft | byte-hard } SIZE | { packet-soft | packet-hard } COUNT\n");
+ fprintf(stderr, "ENCAP := { espinudp | espinudp-nonike } SPORT DPORT OADDR\n");
+
+ exit(-1);
+}
+
+static int xfrm_algo_parse(struct xfrm_algo *alg, enum xfrm_attr_type_t type,
+ char *name, char *key, char *buf, int max)
+{
+ int len;
+ int slen = strlen(key);
+
+#if 0
+ /* XXX: verifying both name and key is required! */
+ fprintf(stderr, "warning: ALGO-NAME/ALGO-KEYMAT values will be sent to the kernel promiscuously! (verifying them isn't implemented yet)\n");
+#endif
+
+ strncpy(alg->alg_name, name, sizeof(alg->alg_name));
+
+ if (slen > 2 && strncmp(key, "0x", 2) == 0) {
+ /* split two chars "0x" from the top */
+ char *p = key + 2;
+ int plen = slen - 2;
+ int i;
+ int j;
+
+ /* Converting hexadecimal numbered string into real key;
+ * Convert each two chars into one char(value). If number
+ * of the length is odd, add zero on the top for rounding.
+ */
+
+ /* calculate length of the converted values(real key) */
+ len = (plen + 1) / 2;
+ if (len > max)
+ invarg("ALGO-KEYMAT value makes buffer overflow\n", key);
+
+ for (i = - (plen % 2), j = 0; j < len; i += 2, j++) {
+ char vbuf[3];
+ __u8 val;
+
+ vbuf[0] = i >= 0 ? p[i] : '0';
+ vbuf[1] = p[i + 1];
+ vbuf[2] = '\0';
+
+ if (get_u8(&val, vbuf, 16))
+ invarg("ALGO-KEYMAT value is invalid", key);
+
+ buf[j] = val;
+ }
+ } else {
+ len = slen;
+ if (len > 0) {
+ if (len > max)
+ invarg("ALGO-KEYMAT value makes buffer overflow\n", key);
+
+ memcpy(buf, key, len);
+ }
+ }
+
+ alg->alg_key_len = len * 8;
+
+ return 0;
+}
+
+static int xfrm_seq_parse(__u32 *seq, int *argcp, char ***argvp)
+{
+ int argc = *argcp;
+ char **argv = *argvp;
+
+ if (get_u32(seq, *argv, 0))
+ invarg("SEQ value is invalid", *argv);
+
+ *seq = htonl(*seq);
+
+ *argcp = argc;
+ *argvp = argv;
+
+ return 0;
+}
+
+static int xfrm_state_flag_parse(__u8 *flags, int *argcp, char ***argvp)
+{
+ int argc = *argcp;
+ char **argv = *argvp;
+ int len = strlen(*argv);
+
+ if (len > 2 && strncmp(*argv, "0x", 2) == 0) {
+ __u8 val = 0;
+
+ if (get_u8(&val, *argv, 16))
+ invarg("FLAG value is invalid", *argv);
+ *flags = val;
+ } else {
+ while (1) {
+ if (strcmp(*argv, "noecn") == 0)
+ *flags |= XFRM_STATE_NOECN;
+ else if (strcmp(*argv, "decap-dscp") == 0)
+ *flags |= XFRM_STATE_DECAP_DSCP;
+ else if (strcmp(*argv, "nopmtudisc") == 0)
+ *flags |= XFRM_STATE_NOPMTUDISC;
+ else if (strcmp(*argv, "wildrecv") == 0)
+ *flags |= XFRM_STATE_WILDRECV;
+ else if (strcmp(*argv, "icmp") == 0)
+ *flags |= XFRM_STATE_ICMP;
+ else if (strcmp(*argv, "af-unspec") == 0)
+ *flags |= XFRM_STATE_AF_UNSPEC;
+ else if (strcmp(*argv, "align4") == 0)
+ *flags |= XFRM_STATE_ALIGN4;
+ else if (strcmp(*argv, "esn") == 0)
+ *flags |= XFRM_STATE_ESN;
+ else {
+ PREV_ARG(); /* back track */
+ break;
+ }
+
+ if (!NEXT_ARG_OK())
+ break;
+ NEXT_ARG();
+ }
+ }
+
+ *argcp = argc;
+ *argvp = argv;
+
+ return 0;
+}
+
+static int xfrm_state_extra_flag_parse(__u32 *extra_flags, int *argcp, char ***argvp)
+{
+ int argc = *argcp;
+ char **argv = *argvp;
+ int len = strlen(*argv);
+
+ if (len > 2 && strncmp(*argv, "0x", 2) == 0) {
+ __u32 val = 0;
+
+ if (get_u32(&val, *argv, 16))
+ invarg("\"EXTRA-FLAG\" is invalid", *argv);
+ *extra_flags = val;
+ } else {
+ while (1) {
+ if (strcmp(*argv, "dont-encap-dscp") == 0)
+ *extra_flags |= XFRM_SA_XFLAG_DONT_ENCAP_DSCP;
+ else {
+ PREV_ARG(); /* back track */
+ break;
+ }
+
+ if (!NEXT_ARG_OK())
+ break;
+ NEXT_ARG();
+ }
+ }
+
+ *argcp = argc;
+ *argvp = argv;
+
+ return 0;
+}
+
+static int xfrm_state_modify(int cmd, unsigned flags, int argc, char **argv)
+{
+ struct rtnl_handle rth;
+ struct {
+ struct nlmsghdr n;
+ struct xfrm_usersa_info xsinfo;
+ char buf[RTA_BUF_SIZE];
+ } req;
+ struct xfrm_replay_state replay;
+ struct xfrm_replay_state_esn replay_esn;
+ __u32 replay_window = 0;
+ __u32 seq = 0, oseq = 0, seq_hi = 0, oseq_hi = 0;
+ char *idp = NULL;
+ char *aeadop = NULL;
+ char *ealgop = NULL;
+ char *aalgop = NULL;
+ char *calgop = NULL;
+ char *coap = NULL;
+ char *sctxp = NULL;
+ __u32 extra_flags = 0;
+ struct xfrm_mark mark = {0, 0};
+ struct {
+ struct xfrm_user_sec_ctx sctx;
+ char str[CTX_BUF_SIZE];
+ } ctx;
+
+ memset(&req, 0, sizeof(req));
+ memset(&replay, 0, sizeof(replay));
+ memset(&replay_esn, 0, sizeof(replay_esn));
+ memset(&ctx, 0, sizeof(ctx));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(req.xsinfo));
+ req.n.nlmsg_flags = NLM_F_REQUEST|flags;
+ req.n.nlmsg_type = cmd;
+ req.xsinfo.family = preferred_family;
+
+ req.xsinfo.lft.soft_byte_limit = XFRM_INF;
+ req.xsinfo.lft.hard_byte_limit = XFRM_INF;
+ req.xsinfo.lft.soft_packet_limit = XFRM_INF;
+ req.xsinfo.lft.hard_packet_limit = XFRM_INF;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "mode") == 0) {
+ NEXT_ARG();
+ xfrm_mode_parse(&req.xsinfo.mode, &argc, &argv);
+ } else if (strcmp(*argv, "mark") == 0) {
+ xfrm_parse_mark(&mark, &argc, &argv);
+ } else if (strcmp(*argv, "reqid") == 0) {
+ NEXT_ARG();
+ xfrm_reqid_parse(&req.xsinfo.reqid, &argc, &argv);
+ } else if (strcmp(*argv, "seq") == 0) {
+ NEXT_ARG();
+ xfrm_seq_parse(&req.xsinfo.seq, &argc, &argv);
+ } else if (strcmp(*argv, "replay-window") == 0) {
+ NEXT_ARG();
+ if (get_u32(&replay_window, *argv, 0))
+ invarg("value after \"replay-window\" is invalid", *argv);
+ } else if (strcmp(*argv, "replay-seq") == 0) {
+ NEXT_ARG();
+ if (get_u32(&seq, *argv, 0))
+ invarg("value after \"replay-seq\" is invalid", *argv);
+ } else if (strcmp(*argv, "replay-seq-hi") == 0) {
+ NEXT_ARG();
+ if (get_u32(&seq_hi, *argv, 0))
+ invarg("value after \"replay-seq-hi\" is invalid", *argv);
+ } else if (strcmp(*argv, "replay-oseq") == 0) {
+ NEXT_ARG();
+ if (get_u32(&oseq, *argv, 0))
+ invarg("value after \"replay-oseq\" is invalid", *argv);
+ } else if (strcmp(*argv, "replay-oseq-hi") == 0) {
+ NEXT_ARG();
+ if (get_u32(&oseq_hi, *argv, 0))
+ invarg("value after \"replay-oseq-hi\" is invalid", *argv);
+ } else if (strcmp(*argv, "flag") == 0) {
+ NEXT_ARG();
+ xfrm_state_flag_parse(&req.xsinfo.flags, &argc, &argv);
+ } else if (strcmp(*argv, "extra-flag") == 0) {
+ NEXT_ARG();
+ xfrm_state_extra_flag_parse(&extra_flags, &argc, &argv);
+ } else if (strcmp(*argv, "sel") == 0) {
+ NEXT_ARG();
+ preferred_family = AF_UNSPEC;
+ xfrm_selector_parse(&req.xsinfo.sel, &argc, &argv);
+ preferred_family = req.xsinfo.sel.family;
+ } else if (strcmp(*argv, "limit") == 0) {
+ NEXT_ARG();
+ xfrm_lifetime_cfg_parse(&req.xsinfo.lft, &argc, &argv);
+ } else if (strcmp(*argv, "encap") == 0) {
+ struct xfrm_encap_tmpl encap;
+ inet_prefix oa;
+ NEXT_ARG();
+ xfrm_encap_type_parse(&encap.encap_type, &argc, &argv);
+ NEXT_ARG();
+ if (get_u16(&encap.encap_sport, *argv, 0))
+ invarg("SPORT value after \"encap\" is invalid", *argv);
+ encap.encap_sport = htons(encap.encap_sport);
+ NEXT_ARG();
+ if (get_u16(&encap.encap_dport, *argv, 0))
+ invarg("DPORT value after \"encap\" is invalid", *argv);
+ encap.encap_dport = htons(encap.encap_dport);
+ NEXT_ARG();
+ get_addr(&oa, *argv, AF_UNSPEC);
+ memcpy(&encap.encap_oa, &oa.data, sizeof(encap.encap_oa));
+ addattr_l(&req.n, sizeof(req.buf), XFRMA_ENCAP,
+ (void *)&encap, sizeof(encap));
+ } else if (strcmp(*argv, "coa") == 0) {
+ inet_prefix coa;
+ xfrm_address_t xcoa;
+
+ if (coap)
+ duparg("coa", *argv);
+ coap = *argv;
+
+ NEXT_ARG();
+
+ get_prefix(&coa, *argv, preferred_family);
+ if (coa.family == AF_UNSPEC)
+ invarg("value after \"coa\" has an unrecognized address family", *argv);
+ if (coa.bytelen > sizeof(xcoa))
+ invarg("value after \"coa\" is too large", *argv);
+
+ memset(&xcoa, 0, sizeof(xcoa));
+ memcpy(&xcoa, &coa.data, coa.bytelen);
+
+ addattr_l(&req.n, sizeof(req.buf), XFRMA_COADDR,
+ (void *)&xcoa, sizeof(xcoa));
+ } else if (strcmp(*argv, "ctx") == 0) {
+ char *context;
+
+ if (sctxp)
+ duparg("ctx", *argv);
+ sctxp = *argv;
+
+ NEXT_ARG();
+ context = *argv;
+
+ xfrm_sctx_parse((char *)&ctx.str, context, &ctx.sctx);
+ addattr_l(&req.n, sizeof(req.buf), XFRMA_SEC_CTX,
+ (void *)&ctx, ctx.sctx.len);
+ } else {
+ /* try to assume ALGO */
+ int type = xfrm_algotype_getbyname(*argv);
+ switch (type) {
+ case XFRMA_ALG_AEAD:
+ case XFRMA_ALG_CRYPT:
+ case XFRMA_ALG_AUTH:
+ case XFRMA_ALG_AUTH_TRUNC:
+ case XFRMA_ALG_COMP:
+ {
+ /* ALGO */
+ struct {
+ union {
+ struct xfrm_algo alg;
+ struct xfrm_algo_aead aead;
+ struct xfrm_algo_auth auth;
+ } u;
+ char buf[XFRM_ALGO_KEY_BUF_SIZE];
+ } alg = {};
+ int len;
+ __u32 icvlen, trunclen;
+ char *name;
+ char *key = "";
+ char *buf;
+
+ switch (type) {
+ case XFRMA_ALG_AEAD:
+ if (ealgop || aalgop || aeadop)
+ duparg("ALGO-TYPE", *argv);
+ aeadop = *argv;
+ break;
+ case XFRMA_ALG_CRYPT:
+ if (ealgop || aeadop)
+ duparg("ALGO-TYPE", *argv);
+ ealgop = *argv;
+ break;
+ case XFRMA_ALG_AUTH:
+ case XFRMA_ALG_AUTH_TRUNC:
+ if (aalgop || aeadop)
+ duparg("ALGO-TYPE", *argv);
+ aalgop = *argv;
+ break;
+ case XFRMA_ALG_COMP:
+ if (calgop)
+ duparg("ALGO-TYPE", *argv);
+ calgop = *argv;
+ break;
+ default:
+ /* not reached */
+ invarg("ALGO-TYPE value is invalid\n", *argv);
+ }
+
+ if (!NEXT_ARG_OK())
+ missarg("ALGO-NAME");
+ NEXT_ARG();
+ name = *argv;
+
+ switch (type) {
+ case XFRMA_ALG_AEAD:
+ case XFRMA_ALG_CRYPT:
+ case XFRMA_ALG_AUTH:
+ case XFRMA_ALG_AUTH_TRUNC:
+ if (!NEXT_ARG_OK())
+ missarg("ALGO-KEYMAT");
+ NEXT_ARG();
+ key = *argv;
+ break;
+ }
+
+ buf = alg.u.alg.alg_key;
+ len = sizeof(alg.u.alg);
+
+ switch (type) {
+ case XFRMA_ALG_AEAD:
+ if (!NEXT_ARG_OK())
+ missarg("ALGO-ICV-LEN");
+ NEXT_ARG();
+ if (get_u32(&icvlen, *argv, 0))
+ invarg("ALGO-ICV-LEN value is invalid",
+ *argv);
+ alg.u.aead.alg_icv_len = icvlen;
+
+ buf = alg.u.aead.alg_key;
+ len = sizeof(alg.u.aead);
+ break;
+ case XFRMA_ALG_AUTH_TRUNC:
+ if (!NEXT_ARG_OK())
+ missarg("ALGO-TRUNC-LEN");
+ NEXT_ARG();
+ if (get_u32(&trunclen, *argv, 0))
+ invarg("ALGO-TRUNC-LEN value is invalid",
+ *argv);
+ alg.u.auth.alg_trunc_len = trunclen;
+
+ buf = alg.u.auth.alg_key;
+ len = sizeof(alg.u.auth);
+ break;
+ }
+
+ xfrm_algo_parse((void *)&alg, type, name, key,
+ buf, sizeof(alg.buf));
+ len += alg.u.alg.alg_key_len;
+
+ addattr_l(&req.n, sizeof(req.buf), type,
+ (void *)&alg, len);
+ break;
+ }
+ default:
+ /* try to assume ID */
+ if (idp)
+ invarg("unknown", *argv);
+ idp = *argv;
+
+ /* ID */
+ xfrm_id_parse(&req.xsinfo.saddr, &req.xsinfo.id,
+ &req.xsinfo.family, 0, &argc, &argv);
+ if (preferred_family == AF_UNSPEC)
+ preferred_family = req.xsinfo.family;
+ }
+ }
+ argc--; argv++;
+ }
+
+ if (req.xsinfo.flags & XFRM_STATE_ESN &&
+ replay_window == 0) {
+ fprintf(stderr, "Error: esn flag set without replay-window.\n");
+ exit(-1);
+ }
+
+ if (replay_window > XFRMA_REPLAY_ESN_MAX) {
+ fprintf(stderr,
+ "Error: replay-window (%u) > XFRMA_REPLAY_ESN_MAX (%u).\n",
+ replay_window, XFRMA_REPLAY_ESN_MAX);
+ exit(-1);
+ }
+
+ if (req.xsinfo.flags & XFRM_STATE_ESN ||
+ replay_window > (sizeof(replay.bitmap) * 8)) {
+ replay_esn.seq = seq;
+ replay_esn.oseq = oseq;
+ replay_esn.seq_hi = seq_hi;
+ replay_esn.oseq_hi = oseq_hi;
+ replay_esn.replay_window = replay_window;
+ replay_esn.bmp_len = (replay_window + sizeof(__u32) * 8 - 1) /
+ (sizeof(__u32) * 8);
+ addattr_l(&req.n, sizeof(req.buf), XFRMA_REPLAY_ESN_VAL,
+ &replay_esn, sizeof(replay_esn));
+ } else {
+ if (seq || oseq) {
+ replay.seq = seq;
+ replay.oseq = oseq;
+ addattr_l(&req.n, sizeof(req.buf), XFRMA_REPLAY_VAL,
+ &replay, sizeof(replay));
+ }
+ req.xsinfo.replay_window = replay_window;
+ }
+
+ if (extra_flags)
+ addattr32(&req.n, sizeof(req.buf), XFRMA_SA_EXTRA_FLAGS,
+ extra_flags);
+
+ if (!idp) {
+ fprintf(stderr, "Not enough information: ID is required\n");
+ exit(1);
+ }
+
+ if (mark.m) {
+ int r = addattr_l(&req.n, sizeof(req.buf), XFRMA_MARK,
+ (void *)&mark, sizeof(mark));
+ if (r < 0) {
+ fprintf(stderr, "XFRMA_MARK failed\n");
+ exit(1);
+ }
+ }
+
+ if (xfrm_xfrmproto_is_ipsec(req.xsinfo.id.proto)) {
+ switch (req.xsinfo.mode) {
+ case XFRM_MODE_TRANSPORT:
+ case XFRM_MODE_TUNNEL:
+ break;
+ case XFRM_MODE_BEET:
+ if (req.xsinfo.id.proto == IPPROTO_ESP)
+ break;
+ default:
+ fprintf(stderr, "MODE value is invalid with XFRM-PROTO value \"%s\"\n",
+ strxf_xfrmproto(req.xsinfo.id.proto));
+ exit(1);
+ }
+
+ switch (req.xsinfo.id.proto) {
+ case IPPROTO_ESP:
+ if (calgop) {
+ fprintf(stderr, "ALGO-TYPE value \"%s\" is invalid with XFRM-PROTO value \"%s\"\n",
+ strxf_algotype(XFRMA_ALG_COMP),
+ strxf_xfrmproto(req.xsinfo.id.proto));
+ exit(1);
+ }
+ if (!ealgop && !aeadop) {
+ fprintf(stderr, "ALGO-TYPE value \"%s\" or \"%s\" is required with XFRM-PROTO value \"%s\"\n",
+ strxf_algotype(XFRMA_ALG_CRYPT),
+ strxf_algotype(XFRMA_ALG_AEAD),
+ strxf_xfrmproto(req.xsinfo.id.proto));
+ exit(1);
+ }
+ break;
+ case IPPROTO_AH:
+ if (ealgop || aeadop || calgop) {
+ fprintf(stderr, "ALGO-TYPE values \"%s\", \"%s\", and \"%s\" are invalid with XFRM-PROTO value \"%s\"\n",
+ strxf_algotype(XFRMA_ALG_CRYPT),
+ strxf_algotype(XFRMA_ALG_AEAD),
+ strxf_algotype(XFRMA_ALG_COMP),
+ strxf_xfrmproto(req.xsinfo.id.proto));
+ exit(1);
+ }
+ if (!aalgop) {
+ fprintf(stderr, "ALGO-TYPE value \"%s\" or \"%s\" is required with XFRM-PROTO value \"%s\"\n",
+ strxf_algotype(XFRMA_ALG_AUTH),
+ strxf_algotype(XFRMA_ALG_AUTH_TRUNC),
+ strxf_xfrmproto(req.xsinfo.id.proto));
+ exit(1);
+ }
+ break;
+ case IPPROTO_COMP:
+ if (ealgop || aalgop || aeadop) {
+ fprintf(stderr, "ALGO-TYPE values \"%s\", \"%s\", \"%s\", and \"%s\" are invalid with XFRM-PROTO value \"%s\"\n",
+ strxf_algotype(XFRMA_ALG_CRYPT),
+ strxf_algotype(XFRMA_ALG_AUTH),
+ strxf_algotype(XFRMA_ALG_AUTH_TRUNC),
+ strxf_algotype(XFRMA_ALG_AEAD),
+ strxf_xfrmproto(req.xsinfo.id.proto));
+ exit(1);
+ }
+ if (!calgop) {
+ fprintf(stderr, "ALGO-TYPE value \"%s\" is required with XFRM-PROTO value \"%s\"\n",
+ strxf_algotype(XFRMA_ALG_COMP),
+ strxf_xfrmproto(req.xsinfo.id.proto));
+ exit(1);
+ }
+ break;
+ }
+ } else {
+ if (ealgop || aalgop || aeadop || calgop) {
+ fprintf(stderr, "ALGO is invalid with XFRM-PROTO value \"%s\"\n",
+ strxf_xfrmproto(req.xsinfo.id.proto));
+ exit(1);
+ }
+ }
+
+ if (xfrm_xfrmproto_is_ro(req.xsinfo.id.proto)) {
+ switch (req.xsinfo.mode) {
+ case XFRM_MODE_ROUTEOPTIMIZATION:
+ case XFRM_MODE_IN_TRIGGER:
+ break;
+ case 0:
+ fprintf(stderr, "\"mode\" is required with XFRM-PROTO value \"%s\"\n",
+ strxf_xfrmproto(req.xsinfo.id.proto));
+ exit(1);
+ default:
+ fprintf(stderr, "MODE value is invalid with XFRM-PROTO value \"%s\"\n",
+ strxf_xfrmproto(req.xsinfo.id.proto));
+ exit(1);
+ }
+
+ if (!coap) {
+ fprintf(stderr, "\"coa\" is required with XFRM-PROTO value \"%s\"\n",
+ strxf_xfrmproto(req.xsinfo.id.proto));
+ exit(1);
+ }
+ } else {
+ if (coap) {
+ fprintf(stderr, "\"coa\" is invalid with XFRM-PROTO value \"%s\"\n",
+ strxf_xfrmproto(req.xsinfo.id.proto));
+ exit(1);
+ }
+ }
+
+ if (rtnl_open_byproto(&rth, 0, NETLINK_XFRM) < 0)
+ exit(1);
+
+ if (req.xsinfo.family == AF_UNSPEC)
+ req.xsinfo.family = AF_INET;
+
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ exit(2);
+
+ rtnl_close(&rth);
+
+ return 0;
+}
+
+static int xfrm_state_allocspi(int argc, char **argv)
+{
+ struct rtnl_handle rth;
+ struct {
+ struct nlmsghdr n;
+ struct xfrm_userspi_info xspi;
+ char buf[RTA_BUF_SIZE];
+ } req;
+ char *idp = NULL;
+ char *minp = NULL;
+ char *maxp = NULL;
+ struct xfrm_mark mark = {0, 0};
+ char res_buf[NLMSG_BUF_SIZE];
+ struct nlmsghdr *res_n = (struct nlmsghdr *)res_buf;
+
+ memset(res_buf, 0, sizeof(res_buf));
+
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(req.xspi));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = XFRM_MSG_ALLOCSPI;
+ req.xspi.info.family = preferred_family;
+
+#if 0
+ req.xsinfo.lft.soft_byte_limit = XFRM_INF;
+ req.xsinfo.lft.hard_byte_limit = XFRM_INF;
+ req.xsinfo.lft.soft_packet_limit = XFRM_INF;
+ req.xsinfo.lft.hard_packet_limit = XFRM_INF;
+#endif
+
+ while (argc > 0) {
+ if (strcmp(*argv, "mode") == 0) {
+ NEXT_ARG();
+ xfrm_mode_parse(&req.xspi.info.mode, &argc, &argv);
+ } else if (strcmp(*argv, "mark") == 0) {
+ xfrm_parse_mark(&mark, &argc, &argv);
+ } else if (strcmp(*argv, "reqid") == 0) {
+ NEXT_ARG();
+ xfrm_reqid_parse(&req.xspi.info.reqid, &argc, &argv);
+ } else if (strcmp(*argv, "seq") == 0) {
+ NEXT_ARG();
+ xfrm_seq_parse(&req.xspi.info.seq, &argc, &argv);
+ } else if (strcmp(*argv, "min") == 0) {
+ if (minp)
+ duparg("min", *argv);
+ minp = *argv;
+
+ NEXT_ARG();
+
+ if (get_u32(&req.xspi.min, *argv, 0))
+ invarg("value after \"min\" is invalid", *argv);
+ } else if (strcmp(*argv, "max") == 0) {
+ if (maxp)
+ duparg("max", *argv);
+ maxp = *argv;
+
+ NEXT_ARG();
+
+ if (get_u32(&req.xspi.max, *argv, 0))
+ invarg("value after \"max\" is invalid", *argv);
+ } else {
+ /* try to assume ID */
+ if (idp)
+ invarg("unknown", *argv);
+ idp = *argv;
+
+ /* ID */
+ xfrm_id_parse(&req.xspi.info.saddr, &req.xspi.info.id,
+ &req.xspi.info.family, 0, &argc, &argv);
+ if (req.xspi.info.id.spi) {
+ fprintf(stderr, "\"spi\" is invalid\n");
+ exit(1);
+ }
+ if (preferred_family == AF_UNSPEC)
+ preferred_family = req.xspi.info.family;
+ }
+ argc--; argv++;
+ }
+
+ if (!idp) {
+ fprintf(stderr, "Not enough information: ID is required\n");
+ exit(1);
+ }
+
+ if (minp) {
+ if (!maxp) {
+ fprintf(stderr, "\"max\" is missing\n");
+ exit(1);
+ }
+ if (req.xspi.min > req.xspi.max) {
+ fprintf(stderr, "value after \"min\" is larger than value after \"max\"\n");
+ exit(1);
+ }
+ } else {
+ if (maxp) {
+ fprintf(stderr, "\"min\" is missing\n");
+ exit(1);
+ }
+
+ /* XXX: Default value defined in PF_KEY;
+ * See kernel's net/key/af_key.c(pfkey_getspi).
+ */
+ req.xspi.min = 0x100;
+ req.xspi.max = 0x0fffffff;
+
+ /* XXX: IPCOMP spi is 16-bits;
+ * See kernel's net/xfrm/xfrm_user(verify_userspi_info).
+ */
+ if (req.xspi.info.id.proto == IPPROTO_COMP)
+ req.xspi.max = 0xffff;
+ }
+
+ if (mark.m & mark.v) {
+ int r = addattr_l(&req.n, sizeof(req.buf), XFRMA_MARK,
+ (void *)&mark, sizeof(mark));
+ if (r < 0) {
+ fprintf(stderr, "XFRMA_MARK failed\n");
+ exit(1);
+ }
+ }
+
+ if (rtnl_open_byproto(&rth, 0, NETLINK_XFRM) < 0)
+ exit(1);
+
+ if (req.xspi.info.family == AF_UNSPEC)
+ req.xspi.info.family = AF_INET;
+
+
+ if (rtnl_talk(&rth, &req.n, res_n, sizeof(res_buf)) < 0)
+ exit(2);
+
+ if (xfrm_state_print(NULL, res_n, (void*)stdout) < 0) {
+ fprintf(stderr, "An error :-)\n");
+ exit(1);
+ }
+
+ rtnl_close(&rth);
+
+ return 0;
+}
+
+static int xfrm_state_filter_match(struct xfrm_usersa_info *xsinfo)
+{
+ if (!filter.use)
+ return 1;
+
+ if (filter.id_src_mask)
+ if (xfrm_addr_match(&xsinfo->saddr, &filter.xsinfo.saddr,
+ filter.id_src_mask))
+ return 0;
+ if (filter.id_dst_mask)
+ if (xfrm_addr_match(&xsinfo->id.daddr, &filter.xsinfo.id.daddr,
+ filter.id_dst_mask))
+ return 0;
+ if ((xsinfo->id.proto^filter.xsinfo.id.proto)&filter.id_proto_mask)
+ return 0;
+ if ((xsinfo->id.spi^filter.xsinfo.id.spi)&filter.id_spi_mask)
+ return 0;
+ if ((xsinfo->mode^filter.xsinfo.mode)&filter.mode_mask)
+ return 0;
+ if ((xsinfo->reqid^filter.xsinfo.reqid)&filter.reqid_mask)
+ return 0;
+ if (filter.state_flags_mask)
+ if ((xsinfo->flags & filter.xsinfo.flags) == 0)
+ return 0;
+
+ return 1;
+}
+
+int xfrm_state_print(const struct sockaddr_nl *who, struct nlmsghdr *n,
+ void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ struct rtattr * tb[XFRMA_MAX+1];
+ struct rtattr * rta;
+ struct xfrm_usersa_info *xsinfo = NULL;
+ struct xfrm_user_expire *xexp = NULL;
+ struct xfrm_usersa_id *xsid = NULL;
+ int len = n->nlmsg_len;
+
+ if (n->nlmsg_type != XFRM_MSG_NEWSA &&
+ n->nlmsg_type != XFRM_MSG_DELSA &&
+ n->nlmsg_type != XFRM_MSG_UPDSA &&
+ n->nlmsg_type != XFRM_MSG_EXPIRE) {
+ fprintf(stderr, "Not a state: %08x %08x %08x\n",
+ n->nlmsg_len, n->nlmsg_type, n->nlmsg_flags);
+ return 0;
+ }
+
+ if (n->nlmsg_type == XFRM_MSG_DELSA) {
+ /* Dont blame me for this .. Herbert made me do it */
+ xsid = NLMSG_DATA(n);
+ len -= NLMSG_SPACE(sizeof(*xsid));
+ } else if (n->nlmsg_type == XFRM_MSG_EXPIRE) {
+ xexp = NLMSG_DATA(n);
+ xsinfo = &xexp->state;
+ len -= NLMSG_SPACE(sizeof(*xexp));
+ } else {
+ xexp = NULL;
+ xsinfo = NLMSG_DATA(n);
+ len -= NLMSG_SPACE(sizeof(*xsinfo));
+ }
+
+ if (len < 0) {
+ fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+ return -1;
+ }
+
+ if (xsinfo && !xfrm_state_filter_match(xsinfo))
+ return 0;
+
+ if (n->nlmsg_type == XFRM_MSG_DELSA)
+ fprintf(fp, "Deleted ");
+ else if (n->nlmsg_type == XFRM_MSG_UPDSA)
+ fprintf(fp, "Updated ");
+ else if (n->nlmsg_type == XFRM_MSG_EXPIRE)
+ fprintf(fp, "Expired ");
+
+ if (n->nlmsg_type == XFRM_MSG_DELSA)
+ rta = XFRMSID_RTA(xsid);
+ else if (n->nlmsg_type == XFRM_MSG_EXPIRE)
+ rta = XFRMEXP_RTA(xexp);
+ else
+ rta = XFRMS_RTA(xsinfo);
+
+ parse_rtattr(tb, XFRMA_MAX, rta, len);
+
+ if (n->nlmsg_type == XFRM_MSG_DELSA) {
+ //xfrm_policy_id_print();
+
+ if (!tb[XFRMA_SA]) {
+ fprintf(stderr, "Buggy XFRM_MSG_DELSA: no XFRMA_SA\n");
+ return -1;
+ }
+ if (RTA_PAYLOAD(tb[XFRMA_SA]) < sizeof(*xsinfo)) {
+ fprintf(stderr, "Buggy XFRM_MSG_DELPOLICY: too short XFRMA_POLICY len\n");
+ return -1;
+ }
+ xsinfo = RTA_DATA(tb[XFRMA_SA]);
+ }
+
+ xfrm_state_info_print(xsinfo, tb, fp, NULL, NULL);
+
+ if (n->nlmsg_type == XFRM_MSG_EXPIRE) {
+ fprintf(fp, "\t");
+ fprintf(fp, "hard %u", xexp->hard);
+ fprintf(fp, "%s", _SL_);
+ }
+
+ if (oneline)
+ fprintf(fp, "\n");
+ fflush(fp);
+
+ return 0;
+}
+
+static int xfrm_state_get_or_delete(int argc, char **argv, int delete)
+{
+ struct rtnl_handle rth;
+ struct {
+ struct nlmsghdr n;
+ struct xfrm_usersa_id xsid;
+ char buf[RTA_BUF_SIZE];
+ } req;
+ struct xfrm_id id;
+ char *idp = NULL;
+ struct xfrm_mark mark = {0, 0};
+
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(req.xsid));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = delete ? XFRM_MSG_DELSA : XFRM_MSG_GETSA;
+ req.xsid.family = preferred_family;
+
+ while (argc > 0) {
+ xfrm_address_t saddr;
+
+ if (strcmp(*argv, "mark") == 0) {
+ xfrm_parse_mark(&mark, &argc, &argv);
+ } else {
+ if (idp)
+ invarg("unknown", *argv);
+ idp = *argv;
+
+ /* ID */
+ memset(&id, 0, sizeof(id));
+ memset(&saddr, 0, sizeof(saddr));
+ xfrm_id_parse(&saddr, &id, &req.xsid.family, 0,
+ &argc, &argv);
+
+ memcpy(&req.xsid.daddr, &id.daddr, sizeof(req.xsid.daddr));
+ req.xsid.spi = id.spi;
+ req.xsid.proto = id.proto;
+
+ addattr_l(&req.n, sizeof(req.buf), XFRMA_SRCADDR,
+ (void *)&saddr, sizeof(saddr));
+ }
+
+ argc--; argv++;
+ }
+
+ if (mark.m & mark.v) {
+ int r = addattr_l(&req.n, sizeof(req.buf), XFRMA_MARK,
+ (void *)&mark, sizeof(mark));
+ if (r < 0) {
+ fprintf(stderr, "XFRMA_MARK failed\n");
+ exit(1);
+ }
+ }
+
+ if (rtnl_open_byproto(&rth, 0, NETLINK_XFRM) < 0)
+ exit(1);
+
+ if (req.xsid.family == AF_UNSPEC)
+ req.xsid.family = AF_INET;
+
+ if (delete) {
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ exit(2);
+ } else {
+ char buf[NLMSG_BUF_SIZE];
+ struct nlmsghdr *res_n = (struct nlmsghdr *)buf;
+
+ memset(buf, 0, sizeof(buf));
+
+ if (rtnl_talk(&rth, &req.n, res_n, sizeof(req)) < 0)
+ exit(2);
+
+ if (xfrm_state_print(NULL, res_n, (void*)stdout) < 0) {
+ fprintf(stderr, "An error :-)\n");
+ exit(1);
+ }
+ }
+
+ rtnl_close(&rth);
+
+ return 0;
+}
+
+/*
+ * With an existing state of nlmsg, make new nlmsg for deleting the state
+ * and store it to buffer.
+ */
+static int xfrm_state_keep(const struct sockaddr_nl *who,
+ struct nlmsghdr *n,
+ void *arg)
+{
+ struct xfrm_buffer *xb = (struct xfrm_buffer *)arg;
+ struct rtnl_handle *rth = xb->rth;
+ struct xfrm_usersa_info *xsinfo = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct nlmsghdr *new_n;
+ struct xfrm_usersa_id *xsid;
+
+ if (n->nlmsg_type != XFRM_MSG_NEWSA) {
+ fprintf(stderr, "Not a state: %08x %08x %08x\n",
+ n->nlmsg_len, n->nlmsg_type, n->nlmsg_flags);
+ return 0;
+ }
+
+ len -= NLMSG_LENGTH(sizeof(*xsinfo));
+ if (len < 0) {
+ fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+ return -1;
+ }
+
+ if (!xfrm_state_filter_match(xsinfo))
+ return 0;
+
+ if (xb->offset > xb->size) {
+ fprintf(stderr, "State buffer overflow\n");
+ return -1;
+ }
+
+ new_n = (struct nlmsghdr *)(xb->buf + xb->offset);
+ new_n->nlmsg_len = NLMSG_LENGTH(sizeof(*xsid));
+ new_n->nlmsg_flags = NLM_F_REQUEST;
+ new_n->nlmsg_type = XFRM_MSG_DELSA;
+ new_n->nlmsg_seq = ++rth->seq;
+
+ xsid = NLMSG_DATA(new_n);
+ xsid->family = xsinfo->family;
+ memcpy(&xsid->daddr, &xsinfo->id.daddr, sizeof(xsid->daddr));
+ xsid->spi = xsinfo->id.spi;
+ xsid->proto = xsinfo->id.proto;
+
+ addattr_l(new_n, xb->size, XFRMA_SRCADDR, &xsinfo->saddr,
+ sizeof(xsid->daddr));
+
+ xb->offset += new_n->nlmsg_len;
+ xb->nlmsg_count ++;
+
+ return 0;
+}
+
+static int xfrm_state_list_or_deleteall(int argc, char **argv, int deleteall)
+{
+ char *idp = NULL;
+ struct rtnl_handle rth;
+
+ if(argc > 0)
+ filter.use = 1;
+ filter.xsinfo.family = preferred_family;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "mode") == 0) {
+ NEXT_ARG();
+ xfrm_mode_parse(&filter.xsinfo.mode, &argc, &argv);
+
+ filter.mode_mask = XFRM_FILTER_MASK_FULL;
+
+ } else if (strcmp(*argv, "reqid") == 0) {
+ NEXT_ARG();
+ xfrm_reqid_parse(&filter.xsinfo.reqid, &argc, &argv);
+
+ filter.reqid_mask = XFRM_FILTER_MASK_FULL;
+
+ } else if (strcmp(*argv, "flag") == 0) {
+ NEXT_ARG();
+ xfrm_state_flag_parse(&filter.xsinfo.flags, &argc, &argv);
+
+ filter.state_flags_mask = XFRM_FILTER_MASK_FULL;
+
+ } else {
+ if (idp)
+ invarg("unknown", *argv);
+ idp = *argv;
+
+ /* ID */
+ xfrm_id_parse(&filter.xsinfo.saddr, &filter.xsinfo.id,
+ &filter.xsinfo.family, 1, &argc, &argv);
+ if (preferred_family == AF_UNSPEC)
+ preferred_family = filter.xsinfo.family;
+ }
+ argc--; argv++;
+ }
+
+ if (rtnl_open_byproto(&rth, 0, NETLINK_XFRM) < 0)
+ exit(1);
+
+ if (deleteall) {
+ struct xfrm_buffer xb;
+ char buf[NLMSG_DELETEALL_BUF_SIZE];
+ int i;
+
+ xb.buf = buf;
+ xb.size = sizeof(buf);
+ xb.rth = &rth;
+
+ for (i = 0; ; i++) {
+ struct {
+ struct nlmsghdr n;
+ char buf[NLMSG_BUF_SIZE];
+ } req = {
+ .n.nlmsg_len = NLMSG_HDRLEN,
+ .n.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
+ .n.nlmsg_type = XFRM_MSG_GETSA,
+ .n.nlmsg_seq = rth.dump = ++rth.seq,
+ };
+
+ xb.offset = 0;
+ xb.nlmsg_count = 0;
+
+ if (show_stats > 1)
+ fprintf(stderr, "Delete-all round = %d\n", i);
+
+ if (rtnl_send(&rth, (void *)&req, req.n.nlmsg_len) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+
+ if (rtnl_dump_filter(&rth, xfrm_state_keep, &xb) < 0) {
+ fprintf(stderr, "Delete-all terminated\n");
+ exit(1);
+ }
+ if (xb.nlmsg_count == 0) {
+ if (show_stats > 1)
+ fprintf(stderr, "Delete-all completed\n");
+ break;
+ }
+
+ if (rtnl_send_check(&rth, xb.buf, xb.offset) < 0) {
+ perror("Failed to send delete-all request\n");
+ exit(1);
+ }
+ if (show_stats > 1)
+ fprintf(stderr, "Delete-all nlmsg count = %d\n", xb.nlmsg_count);
+
+ xb.offset = 0;
+ xb.nlmsg_count = 0;
+ }
+
+ } else {
+ struct xfrm_address_filter addrfilter = {
+ .saddr = filter.xsinfo.saddr,
+ .daddr = filter.xsinfo.id.daddr,
+ .family = filter.xsinfo.family,
+ .splen = filter.id_src_mask,
+ .dplen = filter.id_dst_mask,
+ };
+ struct {
+ struct nlmsghdr n;
+ char buf[NLMSG_BUF_SIZE];
+ } req = {
+ .n.nlmsg_len = NLMSG_HDRLEN,
+ .n.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
+ .n.nlmsg_type = XFRM_MSG_GETSA,
+ .n.nlmsg_seq = rth.dump = ++rth.seq,
+ };
+
+ if (filter.xsinfo.id.proto)
+ addattr8(&req.n, sizeof(req), XFRMA_PROTO,
+ filter.xsinfo.id.proto);
+ addattr_l(&req.n, sizeof(req), XFRMA_ADDRESS_FILTER,
+ &addrfilter, sizeof(addrfilter));
+
+ if (rtnl_send(&rth, (void *)&req, req.n.nlmsg_len) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+
+ if (rtnl_dump_filter(&rth, xfrm_state_print, stdout) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ exit(1);
+ }
+ }
+
+ rtnl_close(&rth);
+
+ exit(0);
+}
+
+static int print_sadinfo(struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ __u32 *f = NLMSG_DATA(n);
+ struct rtattr *tb[XFRMA_SAD_MAX+1];
+ struct rtattr *rta;
+ __u32 *cnt;
+
+ int len = n->nlmsg_len;
+
+ len -= NLMSG_LENGTH(sizeof(__u32));
+ if (len < 0) {
+ fprintf(stderr, "SADinfo: Wrong len %d\n", len);
+ return -1;
+ }
+
+ rta = XFRMSAPD_RTA(f);
+ parse_rtattr(tb, XFRMA_SAD_MAX, rta, len);
+
+ if (tb[XFRMA_SAD_CNT]) {
+ fprintf(fp,"\t SAD");
+ cnt = (__u32 *)RTA_DATA(tb[XFRMA_SAD_CNT]);
+ fprintf(fp," count %d", *cnt);
+ } else {
+ fprintf(fp,"BAD SAD info returned\n");
+ return -1;
+ }
+
+ if (show_stats) {
+ if (tb[XFRMA_SAD_HINFO]) {
+ struct xfrmu_sadhinfo *si;
+
+ if (RTA_PAYLOAD(tb[XFRMA_SAD_HINFO]) < sizeof(*si)) {
+ fprintf(fp,"BAD SAD length returned\n");
+ return -1;
+ }
+
+ si = RTA_DATA(tb[XFRMA_SAD_HINFO]);
+ fprintf(fp," (buckets ");
+ fprintf(fp,"count %d", si->sadhcnt);
+ fprintf(fp," Max %d", si->sadhmcnt);
+ fprintf(fp,")");
+ }
+ }
+ fprintf(fp,"\n");
+
+ return 0;
+}
+
+static int xfrm_sad_getinfo(int argc, char **argv)
+{
+ struct rtnl_handle rth;
+ struct {
+ struct nlmsghdr n;
+ __u32 flags;
+ char ans[64];
+ } req;
+
+ memset(&req, 0, sizeof(req));
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(req.flags));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = XFRM_MSG_GETSADINFO;
+ req.flags = 0XFFFFFFFF;
+
+ if (rtnl_open_byproto(&rth, 0, NETLINK_XFRM) < 0)
+ exit(1);
+
+ if (rtnl_talk(&rth, &req.n, &req.n, sizeof(req)) < 0)
+ exit(2);
+
+ print_sadinfo(&req.n, (void*)stdout);
+
+ rtnl_close(&rth);
+
+ return 0;
+}
+
+static int xfrm_state_flush(int argc, char **argv)
+{
+ struct rtnl_handle rth;
+ struct {
+ struct nlmsghdr n;
+ struct xfrm_usersa_flush xsf;
+ } req;
+ char *protop = NULL;
+
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(req.xsf));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = XFRM_MSG_FLUSHSA;
+ req.xsf.proto = 0;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "proto") == 0) {
+ int ret;
+
+ if (protop)
+ duparg("proto", *argv);
+ protop = *argv;
+
+ NEXT_ARG();
+
+ ret = xfrm_xfrmproto_getbyname(*argv);
+ if (ret < 0)
+ invarg("XFRM-PROTO value is invalid", *argv);
+
+ req.xsf.proto = (__u8)ret;
+ } else
+ invarg("unknown", *argv);
+
+ argc--; argv++;
+ }
+
+ if (rtnl_open_byproto(&rth, 0, NETLINK_XFRM) < 0)
+ exit(1);
+
+ if (show_stats > 1)
+ fprintf(stderr, "Flush state with XFRM-PROTO value \"%s\"\n",
+ strxf_xfrmproto(req.xsf.proto));
+
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ exit(2);
+
+ rtnl_close(&rth);
+
+ return 0;
+}
+
+int do_xfrm_state(int argc, char **argv)
+{
+ if (argc < 1)
+ return xfrm_state_list_or_deleteall(0, NULL, 0);
+
+ if (matches(*argv, "add") == 0)
+ return xfrm_state_modify(XFRM_MSG_NEWSA, 0,
+ argc-1, argv+1);
+ if (matches(*argv, "update") == 0)
+ return xfrm_state_modify(XFRM_MSG_UPDSA, 0,
+ argc-1, argv+1);
+ if (matches(*argv, "allocspi") == 0)
+ return xfrm_state_allocspi(argc-1, argv+1);
+ if (matches(*argv, "delete") == 0)
+ return xfrm_state_get_or_delete(argc-1, argv+1, 1);
+ if (matches(*argv, "deleteall") == 0 || matches(*argv, "delall") == 0)
+ return xfrm_state_list_or_deleteall(argc-1, argv+1, 1);
+ if (matches(*argv, "list") == 0 || matches(*argv, "show") == 0
+ || matches(*argv, "lst") == 0)
+ return xfrm_state_list_or_deleteall(argc-1, argv+1, 0);
+ if (matches(*argv, "get") == 0)
+ return xfrm_state_get_or_delete(argc-1, argv+1, 0);
+ if (matches(*argv, "flush") == 0)
+ return xfrm_state_flush(argc-1, argv+1);
+ if (matches(*argv, "count") == 0) {
+ return xfrm_sad_getinfo(argc, argv);
+ }
+ if (matches(*argv, "help") == 0)
+ usage();
+ fprintf(stderr, "Command \"%s\" is unknown, try \"ip xfrm state help\".\n", *argv);
+ exit(-1);
+}
diff --git a/iproute2/lib/Android.mk b/iproute2/lib/Android.mk
new file mode 100644
index 0000000..3fa5a5e
--- /dev/null
+++ b/iproute2/lib/Android.mk
@@ -0,0 +1,77 @@
+LOCAL_PATH := $(call my-dir)
+
+include $(CLEAR_VARS)
+LOCAL_SRC_FILES := \
+ color.c utils.c rt_names.c ll_types.c ll_proto.c ll_addr.c inet_proto.c \
+ mpls_pton.c namespace.c names.c libgenl.c libnetlink.c
+LOCAL_MODULE := libiprouteutil
+LOCAL_SYSTEM_SHARED_LIBRARIES := libc
+LOCAL_C_INCLUDES := $(LOCAL_PATH)/../include
+LOCAL_CFLAGS := -O2 -g -W -Wall \
+ -DCONFDIR=\"/data/misc/net\" \
+ -DHAVE_UNISTD_H \
+ -DHAVE_ERRNO_H \
+ -DHAVE_NETINET_IN_H \
+ -DHAVE_SYS_IOCTL_H \
+ -DHAVE_SYS_MMAN_H \
+ -DHAVE_SYS_MOUNT_H \
+ -DHAVE_SYS_PRCTL_H \
+ -DHAVE_SYS_RESOURCE_H \
+ -DHAVE_SYS_SELECT_H \
+ -DHAVE_SYS_STAT_H \
+ -DHAVE_SYS_TYPES_H \
+ -DHAVE_STDLIB_H \
+ -DHAVE_STRDUP \
+ -DHAVE_MMAP \
+ -DHAVE_UTIME_H \
+ -DHAVE_GETPAGESIZE \
+ -DHAVE_LSEEK64 \
+ -DHAVE_LSEEK64_PROTOTYPE \
+ -DHAVE_EXT2_IOCTLS \
+ -DHAVE_LINUX_FD_H \
+ -DHAVE_TYPE_SSIZE_T \
+ -DHAVE_SETNS \
+ -D_GNU_SOURCE \
+ -Wno-pointer-arith \
+ -Wno-sign-compare \
+ -Wno-unused-parameter \
+ -Werror
+
+# This is a work around for b/18403920
+LOCAL_LDFLAGS := -Wl,--no-gc-sections
+
+include $(BUILD_SHARED_LIBRARY)
+
+include $(CLEAR_VARS)
+LOCAL_SRC_FILES := ll_map.c libnetlink.c
+LOCAL_MODULE := libnetlink
+LOCAL_SYSTEM_SHARED_LIBRARIES := libc
+LOCAL_C_INCLUDES := $(LOCAL_PATH)/../include
+LOCAL_CFLAGS := -O2 -g -W -Wall \
+ -DHAVE_UNISTD_H \
+ -DHAVE_ERRNO_H \
+ -DHAVE_NETINET_IN_H \
+ -DHAVE_SYS_IOCTL_H \
+ -DHAVE_SYS_MMAN_H \
+ -DHAVE_SYS_MOUNT_H \
+ -DHAVE_SYS_PRCTL_H \
+ -DHAVE_SYS_RESOURCE_H \
+ -DHAVE_SYS_SELECT_H \
+ -DHAVE_SYS_STAT_H \
+ -DHAVE_SYS_TYPES_H \
+ -DHAVE_STDLIB_H \
+ -DHAVE_STRDUP \
+ -DHAVE_MMAP \
+ -DHAVE_UTIME_H \
+ -DHAVE_GETPAGESIZE \
+ -DHAVE_LSEEK64 \
+ -DHAVE_LSEEK64_PROTOTYPE \
+ -DHAVE_EXT2_IOCTLS \
+ -DHAVE_LINUX_FD_H \
+ -DHAVE_TYPE_SSIZE_T \
+ -Wno-pointer-arith \
+ -Wno-sign-compare \
+ -Wno-unused-parameter \
+ -Werror
+
+include $(BUILD_SHARED_LIBRARY)
diff --git a/iproute2/lib/MODULE_LICENSE_GPL b/iproute2/lib/MODULE_LICENSE_GPL
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/iproute2/lib/MODULE_LICENSE_GPL
diff --git a/iproute2/lib/Makefile b/iproute2/lib/Makefile
new file mode 100644
index 0000000..9d1307d
--- /dev/null
+++ b/iproute2/lib/Makefile
@@ -0,0 +1,27 @@
+include ../Config
+
+ifeq ($(IP_CONFIG_SETNS),y)
+ CFLAGS += -DHAVE_SETNS
+endif
+
+CFLAGS += -fPIC
+
+UTILOBJ = utils.o rt_names.o ll_types.o ll_proto.o ll_addr.o \
+ inet_proto.o namespace.o json_writer.o \
+ names.o color.o
+
+NLOBJ=libgenl.o ll_map.o libnetlink.o
+
+all: libnetlink.a libutil.a
+
+libnetlink.a: $(NLOBJ)
+ $(AR) rcs $@ $(NLOBJ)
+
+libutil.a: $(UTILOBJ) $(ADDLIB)
+ $(AR) rcs $@ $(UTILOBJ) $(ADDLIB)
+
+install:
+
+clean:
+ rm -f $(NLOBJ) $(UTILOBJ) $(ADDLIB) libnetlink.a libutil.a
+
diff --git a/iproute2/lib/NOTICE b/iproute2/lib/NOTICE
new file mode 100644
index 0000000..3912109
--- /dev/null
+++ b/iproute2/lib/NOTICE
@@ -0,0 +1,340 @@
+ GNU GENERAL PUBLIC LICENSE
+ Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.
+ 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+ Preamble
+
+ The licenses for most software are designed to take away your
+freedom to share and change it. By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users. This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it. (Some other Free Software Foundation software is covered by
+the GNU Library General Public License instead.) You can apply it to
+your programs, too.
+
+ When we speak of free software, we are referring to freedom, not
+price. Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+ To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+ For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have. You must make sure that they, too, receive or can get the
+source code. And you must show them these terms so they know their
+rights.
+
+ We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+ Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software. If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+ Finally, any free program is threatened constantly by software
+patents. We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary. To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+ The precise terms and conditions for copying, distribution and
+modification follow.
+
+ GNU GENERAL PUBLIC LICENSE
+ TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+ 0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License. The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language. (Hereinafter, translation is included without limitation in
+the term "modification".) Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope. The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+ 1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+ 2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+ a) You must cause the modified files to carry prominent notices
+ stating that you changed the files and the date of any change.
+
+ b) You must cause any work that you distribute or publish, that in
+ whole or in part contains or is derived from the Program or any
+ part thereof, to be licensed as a whole at no charge to all third
+ parties under the terms of this License.
+
+ c) If the modified program normally reads commands interactively
+ when run, you must cause it, when started running for such
+ interactive use in the most ordinary way, to print or display an
+ announcement including an appropriate copyright notice and a
+ notice that there is no warranty (or else, saying that you provide
+ a warranty) and that users may redistribute the program under
+ these conditions, and telling the user how to view a copy of this
+ License. (Exception: if the Program itself is interactive but
+ does not normally print such an announcement, your work based on
+ the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole. If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works. But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+ 3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+ a) Accompany it with the complete corresponding machine-readable
+ source code, which must be distributed under the terms of Sections
+ 1 and 2 above on a medium customarily used for software interchange; or,
+
+ b) Accompany it with a written offer, valid for at least three
+ years, to give any third party, for a charge no more than your
+ cost of physically performing source distribution, a complete
+ machine-readable copy of the corresponding source code, to be
+ distributed under the terms of Sections 1 and 2 above on a medium
+ customarily used for software interchange; or,
+
+ c) Accompany it with the information you received as to the offer
+ to distribute corresponding source code. (This alternative is
+ allowed only for noncommercial distribution and only if you
+ received the program in object code or executable form with such
+ an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it. For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable. However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+ 4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License. Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+ 5. You are not required to accept this License, since you have not
+signed it. However, nothing else grants you permission to modify or
+distribute the Program or its derivative works. These actions are
+prohibited by law if you do not accept this License. Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+ 6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions. You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+ 7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License. If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all. For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices. Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+ 8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded. In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+ 9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time. Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number. If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation. If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+ 10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission. For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this. Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+ NO WARRANTY
+
+ 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+ 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+ END OF TERMS AND CONDITIONS
+
+ How to Apply These Terms to Your New Programs
+
+ If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+ To do so, attach the following notices to the program. It is safest
+to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+ <one line to give the program's name and a brief idea of what it does.>
+ Copyright (C) <year> <name of author>
+
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 2 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+ Gnomovision version 69, Copyright (C) year name of author
+ Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+ This is free software, and you are welcome to redistribute it
+ under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License. Of course, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary. Here is a sample; alter the names:
+
+ Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+ `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+ <signature of Ty Coon>, 1 April 1989
+ Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs. If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library. If this is what you want to do, use the GNU Library General
+Public License instead of this License.
diff --git a/iproute2/lib/color.c b/iproute2/lib/color.c
new file mode 100644
index 0000000..8c9a48b
--- /dev/null
+++ b/iproute2/lib/color.c
@@ -0,0 +1,64 @@
+#include <stdio.h>
+#include <stdarg.h>
+
+#include "color.h"
+
+enum color {
+ C_RED,
+ C_GREEN,
+ C_YELLOW,
+ C_BLUE,
+ C_MAGENTA,
+ C_CYAN,
+ C_WHITE,
+ C_CLEAR
+};
+
+static const char * const color_codes[] = {
+ "\e[31m",
+ "\e[32m",
+ "\e[33m",
+ "\e[34m",
+ "\e[35m",
+ "\e[36m",
+ "\e[37m",
+ "\e[0m",
+ NULL,
+};
+
+static enum color attr_colors[] = {
+ C_CYAN,
+ C_YELLOW,
+ C_MAGENTA,
+ C_BLUE,
+ C_GREEN,
+ C_RED
+};
+
+static int color_is_enabled;
+
+void enable_color(void)
+{
+ color_is_enabled = 1;
+}
+
+int color_fprintf(FILE *fp, enum color_attr attr, const char *fmt, ...)
+{
+ int ret = 0;
+ va_list args;
+
+ va_start(args, fmt);
+
+ if (!color_is_enabled) {
+ ret = vfprintf(fp, fmt, args);
+ goto end;
+ }
+
+ ret += fprintf(fp, "%s", color_codes[attr_colors[attr]]);
+ ret += vfprintf(fp, fmt, args);
+ ret += fprintf(fp, "%s", color_codes[C_CLEAR]);
+
+end:
+ va_end(args);
+ return ret;
+}
diff --git a/iproute2/lib/coverity_model.c b/iproute2/lib/coverity_model.c
new file mode 100644
index 0000000..c896302
--- /dev/null
+++ b/iproute2/lib/coverity_model.c
@@ -0,0 +1,19 @@
+/*
+ * Coverity Scan model
+ *
+ * This is a modeling file for Coverity Scan. Modeling helps to avoid false
+ * positives.
+ *
+ * - A model file can't import any header files.
+ * - Therefore only some built-in primitives like int, char and void are
+ * available but not wchar_t, NULL etc.
+ * - Modeling doesn't need full structs and typedefs. Rudimentary structs
+ * and similar types are sufficient.
+ * - An uninitialized local pointer is not an error. It signifies that the
+ * variable could be either NULL or have some data.
+ *
+ * Coverity Scan doesn't pick up modifications automatically. The model file
+ * must be uploaded by an admin.
+ */
+
+
diff --git a/iproute2/lib/dnet_ntop.c b/iproute2/lib/dnet_ntop.c
new file mode 100644
index 0000000..507a7eb
--- /dev/null
+++ b/iproute2/lib/dnet_ntop.c
@@ -0,0 +1,102 @@
+#include <errno.h>
+#include <string.h>
+#include <sys/types.h>
+#include <netinet/in.h>
+
+#include "utils.h"
+
+static __inline__ u_int16_t dn_ntohs(u_int16_t addr)
+{
+ union {
+ u_int8_t byte[2];
+ u_int16_t word;
+ } u;
+
+ u.word = addr;
+ return ((u_int16_t)u.byte[0]) | (((u_int16_t)u.byte[1]) << 8);
+}
+
+static __inline__ int do_digit(char *str, u_int16_t *addr, u_int16_t scale, size_t *pos, size_t len, int *started)
+{
+ u_int16_t tmp = *addr / scale;
+
+ if (*pos == len)
+ return 1;
+
+ if (((tmp) > 0) || *started || (scale == 1)) {
+ *str = tmp + '0';
+ *started = 1;
+ (*pos)++;
+ *addr -= (tmp * scale);
+ }
+
+ return 0;
+}
+
+
+static const char *dnet_ntop1(const struct dn_naddr *dna, char *str, size_t len)
+{
+ u_int16_t addr, area;
+ size_t pos = 0;
+ int started = 0;
+
+ memcpy(&addr, dna->a_addr, sizeof(addr));
+ addr = dn_ntohs(addr);
+ area = addr >> 10;
+
+ if (dna->a_len != 2)
+ return NULL;
+
+ addr &= 0x03ff;
+
+ if (len == 0)
+ return str;
+
+ if (do_digit(str + pos, &area, 10, &pos, len, &started))
+ return str;
+
+ if (do_digit(str + pos, &area, 1, &pos, len, &started))
+ return str;
+
+ if (pos == len)
+ return str;
+
+ *(str + pos) = '.';
+ pos++;
+ started = 0;
+
+ if (do_digit(str + pos, &addr, 1000, &pos, len, &started))
+ return str;
+
+ if (do_digit(str + pos, &addr, 100, &pos, len, &started))
+ return str;
+
+ if (do_digit(str + pos, &addr, 10, &pos, len, &started))
+ return str;
+
+ if (do_digit(str + pos, &addr, 1, &pos, len, &started))
+ return str;
+
+ if (pos == len)
+ return str;
+
+ *(str + pos) = 0;
+
+ return str;
+}
+
+
+const char *dnet_ntop(int af, const void *addr, char *str, size_t len)
+{
+ switch(af) {
+ case AF_DECnet:
+ errno = 0;
+ return dnet_ntop1((struct dn_naddr *)addr, str, len);
+ default:
+ errno = EAFNOSUPPORT;
+ }
+
+ return NULL;
+}
+
+
diff --git a/iproute2/lib/dnet_pton.c b/iproute2/lib/dnet_pton.c
new file mode 100644
index 0000000..7385756
--- /dev/null
+++ b/iproute2/lib/dnet_pton.c
@@ -0,0 +1,74 @@
+#include <errno.h>
+#include <string.h>
+#include <sys/types.h>
+#include <netinet/in.h>
+
+#include "utils.h"
+
+static __inline__ u_int16_t dn_htons(u_int16_t addr)
+{
+ union {
+ u_int8_t byte[2];
+ u_int16_t word;
+ } u;
+
+ u.word = addr;
+ return ((u_int16_t)u.byte[0]) | (((u_int16_t)u.byte[1]) << 8);
+}
+
+
+static int dnet_num(const char *src, u_int16_t * dst)
+{
+ int rv = 0;
+ int tmp;
+ *dst = 0;
+
+ while ((tmp = *src++) != 0) {
+ tmp -= '0';
+ if ((tmp < 0) || (tmp > 9))
+ return rv;
+
+ rv++;
+ (*dst) *= 10;
+ (*dst) += tmp;
+ }
+
+ return rv;
+}
+
+static int dnet_pton1(const char *src, struct dn_naddr *dna)
+{
+ u_int16_t addr;
+ u_int16_t area = 0;
+ u_int16_t node = 0;
+ int pos;
+
+ pos = dnet_num(src, &area);
+ if ((pos == 0) || (area > 63) || (*(src + pos) != '.'))
+ return 0;
+ pos = dnet_num(src + pos + 1, &node);
+ if ((pos == 0) || (node > 1023))
+ return 0;
+ dna->a_len = 2;
+ addr = dn_htons((area << 10) | node);
+ memcpy(dna->a_addr, &addr, sizeof(addr));
+
+ return 1;
+}
+
+int dnet_pton(int af, const char *src, void *addr)
+{
+ int err;
+
+ switch (af) {
+ case AF_DECnet:
+ errno = 0;
+ err = dnet_pton1(src, (struct dn_naddr *)addr);
+ break;
+ default:
+ errno = EAFNOSUPPORT;
+ err = -1;
+ }
+
+ return err;
+}
diff --git a/iproute2/lib/inet_proto.c b/iproute2/lib/inet_proto.c
new file mode 100644
index 0000000..57a8351
--- /dev/null
+++ b/iproute2/lib/inet_proto.c
@@ -0,0 +1,71 @@
+/*
+ * inet_proto.c
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <netdb.h>
+#include <string.h>
+
+#include "rt_names.h"
+#include "utils.h"
+
+const char *inet_proto_n2a(int proto, char *buf, int len)
+{
+ static char ncache[16];
+ static int icache = -1;
+ struct protoent *pe;
+
+ if (proto == icache)
+ return ncache;
+
+ pe = getprotobynumber(proto);
+ if (pe) {
+ icache = proto;
+ strncpy(ncache, pe->p_name, 16);
+ strncpy(buf, pe->p_name, len);
+ return buf;
+ }
+ snprintf(buf, len, "ipproto-%d", proto);
+ return buf;
+}
+
+int inet_proto_a2n(const char *buf)
+{
+ static char ncache[16];
+ static int icache = -1;
+ struct protoent *pe;
+
+ if (icache>=0 && strcmp(ncache, buf) == 0)
+ return icache;
+
+ if (buf[0] >= '0' && buf[0] <= '9') {
+ __u8 ret;
+ if (get_u8(&ret, buf, 10))
+ return -1;
+ return ret;
+ }
+
+ pe = getprotobyname(buf);
+ if (pe) {
+ icache = pe->p_proto;
+ strncpy(ncache, pe->p_name, 16);
+ return pe->p_proto;
+ }
+ return -1;
+}
+
+
diff --git a/iproute2/lib/ipx_ntop.c b/iproute2/lib/ipx_ntop.c
new file mode 100644
index 0000000..1e46bc2
--- /dev/null
+++ b/iproute2/lib/ipx_ntop.c
@@ -0,0 +1,72 @@
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+#include "utils.h"
+
+static __inline__ int do_digit(char *str, u_int32_t addr, u_int32_t scale, size_t *pos, size_t len)
+{
+ u_int32_t tmp = addr >> (scale * 4);
+
+ if (*pos == len)
+ return 1;
+
+ tmp &= 0x0f;
+ if (tmp > 9)
+ *str = tmp + 'A' - 10;
+ else
+ *str = tmp + '0';
+ (*pos)++;
+
+ return 0;
+}
+
+static const char *ipx_ntop1(const struct ipx_addr *addr, char *str, size_t len)
+{
+ int i;
+ size_t pos = 0;
+
+ if (len == 0)
+ return str;
+
+ for(i = 7; i >= 0; i--)
+ if (do_digit(str + pos, ntohl(addr->ipx_net), i, &pos, len))
+ return str;
+
+ if (pos == len)
+ return str;
+
+ *(str + pos) = '.';
+ pos++;
+
+ for(i = 0; i < 6; i++) {
+ if (do_digit(str + pos, addr->ipx_node[i], 1, &pos, len))
+ return str;
+ if (do_digit(str + pos, addr->ipx_node[i], 0, &pos, len))
+ return str;
+ }
+
+ if (pos == len)
+ return str;
+
+ *(str + pos) = 0;
+
+ return str;
+}
+
+
+const char *ipx_ntop(int af, const void *addr, char *str, size_t len)
+{
+ switch(af) {
+ case AF_IPX:
+ errno = 0;
+ return ipx_ntop1((struct ipx_addr *)addr, str, len);
+ default:
+ errno = EAFNOSUPPORT;
+ }
+
+ return NULL;
+}
+
+
diff --git a/iproute2/lib/ipx_pton.c b/iproute2/lib/ipx_pton.c
new file mode 100644
index 0000000..3dca271
--- /dev/null
+++ b/iproute2/lib/ipx_pton.c
@@ -0,0 +1,108 @@
+#include <errno.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+#include "utils.h"
+
+static u_int32_t hexget(char c)
+{
+ if (c >= 'A' && c <= 'F')
+ return c - 'A' + 10;
+ if (c >= 'a' && c <= 'f')
+ return c - 'a' + 10;
+ if (c >= '0' && c <= '9')
+ return c - '0';
+
+ return 0xf0;
+}
+
+static int ipx_getnet(u_int32_t *net, const char *str)
+{
+ int i;
+ u_int32_t tmp;
+
+ for(i = 0; *str && (i < 8); i++) {
+
+ if ((tmp = hexget(*str)) & 0xf0) {
+ if (*str == '.')
+ return 0;
+ else
+ return -1;
+ }
+
+ str++;
+ (*net) <<= 4;
+ (*net) |= tmp;
+ }
+
+ if (*str == 0)
+ return 0;
+
+ return -1;
+}
+
+static int ipx_getnode(u_int8_t *node, const char *str)
+{
+ int i;
+ u_int32_t tmp;
+
+ for(i = 0; i < 6; i++) {
+ if ((tmp = hexget(*str++)) & 0xf0)
+ return -1;
+ node[i] = (u_int8_t)tmp;
+ node[i] <<= 4;
+ if ((tmp = hexget(*str++)) & 0xf0)
+ return -1;
+ node[i] |= (u_int8_t)tmp;
+ if (*str == ':')
+ str++;
+ }
+
+ return 0;
+}
+
+static int ipx_pton1(const char *src, struct ipx_addr *addr)
+{
+ char *sep = (char *)src;
+ int no_node = 0;
+
+ memset(addr, 0, sizeof(struct ipx_addr));
+
+ while(*sep && (*sep != '.'))
+ sep++;
+
+ if (*sep != '.')
+ no_node = 1;
+
+ if (ipx_getnet(&addr->ipx_net, src))
+ return 0;
+
+ addr->ipx_net = htonl(addr->ipx_net);
+
+ if (no_node)
+ return 1;
+
+ if (ipx_getnode(addr->ipx_node, sep + 1))
+ return 0;
+
+ return 1;
+}
+
+int ipx_pton(int af, const char *src, void *addr)
+{
+ int err;
+
+ switch (af) {
+ case AF_IPX:
+ errno = 0;
+ err = ipx_pton1(src, (struct ipx_addr *)addr);
+ break;
+ default:
+ errno = EAFNOSUPPORT;
+ err = -1;
+ }
+
+ return err;
+}
diff --git a/iproute2/lib/json_writer.c b/iproute2/lib/json_writer.c
new file mode 100644
index 0000000..2af16e1
--- /dev/null
+++ b/iproute2/lib/json_writer.c
@@ -0,0 +1,312 @@
+/*
+ * Simple streaming JSON writer
+ *
+ * This takes care of the annoying bits of JSON syntax like the commas
+ * after elements
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Stephen Hemminger <stephen@networkplumber.org>
+ */
+
+#include <stdio.h>
+#include <stdbool.h>
+#include <stdarg.h>
+#include <assert.h>
+#include <malloc.h>
+#include <inttypes.h>
+#include <stdint.h>
+
+#include "json_writer.h"
+
+struct json_writer {
+ FILE *out; /* output file */
+ unsigned depth; /* nesting */
+ bool pretty; /* optional whitepace */
+ char sep; /* either nul or comma */
+};
+
+/* indentation for pretty print */
+static void jsonw_indent(json_writer_t *self)
+{
+ unsigned i;
+ for (i = 0; i <= self->depth; ++i)
+ fputs(" ", self->out);
+}
+
+/* end current line and indent if pretty printing */
+static void jsonw_eol(json_writer_t *self)
+{
+ if (!self->pretty)
+ return;
+
+ putc('\n', self->out);
+ jsonw_indent(self);
+}
+
+/* If current object is not empty print a comma */
+static void jsonw_eor(json_writer_t *self)
+{
+ if (self->sep != '\0')
+ putc(self->sep, self->out);
+ self->sep = ',';
+}
+
+
+/* Output JSON encoded string */
+/* Handles C escapes, does not do Unicode */
+static void jsonw_puts(json_writer_t *self, const char *str)
+{
+ putc('"', self->out);
+ for (; *str; ++str)
+ switch (*str) {
+ case '\t':
+ fputs("\\t", self->out);
+ break;
+ case '\n':
+ fputs("\\n", self->out);
+ break;
+ case '\r':
+ fputs("\\r", self->out);
+ break;
+ case '\f':
+ fputs("\\f", self->out);
+ break;
+ case '\b':
+ fputs("\\b", self->out);
+ break;
+ case '\\':
+ fputs("\\n", self->out);
+ break;
+ case '"':
+ fputs("\\\"", self->out);
+ break;
+ case '\'':
+ fputs("\\\'", self->out);
+ break;
+ default:
+ putc(*str, self->out);
+ }
+ putc('"', self->out);
+}
+
+/* Create a new JSON stream */
+json_writer_t *jsonw_new(FILE *f)
+{
+ json_writer_t *self = malloc(sizeof(*self));
+ if (self) {
+ self->out = f;
+ self->depth = 0;
+ self->pretty = false;
+ self->sep = '\0';
+ putc('{', self->out);
+ }
+ return self;
+}
+
+/* End output to JSON stream */
+void jsonw_destroy(json_writer_t **self_p)
+{
+ json_writer_t *self = *self_p;
+
+ assert(self->depth == 0);
+ jsonw_eol(self);
+ fputs("}\n", self->out);
+ fflush(self->out);
+ free(self);
+ *self_p = NULL;
+}
+
+void jsonw_pretty(json_writer_t *self, bool on)
+{
+ self->pretty = on;
+}
+
+/* Basic blocks */
+static void jsonw_begin(json_writer_t *self, int c)
+{
+ jsonw_eor(self);
+ putc(c, self->out);
+ ++self->depth;
+ self->sep = '\0';
+}
+
+static void jsonw_end(json_writer_t *self, int c)
+{
+ assert(self->depth > 0);
+
+ --self->depth;
+ if (self->sep != '\0')
+ jsonw_eol(self);
+ putc(c, self->out);
+ self->sep = ',';
+}
+
+
+/* Add a JSON property name */
+void jsonw_name(json_writer_t *self, const char *name)
+{
+ jsonw_eor(self);
+ jsonw_eol(self);
+ self->sep = '\0';
+ jsonw_puts(self, name);
+ putc(':', self->out);
+ if (self->pretty)
+ putc(' ', self->out);
+}
+
+static void jsonw_printf(json_writer_t *self, const char *fmt, ...)
+{
+ va_list ap;
+
+ va_start(ap, fmt);
+ jsonw_eor(self);
+ vfprintf(self->out, fmt, ap);
+ va_end(ap);
+}
+
+/* Collections */
+void jsonw_start_object(json_writer_t *self)
+{
+ jsonw_begin(self, '{');
+}
+
+void jsonw_end_object(json_writer_t *self)
+{
+ jsonw_end(self, '}');
+}
+
+void jsonw_start_array(json_writer_t *self)
+{
+ jsonw_begin(self, '[');
+}
+
+void jsonw_end_array(json_writer_t *self)
+{
+ jsonw_end(self, ']');
+}
+
+/* JSON value types */
+void jsonw_string(json_writer_t *self, const char *value)
+{
+ jsonw_eor(self);
+ jsonw_puts(self, value);
+}
+
+void jsonw_bool(json_writer_t *self, bool val)
+{
+ jsonw_printf(self, "%s", val ? "true" : "false");
+}
+
+#ifdef notused
+void jsonw_null(json_writer_t *self)
+{
+ jsonw_printf(self, "null");
+}
+
+void jsonw_float(json_writer_t *self, double num)
+{
+ jsonw_printf(self, "%g", num);
+}
+#endif
+
+void jsonw_uint(json_writer_t *self, uint64_t num)
+{
+ jsonw_printf(self, "%"PRIu64, num);
+}
+
+void jsonw_int(json_writer_t *self, int64_t num)
+{
+ jsonw_printf(self, "%"PRId64, num);
+}
+
+/* Basic name/value objects */
+void jsonw_string_field(json_writer_t *self, const char *prop, const char *val)
+{
+ jsonw_name(self, prop);
+ jsonw_string(self, val);
+}
+
+void jsonw_bool_field(json_writer_t *self, const char *prop, bool val)
+{
+ jsonw_name(self, prop);
+ jsonw_bool(self, val);
+}
+
+#ifdef notused
+void jsonw_float_field(json_writer_t *self, const char *prop, double val)
+{
+ jsonw_name(self, prop);
+ jsonw_float(self, val);
+}
+#endif
+
+void jsonw_uint_field(json_writer_t *self, const char *prop, uint64_t num)
+{
+ jsonw_name(self, prop);
+ jsonw_uint(self, num);
+}
+
+void jsonw_int_field(json_writer_t *self, const char *prop, int64_t num)
+{
+ jsonw_name(self, prop);
+ jsonw_int(self, num);
+}
+
+#ifdef notused
+void jsonw_null_field(json_writer_t *self, const char *prop)
+{
+ jsonw_name(self, prop);
+ jsonw_null(self);
+}
+#endif
+
+#ifdef TEST
+int main(int argc, char **argv)
+{
+ json_writer_t *wr = jsonw_new(stdout);
+
+ jsonw_pretty(wr, true);
+ jsonw_name(wr, "Vyatta");
+ jsonw_start_object(wr);
+ jsonw_string_field(wr, "url", "http://vyatta.com");
+ jsonw_uint_field(wr, "downloads", 2000000ul);
+ jsonw_float_field(wr, "stock", 8.16);
+
+ jsonw_name(wr, "ARGV");
+ jsonw_start_array(wr);
+ while (--argc)
+ jsonw_string(wr, *++argv);
+ jsonw_end_array(wr);
+
+ jsonw_name(wr, "empty");
+ jsonw_start_array(wr);
+ jsonw_end_array(wr);
+
+ jsonw_name(wr, "NIL");
+ jsonw_start_object(wr);
+ jsonw_end_object(wr);
+
+ jsonw_null_field(wr, "my_null");
+
+ jsonw_name(wr, "special chars");
+ jsonw_start_array(wr);
+ jsonw_string_field(wr, "slash", "/");
+ jsonw_string_field(wr, "newline", "\n");
+ jsonw_string_field(wr, "tab", "\t");
+ jsonw_string_field(wr, "ff", "\f");
+ jsonw_string_field(wr, "quote", "\"");
+ jsonw_string_field(wr, "tick", "\'");
+ jsonw_string_field(wr, "backslash", "\\");
+ jsonw_end_array(wr);
+
+ jsonw_end_object(wr);
+
+ jsonw_destroy(&wr);
+ return 0;
+}
+
+#endif
diff --git a/iproute2/lib/libgenl.c b/iproute2/lib/libgenl.c
new file mode 100644
index 0000000..acb1478
--- /dev/null
+++ b/iproute2/lib/libgenl.c
@@ -0,0 +1,63 @@
+/*
+ * libgenl.c GENL library
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <linux/genetlink.h>
+#include "libgenl.h"
+
+static int genl_parse_getfamily(struct nlmsghdr *nlh)
+{
+ struct rtattr *tb[CTRL_ATTR_MAX + 1];
+ struct genlmsghdr *ghdr = NLMSG_DATA(nlh);
+ int len = nlh->nlmsg_len;
+ struct rtattr *attrs;
+
+ if (nlh->nlmsg_type != GENL_ID_CTRL) {
+ fprintf(stderr, "Not a controller message, nlmsg_len=%d "
+ "nlmsg_type=0x%x\n", nlh->nlmsg_len, nlh->nlmsg_type);
+ return -1;
+ }
+
+ len -= NLMSG_LENGTH(GENL_HDRLEN);
+
+ if (len < 0) {
+ fprintf(stderr, "wrong controller message len %d\n", len);
+ return -1;
+ }
+
+ if (ghdr->cmd != CTRL_CMD_NEWFAMILY) {
+ fprintf(stderr, "Unknown controller command %d\n", ghdr->cmd);
+ return -1;
+ }
+
+ attrs = (struct rtattr *) ((char *) ghdr + GENL_HDRLEN);
+ parse_rtattr(tb, CTRL_ATTR_MAX, attrs, len);
+
+ if (tb[CTRL_ATTR_FAMILY_ID] == NULL) {
+ fprintf(stderr, "Missing family id TLV\n");
+ return -1;
+ }
+
+ return rta_getattr_u16(tb[CTRL_ATTR_FAMILY_ID]);
+}
+
+int genl_resolve_family(struct rtnl_handle *grth, const char *family)
+{
+ GENL_REQUEST(req, 1024, GENL_ID_CTRL, 0, 0, CTRL_CMD_GETFAMILY,
+ NLM_F_REQUEST);
+
+ addattr_l(&req.n, sizeof(req), CTRL_ATTR_FAMILY_NAME,
+ family, strlen(family) + 1);
+
+ if (rtnl_talk(grth, &req.n, &req.n, sizeof(req)) < 0) {
+ fprintf(stderr, "Error talking to the kernel\n");
+ return -2;
+ }
+
+ return genl_parse_getfamily(&req.n);
+}
+
diff --git a/iproute2/lib/libnetlink.c b/iproute2/lib/libnetlink.c
new file mode 100644
index 0000000..d6b5fd3
--- /dev/null
+++ b/iproute2/lib/libnetlink.c
@@ -0,0 +1,840 @@
+/*
+ * libnetlink.c RTnetlink service routines.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <net/if_arp.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <string.h>
+#include <errno.h>
+#include <time.h>
+#include <sys/uio.h>
+
+#include "libnetlink.h"
+
+#ifndef SOL_NETLINK
+#define SOL_NETLINK 270
+#endif
+
+#ifndef MIN
+#define MIN(a, b) ((a) < (b) ? (a) : (b))
+#endif
+
+int rcvbuf = 1024 * 1024;
+
+void rtnl_close(struct rtnl_handle *rth)
+{
+ if (rth->fd >= 0) {
+ close(rth->fd);
+ rth->fd = -1;
+ }
+}
+
+int rtnl_open_byproto(struct rtnl_handle *rth, unsigned subscriptions,
+ int protocol)
+{
+ socklen_t addr_len;
+ int sndbuf = 32768;
+
+ memset(rth, 0, sizeof(*rth));
+
+ rth->proto = protocol;
+ rth->fd = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, protocol);
+ if (rth->fd < 0) {
+ perror("Cannot open netlink socket");
+ return -1;
+ }
+
+ if (setsockopt(rth->fd,SOL_SOCKET,SO_SNDBUF,&sndbuf,sizeof(sndbuf)) < 0) {
+ perror("SO_SNDBUF");
+ return -1;
+ }
+
+ if (setsockopt(rth->fd,SOL_SOCKET,SO_RCVBUF,&rcvbuf,sizeof(rcvbuf)) < 0) {
+ perror("SO_RCVBUF");
+ return -1;
+ }
+
+ memset(&rth->local, 0, sizeof(rth->local));
+ rth->local.nl_family = AF_NETLINK;
+ rth->local.nl_groups = subscriptions;
+
+ if (bind(rth->fd, (struct sockaddr*)&rth->local, sizeof(rth->local)) < 0) {
+ perror("Cannot bind netlink socket");
+ return -1;
+ }
+ addr_len = sizeof(rth->local);
+ if (getsockname(rth->fd, (struct sockaddr*)&rth->local, &addr_len) < 0) {
+ perror("Cannot getsockname");
+ return -1;
+ }
+ if (addr_len != sizeof(rth->local)) {
+ fprintf(stderr, "Wrong address length %d\n", addr_len);
+ return -1;
+ }
+ if (rth->local.nl_family != AF_NETLINK) {
+ fprintf(stderr, "Wrong address family %d\n", rth->local.nl_family);
+ return -1;
+ }
+ rth->seq = time(NULL);
+ return 0;
+}
+
+int rtnl_open(struct rtnl_handle *rth, unsigned subscriptions)
+{
+ return rtnl_open_byproto(rth, subscriptions, NETLINK_ROUTE);
+}
+
+int rtnl_wilddump_request(struct rtnl_handle *rth, int family, int type)
+{
+ return rtnl_wilddump_req_filter(rth, family, type, RTEXT_FILTER_VF);
+}
+
+int rtnl_wilddump_req_filter(struct rtnl_handle *rth, int family, int type,
+ __u32 filt_mask)
+{
+ struct {
+ struct nlmsghdr nlh;
+ struct ifinfomsg ifm;
+ /* attribute has to be NLMSG aligned */
+ struct rtattr ext_req __attribute__ ((aligned(NLMSG_ALIGNTO)));
+ __u32 ext_filter_mask;
+ } req;
+
+ memset(&req, 0, sizeof(req));
+ req.nlh.nlmsg_len = sizeof(req);
+ req.nlh.nlmsg_type = type;
+ req.nlh.nlmsg_flags = NLM_F_DUMP|NLM_F_REQUEST;
+ req.nlh.nlmsg_pid = 0;
+ req.nlh.nlmsg_seq = rth->dump = ++rth->seq;
+ req.ifm.ifi_family = family;
+
+ req.ext_req.rta_type = IFLA_EXT_MASK;
+ req.ext_req.rta_len = RTA_LENGTH(sizeof(__u32));
+ req.ext_filter_mask = filt_mask;
+
+ return send(rth->fd, (void*)&req, sizeof(req), 0);
+}
+
+int rtnl_send(struct rtnl_handle *rth, const void *buf, int len)
+{
+ return send(rth->fd, buf, len, 0);
+}
+
+int rtnl_send_check(struct rtnl_handle *rth, const void *buf, int len)
+{
+ struct nlmsghdr *h;
+ int status;
+ char resp[1024];
+
+ status = send(rth->fd, buf, len, 0);
+ if (status < 0)
+ return status;
+
+ /* Check for immediate errors */
+ status = recv(rth->fd, resp, sizeof(resp), MSG_DONTWAIT|MSG_PEEK);
+ if (status < 0) {
+ if (errno == EAGAIN)
+ return 0;
+ return -1;
+ }
+
+ for (h = (struct nlmsghdr *)resp; NLMSG_OK(h, status);
+ h = NLMSG_NEXT(h, status)) {
+ if (h->nlmsg_type == NLMSG_ERROR) {
+ struct nlmsgerr *err = (struct nlmsgerr*)NLMSG_DATA(h);
+ if (h->nlmsg_len < NLMSG_LENGTH(sizeof(struct nlmsgerr)))
+ fprintf(stderr, "ERROR truncated\n");
+ else
+ errno = -err->error;
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+int rtnl_dump_request(struct rtnl_handle *rth, int type, void *req, int len)
+{
+ struct nlmsghdr nlh;
+ struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK };
+ struct iovec iov[2] = {
+ { .iov_base = &nlh, .iov_len = sizeof(nlh) },
+ { .iov_base = req, .iov_len = len }
+ };
+ struct msghdr msg = {
+ .msg_name = &nladdr,
+ .msg_namelen = sizeof(nladdr),
+ .msg_iov = iov,
+ .msg_iovlen = 2,
+ };
+
+ nlh.nlmsg_len = NLMSG_LENGTH(len);
+ nlh.nlmsg_type = type;
+ nlh.nlmsg_flags = NLM_F_DUMP|NLM_F_REQUEST;
+ nlh.nlmsg_pid = 0;
+ nlh.nlmsg_seq = rth->dump = ++rth->seq;
+
+ return sendmsg(rth->fd, &msg, 0);
+}
+
+int rtnl_dump_request_n(struct rtnl_handle *rth, struct nlmsghdr *n)
+{
+ struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK };
+ struct iovec iov = {
+ .iov_base = (void*) n,
+ .iov_len = n->nlmsg_len
+ };
+ struct msghdr msg = {
+ .msg_name = &nladdr,
+ .msg_namelen = sizeof(nladdr),
+ .msg_iov = &iov,
+ .msg_iovlen = 1,
+ };
+
+ n->nlmsg_flags = NLM_F_DUMP|NLM_F_REQUEST;
+ n->nlmsg_pid = 0;
+ n->nlmsg_seq = rth->dump = ++rth->seq;
+
+ return sendmsg(rth->fd, &msg, 0);
+}
+
+int rtnl_dump_filter_l(struct rtnl_handle *rth,
+ const struct rtnl_dump_filter_arg *arg)
+{
+ struct sockaddr_nl nladdr;
+ struct iovec iov;
+ struct msghdr msg = {
+ .msg_name = &nladdr,
+ .msg_namelen = sizeof(nladdr),
+ .msg_iov = &iov,
+ .msg_iovlen = 1,
+ };
+ char buf[16384];
+ int dump_intr = 0;
+
+ iov.iov_base = buf;
+ while (1) {
+ int status;
+ const struct rtnl_dump_filter_arg *a;
+ int found_done = 0;
+ int msglen = 0;
+
+ iov.iov_len = sizeof(buf);
+ status = recvmsg(rth->fd, &msg, 0);
+
+ if (status < 0) {
+ if (errno == EINTR || errno == EAGAIN)
+ continue;
+ fprintf(stderr, "netlink receive error %s (%d)\n",
+ strerror(errno), errno);
+ return -1;
+ }
+
+ if (status == 0) {
+ fprintf(stderr, "EOF on netlink\n");
+ return -1;
+ }
+
+ if (rth->dump_fp)
+ fwrite(buf, 1, NLMSG_ALIGN(status), rth->dump_fp);
+
+ for (a = arg; a->filter; a++) {
+ struct nlmsghdr *h = (struct nlmsghdr*)buf;
+ msglen = status;
+
+ while (NLMSG_OK(h, msglen)) {
+ int err = 0;
+
+ h->nlmsg_flags &= ~a->nc_flags;
+
+ if (nladdr.nl_pid != 0 ||
+ h->nlmsg_pid != rth->local.nl_pid ||
+ h->nlmsg_seq != rth->dump)
+ goto skip_it;
+
+ if (h->nlmsg_flags & NLM_F_DUMP_INTR)
+ dump_intr = 1;
+
+ if (h->nlmsg_type == NLMSG_DONE) {
+ found_done = 1;
+ break; /* process next filter */
+ }
+ if (h->nlmsg_type == NLMSG_ERROR) {
+ struct nlmsgerr *err = (struct nlmsgerr*)NLMSG_DATA(h);
+ if (h->nlmsg_len < NLMSG_LENGTH(sizeof(struct nlmsgerr))) {
+ fprintf(stderr,
+ "ERROR truncated\n");
+ } else {
+ errno = -err->error;
+ if (rth->proto == NETLINK_SOCK_DIAG &&
+ (errno == ENOENT ||
+ errno == EOPNOTSUPP))
+ return -1;
+
+ perror("RTNETLINK answers");
+ }
+ return -1;
+ }
+
+ if (!rth->dump_fp) {
+ err = a->filter(&nladdr, h, a->arg1);
+ if (err < 0)
+ return err;
+ }
+
+skip_it:
+ h = NLMSG_NEXT(h, msglen);
+ }
+ }
+
+ if (found_done) {
+ if (dump_intr)
+ fprintf(stderr,
+ "Dump was interrupted and may be inconsistent.\n");
+ return 0;
+ }
+
+ if (msg.msg_flags & MSG_TRUNC) {
+ fprintf(stderr, "Message truncated\n");
+ continue;
+ }
+ if (msglen) {
+ fprintf(stderr, "!!!Remnant of size %d\n", msglen);
+ exit(1);
+ }
+ }
+}
+
+int rtnl_dump_filter_nc(struct rtnl_handle *rth,
+ rtnl_filter_t filter,
+ void *arg1, __u16 nc_flags)
+{
+ const struct rtnl_dump_filter_arg a[2] = {
+ { .filter = filter, .arg1 = arg1, .nc_flags = nc_flags, },
+ { .filter = NULL, .arg1 = NULL, .nc_flags = 0, },
+ };
+
+ return rtnl_dump_filter_l(rth, a);
+}
+
+int rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
+ struct nlmsghdr *answer, size_t maxlen)
+{
+ int status;
+ unsigned seq;
+ struct nlmsghdr *h;
+ struct sockaddr_nl nladdr;
+ struct iovec iov = {
+ .iov_base = (void*) n,
+ .iov_len = n->nlmsg_len
+ };
+ struct msghdr msg = {
+ .msg_name = &nladdr,
+ .msg_namelen = sizeof(nladdr),
+ .msg_iov = &iov,
+ .msg_iovlen = 1,
+ };
+ char buf[32768];
+
+ memset(&nladdr, 0, sizeof(nladdr));
+ nladdr.nl_family = AF_NETLINK;
+
+ n->nlmsg_seq = seq = ++rtnl->seq;
+
+ if (answer == NULL)
+ n->nlmsg_flags |= NLM_F_ACK;
+
+ status = sendmsg(rtnl->fd, &msg, 0);
+ if (status < 0) {
+ perror("Cannot talk to rtnetlink");
+ return -1;
+ }
+
+ memset(buf,0,sizeof(buf));
+
+ iov.iov_base = buf;
+ while (1) {
+ iov.iov_len = sizeof(buf);
+ status = recvmsg(rtnl->fd, &msg, 0);
+
+ if (status < 0) {
+ if (errno == EINTR || errno == EAGAIN)
+ continue;
+ fprintf(stderr, "netlink receive error %s (%d)\n",
+ strerror(errno), errno);
+ return -1;
+ }
+ if (status == 0) {
+ fprintf(stderr, "EOF on netlink\n");
+ return -1;
+ }
+ if (msg.msg_namelen != sizeof(nladdr)) {
+ fprintf(stderr, "sender address length == %d\n", msg.msg_namelen);
+ exit(1);
+ }
+ for (h = (struct nlmsghdr*)buf; status >= sizeof(*h); ) {
+ int len = h->nlmsg_len;
+ int l = len - sizeof(*h);
+
+ if (l < 0 || len>status) {
+ if (msg.msg_flags & MSG_TRUNC) {
+ fprintf(stderr, "Truncated message\n");
+ return -1;
+ }
+ fprintf(stderr, "!!!malformed message: len=%d\n", len);
+ exit(1);
+ }
+
+ if (nladdr.nl_pid != 0 ||
+ h->nlmsg_pid != rtnl->local.nl_pid ||
+ h->nlmsg_seq != seq) {
+ /* Don't forget to skip that message. */
+ status -= NLMSG_ALIGN(len);
+ h = (struct nlmsghdr*)((char*)h + NLMSG_ALIGN(len));
+ continue;
+ }
+
+ if (h->nlmsg_type == NLMSG_ERROR) {
+ struct nlmsgerr *err = (struct nlmsgerr*)NLMSG_DATA(h);
+ if (l < sizeof(struct nlmsgerr)) {
+ fprintf(stderr, "ERROR truncated\n");
+ } else if (!err->error) {
+ if (answer)
+ memcpy(answer, h,
+ MIN(maxlen, h->nlmsg_len));
+ return 0;
+ }
+
+ if (rtnl->proto != NETLINK_SOCK_DIAG)
+ fprintf(stderr,
+ "RTNETLINK answers: %s\n",
+ strerror(-err->error));
+ errno = -err->error;
+ return -1;
+ }
+
+ if (answer) {
+ memcpy(answer, h,
+ MIN(maxlen, h->nlmsg_len));
+ return 0;
+ }
+
+ fprintf(stderr, "Unexpected reply!!!\n");
+
+ status -= NLMSG_ALIGN(len);
+ h = (struct nlmsghdr*)((char*)h + NLMSG_ALIGN(len));
+ }
+
+ if (msg.msg_flags & MSG_TRUNC) {
+ fprintf(stderr, "Message truncated\n");
+ continue;
+ }
+
+ if (status) {
+ fprintf(stderr, "!!!Remnant of size %d\n", status);
+ exit(1);
+ }
+ }
+}
+
+int rtnl_listen_all_nsid(struct rtnl_handle *rth)
+{
+ unsigned int on = 1;
+
+ if (setsockopt(rth->fd, SOL_NETLINK, NETLINK_LISTEN_ALL_NSID, &on,
+ sizeof(on)) < 0) {
+ perror("NETLINK_LISTEN_ALL_NSID");
+ return -1;
+ }
+ rth->flags |= RTNL_HANDLE_F_LISTEN_ALL_NSID;
+ return 0;
+}
+
+int rtnl_listen(struct rtnl_handle *rtnl,
+ rtnl_listen_filter_t handler,
+ void *jarg)
+{
+ int status;
+ struct nlmsghdr *h;
+ struct sockaddr_nl nladdr;
+ struct iovec iov;
+ struct msghdr msg = {
+ .msg_name = &nladdr,
+ .msg_namelen = sizeof(nladdr),
+ .msg_iov = &iov,
+ .msg_iovlen = 1,
+ };
+ char buf[16384];
+ char cmsgbuf[BUFSIZ];
+
+ if (rtnl->flags & RTNL_HANDLE_F_LISTEN_ALL_NSID) {
+ msg.msg_control = &cmsgbuf;
+ msg.msg_controllen = sizeof(cmsgbuf);
+ }
+
+ memset(&nladdr, 0, sizeof(nladdr));
+ nladdr.nl_family = AF_NETLINK;
+ nladdr.nl_pid = 0;
+ nladdr.nl_groups = 0;
+
+ iov.iov_base = buf;
+ while (1) {
+ struct rtnl_ctrl_data ctrl;
+ struct cmsghdr *cmsg;
+
+ iov.iov_len = sizeof(buf);
+ status = recvmsg(rtnl->fd, &msg, 0);
+
+ if (status < 0) {
+ if (errno == EINTR || errno == EAGAIN)
+ continue;
+ fprintf(stderr, "netlink receive error %s (%d)\n",
+ strerror(errno), errno);
+ if (errno == ENOBUFS)
+ continue;
+ return -1;
+ }
+ if (status == 0) {
+ fprintf(stderr, "EOF on netlink\n");
+ return -1;
+ }
+ if (msg.msg_namelen != sizeof(nladdr)) {
+ fprintf(stderr, "Sender address length == %d\n", msg.msg_namelen);
+ exit(1);
+ }
+
+ if (rtnl->flags & RTNL_HANDLE_F_LISTEN_ALL_NSID) {
+ memset(&ctrl, 0, sizeof(ctrl));
+ ctrl.nsid = -1;
+ for (cmsg = CMSG_FIRSTHDR(&msg); cmsg;
+ cmsg = CMSG_NXTHDR(&msg, cmsg))
+ if (cmsg->cmsg_level == SOL_NETLINK &&
+ cmsg->cmsg_type == NETLINK_LISTEN_ALL_NSID &&
+ cmsg->cmsg_len == CMSG_LEN(sizeof(int))) {
+ int *data = (int *)CMSG_DATA(cmsg);
+
+ ctrl.nsid = *data;
+ }
+ }
+
+ for (h = (struct nlmsghdr*)buf; status >= sizeof(*h); ) {
+ int err;
+ int len = h->nlmsg_len;
+ int l = len - sizeof(*h);
+
+ if (l<0 || len>status) {
+ if (msg.msg_flags & MSG_TRUNC) {
+ fprintf(stderr, "Truncated message\n");
+ return -1;
+ }
+ fprintf(stderr, "!!!malformed message: len=%d\n", len);
+ exit(1);
+ }
+
+ err = handler(&nladdr, &ctrl, h, jarg);
+ if (err < 0)
+ return err;
+
+ status -= NLMSG_ALIGN(len);
+ h = (struct nlmsghdr*)((char*)h + NLMSG_ALIGN(len));
+ }
+ if (msg.msg_flags & MSG_TRUNC) {
+ fprintf(stderr, "Message truncated\n");
+ continue;
+ }
+ if (status) {
+ fprintf(stderr, "!!!Remnant of size %d\n", status);
+ exit(1);
+ }
+ }
+}
+
+int rtnl_from_file(FILE *rtnl, rtnl_listen_filter_t handler,
+ void *jarg)
+{
+ int status;
+ struct sockaddr_nl nladdr;
+ char buf[16384];
+ struct nlmsghdr *h = (void*)buf;
+
+ memset(&nladdr, 0, sizeof(nladdr));
+ nladdr.nl_family = AF_NETLINK;
+ nladdr.nl_pid = 0;
+ nladdr.nl_groups = 0;
+
+ while (1) {
+ int err, len;
+ int l;
+
+ status = fread(&buf, 1, sizeof(*h), rtnl);
+
+ if (status < 0) {
+ if (errno == EINTR)
+ continue;
+ perror("rtnl_from_file: fread");
+ return -1;
+ }
+ if (status == 0)
+ return 0;
+
+ len = h->nlmsg_len;
+ l = len - sizeof(*h);
+
+ if (l<0 || len>sizeof(buf)) {
+ fprintf(stderr, "!!!malformed message: len=%d @%lu\n",
+ len, ftell(rtnl));
+ return -1;
+ }
+
+ status = fread(NLMSG_DATA(h), 1, NLMSG_ALIGN(l), rtnl);
+
+ if (status < 0) {
+ perror("rtnl_from_file: fread");
+ return -1;
+ }
+ if (status < l) {
+ fprintf(stderr, "rtnl-from_file: truncated message\n");
+ return -1;
+ }
+
+ err = handler(&nladdr, NULL, h, jarg);
+ if (err < 0)
+ return err;
+ }
+}
+
+int addattr(struct nlmsghdr *n, int maxlen, int type)
+{
+ return addattr_l(n, maxlen, type, NULL, 0);
+}
+
+int addattr8(struct nlmsghdr *n, int maxlen, int type, __u8 data)
+{
+ return addattr_l(n, maxlen, type, &data, sizeof(__u8));
+}
+
+int addattr16(struct nlmsghdr *n, int maxlen, int type, __u16 data)
+{
+ return addattr_l(n, maxlen, type, &data, sizeof(__u16));
+}
+
+int addattr32(struct nlmsghdr *n, int maxlen, int type, __u32 data)
+{
+ return addattr_l(n, maxlen, type, &data, sizeof(__u32));
+}
+
+int addattr64(struct nlmsghdr *n, int maxlen, int type, __u64 data)
+{
+ return addattr_l(n, maxlen, type, &data, sizeof(__u64));
+}
+
+int addattrstrz(struct nlmsghdr *n, int maxlen, int type, const char *str)
+{
+ return addattr_l(n, maxlen, type, str, strlen(str)+1);
+}
+
+int addattr_l(struct nlmsghdr *n, int maxlen, int type, const void *data,
+ int alen)
+{
+ int len = RTA_LENGTH(alen);
+ struct rtattr *rta;
+
+ if (NLMSG_ALIGN(n->nlmsg_len) + RTA_ALIGN(len) > maxlen) {
+ fprintf(stderr, "addattr_l ERROR: message exceeded bound of %d\n",maxlen);
+ return -1;
+ }
+ rta = NLMSG_TAIL(n);
+ rta->rta_type = type;
+ rta->rta_len = len;
+ memcpy(RTA_DATA(rta), data, alen);
+ n->nlmsg_len = NLMSG_ALIGN(n->nlmsg_len) + RTA_ALIGN(len);
+ return 0;
+}
+
+int addraw_l(struct nlmsghdr *n, int maxlen, const void *data, int len)
+{
+ if (NLMSG_ALIGN(n->nlmsg_len) + NLMSG_ALIGN(len) > maxlen) {
+ fprintf(stderr, "addraw_l ERROR: message exceeded bound of %d\n",maxlen);
+ return -1;
+ }
+
+ memcpy(NLMSG_TAIL(n), data, len);
+ memset((void *) NLMSG_TAIL(n) + len, 0, NLMSG_ALIGN(len) - len);
+ n->nlmsg_len = NLMSG_ALIGN(n->nlmsg_len) + NLMSG_ALIGN(len);
+ return 0;
+}
+
+struct rtattr *addattr_nest(struct nlmsghdr *n, int maxlen, int type)
+{
+ struct rtattr *nest = NLMSG_TAIL(n);
+
+ addattr_l(n, maxlen, type, NULL, 0);
+ return nest;
+}
+
+int addattr_nest_end(struct nlmsghdr *n, struct rtattr *nest)
+{
+ nest->rta_len = (void *)NLMSG_TAIL(n) - (void *)nest;
+ return n->nlmsg_len;
+}
+
+struct rtattr *addattr_nest_compat(struct nlmsghdr *n, int maxlen, int type,
+ const void *data, int len)
+{
+ struct rtattr *start = NLMSG_TAIL(n);
+
+ addattr_l(n, maxlen, type, data, len);
+ addattr_nest(n, maxlen, type);
+ return start;
+}
+
+int addattr_nest_compat_end(struct nlmsghdr *n, struct rtattr *start)
+{
+ struct rtattr *nest = (void *)start + NLMSG_ALIGN(start->rta_len);
+
+ start->rta_len = (void *)NLMSG_TAIL(n) - (void *)start;
+ addattr_nest_end(n, nest);
+ return n->nlmsg_len;
+}
+
+int rta_addattr32(struct rtattr *rta, int maxlen, int type, __u32 data)
+{
+ int len = RTA_LENGTH(4);
+ struct rtattr *subrta;
+
+ if (RTA_ALIGN(rta->rta_len) + len > maxlen) {
+ fprintf(stderr,"rta_addattr32: Error! max allowed bound %d exceeded\n",maxlen);
+ return -1;
+ }
+ subrta = (struct rtattr*)(((char*)rta) + RTA_ALIGN(rta->rta_len));
+ subrta->rta_type = type;
+ subrta->rta_len = len;
+ memcpy(RTA_DATA(subrta), &data, 4);
+ rta->rta_len = NLMSG_ALIGN(rta->rta_len) + len;
+ return 0;
+}
+
+int rta_addattr_l(struct rtattr *rta, int maxlen, int type,
+ const void *data, int alen)
+{
+ struct rtattr *subrta;
+ int len = RTA_LENGTH(alen);
+
+ if (RTA_ALIGN(rta->rta_len) + RTA_ALIGN(len) > maxlen) {
+ fprintf(stderr,"rta_addattr_l: Error! max allowed bound %d exceeded\n",maxlen);
+ return -1;
+ }
+ subrta = (struct rtattr*)(((char*)rta) + RTA_ALIGN(rta->rta_len));
+ subrta->rta_type = type;
+ subrta->rta_len = len;
+ memcpy(RTA_DATA(subrta), data, alen);
+ rta->rta_len = NLMSG_ALIGN(rta->rta_len) + RTA_ALIGN(len);
+ return 0;
+}
+
+int rta_addattr8(struct rtattr *rta, int maxlen, int type, __u8 data)
+{
+ return rta_addattr_l(rta, maxlen, type, &data, sizeof(__u8));
+}
+
+int rta_addattr16(struct rtattr *rta, int maxlen, int type, __u16 data)
+{
+ return rta_addattr_l(rta, maxlen, type, &data, sizeof(__u16));
+}
+
+int rta_addattr64(struct rtattr *rta, int maxlen, int type, __u64 data)
+{
+ return rta_addattr_l(rta, maxlen, type, &data, sizeof(__u64));
+}
+
+struct rtattr *rta_nest(struct rtattr *rta, int maxlen, int type)
+{
+ struct rtattr *nest = RTA_TAIL(rta);
+
+ rta_addattr_l(rta, maxlen, type, NULL, 0);
+
+ return nest;
+}
+
+int rta_nest_end(struct rtattr *rta, struct rtattr *nest)
+{
+ nest->rta_len = (void *)RTA_TAIL(rta) - (void *)nest;
+
+ return rta->rta_len;
+}
+
+int parse_rtattr(struct rtattr *tb[], int max, struct rtattr *rta, int len)
+{
+ return parse_rtattr_flags(tb, max, rta, len, 0);
+}
+
+int parse_rtattr_flags(struct rtattr *tb[], int max, struct rtattr *rta,
+ int len, unsigned short flags)
+{
+ unsigned short type;
+
+ memset(tb, 0, sizeof(struct rtattr *) * (max + 1));
+ while (RTA_OK(rta, len)) {
+ type = rta->rta_type & ~flags;
+ if ((type <= max) && (!tb[type]))
+ tb[type] = rta;
+ rta = RTA_NEXT(rta,len);
+ }
+ if (len)
+ fprintf(stderr, "!!!Deficit %d, rta_len=%d\n", len, rta->rta_len);
+ return 0;
+}
+
+int parse_rtattr_byindex(struct rtattr *tb[], int max, struct rtattr *rta, int len)
+{
+ int i = 0;
+
+ memset(tb, 0, sizeof(struct rtattr *) * max);
+ while (RTA_OK(rta, len)) {
+ if (rta->rta_type <= max && i < max)
+ tb[i++] = rta;
+ rta = RTA_NEXT(rta,len);
+ }
+ if (len)
+ fprintf(stderr, "!!!Deficit %d, rta_len=%d\n", len, rta->rta_len);
+ return i;
+}
+
+struct rtattr *parse_rtattr_one(int type, struct rtattr *rta, int len)
+{
+ while (RTA_OK(rta, len)) {
+ if (rta->rta_type == type)
+ return rta;
+ rta = RTA_NEXT(rta, len);
+ }
+ if (len)
+ fprintf(stderr, "!!!Deficit %d, rta_len=%d\n", len, rta->rta_len);
+ return NULL;
+}
+
+int __parse_rtattr_nested_compat(struct rtattr *tb[], int max, struct rtattr *rta,
+ int len)
+{
+ if (RTA_PAYLOAD(rta) < len)
+ return -1;
+ if (RTA_PAYLOAD(rta) >= RTA_ALIGN(len) + sizeof(struct rtattr)) {
+ rta = RTA_DATA(rta) + RTA_ALIGN(len);
+ return parse_rtattr_nested(tb, max, rta);
+ }
+ memset(tb, 0, sizeof(struct rtattr *) * (max + 1));
+ return 0;
+}
diff --git a/iproute2/lib/ll_addr.c b/iproute2/lib/ll_addr.c
new file mode 100644
index 0000000..2ce9abf
--- /dev/null
+++ b/iproute2/lib/ll_addr.c
@@ -0,0 +1,97 @@
+/*
+ * ll_addr.c
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include <linux/netdevice.h>
+#include <linux/if_arp.h>
+#include <linux/sockios.h>
+
+#include "rt_names.h"
+#include "utils.h"
+
+
+const char *ll_addr_n2a(const unsigned char *addr, int alen, int type, char *buf, int blen)
+{
+ int i;
+ int l;
+
+ if (alen == 4 &&
+ (type == ARPHRD_TUNNEL || type == ARPHRD_SIT || type == ARPHRD_IPGRE)) {
+ return inet_ntop(AF_INET, addr, buf, blen);
+ }
+ if (alen == 16 && type == ARPHRD_TUNNEL6) {
+ return inet_ntop(AF_INET6, addr, buf, blen);
+ }
+ l = 0;
+ for (i=0; i<alen; i++) {
+ if (i==0) {
+ snprintf(buf+l, blen, "%02x", addr[i]);
+ blen -= 2;
+ l += 2;
+ } else {
+ snprintf(buf+l, blen, ":%02x", addr[i]);
+ blen -= 3;
+ l += 3;
+ }
+ }
+ return buf;
+}
+
+/*NB: lladdr is char * (rather than u8 *) because sa_data is char * (1003.1g) */
+int ll_addr_a2n(char *lladdr, int len, const char *arg)
+{
+ if (strchr(arg, '.')) {
+ inet_prefix pfx;
+ if (get_addr_1(&pfx, arg, AF_INET)) {
+ fprintf(stderr, "\"%s\" is invalid lladdr.\n", arg);
+ return -1;
+ }
+ if (len < 4)
+ return -1;
+ memcpy(lladdr, pfx.data, 4);
+ return 4;
+ } else {
+ int i;
+
+ for (i=0; i<len; i++) {
+ int temp;
+ char *cp = strchr(arg, ':');
+ if (cp) {
+ *cp = 0;
+ cp++;
+ }
+ if (sscanf(arg, "%x", &temp) != 1) {
+ fprintf(stderr, "\"%s\" is invalid lladdr.\n", arg);
+ return -1;
+ }
+ if (temp < 0 || temp > 255) {
+ fprintf(stderr, "\"%s\" is invalid lladdr.\n", arg);
+ return -1;
+ }
+ lladdr[i] = temp;
+ if (!cp)
+ break;
+ arg = cp;
+ }
+ return i+1;
+ }
+}
diff --git a/iproute2/lib/ll_map.c b/iproute2/lib/ll_map.c
new file mode 100644
index 0000000..c6f7027
--- /dev/null
+++ b/iproute2/lib/ll_map.c
@@ -0,0 +1,223 @@
+/*
+ * ll_map.c
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <string.h>
+#include <net/if.h>
+
+#include "libnetlink.h"
+#include "ll_map.h"
+#include "hlist.h"
+
+struct ll_cache {
+ struct hlist_node idx_hash;
+ struct hlist_node name_hash;
+ unsigned flags;
+ unsigned index;
+ unsigned short type;
+ char name[IFNAMSIZ];
+};
+
+#define IDXMAP_SIZE 1024
+static struct hlist_head idx_head[IDXMAP_SIZE];
+static struct hlist_head name_head[IDXMAP_SIZE];
+
+static struct ll_cache *ll_get_by_index(unsigned index)
+{
+ struct hlist_node *n;
+ unsigned h = index & (IDXMAP_SIZE - 1);
+
+ hlist_for_each(n, &idx_head[h]) {
+ struct ll_cache *im
+ = container_of(n, struct ll_cache, idx_hash);
+ if (im->index == index)
+ return im;
+ }
+
+ return NULL;
+}
+
+unsigned namehash(const char *str)
+{
+ unsigned hash = 5381;
+
+ while (*str)
+ hash = ((hash << 5) + hash) + *str++; /* hash * 33 + c */
+
+ return hash;
+}
+
+static struct ll_cache *ll_get_by_name(const char *name)
+{
+ struct hlist_node *n;
+ unsigned h = namehash(name) & (IDXMAP_SIZE - 1);
+
+ hlist_for_each(n, &name_head[h]) {
+ struct ll_cache *im
+ = container_of(n, struct ll_cache, name_hash);
+
+ if (strncmp(im->name, name, IFNAMSIZ) == 0)
+ return im;
+ }
+
+ return NULL;
+}
+
+int ll_remember_index(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg)
+{
+ unsigned int h;
+ const char *ifname;
+ struct ifinfomsg *ifi = NLMSG_DATA(n);
+ struct ll_cache *im;
+ struct rtattr *tb[IFLA_MAX+1];
+
+ if (n->nlmsg_type != RTM_NEWLINK && n->nlmsg_type != RTM_DELLINK)
+ return 0;
+
+ if (n->nlmsg_len < NLMSG_LENGTH(sizeof(ifi)))
+ return -1;
+
+ im = ll_get_by_index(ifi->ifi_index);
+ if (n->nlmsg_type == RTM_DELLINK) {
+ if (im) {
+ hlist_del(&im->name_hash);
+ hlist_del(&im->idx_hash);
+ free(im);
+ }
+ return 0;
+ }
+
+ memset(tb, 0, sizeof(tb));
+ parse_rtattr(tb, IFLA_MAX, IFLA_RTA(ifi), IFLA_PAYLOAD(n));
+ ifname = rta_getattr_str(tb[IFLA_IFNAME]);
+ if (ifname == NULL)
+ return 0;
+
+ if (im) {
+ /* change to existing entry */
+ if (strcmp(im->name, ifname) != 0) {
+ hlist_del(&im->name_hash);
+ h = namehash(ifname) & (IDXMAP_SIZE - 1);
+ hlist_add_head(&im->name_hash, &name_head[h]);
+ }
+
+ im->flags = ifi->ifi_flags;
+ return 0;
+ }
+
+ im = malloc(sizeof(*im));
+ if (im == NULL)
+ return 0;
+ im->index = ifi->ifi_index;
+ strcpy(im->name, ifname);
+ im->type = ifi->ifi_type;
+ im->flags = ifi->ifi_flags;
+
+ h = ifi->ifi_index & (IDXMAP_SIZE - 1);
+ hlist_add_head(&im->idx_hash, &idx_head[h]);
+
+ h = namehash(ifname) & (IDXMAP_SIZE - 1);
+ hlist_add_head(&im->name_hash, &name_head[h]);
+
+ return 0;
+}
+
+const char *ll_idx_n2a(unsigned idx, char *buf)
+{
+ const struct ll_cache *im;
+
+ if (idx == 0)
+ return "*";
+
+ im = ll_get_by_index(idx);
+ if (im)
+ return im->name;
+
+ if (if_indextoname(idx, buf) == NULL)
+ snprintf(buf, IFNAMSIZ, "if%d", idx);
+
+ return buf;
+}
+
+const char *ll_index_to_name(unsigned idx)
+{
+ static char nbuf[IFNAMSIZ];
+
+ return ll_idx_n2a(idx, nbuf);
+}
+
+int ll_index_to_type(unsigned idx)
+{
+ const struct ll_cache *im;
+
+ if (idx == 0)
+ return -1;
+
+ im = ll_get_by_index(idx);
+ return im ? im->type : -1;
+}
+
+int ll_index_to_flags(unsigned idx)
+{
+ const struct ll_cache *im;
+
+ if (idx == 0)
+ return 0;
+
+ im = ll_get_by_index(idx);
+ return im ? im->flags : -1;
+}
+
+unsigned ll_name_to_index(const char *name)
+{
+ const struct ll_cache *im;
+ unsigned idx;
+
+ if (name == NULL)
+ return 0;
+
+ im = ll_get_by_name(name);
+ if (im)
+ return im->index;
+
+ idx = if_nametoindex(name);
+ if (idx == 0)
+ sscanf(name, "if%u", &idx);
+ return idx;
+}
+
+void ll_init_map(struct rtnl_handle *rth)
+{
+ static int initialized;
+
+ if (initialized)
+ return;
+
+ if (rtnl_wilddump_request(rth, AF_UNSPEC, RTM_GETLINK) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+
+ if (rtnl_dump_filter(rth, ll_remember_index, NULL) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ exit(1);
+ }
+
+ initialized = 1;
+}
diff --git a/iproute2/lib/ll_proto.c b/iproute2/lib/ll_proto.c
new file mode 100644
index 0000000..d8df68c
--- /dev/null
+++ b/iproute2/lib/ll_proto.c
@@ -0,0 +1,118 @@
+/*
+ * ll_proto.c
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include <linux/netdevice.h>
+#include <linux/if_arp.h>
+#include <linux/sockios.h>
+
+#include "utils.h"
+#include "rt_names.h"
+
+
+#define __PF(f,n) { ETH_P_##f, #n },
+static const struct {
+ int id;
+ const char *name;
+} llproto_names[] = {
+__PF(LOOP,loop)
+__PF(PUP,pup)
+__PF(PUPAT,pupat)
+__PF(IP,ip)
+__PF(X25,x25)
+__PF(ARP,arp)
+__PF(BPQ,bpq)
+__PF(IEEEPUP,ieeepup)
+__PF(IEEEPUPAT,ieeepupat)
+__PF(DEC,dec)
+__PF(DNA_DL,dna_dl)
+__PF(DNA_RC,dna_rc)
+__PF(DNA_RT,dna_rt)
+__PF(LAT,lat)
+__PF(DIAG,diag)
+__PF(CUST,cust)
+__PF(SCA,sca)
+__PF(RARP,rarp)
+__PF(ATALK,atalk)
+__PF(AARP,aarp)
+__PF(IPX,ipx)
+__PF(IPV6,ipv6)
+__PF(PPP_DISC,ppp_disc)
+__PF(PPP_SES,ppp_ses)
+__PF(ATMMPOA,atmmpoa)
+__PF(ATMFATE,atmfate)
+__PF(802_3,802_3)
+__PF(AX25,ax25)
+__PF(ALL,all)
+__PF(802_2,802_2)
+__PF(SNAP,snap)
+__PF(DDCMP,ddcmp)
+__PF(WAN_PPP,wan_ppp)
+__PF(PPP_MP,ppp_mp)
+__PF(LOCALTALK,localtalk)
+__PF(CAN,can)
+__PF(PPPTALK,ppptalk)
+__PF(TR_802_2,tr_802_2)
+__PF(MOBITEX,mobitex)
+__PF(CONTROL,control)
+__PF(IRDA,irda)
+__PF(ECONET,econet)
+__PF(TIPC,tipc)
+__PF(AOE,aoe)
+__PF(8021Q,802.1Q)
+__PF(8021AD,802.1ad)
+
+{ 0x8100, "802.1Q" },
+{ 0x88cc, "LLDP" },
+{ ETH_P_IP, "ipv4" },
+};
+#undef __PF
+
+
+const char * ll_proto_n2a(unsigned short id, char *buf, int len)
+{
+ int i;
+
+ id = ntohs(id);
+
+ for (i=0; i<sizeof(llproto_names)/sizeof(llproto_names[0]); i++) {
+ if (llproto_names[i].id == id)
+ return llproto_names[i].name;
+ }
+ snprintf(buf, len, "[%d]", id);
+ return buf;
+}
+
+int ll_proto_a2n(unsigned short *id, const char *buf)
+{
+ int i;
+ for (i=0; i < sizeof(llproto_names)/sizeof(llproto_names[0]); i++) {
+ if (strcasecmp(llproto_names[i].name, buf) == 0) {
+ *id = htons(llproto_names[i].id);
+ return 0;
+ }
+ }
+ if (get_u16(id, buf, 0))
+ return -1;
+ *id = htons(*id);
+ return 0;
+}
diff --git a/iproute2/lib/ll_types.c b/iproute2/lib/ll_types.c
new file mode 100644
index 0000000..2c5bf8b
--- /dev/null
+++ b/iproute2/lib/ll_types.c
@@ -0,0 +1,121 @@
+/*
+ * ll_types.c
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include <linux/netdevice.h>
+#include <linux/if_arp.h>
+#include <linux/sockios.h>
+
+#include "rt_names.h"
+
+const char * ll_type_n2a(int type, char *buf, int len)
+{
+#define __PF(f,n) { ARPHRD_##f, #n },
+static const struct {
+ int type;
+ const char *name;
+} arphrd_names[] = {
+{ 0, "generic" },
+__PF(ETHER,ether)
+__PF(EETHER,eether)
+__PF(AX25,ax25)
+__PF(PRONET,pronet)
+__PF(CHAOS,chaos)
+__PF(IEEE802,ieee802)
+__PF(ARCNET,arcnet)
+__PF(APPLETLK,atalk)
+__PF(DLCI,dlci)
+__PF(ATM,atm)
+__PF(METRICOM,metricom)
+__PF(IEEE1394,ieee1394)
+__PF(INFINIBAND,infiniband)
+__PF(SLIP,slip)
+__PF(CSLIP,cslip)
+__PF(SLIP6,slip6)
+__PF(CSLIP6,cslip6)
+__PF(RSRVD,rsrvd)
+__PF(ADAPT,adapt)
+__PF(ROSE,rose)
+__PF(X25,x25)
+__PF(HWX25,hwx25)
+__PF(CAN,can)
+__PF(PPP,ppp)
+__PF(HDLC,hdlc)
+__PF(LAPB,lapb)
+__PF(DDCMP,ddcmp)
+__PF(RAWHDLC,rawhdlc)
+__PF(TUNNEL,ipip)
+__PF(TUNNEL6,tunnel6)
+__PF(FRAD,frad)
+__PF(SKIP,skip)
+__PF(LOOPBACK,loopback)
+__PF(LOCALTLK,ltalk)
+__PF(FDDI,fddi)
+__PF(BIF,bif)
+__PF(SIT,sit)
+__PF(IPDDP,ip/ddp)
+__PF(IPGRE,gre)
+__PF(PIMREG,pimreg)
+__PF(HIPPI,hippi)
+__PF(ASH,ash)
+__PF(ECONET,econet)
+__PF(IRDA,irda)
+__PF(FCPP,fcpp)
+__PF(FCAL,fcal)
+__PF(FCPL,fcpl)
+__PF(FCFABRIC,fcfb0)
+__PF(FCFABRIC+1,fcfb1)
+__PF(FCFABRIC+2,fcfb2)
+__PF(FCFABRIC+3,fcfb3)
+__PF(FCFABRIC+4,fcfb4)
+__PF(FCFABRIC+5,fcfb5)
+__PF(FCFABRIC+6,fcfb6)
+__PF(FCFABRIC+7,fcfb7)
+__PF(FCFABRIC+8,fcfb8)
+__PF(FCFABRIC+9,fcfb9)
+__PF(FCFABRIC+10,fcfb10)
+__PF(FCFABRIC+11,fcfb11)
+__PF(FCFABRIC+12,fcfb12)
+__PF(IEEE802_TR,tr)
+__PF(IEEE80211,ieee802.11)
+__PF(IEEE80211_PRISM,ieee802.11/prism)
+__PF(IEEE80211_RADIOTAP,ieee802.11/radiotap)
+__PF(IEEE802154, ieee802.15.4)
+__PF(PHONET, phonet)
+__PF(PHONET_PIPE, phonet_pipe)
+__PF(CAIF, caif)
+__PF(IP6GRE, gre6)
+__PF(NETLINK, netlink)
+
+__PF(NONE, none)
+__PF(VOID,void)
+};
+#undef __PF
+
+ int i;
+ for (i=0; i<sizeof(arphrd_names)/sizeof(arphrd_names[0]); i++) {
+ if (arphrd_names[i].type == type)
+ return arphrd_names[i].name;
+ }
+ snprintf(buf, len, "[%d]", type);
+ return buf;
+}
diff --git a/iproute2/lib/mpls_ntop.c b/iproute2/lib/mpls_ntop.c
new file mode 100644
index 0000000..945d6d5
--- /dev/null
+++ b/iproute2/lib/mpls_ntop.c
@@ -0,0 +1,48 @@
+#include <errno.h>
+#include <string.h>
+#include <sys/types.h>
+#include <netinet/in.h>
+#include <linux/mpls.h>
+
+#include "utils.h"
+
+static const char *mpls_ntop1(const struct mpls_label *addr, char *buf, size_t buflen)
+{
+ size_t destlen = buflen;
+ char *dest = buf;
+ int count;
+
+ for (count = 0; count < MPLS_MAX_LABELS; count++) {
+ uint32_t entry = ntohl(addr[count].entry);
+ uint32_t label = (entry & MPLS_LS_LABEL_MASK) >> MPLS_LS_LABEL_SHIFT;
+ int len = snprintf(dest, destlen, "%u", label);
+
+ /* Is this the end? */
+ if (entry & MPLS_LS_S_MASK)
+ return buf;
+
+
+ dest += len;
+ destlen -= len;
+ if (destlen) {
+ *dest = '/';
+ dest++;
+ destlen--;
+ }
+ }
+ errno = -E2BIG;
+ return NULL;
+}
+
+const char *mpls_ntop(int af, const void *addr, char *buf, size_t buflen)
+{
+ switch(af) {
+ case AF_MPLS:
+ errno = 0;
+ return mpls_ntop1((struct mpls_label *)addr, buf, buflen);
+ default:
+ errno = EAFNOSUPPORT;
+ }
+
+ return NULL;
+}
diff --git a/iproute2/lib/mpls_pton.c b/iproute2/lib/mpls_pton.c
new file mode 100644
index 0000000..bd448cf
--- /dev/null
+++ b/iproute2/lib/mpls_pton.c
@@ -0,0 +1,58 @@
+#include <errno.h>
+#include <string.h>
+#include <sys/types.h>
+#include <netinet/in.h>
+#include <linux/mpls.h>
+
+#include "utils.h"
+
+
+static int mpls_pton1(const char *name, struct mpls_label *addr)
+{
+ char *endp;
+ unsigned count;
+
+ for (count = 0; count < MPLS_MAX_LABELS; count++) {
+ unsigned long label;
+
+ label = strtoul(name, &endp, 0);
+ /* Fail when the label value is out or range */
+ if (label >= (1 << 20))
+ return 0;
+
+ if (endp == name) /* no digits */
+ return 0;
+
+ addr->entry = htonl(label << MPLS_LS_LABEL_SHIFT);
+ if (*endp == '\0') {
+ addr->entry |= htonl(1 << MPLS_LS_S_SHIFT);
+ return 1;
+ }
+
+ /* Bad character in the address */
+ if (*endp != '/')
+ return 0;
+
+ name = endp + 1;
+ addr += 1;
+ }
+ /* The address was too long */
+ return 0;
+}
+
+int mpls_pton(int af, const char *src, void *addr)
+{
+ int err;
+
+ switch(af) {
+ case AF_MPLS:
+ errno = 0;
+ err = mpls_pton1(src, (struct mpls_label *)addr);
+ break;
+ default:
+ errno = EAFNOSUPPORT;
+ err = -1;
+ }
+
+ return err;
+}
diff --git a/iproute2/lib/names.c b/iproute2/lib/names.c
new file mode 100644
index 0000000..3b5b0b1
--- /dev/null
+++ b/iproute2/lib/names.c
@@ -0,0 +1,183 @@
+/*
+ * names.c db names
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+#include <errno.h>
+
+#include "names.h"
+#include "utils.h"
+
+#define MAX_ENTRIES 256
+#define NAME_MAX_LEN 512
+
+static int read_id_name(FILE *fp, int *id, char *name)
+{
+ char buf[NAME_MAX_LEN];
+ int min, maj;
+
+ while (fgets(buf, sizeof(buf), fp)) {
+ char *p = buf;
+
+ while (*p == ' ' || *p == '\t')
+ p++;
+
+ if (*p == '#' || *p == '\n' || *p == 0)
+ continue;
+
+ if (sscanf(p, "%x:%x %s\n", &maj, &min, name) == 3) {
+ *id = (maj << 16) | min;
+ } else if (sscanf(p, "%x:%x %s #", &maj, &min, name) == 3) {
+ *id = (maj << 16) | min;
+ } else if (sscanf(p, "0x%x %s\n", id, name) != 2 &&
+ sscanf(p, "0x%x %s #", id, name) != 2 &&
+ sscanf(p, "%d %s\n", id, name) != 2 &&
+ sscanf(p, "%d %s #", id, name) != 2) {
+ strcpy(name, p);
+ return -1;
+ }
+ return 1;
+ }
+
+ return 0;
+}
+
+struct db_names *db_names_alloc(void)
+{
+ struct db_names *db;
+
+ db = malloc(sizeof(*db));
+ if (!db)
+ return NULL;
+
+ memset(db, 0, sizeof(*db));
+
+ db->size = MAX_ENTRIES;
+ db->hash = malloc(sizeof(struct db_entry *) * db->size);
+ memset(db->hash, 0, sizeof(struct db_entry *) * db->size);
+
+ return db;
+}
+
+int db_names_load(struct db_names *db, const char *path)
+{
+ struct db_entry *entry;
+ FILE *fp;
+ int id;
+ char namebuf[NAME_MAX_LEN] = {0};
+ int ret = -1;
+
+ fp = fopen(path, "r");
+ if (!fp)
+ return -ENOENT;
+
+ while ((ret = read_id_name(fp, &id, &namebuf[0]))) {
+ if (ret == -1) {
+ fprintf(stderr, "Database %s is corrupted at %s\n",
+ path, namebuf);
+ goto Exit;
+ }
+ ret = -1;
+
+ if (id < 0)
+ continue;
+
+ entry = malloc(sizeof(*entry));
+ if (!entry)
+ goto Exit;
+
+ entry->name = strdup(namebuf);
+ if (!entry->name) {
+ free(entry);
+ goto Exit;
+ }
+
+ entry->id = id;
+ entry->next = db->hash[id & (db->size - 1)];
+ db->hash[id & (db->size - 1)] = entry;
+ }
+ ret = 0;
+
+Exit:
+ fclose(fp);
+ return ret;
+}
+
+void db_names_free(struct db_names *db)
+{
+ int i;
+
+ if (!db)
+ return;
+
+ for (i = 0; i < db->size; i++) {
+ struct db_entry *entry = db->hash[i];
+
+ while (entry) {
+ struct db_entry *next = entry->next;
+
+ free(entry->name);
+ free(entry);
+ entry = next;
+ }
+ }
+
+ free(db->hash);
+ free(db);
+}
+
+char *id_to_name(struct db_names *db, int id, char *name)
+{
+ struct db_entry *entry;
+
+ if (!db)
+ return NULL;
+
+ entry = db->hash[id & (db->size - 1)];
+ while (entry && entry->id != id)
+ entry = entry->next;
+
+ if (entry) {
+ strncpy(name, entry->name, IDNAME_MAX);
+ return name;
+ }
+
+ snprintf(name, IDNAME_MAX, "%d", id);
+ return NULL;
+}
+
+int name_to_id(struct db_names *db, int *id, const char *name)
+{
+ struct db_entry *entry;
+ int i;
+
+ if (!db)
+ return -1;
+
+ if (db->cached && strcmp(db->cached->name, name) == 0) {
+ *id = db->cached->id;
+ return 0;
+ }
+
+ for (i = 0; i < db->size; i++) {
+ entry = db->hash[i];
+ while (entry && strcmp(entry->name, name))
+ entry = entry->next;
+
+ if (entry) {
+ db->cached = entry;
+ *id = entry->id;
+ return 0;
+ }
+ }
+
+ return -1;
+}
diff --git a/iproute2/lib/namespace.c b/iproute2/lib/namespace.c
new file mode 100644
index 0000000..30b5138
--- /dev/null
+++ b/iproute2/lib/namespace.c
@@ -0,0 +1,126 @@
+/*
+ * namespace.c
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <fcntl.h>
+#include <dirent.h>
+#include <limits.h>
+
+#include "utils.h"
+#include "namespace.h"
+
+static void bind_etc(const char *name)
+{
+ char etc_netns_path[PATH_MAX];
+ char netns_name[PATH_MAX];
+ char etc_name[PATH_MAX];
+ struct dirent *entry;
+ DIR *dir;
+
+ snprintf(etc_netns_path, sizeof(etc_netns_path), "%s/%s", NETNS_ETC_DIR, name);
+ dir = opendir(etc_netns_path);
+ if (!dir)
+ return;
+
+ while ((entry = readdir(dir)) != NULL) {
+ if (strcmp(entry->d_name, ".") == 0)
+ continue;
+ if (strcmp(entry->d_name, "..") == 0)
+ continue;
+ snprintf(netns_name, sizeof(netns_name), "%s/%s", etc_netns_path, entry->d_name);
+ snprintf(etc_name, sizeof(etc_name), "/etc/%s", entry->d_name);
+ if (mount(netns_name, etc_name, "none", MS_BIND, NULL) < 0) {
+ fprintf(stderr, "Bind %s -> %s failed: %s\n",
+ netns_name, etc_name, strerror(errno));
+ }
+ }
+ closedir(dir);
+}
+
+int netns_switch(char *name)
+{
+ char net_path[PATH_MAX];
+ int netns;
+
+ snprintf(net_path, sizeof(net_path), "%s/%s", NETNS_RUN_DIR, name);
+ netns = open(net_path, O_RDONLY | O_CLOEXEC);
+ if (netns < 0) {
+ fprintf(stderr, "Cannot open network namespace \"%s\": %s\n",
+ name, strerror(errno));
+ return -1;
+ }
+
+ if (setns(netns, CLONE_NEWNET) < 0) {
+ fprintf(stderr, "setting the network namespace \"%s\" failed: %s\n",
+ name, strerror(errno));
+ close(netns);
+ return -1;
+ }
+ close(netns);
+
+ if (unshare(CLONE_NEWNS) < 0) {
+ fprintf(stderr, "unshare failed: %s\n", strerror(errno));
+ return -1;
+ }
+ /* Don't let any mounts propagate back to the parent */
+ if (mount("", "/", "none", MS_SLAVE | MS_REC, NULL)) {
+ fprintf(stderr, "\"mount --make-rslave /\" failed: %s\n",
+ strerror(errno));
+ return -1;
+ }
+ /* Mount a version of /sys that describes the network namespace */
+ if (umount2("/sys", MNT_DETACH) < 0) {
+ fprintf(stderr, "umount of /sys failed: %s\n", strerror(errno));
+ return -1;
+ }
+ if (mount(name, "/sys", "sysfs", 0, NULL) < 0) {
+ fprintf(stderr, "mount of /sys failed: %s\n",strerror(errno));
+ return -1;
+ }
+
+ /* Setup bind mounts for config files in /etc */
+ bind_etc(name);
+ return 0;
+}
+
+int netns_get_fd(const char *name)
+{
+ char pathbuf[PATH_MAX];
+ const char *path, *ptr;
+
+ path = name;
+ ptr = strchr(name, '/');
+ if (!ptr) {
+ snprintf(pathbuf, sizeof(pathbuf), "%s/%s",
+ NETNS_RUN_DIR, name );
+ path = pathbuf;
+ }
+ return open(path, O_RDONLY);
+}
+
+int netns_foreach(int (*func)(char *nsname, void *arg), void *arg)
+{
+ DIR *dir;
+ struct dirent *entry;
+
+ dir = opendir(NETNS_RUN_DIR);
+ if (!dir)
+ return -1;
+
+ while ((entry = readdir(dir)) != NULL) {
+ if (strcmp(entry->d_name, ".") == 0)
+ continue;
+ if (strcmp(entry->d_name, "..") == 0)
+ continue;
+ if (func(entry->d_name, arg))
+ break;
+ }
+
+ closedir(dir);
+ return 0;
+}
diff --git a/iproute2/lib/rt_names.c b/iproute2/lib/rt_names.c
new file mode 100644
index 0000000..f6d17c0
--- /dev/null
+++ b/iproute2/lib/rt_names.c
@@ -0,0 +1,649 @@
+/*
+ * rt_names.c rtnetlink names DB.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <string.h>
+#include <sys/time.h>
+#include <sys/socket.h>
+#include <dirent.h>
+
+#include <asm/types.h>
+#include <linux/rtnetlink.h>
+
+#include "rt_names.h"
+#include "utils.h"
+
+#define NAME_MAX_LEN 512
+
+struct rtnl_hash_entry {
+ struct rtnl_hash_entry *next;
+ const char *name;
+ unsigned int id;
+};
+
+static int fread_id_name(FILE *fp, int *id, char *namebuf)
+{
+ char buf[NAME_MAX_LEN];
+
+ while (fgets(buf, sizeof(buf), fp)) {
+ char *p = buf;
+
+ while (*p == ' ' || *p == '\t')
+ p++;
+
+ if (*p == '#' || *p == '\n' || *p == 0)
+ continue;
+
+ if (sscanf(p, "0x%x %s\n", id, namebuf) != 2 &&
+ sscanf(p, "0x%x %s #", id, namebuf) != 2 &&
+ sscanf(p, "%d %s\n", id, namebuf) != 2 &&
+ sscanf(p, "%d %s #", id, namebuf) != 2) {
+ strcpy(namebuf, p);
+ return -1;
+ }
+ return 1;
+ }
+ return 0;
+}
+
+static void
+rtnl_hash_initialize(const char *file, struct rtnl_hash_entry **hash, int size)
+{
+ struct rtnl_hash_entry *entry;
+ FILE *fp;
+ int id;
+ char namebuf[NAME_MAX_LEN] = {0};
+ int ret;
+
+ fp = fopen(file, "r");
+ if (!fp)
+ return;
+
+ while ((ret = fread_id_name(fp, &id, &namebuf[0]))) {
+ if (ret == -1) {
+ fprintf(stderr, "Database %s is corrupted at %s\n",
+ file, namebuf);
+ fclose(fp);
+ return;
+ }
+
+ if (id < 0)
+ continue;
+
+ entry = malloc(sizeof(*entry));
+ entry->id = id;
+ entry->name = strdup(namebuf);
+ entry->next = hash[id & (size - 1)];
+ hash[id & (size - 1)] = entry;
+ }
+ fclose(fp);
+}
+
+static void rtnl_tab_initialize(const char *file, char **tab, int size)
+{
+ FILE *fp;
+ int id;
+ char namebuf[NAME_MAX_LEN] = {0};
+ int ret;
+
+ fp = fopen(file, "r");
+ if (!fp)
+ return;
+
+ while ((ret = fread_id_name(fp, &id, &namebuf[0]))) {
+ if (ret == -1) {
+ fprintf(stderr, "Database %s is corrupted at %s\n",
+ file, namebuf);
+ fclose(fp);
+ return;
+ }
+ if (id < 0 || id > size)
+ continue;
+
+ tab[id] = strdup(namebuf);
+ }
+ fclose(fp);
+}
+
+static char *rtnl_rtprot_tab[256] = {
+ [RTPROT_UNSPEC] = "none",
+ [RTPROT_REDIRECT] = "redirect",
+ [RTPROT_KERNEL] = "kernel",
+ [RTPROT_BOOT] = "boot",
+ [RTPROT_STATIC] = "static",
+
+ [RTPROT_GATED] = "gated",
+ [RTPROT_RA] = "ra",
+ [RTPROT_MRT] = "mrt",
+ [RTPROT_ZEBRA] = "zebra",
+ [RTPROT_BIRD] = "bird",
+ [RTPROT_BABEL] = "babel",
+ [RTPROT_DNROUTED] = "dnrouted",
+ [RTPROT_XORP] = "xorp",
+ [RTPROT_NTK] = "ntk",
+ [RTPROT_DHCP] = "dhcp",
+};
+
+
+static int rtnl_rtprot_init;
+
+static void rtnl_rtprot_initialize(void)
+{
+ rtnl_rtprot_init = 1;
+ rtnl_tab_initialize(CONFDIR "/rt_protos",
+ rtnl_rtprot_tab, 256);
+}
+
+const char *rtnl_rtprot_n2a(int id, char *buf, int len)
+{
+ if (id < 0 || id >= 256) {
+ snprintf(buf, len, "%u", id);
+ return buf;
+ }
+ if (!rtnl_rtprot_tab[id]) {
+ if (!rtnl_rtprot_init)
+ rtnl_rtprot_initialize();
+ }
+ if (rtnl_rtprot_tab[id])
+ return rtnl_rtprot_tab[id];
+ snprintf(buf, len, "%u", id);
+ return buf;
+}
+
+int rtnl_rtprot_a2n(__u32 *id, const char *arg)
+{
+ static char *cache;
+ static unsigned long res;
+ char *end;
+ int i;
+
+ if (cache && strcmp(cache, arg) == 0) {
+ *id = res;
+ return 0;
+ }
+
+ if (!rtnl_rtprot_init)
+ rtnl_rtprot_initialize();
+
+ for (i = 0; i < 256; i++) {
+ if (rtnl_rtprot_tab[i] &&
+ strcmp(rtnl_rtprot_tab[i], arg) == 0) {
+ cache = rtnl_rtprot_tab[i];
+ res = i;
+ *id = res;
+ return 0;
+ }
+ }
+
+ res = strtoul(arg, &end, 0);
+ if (!end || end == arg || *end || res > 255)
+ return -1;
+ *id = res;
+ return 0;
+}
+
+
+static char *rtnl_rtscope_tab[256] = {
+ [RT_SCOPE_UNIVERSE] = "global",
+ [RT_SCOPE_NOWHERE] = "nowhere",
+ [RT_SCOPE_HOST] = "host",
+ [RT_SCOPE_LINK] = "link",
+ [RT_SCOPE_SITE] = "site",
+};
+
+static int rtnl_rtscope_init;
+
+static void rtnl_rtscope_initialize(void)
+{
+ rtnl_rtscope_init = 1;
+ rtnl_tab_initialize(CONFDIR "/rt_scopes",
+ rtnl_rtscope_tab, 256);
+}
+
+const char *rtnl_rtscope_n2a(int id, char *buf, int len)
+{
+ if (id < 0 || id >= 256) {
+ snprintf(buf, len, "%d", id);
+ return buf;
+ }
+
+ if (!rtnl_rtscope_tab[id]) {
+ if (!rtnl_rtscope_init)
+ rtnl_rtscope_initialize();
+ }
+
+ if (rtnl_rtscope_tab[id])
+ return rtnl_rtscope_tab[id];
+
+ snprintf(buf, len, "%d", id);
+ return buf;
+}
+
+int rtnl_rtscope_a2n(__u32 *id, const char *arg)
+{
+ static const char *cache;
+ static unsigned long res;
+ char *end;
+ int i;
+
+ if (cache && strcmp(cache, arg) == 0) {
+ *id = res;
+ return 0;
+ }
+
+ if (!rtnl_rtscope_init)
+ rtnl_rtscope_initialize();
+
+ for (i = 0; i < 256; i++) {
+ if (rtnl_rtscope_tab[i] &&
+ strcmp(rtnl_rtscope_tab[i], arg) == 0) {
+ cache = rtnl_rtscope_tab[i];
+ res = i;
+ *id = res;
+ return 0;
+ }
+ }
+
+ res = strtoul(arg, &end, 0);
+ if (!end || end == arg || *end || res > 255)
+ return -1;
+ *id = res;
+ return 0;
+}
+
+
+static char *rtnl_rtrealm_tab[256] = {
+ "unknown",
+};
+
+static int rtnl_rtrealm_init;
+
+static void rtnl_rtrealm_initialize(void)
+{
+ rtnl_rtrealm_init = 1;
+ rtnl_tab_initialize(CONFDIR "/rt_realms",
+ rtnl_rtrealm_tab, 256);
+}
+
+const char *rtnl_rtrealm_n2a(int id, char *buf, int len)
+{
+ if (id < 0 || id >= 256) {
+ snprintf(buf, len, "%d", id);
+ return buf;
+ }
+ if (!rtnl_rtrealm_tab[id]) {
+ if (!rtnl_rtrealm_init)
+ rtnl_rtrealm_initialize();
+ }
+ if (rtnl_rtrealm_tab[id])
+ return rtnl_rtrealm_tab[id];
+ snprintf(buf, len, "%d", id);
+ return buf;
+}
+
+
+int rtnl_rtrealm_a2n(__u32 *id, const char *arg)
+{
+ static char *cache;
+ static unsigned long res;
+ char *end;
+ int i;
+
+ if (cache && strcmp(cache, arg) == 0) {
+ *id = res;
+ return 0;
+ }
+
+ if (!rtnl_rtrealm_init)
+ rtnl_rtrealm_initialize();
+
+ for (i = 0; i < 256; i++) {
+ if (rtnl_rtrealm_tab[i] &&
+ strcmp(rtnl_rtrealm_tab[i], arg) == 0) {
+ cache = rtnl_rtrealm_tab[i];
+ res = i;
+ *id = res;
+ return 0;
+ }
+ }
+
+ res = strtoul(arg, &end, 0);
+ if (!end || end == arg || *end || res > 255)
+ return -1;
+ *id = res;
+ return 0;
+}
+
+
+static struct rtnl_hash_entry dflt_table_entry = { .name = "default" };
+static struct rtnl_hash_entry main_table_entry = { .name = "main" };
+static struct rtnl_hash_entry local_table_entry = { .name = "local" };
+
+static struct rtnl_hash_entry *rtnl_rttable_hash[256] = {
+ [RT_TABLE_DEFAULT] = &dflt_table_entry,
+ [RT_TABLE_MAIN] = &main_table_entry,
+ [RT_TABLE_LOCAL] = &local_table_entry,
+};
+
+static int rtnl_rttable_init;
+
+static void rtnl_rttable_initialize(void)
+{
+ struct dirent *de;
+ DIR *d;
+ int i;
+
+ rtnl_rttable_init = 1;
+ for (i = 0; i < 256; i++) {
+ if (rtnl_rttable_hash[i])
+ rtnl_rttable_hash[i]->id = i;
+ }
+ rtnl_hash_initialize(CONFDIR "/rt_tables",
+ rtnl_rttable_hash, 256);
+
+ d = opendir(CONFDIR "/rt_tables.d");
+ if (!d)
+ return;
+
+ while ((de = readdir(d)) != NULL) {
+ char path[PATH_MAX];
+ size_t len;
+
+ if (*de->d_name == '.')
+ continue;
+
+ /* only consider filenames ending in '.conf' */
+ len = strlen(de->d_name);
+ if (len <= 5)
+ continue;
+ if (strcmp(de->d_name + len - 5, ".conf"))
+ continue;
+
+ snprintf(path, sizeof(path),
+ CONFDIR "/rt_tables.d/%s", de->d_name);
+ rtnl_hash_initialize(path, rtnl_rttable_hash, 256);
+ }
+ closedir(d);
+}
+
+const char *rtnl_rttable_n2a(__u32 id, char *buf, int len)
+{
+ struct rtnl_hash_entry *entry;
+
+ if (id > RT_TABLE_MAX) {
+ snprintf(buf, len, "%u", id);
+ return buf;
+ }
+ if (!rtnl_rttable_init)
+ rtnl_rttable_initialize();
+ entry = rtnl_rttable_hash[id & 255];
+ while (entry && entry->id != id)
+ entry = entry->next;
+ if (entry)
+ return entry->name;
+ snprintf(buf, len, "%u", id);
+ return buf;
+}
+
+int rtnl_rttable_a2n(__u32 *id, const char *arg)
+{
+ static const char *cache;
+ static unsigned long res;
+ struct rtnl_hash_entry *entry;
+ char *end;
+ __u32 i;
+
+ if (cache && strcmp(cache, arg) == 0) {
+ *id = res;
+ return 0;
+ }
+
+ if (!rtnl_rttable_init)
+ rtnl_rttable_initialize();
+
+ for (i = 0; i < 256; i++) {
+ entry = rtnl_rttable_hash[i];
+ while (entry && strcmp(entry->name, arg))
+ entry = entry->next;
+ if (entry) {
+ cache = entry->name;
+ res = entry->id;
+ *id = res;
+ return 0;
+ }
+ }
+
+ i = strtoul(arg, &end, 0);
+ if (!end || end == arg || *end || i > RT_TABLE_MAX)
+ return -1;
+ *id = i;
+ return 0;
+}
+
+
+static char *rtnl_rtdsfield_tab[256] = {
+ "0",
+};
+
+static int rtnl_rtdsfield_init;
+
+static void rtnl_rtdsfield_initialize(void)
+{
+ rtnl_rtdsfield_init = 1;
+ rtnl_tab_initialize(CONFDIR "/rt_dsfield",
+ rtnl_rtdsfield_tab, 256);
+}
+
+const char *rtnl_dsfield_n2a(int id, char *buf, int len)
+{
+ if (id < 0 || id >= 256) {
+ snprintf(buf, len, "%d", id);
+ return buf;
+ }
+ if (!rtnl_rtdsfield_tab[id]) {
+ if (!rtnl_rtdsfield_init)
+ rtnl_rtdsfield_initialize();
+ }
+ if (rtnl_rtdsfield_tab[id])
+ return rtnl_rtdsfield_tab[id];
+ snprintf(buf, len, "0x%02x", id);
+ return buf;
+}
+
+
+int rtnl_dsfield_a2n(__u32 *id, const char *arg)
+{
+ static char *cache;
+ static unsigned long res;
+ char *end;
+ int i;
+
+ if (cache && strcmp(cache, arg) == 0) {
+ *id = res;
+ return 0;
+ }
+
+ if (!rtnl_rtdsfield_init)
+ rtnl_rtdsfield_initialize();
+
+ for (i = 0; i < 256; i++) {
+ if (rtnl_rtdsfield_tab[i] &&
+ strcmp(rtnl_rtdsfield_tab[i], arg) == 0) {
+ cache = rtnl_rtdsfield_tab[i];
+ res = i;
+ *id = res;
+ return 0;
+ }
+ }
+
+ res = strtoul(arg, &end, 16);
+ if (!end || end == arg || *end || res > 255)
+ return -1;
+ *id = res;
+ return 0;
+}
+
+
+static struct rtnl_hash_entry dflt_group_entry = {
+ .id = 0, .name = "default"
+};
+
+static struct rtnl_hash_entry *rtnl_group_hash[256] = {
+ [0] = &dflt_group_entry,
+};
+
+static int rtnl_group_init;
+
+static void rtnl_group_initialize(void)
+{
+ rtnl_group_init = 1;
+ rtnl_hash_initialize(CONFDIR "/group",
+ rtnl_group_hash, 256);
+}
+
+int rtnl_group_a2n(int *id, const char *arg)
+{
+ static const char *cache;
+ static unsigned long res;
+ struct rtnl_hash_entry *entry;
+ char *end;
+ int i;
+
+ if (cache && strcmp(cache, arg) == 0) {
+ *id = res;
+ return 0;
+ }
+
+ if (!rtnl_group_init)
+ rtnl_group_initialize();
+
+ for (i = 0; i < 256; i++) {
+ entry = rtnl_group_hash[i];
+ while (entry && strcmp(entry->name, arg))
+ entry = entry->next;
+ if (entry) {
+ cache = entry->name;
+ res = entry->id;
+ *id = res;
+ return 0;
+ }
+ }
+
+ i = strtol(arg, &end, 0);
+ if (!end || end == arg || *end || i < 0)
+ return -1;
+ *id = i;
+ return 0;
+}
+
+const char *rtnl_group_n2a(int id, char *buf, int len)
+{
+ struct rtnl_hash_entry *entry;
+ int i;
+
+ if (!rtnl_group_init)
+ rtnl_group_initialize();
+
+ for (i = 0; i < 256; i++) {
+ entry = rtnl_group_hash[i];
+ if (entry && entry->id == id)
+ return entry->name;
+ }
+
+ snprintf(buf, len, "%d", id);
+ return buf;
+}
+
+static char *nl_proto_tab[256] = {
+ [NETLINK_ROUTE] = "rtnl",
+ [NETLINK_UNUSED] = "unused",
+ [NETLINK_USERSOCK] = "usersock",
+ [NETLINK_FIREWALL] = "fw",
+ [NETLINK_SOCK_DIAG] = "tcpdiag",
+ [NETLINK_NFLOG] = "nflog",
+ [NETLINK_XFRM] = "xfrm",
+ [NETLINK_SELINUX] = "selinux",
+ [NETLINK_ISCSI] = "iscsi",
+ [NETLINK_AUDIT] = "audit",
+ [NETLINK_FIB_LOOKUP] = "fiblookup",
+ [NETLINK_CONNECTOR] = "connector",
+ [NETLINK_NETFILTER] = "nft",
+ [NETLINK_IP6_FW] = "ip6fw",
+ [NETLINK_DNRTMSG] = "dec-rt",
+ [NETLINK_KOBJECT_UEVENT] = "uevent",
+ [NETLINK_GENERIC] = "genl",
+ [NETLINK_SCSITRANSPORT] = "scsi-trans",
+ [NETLINK_ECRYPTFS] = "ecryptfs",
+ [NETLINK_RDMA] = "rdma",
+ [NETLINK_CRYPTO] = "crypto",
+};
+
+static int nl_proto_init;
+
+static void nl_proto_initialize(void)
+{
+ nl_proto_init = 1;
+ rtnl_tab_initialize(CONFDIR "/nl_protos",
+ nl_proto_tab, 256);
+}
+
+const char *nl_proto_n2a(int id, char *buf, int len)
+{
+ if (id < 0 || id >= 256) {
+ snprintf(buf, len, "%u", id);
+ return buf;
+ }
+
+ if (!nl_proto_init)
+ nl_proto_initialize();
+
+ if (nl_proto_tab[id])
+ return nl_proto_tab[id];
+
+ snprintf(buf, len, "%u", id);
+ return buf;
+}
+
+int nl_proto_a2n(__u32 *id, const char *arg)
+{
+ static char *cache;
+ static unsigned long res;
+ char *end;
+ int i;
+
+ if (cache && strcmp(cache, arg) == 0) {
+ *id = res;
+ return 0;
+ }
+
+ if (!nl_proto_init)
+ nl_proto_initialize();
+
+ for (i = 0; i < 256; i++) {
+ if (nl_proto_tab[i] &&
+ strcmp(nl_proto_tab[i], arg) == 0) {
+ cache = nl_proto_tab[i];
+ res = i;
+ *id = res;
+ return 0;
+ }
+ }
+
+ res = strtoul(arg, &end, 0);
+ if (!end || end == arg || *end || res > 255)
+ return -1;
+ *id = res;
+ return 0;
+}
diff --git a/iproute2/lib/utils.c b/iproute2/lib/utils.c
new file mode 100644
index 0000000..46a20de
--- /dev/null
+++ b/iproute2/lib/utils.c
@@ -0,0 +1,1062 @@
+/*
+ * utils.c
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <math.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <string.h>
+#include <netdb.h>
+#include <arpa/inet.h>
+#include <asm/types.h>
+#include <linux/pkt_sched.h>
+#include <linux/param.h>
+#include <linux/if_arp.h>
+#include <linux/mpls.h>
+#include <time.h>
+#include <sys/time.h>
+#include <errno.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "namespace.h"
+
+int timestamp_short = 0;
+
+int get_integer(int *val, const char *arg, int base)
+{
+ long res;
+ char *ptr;
+
+ if (!arg || !*arg)
+ return -1;
+
+ res = strtol(arg, &ptr, base);
+
+ /* If there were no digits at all, strtol() stores
+ * the original value of nptr in *endptr (and returns 0).
+ * In particular, if *nptr is not '\0' but **endptr is '\0' on return,
+ * the entire string is valid.
+ */
+ if (!ptr || ptr == arg || *ptr)
+ return -1;
+
+ /* If an underflow occurs, strtol() returns LONG_MIN.
+ * If an overflow occurs, strtol() returns LONG_MAX.
+ * In both cases, errno is set to ERANGE.
+ */
+ if ((res == LONG_MAX || res == LONG_MIN) && errno == ERANGE)
+ return -1;
+
+ /* Outside range of int */
+ if (res < INT_MIN || res > INT_MAX)
+ return -1;
+
+ *val = res;
+ return 0;
+}
+
+int mask2bits(__u32 netmask)
+{
+ unsigned bits = 0;
+ __u32 mask = ntohl(netmask);
+ __u32 host = ~mask;
+
+ /* a valid netmask must be 2^n - 1 */
+ if ((host & (host + 1)) != 0)
+ return -1;
+
+ for (; mask; mask <<= 1)
+ ++bits;
+ return bits;
+}
+
+static int get_netmask(unsigned *val, const char *arg, int base)
+{
+ inet_prefix addr;
+
+ if (!get_unsigned(val, arg, base))
+ return 0;
+
+ /* try coverting dotted quad to CIDR */
+ if (!get_addr_1(&addr, arg, AF_INET) && addr.family == AF_INET) {
+ int b = mask2bits(addr.data[0]);
+
+ if (b >= 0) {
+ *val = b;
+ return 0;
+ }
+ }
+
+ return -1;
+}
+
+int get_unsigned(unsigned *val, const char *arg, int base)
+{
+ unsigned long res;
+ char *ptr;
+
+ if (!arg || !*arg)
+ return -1;
+
+ res = strtoul(arg, &ptr, base);
+
+ /* empty string or trailing non-digits */
+ if (!ptr || ptr == arg || *ptr)
+ return -1;
+
+ /* overflow */
+ if (res == ULONG_MAX && errno == ERANGE)
+ return -1;
+
+ /* out side range of unsigned */
+ if (res > UINT_MAX)
+ return -1;
+
+ *val = res;
+ return 0;
+}
+
+/*
+ * get_time_rtt is "translated" from a similar routine "get_time" in
+ * tc_util.c. We don't use the exact same routine because tc passes
+ * microseconds to the kernel and the callers of get_time_rtt want to
+ * pass milliseconds (standard unit for rtt values since 2.6.27), and
+ * have a different assumption for the units of a "raw" number.
+ */
+int get_time_rtt(unsigned *val, const char *arg, int *raw)
+{
+ double t;
+ unsigned long res;
+ char *p;
+
+ if (strchr(arg, '.') != NULL) {
+ t = strtod(arg, &p);
+ if (t < 0.0)
+ return -1;
+
+ /* no digits? */
+ if (!p || p == arg)
+ return -1;
+
+ /* over/underflow */
+ if ((t == HUGE_VALF || t == HUGE_VALL) && errno == ERANGE)
+ return -1;
+ } else {
+ res = strtoul(arg, &p, 0);
+
+ /* empty string? */
+ if (!p || p == arg)
+ return -1;
+
+ /* overflow */
+ if (res == ULONG_MAX && errno == ERANGE)
+ return -1;
+
+ t = (double)res;
+ }
+
+ if (p == arg)
+ return -1;
+ *raw = 1;
+
+ if (*p) {
+ *raw = 0;
+ if (strcasecmp(p, "s") == 0 || strcasecmp(p, "sec")==0 ||
+ strcasecmp(p, "secs")==0)
+ t *= 1000;
+ else if (strcasecmp(p, "ms") == 0 || strcasecmp(p, "msec")==0 ||
+ strcasecmp(p, "msecs") == 0)
+ t *= 1.0; /* allow suffix, do nothing */
+ else
+ return -1;
+ }
+
+ /* emulate ceil() without having to bring-in -lm and always be >= 1 */
+
+ *val = t;
+ if (*val < t)
+ *val += 1;
+
+ return 0;
+
+}
+
+int get_u64(__u64 *val, const char *arg, int base)
+{
+ unsigned long long res;
+ char *ptr;
+
+ if (!arg || !*arg)
+ return -1;
+
+ res = strtoull(arg, &ptr, base);
+
+ /* empty string or trailing non-digits */
+ if (!ptr || ptr == arg || *ptr)
+ return -1;
+
+ /* overflow */
+ if (res == ULLONG_MAX && errno == ERANGE)
+ return -1;
+
+ /* in case ULL is 128 bits */
+ if (res > 0xFFFFFFFFFFFFFFFFULL)
+ return -1;
+
+ *val = res;
+ return 0;
+}
+
+int get_u32(__u32 *val, const char *arg, int base)
+{
+ unsigned long res;
+ char *ptr;
+
+ if (!arg || !*arg)
+ return -1;
+ res = strtoul(arg, &ptr, base);
+
+ /* empty string or trailing non-digits */
+ if (!ptr || ptr == arg || *ptr)
+ return -1;
+
+ /* overflow */
+ if (res == ULONG_MAX && errno == ERANGE)
+ return -1;
+
+ /* in case UL > 32 bits */
+ if (res > 0xFFFFFFFFUL)
+ return -1;
+
+ *val = res;
+ return 0;
+}
+
+int get_u16(__u16 *val, const char *arg, int base)
+{
+ unsigned long res;
+ char *ptr;
+
+ if (!arg || !*arg)
+ return -1;
+ res = strtoul(arg, &ptr, base);
+
+ /* empty string or trailing non-digits */
+ if (!ptr || ptr == arg || *ptr)
+ return -1;
+
+ /* overflow */
+ if (res == ULONG_MAX && errno == ERANGE)
+ return -1;
+
+ if (res > 0xFFFFUL)
+ return -1;
+
+ *val = res;
+ return 0;
+}
+
+int get_u8(__u8 *val, const char *arg, int base)
+{
+ unsigned long res;
+ char *ptr;
+
+ if (!arg || !*arg)
+ return -1;
+
+ res = strtoul(arg, &ptr, base);
+ /* empty string or trailing non-digits */
+ if (!ptr || ptr == arg || *ptr)
+ return -1;
+
+ /* overflow */
+ if (res == ULONG_MAX && errno == ERANGE)
+ return -1;
+
+ if (res > 0xFFUL)
+ return -1;
+
+ *val = res;
+ return 0;
+}
+
+int get_s32(__s32 *val, const char *arg, int base)
+{
+ long res;
+ char *ptr;
+
+ errno = 0;
+
+ if (!arg || !*arg)
+ return -1;
+ res = strtol(arg, &ptr, base);
+ if (!ptr || ptr == arg || *ptr)
+ return -1;
+ if ((res == LONG_MIN || res == LONG_MAX) && errno == ERANGE)
+ return -1;
+ if (res > INT32_MAX || res < INT32_MIN)
+ return -1;
+
+ *val = res;
+ return 0;
+}
+
+int get_s16(__s16 *val, const char *arg, int base)
+{
+ long res;
+ char *ptr;
+
+ if (!arg || !*arg)
+ return -1;
+ res = strtol(arg, &ptr, base);
+ if (!ptr || ptr == arg || *ptr)
+ return -1;
+ if ((res == LONG_MIN || res == LONG_MAX) && errno == ERANGE)
+ return -1;
+ if (res > 0x7FFF || res < -0x8000)
+ return -1;
+
+ *val = res;
+ return 0;
+}
+
+int get_s8(__s8 *val, const char *arg, int base)
+{
+ long res;
+ char *ptr;
+
+ if (!arg || !*arg)
+ return -1;
+ res = strtol(arg, &ptr, base);
+ if (!ptr || ptr == arg || *ptr)
+ return -1;
+ if ((res == LONG_MIN || res == LONG_MAX) && errno == ERANGE)
+ return -1;
+ if (res > 0x7F || res < -0x80)
+ return -1;
+ *val = res;
+ return 0;
+}
+
+/* This uses a non-standard parsing (ie not inet_aton, or inet_pton)
+ * because of legacy choice to parse 10.8 as 10.8.0.0 not 10.0.0.8
+ */
+static int get_addr_ipv4(__u8 *ap, const char *cp)
+{
+ int i;
+
+ for (i = 0; i < 4; i++) {
+ unsigned long n;
+ char *endp;
+
+ n = strtoul(cp, &endp, 0);
+ if (n > 255)
+ return -1; /* bogus network value */
+
+ if (endp == cp) /* no digits */
+ return -1;
+
+ ap[i] = n;
+
+ if (*endp == '\0')
+ break;
+
+ if (i == 3 || *endp != '.')
+ return -1; /* extra characters */
+ cp = endp + 1;
+ }
+
+ return 1;
+}
+
+int get_addr64(__u64 *ap, const char *cp)
+{
+ int i;
+
+ union {
+ __u16 v16[4];
+ __u64 v64;
+ } val;
+
+ for (i = 0; i < 4; i++) {
+ unsigned long n;
+ char *endp;
+
+ n = strtoul(cp, &endp, 16);
+ if (n > 0xffff)
+ return -1; /* bogus network value */
+
+ if (endp == cp) /* no digits */
+ return -1;
+
+ val.v16[i] = htons(n);
+
+ if (*endp == '\0')
+ break;
+
+ if (i == 3 || *endp != ':')
+ return -1; /* extra characters */
+ cp = endp + 1;
+ }
+
+ *ap = val.v64;
+
+ return 1;
+}
+
+int get_addr_1(inet_prefix *addr, const char *name, int family)
+{
+ memset(addr, 0, sizeof(*addr));
+
+ if (strcmp(name, "default") == 0 ||
+ strcmp(name, "all") == 0 ||
+ strcmp(name, "any") == 0) {
+ if ((family == AF_DECnet) || (family == AF_MPLS))
+ return -1;
+ addr->family = family;
+ addr->bytelen = (family == AF_INET6 ? 16 : 4);
+ addr->bitlen = -1;
+ return 0;
+ }
+
+ if (family == AF_PACKET) {
+ int len;
+ len = ll_addr_a2n((char *)&addr->data, sizeof(addr->data), name);
+ if (len < 0)
+ return -1;
+
+ addr->family = AF_PACKET;
+ addr->bytelen = len;
+ addr->bitlen = len * 8;
+ return 0;
+ }
+
+ if (strchr(name, ':')) {
+ addr->family = AF_INET6;
+ if (family != AF_UNSPEC && family != AF_INET6)
+ return -1;
+ if (inet_pton(AF_INET6, name, addr->data) <= 0)
+ return -1;
+ addr->bytelen = 16;
+ addr->bitlen = -1;
+ return 0;
+ }
+
+#ifndef ANDROID
+ if (family == AF_DECnet) {
+ struct dn_naddr dna;
+ addr->family = AF_DECnet;
+ if (dnet_pton(AF_DECnet, name, &dna) <= 0)
+ return -1;
+ memcpy(addr->data, dna.a_addr, 2);
+ addr->bytelen = 2;
+ addr->bitlen = -1;
+ return 0;
+ }
+#endif
+
+ if (family == AF_MPLS) {
+ int i;
+ addr->family = AF_MPLS;
+ if (mpls_pton(AF_MPLS, name, addr->data) <= 0)
+ return -1;
+ addr->bytelen = 4;
+ addr->bitlen = 20;
+ /* How many bytes do I need? */
+ for (i = 0; i < 8; i++) {
+ if (ntohl(addr->data[i]) & MPLS_LS_S_MASK) {
+ addr->bytelen = (i + 1)*4;
+ break;
+ }
+ }
+ return 0;
+ }
+
+ addr->family = AF_INET;
+ if (family != AF_UNSPEC && family != AF_INET)
+ return -1;
+
+ if (get_addr_ipv4((__u8 *)addr->data, name) <= 0)
+ return -1;
+
+ addr->bytelen = 4;
+ addr->bitlen = -1;
+ return 0;
+}
+
+int af_bit_len(int af)
+{
+ switch (af) {
+ case AF_INET6:
+ return 128;
+ case AF_INET:
+ return 32;
+ case AF_DECnet:
+ return 16;
+ case AF_IPX:
+ return 80;
+ case AF_MPLS:
+ return 20;
+ }
+
+ return 0;
+}
+
+int af_byte_len(int af)
+{
+ return af_bit_len(af) / 8;
+}
+
+int get_prefix_1(inet_prefix *dst, char *arg, int family)
+{
+ int err;
+ unsigned plen;
+ char *slash;
+
+ memset(dst, 0, sizeof(*dst));
+
+ if (strcmp(arg, "default") == 0 ||
+ strcmp(arg, "any") == 0 ||
+ strcmp(arg, "all") == 0) {
+ if ((family == AF_DECnet) || (family == AF_MPLS))
+ return -1;
+ dst->family = family;
+ dst->bytelen = 0;
+ dst->bitlen = 0;
+ return 0;
+ }
+
+ slash = strchr(arg, '/');
+ if (slash)
+ *slash = 0;
+
+ err = get_addr_1(dst, arg, family);
+ if (err == 0) {
+ dst->bitlen = af_bit_len(dst->family);
+
+ if (slash) {
+ if (get_netmask(&plen, slash+1, 0)
+ || plen > dst->bitlen) {
+ err = -1;
+ goto done;
+ }
+ dst->flags |= PREFIXLEN_SPECIFIED;
+ dst->bitlen = plen;
+ }
+ }
+done:
+ if (slash)
+ *slash = '/';
+ return err;
+}
+
+int get_addr(inet_prefix *dst, const char *arg, int family)
+{
+ if (get_addr_1(dst, arg, family)) {
+ fprintf(stderr, "Error: %s address is expected rather than \"%s\".\n",
+ family_name(family) ,arg);
+ exit(1);
+ }
+ return 0;
+}
+
+int get_prefix(inet_prefix *dst, char *arg, int family)
+{
+ if (family == AF_PACKET) {
+ fprintf(stderr, "Error: \"%s\" may be inet prefix, but it is not allowed in this context.\n", arg);
+ exit(1);
+ }
+ if (get_prefix_1(dst, arg, family)) {
+ fprintf(stderr, "Error: %s prefix is expected rather than \"%s\".\n",
+ family_name(family) ,arg);
+ exit(1);
+ }
+ return 0;
+}
+
+__u32 get_addr32(const char *name)
+{
+ inet_prefix addr;
+ if (get_addr_1(&addr, name, AF_INET)) {
+ fprintf(stderr, "Error: an IP address is expected rather than \"%s\"\n", name);
+ exit(1);
+ }
+ return addr.data[0];
+}
+
+void incomplete_command(void)
+{
+ fprintf(stderr, "Command line is not complete. Try option \"help\"\n");
+ exit(-1);
+}
+
+void missarg(const char *key)
+{
+ fprintf(stderr, "Error: argument \"%s\" is required\n", key);
+ exit(-1);
+}
+
+void invarg(const char *msg, const char *arg)
+{
+ fprintf(stderr, "Error: argument \"%s\" is wrong: %s\n", arg, msg);
+ exit(-1);
+}
+
+void duparg(const char *key, const char *arg)
+{
+ fprintf(stderr, "Error: duplicate \"%s\": \"%s\" is the second value.\n", key, arg);
+ exit(-1);
+}
+
+void duparg2(const char *key, const char *arg)
+{
+ fprintf(stderr, "Error: either \"%s\" is duplicate, or \"%s\" is a garbage.\n", key, arg);
+ exit(-1);
+}
+
+int matches(const char *cmd, const char *pattern)
+{
+ int len = strlen(cmd);
+ if (len > strlen(pattern))
+ return -1;
+ return memcmp(pattern, cmd, len);
+}
+
+int inet_addr_match(const inet_prefix *a, const inet_prefix *b, int bits)
+{
+ const __u32 *a1 = a->data;
+ const __u32 *a2 = b->data;
+ int words = bits >> 0x05;
+
+ bits &= 0x1f;
+
+ if (words)
+ if (memcmp(a1, a2, words << 2))
+ return -1;
+
+ if (bits) {
+ __u32 w1, w2;
+ __u32 mask;
+
+ w1 = a1[words];
+ w2 = a2[words];
+
+ mask = htonl((0xffffffff) << (0x20 - bits));
+
+ if ((w1 ^ w2) & mask)
+ return 1;
+ }
+
+ return 0;
+}
+
+int __iproute2_hz_internal;
+
+int __get_hz(void)
+{
+ char name[1024];
+ int hz = 0;
+ FILE *fp;
+
+ if (getenv("HZ"))
+ return atoi(getenv("HZ")) ? : HZ;
+
+ if (getenv("PROC_NET_PSCHED")) {
+ snprintf(name, sizeof(name)-1, "%s", getenv("PROC_NET_PSCHED"));
+ } else if (getenv("PROC_ROOT")) {
+ snprintf(name, sizeof(name)-1, "%s/net/psched", getenv("PROC_ROOT"));
+ } else {
+ strcpy(name, "/proc/net/psched");
+ }
+ fp = fopen(name, "r");
+
+ if (fp) {
+ unsigned nom, denom;
+ if (fscanf(fp, "%*08x%*08x%08x%08x", &nom, &denom) == 2)
+ if (nom == 1000000)
+ hz = denom;
+ fclose(fp);
+ }
+ if (hz)
+ return hz;
+ return HZ;
+}
+
+int __iproute2_user_hz_internal;
+
+int __get_user_hz(void)
+{
+ return sysconf(_SC_CLK_TCK);
+}
+
+const char *rt_addr_n2a(int af, int len, const void *addr, char *buf, int buflen)
+{
+ switch (af) {
+ case AF_INET:
+ case AF_INET6:
+ return inet_ntop(af, addr, buf, buflen);
+#ifndef ANDROID
+ case AF_MPLS:
+ return mpls_ntop(af, addr, buf, buflen);
+ case AF_IPX:
+ return ipx_ntop(af, addr, buf, buflen);
+ case AF_DECnet:
+ {
+ struct dn_naddr dna = { 2, { 0, 0, }};
+ memcpy(dna.a_addr, addr, 2);
+ return dnet_ntop(af, &dna, buf, buflen);
+ }
+#endif
+ case AF_PACKET:
+ return ll_addr_n2a(addr, len, ARPHRD_VOID, buf, buflen);
+ default:
+ return "???";
+ }
+}
+
+int read_family(const char *name)
+{
+ int family = AF_UNSPEC;
+ if (strcmp(name, "inet") == 0)
+ family = AF_INET;
+ else if (strcmp(name, "inet6") == 0)
+ family = AF_INET6;
+ else if (strcmp(name, "dnet") == 0)
+ family = AF_DECnet;
+ else if (strcmp(name, "link") == 0)
+ family = AF_PACKET;
+ else if (strcmp(name, "ipx") == 0)
+ family = AF_IPX;
+ else if (strcmp(name, "mpls") == 0)
+ family = AF_MPLS;
+ else if (strcmp(name, "bridge") == 0)
+ family = AF_BRIDGE;
+ return family;
+}
+
+const char *family_name(int family)
+{
+ if (family == AF_INET)
+ return "inet";
+ if (family == AF_INET6)
+ return "inet6";
+ if (family == AF_DECnet)
+ return "dnet";
+ if (family == AF_PACKET)
+ return "link";
+ if (family == AF_IPX)
+ return "ipx";
+ if (family == AF_MPLS)
+ return "mpls";
+ if (family == AF_BRIDGE)
+ return "bridge";
+ return "???";
+}
+
+#ifdef RESOLVE_HOSTNAMES
+struct namerec
+{
+ struct namerec *next;
+ const char *name;
+ inet_prefix addr;
+};
+
+#define NHASH 257
+static struct namerec *nht[NHASH];
+
+static const char *resolve_address(const void *addr, int len, int af)
+{
+ struct namerec *n;
+ struct hostent *h_ent;
+ unsigned hash;
+ static int notfirst;
+
+
+ if (af == AF_INET6 && ((__u32*)addr)[0] == 0 &&
+ ((__u32*)addr)[1] == 0 && ((__u32*)addr)[2] == htonl(0xffff)) {
+ af = AF_INET;
+ addr += 12;
+ len = 4;
+ }
+
+ hash = *(__u32 *)(addr + len - 4) % NHASH;
+
+ for (n = nht[hash]; n; n = n->next) {
+ if (n->addr.family == af &&
+ n->addr.bytelen == len &&
+ memcmp(n->addr.data, addr, len) == 0)
+ return n->name;
+ }
+ if ((n = malloc(sizeof(*n))) == NULL)
+ return NULL;
+ n->addr.family = af;
+ n->addr.bytelen = len;
+ n->name = NULL;
+ memcpy(n->addr.data, addr, len);
+ n->next = nht[hash];
+ nht[hash] = n;
+ if (++notfirst == 1)
+ sethostent(1);
+ fflush(stdout);
+
+ if ((h_ent = gethostbyaddr(addr, len, af)) != NULL)
+ n->name = strdup(h_ent->h_name);
+
+ /* Even if we fail, "negative" entry is remembered. */
+ return n->name;
+}
+#endif
+
+const char *format_host(int af, int len, const void *addr,
+ char *buf, int buflen)
+{
+#ifdef RESOLVE_HOSTNAMES
+ if (resolve_hosts) {
+ const char *n;
+
+ len = len <= 0 ? af_byte_len(af) : len;
+
+ if (len > 0 &&
+ (n = resolve_address(addr, len, af)) != NULL)
+ return n;
+ }
+#endif
+ return rt_addr_n2a(af, len, addr, buf, buflen);
+}
+
+
+char *hexstring_n2a(const __u8 *str, int len, char *buf, int blen)
+{
+ char *ptr = buf;
+ int i;
+
+ for (i=0; i<len; i++) {
+ if (blen < 3)
+ break;
+ sprintf(ptr, "%02x", str[i]);
+ ptr += 2;
+ blen -= 2;
+ }
+ return buf;
+}
+
+__u8* hexstring_a2n(const char *str, __u8 *buf, int blen)
+{
+ int cnt = 0;
+ char *endptr;
+
+ if (strlen(str) % 2)
+ return NULL;
+ while (cnt < blen && strlen(str) > 1) {
+ unsigned int tmp;
+ char tmpstr[3];
+
+ strncpy(tmpstr, str, 2);
+ tmpstr[2] = '\0';
+ tmp = strtoul(tmpstr, &endptr, 16);
+ if (errno != 0 || tmp > 0xFF || *endptr != '\0')
+ return NULL;
+ buf[cnt++] = tmp;
+ str += 2;
+ }
+ return buf;
+}
+
+int addr64_n2a(__u64 addr, char *buff, size_t len)
+{
+ __u16 *words = (__u16 *)&addr;
+ __u16 v;
+ int i, ret;
+ size_t written = 0;
+ char *sep = ":";
+
+ for (i = 0; i < 4; i++) {
+ v = ntohs(words[i]);
+
+ if (i == 3)
+ sep = "";
+
+ ret = snprintf(&buff[written], len - written, "%x%s", v, sep);
+ if (ret < 0)
+ return ret;
+
+ written += ret;
+ }
+
+ return written;
+}
+
+int print_timestamp(FILE *fp)
+{
+ struct timeval tv;
+ struct tm *tm;
+
+ gettimeofday(&tv, NULL);
+ tm = localtime(&tv.tv_sec);
+
+ if (timestamp_short) {
+ char tshort[40];
+
+ strftime(tshort, sizeof(tshort), "%Y-%m-%dT%H:%M:%S", tm);
+ fprintf(fp, "[%s.%06ld] ", tshort, tv.tv_usec);
+ } else {
+ char *tstr = asctime(tm);
+
+ tstr[strlen(tstr)-1] = 0;
+ fprintf(fp, "Timestamp: %s %ld usec\n",
+ tstr, tv.tv_usec);
+ }
+
+ return 0;
+}
+
+int cmdlineno;
+
+/* Like glibc getline but handle continuation lines and comments */
+ssize_t getcmdline(char **linep, size_t *lenp, FILE *in)
+{
+ ssize_t cc;
+ char *cp;
+
+ if ((cc = getline(linep, lenp, in)) < 0)
+ return cc; /* eof or error */
+ ++cmdlineno;
+
+ cp = strchr(*linep, '#');
+ if (cp)
+ *cp = '\0';
+
+ while ((cp = strstr(*linep, "\\\n")) != NULL) {
+ char *line1 = NULL;
+ size_t len1 = 0;
+ ssize_t cc1;
+
+ if ((cc1 = getline(&line1, &len1, in)) < 0) {
+ fprintf(stderr, "Missing continuation line\n");
+ return cc1;
+ }
+
+ ++cmdlineno;
+ *cp = 0;
+
+ cp = strchr(line1, '#');
+ if (cp)
+ *cp = '\0';
+
+ *lenp = strlen(*linep) + strlen(line1) + 1;
+ *linep = realloc(*linep, *lenp);
+ if (!*linep) {
+ fprintf(stderr, "Out of memory\n");
+ *lenp = 0;
+ return -1;
+ }
+ cc += cc1 - 2;
+ strcat(*linep, line1);
+ free(line1);
+ }
+ return cc;
+}
+
+/* split command line into argument vector */
+int makeargs(char *line, char *argv[], int maxargs)
+{
+ static const char ws[] = " \t\r\n";
+ char *cp;
+ int argc = 0;
+
+ for (cp = line + strspn(line, ws); *cp; cp += strspn(cp, ws)) {
+ if (argc >= (maxargs - 1)) {
+ fprintf(stderr, "Too many arguments to command\n");
+ exit(1);
+ }
+
+ /* word begins with quote */
+ if (*cp == '\'' || *cp == '"') {
+ char quote = *cp++;
+
+ argv[argc++] = cp;
+ /* find ending quote */
+ cp = strchr(cp, quote);
+ if (cp == NULL) {
+ fprintf(stderr, "Unterminated quoted string\n");
+ exit(1);
+ }
+ *cp++ = 0;
+ continue;
+ }
+
+ argv[argc++] = cp;
+ /* find end of word */
+ cp += strcspn(cp, ws);
+ *cp++ = 0;
+ }
+ argv[argc] = NULL;
+
+ return argc;
+}
+
+int inet_get_addr(const char *src, __u32 *dst, struct in6_addr *dst6)
+{
+ if (strchr(src, ':'))
+ return inet_pton(AF_INET6, src, dst6);
+ else
+ return inet_pton(AF_INET, src, dst);
+}
+
+void print_nlmsg_timestamp(FILE *fp, const struct nlmsghdr *n)
+{
+ char *tstr;
+ time_t secs = ((__u32*)NLMSG_DATA(n))[0];
+ long usecs = ((__u32*)NLMSG_DATA(n))[1];
+ tstr = asctime(localtime(&secs));
+ tstr[strlen(tstr)-1] = 0;
+ fprintf(fp, "Timestamp: %s %lu us\n", tstr, usecs);
+}
+
+static int on_netns(char *nsname, void *arg)
+{
+ struct netns_func *f = arg;
+
+ if (netns_switch(nsname))
+ return -1;
+
+ return f->func(nsname, f->arg);
+}
+
+static int on_netns_label(char *nsname, void *arg)
+{
+ printf("\nnetns: %s\n", nsname);
+ return on_netns(nsname, arg);
+}
+
+int do_each_netns(int (*func)(char *nsname, void *arg), void *arg,
+ bool show_label)
+{
+ struct netns_func nsf = { .func = func, .arg = arg };
+
+ if (show_label)
+ return netns_foreach(on_netns_label, &nsf);
+
+ return netns_foreach(on_netns, &nsf);
+}
+
+char *int_to_str(int val, char *buf)
+{
+ sprintf(buf, "%d", val);
+ return buf;
+}
diff --git a/iproute2/man/Makefile b/iproute2/man/Makefile
new file mode 100644
index 0000000..749faa1
--- /dev/null
+++ b/iproute2/man/Makefile
@@ -0,0 +1,14 @@
+INSTALL=install
+INSTALLDIR=install -m 0755 -d
+INSTALLMAN=install -m 0644
+
+SUBDIRS = man3 man7 man8
+
+all clean install:
+ @for subdir in $(SUBDIRS); do $(MAKE) -C $$subdir $@ || exit $$?; done
+
+distclean: clean
+
+.PHONY: install clean distclean
+
+.EXPORT_ALL_VARIABLES:
diff --git a/iproute2/man/man3/Makefile b/iproute2/man/man3/Makefile
new file mode 100644
index 0000000..bf55658
--- /dev/null
+++ b/iproute2/man/man3/Makefile
@@ -0,0 +1,13 @@
+MAN3PAGES=libnetlink.3
+
+all:
+
+distclean: clean
+
+clean:
+
+install:
+ $(INSTALLDIR) $(DESTDIR)$(MANDIR)/man3
+ $(INSTALLMAN) $(MAN3PAGES) $(DESTDIR)$(MANDIR)/man3
+
+.PHONY: install clean distclean
diff --git a/iproute2/man/man3/libnetlink.3 b/iproute2/man/man3/libnetlink.3
new file mode 100644
index 0000000..99be9cc
--- /dev/null
+++ b/iproute2/man/man3/libnetlink.3
@@ -0,0 +1,200 @@
+.TH libnetlink 3
+.SH NAME
+libnetlink \- A library for accessing the netlink service
+.SH SYNOPSIS
+.nf
+#include <asm/types.h>
+.br
+#include <libnetlink.h>
+.br
+#include <linux/netlink.h>
+.br
+#include <linux/rtnetlink.h>
+.sp
+int rtnl_open(struct rtnl_handle *rth, unsigned subscriptions)
+.sp
+int rtnl_wilddump_request(struct rtnl_handle *rth, int family, int type)
+.sp
+int rtnl_send(struct rtnl_handle *rth, char *buf, int len)
+.sp
+int rtnl_dump_request(struct rtnl_handle *rth, int type, void *req, int len)
+.sp
+int rtnl_dump_filter(struct rtnl_handle *rth,
+ int (*filter)(struct sockaddr_nl *, struct nlmsghdr *n, void *),
+ void *arg1,
+ int (*junk)(struct sockaddr_nl *,struct nlmsghdr *n, void *),
+ void *arg2)
+.sp
+int rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n, pid_t peer,
+ unsigned groups, struct nlmsghdr *answer,
+.br
+ int (*junk)(struct sockaddr_nl *,struct nlmsghdr *n, void *),
+.br
+ void *jarg)
+.sp
+int rtnl_listen(struct rtnl_handle *rtnl,
+ int (*handler)(struct sockaddr_nl *, struct rtnl_ctrl_data *,
+ struct nlmsghdr *n, void *),
+ void *jarg)
+.sp
+int rtnl_from_file(FILE *rtnl,
+ int (*handler)(struct sockaddr_nl *,struct nlmsghdr *n, void *),
+ void *jarg)
+.sp
+int addattr32(struct nlmsghdr *n, int maxlen, int type, __u32 data)
+.sp
+int addattr_l(struct nlmsghdr *n, int maxlen, int type, void *data, int alen)
+.sp
+int rta_addattr32(struct rtattr *rta, int maxlen, int type, __u32 data)
+.sp
+int rta_addattr_l(struct rtattr *rta, int maxlen, int type, void *data, int alen)
+.SH DESCRIPTION
+libnetlink provides a higher level interface to
+.BR rtnetlink(7).
+The read functions return 0 on success and a negative errno on failure.
+The send functions return the amount of data sent, or -1 on error.
+.TP
+rtnl_open
+Open a rtnetlink socket and save the state into the
+.B rth
+handle. This handle is passed to all subsequent calls.
+.B subscriptions
+is a bitmap of the rtnetlink multicast groups the socket will be
+a member of.
+
+.TP
+rtnl_wilddump_request
+Request a full dump of the
+.B type
+database for
+.B family
+addresses.
+.B type
+is a rtnetlink message type.
+.\" XXX
+
+.TP
+rtnl_dump_request
+Request a full dump of the
+.B type
+data buffer into
+.B buf
+with maximum length of
+.B len.
+.B type
+is a rtnetlink message type.
+
+.TP
+rtnl_dump_filter
+Receive netlink data after a request and filter it.
+The
+.B filter
+callback checks if the received message is wanted. It gets the source
+address of the message, the message itself and
+.B arg1
+as arguments. 0 as return means that the filter passed, a negative
+value is returned
+by
+.I rtnl_dump_filter
+in case of error. NULL for
+.I filter
+means to not use a filter.
+.B junk
+is used to filter messages not destined to the local socket.
+Only one message bundle is received. If there is a message
+pending, this function does not block.
+
+.TP
+rtnl_listen
+Receive netlink data after a request and pass it to
+.I handler.
+.B handler
+is a callback that gets the message source address, anscillary data, the message
+itself, and the
+.B jarg
+cookie as arguments. It will get called for all received messages.
+Only one message bundle is received. If there is a message
+pending this function does not block.
+
+.TP
+rtnl_from_file
+Works like
+.I rtnl_listen,
+but reads a netlink message bundle from the file
+.B file
+and passes the messages to
+.B handler
+for parsing. The file should contain raw data as received from a rtnetlink socket.
+.PP
+The following functions are useful to construct custom rtnetlink messages. For
+simple database dumping with filtering it is better to use the higher level
+functions above. See
+.BR rtnetlink(3)
+and
+.BR netlink(3)
+on how to generate a rtnetlink message. The following utility functions
+require a continuous buffer that already contains a netlink message header
+and a rtnetlink request.
+
+.TP
+rtnl_send
+Send the rtnetlink message in
+.B buf
+of length
+.B len
+to handle
+.B rth.
+
+.TP
+addattr32
+Add a __u32 attribute of type
+.B type
+and with value
+.B data
+to netlink message
+.B n,
+which is part of a buffer of length
+.B maxlen.
+
+.TP
+addattr_l
+Add a variable length attribute of type
+.B type
+and with value
+.B data
+and
+.B alen
+length to netlink message
+.B n,
+which is part of a buffer of length
+.B maxlen.
+.B data
+is copied.
+
+.TP
+rta_addattr32
+Initialize the rtnetlink attribute
+.B rta
+with a __u32 data value.
+
+.TP
+rta_addattr32
+Initialize the rtnetlink attribute
+.B rta
+with a variable length data value.
+
+.SH BUGS
+This library is meant for internal use, use libmnl for new programs.
+
+The functions sometimes use fprintf and exit when a fatal error occurs.
+This library should be named librtnetlink.
+
+.SH AUTHORS
+netlink/rtnetlink was designed and written by Alexey Kuznetsov.
+Andi Kleen wrote the man page.
+
+.SH SEE ALSO
+.BR netlink(7),
+.BR rtnetlink(7)
+.br
+/usr/include/linux/rtnetlink.h
diff --git a/iproute2/man/man7/Makefile b/iproute2/man/man7/Makefile
new file mode 100644
index 0000000..ccfd839
--- /dev/null
+++ b/iproute2/man/man7/Makefile
@@ -0,0 +1,13 @@
+MAN7PAGES = tc-hfsc.7
+
+all:
+
+distclean: clean
+
+clean:
+
+install:
+ $(INSTALLDIR) $(DESTDIR)$(MANDIR)/man7
+ $(INSTALLMAN) $(MAN7PAGES) $(DESTDIR)$(MANDIR)/man7
+
+.PHONY: install clean distclean
diff --git a/iproute2/man/man7/tc-hfsc.7 b/iproute2/man/man7/tc-hfsc.7
new file mode 100644
index 0000000..ca04961
--- /dev/null
+++ b/iproute2/man/man7/tc-hfsc.7
@@ -0,0 +1,562 @@
+.TH "TC\-HFSC" 7 "31 October 2011" iproute2 Linux
+.SH "NAME"
+tc-hfcs \- Hierarchical Fair Service Curve
+.
+.SH "HISTORY & INTRODUCTION"
+.
+HFSC (Hierarchical Fair Service Curve) is a network packet scheduling algorithm that was first presented at
+SIGCOMM'97. Developed as a part of ALTQ (ALTernative Queuing) on NetBSD, found
+its way quickly to other BSD systems, and then a few years ago became part of
+the linux kernel. Still, it's not the most popular scheduling algorithm \-
+especially if compared to HTB \- and it's not well documented for the enduser. This introduction aims to explain how HFSC works without using
+too much math (although some math it will be
+inevitable).
+
+In short HFSC aims to:
+.
+.RS 4
+.IP \fB1)\fR 4
+guarantee precise bandwidth and delay allocation for all leaf classes (realtime
+criterion)
+.IP \fB2)\fR
+allocate excess bandwidth fairly as specified by class hierarchy (linkshare &
+upperlimit criterion)
+.IP \fB3)\fR
+minimize any discrepancy between the service curve and the actual amount of
+service provided during linksharing
+.RE
+.PP
+.
+The main "selling" point of HFSC is feature \fB(1)\fR, which is achieved by
+using nonlinear service curves (more about what it actually is later). This is
+particularly useful in VoIP or games, where not only a guarantee of consistent
+bandwidth is important, but also limiting the initial delay of a data stream. Note that
+it matters only for leaf classes (where the actual queues are) \- thus class
+hierarchy is ignored in the realtime case.
+
+Feature \fB(2)\fR is well, obvious \- any algorithm featuring class hierarchy
+(such as HTB or CBQ) strives to achieve that. HFSC does that well, although
+you might end with unusual situations, if you define service curves carelessly
+\- see section CORNER CASES for examples.
+
+Feature \fB(3)\fR is mentioned due to the nature of the problem. There may be
+situations where it's either not possible to guarantee service of all curves at
+the same time, and/or it's impossible to do so fairly. Both will be explained
+later. Note that this is mainly related to interior (aka aggregate) classes, as
+the leafs are already handled by \fB(1)\fR. Still, it's perfectly possible to
+create a leaf class without realtime service, and in such a case the caveats will
+naturally extend to leaf classes as well.
+
+.SH ABBREVIATIONS
+For the remaining part of the document, we'll use following shortcuts:
+.nf
+.RS 4
+
+RT \- realtime
+LS \- linkshare
+UL \- upperlimit
+SC \- service curve
+.fi
+.
+.SH "BASICS OF HFSC"
+.
+To understand how HFSC works, we must first introduce a service curve.
+Overall, it's a nondecreasing function of some time unit, returning the amount
+of
+service (an allowed or allocated amount of bandwidth) at some specific point in
+time. The purpose of it should be subconsciously obvious: if a class was
+allowed to transfer not less than the amount specified by its service curve,
+then the service curve is not violated.
+
+Still, we need more elaborate criterion than just the above (although in
+the most generic case it can be reduced to it). The criterion has to take two
+things into account:
+.
+.RS 4
+.IP \(bu 4
+idling periods
+.IP \(bu
+the ability to "look back", so if during current active period the service curve is violated, maybe it
+isn't if we count excess bandwidth received during earlier active period(s)
+.RE
+.PP
+Let's define the criterion as follows:
+.RS 4
+.nf
+.IP "\fB(1)\fR" 4
+For each t1, there must exist t0 in set B, so S(t1\-t0)\~<=\~w(t0,t1)
+.fi
+.RE
+.
+.PP
+Here 'w' denotes the amount of service received during some time period between t0
+and t1. B is a set of all times, where a session becomes active after idling
+period (further denoted as 'becoming backlogged'). For a clearer picture,
+imagine two situations:
+.
+.RS 4
+.IP \fBa)\fR 4
+our session was active during two periods, with a small time gap between them
+.IP \fBb)\fR
+as in (a), but with a larger gap
+.RE
+.
+.PP
+Consider \fB(a)\fR: if the service received during both periods meets
+\fB(1)\fR, then all is well. But what if it doesn't do so during the 2nd
+period? If the amount of service received during the 1st period is larger
+than the service curve, then it might compensate for smaller service during
+the 2nd period \fIand\fR the gap \- if the gap is small enough.
+
+If the gap is larger \fB(b)\fR \- then it's less likely to happen (unless the
+excess bandwidth allocated during the 1st part was really large). Still, the
+larger the gap \- the less interesting is what happened in the past (e.g. 10
+minutes ago) \- what matters is the current traffic that just started.
+
+From HFSC's perspective, more interesting is answering the following question:
+when should we start transferring packets, so a service curve of a class is not
+violated. Or rephrasing it: How much X() amount of service should a session
+receive by time t, so the service curve is not violated. Function X() defined
+as below is the basic building block of HFSC, used in: eligible, deadline,
+virtual\-time and fit\-time curves. Of course, X() is based on equation
+\fB(1)\fR and is defined recursively:
+
+.RS 4
+.IP \(bu 4
+At the 1st backlogged period beginning function X is initialized to generic
+service curve assigned to a class
+.IP \(bu
+At any subsequent backlogged period, X() is:
+.nf
+\fBmin(X() from previous period ; w(t0)+S(t\-t0) for t>=t0),\fR
+.fi
+\&... where t0 denotes the beginning of the current backlogged period.
+.RE
+.
+.PP
+HFSC uses either linear, or two\-piece linear service curves. In case of
+linear or two\-piece linear convex functions (first slope < second slope),
+min() in X's definition reduces to the 2nd argument. But in case of two\-piece
+concave functions, the 1st argument might quickly become lesser for some
+t>=t0. Note, that for some backlogged period, X() is defined only from that
+period's beginning. We also define X^(\-1)(w) as smallest t>=t0, for which
+X(t)\~=\~w. We have to define it this way, as X() is usually not an injection.
+
+The above generic X() can be one of the following:
+.
+.RS 4
+.IP "E()" 4
+In realtime criterion, selects packets eligible for sending. If none are
+eligible, HFSC will use linkshare criterion. Eligible time \&'et' is calculated
+with reference to packets' heads ( et\~=\~E^(\-1)(w) ). It's based on RT
+service curve, \fIbut in case of a convex curve, uses its 2nd slope only.\fR
+.IP "D()"
+In realtime criterion, selects the most suitable packet from the ones chosen
+by E(). Deadline time \&'dt' corresponds to packets' tails
+(dt\~=\~D^(\-1)(w+l), where \&'l' is packet's length). Based on RT service
+curve.
+.IP "V()"
+In linkshare criterion, arbitrates which packet to send next. Note that V() is
+function of a virtual time \- see \fBLINKSHARE CRITERION\fR section for
+details. Virtual time \&'vt' corresponds to packets' heads
+(vt\~=\~V^(\-1)(w)). Based on LS service curve.
+.IP "F()"
+An extension to linkshare criterion, used to limit at which speed linkshare
+criterion is allowed to dequeue. Fit\-time 'ft' corresponds to packets' heads
+as well (ft\~=\~F^(\-1)(w)). Based on UL service curve.
+.RE
+
+Be sure to make clean distinction between session's RT, LS and UL service
+curves and the above "utility" functions.
+.
+.SH "REALTIME CRITERION"
+.
+RT criterion \fIignores class hierarchy\fR and guarantees precise bandwidth and
+delay allocation. We say that a packet is eligible for sending, when the
+current real
+time is later than the eligible time of the packet. From all eligible packets, the one most
+suited for sending is the one with the shortest deadline time. This sounds
+simple, but consider the following example:
+
+Interface 10Mbit, two classes, both with two\-piece linear service curves:
+.RS 4
+.IP \(bu 4
+1st class \- 2Mbit for 100ms, then 7Mbit (convex \- 1st slope < 2nd slope)
+.IP \(bu
+2nd class \- 7Mbit for 100ms, then 2Mbit (concave \- 1st slope > 2nd slope)
+.RE
+.PP
+Assume for a moment, that we only use D() for both finding eligible packets,
+and choosing the most fitting one, thus eligible time would be computed as
+D^(\-1)(w) and deadline time would be computed as D^(\-1)(w+l). If the 2nd
+class starts sending packets 1 second after the 1st class, it's of course
+impossible to guarantee 14Mbit, as the interface capability is only 10Mbit.
+The only workaround in this scenario is to allow the 1st class to send the
+packets earlier that would normally be allowed. That's where separate E() comes
+to help. Putting all the math aside (see HFSC paper for details), E() for RT
+concave service curve is just like D(), but for the RT convex service curve \-
+it's constructed using \fIonly\fR RT service curve's 2nd slope (in our example
+ 7Mbit).
+
+The effect of such E() \- packets will be sent earlier, and at the same time
+D() \fIwill\fR be updated \- so the current deadline time calculated from it
+will be later. Thus, when the 2nd class starts sending packets later, both
+the 1st and the 2nd class will be eligible, but the 2nd session's deadline
+time will be smaller and its packets will be sent first. When the 1st class
+becomes idle at some later point, the 2nd class will be able to "buffer" up
+again for later active period of the 1st class.
+
+A short remark \- in a situation, where the total amount of bandwidth
+available on the interface is larger than the allocated total realtime parts
+(imagine a 10 Mbit interface, but 1Mbit/2Mbit and 2Mbit/1Mbit classes), the sole
+speed of the interface could suffice to guarantee the times.
+
+Important part of RT criterion is that apart from updating its D() and E(),
+also V() used by LS criterion is updated. Generally the RT criterion is
+secondary to LS one, and used \fIonly\fR if there's a risk of violating precise
+realtime requirements. Still, the "participation" in bandwidth distributed by
+LS criterion is there, so V() has to be updated along the way. LS criterion can
+than properly compensate for non\-ideal fair sharing situation, caused by RT
+scheduling. If you use UL service curve its F() will be updated as well (UL
+service curve is an extension to LS one \- see \fBUPPERLIMIT CRITERION\fR
+section).
+
+Anyway \- careless specification of LS and RT service curves can lead to
+potentially undesired situations (see CORNER CASES for examples). This wasn't
+the case in HFSC paper where LS and RT service curves couldn't be specified
+separately.
+
+.SH "LINKSHARING CRITERION"
+.
+LS criterion's task is to distribute bandwidth according to specified class
+hierarchy. Contrary to RT criterion, there're no comparisons between current
+real time and virtual time \- the decision is based solely on direct comparison
+of virtual times of all active subclasses \- the one with the smallest vt wins
+and gets scheduled. One immediate conclusion from this fact is that absolute
+values don't matter \- only ratios between them (so for example, two children
+classes with simple linear 1Mbit service curves will get the same treatment
+from LS criterion's perspective, as if they were 5Mbit). The other conclusion
+is, that in perfectly fluid system with linear curves, all virtual times across
+whole class hierarchy would be equal.
+
+Why is VC defined in term of virtual time (and what is it)?
+
+Imagine an example: class A with two children \- A1 and A2, both with let's say
+10Mbit SCs. If A2 is idle, A1 receives all the bandwidth of A (and update its
+V() in the process). When A2 becomes active, A1's virtual time is already
+\fIfar\fR later than A2's one. Considering the type of decision made by LS
+criterion, A1 would become idle for a long time. We can workaround this
+situation by adjusting virtual time of the class becoming active \- we do that
+by getting such time "up to date". HFSC uses a mean of the smallest and the
+biggest virtual time of currently active children fit for sending. As it's not
+real time anymore (excluding trivial case of situation where all classes become
+active at the same time, and never become idle), it's called virtual time.
+
+Such approach has its price though. The problem is analogous to what was
+presented in previous section and is caused by non\-linearity of service
+curves:
+.IP 1) 4
+either it's impossible to guarantee service curves and satisfy fairness
+during certain time periods:
+
+.RS 4
+Recall the example from RT section, slightly modified (with 3Mbit slopes
+instead of 2Mbit ones):
+
+.IP \(bu 4
+1st class \- 3Mbit for 100ms, then 7Mbit (convex \- 1st slope < 2nd slope)
+.IP \(bu
+2nd class \- 7Mbit for 100ms, then 3Mbit (concave \- 1st slope > 2nd slope)
+
+.PP
+They sum up nicely to 10Mbit \- the interface's capacity. But if we wanted to only
+use LS for guarantees and fairness \- it simply won't work. In LS context,
+only V() is used for making decision which class to schedule. If the 2nd class
+becomes active when the 1st one is in its second slope, the fairness will be
+preserved \- ratio will be 1:1 (7Mbit:7Mbit), but LS itself is of course
+unable to guarantee the absolute values themselves \- as it would have to go
+beyond of what the interface is capable of.
+.RE
+
+.IP 2) 4
+and/or it's impossible to guarantee service curves of all classes at the same
+time [fairly or not]:
+
+.RS 4
+
+This is similar to the above case, but a bit more subtle. We will consider two
+subtrees, arbitrated by their common (root here) parent:
+
+.nf
+R (root) -\ 10Mbit
+
+A \- 7Mbit, then 3Mbit
+A1 \- 5Mbit, then 2Mbit
+A2 \- 2Mbit, then 1Mbit
+
+B \- 3Mbit, then 7Mbit
+.fi
+
+R arbitrates between left subtree (A) and right (B). Assume that A2 and B are
+constantly backlogged, and at some later point A1 becomes backlogged (when all
+other classes are in their 2nd linear part).
+
+What happens now? B (choice made by R) will \fIalways\fR get 7 Mbit as R is
+only (obviously) concerned with the ratio between its direct children. Thus A
+subtree gets 3Mbit, but its children would want (at the point when A1 became
+backlogged) 5Mbit + 1Mbit. That's of course impossible, as they can only get
+3Mbit due to interface limitation.
+
+In the left subtree \- we have the same situation as previously (fair split
+between A1 and A2, but violated guarantees), but in the whole tree \- there's
+no fairness (B got 7Mbit, but A1 and A2 have to fit together in 3Mbit) and
+there's no guarantees for all classes (only B got what it wanted). Even if we
+violated fairness in the A subtree and set A2's service curve to 0, A1 would
+still not get the required bandwidth.
+.RE
+.
+.SH "UPPERLIMIT CRITERION"
+.
+UL criterion is an extensions to LS one, that permits sending packets only
+if current real time is later than fit\-time ('ft'). So the modified LS
+criterion becomes: choose the smallest virtual time from all active children,
+such that fit\-time < current real time also holds. Fit\-time is calculated
+from F(), which is based on UL service curve. As you can see, its role is
+kinda similar to E() used in RT criterion. Also, for obvious reasons \- you
+can't specify UL service curve without LS one.
+
+The main purpose of the UL service curve is to limit HFSC to bandwidth available on the
+upstream router (think adsl home modem/router, and linux server as
+NAT/firewall/etc. with 100Mbit+ connection to mentioned modem/router).
+Typically, it's used to create a single class directly under root, setting
+a linear UL service curve to available bandwidth \- and then creating your class
+structure from that class downwards. Of course, you're free to add a UL service
+curve (linear or not) to any class with LS criterion.
+
+An important part about the UL service curve is that whenever at some point in time
+a class doesn't qualify for linksharing due to its fit\-time, the next time it
+does qualify it will update its virtual time to the smallest virtual time of
+all active children fit for linksharing. This way, one of the main things the LS
+criterion tries to achieve \- equality of all virtual times across whole
+hierarchy \- is preserved (in perfectly fluid system with only linear curves,
+all virtual times would be equal).
+
+Without that, 'vt' would lag behind other virtual times, and could cause
+problems. Consider an interface with a capacity of 10Mbit, and the following leaf classes
+(just in case you're skipping this text quickly \- this example shows behavior
+that \f(BIdoesn't happen\fR):
+
+.nf
+A \- ls 5.0Mbit
+B \- ls 2.5Mbit
+C \- ls 2.5Mbit, ul 2.5Mbit
+.fi
+
+If B was idle, while A and C were constantly backlogged, A and C would normally
+(as far as LS criterion is concerned) divide bandwidth in 2:1 ratio. But due
+to UL service curve in place, C would get at most 2.5Mbit, and A would get the
+remaining 7.5Mbit. The longer the backlogged period, the more the virtual times of
+A and C would drift apart. If B became backlogged at some later point in time,
+its virtual time would be set to (A's\~vt\~+\~C's\~vt)/2, thus blocking A from
+sending any traffic until B's virtual time catches up with A.
+.
+.SH "SEPARATE LS / RT SCs"
+.
+Another difference from the original HFSC paper is that RT and LS SCs can be
+specified separately. Moreover, leaf classes are allowed to have only either
+RT SC or LS SC. For interior classes, only LS SCs make sense: any RT SC will
+be ignored.
+.
+.SH "CORNER CASES"
+.
+Separate service curves for LS and RT criteria can lead to certain traps
+that come from "fighting" between ideal linksharing and enforced realtime
+guarantees. Those situations didn't exist in original HFSC paper, where
+specifying separate LS / RT service curves was not discussed.
+
+Consider an interface with a 10Mbit capacity, with the following leaf classes:
+
+.nf
+A \- ls 5.0Mbit, rt 8Mbit
+B \- ls 2.5Mbit
+C \- ls 2.5Mbit
+.fi
+
+Imagine A and C are constantly backlogged. As B is idle, A and C would divide
+bandwidth in 2:1 ratio, considering LS service curve (so in theory \- 6.66 and
+3.33). Alas RT criterion takes priority, so A will get 8Mbit and LS will be
+able to compensate class C for only 2 Mbit \- this will cause discrepancy
+between virtual times of A and C.
+
+Assume this situation lasts for a long time with no idle periods, and
+suddenly B becomes active. B's virtual time will be updated to
+(A's\~vt\~+\~C's\~vt)/2, effectively landing in the middle between A's and C's
+virtual time. The effect \- B, having no RT guarantees, will be punished and
+will not be allowed to transfer until C's virtual time catches up.
+
+If the interface had a higher capacity, for example 100Mbit, this example
+would behave perfectly fine though.
+
+Let's look a bit closer at the above example \- it "cleverly" invalidates one
+of the basic things LS criterion tries to achieve \- equality of all virtual
+times across class hierarchy. Leaf classes without RT service curves are
+literally left to their own fate (governed by messed up virtual times).
+
+Also, it doesn't make much sense. Class A will always be guaranteed up to
+8Mbit, and this is more than any absolute bandwidth that could happen from its
+LS criterion (excluding trivial case of only A being active). If the bandwidth
+taken by A is smaller than absolute value from LS criterion, the unused part
+will be automatically assigned to other active classes (as A has idling periods
+in such case). The only "advantage" is, that even in case of low bandwidth on
+average, bursts would be handled at the speed defined by RT criterion. Still,
+if extra speed is needed (e.g. due to latency), non linear service curves
+should be used in such case.
+
+In the other words: the LS criterion is meaningless in the above example.
+
+You can quickly "workaround" it by making sure each leaf class has RT service
+curve assigned (thus guaranteeing all of them will get some bandwidth), but it
+doesn't make it any more valid.
+
+Keep in mind - if you use nonlinear curves and irregularities explained above
+happen \fIonly\fR in the first segment, then there's little wrong with
+"overusing" RT curve a bit:
+
+.nf
+A \- ls 5.0Mbit, rt 9Mbit/30ms, then 1Mbit
+B \- ls 2.5Mbit
+C \- ls 2.5Mbit
+.fi
+
+Here, the vt of A will "spike" in the initial period, but then A will never get more
+than 1Mbit until B & C catch up. Then everything will be back to normal.
+.
+.SH "LINUX AND TIMER RESOLUTION"
+.
+In certain situations, the scheduler can throttle itself and setup so
+called watchdog to wakeup dequeue function at some time later. In case of HFSC
+it happens when for example no packet is eligible for scheduling, and UL
+service curve is used to limit the speed at which LS criterion is allowed to
+dequeue packets. It's called throttling, and accuracy of it is dependent on
+how the kernel is compiled.
+
+There're 3 important options in modern kernels, as far as timers' resolution
+goes: \&'tickless system', \&'high resolution timer support' and \&'timer
+frequency'.
+
+If you have \&'tickless system' enabled, then the timer interrupt will trigger
+as slowly as possible, but each time a scheduler throttles itself (or any
+other part of the kernel needs better accuracy), the rate will be increased as
+needed / possible. The ceiling is either \&'timer frequency' if \&'high
+resolution timer support' is not available or not compiled in, or it's
+hardware dependent and can go \fIfar\fR beyond the highest \&'timer frequency'
+setting available.
+
+If \&'tickless system' is not enabled, the timer will trigger at a fixed rate
+specified by \&'timer frequency' \- regardless if high resolution timers are
+or aren't available.
+
+This is important to keep those settings in mind, as in scenario like: no
+tickless, no HR timers, frequency set to 100hz \- throttling accuracy would be
+at 10ms. It doesn't automatically mean you would be limited to ~0.8Mbit/s
+(assuming packets at ~1KB) \- as long as your queues are prepared to cover for
+timer inaccuracy. Of course, in case of e.g. locally generated UDP traffic \-
+appropriate socket size is needed as well. Short example to make it more
+understandable (assume hardcore anti\-schedule settings \- HZ=100, no HR
+timers, no tickless):
+
+.nf
+tc qdisc add dev eth0 root handle 1:0 hfsc default 1
+tc class add dev eth0 parent 1:0 classid 1:1 hfsc rt m2 10Mbit
+.fi
+
+Assuming packet of ~1KB size and HZ=100, that averages to ~0.8Mbit \- anything
+beyond it (e.g. the above example with specified rate over 10x larger) will
+require appropriate queuing and cause bursts every ~10 ms. As you can
+imagine, any HFSC's RT guarantees will be seriously invalidated by that.
+Aforementioned example is mainly important if you deal with old hardware \- as
+is particularly popular for home server chores. Even then, you can easily
+set HZ=1000 and have very accurate scheduling for typical adsl speeds.
+
+Anything modern (apic or even hpet msi based timers + \&'tickless system')
+will provide enough accuracy for superb 1Gbit scheduling. For example, on one
+of my cheap dual-core AMD boards I have the following settings:
+
+.nf
+tc qdisc add dev eth0 parent root handle 1:0 hfsc default 1
+tc class add dev eth0 parent 1:0 classid 1:1 hfsc rt m2 300mbit
+.fi
+
+And a simple:
+
+.nf
+nc \-u dst.host.com 54321 </dev/zero
+nc \-l \-p 54321 >/dev/null
+.fi
+
+\&...will yield the following effects over a period of ~10 seconds (taken from
+/proc/interrupts):
+
+.nf
+319: 42124229 0 HPET_MSI\-edge hpet2 (before)
+319: 42436214 0 HPET_MSI\-edge hpet2 (after 10s.)
+.fi
+
+That's roughly 31000/s. Now compare it with HZ=1000 setting. The obvious
+drawback of it is that cpu load can be rather high with servicing that
+many timer interrupts. The example with 300Mbit RT service curve on 1Gbit link is
+particularly ugly, as it requires a lot of throttling with minuscule delays.
+
+Also note that it's just an example showing the capabilities of current hardware.
+The above example (essentially a 300Mbit TBF emulator) is pointless on an internal
+interface to begin with: you will pretty much always want a regular LS service
+curve there, and in such a scenario HFSC simply doesn't throttle at all.
+
+300Mbit RT service curve (selected columns from mpstat \-P ALL 1):
+
+.nf
+10:56:43 PM CPU %sys %irq %soft %idle
+10:56:44 PM all 20.10 6.53 34.67 37.19
+10:56:44 PM 0 35.00 0.00 63.00 0.00
+10:56:44 PM 1 4.95 12.87 6.93 73.27
+.fi
+
+So, in the rare case you need those speeds with only a RT service curve, or with a UL
+service curve: remember the drawbacks.
+.
+.SH "CAVEAT: RANDOM ONLINE EXAMPLES"
+.
+For reasons unknown (though well guessed), many examples you can google love to
+overuse UL criterion and stuff it in every node possible. This makes no sense
+and works against what HFSC tries to do (and does pretty damn well). Use UL
+where it makes sense: on the uppermost node to match upstream router's uplink
+capacity. Or in special cases, such as testing (limit certain subtree to some
+speed), or customers that must never get more than certain speed. In the last
+case you can usually achieve the same by just using a RT criterion without LS+UL
+on leaf nodes.
+
+As for the router case - remember it's good to differentiate between "traffic to
+router" (remote console, web config, etc.) and "outgoing traffic", so for
+example:
+
+.nf
+tc qdisc add dev eth0 root handle 1:0 hfsc default 0x8002
+tc class add dev eth0 parent 1:0 classid 1:999 hfsc rt m2 50Mbit
+tc class add dev eth0 parent 1:0 classid 1:1 hfsc ls m2 2Mbit ul m2 2Mbit
+.fi
+
+\&... so "internet" tree under 1:1 and "router itself" as 1:999
+.
+.SH "LAYER2 ADAPTATION"
+.
+Please refer to \fBtc\-stab\fR(8)
+.
+.SH "SEE ALSO"
+.
+\fBtc\fR(8), \fBtc\-hfsc\fR(8), \fBtc\-stab\fR(8)
+
+Please direct bugreports and patches to: <net...@vger.kernel.org>
+.
+.SH "AUTHOR"
+.
+Manpage created by Michal Soltys (sol...@ziu.info)
diff --git a/iproute2/man/man8/Makefile b/iproute2/man/man8/Makefile
new file mode 100644
index 0000000..2f77640
--- /dev/null
+++ b/iproute2/man/man8/Makefile
@@ -0,0 +1,39 @@
+TARGETS = ip-address.8 ip-link.8 ip-route.8
+
+MAN8PAGES = $(TARGETS) ip.8 arpd.8 lnstat.8 routel.8 rtacct.8 rtmon.8 rtpr.8 ss.8 \
+ tc.8 tc-bfifo.8 tc-bpf.8 tc-cbq.8 tc-cbq-details.8 tc-choke.8 tc-codel.8 \
+ tc-fq.8 \
+ tc-drr.8 tc-ematch.8 tc-fq_codel.8 tc-hfsc.8 tc-htb.8 tc-pie.8 \
+ tc-mqprio.8 tc-netem.8 tc-pfifo.8 tc-pfifo_fast.8 tc-prio.8 tc-red.8 \
+ tc-sfb.8 tc-sfq.8 tc-stab.8 tc-tbf.8 \
+ bridge.8 rtstat.8 ctstat.8 nstat.8 routef.8 \
+ ip-addrlabel.8 ip-fou.8 ip-gue.8 ip-l2tp.8 \
+ ip-maddress.8 ip-monitor.8 ip-mroute.8 ip-neighbour.8 \
+ ip-netns.8 ip-ntable.8 ip-rule.8 ip-tunnel.8 ip-xfrm.8 \
+ ip-tcp_metrics.8 ip-netconf.8 ip-token.8 \
+ tipc.8 tipc-bearer.8 tipc-link.8 tipc-media.8 tipc-nametable.8 \
+ tipc-node.8 tipc-socket.8 \
+ tc-basic.8 tc-cgroup.8 tc-flow.8 tc-flower.8 tc-fw.8 tc-route.8 \
+ tc-tcindex.8 tc-u32.8
+
+all: $(TARGETS)
+
+ip-address.8: ip-address.8.in
+ sed "s|@SYSCONFDIR@|$(CONFDIR)|g" $< > $@
+
+ip-link.8: ip-link.8.in
+ sed "s|@SYSCONFDIR@|$(CONFDIR)|g" $< > $@
+
+ip-route.8: ip-route.8.in
+ sed "s|@SYSCONFDIR@|$(CONFDIR)|g" $< > $@
+
+distclean: clean
+
+clean:
+ @rm -f $(TARGETS)
+
+install:
+ $(INSTALLDIR) $(DESTDIR)$(MANDIR)/man8
+ $(INSTALLMAN) $(MAN8PAGES) $(DESTDIR)$(MANDIR)/man8
+
+.PHONY: install clean distclean
diff --git a/iproute2/man/man8/arpd.8 b/iproute2/man/man8/arpd.8
new file mode 100644
index 0000000..5050a98
--- /dev/null
+++ b/iproute2/man/man8/arpd.8
@@ -0,0 +1,69 @@
+.TH ARPD 8 "28 June, 2007"
+
+.SH NAME
+arpd \- userspace arp daemon.
+
+.SH SYNOPSIS
+Usage: arpd [ -lkh? ] [ -a N ] [ -b dbase ] [ -B number ] [ -f file ] [-p interval ] [ -n time ] [ -R rate ] [ <INTERFACES> ]
+
+.SH DESCRIPTION
+The
+.B arpd
+daemon collects gratuitous ARP information, saving it on local disk and feeding it to the kernel on demand to avoid redundant broadcasting due to limited size of the kernel ARP cache.
+
+.SH OPTIONS
+.TP
+-h -?
+Print help
+.TP
+-l
+Dump the arpd database to stdout and exit. The output consists of three columns: the interface index, the IP address of the interface, and the MAC address of the interface. Negative entries for dead hosts are also shown, in this case the MAC address is replaced by the word FAILED followed by a colon and the most recent time when the fact that the host is dead was proven.
+.TP
+-f <FILE>
+Read and load an arpd database from FILE in a text format similar to that dumped by option -l. Exit after load, possibly listing resulting database, if option -l is also given. If FILE is -, stdin is read to get the ARP table.
+.TP
+-b <DATABASE>
+the location of the database file. The default location is /var/lib/arpd/arpd.db
+.TP
+-a <NUMBER>
+With this option, arpd not only passively listens for ARP packets on the interface, but also sends broadcast queries itself. NUMBER is the number of such queries to make before a destination is considered dead. When arpd is started as kernel helper (i.e. with app_solicit enabled in sysctl or even with option -k) without this option and still did not learn enough information, you can observe 1 second gaps in service. Not fatal, but not good.
+.TP
+-k
+Suppress sending broadcast queries by the kernel. This option only makes sense together with option -a.
+.TP
+-n <TIME>
+Specifies the timeout of the negative cache. When resolution fails, arpd suppresses further attempts to resolve for this period. This option only makes sense together with option '-k'. This timeout should not be too much longer than the boot time of a typical host not supporting gratuitous ARP. Default value is 60 seconds.
+.TP
+-p <TIME>
+The time to wait in seconds between polling attempts to the kernel ARP table. TIME may be a floating point number. The default value is 30.
+.TP
+-R <RATE>
+Maximal steady rate of broadcasts sent by arpd in packets per second. Default value is 1.
+.TP
+-B <NUMBER>
+The number of broadcasts sent by arpd back to back. Default value is 3. Together with the -R option, this option ensures that the number of ARP queries that are broadcast does not exceed B+R*T over any interval of time T.
+.P
+<INTERFACES> is a list of names of networking interfaces to watch. If no interfaces are given, arpd monitors all the interfaces. In this case arpd does not adjust sysctl parameters, it is assumed that the user does this himself after arpd is started.
+.P
+.SH SIGNALS
+.TP
+When arpd receives a SIGINT or SIGTERM signal, it exits gracefully, syncing the database and restoring adjusted sysctl parameters. On a SIGHUP it syncs the database to disk. With SIGUSR1 it sends some statistics to syslog. The effect of any other signals is undefined. In particular, they may corrupt the database and leave the sysctl parameters in an unpredictable state.
+.P
+.SH NOTE
+.TP
+In order for arpd to be able to serve as ARP resolver, the kernel must be compiled with the option CONFIG_ARPD and, in the case when interface list in not given on command line, variable app_solicit on interfaces of interest should be in /proc/sys/net/ipv4/neigh/*. If this is not made arpd still collects gratuitous ARP information in its database.
+.SH EXAMPLES
+.TP
+arpd -b /var/tmp/arpd.db
+Start arpd to collect gratuitous ARP, but not messing with kernel functionality.
+.TP
+killall arpd ; arpd -l -b /var/tmp/arpd.db
+Look at result after some time.
+.TP
+arpd -b /var/tmp/arpd.db -a 1 eth0 eth1
+Enable kernel helper, leaving leading role to kernel.
+.TP
+arpd -b /var/tmp/arpd.db -a 3 -k eth0 eth1
+Completely replace kernel resolution on interfaces eth0 and eth1. In this case the kernel still does unicast probing to validate entries, but all the broadcast activity is suppressed and made under authority of arpd.
+.PP
+This is the mode in which arpd normally is supposed to work. It is not the default to prevent occasional enabling of too aggressive a mode.
diff --git a/iproute2/man/man8/bridge.8 b/iproute2/man/man8/bridge.8
new file mode 100644
index 0000000..0ec6f17
--- /dev/null
+++ b/iproute2/man/man8/bridge.8
@@ -0,0 +1,593 @@
+.TH BRIDGE 8 "1 August 2012" "iproute2" "Linux"
+.SH NAME
+bridge \- show / manipulate bridge addresses and devices
+.SH SYNOPSIS
+
+.ad l
+.in +8
+.ti -8
+.B bridge
+.RI "[ " OPTIONS " ] " OBJECT " { " COMMAND " | "
+.BR help " }"
+.sp
+
+.ti -8
+.IR OBJECT " := { "
+.BR link " | " fdb " | " mdb " | " vlan " | " monitor " }"
+.sp
+
+.ti -8
+.IR OPTIONS " := { "
+\fB\-V\fR[\fIersion\fR] |
+\fB\-s\fR[\fItatistics\fR] |
+\fB\-n\fR[\fIetns\fR] name }
+\fB\-b\fR[\fIatch\fR] filename }
+
+.ti -8
+.BR "bridge link set"
+.B dev
+.IR DEV
+.IR " [ "
+.B cost
+.IR COST " ] [ "
+.B priority
+.IR PRIO " ] [ "
+.B state
+.IR STATE "] ["
+.BR guard " { " on " | " off " } ] [ "
+.BR hairpin " { " on " | " off " } ] [ "
+.BR fastleave " { " on " | " off " } ] [ "
+.BR root_block " { " on " | " off " } ] [ "
+.BR learning " { " on " | " off " } ] [ "
+.BR learning_sync " { " on " | " off " } ] [ "
+.BR flood " { " on " | " off " } ] [ "
+.BR hwmode " { " vepa " | " veb " } ] [ "
+.BR self " ] [ " master " ] "
+
+.ti -8
+.BR "bridge link" " [ " show " ] [ "
+.B dev
+.IR DEV " ]"
+
+.ti -8
+.BR "bridge fdb" " { " add " | " append " | " del " | " replace " } "
+.I LLADDR
+.B dev
+.IR DEV " { "
+.BR local " | " temp " } [ "
+.BR self " ] [ " master " ] [ " router " ] [ " use " ] [ "
+.B dst
+.IR IPADDR " ] [ "
+.B vni
+.IR VNI " ] ["
+.B port
+.IR PORT " ] ["
+.B via
+.IR DEVICE " ]"
+
+.ti -8
+.BR "bridge fdb" " [ " show " ] [ "
+.B dev
+.IR DEV " ]"
+
+.ti -8
+.BR "bridge mdb" " { " add " | " del " } "
+.B dev
+.IR DEV
+.B port
+.IR PORT
+.B grp
+.IR GROUP " [ "
+.BR permanent " | " temp " ] [ "
+.B vid
+.IR VID " ] "
+
+.ti -8
+.BR "bridge mdb show " [ "
+.B dev
+.IR DEV " ]"
+
+.ti -8
+.BR "bridge vlan" " { " add " | " del " } "
+.B dev
+.IR DEV
+.B vid
+.IR VID " [ "
+.BR pvid " ] [ " untagged " ] [ "
+.BR self " ] [ " master " ] "
+
+.ti -8
+.BR "bridge vlan" " [ " show " ] [ "
+.B dev
+.IR DEV " ]"
+
+.ti -8
+.BR "bridge monitor" " [ " all " | " neigh " | " link " | " mdb " ]"
+
+.SH OPTIONS
+
+.TP
+.BR "\-V" , " -Version"
+print the version of the
+.B bridge
+utility and exit.
+
+.TP
+.BR "\-s" , " \-stats", " \-statistics"
+output more information. If this option
+is given multiple times, the amount of information increases.
+As a rule, the information is statistics or some time values.
+
+.TP
+.BR "\-n" , " \-net" , " \-netns " <NETNS>
+switches
+.B bridge
+to the specified network namespace
+.IR NETNS .
+Actually it just simplifies executing of:
+
+.B ip netns exec
+.IR NETNS
+.B bridge
+.RI "[ " OPTIONS " ] " OBJECT " { " COMMAND " | "
+.BR help " }"
+
+to
+
+.B bridge
+.RI "-n[etns] " NETNS " [ " OPTIONS " ] " OBJECT " { " COMMAND " | "
+.BR help " }"
+
+.TP
+.BR "\-b", " \-batch " <FILENAME>
+Read commands from provided file or standard input and invoke them.
+First failure will cause termination of bridge command.
+
+.TP
+.BR "\-force"
+Don't terminate bridge command on errors in batch mode.
+If there were any errors during execution of the commands, the application
+return code will be non zero.
+
+.SH BRIDGE - COMMAND SYNTAX
+
+.SS
+.I OBJECT
+
+.TP
+.B link
+- Bridge port.
+
+.TP
+.B fdb
+- Forwarding Database entry.
+
+.TP
+.B mdb
+- Multicast group database entry.
+
+.TP
+.B vlan
+- VLAN filter list.
+
+.SS
+.I COMMAND
+
+Specifies the action to perform on the object.
+The set of possible actions depends on the object type.
+As a rule, it is possible to
+.BR "add" , " delete"
+and
+.B show
+(or
+.B list
+) objects, but some objects do not allow all of these operations
+or have some additional commands. The
+.B help
+command is available for all objects. It prints
+out a list of available commands and argument syntax conventions.
+.sp
+If no command is given, some default command is assumed.
+Usually it is
+.B list
+or, if the objects of this class cannot be listed,
+.BR "help" .
+
+.SH bridge link - bridge port
+
+.B link
+objects correspond to the port devices of the bridge.
+
+.P
+The corresponding commands set and display port status and bridge specific
+attributes.
+
+.SS bridge link set - set bridge specific attributes on a port
+
+.TP
+.BI dev " NAME "
+interface name of the bridge port
+
+.TP
+.BI cost " COST "
+the STP path cost of the specified port.
+
+.TP
+.BI priority " PRIO "
+the STP port priority. The priority value is an unsigned 8-bit quantity
+(number between 0 and 255). This metric is used in the designated port an
+droot port selectio algorithms.
+
+.TP
+.BI state " STATE "
+the operation state of the port. This is primarily used by user space STP/RSTP
+implementation. One may enter a lowercased port state name, or one of the
+numbers below. Negative inputs are ignored, and unrecognized names return an
+error.
+
+.B 0
+- port is DISABLED. Make this port completely inactive.
+.sp
+
+.B 1
+- STP LISTENING state. Only valid if STP is enabled on the brige. In this
+state the port for list for STP BPDUs and drop all other traffic.
+.sp
+
+.B 2
+- STP LEARNING state. Only valid if STP is enabled on the bridge. In this
+state the port will accept traffic only for the purpose of updating MAC
+address tables.
+.sp
+
+.B 3
+- STP FORWARDING state. Port is fully active.
+.sp
+
+.B 4
+- STP BLOCKING state. Only valid if STP is enabled on the bridge. This state
+is used during the STP election process. In this state, port will only process
+STP BPDUs.
+.sp
+
+.TP
+.BR "guard on " or " guard off "
+Controls whether STP BPUDs will be processed by the bridge port. By default,
+the flag is turned off allowed BPDU processing. Turning this flag on will
+cause the port to stop processing STP BPDUs.
+
+.TP
+.BR "hairpin on " or " hairpin off "
+Controls whether traffic may be send back out of the port on which it was
+received. By default, this flag is turned off and the bridge will not forward
+traffic back out of the receiving port.
+
+.TP
+.BR "fastleave on " or " fastleave off "
+This flag allows the bridge to immediately stop multicast traffic on a port
+that receives IGMP Leave message. It is only used with IGMP snooping is
+enabled on the bridge. By default the flag is off.
+
+.TP
+.BR "root_block on " or " root_block off "
+Controls whether a given port is allowed to become root port or not. Only used
+when STP is enabled on the bridge. By default the flag is off.
+
+.TP
+.BR "learning on " or " learning off "
+Controls whether a given port will learn MAC addresses from received traffic or
+not. If learning if off, the bridge will end up flooding any traffic for which
+it has no FDB entry. By default this flag is on.
+
+.TP
+.BR "learning_sync on " or " learning_sync off "
+Controls whether a given port will sync MAC addresses learned on device port to
+bridge FDB.
+
+.TP
+.BR "flooding on " or " flooding off "
+Controls whether a given port will flood unicast traffic for which there is no FDB entry. By default this flag is on.
+
+.TP
+.BI hwmode
+Some network interface cards support HW bridge functionality and they may be
+configured in different modes. Currently support modes are:
+
+.B vepa
+- Data sent between HW ports is sent on the wire to the external
+switch.
+
+.B veb
+- bridging happens in hardware.
+
+.TP
+.BI self
+link setting is configured on specified physical device
+
+.TP
+.BI master
+link setting is configured on the software bridge (default)
+
+.TP
+.BR "\-t" , " \-timestamp"
+display current time when using monitor option.
+
+.SS bridge link show - list bridge port configuration.
+
+This command displays the current bridge port configuration and flags.
+
+.SH bridge fdb - forwarding database management
+
+.B fdb
+objects contain known Ethernet addresses on a link.
+
+.P
+The corresponding commands display fdb entries, add new entries,
+append entries,
+and delete old ones.
+
+.SS bridge fdb add - add a new fdb entry
+
+This command creates a new fdb entry.
+
+.TP
+.BI "LLADDR"
+the Ethernet MAC address.
+
+.TP
+.BI dev " DEV"
+the interface to which this address is associated.
+
+.B self
+- the address is associated with the port drivers fdb. Usually hardware.
+.sp
+
+.B master
+- the address is associated with master devices fdb. Usually software (default).
+.sp
+
+.B router
+- the destination address is associated with a router.
+Valid if the referenced device is a VXLAN type device and has
+route shortcircuit enabled.
+.sp
+
+.B use
+- the address is in use. User space can use this option to
+indicate to the kernel that the fdb entry is in use.
+.sp
+
+.in -8
+The next command line parameters apply only
+when the specified device
+.I DEV
+is of type VXLAN.
+.TP
+.BI dst " IPADDR"
+the IP address of the destination
+VXLAN tunnel endpoint where the Ethernet MAC ADDRESS resides.
+
+.TP
+.BI vni " VNI"
+the VXLAN VNI Network Identifier (or VXLAN Segment ID)
+to use to connect to the remote VXLAN tunnel endpoint.
+If omitted the value specified at vxlan device creation
+will be used.
+
+.TP
+.BI port " PORT"
+the UDP destination PORT number to use to connect to the
+remote VXLAN tunnel endpoint.
+If omitted the default value is used.
+
+.TP
+.BI via " DEVICE"
+device name of the outgoing interface for the
+VXLAN device driver to reach the
+remote VXLAN tunnel endpoint.
+
+.SS bridge fdb append - append a forwarding database entry
+This command adds a new fdb entry with an already known
+.IR LLADDR .
+Valid only for multicast link layer addresses.
+The command adds support for broadcast and multicast
+Ethernet MAC addresses.
+The Ethernet MAC address is added multiple times into
+the forwarding database and the vxlan device driver
+sends a copy of the data packet to each entry found.
+
+.PP
+The arguments are the same as with
+.BR "bridge fdb add" .
+
+.SS bridge fdb delete - delete a forwarding database entry
+This command removes an existing fdb entry.
+
+.PP
+The arguments are the same as with
+.BR "bridge fdb add" .
+
+.SS bridge fdb replace - replace a forwarding database entry
+If no matching entry is found, a new one will be created instead.
+
+.PP
+The arguments are the same as with
+.BR "bridge fdb add" .
+
+.SS bridge fdb show - list forwarding entries.
+
+This command displays the current forwarding table.
+
+.PP
+With the
+.B -statistics
+option, the command becomes verbose. It prints out the last updated
+and last used time for each entry.
+
+.SH bridge mdb - multicast group database management
+
+.B mdb
+objects contain known IP multicast group addresses on a link.
+
+.P
+The corresponding commands display mdb entries, add new entries,
+and delete old ones.
+
+.SS bridge mdb add - add a new multicast group database entry
+
+This command creates a new mdb entry.
+
+.TP
+.BI dev " DEV"
+the interface where this group address is associated.
+
+.TP
+.BI port " PORT"
+the port whose link is known to have members of this multicast group.
+
+.TP
+.BI grp " GROUP"
+the IP multicast group address whose members reside on the link connected to
+the port.
+
+.B permanent
+- the mdb entry is permanent
+.sp
+
+.B temp
+- the mdb entry is temporary (default)
+.sp
+
+.TP
+.BI vid " VID"
+the VLAN ID which is known to have members of this multicast group.
+
+.in -8
+.SS bridge mdb delete - delete a multicast group database entry
+This command removes an existing mdb entry.
+
+.PP
+The arguments are the same as with
+.BR "bridge mdb add" .
+
+.SS bridge mdb show - list multicast group database entries
+
+This command displays the current multicast group membership table. The table
+is populated by IGMP and MLD snooping in the bridge driver automatically. It
+can be altered by
+.B bridge mdb add
+and
+.B bridge mdb del
+commands manually too.
+
+.TP
+.BI dev " DEV"
+the interface only whose entries should be listed. Default is to list all
+bridge interfaces.
+
+.PP
+With the
+.B -details
+option, the command becomes verbose. It prints out the ports known to have
+a connected router.
+
+.SH bridge vlan - VLAN filter list
+
+.B vlan
+objects contain known VLAN IDs for a link.
+
+.P
+The corresponding commands display vlan filter entries, add new entries,
+and delete old ones.
+
+.SS bridge vlan add - add a new vlan filter entry
+
+This command creates a new vlan filter entry.
+
+.TP
+.BI dev " NAME"
+the interface with which this vlan is associated.
+
+.TP
+.BI vid " VID"
+the VLAN ID that identifies the vlan.
+
+.TP
+.BI pvid
+the vlan specified is to be considered a PVID at ingress.
+Any untagged frames will be assigned to this VLAN.
+
+.TP
+.BI untagged
+the vlan specified is to be treated as untagged on egress.
+
+.TP
+.BI self
+the vlan is configured on the specified physical device. Required if the
+device is the bridge device.
+
+.TP
+.BI master
+the vlan is configured on the software bridge (default).
+
+.SS bridge vlan delete - delete a forwarding database entry
+This command removes an existing fdb entry.
+
+.PP
+The arguments are the same as with
+.BR "bridge vlan add".
+The
+.BR "pvid " and " untagged"
+flags are ignored.
+
+.SS bridge vlan show - list vlan configuration.
+
+This command displays the current VLAN filter table.
+
+.SH bridge monitor - state monitoring
+
+The
+.B bridge
+utility can monitor the state of devices and addresses
+continuously. This option has a slightly different format.
+Namely, the
+.B monitor
+command is the first in the command line and then the object list follows:
+
+.BR "bridge monitor" " [ " all " |"
+.IR OBJECT-LIST " ]"
+
+.I OBJECT-LIST
+is the list of object types that we want to monitor.
+It may contain
+.BR link ", " fdb ", and " mdb "."
+If no
+.B file
+argument is given,
+.B bridge
+opens RTNETLINK, listens on it and dumps state changes in the format
+described in previous sections.
+
+.P
+If a file name is given, it does not listen on RTNETLINK,
+but opens the file containing RTNETLINK messages saved in binary format
+and dumps them.
+
+.SH NOTES
+This command uses facilities added in Linux 3.0.
+
+Although the forwarding table is maintained on a per-bridge device basis
+the bridge device is not part of the syntax. This is a limitation of the
+underlying netlink neighbour message protocol. When displaying the
+forwarding table, entries for all bridges are displayed.
+Add/delete/modify commands determine the underlying bridge device
+based on the bridge to which the corresponding ethernet device is attached.
+
+
+.SH SEE ALSO
+.BR ip (8)
+.SH BUGS
+.RB "Please direct bugreports and patches to: " <netdev@vger.kernel.org>
+
+.SH AUTHOR
+Original Manpage by Stephen Hemminger
diff --git a/iproute2/man/man8/ctstat.8 b/iproute2/man/man8/ctstat.8
new file mode 100644
index 0000000..080e2b2
--- /dev/null
+++ b/iproute2/man/man8/ctstat.8
@@ -0,0 +1 @@
+.so man8/lnstat.8
diff --git a/iproute2/man/man8/genl.8 b/iproute2/man/man8/genl.8
new file mode 100644
index 0000000..b9de594
--- /dev/null
+++ b/iproute2/man/man8/genl.8
@@ -0,0 +1,77 @@
+.TH GENL 8 "29 Oct 2015" "iproute2" "Linux"
+.SH NAME
+genl \- generic netlink utility frontend
+.SH SYNOPSIS
+.in +8
+.ti -8
+.BR genl " [ " -s [ tatistics "] ] [ " -d [ etails "] ] [ " -r [ aw "] ] " OBJECT
+
+.ti -8
+.BR genl " { " -V [ ersion "] | " -h [ elp "] }"
+
+.ti -8
+.IR OBJECT " := { "
+.B ctrl
+.IR CTRL_OPTS " }"
+
+.ti -8
+.IR CTRL_OPTS " := { "
+.BR help " | " list " | " monitor " | " get
+.IR PARMS " }"
+
+.ti -8
+.IR PARMS " := { "
+.B name
+.IR NAME " | "
+.B id
+.IR ID " }"
+.SH DESCRIPTION
+The
+.B genl
+utility provides a simple frontend to the generic netlink library. Although it's
+designed to support multiple
+.IR OBJECT s,
+for now only the
+.B ctrl
+object is available, which is used to query the generic netlink controller.
+.SS ctrl
+The generic netlink controller can be queried in various ways:
+.TP
+.B help
+This command just prints a help text for the
+.B ctrl
+object.
+.TP
+.B list
+Show the registered netlink users.
+.TP
+.B monitor
+Listen for generic netlink notifications.
+.TP
+.B get
+Query the controller for a given user, identified either by
+.BR name " or " id .
+.SH OPTIONS
+genl supports the following options.
+.TP
+.B \-h, \-help
+Show summary of options.
+.TP
+.B \-V, \-Version
+Show version of program.
+.TP
+.B \-s, \-stats, \-statistics
+Show object statistics.
+.TP
+.B \-d, \-details
+Show object details.
+.TP
+.B \-r, \-raw
+Dump raw output only.
+.SH SEE ALSO
+.BR ip (8)
+.br
+.SH AUTHOR
+genl was written by Jamal Hadi Salim <hadi@cyberus.ca>.
+.PP
+This manual page was written by Petr Sabata <contyk@redhat.com>.
diff --git a/iproute2/man/man8/ifcfg.8 b/iproute2/man/man8/ifcfg.8
new file mode 100644
index 0000000..1a3786c
--- /dev/null
+++ b/iproute2/man/man8/ifcfg.8
@@ -0,0 +1,48 @@
+.TH IFCFG 8 "September 24 2009" "iproute2" "Linux"
+.SH NAME
+ifcfg \- simplistic script which replaces ifconfig IP management
+.SH SYNOPSIS
+.ad l
+.in +8
+.ti -8
+.B ifcfg
+.RI "[ " DEVICE " ] [ " command " ] " ADDRESS " [ " PEER " ] "
+.sp
+
+.SH DESCRIPTION
+This manual page documents briefly the
+.B ifcfg
+command.
+.PP
+This is a simplistic script replacing one option of
+.B ifconfig
+, namely, IP address management. It not only adds
+addresses, but also carries out Duplicate Address Detection RFC-DHCP,
+sends unsolicited ARP to update the caches of other hosts sharing
+the interface, adds some control routes and restarts Router Discovery
+when it is necessary.
+
+.SH IFCONFIG - COMMAND SYNTAX
+
+.SS
+.TP
+.B DEVICE
+- it may have alias, suffix, separated by colon.
+
+.TP
+.B command
+- add, delete or stop.
+
+.TP
+.B ADDRESS
+- optionally followed by prefix length.
+
+.TP
+.B peer
+- optional peer address for pointpoint interfaces.
+
+.SH NOTES
+This script is not suitable for use with IPv6.
+
+.SH SEE ALSO
+.RB "IP Command reference " ip-cref.ps
diff --git a/iproute2/man/man8/ifstat.8 b/iproute2/man/man8/ifstat.8
new file mode 100644
index 0000000..e49d868
--- /dev/null
+++ b/iproute2/man/man8/ifstat.8
@@ -0,0 +1,59 @@
+.TH IFSTAT 8 "28 Oct 2015" "iproute2" "Linux"
+.SH NAME
+ifstat \- handy utility to read network interface statistics
+.SH SYNOPSIS
+.in +8
+.ti -8
+.BR ifstat " [ "
+.IR OPTIONS " ] [ " INTERFACE_LIST " ]"
+
+.ti -8
+.IR INTERFACE_LIST " := " INTERFACE_LIST " | " interface
+.SH DESCRIPTION
+\fBifstat\fP neatly prints out network interface statistics.
+The utility keeps records of the previous data displayed in history files and
+by default only shows difference between the last and the current call.
+Location of the history files defaults to /tmp/.ifstat.u$UID but may be
+overridden with the IFSTAT_HISTORY environment variable.
+.SH OPTIONS
+.TP
+.B \-h, \-\-help
+Show summary of options.
+.TP
+.B \-V, \-\-version
+Show version of program.
+.TP
+.B \-a, \-\-ignore
+Ignore the history file.
+.TP
+.B \-d, \-\-scan=SECS
+Sample statistics every SECS second.
+.TP
+.B \-e, \-\-errors
+Show errors.
+.TP
+.B \-n, \-\-nooutput
+Don't display any output. Update the history file only.
+.TP
+.B \-r, \-\-reset
+Reset history.
+.TP
+.B \-s, \-\-noupdate
+Don't update the history file.
+.TP
+.B \-t, \-\-interval=SECS
+Report average over the last SECS seconds.
+.TP
+.B \-z, \-\-zeros
+Show entries with zero activity.
+.SH ENVIRONMENT
+.TP
+.B IFSTAT_HISTORY
+If set, it's value is interpreted as alternate history file path.
+.SH SEE ALSO
+.BR ip (8)
+.br
+.SH AUTHOR
+ifstat was written by Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>.
+.PP
+This manual page was written by Petr Sabata <contyk@redhat.com>.
diff --git a/iproute2/man/man8/ip-address.8.in b/iproute2/man/man8/ip-address.8.in
new file mode 100644
index 0000000..159d906
--- /dev/null
+++ b/iproute2/man/man8/ip-address.8.in
@@ -0,0 +1,342 @@
+.TH "IP\-ADDRESS" 8 "20 Dec 2011" "iproute2" "Linux"
+.SH "NAME"
+ip-address \- protocol address management
+.SH "SYNOPSIS"
+.sp
+.ad l
+.in +8
+.ti -8
+.B ip
+.RI "[ " OPTIONS " ]"
+.B address
+.RI " { " COMMAND " | "
+.BR help " }"
+.sp
+
+.ti -8
+.BR "ip address" " { " add " | " change " | " replace " } "
+.IB IFADDR " dev " IFNAME
+.RI "[ " LIFETIME " ] [ " CONFFLAG-LIST " ]"
+
+.ti -8
+.BR "ip address del"
+.IB IFADDR " dev " IFNAME " [ " mngtmpaddr " ]"
+
+.ti -8
+.BR "ip address" " { " show " | " save " | " flush " } [ " dev
+.IR IFNAME " ] [ "
+.B scope
+.IR SCOPE-ID " ] [ "
+.B to
+.IR PREFIX " ] [ " FLAG-LIST " ] [ "
+.B label
+.IR PATTERN " ] [ " up " ]"
+
+.ti -8
+.BR "ip address" " { " showdump " | " restore " }"
+
+.ti -8
+.IR IFADDR " := " PREFIX " | " ADDR
+.B peer
+.IR PREFIX " [ "
+.B broadcast
+.IR ADDR " ] [ "
+.B anycast
+.IR ADDR " ] [ "
+.B label
+.IR LABEL " ] [ "
+.B scope
+.IR SCOPE-ID " ]"
+
+.ti -8
+.IR SCOPE-ID " := "
+.RB "[ " host " | " link " | " global " | "
+.IR NUMBER " ]"
+
+.ti -8
+.IR FLAG-LIST " := [ " FLAG-LIST " ] " FLAG
+
+.ti -8
+.IR FLAG " := "
+.RB "[ " permanent " | " dynamic " | " secondary " | " primary " | \
+[ - ] " tentative " | [ - ] " deprecated " | [ - ] " dadfailed " | "\
+temporary " | " CONFFLAG-LIST " ]"
+
+.ti -8
+.IR CONFFLAG-LIST " := [ " CONFFLAG-LIST " ] " CONFFLAG
+
+.ti -8
+.IR CONFFLAG " := "
+.RB "[ " home " | " mngtmpaddr " | " nodad " | " noprefixroute " ]"
+
+.ti -8
+.IR LIFETIME " := [ "
+.BI valid_lft " LFT"
+.RB "| " preferred_lft
+.IR LFT " ]"
+
+.ti -8
+.IR LFT " := [ "
+.BR forever " |"
+.IR SECONDS " ]"
+
+.SH "DESCRIPTION"
+The
+.B address
+is a protocol (IPv4 or IPv6) address attached
+to a network device. Each device must have at least one address
+to use the corresponding protocol. It is possible to have several
+different addresses attached to one device. These addresses are not
+discriminated, so that the term
+.B alias
+is not quite appropriate for them and we do not use it in this document.
+.sp
+The
+.B ip address
+command displays addresses and their properties, adds new addresses
+and deletes old ones.
+
+.SS ip address add - add new protocol address.
+
+.TP
+.BI dev " IFNAME "
+the name of the device to add the address to.
+
+.TP
+.BI local " ADDRESS " (default)
+the address of the interface. The format of the address depends
+on the protocol. It is a dotted quad for IP and a sequence of
+hexadecimal halfwords separated by colons for IPv6. The
+.I ADDRESS
+may be followed by a slash and a decimal number which encodes
+the network prefix length.
+
+.TP
+.BI peer " ADDRESS"
+the address of the remote endpoint for pointopoint interfaces.
+Again, the
+.I ADDRESS
+may be followed by a slash and a decimal number, encoding the network
+prefix length. If a peer address is specified, the local address
+cannot have a prefix length. The network prefix is associated
+with the peer rather than with the local address.
+
+.TP
+.BI broadcast " ADDRESS"
+the broadcast address on the interface.
+.sp
+It is possible to use the special symbols
+.B '+'
+and
+.B '-'
+instead of the broadcast address. In this case, the broadcast address
+is derived by setting/resetting the host bits of the interface prefix.
+
+.TP
+.BI label " LABEL"
+Each address may be tagged with a label string.
+In order to preserve compatibility with Linux-2.0 net aliases,
+this string must coincide with the name of the device or must be prefixed
+with the device name followed by colon.
+
+.TP
+.BI scope " SCOPE_VALUE"
+the scope of the area where this address is valid.
+The available scopes are listed in file
+.BR "@SYSCONFDIR@/rt_scopes" .
+Predefined scope values are:
+
+.in +8
+.B global
+- the address is globally valid.
+.sp
+.B site
+- (IPv6 only, deprecated) the address is site local, i.e. it is
+valid inside this site.
+.sp
+.B link
+- the address is link local, i.e. it is valid only on this device.
+.sp
+.B host
+- the address is valid only inside this host.
+.in -8
+
+.TP
+.BI valid_lft " LFT"
+the valid lifetime of this address; see section 5.5.4 of
+RFC 4862. When it expires, the address is removed by the kernel.
+Defaults to
+.BR "forever" .
+
+.TP
+.BI preferred_lft " LFT"
+the preferred lifetime of this address; see section 5.5.4
+of RFC 4862. When it expires, the address is no longer used for new
+outgoing connections. Defaults to
+.BR "forever" .
+
+.TP
+.B home
+(IPv6 only) designates this address the "home address" as defined in
+RFC 6275.
+
+.TP
+.B mngtmpaddr
+(IPv6 only) make the kernel manage temporary addresses created from this one as
+template on behalf of Privacy Extensions (RFC3041). For this to become active,
+the \fBuse_tempaddr\fP sysctl setting has to be set to a value greater than
+zero. The given address needs to have a prefix length of 64. This flag allows
+to use privacy extensions in a manually configured network, just like if
+stateless auto-configuration was active.
+
+.TP
+.B nodad
+(IPv6 only) do not perform Duplicate Address Detection (RFC 4862) when
+adding this address.
+
+.TP
+.B noprefixroute
+Do not automatically create a route for the network prefix of the added
+address, and don't search for one to delete when removing the address. Changing
+an address to add this flag will remove the automatically added prefix route,
+changing it to remove this flag will create the prefix route automatically.
+
+.SS ip address delete - delete protocol address
+.B Arguments:
+coincide with the arguments of
+.B ip addr add.
+The device name is a required argument. The rest are optional.
+If no arguments are given, the first address is deleted.
+
+.SS ip address show - look at protocol addresses
+
+.TP
+.BI dev " IFNAME " (default)
+name of device.
+
+.TP
+.BI scope " SCOPE_VAL"
+only list addresses with this scope.
+
+.TP
+.BI to " PREFIX"
+only list addresses matching this prefix.
+
+.TP
+.BI label " PATTERN"
+only list addresses with labels matching the
+.IR "PATTERN" .
+.I PATTERN
+is a usual shell style pattern.
+
+.TP
+.B up
+only list running interfaces.
+
+.TP
+.BR dynamic " and " permanent
+(IPv6 only) only list addresses installed due to stateless
+address configuration or only list permanent (not dynamic)
+addresses.
+
+.TP
+.B tentative
+(IPv6 only) only list addresses which have not yet passed duplicate
+address detection.
+
+.TP
+.B -tentative
+(IPv6 only) only list addresses which are not in the process of
+duplicate address detection currently.
+
+.TP
+.B deprecated
+(IPv6 only) only list deprecated addresses.
+
+.TP
+.B -deprecated
+(IPv6 only) only list addresses not being deprecated.
+
+.TP
+.B dadfailed
+(IPv6 only) only list addresses which have failed duplicate
+address detection.
+
+.TP
+.B -dadfailed
+(IPv6 only) only list addresses which have not failed duplicate
+address detection.
+
+.TP
+.B temporary
+(IPv6 only) only list temporary addresses.
+
+.TP
+.BR primary " and " secondary
+only list primary (or secondary) addresses.
+
+.SS ip address flush - flush protocol addresses
+This command flushes the protocol addresses selected by some criteria.
+
+.PP
+This command has the same arguments as
+.B show.
+The difference is that it does not run when no arguments are given.
+
+.PP
+.B Warning:
+This command and other
+.B flush
+commands are unforgiving. They will cruelly purge all the addresses.
+
+.PP
+With the
+.B -statistics
+option, the command becomes verbose. It prints out the number of deleted
+addresses and the number of rounds made to flush the address list.
+If this option is given twice,
+.B ip address flush
+also dumps all the deleted addresses in the format described in the
+previous subsection.
+
+.SH "EXAMPLES"
+.PP
+ip address show
+.RS 4
+Shows IPv4 and IPv6 addresses assigned to all network interfaces. The 'show'
+subcommand can be omitted.
+.RE
+.PP
+ip address show up
+.RS 4
+Same as above except that only addresses assigned to active network interfaces
+are shown.
+.RE
+.PP
+ip address show dev eth0
+.RS 4
+Shows IPv4 and IPv6 addresses assigned to network interface eth0.
+.RE
+.PP
+ip address add 2001:0db8:85a3::0370:7334/64 dev eth1
+.RS 4
+Adds an IPv6 address to network interface eth1.
+.RE
+.PP
+ip address delete 2001:0db8:85a3::0370:7334/64 dev eth1
+.RS 4
+Delete the IPv6 address added above.
+.RE
+.PP
+ip address flush dev eth4 scope global
+.RS 4
+Removes all global IPv4 and IPv6 addresses from device eth4. Without 'scope
+global' it would remove all addresses including IPv6 link-local ones.
+.RE
+
+.SH SEE ALSO
+.br
+.BR ip (8)
+
+.SH AUTHOR
+Original Manpage by Michail Litvak <mci@owl.openwall.com>
diff --git a/iproute2/man/man8/ip-addrlabel.8 b/iproute2/man/man8/ip-addrlabel.8
new file mode 100644
index 0000000..51ef572
--- /dev/null
+++ b/iproute2/man/man8/ip-addrlabel.8
@@ -0,0 +1,68 @@
+.TH IP\-ADDRLABEL 8 "20 Dec 2011" "iproute2" "Linux"
+.SH "NAME"
+ip-addrlabel \- protocol address label management
+.SH "SYNOPSIS"
+.sp
+.ad l
+.in +8
+.ti -8
+.B ip
+.RI "[ " OPTIONS " ]"
+.B addrlabel
+.RI " { " COMMAND " | "
+.BR help " }"
+.sp
+
+.ti -8
+.IR OPTIONS " := { "
+\fB\-V\fR[\fIersion\fR] |
+\fB\-s\fR[\fItatistics\fR] |
+\fB\-r\fR[\fIesolve\fR] |
+\fB\-f\fR[\fIamily\fR] {
+.BR inet " | " inet6 " | " ipx " | " dnet " | " link " } | "
+\fB\-o\fR[\fIneline\fR] }
+
+.ti -8
+.BR "ip addrlabel" " { " add " | " del " } " prefix
+.BR PREFIX " [ "
+.B dev
+.IR DEV " ] [ "
+.B label
+.IR NUMBER " ]"
+
+.ti -8
+.BR "ip addrlabel" " { " list " | " flush " }"
+
+.SH "DESCRIPTION"
+IPv6 address labels are used for address selection;
+they are described in RFC 3484. Precedence is managed by userspace,
+and only the label itself is stored in the kernel.
+
+.SS ip addrlabel add - add an address label
+add an address label entry to the kernel.
+.TP
+.BI prefix " PREFIX"
+.TP
+.BI dev " DEV"
+the outgoing interface.
+.TP
+.BI label " NUMBER"
+the label for the prefix.
+0xffffffff is reserved.
+.SS ip addrlabel del - delete an address label
+delete an address label entry from the kernel.
+.B Arguments:
+coincide with the arguments of
+.B ip addrlabel add
+but the label is not required.
+.SS ip addrlabel list - list address labels
+list the current address label entries in the kernel.
+.SS ip addrlabel flush - flush address labels
+flush all address labels in the kernel. This does not restore any default settings.
+
+.SH SEE ALSO
+.br
+.BR ip (8)
+
+.SH AUTHOR
+Manpage by Yoshifuji Hideaki / 吉藤英明
diff --git a/iproute2/man/man8/ip-fou.8 b/iproute2/man/man8/ip-fou.8
new file mode 100644
index 0000000..0fa22ee
--- /dev/null
+++ b/iproute2/man/man8/ip-fou.8
@@ -0,0 +1,76 @@
+.TH IP\-FOU 8 "2 Nov 2014" "iproute2" "Linux"
+.SH "NAME"
+ip-fou \- Foo-over-UDP receive port configuration
+.P
+ip-gue \- Generic UDP Encapsulation receive port configuration
+.SH "SYNOPSIS"
+.sp
+.ad l
+.in +8
+.ti -8
+.B ip
+.RI "[ " OPTIONS " ]"
+.B fou
+.RI " { " COMMAND " | "
+.BR help " }"
+.sp
+.ti -8
+.BR "ip fou add"
+.B port
+.IR PORT
+.RB "{ "
+.B gue
+.RI "|"
+.B ipproto
+.IR PROTO
+.RB " }"
+.br
+.ti -8
+.BR "ip fou del"
+.B port
+.IR PORT
+.SH DESCRIPTION
+The
+.B ip fou
+commands are used to create and delete receive ports for Foo-over-UDP
+(FOU) as well as Generic UDP Encapsulation (GUE).
+.PP
+Foo-over-UDP allows encapsulating packets of an IP protocol directly
+over UDP. The receiver infers the protocol of a packet received on
+a FOU UDP port to be the protocol configured for the port.
+.PP
+Generic UDP Encapsulation (GUE) encapsulates packets of an IP protocol
+within UDP and an encapsulation header. The encapsulation header contains the
+IP protocol number for the encapsulated packet.
+.PP
+When creating a FOU or GUE receive port, the port number is specified in
+.I PORT
+argument. If FOU is used, the IP protocol number associated with the port is specified in
+.I PROTO
+argument.
+.PP
+A FOU or GUE receive port is deleted by specifying
+.I PORT
+in the delete command.
+.SH EXAMPLES
+.PP
+.SS Configure a FOU receive port for GRE bound to 7777
+.nf
+# ip fou add port 8888 ipproto 47
+.PP
+.SS Configure a FOU receive port for IPIP bound to 8888
+.nf
+# ip fou add port 8888 ipproto 4
+.PP
+.SS Configure a GUE receive port bound to 9999
+.nf
+# ip fou add port 9999 gue
+.PP
+.SS Delete the GUE receive port bound to 9999
+.nf
+# ip fou del port 9999
+.SH SEE ALSO
+.br
+.BR ip (8)
+.SH AUTHOR
+Tom Herbert <therbert@google.com>
diff --git a/iproute2/man/man8/ip-gue.8 b/iproute2/man/man8/ip-gue.8
new file mode 100644
index 0000000..4d2914c
--- /dev/null
+++ b/iproute2/man/man8/ip-gue.8
@@ -0,0 +1 @@
+.so man8/ip-fou.8
diff --git a/iproute2/man/man8/ip-l2tp.8 b/iproute2/man/man8/ip-l2tp.8
new file mode 100644
index 0000000..1738035
--- /dev/null
+++ b/iproute2/man/man8/ip-l2tp.8
@@ -0,0 +1,389 @@
+.TH IP\-L2TP 8 "19 Apr 2012" "iproute2" "Linux"
+.SH "NAME"
+ip-l2tp - L2TPv3 static unmanaged tunnel configuration
+.SH "SYNOPSIS"
+.sp
+.ad l
+.in +8
+.ti -8
+.B ip
+.RI "[ " OPTIONS " ]"
+.B l2tp
+.RI " { " COMMAND " | "
+.BR help " }"
+.sp
+.ti -8
+.BR "ip l2tp add tunnel"
+.br
+.B remote
+.RI "[ " ADDR " ]"
+.B local
+.RI "[ " ADDR " ]"
+.br
+.B tunnel_id
+.IR ID
+.B peer_tunnel_id
+.IR ID
+.br
+.RB "[ " encap " { " ip " | " udp " } ]"
+.br
+.RB "[ " udp_sport
+.IR PORT
+.RB " ] [ " udp_dport
+.IR PORT
+.RB " ]"
+.br
+.ti -8
+.BR "ip l2tp add session"
+.RB "[ " name
+.IR NAME
+.RB " ]"
+.br
+.B tunnel_id
+.IR ID
+.B session_id
+.IR ID
+.B peer_session_id
+.IR ID
+.br
+.RB "[ " cookie
+.IR HEXSTR
+.RB " ] [ " peer_cookie
+.IR HEXSTR
+.RB " ]"
+.br
+.RB "[ " l2spec_type " { " none " | " default " } ]"
+.br
+.RB "[ " offset
+.IR OFFSET
+.RB " ] [ " peer_offset
+.IR OFFSET
+.RB " ]"
+.br
+.ti -8
+.BR "ip l2tp del tunnel"
+.B tunnel_id
+.IR ID
+.br
+.ti -8
+.BR "ip l2tp del session"
+.B tunnel_id
+.IR ID
+.B session_id
+.IR ID
+.br
+.ti -8
+.BR "ip l2tp show tunnel"
+.B "[" tunnel_id
+.IR ID
+.B "]"
+.br
+.ti -8
+.BR "ip l2tp show session"
+.B "[" tunnel_id
+.IR ID
+.B "] [" session_id
+.IR ID
+.B "]"
+.br
+.ti -8
+.IR NAME " := "
+.IR STRING
+.ti -8
+.IR ADDR " := { " IP_ADDRESS " }"
+.ti -8
+.IR PORT " := { " NUMBER " }"
+.ti -8
+.IR ID " := { " NUMBER " }"
+.ti -8
+.ti -8
+.IR HEXSTR " := { 8 or 16 hex digits (4 / 8 bytes) }"
+.SH DESCRIPTION
+The
+.B ip l2tp
+commands are used to establish static, or so-called
+.I unmanaged
+L2TPv3 ethernet tunnels. For unmanaged tunnels, there is no L2TP
+control protocol so no userspace daemon is required - tunnels are
+manually created by issuing commands at a local system and at a remote
+peer.
+.PP
+L2TPv3 is suitable for Layer-2 tunneling. Static tunnels are useful
+to establish network links across IP networks when the tunnels are
+fixed. L2TPv3 tunnels can carry data of more than one session. Each
+session is identified by a session_id and its parent tunnel's
+tunnel_id. A tunnel must be created before a session can be created in
+the tunnel.
+.PP
+When creating an L2TP tunnel, the IP address of the remote peer is
+specified, which can be either an IPv4 or IPv6 address. The local IP
+address to be used to reach the peer must also be specified. This is
+the address on which the local system will listen for and accept
+received L2TP data packets from the peer.
+.PP
+L2TPv3 defines two packet encapsulation formats: UDP or IP. UDP
+encapsulation is most common. IP encapsulation uses a dedicated IP
+protocol value to carry L2TP data without the overhead of UDP. Use IP
+encapsulation only when there are no NAT devices or firewalls in the
+network path.
+.PP
+When an L2TPv3 ethernet session is created, a virtual network
+interface is created for the session, which must then be configured
+and brought up, just like any other network interface. When data is
+passed through the interface, it is carried over the L2TP tunnel to
+the peer. By configuring the system's routing tables or adding the
+interface to a bridge, the L2TP interface is like a virtual wire
+(pseudowire) connected to the peer.
+.PP
+Establishing an unmanaged L2TPv3 ethernet pseudowire involves manually
+creating L2TP contexts on the local system and at the peer. Parameters
+used at each site must correspond or no data will be passed. No
+consistency checks are possible since there is no control protocol
+used to establish unmanaged L2TP tunnels. Once the virtual network
+interface of a given L2TP session is configured and enabled, data can
+be transmitted, even if the peer isn't yet configured. If the peer
+isn't configured, the L2TP data packets will be discarded by
+the peer.
+.PP
+To establish an unmanaged L2TP tunnel, use
+.B l2tp add tunnel
+and
+.B l2tp add session
+commands described in this document. Then configure and enable the
+tunnel's virtual network interface, as required.
+.PP
+Note that unmanaged tunnels carry only ethernet frames. If you need to
+carry PPP traffic (L2TPv2) or your peer doesn't support unmanaged
+L2TPv3 tunnels, you will need an L2TP server which implements the L2TP
+control protocol. The L2TP control protocol allows dynamic L2TP
+tunnels and sessions to be established and provides for detecting and
+acting upon network failures.
+.SS ip l2tp add tunnel - add a new tunnel
+.TP
+.BI name " NAME "
+sets the session network interface name. Default is l2tpethN.
+.TP
+.BI tunnel_id " ID"
+set the tunnel id, which is a 32-bit integer value. Uniquely
+identifies the tunnel. The value used must match the peer_tunnel_id
+value being used at the peer.
+.TP
+.BI peer_tunnel_id " ID"
+set the peer tunnel id, which is a 32-bit integer value assigned to
+the tunnel by the peer. The value used must match the tunnel_id value
+being used at the peer.
+.TP
+.BI remote " ADDR"
+set the IP address of the remote peer. May be specified as an IPv4
+address or an IPv6 address.
+.TP
+.BI local " ADDR"
+set the IP address of the local interface to be used for the
+tunnel. This address must be the address of a local interface. May be
+specified as an IPv4 address or an IPv6 address.
+.TP
+.BI encap " ENCAP"
+set the encapsulation type of the tunnel.
+.br
+Valid values for encapsulation are:
+.BR udp ", " ip "."
+.TP
+.BI udp_sport " PORT"
+set the UDP source port to be used for the tunnel. Must be present
+when udp encapsulation is selected. Ignored when ip encapsulation is
+selected.
+.TP
+.BI udp_dport " PORT"
+set the UDP destination port to be used for the tunnel. Must be
+present when udp encapsulation is selected. Ignored when ip
+encapsulation is selected.
+.SS ip l2tp del tunnel - destroy a tunnel
+.TP
+.BI tunnel_id " ID"
+set the tunnel id of the tunnel to be deleted. All sessions within the
+tunnel must be deleted first.
+.SS ip l2tp show tunnel - show information about tunnels
+.TP
+.BI tunnel_id " ID"
+set the tunnel id of the tunnel to be shown. If not specified,
+information about all tunnels is printed.
+.SS ip l2tp add session - add a new session to a tunnel
+.TP
+.BI name " NAME "
+sets the session network interface name. Default is l2tpethN.
+.TP
+.BI tunnel_id " ID"
+set the tunnel id, which is a 32-bit integer value. Uniquely
+identifies the tunnel into which the session will be created. The
+tunnel must already exist.
+.TP
+.BI session_id " ID"
+set the session id, which is a 32-bit integer value. Uniquely
+identifies the session being created. The value used must match the
+peer_session_id value being used at the peer.
+.TP
+.BI peer_session_id " ID"
+set the peer session id, which is a 32-bit integer value assigned to
+the session by the peer. The value used must match the session_id
+value being used at the peer.
+.TP
+.BI cookie " HEXSTR"
+sets an optional cookie value to be assigned to the session. This is a
+4 or 8 byte value, specified as 8 or 16 hex digits,
+e.g. 014d3636deadbeef. The value must match the peer_cookie value set
+at the peer. The cookie value is carried in L2TP data packets and is
+checked for expected value at the peer. Default is to use no cookie.
+.TP
+.BI peer_cookie " HEXSTR"
+sets an optional peer cookie value to be assigned to the session. This
+is a 4 or 8 byte value, specified as 8 or 16 hex digits,
+e.g. 014d3636deadbeef. The value must match the cookie value set at
+the peer. It tells the local system what cookie value to expect to
+find in received L2TP packets. Default is to use no cookie.
+.TP
+.BI l2spec_type " L2SPECTYPE"
+set the layer2specific header type of the session.
+.br
+Valid values are:
+.BR none ", " udp "."
+.TP
+.BI offset " OFFSET"
+sets the byte offset from the L2TP header where user data starts in
+transmitted L2TP data packets. This is hardly ever used. If set, the
+value must match the peer_offset value used at the peer. Default is 0.
+.TP
+.BI peer_offset " OFFSET"
+sets the byte offset from the L2TP header where user data starts in
+received L2TP data packets. This is hardly ever used. If set, the
+value must match the offset value used at the peer. Default is 0.
+.SS ip l2tp del session - destroy a session
+.TP
+.BI tunnel_id " ID"
+set the tunnel id in which the session to be deleted is located.
+.TP
+.BI session_id " ID"
+set the session id of the session to be deleted.
+.SS ip l2tp show session - show information about sessions
+.TP
+.BI tunnel_id " ID"
+set the tunnel id of the session(s) to be shown. If not specified,
+information about sessions in all tunnels is printed.
+.TP
+.BI session_id " ID"
+set the session id of the session to be shown. If not specified,
+information about all sessions is printed.
+.SH EXAMPLES
+.PP
+.SS Setup L2TP tunnels and sessions
+.nf
+site-A:# ip l2tp add tunnel tunnel_id 3000 peer_tunnel_id 4000 \\
+ encap udp local 1.2.3.4 remote 5.6.7.8 \\
+ udp_sport 5000 udp_dport 6000
+site-A:# ip l2tp add session tunnel_id 3000 session_id 1000 \\
+ peer_session_id 2000
+
+site-B:# ip l2tp add tunnel tunnel_id 4000 peer_tunnel_id 3000 \\
+ encap udp local 5.6.7.8 remote 1.2.3.4 \\
+ udp_sport 6000 udp_dport 5000
+site-B:# ip l2tp add session tunnel_id 4000 session_id 2000 \\
+ peer_session_id 1000
+
+site-A:# ip link set l2tpeth0 up mtu 1488
+
+site-B:# ip link set l2tpeth0 up mtu 1488
+.fi
+.PP
+Notice that the IP addresses, UDP ports and tunnel / session ids are
+matched and reversed at each site.
+.SS Configure as IP interfaces
+The two interfaces can be configured with IP addresses if only IP data
+is to be carried. This is perhaps the simplest configuration.
+.PP
+.nf
+site-A:# ip addr add 10.42.1.1 peer 10.42.1.2 dev l2tpeth0
+
+site-B:# ip addr add 10.42.1.2 peer 10.42.1.1 dev l2tpeth0
+
+site-A:# ping 10.42.1.2
+.fi
+.PP
+Now the link should be usable. Add static routes as needed to have
+data sent over the new link.
+.PP
+.SS Configure as bridged interfaces
+To carry non-IP data, the L2TP network interface is added to a bridge
+instead of being assigned its own IP address, using standard Linux
+utilities. Since raw ethernet frames are then carried inside the
+tunnel, the MTU of the L2TP interfaces must be set to allow space for
+those headers.
+.PP
+.nf
+site-A:# ip link set l2tpeth0 up mtu 1446
+site-A:# ip link add br0 type bridge
+site-A:# ip link set l2tpeth0 master br0
+site-A:# ip link set eth0 master br0
+site-A:# ip link set br0 up
+.fi
+.PP
+If you are using VLANs, setup a bridge per VLAN and bridge each VLAN
+over a separate L2TP session. For example, to bridge VLAN ID 5 on eth1
+over an L2TP pseudowire:
+.PP
+.nf
+site-A:# ip link set l2tpeth0 up mtu 1446
+site-A:# ip link add brvlan5 type bridge
+site-A:# ip link set l2tpeth0.5 master brvlan5
+site-A:# ip link set eth1.5 master brvlan5
+site-A:# ip link set brvlan5 up
+.fi
+.PP
+Adding the L2TP interface to a bridge causes the bridge to forward
+traffic over the L2TP pseudowire just like it forwards over any other
+interface. The bridge learns MAC addresses of hosts attached to each
+interface and intelligently forwards frames from one bridge port to
+another. IP addresses are not assigned to the l2tpethN interfaces. If
+the bridge is correctly configured at both sides of the L2TP
+pseudowire, it should be possible to reach hosts in the peer's bridged
+network.
+.PP
+When raw ethernet frames are bridged across an L2TP tunnel, large
+frames may be fragmented and forwarded as individual IP fragments to
+the recipient, depending on the MTU of the physical interface used by
+the tunnel. When the ethernet frames carry protocols which are
+reassembled by the recipient, like IP, this isn't a problem. However,
+such fragmentation can cause problems for protocols like PPPoE where
+the recipient expects to receive ethernet frames exactly as
+transmitted. In such cases, it is important that frames leaving the
+tunnel are reassembled back into a single frame before being
+forwarded on. To do so, enable netfilter connection tracking
+(conntrack) or manually load the Linux netfilter defrag modules at
+each tunnel endpoint.
+.PP
+.nf
+site-A:# modprobe nf_defrag_ipv4
+
+site-B:# modprobe nf_defrag_ipv4
+.fi
+.PP
+If L2TP is being used over IPv6, use the IPv6 defrag module.
+.SH INTEROPERABILITY
+.PP
+Unmanaged (static) L2TPv3 tunnels are supported by some network
+equipment equipment vendors such as Cisco.
+.PP
+In Linux, L2TP Hello messages are not supported in unmanaged
+tunnels. Hello messages are used by L2TP clients and servers to detect
+link failures in order to automate tearing down and reestablishing
+dynamic tunnels. If a non-Linux peer supports Hello messages in
+unmanaged tunnels, it must be turned off to interoperate with Linux.
+.PP
+Linux defaults to use the Default Layer2SpecificHeader type as defined
+in the L2TPv3 protocol specification, RFC3931. This setting must be
+consistent with that configured at the peer. Some vendor
+implementations (e.g. Cisco) default to use a Layer2SpecificHeader
+type of None.
+.SH SEE ALSO
+.br
+.BR ip (8)
+.SH AUTHOR
+James Chapman <jchapman@katalix.com>
diff --git a/iproute2/man/man8/ip-link.8.in b/iproute2/man/man8/ip-link.8.in
new file mode 100644
index 0000000..4d32343
--- /dev/null
+++ b/iproute2/man/man8/ip-link.8.in
@@ -0,0 +1,1189 @@
+.TH IP\-LINK 8 "13 Dec 2012" "iproute2" "Linux"
+.SH "NAME"
+ip-link \- network device configuration
+.SH "SYNOPSIS"
+.sp
+.ad l
+.in +8
+.ti -8
+.B ip
+.RI "[ " OPTIONS " ]"
+.B link
+.RI " { " COMMAND " | "
+.BR help " }"
+.sp
+
+.ti -8
+.IR OPTIONS " := { "
+\fB\-V\fR[\fIersion\fR] |
+\fB\-h\fR[\fIuman-readable\fR] |
+\fB\-s\fR[\fItatistics\fR] |
+\fB\-r\fR[\fIesolve\fR] |
+\fB\-f\fR[\fIamily\fR] {
+.BR inet " | " inet6 " | " ipx " | " dnet " | " link " } | "
+\fB\-o\fR[\fIneline\fR] |
+\fB\-br\fR[\fIief\fR] }
+
+.ti -8
+.BI "ip link add"
+.RB "[ " link
+.IR DEVICE " ]"
+.RB "[ " name " ]"
+.I NAME
+.br
+.RB "[ " txqueuelen
+.IR PACKETS " ]"
+.br
+.RB "[ " address
+.IR LLADDR " ]"
+.RB "[ " broadcast
+.IR LLADDR " ]"
+.br
+.RB "[ " mtu
+.IR MTU " ]"
+.RB "[ " index
+.IR IDX " ]"
+.br
+.RB "[ " numtxqueues
+.IR QUEUE_COUNT " ]"
+.RB "[ " numrxqueues
+.IR QUEUE_COUNT " ]"
+.br
+.BR type " TYPE"
+.RI "[ " ARGS " ]"
+
+.ti -8
+.IR TYPE " := [ "
+.BR bridge " | "
+.BR bond " | "
+.BR can " | "
+.BR dummy " | "
+.BR hsr " | "
+.BR ifb " | "
+.BR ipoib " |"
+.BR macvlan " | "
+.BR macvtap " | "
+.BR vcan " | "
+.BR veth " | "
+.BR vlan " | "
+.BR vxlan " |"
+.BR ip6tnl " |"
+.BR ipip " |"
+.BR sit " |"
+.BR gre " |"
+.BR gretap " |"
+.BR ip6gre " |"
+.BR ip6gretap " |"
+.BR vti " |"
+.BR nlmon " |"
+.BR ipvlan " |"
+.BR lowpan " |"
+.BR geneve " ]"
+
+.ti -8
+.BR "ip link delete " {
+.IR DEVICE " | "
+.BI "group " GROUP
+}
+.BI type " TYPE"
+.RI "[ " ARGS " ]"
+
+.ti -8
+.BR "ip link set " {
+.IR DEVICE " | "
+.BI "group " GROUP
+.RB "} { " up " | " down " | " arp " { " on " | " off " } |"
+.br
+.BR promisc " { " on " | " off " } |"
+.br
+.BR allmulticast " { " on " | " off " } |"
+.br
+.BR dynamic " { " on " | " off " } |"
+.br
+.BR multicast " { " on " | " off " } |"
+.br
+.BR protodown " { " on " | " off " } |"
+.br
+.B txqueuelen
+.IR PACKETS " |"
+.br
+.B name
+.IR NEWNAME " |"
+.br
+.B address
+.IR LLADDR " |"
+.B broadcast
+.IR LLADDR " |"
+.br
+.B mtu
+.IR MTU " |"
+.br
+.B netns
+.IR PID " |"
+.br
+.B netns
+.IR NETNSNAME " |"
+.br
+.B alias
+.IR NAME " |"
+.br
+.B vf
+.IR NUM " ["
+.B mac
+.IR LLADDR " ] ["
+.B vlan
+.IR VLANID " [ "
+.B qos
+.IR VLAN-QOS " ] ] ["
+.B rate
+.IR TXRATE " ] ["
+.B max_tx_rate
+.IR TXRATE " ] ["
+.B min_tx_rate
+.IR TXRATE " ] ["
+.B spoofchk { on | off } ] [
+.B state { auto | enable | disable}
+] |
+.br
+.B master
+.IR DEVICE " |"
+.br
+.B nomaster " |"
+.br
+.B addrgenmode { eui64 | none | stable_secret | random }
+.br
+.B link-netnsid ID
+.BR " }"
+
+
+.ti -8
+.B ip link show
+.RI "[ " DEVICE " | "
+.B group
+.IR GROUP " | "
+.BR up " | "
+.B master
+.IR DEVICE " | "
+.B type
+.IR TYPE " ]"
+
+.ti -8
+.B ip link help
+.RI "[ " TYPE " ]"
+
+.SH "DESCRIPTION"
+.SS ip link add - add virtual link
+
+.TP
+.BI link " DEVICE "
+specifies the physical device to act operate on.
+
+.I NAME
+specifies the name of the new virtual device.
+
+.I TYPE
+specifies the type of the new device.
+.sp
+Link types:
+
+.in +8
+.B bridge
+- Ethernet Bridge device
+.sp
+.B bond
+- Bonding device
+.B can
+- Controller Area Network interface
+.sp
+.B dummy
+- Dummy network interface
+.sp
+.B hsr
+- High-availability Seamless Redundancy device
+.sp
+.B ifb
+- Intermediate Functional Block device
+.sp
+.B ipoib
+- IP over Infiniband device
+.sp
+.B macvlan
+- Virtual interface base on link layer address (MAC)
+.sp
+.B macvtap
+- Virtual interface based on link layer address (MAC) and TAP.
+.sp
+.B vcan
+- Virtual Controller Area Network interface
+.sp
+.B veth
+- Virtual ethernet interface
+.sp
+.BR vlan
+- 802.1q tagged virtual LAN interface
+.sp
+.BR vxlan
+- Virtual eXtended LAN
+.sp
+.BR ip6tnl
+- Virtual tunnel interface IPv4|IPv6 over IPv6
+.sp
+.BR ipip
+- Virtual tunnel interface IPv4 over IPv4
+.sp
+.BR sit
+- Virtual tunnel interface IPv6 over IPv4
+.sp
+.BR gre
+- Virtual tunnel interface GRE over IPv4
+.sp
+.BR gretap
+- Virtual L2 tunnel interface GRE over IPv4
+.sp
+.BR ip6gre
+- Virtual tunnel interface GRE over IPv6
+.sp
+.BR ip6gretap
+- Virtual L2 tunnel interface GRE over IPv6
+.sp
+.BR vti
+- Virtual tunnel interface
+.sp
+.BR nlmon
+- Netlink monitoring device
+.sp
+.BR ipvlan
+- Interface for L3 (IPv6/IPv4) based VLANs
+.sp
+.BR lowpan
+- Interface for 6LoWPAN (IPv6) over IEEE 802.15.4 / Bluetooth
+.sp
+.BR geneve
+- GEneric NEtwork Virtualization Encapsulation
+.in -8
+
+.TP
+.BI numtxqueues " QUEUE_COUNT "
+specifies the number of transmit queues for new device.
+
+.TP
+.BI numrxqueues " QUEUE_COUNT "
+specifies the number of receive queues for new device.
+
+.TP
+.BI index " IDX "
+specifies the desired index of the new virtual device. The link creation fails, if the index is busy.
+
+.TP
+VLAN Type Support
+For a link of type
+.I VLAN
+the following additional arguments are supported:
+
+.BI "ip link add
+.BI link " DEVICE "
+.BI name " NAME "
+.BI type " vlan "
+[
+.BI protocol " VLAN_PROTO "
+]
+.BI id " VLANID "
+[
+.BR reorder_hdr " { " on " | " off " } "
+]
+[
+.BR gvrp " { " on " | " off " } "
+]
+[
+.BR mvrp " { " on " | " off " } "
+]
+[
+.BR loose_binding " { " on " | " off " } "
+]
+[
+.BI ingress-qos-map " QOS-MAP "
+]
+[
+.BI egress-qos-map " QOS-MAP "
+]
+
+.in +8
+.sp
+.BI protocol " VLAN_PROTO "
+- either 802.1Q or 802.1ad.
+
+.BI id " VLANID "
+- specifies the VLAN Identifer to use. Note that numbers with a leading " 0 " or " 0x " are interpreted as octal or hexadeimal, respectively.
+
+.BR reorder_hdr " { " on " | " off " } "
+- specifies whether ethernet headers are reordered or not (default is
+.BR on ")."
+
+.in +4
+If
+.BR reorder_hdr " is " on
+then VLAN header will be not inserted immediately but only before passing to the
+physical device (if this device does not support VLAN offloading), the similar
+on the RX direction - by default the packet will be untagged before being
+received by VLAN device. Reordering allows to accelerate tagging on egress and
+to hide VLAN header on ingress so the packet looks like regular Ethernet packet,
+at the same time it might be confusing for packet capture as the VLAN header
+does not exist within the packet.
+
+VLAN offloading can be checked by
+.BR ethtool "(8):"
+.in +4
+.sp
+.B ethtool -k
+<phy_dev> |
+.RB grep " tx-vlan-offload"
+.sp
+.in -4
+where <phy_dev> is the physical device to which VLAN device is bound.
+.in -4
+
+.BR gvrp " { " on " | " off " } "
+- specifies whether this VLAN should be registered using GARP VLAN Registration Protocol.
+
+.BR mvrp " { " on " | " off " } "
+- specifies whether this VLAN should be registered using Multiple VLAN Registration Protocol.
+
+.BR loose_binding " { " on " | " off " } "
+- specifies whether the VLAN device state is bound to the physical device state.
+
+.BI ingress-qos-map " QOS-MAP "
+- defines a mapping of VLAN header prio field to the Linux internal packet
+priority on incoming frames. The format is FROM:TO with multiple mappings
+separated by spaces.
+
+.BI egress-qos-map " QOS-MAP "
+- defines a mapping of Linux internal packet priority to VLAN header prio field
+but for outgoing frames. The format is the same as for ingress-qos-map.
+.in +4
+
+Linux packet priority can be set by
+.BR iptables "(8)":
+.in +4
+.sp
+.B iptables
+-t mangle -A POSTROUTING [...] -j CLASSIFY --set-class 0:4
+.sp
+.in -4
+and this "4" priority can be used in the egress qos mapping to set VLAN prio "5":
+.sp
+.in +4
+.B ip
+link set veth0.10 type vlan egress 4:5
+.in -4
+.in -4
+.in -8
+
+.TP
+VXLAN Type Support
+For a link of type
+.I VXLAN
+the following additional arguments are supported:
+
+.BI "ip link add " DEVICE
+.BI type " vxlan " id " ID"
+[
+.BI dev " PHYS_DEV "
+.RB " ] [ { " group " | " remote " } "
+.I IPADDR
+] [
+.B local
+.RI "{ "IPADDR " | "any " } "
+] [
+.BI ttl " TTL "
+] [
+.BI tos " TOS "
+] [
+.BI dstport " PORT "
+] [
+.BI srcport " MIN MAX "
+] [
+.I "[no]learning "
+] [
+.I "[no]proxy "
+] [
+.I "[no]rsc "
+] [
+.I "[no]l2miss "
+] [
+.I "[no]l3miss "
+] [
+.I "[no]udpcsum "
+] [
+.I "[no]udp6zerocsumtx "
+] [
+.I "[no]udp6zerocsumrx "
+] [
+.BI ageing " SECONDS "
+] [
+.BI maxaddress " NUMBER "
+] [
+.B gbp
+]
+
+.in +8
+.sp
+.BI id " VNI "
+- specifies the VXLAN Network Identifer (or VXLAN Segment
+Identifier) to use.
+
+.BI dev " PHYS_DEV"
+- specifies the physical device to use for tunnel endpoint communication.
+
+.sp
+.BI group " IPADDR"
+- specifies the multicast IP address to join.
+This parameter cannot be specified with the
+.B remote
+parameter.
+
+.sp
+.BI remote " IPADDR"
+- specifies the unicast destination IP address to use in outgoing packets
+when the destination link layer address is not known in the VXLAN device
+forwarding database. This parameter cannot be specified with the
+.B group
+parameter.
+
+.sp
+.BI local " IPADDR"
+- specifies the source IP address to use in outgoing packets.
+
+.sp
+.BI ttl " TTL"
+- specifies the TTL value to use in outgoing packets.
+
+.sp
+.BI tos " TOS"
+- specifies the TOS value to use in outgoing packets.
+
+.sp
+.BI dstport " PORT"
+- specifies the UDP destination port to communicate to the remote VXLAN tunnel endpoint.
+
+.sp
+.BI srcport " MIN MAX"
+- specifies the range of port numbers to use as UDP
+source ports to communicate to the remote VXLAN tunnel endpoint.
+
+.sp
+.I [no]learning
+- specifies if unknown source link layer addresses and IP addresses
+are entered into the VXLAN device forwarding database.
+
+.sp
+.I [no]rsc
+- specifies if route short circuit is turned on.
+
+.sp
+.I [no]proxy
+- specifies ARP proxy is turned on.
+
+.sp
+.I [no]l2miss
+- specifies if netlink LLADDR miss notifications are generated.
+
+.sp
+.I [no]l3miss
+- specifies if netlink IP ADDR miss notifications are generated.
+
+.sp
+.I [no]udpcsum
+- specifies if UDP checksum is filled in
+
+.sp
+.I [no]udp6zerocsumtx
+- specifies if UDP checksum is filled in
+
+.sp
+.I [no]udp6zerocsumrx
+- specifies if UDP checksum is received
+
+.sp
+.BI ageing " SECONDS"
+- specifies the lifetime in seconds of FDB entries learnt by the kernel.
+
+.sp
+.BI maxaddress " NUMBER"
+- specifies the maximum number of FDB entries.
+
+.sp
+.B gbp
+- enables the Group Policy extension (VXLAN-GBP).
+
+.in +4
+Allows to transport group policy context across VXLAN network peers.
+If enabled, includes the mark of a packet in the VXLAN header for outgoing
+packets and fills the packet mark based on the information found in the
+VXLAN header for incomming packets.
+
+Format of upper 16 bits of packet mark (flags);
+
+.in +2
++-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+.br
+|-|-|-|-|-|-|-|-|-|D|-|-|A|-|-|-|
+.br
++-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+
+.B D :=
+Don't Learn bit. When set, this bit indicates that the egress
+VTEP MUST NOT learn the source address of the encapsulated frame.
+
+.B A :=
+Indicates that the group policy has already been applied to
+this packet. Policies MUST NOT be applied by devices when the A bit is set.
+.in -2
+
+Format of lower 16 bits of packet mark (policy ID):
+
+.in +2
++-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+.br
+| Group Policy ID |
+.br
++-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+.in -2
+
+Example:
+ iptables -A OUTPUT [...] -j MARK --set-mark 0x800FF
+
+.in -4
+
+.in -8
+
+.TP
+GRE, IPIP, SIT Type Support
+For a link of types
+.I GRE/IPIP/SIT
+the following additional arguments are supported:
+
+.BI "ip link add " DEVICE
+.BR type " { gre | ipip | sit } "
+.BI " remote " ADDR " local " ADDR
+[
+.BR encap " { fou | gue | none } "
+] [
+.BI "encap-sport { " PORT " | auto } "
+] [
+.BI "encap-dport " PORT
+] [
+.I " [no]encap-csum "
+] [
+.I " [no]encap-remcsum "
+]
+
+.in +8
+.sp
+.BI remote " ADDR "
+- specifies the remote address of the tunnel.
+
+.sp
+.BI local " ADDR "
+- specifies the fixed local address for tunneled packets.
+It must be an address on another interface on this host.
+
+.sp
+.BR encap " { fou | gue | none } "
+- specifies type of secondary UDP encapsulation. "fou" indicates
+Foo-Over-UDP, "gue" indicates Generic UDP Encapsulation.
+
+.sp
+.BI "encap-sport { " PORT " | auto } "
+- specifies the source port in UDP encapsulation.
+.IR PORT
+indicates the port by number, "auto"
+indicates that the port number should be chosen automatically
+(the kernel picks a flow based on the flow hash of the
+encapsulated packet).
+
+.sp
+.I [no]encap-csum
+- specifies if UDP checksums are enabled in the secondary
+encapsulation.
+
+.sp
+.I [no]encap-remcsum
+- specifies if Remote Checksum Offload is enabled. This is only
+applicable for Generic UDP Encapsulation.
+
+.in -8
+
+.TP
+IP6GRE/IP6GRETAP Type Support
+For a link of type
+.I IP6GRE/IP6GRETAP
+the following additional arguments are supported:
+
+.BI "ip link add " DEVICE
+.BI type " { ip6gre | ip6gretap } " remote " ADDR " local " ADDR
+[
+.I "[i|o]seq]"
+] [
+.I "[i|o]key" KEY
+] [
+.I " [i|o]csum "
+] [
+.BI hoplimit " TTL "
+] [
+.BI encaplimit " ELIM "
+] [
+.BI tclass " TCLASS "
+] [
+.BI flowlabel " FLOWLABEL "
+] [
+.BI "dscp inherit"
+] [
+.BI dev " PHYS_DEV "
+]
+
+.in +8
+.sp
+.BI remote " ADDR "
+- specifies the remote IPv6 address of the tunnel.
+
+.sp
+.BI local " ADDR "
+- specifies the fixed local IPv6 address for tunneled packets.
+It must be an address on another interface on this host.
+
+.sp
+.BI [i|o]seq
+- serialize packets.
+The
+.B oseq
+flag enables sequencing of outgoing packets.
+The
+.B iseq
+flag requires that all input packets are serialized.
+
+.sp
+.BI [i|o]key " KEY"
+- use keyed GRE with key
+.IR KEY ". "KEY
+is either a number or an IPv4 address-like dotted quad.
+The
+.B key
+parameter specifies the same key to use in both directions.
+The
+.BR ikey " and " okey
+parameters specify different keys for input and output.
+
+.sp
+.BI [i|o]csum
+- generate/require checksums for tunneled packets.
+The
+.B ocsum
+flag calculates checksums for outgoing packets.
+The
+.B icsum
+flag requires that all input packets have the correct
+checksum. The
+.B csum
+flag is equivalent to the combination
+.BR "icsum ocsum" .
+
+.sp
+.BI hoplimit " TTL"
+- specifies Hop Limit value to use in outgoing packets.
+
+.sp
+.BI encaplimit " ELIM"
+- specifies a fixed encapsulation limit. Default is 4.
+
+.sp
+.BI flowlabel " FLOWLABEL"
+- specifies a fixed flowlabel.
+
+.sp
+.BI tclass " TCLASS"
+- specifies the traffic class field on
+tunneled packets, which can be specified as either a two-digit
+hex value (e.g. c0) or a predefined string (e.g. internet).
+The value
+.B inherit
+causes the field to be copied from the original IP header. The
+values
+.BI "inherit/" STRING
+or
+.BI "inherit/" 00 ".." ff
+will set the field to
+.I STRING
+or
+.IR 00 ".." ff
+when tunneling non-IP packets. The default value is 00.
+
+.in -8
+
+.TP
+IPoIB Type Support
+For a link of type
+.I IPoIB
+the following additional arguments are supported:
+
+.BI "ip link add " DEVICE " name " NAME
+.BI type " ipoib [ " pkey " PKEY ] [" mode " MODE " ]
+
+.in +8
+.sp
+.BI pkey " PKEY "
+- specifies the IB P-Key to use.
+
+.BI mode " MODE "
+- specifies the mode (datagram or connected) to use.
+
+.TP
+GENEVE Type Support
+For a link of type
+.I GENEVE
+the following additional arguments are supported:
+
+.BI "ip link add " DEVICE
+.BI type " geneve " id " ID " remote " IPADDR"
+[
+.BI ttl " TTL "
+] [
+.BI tos " TOS "
+]
+
+.in +8
+.sp
+.BI id " VNI "
+- specifies the Virtual Network Identifer to use.
+
+.sp
+.BI remote " IPADDR"
+- specifies the unicast destination IP address to use in outgoing packets.
+
+.sp
+.BI ttl " TTL"
+- specifies the TTL value to use in outgoing packets.
+
+.sp
+.BI tos " TOS"
+- specifies the TOS value to use in outgoing packets.
+
+.in -8
+
+.TP
+MACVLAN and MACVTAP Type Support
+For a link of type
+.I MACVLAN
+or
+.I MACVTAP
+the following additional arguments are supported:
+
+.BI "ip link add link " DEVICE " name " NAME
+.BR type " { " macvlan " | " macvtap " } "
+.BR mode " { " private " | " vepa " | " bridge " | " passthru
+.BR " [ " nopromisc " ] } "
+
+.in +8
+.sp
+.BR type " { " macvlan " | " macvtap " } "
+- specifies the link type to use.
+.BR macvlan " creates just a virtual interface, while "
+.BR macvtap " in addition creates a character device "
+.BR /dev/tapX " to be used just like a " tuntap " device."
+
+.B mode private
+- Do not allow communication between
+.B macvlan
+instances on the same physical interface, even if the external switch supports
+hairpin mode.
+
+.B mode vepa
+- Virtual Ethernet Port Aggregator mode. Data from one
+.B macvlan
+instance to the other on the same physical interface is transmitted over the
+physical interface. Either the attached switch needs to support hairpin mode,
+or there must be a TCP/IP router forwarding the packets in order to allow
+communication. This is the default mode.
+
+.B mode bridge
+- In bridge mode, all endpoints are directly connected to each other,
+communication is not redirected through the physical interface's peer.
+
+.BR mode " " passthru " [ " nopromisc " ] "
+- This mode gives more power to a single endpoint, usually in
+.BR macvtap " mode. It is not allowed for more than one endpoint on the same "
+physical interface. All traffic will be forwarded to this endpoint, allowing
+virtio guests to change MAC address or set promiscuous mode in order to bridge
+the interface or create vlan interfaces on top of it. By default, this mode
+forces the underlying interface into promiscuous mode. Passing the
+.BR nopromisc " flag prevents this, so the promisc flag may be controlled "
+using standard tools.
+.in -8
+
+.SS ip link delete - delete virtual link
+
+.TP
+.BI dev " DEVICE "
+specifies the virtual device to act operate on.
+
+.TP
+.BI group " GROUP "
+specifies the group of virtual links to delete. Group 0 is not allowed to be
+deleted since it is the default group.
+
+.TP
+.BI type " TYPE "
+specifies the type of the device.
+
+.SS ip link set - change device attributes
+
+.TP
+.BI dev " DEVICE "
+.I DEVICE
+specifies network device to operate on. When configuring SR-IOV Virtual Function
+(VF) devices, this keyword should specify the associated Physical Function (PF)
+device.
+
+.TP
+.BI group " GROUP "
+.I GROUP
+has a dual role: If both group and dev are present, then move the device to the
+specified group. If only a group is specified, then the command operates on
+all devices in that group.
+
+.TP
+.BR up " and " down
+change the state of the device to
+.B UP
+or
+.BR "DOWN" .
+
+.TP
+.BR "arp on " or " arp off"
+change the
+.B NOARP
+flag on the device.
+
+.TP
+.BR "multicast on " or " multicast off"
+change the
+.B MULTICAST
+flag on the device.
+
+.TP
+.BR "protodown on " or " protodown off"
+change the
+.B PROTODOWN
+state on the device. Indicates that a protocol error has been detected on the port. Switch drivers can react to this error by doing a phys down on the switch port.
+
+.TP
+.BR "dynamic on " or " dynamic off"
+change the
+.B DYNAMIC
+flag on the device. Indicates that address can change when interface goes down (currently
+.B NOT
+used by the Linux).
+
+.TP
+.BI name " NAME"
+change the name of the device. This operation is not
+recommended if the device is running or has some addresses
+already configured.
+
+.TP
+.BI txqueuelen " NUMBER"
+.TP
+.BI txqlen " NUMBER"
+change the transmit queue length of the device.
+
+.TP
+.BI mtu " NUMBER"
+change the
+.I MTU
+of the device.
+
+.TP
+.BI address " LLADDRESS"
+change the station address of the interface.
+
+.TP
+.BI broadcast " LLADDRESS"
+.TP
+.BI brd " LLADDRESS"
+.TP
+.BI peer " LLADDRESS"
+change the link layer broadcast address or the peer address when
+the interface is
+.IR "POINTOPOINT" .
+
+.TP
+.BI netns " NETNSNAME " \fR| " PID"
+move the device to the network namespace associated with name
+.IR "NETNSNAME " or
+.RI process " PID".
+
+Some devices are not allowed to change network namespace: loopback, bridge,
+ppp, wireless. These are network namespace local devices. In such case
+.B ip
+tool will return "Invalid argument" error. It is possible to find out if device is local
+to a single network namespace by checking
+.B netns-local
+flag in the output of the
+.BR ethtool ":"
+
+.in +8
+.B ethtool -k
+.I DEVICE
+.in -8
+
+To change network namespace for wireless devices the
+.B iw
+tool can be used. But it allows to change network namespace only for physical devices and by process
+.IR PID .
+
+.TP
+.BI alias " NAME"
+give the device a symbolic name for easy reference.
+
+.TP
+.BI group " GROUP"
+specify the group the device belongs to.
+The available groups are listed in file
+.BR "@SYSCONFDIR@/group" .
+
+.TP
+.BI vf " NUM"
+specify a Virtual Function device to be configured. The associated PF device
+must be specified using the
+.B dev
+parameter.
+
+.in +8
+.BI mac " LLADDRESS"
+- change the station address for the specified VF. The
+.B vf
+parameter must be specified.
+
+.sp
+.BI vlan " VLANID"
+- change the assigned VLAN for the specified VF. When specified, all traffic
+sent from the VF will be tagged with the specified VLAN ID. Incoming traffic
+will be filtered for the specified VLAN ID, and will have all VLAN tags
+stripped before being passed to the VF. Setting this parameter to 0 disables
+VLAN tagging and filtering. The
+.B vf
+parameter must be specified.
+
+.sp
+.BI qos " VLAN-QOS"
+- assign VLAN QOS (priority) bits for the VLAN tag. When specified, all VLAN
+tags transmitted by the VF will include the specified priority bits in the
+VLAN tag. If not specified, the value is assumed to be 0. Both the
+.B vf
+and
+.B vlan
+parameters must be specified. Setting both
+.B vlan
+and
+.B qos
+as 0 disables VLAN tagging and filtering for the VF.
+
+.sp
+.BI rate " TXRATE"
+-- change the allowed transmit bandwidth, in Mbps, for the specified VF.
+Setting this parameter to 0 disables rate limiting.
+.B vf
+parameter must be specified.
+Please use new API
+.B "max_tx_rate"
+option instead.
+
+.sp
+.BI max_tx_rate " TXRATE"
+- change the allowed maximum transmit bandwidth, in Mbps, for the specified VF.
+.B vf
+parameter must be specified.
+
+.sp
+.BI min_tx_rate " TXRATE"
+- change the allowed minimum transmit bandwidth, in Mbps, for the specified VF.
+Minimum TXRATE should be always <= Maximum TXRATE.
+.B vf
+parameter must be specified.
+
+.sp
+.BI spoofchk " on|off"
+- turn packet spoof checking on or off for the specified VF.
+.sp
+.BI state " auto|enable|disable"
+- set the virtual link state as seen by the specified VF. Setting to auto means a
+reflection of the PF link state, enable lets the VF to communicate with other VFs on
+this host even if the PF link state is down, disable causes the HW to drop any packets
+sent by the VF.
+.in -8
+
+.TP
+.BI master " DEVICE"
+set master device of the device (enslave device).
+
+.TP
+.BI nomaster
+unset master device of the device (release device).
+
+.TP
+.BI addrgenmode " eui64|none|stable_secret|random"
+set the IPv6 address generation mode
+
+.I eui64
+- use a Modified EUI-64 format interface identifier
+
+.I none
+- disable automatic address generation
+
+.I stable_secret
+- generate the interface identifier based on a preset /proc/sys/net/ipv6/conf/{default,DEVICE}/stable_secret
+
+.I random
+- like stable_secret, but auto-generate a new random secret if none is set
+
+.TP
+.BR "link-netnsid "
+set peer netnsid for a cross-netns interface
+
+.PP
+.B Warning:
+If multiple parameter changes are requested,
+.B ip
+aborts immediately after any of the changes have failed.
+This is the only case when
+.B ip
+can move the system to an unpredictable state. The solution
+is to avoid changing several parameters with one
+.B ip link set
+call.
+
+.SS ip link show - display device attributes
+
+.TP
+.BI dev " NAME " (default)
+.I NAME
+specifies the network device to show.
+If this argument is omitted all devices in the default group are listed.
+
+.TP
+.BI group " GROUP "
+.I GROUP
+specifies what group of devices to show.
+
+.TP
+.B up
+only display running interfaces.
+
+.TP
+.BI master " DEVICE "
+.I DEVICE
+specifies the master device which enslaves devices to show.
+
+.TP
+.BI type " TYPE "
+.I TYPE
+specifies the type of devices to show.
+
+.TP
+The show command has additional formatting options:
+
+.RS
+.TP
+.BR "\-s" , " \-stats", " \-statistics"
+output more statistics about packet usage.
+
+.TP
+.BR "\-d", " \-details"
+output more detailed information.
+
+.TP
+.BR "\-h", " \-human", " \-human-readable"
+output statistics with human readable values number followed by suffix
+
+.TP
+.BR "\-iec"
+print human readable rates in IEC units (ie. 1K = 1024).
+.RE
+
+.SS ip link help - display help
+
+.PP
+.I "TYPE"
+specifies which help of link type to dislpay.
+
+.SS
+.I GROUP
+may be a number or a string from the file
+.B @SYSCONFDIR@/group
+which can be manually filled.
+
+.SH "EXAMPLES"
+.PP
+ip link show
+.RS 4
+Shows the state of all network interfaces on the system.
+.RE
+.PP
+ip link show type bridge
+.RS 4
+Shows the bridge devices.
+.RE
+.PP
+ip link show type vlan
+.RS 4
+Shows the vlan devices.
+.RE
+.PP
+ip link show master br0
+.RS 4
+Shows devices enslaved by br0
+.RE
+.PP
+ip link set dev ppp0 mtu 1400
+.RS 4
+Change the MTU the ppp0 device.
+.RE
+.PP
+ip link add link eth0 name eth0.10 type vlan id 10
+.RS 4
+Creates a new vlan device eth0.10 on device eth0.
+.RE
+.PP
+ip link delete dev eth0.10
+.RS 4
+Removes vlan device.
+.RE
+
+ip link help gre
+.RS 4
+Display help for the gre link type.
+.RE
+.PP
+ip link add name tun1 type ipip remote 192.168.1.1
+local 192.168.1.2 ttl 225 encap gue encap-sport auto
+encap-dport 5555 encap-csum encap-remcsum
+.RS 4
+Creates an IPIP that is encapsulated with Generic UDP Encapsulation,
+and the outer UDP checksum and remote checksum offload are enabled.
+
+.RE
+.PP
+ip link add link wpan0 lowpan0 type lowpan
+.RS 4
+Creates a 6LoWPAN interface named lowpan0 on the underlying
+IEEE 802.15.4 device wpan0.
+.RE
+
+.SH SEE ALSO
+.br
+.BR ip (8),
+.BR ip-netns (8),
+.BR ethtool (8),
+.BR iptables (8)
+
+.SH AUTHOR
+Original Manpage by Michail Litvak <mci@owl.openwall.com>
diff --git a/iproute2/man/man8/ip-maddress.8 b/iproute2/man/man8/ip-maddress.8
new file mode 100644
index 0000000..f3432bb
--- /dev/null
+++ b/iproute2/man/man8/ip-maddress.8
@@ -0,0 +1,59 @@
+.TH IP\-MADDRESS 8 "20 Dec 2011" "iproute2" "Linux"
+.SH "NAME"
+ip-maddress \- multicast addresses management
+.SH "SYNOPSIS"
+.sp
+.ad l
+.in +8
+.ti -8
+.B ip
+.RI "[ " OPTIONS " ]"
+.B maddress
+.RI " { " COMMAND " | "
+.BR help " }"
+.sp
+.ti -8
+
+.BR "ip maddress" " [ " add " | " del " ]"
+.IB MULTIADDR " dev " NAME
+
+.ti -8
+.BR "ip maddress show" " [ " dev
+.IR NAME " ]"
+
+.SH DESCRIPTION
+.B maddress
+objects are multicast addresses.
+
+.SS ip maddress show - list multicast addresses
+
+.TP
+.BI dev " NAME " (default)
+the device name.
+
+.TP
+.B ip maddress add - add a multicast address
+.TP
+.B ip maddress delete - delete a multicast address
+.sp
+These commands attach/detach a static link-layer multicast address
+to listen on the interface.
+Note that it is impossible to join protocol multicast groups
+statically. This command only manages link-layer addresses.
+
+.RS
+.TP
+.BI address " LLADDRESS " (default)
+the link-layer multicast address.
+
+.TP
+.BI dev " NAME"
+the device to join/leave this multicast address.
+.RE
+
+.SH SEE ALSO
+.br
+.BR ip (8)
+
+.SH AUTHOR
+Original Manpage by Michail Litvak <mci@owl.openwall.com>
diff --git a/iproute2/man/man8/ip-monitor.8 b/iproute2/man/man8/ip-monitor.8
new file mode 100644
index 0000000..d2bd381
--- /dev/null
+++ b/iproute2/man/man8/ip-monitor.8
@@ -0,0 +1,135 @@
+.TH IP\-MONITOR 8 "13 Dec 2012" "iproute2" "Linux"
+.SH "NAME"
+ip-monitor, rtmon \- state monitoring
+.SH "SYNOPSIS"
+.sp
+.ad l
+.in +8
+.ti -8
+.BR "ip " " [ "
+.IR ip-OPTIONS " ]"
+.BR "monitor" " [ " all " |"
+.IR OBJECT-LIST " ] ["
+.BI file " FILENAME "
+] [
+.BI label
+] [
+.BI all-nsid
+] [
+.BI dev " DEVICE "
+]
+.sp
+
+.SH OPTIONS
+
+.TP
+.BR "\-t" , " \-timestamp"
+Prints timestamp before the event message on the separated line in format:
+ Timestamp: <Day> <Month> <DD> <hh:mm:ss> <YYYY> <usecs> usec
+ <EVENT>
+
+.TP
+.BR "\-ts" , " \-tshort"
+Prints short timestamp before the event message on the same line in format:
+ [<YYYY>-<MM>-<DD>T<hh:mm:ss>.<ms>] <EVENT>
+
+.SH DESCRIPTION
+The
+.B ip
+utility can monitor the state of devices, addresses
+and routes continuously. This option has a slightly different format.
+Namely, the
+.B monitor
+command is the first in the command line and then the object list follows:
+
+.BR "ip monitor" " [ " all " |"
+.IR OBJECT-LIST " ] ["
+.BI file " FILENAME "
+] [
+.BI label
+] [
+.BI all-nsid
+] [
+.BI dev " DEVICE "
+]
+
+.I OBJECT-LIST
+is the list of object types that we want to monitor.
+It may contain
+.BR link ", " address ", " route ", " mroute ", " prefix ", "
+.BR neigh ", " netconf ", " rule " and " nsid "."
+If no
+.B file
+argument is given,
+.B ip
+opens RTNETLINK, listens on it and dumps state changes in the format
+described in previous sections.
+
+.P
+If the
+.BI label
+option is set, a prefix is displayed before each message to
+show the family of the message. For example:
+.sp
+.in +2
+[NEIGH]10.16.0.112 dev eth0 lladdr 00:04:23:df:2f:d0 REACHABLE
+[LINK]3: eth1: <BROADCAST,MULTICAST> mtu 1500 qdisc pfifo_fast state DOWN group default
+ link/ether 52:54:00:12:34:57 brd ff:ff:ff:ff:ff:ff
+.in -2
+.sp
+
+.P
+If the
+.BI all-nsid
+option is set, the program listens to all network namespaces that have a
+nsid assigned into the network namespace were the program is running.
+A prefix is displayed to show the network namespace where the message
+originates. Example:
+.sp
+.in +2
+[nsid 0]10.16.0.112 dev eth0 lladdr 00:04:23:df:2f:d0 REACHABLE
+.in -2
+.sp
+
+.P
+If the
+.BI file
+option is given, the program does not listen on RTNETLINK,
+but opens the given file, and dumps its contents. The file
+should contain RTNETLINK messages saved in binary format.
+Such a file can be generated with the
+.B rtmon
+utility. This utility has a command line syntax similar to
+.BR "ip monitor" .
+Ideally,
+.B rtmon
+should be started before the first network configuration command
+is issued. F.e. if you insert:
+.sp
+.in +8
+rtmon file /var/log/rtmon.log
+.in -8
+.sp
+in a startup script, you will be able to view the full history
+later.
+
+.P
+Nevertheless, it is possible to start
+.B rtmon
+at any time.
+It prepends the history with the state snapshot dumped at the moment
+of starting.
+
+.P
+If the
+.BI dev
+option is given, the program prints only events related to this device.
+
+.SH SEE ALSO
+.br
+.BR ip (8)
+
+.SH AUTHOR
+Original Manpage by Michail Litvak <mci@owl.openwall.com>
+.br
+Manpage revised by Nicolas Dichtel <nicolas.dichtel@6wind.com>
diff --git a/iproute2/man/man8/ip-mroute.8 b/iproute2/man/man8/ip-mroute.8
new file mode 100644
index 0000000..e89b6b2
--- /dev/null
+++ b/iproute2/man/man8/ip-mroute.8
@@ -0,0 +1,58 @@
+.TH IP\-MROUTE 8 "13 Dec 2012" "iproute2" "Linux"
+.SH "NAME"
+ip-mroute \- multicast routing cache management
+.SH "SYNOPSIS"
+.sp
+.ad l
+.in +8
+.ti -8
+.BR "ip " " [ ip-OPTIONS ] " "mroute show" " [ [ "
+.BR " to " " ] "
+.IR PREFIX " ] [ "
+.B from
+.IR PREFIX " ] [ "
+.B iif
+.IR DEVICE " ] [ "
+.B table
+.IR TABLE_ID " ] "
+
+.SH DESCRIPTION
+.B mroute
+objects are multicast routing cache entries created by a user-level
+mrouting daemon (f.e.
+.B pimd
+or
+.B mrouted
+).
+
+Due to the limitations of the current interface to the multicast routing
+engine, it is impossible to change
+.B mroute
+objects administratively, so we can only display them. This limitation
+will be removed in the future.
+
+.SS ip mroute show - list mroute cache entries
+
+.TP
+.BI to " PREFIX " (default)
+the prefix selecting the destination multicast addresses to list.
+
+.TP
+.BI iif " NAME"
+the interface on which multicast packets are received.
+
+.TP
+.BI from " PREFIX"
+the prefix selecting the IP source addresses of the multicast route.
+
+.TP
+.BI table " TABLE_ID"
+the table id selecting the multicast table. It can be
+.BR local ", " main ", " default ", " all " or a number."
+
+.SH SEE ALSO
+.br
+.BR ip (8)
+
+.SH AUTHOR
+Original Manpage by Michail Litvak <mci@owl.openwall.com>
diff --git a/iproute2/man/man8/ip-neighbour.8 b/iproute2/man/man8/ip-neighbour.8
new file mode 100644
index 0000000..c9b0256
--- /dev/null
+++ b/iproute2/man/man8/ip-neighbour.8
@@ -0,0 +1,204 @@
+.TH IP\-NEIGHBOUR 8 "20 Dec 2011" "iproute2" "Linux"
+.SH "NAME"
+ip-neighbour \- neighbour/arp tables management.
+.SH "SYNOPSIS"
+.sp
+.ad l
+.in +8
+.ti -8
+.B ip
+.RI "[ " OPTIONS " ]"
+.B neigh
+.RI " { " COMMAND " | "
+.BR help " }"
+.sp
+
+.ti -8
+.BR "ip neigh" " { " add " | " del " | " change " | " replace " } { "
+.IR ADDR " [ "
+.B lladdr
+.IR LLADDR " ] [ "
+.BR nud " { " permanent " | " noarp " | " stale " | " reachable " } ] | " proxy
+.IR ADDR " } [ "
+.B dev
+.IR DEV " ]"
+
+.ti -8
+.BR "ip neigh" " { " show " | " flush " } [ " proxy " ] [ " to
+.IR PREFIX " ] [ "
+.B dev
+.IR DEV " ] [ "
+.B nud
+.IR STATE " ]"
+
+
+.SH DESCRIPTION
+The
+.B ip neigh
+command manipulates
+.I neighbour
+objects that establish bindings between protocol addresses and
+link layer addresses for hosts sharing the same link.
+Neighbour entries are organized into tables. The IPv4 neighbour table
+is also known by another name - the ARP table.
+
+.P
+The corresponding commands display neighbour bindings
+and their properties, add new neighbour entries and delete old ones.
+
+.TP
+ip neighbour add
+add a new neighbour entry
+.TP
+ip neighbour change
+change an existing entry
+.TP
+ip neighbour replace
+add a new entry or change an existing one
+.RS
+.PP
+These commands create new neighbour records or update existing ones.
+
+.TP
+.BI to " ADDRESS " (default)
+the protocol address of the neighbour. It is either an IPv4 or IPv6 address.
+
+.TP
+.BI dev " NAME"
+the interface to which this neighbour is attached.
+
+.TP
+.BI lladdr " LLADDRESS"
+the link layer address of the neighbour.
+.I LLADDRESS
+can also be
+.BR "null" .
+
+.TP
+.BI nud " NUD_STATE"
+the state of the neighbour entry.
+.B nud
+is an abbreviation for 'Neighbour Unreachability Detection'.
+The state can take one of the following values:
+
+.TP
+.B permanent
+the neighbour entry is valid forever and can be only
+be removed administratively.
+.TP
+.B noarp
+the neighbour entry is valid. No attempts to validate
+this entry will be made but it can be removed when its lifetime expires.
+.TP
+.B reachable
+the neighbour entry is valid until the reachability
+timeout expires.
+.TP
+.B stale
+the neighbour entry is valid but suspicious.
+This option to
+.B ip neigh
+does not change the neighbour state if it was valid and the address
+is not changed by this command.
+.RE
+
+.TP
+ip neighbour delete
+delete a neighbour entry
+.RS
+.PP
+The arguments are the same as with
+.BR "ip neigh add" ,
+except that
+.B lladdr
+and
+.B nud
+are ignored.
+
+.PP
+.B Warning:
+Attempts to delete or manually change a
+.B noarp
+entry created by the kernel may result in unpredictable behaviour.
+Particularly, the kernel may try to resolve this address even
+on a
+.B NOARP
+interface or if the address is multicast or broadcast.
+.RE
+
+.TP
+ip neighbour show
+list neighbour entries
+.RS
+.TP
+.BI to " ADDRESS " (default)
+the prefix selecting the neighbours to list.
+
+.TP
+.BI dev " NAME"
+only list the neighbours attached to this device.
+
+.TP
+.BI proxy
+list neighbour proxies.
+
+.TP
+.B unused
+only list neighbours which are not currently in use.
+
+.TP
+.BI nud " NUD_STATE"
+only list neighbour entries in this state.
+.I NUD_STATE
+takes values listed below or the special value
+.B all
+which means all states. This option may occur more than once.
+If this option is absent,
+.B ip
+lists all entries except for
+.B none
+and
+.BR "noarp" .
+.RE
+
+.TP
+ip neighbour flush
+flush neighbour entries
+.RS
+This command has the same arguments as
+.B show.
+The differences are that it does not run when no arguments are given,
+and that the default neighbour states to be flushed do not include
+.B permanent
+and
+.BR "noarp" .
+
+.PP
+With the
+.B -statistics
+option, the command becomes verbose. It prints out the number of
+deleted neighbours and the number of rounds made to flush the
+neighbour table. If the option is given
+twice,
+.B ip neigh flush
+also dumps all the deleted neighbours.
+.RE
+
+.SH EXAMPLES
+.PP
+ip neighbour
+.RS
+Shows the current neighbour table in kernel.
+.RE
+.PP
+ip neigh flush dev eth0
+.RS
+Removes entries in the neighbour table on device eth0.
+.RE
+
+.SH SEE ALSO
+.br
+.BR ip (8)
+
+.SH AUTHOR
+Original Manpage by Michail Litvak <mci@owl.openwall.com>
diff --git a/iproute2/man/man8/ip-netconf.8 b/iproute2/man/man8/ip-netconf.8
new file mode 100644
index 0000000..2718258
--- /dev/null
+++ b/iproute2/man/man8/ip-netconf.8
@@ -0,0 +1,36 @@
+.TH IP\-NETCONF 8 "13 Dec 2012" "iproute2" "Linux"
+.SH "NAME"
+ip-netconf \- network configuration monitoring
+.SH "SYNOPSIS"
+.sp
+.ad l
+.in +8
+.ti -8
+.BR "ip " " [ ip-OPTIONS ] " "netconf show" " [ "
+.B dev
+.IR NAME " ]"
+
+.SH DESCRIPTION
+The
+.B ip netconf
+utility can monitor IPv4 and IPv6 parameters (see
+.BR "/proc/sys/net/ipv[4|6]/conf/[all|DEV]/" ")"
+like forwarding, rp_filter
+or mc_forwarding status.
+
+If no interface is specified, the entry
+.B all
+is displayed.
+
+.SS ip netconf show - display network parameters
+
+.TP
+.BI dev " NAME"
+the name of the device to display network parameters for.
+
+.SH SEE ALSO
+.br
+.BR ip (8)
+
+.SH AUTHOR
+Original Manpage by Nicolas Dichtel <nicolas.dichtel@6wind.com>
diff --git a/iproute2/man/man8/ip-netns.8 b/iproute2/man/man8/ip-netns.8
new file mode 100644
index 0000000..c9b0fbc
--- /dev/null
+++ b/iproute2/man/man8/ip-netns.8
@@ -0,0 +1,213 @@
+.TH IP\-NETNS 8 "16 Jan 2013" "iproute2" "Linux"
+.SH NAME
+ip-netns \- process network namespace management
+.SH SYNOPSIS
+.sp
+.ad l
+.in +8
+.ti -8
+.B ip
+.RI "[ " OPTIONS " ]"
+.B netns
+.RI " { " COMMAND " | "
+.BR help " }"
+.sp
+.ti -8
+.BR "ip netns" " { " list " } "
+
+.ti -8
+.B ip netns add
+.I NETNSNAME
+
+.ti -8
+.B ip [-all] netns del
+.RI "[ " NETNSNAME " ]"
+
+.ti -8
+.BR "ip netns" " { " set " } "
+.I NETNSNAME NETNSID
+
+.ti -8
+.BR "ip netns identify"
+.RI "[ " PID " ]"
+
+.ti -8
+.BR "ip netns pids"
+.I NETNSNAME
+
+.ti -8
+.BR "ip [-all] netns exec "
+.RI "[ " NETNSNAME " ] " command ...
+
+.ti -8
+.BR "ip netns monitor"
+
+.ti -8
+.BR "ip netns list-id"
+
+.SH DESCRIPTION
+A network namespace is logically another copy of the network stack,
+with its own routes, firewall rules, and network devices.
+
+By default a process inherits its network namespace from its parent. Initially all
+the processes share the same default network namespace from the init process.
+
+By convention a named network namespace is an object at
+.BR "/var/run/netns/" NAME
+that can be opened. The file descriptor resulting from opening
+.BR "/var/run/netns/" NAME
+refers to the specified network namespace. Holding that file
+descriptor open keeps the network namespace alive. The file
+descriptor can be used with the
+.B setns(2)
+system call to change the network namespace associated with a task.
+
+For applications that are aware of network namespaces, the convention
+is to look for global network configuration files first in
+.BR "/etc/netns/" NAME "/"
+then in
+.BR "/etc/".
+For example, if you want a different version of
+.BR /etc/resolv.conf
+for a network namespace used to isolate your vpn you would name it
+.BR /etc/netns/myvpn/resolv.conf.
+
+.B ip netns exec
+automates handling of this configuration, file convention for network
+namespace unaware applications, by creating a mount namespace and
+bind mounting all of the per network namespace configure files into
+their traditional location in /etc.
+
+.TP
+.B ip netns list - show all of the named network namespaces
+.sp
+This command displays all of the network namespaces in /var/run/netns
+
+.TP
+.B ip netns add NAME - create a new named network namespace
+.sp
+If NAME is available in /var/run/netns/ this command creates a new
+network namespace and assigns NAME.
+
+.TP
+.B ip [-all] netns delete [ NAME ] - delete the name of a network namespace(s)
+.sp
+If NAME is present in /var/run/netns it is umounted and the mount
+point is removed. If this is the last user of the network namespace the
+network namespace will be freed and all physical devices will be moved to the
+default one, otherwise the network namespace persists until it has no more
+users. ip netns delete may fail if the mount point is in use in another mount
+namespace.
+
+If
+.B -all
+option was specified then all the network namespace names will be removed.
+
+It is possible to lose the physical device when it was moved to netns and
+then this netns was deleted with a running process:
+
+.RS 10
+$ ip netns add net0
+.RE
+.RS 10
+$ ip link set dev eth0 netns net0
+.RE
+.RS 10
+$ ip netns exec net0 SOME_PROCESS_IN_BACKGROUND
+.RE
+.RS 10
+$ ip netns del net0
+.RE
+
+.RS
+and eth0 will appear in the default netns only after SOME_PROCESS_IN_BACKGROUND
+will exit or will be killed. To prevent this the processes running in net0
+should be killed before deleting the netns:
+
+.RE
+.RS 10
+$ ip netns pids net0 | xargs kill
+.RE
+.RS 10
+$ ip netns del net0
+.RE
+
+.TP
+.B ip netns set NAME NETNSID - assign an id to a peer network namespace
+.sp
+This command assigns a id to a peer network namespace. This id is valid
+only in the current network namespace.
+This id will be used by the kernel in some netlink messages. If no id is
+assigned when the kernel needs it, it will be automatically assigned by
+the kernel.
+Once it is assigned, it's not possible to change it.
+
+.TP
+.B ip netns identify [PID] - Report network namespaces names for process
+.sp
+This command walks through /var/run/netns and finds all the network
+namespace names for network namespace of the specified process, if PID is
+not specified then the current process will be used.
+
+.TP
+.B ip netns pids NAME - Report processes in the named network namespace
+.sp
+This command walks through proc and finds all of the process who have
+the named network namespace as their primary network namespace.
+
+.TP
+.B ip [-all] netns exec [ NAME ] cmd ... - Run cmd in the named network namespace
+.sp
+This command allows applications that are network namespace unaware
+to be run in something other than the default network namespace with
+all of the configuration for the specified network namespace appearing
+in the customary global locations. A network namespace and bind mounts
+are used to move files from their network namespace specific location
+to their default locations without affecting other processes.
+
+If
+.B -all
+option was specified then
+.B cmd
+will be executed synchronously on the each named network namespace even if
+.B cmd
+fails on some of them. Network namespace name is printed on each
+.B cmd
+executing.
+
+.TP
+.B ip netns monitor - Report as network namespace names are added and deleted
+.sp
+This command watches network namespace name addition and deletion events
+and prints a line for each event it sees.
+
+.TP
+.B ip netns list-id - list network namespace ids (nsid)
+.sp
+Network namespace ids are used to identify a peer network namespace. This
+command displays nsid of the current network namespace and provides the
+corresponding iproute2 netns name (from /var/run/netns) if any.
+
+.SH EXAMPLES
+.PP
+ip netns list
+.RS
+Shows the list of current named network namespaces
+.RE
+.PP
+ip netns add vpn
+.RS
+Creates a network namespace and names it vpn
+.RE
+.PP
+ip netns exec vpn ip link set lo up
+.RS
+Bring up the loopback interface in the vpn network namespace.
+.RE
+
+.SH SEE ALSO
+.br
+.BR ip (8)
+
+.SH AUTHOR
+Original Manpage by Eric W. Biederman
diff --git a/iproute2/man/man8/ip-ntable.8 b/iproute2/man/man8/ip-ntable.8
new file mode 100644
index 0000000..462e589
--- /dev/null
+++ b/iproute2/man/man8/ip-ntable.8
@@ -0,0 +1,101 @@
+.TH IP\-NTABLE 8 "20 Dec 2011" "iproute2" "Linux"
+.SH "NAME"
+ip-ntable - neighbour table configuration
+.SH "SYNOPSIS"
+.sp
+.ad l
+.in +8
+.ti -8
+.B ip
+.RI "[ " OPTIONS " ]"
+.B address
+.RI " { " COMMAND " | "
+.BR help " }"
+.sp
+
+.ti -8
+.BR "ip ntable change name"
+.IR NAME " [ "
+.B dev
+.IR DEV " ] " PARMS
+
+.ti -8
+.IR PARMS " := { "
+.B thresh1
+.IR VAL " | "
+.B thresh2
+.IR VAL " | "
+.B thresh3
+.IR VAL " | "
+.B gc_int
+.IR MSEC " | "
+.B base_reachable
+.IR MSEC " | "
+.B retrans
+.IR MSEC " | " "gc_stale MSEC " " | "
+.B delay_probe
+.IR MSEC " | " "queue LEN " " | "
+.B app_probs
+.IR VAL " | "
+.B ucast_probes
+.IR VAL " | " "mcast_probes VAL " " | "
+.B anycast_delay
+.IR MSEC " | "
+.B proxy_delay
+.IR MSEC " | " "proxy_queue LEN " " | "
+.B locktime
+.IR MSEC " }"
+
+.ti -8
+.BR "ip ntable show" " [ "
+.B dev
+.IR DEV " ] [ "
+.B name
+.IR NAME " ]"
+
+.SH DESCRIPTION
+.I ip ntable
+controls the parameters for the neighbour tables.
+
+.SS ip ntable show - list the ip neighbour tables
+
+This commands displays neighbour table parameters and statistics.
+
+.TP
+.BI dev " DEV"
+only list the table attached to this device.
+
+.TP
+.BI name " NAME"
+only lists the table with the given name.
+
+.SS ip ntable change - modify table parameter
+
+This command allows modifying table parameters such as timers and queue lengths.
+.TP
+.BI name " NAME"
+the name of the table to modify.
+
+.TP
+.BI dev " DEV"
+the name of the device to modify the table values.
+
+.SH EXAMPLES
+.PP
+ip ntable show dev eth0
+.RS 4
+Shows the neighbour table (IPv4 ARP and IPv6 ndisc) parameters on device eth0.
+.RE
+.PP
+ip ntable change name arp_cache queue 8 dev eth0
+.RS 4
+Changes the number of packets queued while address is being resolved from the
+default value (3) to 8 packets.
+.RE
+
+.SH SEE ALSO
+.br
+.BR ip (8)
+
+.SH AUTHOR
+Manpage by Stephen Hemminger
diff --git a/iproute2/man/man8/ip-route.8.in b/iproute2/man/man8/ip-route.8.in
new file mode 100644
index 0000000..c764bfc
--- /dev/null
+++ b/iproute2/man/man8/ip-route.8.in
@@ -0,0 +1,932 @@
+.TH IP\-ROUTE 8 "13 Dec 2012" "iproute2" "Linux"
+.SH "NAME"
+ip-route \- routing table management
+.SH "SYNOPSIS"
+.sp
+.ad l
+.in +8
+.ti -8
+.B ip
+.RI "[ " ip-OPTIONS " ]"
+.B route
+.RI " { " COMMAND " | "
+.BR help " }"
+.sp
+.ti -8
+
+.ti -8
+.BR "ip route" " { "
+.BR list " | " flush " } "
+.I SELECTOR
+
+.ti -8
+.BR "ip route save"
+.I SELECTOR
+
+.ti -8
+.BR "ip route restore"
+
+.ti -8
+.B ip route get
+.IR ADDRESS " [ "
+.BI from " ADDRESS " iif " STRING"
+.RB " ] [ " oif
+.IR STRING " ] [ "
+.B tos
+.IR TOS " ]"
+
+.ti -8
+.BR "ip route" " { " add " | " del " | " change " | " append " | "\
+replace " } "
+.I ROUTE
+
+.ti -8
+.IR SELECTOR " := "
+.RB "[ " root
+.IR PREFIX " ] [ "
+.B match
+.IR PREFIX " ] [ "
+.B exact
+.IR PREFIX " ] [ "
+.B table
+.IR TABLE_ID " ] [ "
+.B proto
+.IR RTPROTO " ] [ "
+.B type
+.IR TYPE " ] [ "
+.B scope
+.IR SCOPE " ]"
+
+.ti -8
+.IR ROUTE " := " NODE_SPEC " [ " INFO_SPEC " ]"
+
+.ti -8
+.IR NODE_SPEC " := [ " TYPE " ] " PREFIX " ["
+.B tos
+.IR TOS " ] [ "
+.B table
+.IR TABLE_ID " ] [ "
+.B proto
+.IR RTPROTO " ] [ "
+.B scope
+.IR SCOPE " ] [ "
+.B metric
+.IR METRIC " ]"
+
+.ti -8
+.IR INFO_SPEC " := " "NH OPTIONS FLAGS" " ["
+.B nexthop
+.IR NH " ] ..."
+
+.ti -8
+.IR NH " := [ "
+.B encap
+.IR ENCAP " ] [ "
+.B via
+[
+.IR FAMILY " ] " ADDRESS " ] [ "
+.B dev
+.IR STRING " ] [ "
+.B weight
+.IR NUMBER " ] " NHFLAGS
+
+.ti -8
+.IR FAMILY " := [ "
+.BR inet " | " inet6 " | " ipx " | " dnet " | " mpls " | " bridge " | " link " ]"
+
+.ti -8
+.IR OPTIONS " := " FLAGS " [ "
+.B mtu
+.IR NUMBER " ] [ "
+.B advmss
+.IR NUMBER " ] [ "
+.B as
+[
+.B to
+]
+.IR ADDRESS " ]"
+.B rtt
+.IR TIME " ] [ "
+.B rttvar
+.IR TIME " ] [ "
+.B reordering
+.IR NUMBER " ] [ "
+.B window
+.IR NUMBER " ] [ "
+.B cwnd
+.IR NUMBER " ] [ "
+.B ssthresh
+.IR REALM " ] [ "
+.B realms
+.IR REALM " ] [ "
+.B rto_min
+.IR TIME " ] [ "
+.B initcwnd
+.IR NUMBER " ] [ "
+.B initrwnd
+.IR NUMBER " ] [ "
+.B features
+.IR FEATURES " ] [ "
+.B quickack
+.IR BOOL " ] [ "
+.B congctl
+.IR NAME " ] [ "
+.B pref
+.IR PREF " ] [ "
+.B expires
+.IR TIME " ]"
+
+.ti -8
+.IR TYPE " := [ "
+.BR unicast " | " local " | " broadcast " | " multicast " | "\
+throw " | " unreachable " | " prohibit " | " blackhole " | " nat " ]"
+
+.ti -8
+.IR TABLE_ID " := [ "
+.BR local "| " main " | " default " | " all " |"
+.IR NUMBER " ]"
+
+.ti -8
+.IR SCOPE " := [ "
+.BR host " | " link " | " global " |"
+.IR NUMBER " ]"
+
+.ti -8
+.IR NHFLAGS " := [ "
+.BR onlink " | " pervasive " ]"
+
+.ti -8
+.IR RTPROTO " := [ "
+.BR kernel " | " boot " | " static " |"
+.IR NUMBER " ]"
+
+.ti -8
+.IR FEATURES " := [ "
+.BR ecn " | ]"
+
+.ti -8
+.IR PREF " := [ "
+.BR low " | " medium " | " high " ]"
+
+.ti -8
+.IR ENCAP " := [ "
+.IR MPLS " | " IP " ]"
+
+.ti -8
+.IR ENCAP_MPLS " := "
+.BR mpls " [ "
+.IR LABEL " ]"
+
+.ti -8
+.IR ENCAP_IP " := "
+.B ip
+.B id
+.IR TUNNEL_ID
+.B dst
+.IR REMOTE_IP " [ "
+.B tos
+.IR TOS " ] ["
+.B ttl
+.IR TTL " ]"
+
+.SH DESCRIPTION
+.B ip route
+is used to manipulate entries in the kernel routing tables.
+.sp
+.B Route types:
+
+.in +8
+.B unicast
+- the route entry describes real paths to the destinations covered
+by the route prefix.
+
+.sp
+.B unreachable
+- these destinations are unreachable. Packets are discarded and the
+ICMP message
+.I host unreachable
+is generated.
+The local senders get an
+.I EHOSTUNREACH
+error.
+
+.sp
+.B blackhole
+- these destinations are unreachable. Packets are discarded silently.
+The local senders get an
+.I EINVAL
+error.
+
+.sp
+.B prohibit
+- these destinations are unreachable. Packets are discarded and the
+ICMP message
+.I communication administratively prohibited
+is generated. The local senders get an
+.I EACCES
+error.
+
+.sp
+.B local
+- the destinations are assigned to this host. The packets are looped
+back and delivered locally.
+
+.sp
+.B broadcast
+- the destinations are broadcast addresses. The packets are sent as
+link broadcasts.
+
+.sp
+.B throw
+- a special control route used together with policy rules. If such a
+route is selected, lookup in this table is terminated pretending that
+no route was found. Without policy routing it is equivalent to the
+absence of the route in the routing table. The packets are dropped
+and the ICMP message
+.I net unreachable
+is generated. The local senders get an
+.I ENETUNREACH
+error.
+
+.sp
+.B nat
+- a special NAT route. Destinations covered by the prefix
+are considered to be dummy (or external) addresses which require translation
+to real (or internal) ones before forwarding. The addresses to translate to
+are selected with the attribute
+.BR "via" .
+.B Warning:
+Route NAT is no longer supported in Linux 2.6.
+
+.sp
+.B anycast
+.RI "- " "not implemented"
+the destinations are
+.I anycast
+addresses assigned to this host. They are mainly equivalent
+to
+.B local
+with one difference: such addresses are invalid when used
+as the source address of any packet.
+
+.sp
+.B multicast
+- a special type used for multicast routing. It is not present in
+normal routing tables.
+.in -8
+
+.P
+.B Route tables:
+Linux-2.x can pack routes into several routing tables identified
+by a number in the range from 1 to 2^31 or by name from the file
+.B @SYSCONFDIR@/rt_tables
+By default all normal routes are inserted into the
+.B main
+table (ID 254) and the kernel only uses this table when calculating routes.
+Values (0, 253, 254, and 255) are reserved for built-in use.
+
+.sp
+Actually, one other table always exists, which is invisible but
+even more important. It is the
+.B local
+table (ID 255). This table
+consists of routes for local and broadcast addresses. The kernel maintains
+this table automatically and the administrator usually need not modify it
+or even look at it.
+
+The multiple routing tables enter the game when
+.I policy routing
+is used.
+
+.TP
+ip route add
+add new route
+.TP
+ip route change
+change route
+.TP
+ip route replace
+change or add new one
+.RS
+.TP
+.BI to " TYPE PREFIX " (default)
+the destination prefix of the route. If
+.I TYPE
+is omitted,
+.B ip
+assumes type
+.BR "unicast" .
+Other values of
+.I TYPE
+are listed above.
+.I PREFIX
+is an IP or IPv6 address optionally followed by a slash and the
+prefix length. If the length of the prefix is missing,
+.B ip
+assumes a full-length host route. There is also a special
+.I PREFIX
+.B default
+- which is equivalent to IP
+.B 0/0
+or to IPv6
+.BR "::/0" .
+
+.TP
+.BI tos " TOS"
+.TP
+.BI dsfield " TOS"
+the Type Of Service (TOS) key. This key has no associated mask and
+the longest match is understood as: First, compare the TOS
+of the route and of the packet. If they are not equal, then the packet
+may still match a route with a zero TOS.
+.I TOS
+is either an 8 bit hexadecimal number or an identifier
+from
+.BR "@SYSCONFDIR@/rt_dsfield" .
+
+.TP
+.BI metric " NUMBER"
+.TP
+.BI preference " NUMBER"
+the preference value of the route.
+.I NUMBER
+is an arbitrary 32bit number.
+
+.TP
+.BI table " TABLEID"
+the table to add this route to.
+.I TABLEID
+may be a number or a string from the file
+.BR "@SYSCONFDIR@/rt_tables" .
+If this parameter is omitted,
+.B ip
+assumes the
+.B main
+table, with the exception of
+.BR local ", " broadcast " and " nat
+routes, which are put into the
+.B local
+table by default.
+
+.TP
+.BI dev " NAME"
+the output device name.
+
+.TP
+.BI via " [ FAMILY ] ADDRESS"
+the address of the nexthop router, in the address family FAMILY.
+Actually, the sense of this field depends on the route type. For
+normal
+.B unicast
+routes it is either the true next hop router or, if it is a direct
+route installed in BSD compatibility mode, it can be a local address
+of the interface. For NAT routes it is the first address of the block
+of translated IP destinations.
+
+.TP
+.BI src " ADDRESS"
+the source address to prefer when sending to the destinations
+covered by the route prefix.
+
+.TP
+.BI realm " REALMID"
+the realm to which this route is assigned.
+.I REALMID
+may be a number or a string from the file
+.BR "@SYSCONFDIR@/rt_realms" .
+
+.TP
+.BI mtu " MTU"
+.TP
+.BI "mtu lock" " MTU"
+the MTU along the path to the destination. If the modifier
+.B lock
+is not used, the MTU may be updated by the kernel due to
+Path MTU Discovery. If the modifier
+.B lock
+is used, no path MTU discovery will be tried, all packets
+will be sent without the DF bit in IPv4 case or fragmented
+to MTU for IPv6.
+
+.TP
+.BI window " NUMBER"
+the maximal window for TCP to advertise to these destinations,
+measured in bytes. It limits maximal data bursts that our TCP
+peers are allowed to send to us.
+
+.TP
+.BI rtt " TIME"
+the initial RTT ('Round Trip Time') estimate. If no suffix is
+specified the units are raw values passed directly to the
+routing code to maintain compatibility with previous releases.
+Otherwise if a suffix of s, sec or secs is used to specify
+seconds and ms, msec or msecs to specify milliseconds.
+
+
+.TP
+.BI rttvar " TIME " "(2.3.15+ only)"
+the initial RTT variance estimate. Values are specified as with
+.BI rtt
+above.
+
+.TP
+.BI rto_min " TIME " "(2.6.23+ only)"
+the minimum TCP Retransmission TimeOut to use when communicating with this
+destination. Values are specified as with
+.BI rtt
+above.
+
+.TP
+.BI ssthresh " NUMBER " "(2.3.15+ only)"
+an estimate for the initial slow start threshold.
+
+.TP
+.BI cwnd " NUMBER " "(2.3.15+ only)"
+the clamp for congestion window. It is ignored if the
+.B lock
+flag is not used.
+
+.TP
+.BI initcwnd " NUMBER " "(2.5.70+ only)"
+the initial congestion window size for connections to this destination.
+Actual window size is this value multiplied by the MSS
+(``Maximal Segment Size'') for same connection. The default is
+zero, meaning to use the values specified in RFC2414.
+
+.TP
+.BI initrwnd " NUMBER " "(2.6.33+ only)"
+the initial receive window size for connections to this destination.
+Actual window size is this value multiplied by the MSS of the connection.
+The default value is zero, meaning to use Slow Start value.
+
+.TP
+.BI features " FEATURES " (3.18+ only)
+Enable or disable per-route features. Only available feature at this
+time is
+.B ecn
+to enable explicit congestion notification when initiating connections to the
+given destination network.
+When responding to a connection request from the given network, ecn will
+also be used even if the
+.B net.ipv4.tcp_ecn
+sysctl is set to 0.
+
+.TP
+.BI quickack " BOOL " "(3.11+ only)"
+Enable or disable quick ack for connections to this destination.
+
+.TP
+.BI congctl " NAME " "(3.20+ only)"
+.TP
+.BI "congctl lock" " NAME " "(3.20+ only)"
+Sets a specific TCP congestion control algorithm only for a given destination.
+If not specified, Linux keeps the current global default TCP congestion control
+algorithm, or the one set from the application. If the modifier
+.B lock
+is not used, an application may nevertheless overwrite the suggested congestion
+control algorithm for that destination. If the modifier
+.B lock
+is used, then an application is not allowed to overwrite the specified congestion
+control algorithm for that destination, thus it will be enforced/guaranteed to
+use the proposed algorithm.
+
+.TP
+.BI advmss " NUMBER " "(2.3.15+ only)"
+the MSS ('Maximal Segment Size') to advertise to these
+destinations when establishing TCP connections. If it is not given,
+Linux uses a default value calculated from the first hop device MTU.
+(If the path to these destination is asymmetric, this guess may be wrong.)
+
+.TP
+.BI reordering " NUMBER " "(2.3.15+ only)"
+Maximal reordering on the path to this destination.
+If it is not given, Linux uses the value selected with
+.B sysctl
+variable
+.BR "net/ipv4/tcp_reordering" .
+
+.TP
+.BI nexthop " NEXTHOP"
+the nexthop of a multipath route.
+.I NEXTHOP
+is a complex value with its own syntax similar to the top level
+argument lists:
+
+.in +8
+.BI via " [ FAMILY ] ADDRESS"
+- is the nexthop router.
+.sp
+
+.BI dev " NAME"
+- is the output device.
+.sp
+
+.BI weight " NUMBER"
+- is a weight for this element of a multipath
+route reflecting its relative bandwidth or quality.
+.in -8
+
+.TP
+.BI scope " SCOPE_VAL"
+the scope of the destinations covered by the route prefix.
+.I SCOPE_VAL
+may be a number or a string from the file
+.BR "@SYSCONFDIR@/rt_scopes" .
+If this parameter is omitted,
+.B ip
+assumes scope
+.B global
+for all gatewayed
+.B unicast
+routes, scope
+.B link
+for direct
+.BR unicast " and " broadcast
+routes and scope
+.BR host " for " local
+routes.
+
+.TP
+.BI protocol " RTPROTO"
+the routing protocol identifier of this route.
+.I RTPROTO
+may be a number or a string from the file
+.BR "@SYSCONFDIR@/rt_protos" .
+If the routing protocol ID is not given,
+.B ip assumes protocol
+.B boot
+(i.e. it assumes the route was added by someone who doesn't
+understand what they are doing). Several protocol values have
+a fixed interpretation.
+Namely:
+
+.in +8
+.B redirect
+- the route was installed due to an ICMP redirect.
+.sp
+
+.B kernel
+- the route was installed by the kernel during autoconfiguration.
+.sp
+
+.B boot
+- the route was installed during the bootup sequence.
+If a routing daemon starts, it will purge all of them.
+.sp
+
+.B static
+- the route was installed by the administrator
+to override dynamic routing. Routing daemon will respect them
+and, probably, even advertise them to its peers.
+.sp
+
+.B ra
+- the route was installed by Router Discovery protocol.
+.in -8
+
+.sp
+The rest of the values are not reserved and the administrator is free
+to assign (or not to assign) protocol tags.
+
+.TP
+.B onlink
+pretend that the nexthop is directly attached to this link,
+even if it does not match any interface prefix.
+
+.TP
+.BI pref " PREF"
+the IPv6 route preference.
+.I PREF
+is a string specifying the route preference as defined in RFC4191 for Router
+Discovery messages. Namely:
+
+.in +8
+.B low
+- the route has a lowest priority
+.sp
+
+.B medium
+- the route has a default priority
+.sp
+
+.B high
+- the route has a highest priority
+.sp
+
+.TP
+.BI encap " ENCAPTYPE ENCAPHDR"
+attach tunnel encapsulation attributes to this route.
+.sp
+.I ENCAPTYPE
+is a string specifying the supported encapsulation type. Namely:
+
+.in +8
+.BI mpls
+- encapsulation type MPLS
+.sp
+.BI ip
+- IP encapsulation (Geneve, GRE, VXLAN, ...)
+.sp
+
+.in -8
+.I ENCAPHDR
+is a set of encapsulation attributes specific to the
+.I ENCAPTYPE.
+
+.in +8
+.B mpls
+.in +2
+.I MPLSLABEL
+- mpls label stack with labels separated by
+.I "/"
+.in -2
+.sp
+
+.B ip
+.in +2
+.B id
+.I TUNNEL_ID
+.B dst
+.IR REMOTE_IP " [ "
+.B tos
+.IR TOS " ] ["
+.B ttl
+.IR TTL " ]"
+.in -2
+.sp
+
+.in -8
+.RE
+
+.TP
+.BI expires " TIME " "(4.4+ only)"
+the route will be deleted after the expires time.
+.B Only
+support IPv6 at present.
+
+.TP
+ip route delete
+delete route
+.RS
+.B ip route del
+has the same arguments as
+.BR "ip route add" ,
+but their semantics are a bit different.
+
+Key values
+.RB "(" to ", " tos ", " preference " and " table ")"
+select the route to delete. If optional attributes are present,
+.B ip
+verifies that they coincide with the attributes of the route to delete.
+If no route with the given key and attributes was found,
+.B ip route del
+fails.
+.RE
+
+.TP
+ip route show
+list routes
+.RS
+the command displays the contents of the routing tables or the route(s)
+selected by some criteria.
+
+.TP
+.BI to " SELECTOR " (default)
+only select routes from the given range of destinations.
+.I SELECTOR
+consists of an optional modifier
+.RB "(" root ", " match " or " exact ")"
+and a prefix.
+.BI root " PREFIX"
+selects routes with prefixes not shorter than
+.IR PREFIX "."
+F.e.
+.BI root " 0/0"
+selects the entire routing table.
+.BI match " PREFIX"
+selects routes with prefixes not longer than
+.IR PREFIX "."
+F.e.
+.BI match " 10.0/16"
+selects
+.IR 10.0/16 ","
+.IR 10/8 " and " 0/0 ,
+but it does not select
+.IR 10.1/16 " and " 10.0.0/24 .
+And
+.BI exact " PREFIX"
+(or just
+.IR PREFIX ")"
+selects routes with this exact prefix. If neither of these options
+are present,
+.B ip
+assumes
+.BI root " 0/0"
+i.e. it lists the entire table.
+
+.TP
+.BI tos " TOS"
+.TP
+.BI dsfield " TOS"
+only select routes with the given TOS.
+
+.TP
+.BI table " TABLEID"
+show the routes from this table(s). The default setting is to show table
+.BR main "."
+.I TABLEID
+may either be the ID of a real table or one of the special values:
+.sp
+.in +8
+.B all
+- list all of the tables.
+.sp
+.B cache
+- dump the routing cache.
+.in -8
+
+.TP
+.B cloned
+.TP
+.B cached
+list cloned routes i.e. routes which were dynamically forked from
+other routes because some route attribute (f.e. MTU) was updated.
+Actually, it is equivalent to
+.BR "table cache" "."
+
+.TP
+.BI from " SELECTOR"
+the same syntax as for
+.BR to ","
+but it binds the source address range rather than destinations.
+Note that the
+.B from
+option only works with cloned routes.
+
+.TP
+.BI protocol " RTPROTO"
+only list routes of this protocol.
+
+.TP
+.BI scope " SCOPE_VAL"
+only list routes with this scope.
+
+.TP
+.BI type " TYPE"
+only list routes of this type.
+
+.TP
+.BI dev " NAME"
+only list routes going via this device.
+
+.TP
+.BI via " [ FAMILY ] PREFIX"
+only list routes going via the nexthop routers selected by
+.IR PREFIX "."
+
+.TP
+.BI src " PREFIX"
+only list routes with preferred source addresses selected
+by
+.IR PREFIX "."
+
+.TP
+.BI realm " REALMID"
+.TP
+.BI realms " FROMREALM/TOREALM"
+only list routes with these realms.
+.RE
+
+.TP
+ip route flush
+flush routing tables
+.RS
+this command flushes routes selected by some criteria.
+
+.sp
+The arguments have the same syntax and semantics as the arguments of
+.BR "ip route show" ,
+but routing tables are not listed but purged. The only difference is
+the default action:
+.B show
+dumps all the IP main routing table but
+.B flush
+prints the helper page.
+
+.sp
+With the
+.B -statistics
+option, the command becomes verbose. It prints out the number of
+deleted routes and the number of rounds made to flush the routing
+table. If the option is given
+twice,
+.B ip route flush
+also dumps all the deleted routes in the format described in the
+previous subsection.
+.RE
+
+.TP
+ip route get
+get a single route
+.RS
+this command gets a single route to a destination and prints its
+contents exactly as the kernel sees it.
+
+.TP
+.BI to " ADDRESS " (default)
+the destination address.
+
+.TP
+.BI from " ADDRESS"
+the source address.
+
+.TP
+.BI tos " TOS"
+.TP
+.BI dsfield " TOS"
+the Type Of Service.
+
+.TP
+.BI iif " NAME"
+the device from which this packet is expected to arrive.
+
+.TP
+.BI oif " NAME"
+force the output device on which this packet will be routed.
+
+.TP
+.B connected
+if no source address
+.RB "(option " from ")"
+was given, relookup the route with the source set to the preferred
+address received from the first lookup.
+If policy routing is used, it may be a different route.
+
+.P
+Note that this operation is not equivalent to
+.BR "ip route show" .
+.B show
+shows existing routes.
+.B get
+resolves them and creates new clones if necessary. Essentially,
+.B get
+is equivalent to sending a packet along this path.
+If the
+.B iif
+argument is not given, the kernel creates a route
+to output packets towards the requested destination.
+This is equivalent to pinging the destination
+with a subsequent
+.BR "ip route ls cache" ,
+however, no packets are actually sent. With the
+.B iif
+argument, the kernel pretends that a packet arrived from this interface
+and searches for a path to forward the packet.
+.RE
+
+.TP
+ip route save
+save routing table information to stdout
+.RS
+This command behaves like
+.BR "ip route show"
+except that the output is raw data suitable for passing to
+.BR "ip route restore" .
+.RE
+
+.TP
+ip route restore
+restore routing table information from stdin
+.RS
+This command expects to read a data stream as returned from
+.BR "ip route save" .
+It will attempt to restore the routing table information exactly as
+it was at the time of the save, so any translation of information
+in the stream (such as device indexes) must be done first. Any existing
+routes are left unchanged. Any routes specified in the data stream that
+already exist in the table will be ignored.
+.RE
+
+.SH EXAMPLES
+.PP
+ip ro
+.RS 4
+Show all route entries in the kernel.
+.RE
+.PP
+ip route add default via 192.168.1.1 dev eth0
+.RS 4
+Adds a default route (for all addresses) via the local gateway 192.168.1.1 that can
+be reached on device eth0.
+.RE
+.PP
+ip route add 10.1.1.0/30 encap mpls 200/300 via 10.1.1.1 dev eth0
+.RS 4
+Adds an ipv4 route with mpls encapsulation attributes attached to it.
+.RE
+.SH SEE ALSO
+.br
+.BR ip (8)
+
+.SH AUTHOR
+Original Manpage by Michail Litvak <mci@owl.openwall.com>
diff --git a/iproute2/man/man8/ip-rule.8 b/iproute2/man/man8/ip-rule.8
new file mode 100644
index 0000000..b7008c6
--- /dev/null
+++ b/iproute2/man/man8/ip-rule.8
@@ -0,0 +1,297 @@
+.TH IP\-RULE 8 "20 Dec 2011" "iproute2" "Linux"
+.SH "NAME"
+ip-rule \- routing policy database management
+.SH "SYNOPSIS"
+.sp
+.ad l
+.in +8
+.ti -8
+.B ip
+.RI "[ " OPTIONS " ]"
+.B rule
+.RI " { " COMMAND " | "
+.BR help " }"
+.sp
+
+.ti -8
+.B ip rule
+.RB " [ " list " | " add " | " del " | " flush " | " save " ]"
+.I SELECTOR ACTION
+
+.ti -8
+.B ip rule " restore "
+
+.ti -8
+.IR SELECTOR " := [ "
+.B from
+.IR PREFIX " ] [ "
+.B to
+.IR PREFIX " ] [ "
+.B tos
+.IR TOS " ] [ "
+.B fwmark
+.IR FWMARK[/MASK] " ] [ "
+.B iif
+.IR STRING " ] [ "
+.B oif
+.IR STRING " ] [ "
+.B pref
+.IR NUMBER " ]"
+
+.ti -8
+.IR ACTION " := [ "
+.B table
+.IR TABLE_ID " ] [ "
+.B nat
+.IR ADDRESS " ] [ "
+.B realms
+.RI "[" SRCREALM "/]" DSTREALM " ]"
+.I SUPPRESSOR
+
+.ti -8
+.IR SUPPRESSOR " := [ "
+.B suppress_prefixlength
+.IR NUMBER " ] [ "
+.B suppress_ifgroup
+.IR GROUP " ]"
+
+.ti -8
+.IR TABLE_ID " := [ "
+.BR local " | " main " | " default " |"
+.IR NUMBER " ]"
+
+.SH DESCRIPTION
+.I ip rule
+manipulates rules
+in the routing policy database control the route selection algorithm.
+
+.P
+Classic routing algorithms used in the Internet make routing decisions
+based only on the destination address of packets (and in theory,
+but not in practice, on the TOS field).
+
+.P
+In some circumstances we want to route packets differently depending not only
+on destination addresses, but also on other packet fields: source address,
+IP protocol, transport protocol ports or even packet payload.
+This task is called 'policy routing'.
+
+.P
+To solve this task, the conventional destination based routing table, ordered
+according to the longest match rule, is replaced with a 'routing policy
+database' (or RPDB), which selects routes by executing some set of rules.
+
+.P
+Each policy routing rule consists of a
+.B selector
+and an
+.B action predicate.
+The RPDB is scanned in order of decreasing priority. The selector
+of each rule is applied to {source address, destination address, incoming
+interface, tos, fwmark} and, if the selector matches the packet,
+the action is performed. The action predicate may return with success.
+In this case, it will either give a route or failure indication
+and the RPDB lookup is terminated. Otherwise, the RPDB program
+continues with the next rule.
+
+.P
+Semantically, the natural action is to select the nexthop and the output device.
+
+.P
+At startup time the kernel configures the default RPDB consisting of three
+rules:
+
+.TP
+1.
+Priority: 0, Selector: match anything, Action: lookup routing
+table
+.B local
+(ID 255).
+The
+.B local
+table is a special routing table containing
+high priority control routes for local and broadcast addresses.
+.sp
+Rule 0 is special. It cannot be deleted or overridden.
+
+.TP
+2.
+Priority: 32766, Selector: match anything, Action: lookup routing
+table
+.B main
+(ID 254).
+The
+.B main
+table is the normal routing table containing all non-policy
+routes. This rule may be deleted and/or overridden with other
+ones by the administrator.
+
+.TP
+3.
+Priority: 32767, Selector: match anything, Action: lookup routing
+table
+.B default
+(ID 253).
+The
+.B default
+table is empty. It is reserved for some post-processing if no previous
+default rules selected the packet.
+This rule may also be deleted.
+
+.P
+Each RPDB entry has additional
+attributes. F.e. each rule has a pointer to some routing
+table. NAT and masquerading rules have an attribute to select new IP
+address to translate/masquerade. Besides that, rules have some
+optional attributes, which routes have, namely
+.BR "realms" .
+These values do not override those contained in the routing tables. They
+are only used if the route did not select any attributes.
+
+.sp
+The RPDB may contain rules of the following types:
+
+.RS
+.B unicast
+- the rule prescribes to return the route found
+in the routing table referenced by the rule.
+
+.B blackhole
+- the rule prescribes to silently drop the packet.
+
+.B unreachable
+- the rule prescribes to generate a 'Network is unreachable' error.
+
+.B prohibit
+- the rule prescribes to generate 'Communication is administratively
+prohibited' error.
+
+.B nat
+- the rule prescribes to translate the source address
+of the IP packet into some other value.
+.RE
+
+.TP
+.B ip rule add - insert a new rule
+.TP
+.B ip rule delete - delete a rule
+.RS
+.TP
+.BI type " TYPE " (default)
+the type of this rule. The list of valid types was given in the previous
+subsection.
+
+.TP
+.BI from " PREFIX"
+select the source prefix to match.
+
+.TP
+.BI to " PREFIX"
+select the destination prefix to match.
+
+.TP
+.BI iif " NAME"
+select the incoming device to match. If the interface is loopback,
+the rule only matches packets originating from this host. This means
+that you may create separate routing tables for forwarded and local
+packets and, hence, completely segregate them.
+
+.TP
+.BI oif " NAME"
+select the outgoing device to match. The outgoing interface is only
+available for packets originating from local sockets that are bound to
+a device.
+
+.TP
+.BI tos " TOS"
+.TP
+.BI dsfield " TOS"
+select the TOS value to match.
+
+.TP
+.BI fwmark " MARK"
+select the
+.B fwmark
+value to match.
+
+.TP
+.BI priority " PREFERENCE"
+the priority of this rule. Each rule should have an explicitly
+set
+.I unique
+priority value.
+The options preference and order are synonyms with priority.
+
+.TP
+.BI table " TABLEID"
+the routing table identifier to lookup if the rule selector matches.
+It is also possible to use lookup instead of table.
+
+.TP
+.BI suppress_prefixlength " NUMBER"
+reject routing decisions that have a prefix length of NUMBER or less.
+
+.TP
+.BI suppress_ifgroup " GROUP"
+reject routing decisions that use a device belonging to the interface
+group GROUP.
+
+.TP
+.BI realms " FROM/TO"
+Realms to select if the rule matched and the routing table lookup
+succeeded. Realm
+.I TO
+is only used if the route did not select any realm.
+
+.TP
+.BI nat " ADDRESS"
+The base of the IP address block to translate (for source addresses).
+The
+.I ADDRESS
+may be either the start of the block of NAT addresses (selected by NAT
+routes) or a local host address (or even zero).
+In the last case the router does not translate the packets, but
+masquerades them to this address.
+Using map-to instead of nat means the same thing.
+
+.B Warning:
+Changes to the RPDB made with these commands do not become active
+immediately. It is assumed that after a script finishes a batch of
+updates, it flushes the routing cache with
+.BR "ip route flush cache" .
+.RE
+.TP
+.B ip rule flush - also dumps all the deleted rules.
+This command has no arguments.
+.TP
+.B ip rule show - list rules
+This command has no arguments.
+The options list or lst are synonyms with show.
+
+.TP
+.B ip rule save
+save rules table information to stdout
+.RS
+This command behaves like
+.BR "ip rule show"
+except that the output is raw data suitable for passing to
+.BR "ip rule restore" .
+.RE
+
+.TP
+.B ip rule restore
+restore rules table information from stdin
+.RS
+This command expects to read a data stream as returned from
+.BR "ip rule save" .
+It will attempt to restore the rules table information exactly as
+it was at the time of the save. Any rules already in the table are
+left unchanged, and duplicates are not ignored.
+.RE
+
+.SH SEE ALSO
+.br
+.BR ip (8)
+
+.SH AUTHOR
+Original Manpage by Michail Litvak <mci@owl.openwall.com>
diff --git a/iproute2/man/man8/ip-tcp_metrics.8 b/iproute2/man/man8/ip-tcp_metrics.8
new file mode 100644
index 0000000..5d2dac8
--- /dev/null
+++ b/iproute2/man/man8/ip-tcp_metrics.8
@@ -0,0 +1,143 @@
+.TH "IP\-TCP_METRICS" 8 "23 Aug 2012" "iproute2" "Linux"
+.SH "NAME"
+ip-tcp_metrics \- management for TCP Metrics
+.SH "SYNOPSIS"
+.sp
+.ad l
+.in +8
+.ti -8
+.B ip
+.RI "[ " OPTIONS " ]"
+.B tcp_metrics
+.RI "{ " COMMAND " | "
+.BR help " }"
+.sp
+
+.ti -8
+.BR "ip tcp_metrics" " { " show " | " flush " }
+.IR SELECTOR
+
+.ti -8
+.BR "ip tcp_metrics delete " [ " address " ]
+.IR ADDRESS
+
+.ti -8
+.IR SELECTOR " := "
+.RB "[ [ " address " ] "
+.IR PREFIX " ]"
+
+.SH "DESCRIPTION"
+.B ip tcp_metrics
+is used to manipulate entries in the kernel that keep TCP information
+for IPv4 and IPv6 destinations. The entries are created when
+TCP sockets want to share information for destinations and are
+stored in a cache keyed by the destination address. The saved
+information may include values for metrics (initially obtained from
+routes), recent TSVAL for TIME-WAIT recycling purposes, state for the
+Fast Open feature, etc.
+For performance reasons the cache can not grow above configured limit
+and the older entries are replaced with fresh information, sometimes
+reclaimed and used for new destinations. The kernel never removes
+entries, they can be flushed only with this tool.
+
+.SS ip tcp_metrics show - show cached entries
+
+.TP
+.BI address " PREFIX " (default)
+IPv4/IPv6 prefix or address. If no prefix is provided all entries are shown.
+
+.LP
+The output may contain the following information:
+
+.BI age " <S.MMM>" sec
+- time after the entry was created, reset or updated with metrics
+from sockets. The entry is reset and refreshed on use with metrics from
+route if the metrics are not updated in last hour. Not all cached values
+reset the age on update.
+
+.BI cwnd " <N>"
+- CWND metric value
+
+.BI fo_cookie " <HEX-STRING>"
+- Cookie value received in SYN-ACK to be used by Fast Open for next SYNs
+
+.BI fo_mss " <N>"
+- MSS value received in SYN-ACK to be used by Fast Open for next SYNs
+
+.BI fo_syn_drops " <N>/<S.MMM>" "sec ago"
+- Number of drops of initial outgoing Fast Open SYNs with data
+detected by monitoring the received SYN-ACK after SYN retransmission.
+The seconds show the time after last SYN drop and together with
+the drop count can be used to disable Fast Open for some time.
+
+.BI reordering " <N>"
+- Reordering metric value
+
+.BI rtt " <N>" us
+- RTT metric value
+
+.BI rttvar " <N>" us
+- RTTVAR metric value
+
+.BI ssthresh " <SSTHRESH>"
+- SSTHRESH metric value
+
+.BI tw_ts " <TSVAL>/<SEC>" "sec ago"
+- recent TSVAL and the seconds after saving it into TIME-WAIT socket
+
+.SS ip tcp_metrics delete - delete single entry
+
+.TP
+.BI address " ADDRESS " (default)
+IPv4/IPv6 address. The address is a required argument.
+
+.SS ip tcp_metrics flush - flush entries
+This command flushes the entries selected by some criteria.
+
+.PP
+This command has the same arguments as
+.B show.
+
+.SH "EXAMPLES"
+.PP
+ip tcp_metrics show address 192.168.0.0/24
+.RS 4
+Shows the entries for destinations from subnet
+.RE
+.PP
+ip tcp_metrics show 192.168.0.0/24
+.RS 4
+The same but address keyword is optional
+.RE
+.PP
+ip tcp_metrics
+.RS 4
+Show all is the default action
+.RE
+.PP
+ip tcp_metrics delete 192.168.0.1
+.RS 4
+Removes the entry for 192.168.0.1 from cache.
+.RE
+.PP
+ip tcp_metrics flush 192.168.0.0/24
+.RS 4
+Removes entries for destinations from subnet
+.RE
+.PP
+ip tcp_metrics flush all
+.RS 4
+Removes all entries from cache
+.RE
+.PP
+ip -6 tcp_metrics flush all
+.RS 4
+Removes all IPv6 entries from cache keeping the IPv4 entries.
+.RE
+
+.SH SEE ALSO
+.br
+.BR ip (8)
+
+.SH AUTHOR
+Original Manpage by Julian Anastasov <ja@ssi.bg>
diff --git a/iproute2/man/man8/ip-token.8 b/iproute2/man/man8/ip-token.8
new file mode 100644
index 0000000..35a3d1e
--- /dev/null
+++ b/iproute2/man/man8/ip-token.8
@@ -0,0 +1,66 @@
+.TH IP\-TOKEN 8 "28 Mar 2013" "iproute2" "Linux"
+.SH "NAME"
+ip-token \- tokenized interface identifier support
+.SH "SYNOPSIS"
+.sp
+.ad l
+.in +8
+.ti -8
+.B ip token
+.RI " { " COMMAND " | "
+.BR help " }"
+.sp
+
+.ti -8
+.BR "ip token" " { " set " } "
+.IR TOKEN
+.B dev
+.IR DEV
+
+.ti -8
+.BR "ip token" " { " get " } "
+.B dev
+.IR DEV
+
+.ti -8
+.BR "ip token" " { " list " }"
+
+.SH "DESCRIPTION"
+IPv6 tokenized interface identifier support is used for assigning well-known
+host-part addresses to nodes whilst still obtaining a global network prefix
+from Router advertisements. The primary target for tokenized identifiers are
+server platforms where addresses are usually manually configured, rather than
+using DHCPv6 or SLAAC. By using tokenized identifiers, hosts can still
+determine their network prefix by use of SLAAC, but more readily be
+automatically renumbered should their network prefix change [1]. Tokenized
+IPv6 Identifiers are described in the draft
+[1]: <draft-chown-6man-tokenised-ipv6-identifiers-02>.
+
+.SS ip token set - set an interface token
+set the interface token to the kernel. Once a token is set, it cannot be
+removed from the interface, only overwritten.
+.TP
+.I TOKEN
+the interface identifier token address.
+.TP
+.BI dev " DEV"
+the networking interface.
+
+.SS ip token get - get the interface token from the kernel
+show a tokenized interface identifier of a particular networking device.
+.B Arguments:
+coincide with the arguments of
+.B ip token set
+but the
+.I TOKEN
+must be left out.
+.SS ip token list - list all interface tokens
+list all tokenized interface identifiers for the networking interfaces from
+the kernel.
+
+.SH SEE ALSO
+.br
+.BR ip (8)
+
+.SH AUTHOR
+Manpage by Daniel Borkmann
diff --git a/iproute2/man/man8/ip-tunnel.8 b/iproute2/man/man8/ip-tunnel.8
new file mode 100644
index 0000000..8b746cb
--- /dev/null
+++ b/iproute2/man/man8/ip-tunnel.8
@@ -0,0 +1,262 @@
+.TH IP\-TUNNEL 8 "20 Dec 2011" "iproute2" "Linux"
+.SH "NAME"
+ip-tunnel - tunnel configuration
+.SH "SYNOPSIS"
+.sp
+.ad l
+.in +8
+.ti -8
+.B ip tunnel help
+.sp
+.ti -8
+.BR "ip "
+.RI "[ " OPTIONS " ]"
+.BR "tunnel" " { " add " | " change " | " del " | " show " | " prl " }"
+.RI "[ " NAME " ]"
+.br
+.RB "[ " mode
+.IR MODE " ] [ "
+.B remote
+.IR ADDR " ] [ "
+.B local
+.IR ADDR " ]"
+.br
+.RB "[ [" i "|" o "]" seq " ] [ [" i "|" o "]" key
+.IR KEY " ] [ "
+.RB "[" i "|" o "]" csum " ] ]"
+.br
+.RB "[ " encaplimit
+.IR ELIM " ]"
+.RB "[ " ttl "|" hoplimit
+.IR TTL " ]"
+.br
+.RB "[ " tos
+.IR TOS " ] [ "
+.B flowlabel
+.IR FLOWLABEL " ]"
+.br
+.RB "[ " prl-default
+.IR ADDR " ] [ "
+.B prl-nodefault
+.IR ADDR " ] [ "
+.B prl-delete
+.IR ADDR " ]"
+.br
+.RB "[ [" no "]" pmtudisc " ]"
+.RB "[ " dev
+.IR PHYS_DEV " ]"
+
+.ti -8
+.IR MODE " := "
+.RB " { " ipip " | " gre " | " sit " | " isatap " | " vti " | " ip6ip6 " | " ipip6 " | " ip6gre " | " vti6 " | " any " }"
+
+.ti -8
+.IR ADDR " := { " IP_ADDRESS " |"
+.BR any " }"
+
+.ti -8
+.IR TOS " := { " STRING " | " 00 ".." ff " |"
+.BR inherit " |"
+.BI "inherit/" STRING
+.RB "|"
+.BI "inherit/" 00 ".." ff
+.RB "}"
+
+.ti -8
+.IR ELIM " := {"
+.BR none " | "
+.IR 0 ".." 255 " }"
+
+.ti -8
+.ti -8
+.IR TTL " := { " 1 ".." 255 " | "
+.BR inherit " }"
+
+.ti -8
+.IR KEY " := { " DOTTED_QUAD " | " NUMBER " }"
+
+.ti -8
+.IR TIME " := " NUMBER "[s|ms]"
+
+.SH DESCRIPTION
+.B tunnel
+objects are tunnels, encapsulating packets in IP packets and then
+sending them over the IP infrastructure.
+The encapsulating (or outer) address family is specified by the
+.B -f
+option. The default is IPv4.
+
+.TP
+.B ip tunnel add
+add a new tunnel
+.TP
+.B ip tunnel change
+change an existing tunnel
+.TP
+.B ip tunnel delete
+destroy a tunnel
+.RS
+.TP
+.BI name " NAME " (default)
+select the tunnel device name.
+
+.TP
+.BI mode " MODE"
+set the tunnel mode. Available modes depend on the encapsulating address family.
+.br
+Modes for IPv4 encapsulation available:
+.BR ipip ", " sit ", " isatap ", " vti ", and " gre "."
+.br
+Modes for IPv6 encapsulation available:
+.BR ip6ip6 ", " ipip6 ", " ip6gre ", " vti6 ", and " any "."
+
+.TP
+.BI remote " ADDRESS"
+set the remote endpoint of the tunnel.
+
+.TP
+.BI local " ADDRESS"
+set the fixed local address for tunneled packets.
+It must be an address on another interface of this host.
+
+.TP
+.BI ttl " N"
+.TP
+.BI hoplimit " N"
+set a fixed TTL (IPv4) or hoplimit (IPv6)
+.I N
+on tunneled packets.
+.I N
+is a number in the range 1--255. 0 is a special value
+meaning that packets inherit the TTL value.
+The default value for IPv4 tunnels is:
+.BR "inherit" .
+The default value for IPv6 tunnels is:
+.BR "64" .
+
+
+.TP
+.BI tos " T"
+.TP
+.BI dsfield " T"
+.TP
+.BI tclass " T"
+set the type of service (IPv4) or traffic class (IPv6) field on
+tunneled packets, which can be specified as either a two-digit
+hex value (e.g. c0) or a predefined string (e.g. internet).
+The value
+.B inherit
+causes the field to be copied from the original IP header. The
+values
+.BI "inherit/" STRING
+or
+.BI "inherit/" 00 ".." ff
+will set the field to
+.I STRING
+or
+.IR 00 ".." ff
+when tunneling non-IP packets. The default value is 00.
+
+.TP
+.BI dev " NAME"
+bind the tunnel to the device
+.I NAME
+so that tunneled packets will only be routed via this device and will
+not be able to escape to another device when the route to endpoint
+changes.
+
+.TP
+.B nopmtudisc
+disable Path MTU Discovery on this tunnel.
+It is enabled by default. Note that a fixed ttl is incompatible
+with this option: tunneling with a fixed ttl always makes pmtu
+discovery.
+
+.TP
+.BI key " K"
+.TP
+.BI ikey " K"
+.TP
+.BI okey " K"
+.RB ( " only GRE tunnels " )
+use keyed GRE with key
+.IR K ". " K
+is either a number or an IP address-like dotted quad.
+The
+.B key
+parameter sets the key to use in both directions.
+The
+.BR ikey " and " okey
+parameters set different keys for input and output.
+
+.TP
+.BR csum ", " icsum ", " ocsum
+.RB ( " only GRE tunnels " )
+generate/require checksums for tunneled packets.
+The
+.B ocsum
+flag calculates checksums for outgoing packets.
+The
+.B icsum
+flag requires that all input packets have the correct
+checksum. The
+.B csum
+flag is equivalent to the combination
+.BR "icsum ocsum" .
+
+.TP
+.BR seq ", " iseq ", " oseq
+.RB ( " only GRE tunnels " )
+serialize packets.
+The
+.B oseq
+flag enables sequencing of outgoing packets.
+The
+.B iseq
+flag requires that all input packets are serialized.
+The
+.B seq
+flag is equivalent to the combination
+.BR "iseq oseq" .
+.B It doesn't work. Don't use it.
+
+.TP
+.BI encaplim " ELIM"
+.RB ( " only IPv6 tunnels " )
+set a fixed encapsulation limit. Default is 4.
+
+.TP
+.BI flowlabel " FLOWLABEL"
+.RB ( " only IPv6 tunnels " )
+set a fixed flowlabel.
+.RE
+
+.TP
+.B ip tunnel prl
+potential router list (ISATAP only)
+.RS
+.TP
+.BI dev " NAME"
+mandatory device name.
+
+.TP
+.BI prl-default " ADDR"
+.TP
+.BI prl-nodefault " ADDR"
+.TP
+.BI prl-delete " ADDR"
+.RB "Add or delete " ADDR
+as a potential router or default router.
+.RE
+
+.TP
+.B ip tunnel show
+list tunnels
+This command has no arguments.
+
+.SH SEE ALSO
+.br
+.BR ip (8)
+
+.SH AUTHOR
+Original Manpage by Michail Litvak <mci@owl.openwall.com>
diff --git a/iproute2/man/man8/ip-xfrm.8 b/iproute2/man/man8/ip-xfrm.8
new file mode 100644
index 0000000..dae0728
--- /dev/null
+++ b/iproute2/man/man8/ip-xfrm.8
@@ -0,0 +1,694 @@
+.TH IP\-XFRM 8 "20 Dec 2011" "iproute2" "Linux"
+.SH "NAME"
+ip-xfrm \- transform configuration
+.SH "SYNOPSIS"
+.sp
+.ad l
+.in +8
+.ti -8
+.B ip
+.RI "[ " OPTIONS " ]"
+.B xfrm
+.RI " { " COMMAND " | "
+.BR help " }"
+.sp
+
+.ti -8
+.B "ip xfrm"
+.IR XFRM-OBJECT " { " COMMAND " | "
+.BR help " }"
+.sp
+
+.ti -8
+.IR XFRM-OBJECT " :="
+.BR state " | " policy " | " monitor
+.sp
+
+.ti -8
+.BR "ip xfrm state" " { " add " | " update " } "
+.IR ID " [ " ALGO-LIST " ]"
+.RB "[ " mode
+.IR MODE " ]"
+.RB "[ " mark
+.I MARK
+.RB "[ " mask
+.IR MASK " ] ]"
+.RB "[ " reqid
+.IR REQID " ]"
+.RB "[ " seq
+.IR SEQ " ]"
+.RB "[ " replay-window
+.IR SIZE " ]"
+.RB "[ " replay-seq
+.IR SEQ " ]"
+.RB "[ " replay-oseq
+.IR SEQ " ]"
+.RB "[ " replay-seq-hi
+.IR SEQ " ]"
+.RB "[ " replay-oseq-hi
+.IR SEQ " ]"
+.RB "[ " flag
+.IR FLAG-LIST " ]"
+.RB "[ " sel
+.IR SELECTOR " ] [ " LIMIT-LIST " ]"
+.RB "[ " encap
+.IR ENCAP " ]"
+.RB "[ " coa
+.IR ADDR "[/" PLEN "] ]"
+.RB "[ " ctx
+.IR CTX " ]"
+
+.ti -8
+.B "ip xfrm state allocspi"
+.I ID
+.RB "[ " mode
+.IR MODE " ]"
+.RB "[ " mark
+.I MARK
+.RB "[ " mask
+.IR MASK " ] ]"
+.RB "[ " reqid
+.IR REQID " ]"
+.RB "[ " seq
+.IR SEQ " ]"
+.RB "[ " min
+.I SPI
+.B max
+.IR SPI " ]"
+
+.ti -8
+.BR "ip xfrm state" " { " delete " | " get " } "
+.I ID
+.RB "[ " mark
+.I MARK
+.RB "[ " mask
+.IR MASK " ] ]"
+
+.ti -8
+.BR "ip xfrm state" " { " deleteall " | " list " } ["
+.IR ID " ]"
+.RB "[ " mode
+.IR MODE " ]"
+.RB "[ " reqid
+.IR REQID " ]"
+.RB "[ " flag
+.IR FLAG-LIST " ]"
+
+.ti -8
+.BR "ip xfrm state flush" " [ " proto
+.IR XFRM-PROTO " ]"
+
+.ti -8
+.BR "ip xfrm state count"
+
+.ti -8
+.IR ID " :="
+.RB "[ " src
+.IR ADDR " ]"
+.RB "[ " dst
+.IR ADDR " ]"
+.RB "[ " proto
+.IR XFRM-PROTO " ]"
+.RB "[ " spi
+.IR SPI " ]"
+
+.ti -8
+.IR XFRM-PROTO " :="
+.BR esp " | " ah " | " comp " | " route2 " | " hao
+
+.ti -8
+.IR ALGO-LIST " := [ " ALGO-LIST " ] " ALGO
+
+.ti -8
+.IR ALGO " :="
+.RB "{ " enc " | " auth " } "
+.IR ALGO-NAME " " ALGO-KEYMAT " |"
+.br
+.B auth-trunc
+.IR ALGO-NAME " " ALGO-KEYMAT " " ALGO-TRUNC-LEN " |"
+.br
+.B aead
+.IR ALGO-NAME " " ALGO-KEYMAT " " ALGO-ICV-LEN " |"
+.br
+.B comp
+.IR ALGO-NAME
+
+.ti -8
+.IR MODE " := "
+.BR transport " | " tunnel " | " beet " | " ro " | " in_trigger
+
+.ti -8
+.IR FLAG-LIST " := [ " FLAG-LIST " ] " FLAG
+
+.ti -8
+.IR FLAG " :="
+.BR noecn " | " decap-dscp " | " nopmtudisc " | " wildrecv " | " icmp " | "
+.BR af-unspec " | " align4 " | " esn
+
+.ti -8
+.IR SELECTOR " :="
+.RB "[ " src
+.IR ADDR "[/" PLEN "] ]"
+.RB "[ " dst
+.IR ADDR "[/" PLEN "] ]"
+.RB "[ " dev
+.IR DEV " ]"
+.br
+.RI "[ " UPSPEC " ]"
+
+.ti -8
+.IR UPSPEC " := "
+.BR proto " {"
+.IR PROTO " |"
+.br
+.RB "{ " tcp " | " udp " | " sctp " | " dccp " } [ " sport
+.IR PORT " ]"
+.RB "[ " dport
+.IR PORT " ] |"
+.br
+.RB "{ " icmp " | " ipv6-icmp " | " mobility-header " } [ " type
+.IR NUMBER " ]"
+.RB "[ " code
+.IR NUMBER " ] |"
+.br
+.BR gre " [ " key
+.RI "{ " DOTTED-QUAD " | " NUMBER " } ] }"
+
+.ti -8
+.IR LIMIT-LIST " := [ " LIMIT-LIST " ]"
+.B limit
+.I LIMIT
+
+.ti -8
+.IR LIMIT " :="
+.RB "{ " time-soft " | " time-hard " | " time-use-soft " | " time-use-hard " }"
+.IR "SECONDS" " |"
+.br
+.RB "{ " byte-soft " | " byte-hard " }"
+.IR SIZE " |"
+.br
+.RB "{ " packet-soft " | " packet-hard " }"
+.I COUNT
+
+.ti -8
+.IR ENCAP " :="
+.RB "{ " espinudp " | " espinudp-nonike " }"
+.IR SPORT " " DPORT " " OADDR
+
+.ti -8
+.BR "ip xfrm policy" " { " add " | " update " }"
+.I SELECTOR
+.B dir
+.I DIR
+.RB "[ " ctx
+.IR CTX " ]"
+.RB "[ " mark
+.I MARK
+.RB "[ " mask
+.IR MASK " ] ]"
+.RB "[ " index
+.IR INDEX " ]"
+.RB "[ " ptype
+.IR PTYPE " ]"
+.RB "[ " action
+.IR ACTION " ]"
+.RB "[ " priority
+.IR PRIORITY " ]"
+.RB "[ " flag
+.IR FLAG-LIST " ]"
+.RI "[ " LIMIT-LIST " ] [ " TMPL-LIST " ]"
+
+.ti -8
+.BR "ip xfrm policy" " { " delete " | " get " }"
+.RI "{ " SELECTOR " | "
+.B index
+.IR INDEX " }"
+.B dir
+.I DIR
+.RB "[ " ctx
+.IR CTX " ]"
+.RB "[ " mark
+.I MARK
+.RB "[ " mask
+.IR MASK " ] ]"
+.RB "[ " ptype
+.IR PTYPE " ]"
+
+.ti -8
+.BR "ip xfrm policy" " { " deleteall " | " list " }"
+.RI "[ " SELECTOR " ]"
+.RB "[ " dir
+.IR DIR " ]"
+.RB "[ " index
+.IR INDEX " ]"
+.RB "[ " ptype
+.IR PTYPE " ]"
+.RB "[ " action
+.IR ACTION " ]"
+.RB "[ " priority
+.IR PRIORITY " ]"
+
+.ti -8
+.B "ip xfrm policy flush"
+.RB "[ " ptype
+.IR PTYPE " ]"
+
+.ti -8
+.B "ip xfrm policy count"
+
+.ti -8
+.B "ip xfrm policy set"
+.RB "[ " hthresh4
+.IR LBITS " " RBITS " ]"
+.RB "[ " hthresh6
+.IR LBITS " " RBITS " ]"
+
+.ti -8
+.IR SELECTOR " :="
+.RB "[ " src
+.IR ADDR "[/" PLEN "] ]"
+.RB "[ " dst
+.IR ADDR "[/" PLEN "] ]"
+.RB "[ " dev
+.IR DEV " ]"
+.RI "[ " UPSPEC " ]"
+
+.ti -8
+.IR UPSPEC " := "
+.BR proto " {"
+.IR PROTO " |"
+.br
+.RB "{ " tcp " | " udp " | " sctp " | " dccp " } [ " sport
+.IR PORT " ]"
+.RB "[ " dport
+.IR PORT " ] |"
+.br
+.RB "{ " icmp " | " ipv6-icmp " | " mobility-header " } [ " type
+.IR NUMBER " ]"
+.RB "[ " code
+.IR NUMBER " ] |"
+.br
+.BR gre " [ " key
+.RI "{ " DOTTED-QUAD " | " NUMBER " } ] }"
+
+.ti -8
+.IR DIR " := "
+.BR in " | " out " | " fwd
+
+.ti -8
+.IR PTYPE " := "
+.BR main " | " sub
+
+.ti -8
+.IR ACTION " := "
+.BR allow " | " block
+
+.ti -8
+.IR FLAG-LIST " := [ " FLAG-LIST " ] " FLAG
+
+.ti -8
+.IR FLAG " :="
+.BR localok " | " icmp
+
+.ti -8
+.IR LIMIT-LIST " := [ " LIMIT-LIST " ]"
+.B limit
+.I LIMIT
+
+.ti -8
+.IR LIMIT " :="
+.RB "{ " time-soft " | " time-hard " | " time-use-soft " | " time-use-hard " }"
+.IR "SECONDS" " |"
+.br
+.RB "{ " byte-soft " | " byte-hard " }"
+.IR SIZE " |"
+.br
+.RB "{ " packet-soft " | " packet-hard " }"
+.I COUNT
+
+.ti -8
+.IR TMPL-LIST " := [ " TMPL-LIST " ]"
+.B tmpl
+.I TMPL
+
+.ti -8
+.IR TMPL " := " ID
+.RB "[ " mode
+.IR MODE " ]"
+.RB "[ " reqid
+.IR REQID " ]"
+.RB "[ " level
+.IR LEVEL " ]"
+
+.ti -8
+.IR ID " :="
+.RB "[ " src
+.IR ADDR " ]"
+.RB "[ " dst
+.IR ADDR " ]"
+.RB "[ " proto
+.IR XFRM-PROTO " ]"
+.RB "[ " spi
+.IR SPI " ]"
+
+.ti -8
+.IR XFRM-PROTO " :="
+.BR esp " | " ah " | " comp " | " route2 " | " hao
+
+.ti -8
+.IR MODE " := "
+.BR transport " | " tunnel " | " beet " | " ro " | " in_trigger
+
+.ti -8
+.IR LEVEL " :="
+.BR required " | " use
+
+.ti -8
+.BR "ip xfrm monitor" " ["
+.BI all-nsid
+] [
+.BI all
+ |
+.IR LISTofXFRM-OBJECTS " ]"
+
+.ti -8
+.IR LISTofXFRM-OBJECTS " := [ " LISTofXFRM-OBJECTS " ] " XFRM-OBJECT
+
+.ti -8
+.IR XFRM-OBJECT " := "
+.BR acquire " | " expire " | " SA " | " policy " | " aevent " | " report
+
+.in -8
+.ad b
+
+.SH DESCRIPTION
+
+xfrm is an IP framework for transforming packets (such as encrypting
+their payloads). This framework is used to implement the IPsec protocol
+suite (with the
+.B state
+object operating on the Security Association Database, and the
+.B policy
+object operating on the Security Policy Database). It is also used for
+the IP Payload Compression Protocol and features of Mobile IPv6.
+
+.TS
+l l.
+ip xfrm state add add new state into xfrm
+ip xfrm state update update existing state in xfrm
+ip xfrm state allocspi allocate an SPI value
+ip xfrm state delete delete existing state in xfrm
+ip xfrm state get get existing state in xfrm
+ip xfrm state deleteall delete all existing state in xfrm
+ip xfrm state list print out the list of existing state in xfrm
+ip xfrm state flush flush all state in xfrm
+ip xfrm state count count all existing state in xfrm
+.TE
+
+.TP
+.IR ID
+is specified by a source address, destination address,
+.RI "transform protocol " XFRM-PROTO ","
+and/or Security Parameter Index
+.IR SPI "."
+(For IP Payload Compression, the Compression Parameter Index or CPI is used for
+.IR SPI ".)"
+
+.TP
+.I XFRM-PROTO
+specifies a transform protocol:
+.RB "IPsec Encapsulating Security Payload (" esp "),"
+.RB "IPsec Authentication Header (" ah "),"
+.RB "IP Payload Compression (" comp "),"
+.RB "Mobile IPv6 Type 2 Routing Header (" route2 "), or"
+.RB "Mobile IPv6 Home Address Option (" hao ")."
+
+.TP
+.I ALGO-LIST
+contains one or more algorithms to use. Each algorithm
+.I ALGO
+is specified by:
+.RS
+.IP \[bu]
+the algorithm type:
+.RB "encryption (" enc "),"
+.RB "authentication (" auth " or " auth-trunc "),"
+.RB "authenticated encryption with associated data (" aead "), or"
+.RB "compression (" comp ")"
+.IP \[bu]
+the algorithm name
+.IR ALGO-NAME
+(see below)
+.IP \[bu]
+.RB "(for all except " comp ")"
+the keying material
+.IR ALGO-KEYMAT ","
+which may include both a key and a salt or nonce value; refer to the
+corresponding RFC
+.IP \[bu]
+.RB "(for " auth-trunc " only)"
+the truncation length
+.I ALGO-TRUNC-LEN
+in bits
+.IP \[bu]
+.RB "(for " aead " only)"
+the Integrity Check Value length
+.I ALGO-ICV-LEN
+in bits
+.RE
+
+.nh
+.RS
+Encryption algorithms include
+.BR ecb(cipher_null) ", " cbc(des) ", " cbc(des3_ede) ", " cbc(cast5) ","
+.BR cbc(blowfish) ", " cbc(aes) ", " cbc(serpent) ", " cbc(camellia) ","
+.BR cbc(twofish) ", and " rfc3686(ctr(aes)) "."
+
+Authentication algorithms include
+.BR digest_null ", " hmac(md5) ", " hmac(sha1) ", " hmac(sha256) ","
+.BR hmac(sha384) ", " hmac(sha512) ", " hmac(rmd610) ", and " xcbc(aes) "."
+
+Authenticated encryption with associated data (AEAD) algorithms include
+.BR rfc4106(gcm(aes)) ", " rfc4309(ccm(aes)) ", and " rfc4543(gcm(aes)) "."
+
+Compression algorithms include
+.BR deflate ", " lzs ", and " lzjh "."
+.RE
+.hy
+
+.TP
+.I MODE
+specifies a mode of operation for the transform protocol. IPsec and IP Payload
+Compression modes are
+.BR transport ", " tunnel ","
+and (for IPsec ESP only) Bound End-to-End Tunnel
+.RB "(" beet ")."
+Mobile IPv6 modes are route optimization
+.RB "(" ro ")"
+and inbound trigger
+.RB "(" in_trigger ")."
+
+.TP
+.I FLAG-LIST
+contains one or more of the following optional flags:
+.BR noecn ", " decap-dscp ", " nopmtudisc ", " wildrecv ", " icmp ", "
+.BR af-unspec ", " align4 ", or " esn "."
+
+.TP
+.IR SELECTOR
+selects the traffic that will be controlled by the policy, based on the source
+address, the destination address, the network device, and/or
+.IR UPSPEC "."
+
+.TP
+.IR UPSPEC
+selects traffic by protocol. For the
+.BR tcp ", " udp ", " sctp ", or " dccp
+protocols, the source and destination port can optionally be specified.
+For the
+.BR icmp ", " ipv6-icmp ", or " mobility-header
+protocols, the type and code numbers can optionally be specified.
+For the
+.B gre
+protocol, the key can optionally be specified as a dotted-quad or number.
+Other protocols can be selected by name or number
+.IR PROTO "."
+
+.TP
+.I LIMIT-LIST
+sets limits in seconds, bytes, or numbers of packets.
+
+.TP
+.I ENCAP
+encapsulates packets with protocol
+.BR espinudp " or " espinudp-nonike ","
+.RI "using source port " SPORT ", destination port " DPORT
+.RI ", and original address " OADDR "."
+
+.sp
+.PP
+.TS
+l l.
+ip xfrm policy add add a new policy
+ip xfrm policy update update an existing policy
+ip xfrm policy delete delete an existing policy
+ip xfrm policy get get an existing policy
+ip xfrm policy deleteall delete all existing xfrm policies
+ip xfrm policy list print out the list of xfrm policies
+ip xfrm policy flush flush policies
+.TE
+
+.TP
+.IR SELECTOR
+selects the traffic that will be controlled by the policy, based on the source
+address, the destination address, the network device, and/or
+.IR UPSPEC "."
+
+.TP
+.IR UPSPEC
+selects traffic by protocol. For the
+.BR tcp ", " udp ", " sctp ", or " dccp
+protocols, the source and destination port can optionally be specified.
+For the
+.BR icmp ", " ipv6-icmp ", or " mobility-header
+protocols, the type and code numbers can optionally be specified.
+For the
+.B gre
+protocol, the key can optionally be specified as a dotted-quad or number.
+Other protocols can be selected by name or number
+.IR PROTO "."
+
+.TP
+.I DIR
+selects the policy direction as
+.BR in ", " out ", or " fwd "."
+
+.TP
+.I CTX
+sets the security context.
+
+.TP
+.I PTYPE
+can be
+.BR main " (default) or " sub "."
+
+.TP
+.I ACTION
+can be
+.BR allow " (default) or " block "."
+
+.TP
+.I PRIORITY
+is a number that defaults to zero.
+
+.TP
+.I FLAG-LIST
+contains one or both of the following optional flags:
+.BR local " or " icmp "."
+
+.TP
+.I LIMIT-LIST
+sets limits in seconds, bytes, or numbers of packets.
+
+.TP
+.I TMPL-LIST
+is a template list specified using
+.IR ID ", " MODE ", " REQID ", and/or " LEVEL ". "
+
+.TP
+.IR ID
+is specified by a source address, destination address,
+.RI "transform protocol " XFRM-PROTO ","
+and/or Security Parameter Index
+.IR SPI "."
+(For IP Payload Compression, the Compression Parameter Index or CPI is used for
+.IR SPI ".)"
+
+.TP
+.I XFRM-PROTO
+specifies a transform protocol:
+.RB "IPsec Encapsulating Security Payload (" esp "),"
+.RB "IPsec Authentication Header (" ah "),"
+.RB "IP Payload Compression (" comp "),"
+.RB "Mobile IPv6 Type 2 Routing Header (" route2 "), or"
+.RB "Mobile IPv6 Home Address Option (" hao ")."
+
+.TP
+.I MODE
+specifies a mode of operation for the transform protocol. IPsec and IP Payload
+Compression modes are
+.BR transport ", " tunnel ","
+and (for IPsec ESP only) Bound End-to-End Tunnel
+.RB "(" beet ")."
+Mobile IPv6 modes are route optimization
+.RB "(" ro ")"
+and inbound trigger
+.RB "(" in_trigger ")."
+
+.TP
+.I LEVEL
+can be
+.BR required " (default) or " use "."
+
+.sp
+.PP
+.TS
+l l.
+ip xfrm policy count count existing policies
+.TE
+
+.PP
+Use one or more -s options to display more details, including policy hash table
+information.
+
+.sp
+.PP
+.TS
+l l.
+ip xfrm policy set configure the policy hash table
+.TE
+
+.PP
+Security policies whose address prefix lengths are greater than or equal
+policy hash table thresholds are hashed. Others are stored in the
+policy_inexact chained list.
+
+.TP
+.I LBITS
+specifies the minimum local address prefix length of policies that are
+stored in the Security Policy Database hash table.
+
+.TP
+.I RBITS
+specifies the minimum remote address prefix length of policies that are
+stored in the Security Policy Database hash table.
+
+.sp
+.PP
+.TS
+l l.
+ip xfrm monitor state monitoring for xfrm objects
+.TE
+
+.PP
+The xfrm objects to monitor can be optionally specified.
+
+.P
+If the
+.BI all-nsid
+option is set, the program listens to all network namespaces that have a
+nsid assigned into the network namespace were the program is running.
+A prefix is displayed to show the network namespace where the message
+originates. Example:
+.sp
+.in +2
+[nsid 1]Flushed state proto 0
+.in -2
+.sp
+
+.SH AUTHOR
+Manpage revised by David Ward <david.ward@ll.mit.edu>
+.br
+Manpage revised by Christophe Gouault <christophe.gouault@6wind.com>
+.br
+Manpage revised by Nicolas Dichtel <nicolas.dichtel@6wind.com>
diff --git a/iproute2/man/man8/ip.8 b/iproute2/man/man8/ip.8
new file mode 100644
index 0000000..b1f6907
--- /dev/null
+++ b/iproute2/man/man8/ip.8
@@ -0,0 +1,319 @@
+.TH IP 8 "20 Dec 2011" "iproute2" "Linux"
+.SH NAME
+ip \- show / manipulate routing, devices, policy routing and tunnels
+.SH SYNOPSIS
+
+.ad l
+.in +8
+.ti -8
+.B ip
+.RI "[ " OPTIONS " ] " OBJECT " { " COMMAND " | "
+.BR help " }"
+.sp
+
+.ti -8
+.B ip
+.RB "[ " -force " ] "
+.BI "-batch " filename
+.sp
+
+.ti -8
+.IR OBJECT " := { "
+.BR link " | " address " | " addrlabel " | " route " | " rule " | " neigh " | "\
+ ntable " | " tunnel " | " tuntap " | " maddress " | " mroute " | " mrule " | "\
+ monitor " | " xfrm " | " netns " | " l2tp " | " tcp_metrics " }"
+.sp
+
+.ti -8
+.IR OPTIONS " := { "
+\fB\-V\fR[\fIersion\fR] |
+\fB\-h\fR[\fIuman-readable\fR] |
+\fB\-s\fR[\fItatistics\fR] |
+\fB\-r\fR[\fIesolve\fR] |
+\fB\-f\fR[\fIamily\fR] {
+.BR inet " | " inet6 " | " ipx " | " dnet " | " link " } | "
+\fB\-o\fR[\fIneline\fR] |
+\fB\-n\fR[\fIetns\fR] name |
+\fB\-a\fR[\fIll\fR] |
+\fB\-c\fR[\fIolor\fR] }
+
+
+.SH OPTIONS
+
+.TP
+.BR "\-V" , " -Version"
+Print the version of the
+.B ip
+utility and exit.
+
+.TP
+.BR "\-h", " \-human", " \-human-readable"
+output statistics with human readable values followed by suffix.
+
+.TP
+.BR "\-b", " \-batch " <FILENAME>
+Read commands from provided file or standard input and invoke them.
+First failure will cause termination of ip.
+
+.TP
+.BR "\-force"
+Don't terminate ip on errors in batch mode.
+If there were any errors during execution of the commands, the application return code will be non zero.
+
+.TP
+.BR "\-s" , " \-stats" , " \-statistics"
+Output more information. If the option
+appears twice or more, the amount of information increases.
+As a rule, the information is statistics or some time values.
+
+.TP
+.BR "\-d" , " \-details"
+Output more detailed information.
+
+.TP
+.BR "\-l" , " \-loops " <COUNT>
+Specify maximum number of loops the 'ip address flush' logic
+will attempt before giving up. The default is 10.
+Zero (0) means loop until all addresses are removed.
+
+.TP
+.BR "\-f" , " \-family " <FAMILY>
+Specifies the protocol family to use. The protocol family identifier can be one of
+.BR "inet" , " inet6" , " bridge" , " ipx" , " dnet" , " mpls"
+or
+.BR link .
+If this option is not present,
+the protocol family is guessed from other arguments. If the rest
+of the command line does not give enough information to guess the
+family,
+.B ip
+falls back to the default one, usually
+.B inet
+or
+.BR "any" .
+.B link
+is a special family identifier meaning that no networking protocol
+is involved.
+
+.TP
+.B \-4
+shortcut for
+.BR "-family inet" .
+
+.TP
+.B \-6
+shortcut for
+.BR "\-family inet6" .
+
+.TP
+.B \-B
+shortcut for
+.BR "\-family bridge" .
+
+.TP
+.B \-D
+shortcut for
+.BR "\-family decnet" .
+
+.TP
+.B \-I
+shortcut for
+.BR "\-family ipx" .
+
+.TP
+.B \-M
+shortcut for
+.BR "\-family mpls" .
+
+.TP
+.B \-0
+shortcut for
+.BR "\-family link" .
+
+.TP
+.BR "\-o" , " \-oneline"
+output each record on a single line, replacing line feeds
+with the
+.B '\e'
+character. This is convenient when you want to count records
+with
+.BR wc (1)
+or to
+.BR grep (1)
+the output.
+
+.TP
+.BR "\-r" , " \-resolve"
+use the system's name resolver to print DNS names instead of
+host addresses.
+
+.TP
+.BR "\-n" , " \-netns " <NETNS>
+switches
+.B ip
+to the specified network namespace
+.IR NETNS .
+Actually it just simplifies executing of:
+
+.B ip netns exec
+.IR NETNS
+.B ip
+.RI "[ " OPTIONS " ] " OBJECT " { " COMMAND " | "
+.BR help " }"
+
+to
+
+.B ip
+.RI "-n[etns] " NETNS " [ " OPTIONS " ] " OBJECT " { " COMMAND " | "
+.BR help " }"
+
+.TP
+.BR "\-a" , " \-all"
+executes specified command over all objects, it depends if command supports this option.
+
+.TP
+.BR "\-c" , " -color"
+Use color output.
+
+.TP
+.BR "\-t" , " \-timestamp"
+display current time when using monitor option.
+
+.SH IP - COMMAND SYNTAX
+
+.SS
+.I OBJECT
+
+.TP
+.B address
+- protocol (IP or IPv6) address on a device.
+
+.TP
+.B addrlabel
+- label configuration for protocol address selection.
+
+.TP
+.B l2tp
+- tunnel ethernet over IP (L2TPv3).
+
+.TP
+.B link
+- network device.
+
+.TP
+.B maddress
+- multicast address.
+
+.TP
+.B monitor
+- watch for netlink messages.
+
+.TP
+.B mroute
+- multicast routing cache entry.
+
+.TP
+.B mrule
+- rule in multicast routing policy database.
+
+.TP
+.B neighbour
+- manage ARP or NDISC cache entries.
+
+.TP
+.B netns
+- manage network namespaces.
+
+.TP
+.B ntable
+- manage the neighbor cache's operation.
+
+.TP
+.B route
+- routing table entry.
+
+.TP
+.B rule
+- rule in routing policy database.
+
+.TP
+.B tcp_metrics/tcpmetrics
+- manage TCP Metrics
+
+.TP
+.B tunnel
+- tunnel over IP.
+
+.TP
+.B tuntap
+- manage TUN/TAP devices.
+
+.TP
+.B xfrm
+- manage IPSec policies.
+
+.PP
+The names of all objects may be written in full or
+abbreviated form, for example
+.B address
+can be abbreviated as
+.B addr
+or just
+.B a.
+
+.SS
+.I COMMAND
+
+Specifies the action to perform on the object.
+The set of possible actions depends on the object type.
+As a rule, it is possible to
+.BR "add" , " delete"
+and
+.B show
+(or
+.B list
+) objects, but some objects do not allow all of these operations
+or have some additional commands. The
+.B help
+command is available for all objects. It prints
+out a list of available commands and argument syntax conventions.
+.sp
+If no command is given, some default command is assumed.
+Usually it is
+.B list
+or, if the objects of this class cannot be listed,
+.BR "help" .
+
+.SH EXIT STATUS
+Exit status is 0 if command was successful, and 1 if there is a syntax error.
+If an error was reported by the kernel exit status is 2.
+
+.SH HISTORY
+.B ip
+was written by Alexey N. Kuznetsov and added in Linux 2.2.
+.SH SEE ALSO
+.BR ip-address (8),
+.BR ip-addrlabel (8),
+.BR ip-l2tp (8),
+.BR ip-link (8),
+.BR ip-maddress (8),
+.BR ip-monitor (8),
+.BR ip-mroute (8),
+.BR ip-neighbour (8),
+.BR ip-netns (8),
+.BR ip-ntable (8),
+.BR ip-route (8),
+.BR ip-rule (8),
+.BR ip-tcp_metrics (8),
+.BR ip-tunnel (8),
+.BR ip-xfrm (8)
+.br
+.RB "IP Command reference " ip-cref.ps
+.SH REPORTING BUGS
+Report any bugs to the Network Developers mailing list
+.B <netdev@vger.kernel.org>
+where the development and maintenance is primarily done.
+You do not have to be subscribed to the list to send a message there.
+
+.SH AUTHOR
+Original Manpage by Michail Litvak <mci@owl.openwall.com>
diff --git a/iproute2/man/man8/lnstat.8 b/iproute2/man/man8/lnstat.8
new file mode 100644
index 0000000..acd5f4a
--- /dev/null
+++ b/iproute2/man/man8/lnstat.8
@@ -0,0 +1,263 @@
+.TH LNSTAT 8
+.SH NAME
+lnstat \- unified linux network statistics
+.SH SYNOPSIS
+.B lnstat
+.RI [ options ]
+.SH DESCRIPTION
+This manual page documents briefly the
+.B lnstat
+command.
+.PP
+\fBlnstat\fP is a generalized and more feature-complete replacement for the old
+rtstat program. It is commonly used to periodically print a selection of
+statistical values exported by the kernel.
+In addition to routing cache statistics, it supports any kind of statistics the
+linux kernel exports via a file in /proc/net/stat/.
+.PP
+Each file in /proc/net/stat/ contains a header line listing the column names.
+These names are used by \fBlnstat\fP as keys for selecting which statistics to
+print. For every CPU present in the system, a line follows which lists the
+actual values for each column of the file. \fBlnstat\fP sums these values up
+(which in fact are counters) before printing them. After each interval, only
+the difference to the last value is printed.
+.PP
+Files and columns may be selected by using the \fB-f\fP and \fB-k\fP
+parameters. By default, all columns of all files are printed.
+.SH OPTIONS
+lnstat supports the following options.
+.TP
+.B \-h, \-\-help
+Show summary of options.
+.TP
+.B \-V, \-\-version
+Show version of program.
+.TP
+.B \-c, \-\-count <count>
+Print <count> number of intervals.
+.TP
+.B \-d, \-\-dump
+Dump list of available files/keys.
+.TP
+.B \-f, \-\-file <file>
+Statistics file to use, may be specified multiple times. By default all files in /proc/net/stat are scanned.
+.TP
+.B \-i, \-\-interval <intv>
+Set interval to 'intv' seconds.
+.TP
+.B \-j, \-\-json
+Display results in JSON format
+.TP
+.B \-k, \-\-keys k,k,k,...
+Display only keys specified. Each key \fBk\fP is of the form \fB[file:]key\fP. If \fB<file>\fP
+is given, the search for the given key is limited to that file. Otherwise the first file containing
+the searched key is being used.
+.TP
+.B \-s, \-\-subject [0-2]
+Specify display of subject/header. '0' means no header at all, '1' prints a header only at start of the program and '2' prints a header every 20 lines.
+.TP
+.B \-w, \-\-width n,n,n,...
+Width for each field.
+.SH USAGE EXAMPLES
+.TP
+.B # lnstat -d
+Get a list of supported statistics files.
+.TP
+.B # lnstat -k arp_cache:entries,rt_cache:in_hit,arp_cache:destroys
+Select the specified files and keys.
+.TP
+.B # lnstat -i 10
+Use an interval of 10 seconds.
+.TP
+.B # lnstat -f ip_conntrack
+Use only the specified file for statistics.
+.TP
+.B # lnstat -s 0
+Do not print a header at all.
+.TP
+.B # lnstat -s 20
+Print a header at start and every 20 lines.
+.TP
+.B # lnstat -c -1 -i 1 -f rt_cache -k entries,in_hit,in_slow_tot
+Display statistics for keys entries, in_hit and in_slow_tot of field rt_cache every second.
+
+.SH FILES
+.TP
+.B /proc/net/stat/arp_cache, /proc/net/stat/ndisc_cache
+Statistics around neighbor cache and ARP. \fBarp_cache\fP is for IPv4, \fBndisc_cache\fP is the same for IPv6.
+.sp
+.B entries
+Number of entries in the neighbor table.
+.sp
+.B allocs
+How many neighbor entries have been allocated.
+.sp
+.B destroys
+How many neighbor entries have been removed.
+.sp
+.B hash_grows
+How often the neighbor (hash) table was increased.
+.sp
+.B lookups
+How many lookups were performed.
+.sp
+.B hits
+How many \fBlookups\fP were successful.
+.sp
+.B res_failed
+How many neighbor lookups failed.
+.sp
+.B rcv_probes_mcast
+How many multicast neighbor solicitations were received. (IPv6 only.)
+.sp
+.B rcv_probes_ucast
+How many unicast neighbor solicitations were received. (IPv6 only.)
+.sp
+.B periodic_gc_runs
+How many garbage collection runs were executed.
+.sp
+.B forced_gc_runs
+How many forced garbage collection runs were executed. Happens when adding an
+entry and the table is too full.
+.sp
+.B unresolved_discards
+How many neighbor table entries were discarded due to lookup failure.
+.sp
+.B table_fulls
+Number of table overflows. Happens if table is full and forced GC run (see
+\fBforced_gc_runs\fP) has failed.
+
+.TP
+.B /proc/net/stat/ip_conntrack, /proc/net/stat/nf_conntrack
+Conntrack related counters. \fBip_conntrack\fP is for backwards compatibility
+with older userspace only and shows the same data as \fBnf_conntrack\fP.
+.sp
+.B entries
+Number of entries in conntrack table.
+.sp
+.B searched
+Number of conntrack table lookups performed.
+.sp
+.B found
+Number of \fBsearched\fP entries which were successful.
+.sp
+.B new
+Number of conntrack entries added which were not expected before.
+.sp
+.B invalid
+Number of packets seen which can not be tracked.
+.sp
+.B ignore
+Number of packets seen which are already connected to a conntrack entry.
+.sp
+.B delete
+Number of conntrack entries which were removed.
+.sp
+.B delete_list
+Number of conntrack entries which were put to dying list.
+.sp
+.B insert
+Number of entries inserted into the list.
+.sp
+.B insert_failed
+Number of entries for which list insertion was attempted but failed (happens if
+the same entry is already present).
+.sp
+.B drop
+Number of packets dropped due to conntrack failure. Either new conntrack entry
+allocation failed, or protocol helper dropped the packet.
+.sp
+.B early_drop
+Number of dropped conntrack entries to make room for new ones, if maximum table
+size was reached.
+.sp
+.B icmp_error
+Number of packets which could not be tracked due to error situation. This is a
+subset of \fBinvalid\fP.
+.sp
+.B expect_new
+Number of conntrack entries added after an expectation for them was already
+present.
+.sp
+.B expect_create
+Number of expectations added.
+.sp
+.B expect_delete
+Number of expectations deleted.
+.sp
+.B search_restart
+Number of conntrack table lookups which had to be restarted due to hashtable
+resizes.
+
+.TP
+.B /proc/net/stat/rt_cache
+Routing cache statistics.
+.sp
+.B entries
+Number of entries in routing cache.
+.sp
+.B in_hit
+Number of route cache hits for incoming packets. Deprecated since IP route
+cache removal, therefore always zero.
+.sp
+.B in_slow_tot
+Number of routing cache entries added for input traffic.
+.sp
+.B in_slow_mc
+Number of multicast routing cache entries added for input traffic.
+.sp
+.B in_no_route
+Number of input packets for which no routing table entry was found.
+.sp
+.B in_brd
+Number of matched input broadcast packets.
+.sp
+.B in_martian_dst
+Number of incoming martian destination packets.
+.sp
+.B in_martian_src
+Number of incoming martian source packets.
+.sp
+.B out_hit
+Number of route cache hits for outgoing packets. Deprecated since IP route
+cache removal, therefore always zero.
+.sp
+.B out_slow_tot
+Number of routing cache entries added for output traffic.
+.sp
+.B out_slow_mc
+Number of multicast routing cache entries added for output traffic.
+.sp
+.B gc_total
+Total number of garbage collection runs. Deprecated since IP route cache
+removal, therefore always zero.
+.sp
+.B gc_ignored
+Number of ignored garbage collection runs due to minimum GC interval not
+reached and routing cache not full. Deprecated since IP route cache removal,
+therefore always zero.
+.sp
+.B gc_goal_miss
+Number of garbage collector goal misses. Deprecated since IP route cache
+removal, therefore always zero.
+.sp
+.B gc_dst_overflow
+Number of destination cache overflows. Deprecated since IP route cache removal,
+therefore always zero.
+.sp
+.B in_hlist_search
+Number of hash table list traversals for input traffic. Deprecated since IP
+route cache removal, therefore always zero.
+.sp
+.B out_hlist_search
+Number of hash table list traversals for output traffic. Deprecated since IP
+route cache removal, therefore always zero.
+
+.SH SEE ALSO
+.BR ip (8),
+and /usr/share/doc/iproute-doc/README.lnstat (package iproute-doc on Debian)
+.br
+.SH AUTHOR
+lnstat was written by Harald Welte <laforge@gnumonks.org>.
+.PP
+This manual page was written by Michael Prokop <mika@grml.org> for the Debian project (but may be used by others).
diff --git a/iproute2/man/man8/nstat.8 b/iproute2/man/man8/nstat.8
new file mode 100644
index 0000000..c703cc8
--- /dev/null
+++ b/iproute2/man/man8/nstat.8
@@ -0,0 +1 @@
+.so man8/rtacct.8
diff --git a/iproute2/man/man8/routef.8 b/iproute2/man/man8/routef.8
new file mode 100644
index 0000000..c2a7059
--- /dev/null
+++ b/iproute2/man/man8/routef.8
@@ -0,0 +1 @@
+.so man8/routel.8
diff --git a/iproute2/man/man8/routel.8 b/iproute2/man/man8/routel.8
new file mode 100644
index 0000000..82d580f
--- /dev/null
+++ b/iproute2/man/man8/routel.8
@@ -0,0 +1,32 @@
+.TH "ROUTEL" "8" "3 Jan, 2008" "iproute2" "Linux"
+.SH "NAME"
+.LP
+routel \- list routes with pretty output format
+.br
+routef \- flush routes
+.SH "SYNTAX"
+.LP
+routel [\fItablenr\fP [\fIraw ip args...\fP]]
+.br
+routef
+.SH "DESCRIPTION"
+.LP
+These programs are a set of helper scripts you can use instead of raw iproute2 commands.
+.br
+The routel script will list routes in a format that some might consider easier to interpret then the ip route list equivalent.
+.br
+The routef script does not take any arguments and will simply flush the routing table down the drain. Beware! This means deleting all routes which will make your network unusable!
+
+.SH "FILES"
+.LP
+\fI/usr/bin/routef\fP
+.br
+\fI/usr/bin/routel\fP
+.SH "AUTHORS"
+.LP
+The routel script was written by Stephen R. van den Berg <srb@cuci.nl>, 1999/04/18 and donated to the public domain.
+.br
+This manual page was written by Andreas Henriksson <andreas@fatal.se>, for the Debian GNU/Linux system.
+.SH "SEE ALSO"
+.LP
+ip(8)
diff --git a/iproute2/man/man8/rtacct.8 b/iproute2/man/man8/rtacct.8
new file mode 100644
index 0000000..7cf97aa
--- /dev/null
+++ b/iproute2/man/man8/rtacct.8
@@ -0,0 +1,49 @@
+.TH RTACCT 8 "27 June, 2007"
+
+.SH NAME
+nstat, rtacct - network statistics tools.
+
+.SH SYNOPSIS
+Usage: nstat [ -h?vVzrnasd:t: ] [ PATTERN [ PATTERN ] ]
+.br
+Usage: rtacct [ -h?vVzrnasd:t: ] [ ListOfRealms ]
+
+.SH DESCRIPTION
+.B nstat
+and
+.B rtacct
+are simple tools to monitor kernel snmp counters and network interface statistics.
+
+.SH OPTIONS
+.B \-h, \-\-help
+Print help
+.TP
+.B \-V, \-\-version
+Print version
+.TP
+.B \-z, \-\-zero
+Dump zero counters too. By default they are not shown.
+.TP
+.B \-r, \-\-reset
+Reset history.
+.TP
+.B \-n, \-\-nooutput
+Do not display anything, only update history.
+.TP
+.B \-a, \-\-ignore
+Dump absolute values of counters. The default is to calculate increments since the previous use.
+.TP
+.B \-s, \-\-noupdate
+Do not update history, so that the next time you will see counters including values accumulated to the moment of this measurement too.
+.B \-j, \-\-json
+Display results in JSON format.
+.TP
+.B \-d, \-\-interval <INTERVAL>
+Run in daemon mode collecting statistics. <INTERVAL> is interval between measurements in seconds.
+.TP
+
+Time interval to average rates. Default value is 60 seconds.
+.TP
+
+.SH SEE ALSO
+lnstat(8)
diff --git a/iproute2/man/man8/rtmon.8 b/iproute2/man/man8/rtmon.8
new file mode 100644
index 0000000..38a2b77
--- /dev/null
+++ b/iproute2/man/man8/rtmon.8
@@ -0,0 +1,68 @@
+.TH RTMON 8
+.SH NAME
+rtmon \- listens to and monitors RTnetlink
+.SH SYNOPSIS
+.B rtmon
+.RI "[ options ] file FILE [ all | LISTofOBJECTS ]"
+.SH DESCRIPTION
+This manual page documents briefly the
+.B rtmon
+command.
+.PP
+.B rtmon
+listens on
+.I netlink
+socket and monitors routing table changes.
+
+.I rtmon
+can be started before the first network configuration command is issued.
+For example if you insert:
+
+.B rtmon file /var/log/rtmon.log
+
+in a startup script, you will be able to view the full history later.
+Certainly, it is possible to start rtmon at any time. It prepends the history with the state snapshot dumped at the moment of starting.
+
+.SH OPTIONS
+.I rtmon supports the following options:
+.TP
+.B \-Version
+Print version and exit.
+.TP
+.B help
+Show summary of options.
+.TP
+.B file FILE [ all | LISTofOBJECTS ]
+Log output to FILE. LISTofOBJECTS is the list of object types that we
+want to monitor. It may contain 'link', 'address', 'route'
+and 'all'. 'link' specifies the network device, 'address' the protocol
+(IP or IPv6) address on a device, 'route' the routing table entry
+and 'all' does what the name says.
+.TP
+.B \-family [ inet | inet6 | link | help ]
+Specify protocol family. 'inet' is IPv4, 'inet6' is IPv6, 'link'
+means that no networking protocol is involved and 'help' prints usage information.
+.TP
+.B \-4
+Use IPv4. Shortcut for -family inet.
+.TP
+.B \-6
+Use IPv6. Shortcut for -family inet6.
+.TP
+.B \-0
+Use a special family identifier meaning that no networking protocol is involved. Shortcut for -family link.
+.SH USAGE EXAMPLES
+.TP
+.B # rtmon file /var/log/rtmon.log
+Log to file /var/log/rtmon.log, then run:
+.TP
+.B # ip monitor file /var/log/rtmon.log
+to display logged output from file.
+.SH SEE ALSO
+.BR ip (8)
+.SH AUTHOR
+.B rtmon
+was written by Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>.
+.PP
+This manual page was written by Michael Prokop <mika@grml.org>,
+for the Debian project (but may be used by others).
diff --git a/iproute2/man/man8/rtpr.8 b/iproute2/man/man8/rtpr.8
new file mode 100644
index 0000000..5e32b2e
--- /dev/null
+++ b/iproute2/man/man8/rtpr.8
@@ -0,0 +1,25 @@
+.TH RTPR 8 "18 September, 2015"
+
+.SH NAME
+rtpr \- replace backslashes with newlines.
+
+.SH DESCRIPTION
+.B rtpr
+is a trivial bash script which converts backslashes in standard input to newlines. It's sole purpose is to be fed with input from
+.B ip
+when executed with it's
+.B --oneline
+flag.
+
+.SH EXAMPLES
+.TP
+ip --onenline address show | rtpr
+Undo oneline converted
+.B ip-address
+output.
+
+.SH SEE ALSO
+.BR ip (8)
+
+.SH AUTHORS
+Stephen Hemminger <shemming@brocade.com>
diff --git a/iproute2/man/man8/rtstat.8 b/iproute2/man/man8/rtstat.8
new file mode 100644
index 0000000..080e2b2
--- /dev/null
+++ b/iproute2/man/man8/rtstat.8
@@ -0,0 +1 @@
+.so man8/lnstat.8
diff --git a/iproute2/man/man8/ss.8 b/iproute2/man/man8/ss.8
new file mode 100644
index 0000000..758460c
--- /dev/null
+++ b/iproute2/man/man8/ss.8
@@ -0,0 +1,204 @@
+.TH SS 8
+.SH NAME
+ss \- another utility to investigate sockets
+.SH SYNOPSIS
+.B ss
+.RI [ options ] " [ FILTER ]"
+.SH DESCRIPTION
+.B ss
+is used to dump socket statistics. It allows showing information similar
+to
+.IR netstat .
+It can display more TCP and state informations than other tools.
+
+.SH OPTIONS
+When no option is used ss displays a list of
+open non-listening sockets (e.g. TCP/UNIX/UDP) that have established connection.
+.TP
+.B \-h, \-\-help
+Show summary of options.
+.TP
+.B \-V, \-\-version
+Output version information.
+.TP
+.B \-n, \-\-numeric
+Do not try to resolve service names.
+.TP
+.B \-r, \-\-resolve
+Try to resolve numeric address/ports.
+.TP
+.B \-a, \-\-all
+Display both listening and non-listening (for TCP this means established connections) sockets.
+.TP
+.B \-l, \-\-listening
+Display only listening sockets (these are omitted by default).
+.TP
+.B \-o, \-\-options
+Show timer information.
+.TP
+.B \-e, \-\-extended
+Show detailed socket information
+.TP
+.B \-m, \-\-memory
+Show socket memory usage.
+.TP
+.B \-p, \-\-processes
+Show process using socket.
+.TP
+.B \-i, \-\-info
+Show internal TCP information.
+.TP
+.B \-K, \-\-kill
+Attempts to forcibly close sockets. This option displays sockets that are
+successfully closed and silently skips sockets that the kernel does not support
+closing. It supports IPv4 and IPv6 sockets only.
+.TP
+.B \-s, \-\-summary
+Print summary statistics. This option does not parse socket lists obtaining
+summary from various sources. It is useful when amount of sockets is so huge
+that parsing /proc/net/tcp is painful.
+.TP
+.B \-Z, \-\-context
+As the
+.B \-p
+option but also shows process security context.
+.sp
+For
+.BR netlink (7)
+sockets the initiating process context is displayed as follows:
+.RS
+.RS
+.IP "1." 4
+If valid pid show the process context.
+.IP "2." 4
+If destination is kernel (pid = 0) show kernel initial context.
+.IP "3." 4
+If a unique identifier has been allocated by the kernel or netlink user,
+show context as "unavailable". This will generally indicate that a
+process has more than one netlink socket active.
+.RE
+.RE
+.TP
+.B \-z, \-\-contexts
+As the
+.B \-Z
+option but also shows the socket context. The socket context is
+taken from the associated inode and is not the actual socket
+context held by the kernel. Sockets are typically labeled with the
+context of the creating process, however the context shown will reflect
+any policy role, type and/or range transition rules applied,
+and is therefore a useful reference.
+.TP
+.B \-N NSNAME, \-\-net=NSNAME
+Switch to the specified network namespace name.
+.TP
+.B \-b, \-\-bpf
+Show socket BPF filters (only administrators are allowed to get these information).
+.TP
+.B \-4, \-\-ipv4
+Display only IP version 4 sockets (alias for -f inet).
+.TP
+.B \-6, \-\-ipv6
+Display only IP version 6 sockets (alias for -f inet6).
+.TP
+.B \-0, \-\-packet
+Display PACKET sockets (alias for -f link).
+.TP
+.B \-t, \-\-tcp
+Display TCP sockets.
+.TP
+.B \-u, \-\-udp
+Display UDP sockets.
+.TP
+.B \-d, \-\-dccp
+Display DCCP sockets.
+.TP
+.B \-w, \-\-raw
+Display RAW sockets.
+.TP
+.B \-x, \-\-unix
+Display Unix domain sockets (alias for -f unix).
+.TP
+.B \-f FAMILY, \-\-family=FAMILY
+Display sockets of type FAMILY.
+Currently the following families are supported: unix, inet, inet6, link, netlink.
+.TP
+.B \-A QUERY, \-\-query=QUERY, \-\-socket=QUERY
+List of socket tables to dump, separated by commas. The following identifiers
+are understood: all, inet, tcp, udp, raw, unix, packet, netlink, unix_dgram,
+unix_stream, unix_seqpacket, packet_raw, packet_dgram.
+.TP
+.B \-D FILE, \-\-diag=FILE
+Do not display anything, just dump raw information about TCP sockets to FILE after applying filters. If FILE is - stdout is used.
+.TP
+.B \-F FILE, \-\-filter=FILE
+Read filter information from FILE.
+Each line of FILE is interpreted like single command line option. If FILE is - stdin is used.
+.TP
+.B FILTER := [ state STATE-FILTER ] [ EXPRESSION ]
+Please take a look at the official documentation (Debian package iproute-doc) for details regarding filters.
+
+.SH STATE-FILTER
+
+.B STATE-FILTER
+allows to construct arbitrary set of states to match. Its syntax is sequence of keywords state and exclude followed by identifier of state.
+.TP
+Available identifiers are:
+
+All standard TCP states:
+.BR established ", " syn-sent ", " syn-recv ", " fin-wait-1 ", " fin-wait-2 ", " time-wait ", " closed ", " close-wait ", " last-ack ", "
+.BR listen " and " closing.
+
+.B all
+- for all the states
+
+.B connected
+- all the states except for
+.BR listen " and " closed
+
+.B synchronized
+- all the
+.B connected
+states except for
+.B syn-sent
+
+.B bucket
+- states, which are maintained as minisockets, i.e.
+.BR time-wait " and " syn-recv
+
+.B big
+- opposite to
+.B bucket
+
+.SH USAGE EXAMPLES
+.TP
+.B ss -t -a
+Display all TCP sockets.
+.TP
+.B ss -t -a -Z
+Display all TCP sockets with process SELinux security contexts.
+.TP
+.B ss -u -a
+Display all UDP sockets.
+.TP
+.B ss -o state established '( dport = :ssh or sport = :ssh )'
+Display all established ssh connections.
+.TP
+.B ss -x src /tmp/.X11-unix/*
+Find all local processes connected to X server.
+.TP
+.B ss -o state fin-wait-1 '( sport = :http or sport = :https )' dst 193.233.7/24
+List all the tcp sockets in state FIN-WAIT-1 for our apache to network 193.233.7/24 and look at their timers.
+.SH SEE ALSO
+.BR ip (8),
+.BR /usr/share/doc/iproute-doc/ss.html " (package iproutedoc)",
+.br
+.BR RFC " 793 "
+- https://tools.ietf.org/rfc/rfc793.txt (TCP states)
+
+.SH AUTHOR
+.I ss
+was written by Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>.
+.PP
+This manual page was written by Michael Prokop <mika@grml.org>
+for the Debian project (but may be used by others).
diff --git a/iproute2/man/man8/tc-basic.8 b/iproute2/man/man8/tc-basic.8
new file mode 100644
index 0000000..fb39eaa
--- /dev/null
+++ b/iproute2/man/man8/tc-basic.8
@@ -0,0 +1,34 @@
+.TH "Basic classifier in tc" 8 "21 Oct 2015" "iproute2" "Linux"
+
+.SH NAME
+basic \- basic traffic control filter
+.SH SYNOPSIS
+.in +8
+.ti -8
+.BR tc " " filter " ... " basic " [ " match
+.IR EMATCH_TREE " ] [ "
+.B action
+.IR ACTION_SPEC " ] [ "
+.B classid
+.IR CLASSID " ]"
+.SH DESCRIPTION
+The
+.B basic
+filter allows to classify packets using the extended match infrastructure.
+.SH OPTIONS
+.TP
+.BI action " ACTION_SPEC"
+Apply an action from the generic actions framework on matching packets.
+.TP
+.BI classid " CLASSID"
+Push matching packets into the class identified by
+.IR CLASSID .
+.TP
+.BI match " EMATCH_TREE"
+Match packets using the extended match infrastructure. See
+.BR tc-ematch (8)
+for a detailed description of the allowed syntax in
+.IR EMATCH_TREE .
+.SH SEE ALSO
+.BR tc (8),
+.BR tc-ematch (8)
diff --git a/iproute2/man/man8/tc-bfifo.8 b/iproute2/man/man8/tc-bfifo.8
new file mode 100644
index 0000000..3e29032
--- /dev/null
+++ b/iproute2/man/man8/tc-bfifo.8
@@ -0,0 +1,74 @@
+.TH PBFIFO 8 "10 January 2002" "iproute2" "Linux"
+.SH NAME
+pfifo \- Packet limited First In, First Out queue
+.P
+bfifo \- Byte limited First In, First Out queue
+
+.SH SYNOPSIS
+.B tc qdisc ... add pfifo
+.B [ limit
+packets
+.B ]
+.P
+.B tc qdisc ... add bfifo
+.B [ limit
+bytes
+.B ]
+
+.SH DESCRIPTION
+The pfifo and bfifo qdiscs are unadorned First In, First Out queues. They are the
+simplest queues possible and therefore have no overhead.
+.B pfifo
+constrains the queue size as measured in packets.
+.B bfifo
+does so as measured in bytes.
+
+Like all non-default qdiscs, they maintain statistics. This might be a reason to prefer
+pfifo or bfifo over the default.
+
+.SH ALGORITHM
+A list of packets is maintained, when a packet is enqueued it gets inserted at the tail of
+a list. When a packet needs to be sent out to the network, it is taken from the head of the list.
+
+If the list is too long, no further packets are allowed on. This is called 'tail drop'.
+
+.SH PARAMETERS
+.TP
+limit
+Maximum queue size. Specified in bytes for bfifo, in packets for pfifo. For pfifo, defaults
+to the interface txqueuelen, as specified with
+.BR ifconfig (8)
+or
+.BR ip (8).
+The range for this parameter is [0, UINT32_MAX].
+
+For bfifo, it defaults to the txqueuelen multiplied by the interface MTU.
+The range for this parameter is [0, UINT32_MAX] bytes.
+
+Note: The link layer header was considered when counting packets length.
+
+.SH OUTPUT
+The output of
+.B tc -s qdisc ls
+contains the limit, either in packets or in bytes, and the number of bytes
+and packets actually sent. An unsent and dropped packet only appears between braces
+and is not counted as 'Sent'.
+
+In this example, the queue length is 100 packets, 45894 bytes were sent over 681 packets.
+No packets were dropped, and as the pfifo queue does not slow down packets, there were also no
+overlimits:
+.P
+.nf
+# tc -s qdisc ls dev eth0
+qdisc pfifo 8001: dev eth0 limit 100p
+ Sent 45894 bytes 681 pkts (dropped 0, overlimits 0)
+.fi
+
+If a backlog occurs, this is displayed as well.
+.SH SEE ALSO
+.BR tc (8)
+
+.SH AUTHORS
+Alexey N. Kuznetsov, <kuznet@ms2.inr.ac.ru>
+
+This manpage maintained by bert hubert <ahu@ds9a.nl>
diff --git a/iproute2/man/man8/tc-bpf.8 b/iproute2/man/man8/tc-bpf.8
new file mode 100644
index 0000000..c8d5c5f
--- /dev/null
+++ b/iproute2/man/man8/tc-bpf.8
@@ -0,0 +1,924 @@
+.TH "BPF classifier and actions in tc" 8 "18 May 2015" "iproute2" "Linux"
+.SH NAME
+BPF \- BPF programmable classifier and actions for ingress/egress
+queueing disciplines
+.SH SYNOPSIS
+.SS eBPF classifier (filter) or action:
+.B tc filter ... bpf
+[
+.B object-file
+OBJ_FILE ] [
+.B section
+CLS_NAME ] [
+.B export
+UDS_FILE ] [
+.B verbose
+] [
+.B police
+POLICE_SPEC ] [
+.B action
+ACTION_SPEC ] [
+.B classid
+CLASSID ]
+.br
+.B tc action ... bpf
+[
+.B object-file
+OBJ_FILE ] [
+.B section
+CLS_NAME ] [
+.B export
+UDS_FILE ] [
+.B verbose
+]
+
+.SS cBPF classifier (filter) or action:
+.B tc filter ... bpf
+[
+.B bytecode-file
+BPF_FILE |
+.B bytecode
+BPF_BYTECODE ] [
+.B police
+POLICE_SPEC ] [
+.B action
+ACTION_SPEC ] [
+.B classid
+CLASSID ]
+.br
+.B tc action ... bpf
+[
+.B bytecode-file
+BPF_FILE |
+.B bytecode
+BPF_BYTECODE ]
+
+.SH DESCRIPTION
+
+Extended Berkeley Packet Filter (
+.B eBPF
+) and classic Berkeley Packet Filter
+(originally known as BPF, for better distinction referred to as
+.B cBPF
+here) are both available as a fully programmable and highly efficient
+classifier and actions. They both offer a minimal instruction set for
+implementing small programs which can safely be loaded into the kernel
+and thus executed in a tiny virtual machine from kernel space. An in-kernel
+verifier guarantees that a specified program always terminates and neither
+crashes nor leaks data from the kernel.
+
+In Linux, it's generally considered that eBPF is the successor of cBPF.
+The kernel internally transforms cBPF expressions into eBPF expressions and
+executes the latter. Execution of them can be performed in an interpreter
+or at setup time, they can be just-in-time compiled (JIT'ed) to run as
+native machine code. Currently, x86_64, ARM64 and s390 architectures have
+eBPF JIT support, whereas PPC, SPARC, ARM and MIPS have cBPF, but did not
+(yet) switch to eBPF JIT support.
+
+eBPF's instruction set has similar underlying principles as the cBPF
+instruction set, it however is modelled closer to the underlying
+architecture to better mimic native instruction sets with the aim to
+achieve a better run-time performance. It is designed to be JIT'ed with
+a one to one mapping, which can also open up the possibility for compilers
+to generate optimized eBPF code through an eBPF backend that performs
+almost as fast as natively compiled code. Given that LLVM provides such
+an eBPF backend, eBPF programs can therefore easily be programmed in a
+subset of the C language. Other than that, eBPF infrastructure also comes
+with a construct called "maps". eBPF maps are key/value stores that are
+shared between multiple eBPF programs, but also between eBPF programs and
+user space applications.
+
+For the traffic control subsystem, classifier and actions that can be
+attached to ingress and egress qdiscs can be written in eBPF or cBPF. The
+advantage over other classifier and actions is that eBPF/cBPF provides the
+generic framework, while users can implement their highly specialized use
+cases efficiently. This means that the classifier or action written that
+way will not suffer from feature bloat, and can therefore execute its task
+highly efficient. It allows for non-linear classification and even merging
+the action part into the classification. Combined with efficient eBPF map
+data structures, user space can push new policies like classids into the
+kernel without reloading a classifier, or it can gather statistics that
+are pushed into one map and use another one for dynamically load balancing
+traffic based on the determined load, just to provide a few examples.
+
+.SH PARAMETERS
+.SS object-file
+points to an object file that has an executable and linkable format (ELF)
+and contains eBPF opcodes and eBPF map definitions. The LLVM compiler
+infrastructure with
+.B clang(1)
+as a C language front end is one project that supports emitting eBPF object
+files that can be passed to the eBPF classifier (more details in the
+.B EXAMPLES
+section). This option is mandatory when an eBPF classifier or action is
+to be loaded.
+
+.SS section
+is the name of the ELF section from the object file, where the eBPF
+classifier or action resides. By default the section name for the
+classifier is called "classifier", and for the action "action". Given
+that a single object file can contain multiple classifier and actions,
+the corresponding section name needs to be specified, if it differs
+from the defaults.
+
+.SS export
+points to a Unix domain socket file. In case the eBPF object file also
+contains a section named "maps" with eBPF map specifications, then the
+map file descriptors can be handed off via the Unix domain socket to
+an eBPF "agent" herding all descriptors after tc lifetime. This can be
+some third party application implementing the IPC counterpart for the
+import, that uses them for calling into
+.B bpf(2)
+system call to read out or update eBPF map data from user space, for
+example, for monitoring purposes or to push down new policies.
+
+.SS verbose
+if set, it will dump the eBPF verifier output, even if loading the eBPF
+program was successful. By default, only on error, the verifier log is
+being emitted to the user.
+
+.SS police
+is an optional parameter for an eBPF/cBPF classifier that specifies a
+police in
+.B tc(1)
+which is attached to the classifier, for example, on an ingress qdisc.
+
+.SS action
+is an optional parameter for an eBPF/cBPF classifier that specifies a
+subsequent action in
+.B tc(1)
+which is attached to a classifier.
+
+.SS classid
+.SS flowid
+provides the default traffic control class identifier for this eBPF/cBPF
+classifier. The default class identifier can also be overwritten by the
+return code of the eBPF/cBPF program. A default return code of
+.B -1
+specifies the here provided default class identifier to be used. A return
+code of the eBPF/cBPF program of 0 implies that no match took place, and
+a return code other than these two will override the default classid. This
+allows for efficient, non-linear classification with only a single eBPF/cBPF
+program as opposed to having multiple individual programs for various class
+identifiers which would need to reparse packet contents.
+
+.SS bytecode
+is being used for loading cBPF classifier and actions only. The cBPF bytecode
+is directly passed as a text string in the form of
+.B \'s,c t f k,c t f k,c t f k,...\'
+, where
+.B s
+denotes the number of subsequent 4-tuples. One such 4-tuple consists of
+.B c t f k
+decimals, where
+.B c
+represents the cBPF opcode,
+.B t
+the jump true offset target,
+.B f
+the jump false offset target and
+.B k
+the immediate constant/literal. There are various tools that generate code
+in this loadable format, for example,
+.B bpf_asm
+that ships with the Linux kernel source tree under
+.B tools/net/
+, so it is certainly not expected to hack this by hand. The
+.B bytecode
+or
+.B bytecode-file
+option is mandatory when a cBPF classifier or action is to be loaded.
+
+.SS bytecode-file
+also being used to load a cBPF classifier or action. It's effectively the
+same as
+.B bytecode
+only that the cBPF bytecode is not passed directly via command line, but
+rather resides in a text file.
+
+.SH EXAMPLES
+.SS eBPF TOOLING
+A full blown example including eBPF agent code can be found inside the
+iproute2 source package under:
+.B examples/bpf/
+
+As prerequisites, the kernel needs to have the eBPF system call namely
+.B bpf(2)
+enabled and ships with
+.B cls_bpf
+and
+.B act_bpf
+kernel modules for the traffic control subsystem. To enable eBPF/eBPF JIT
+support, depending which of the two the given architecture supports:
+
+.in +4n
+.B echo 1 > /proc/sys/net/core/bpf_jit_enable
+.in
+
+A given restricted C file can be compiled via LLVM as:
+
+.in +4n
+.B clang -O2 -emit-llvm -c bpf.c -o - | llc -march=bpf -filetype=obj -o bpf.o
+.in
+
+The compiler invocation might still simplify in future, so for now,
+it's quite handy to alias this construct in one way or another, for
+example:
+.in +4n
+.nf
+.sp
+__bcc() {
+ clang -O2 -emit-llvm -c $1 -o - | \\
+ llc -march=bpf -filetype=obj -o "`basename $1 .c`.o"
+}
+
+alias bcc=__bcc
+.fi
+.in
+
+A minimal, stand-alone unit, which matches on all traffic with the
+default classid (return code of -1) looks like:
+
+.in +4n
+.nf
+.sp
+#include <linux/bpf.h>
+
+#ifndef __section
+# define __section(x) __attribute__((section(x), used))
+#endif
+
+__section("classifier") int cls_main(struct __sk_buff *skb)
+{
+ return -1;
+}
+
+char __license[] __section("license") = "GPL";
+.fi
+.in
+
+More examples can be found further below in subsection
+.B eBPF PROGRAMMING
+as focus here will be on tooling.
+
+There can be various other sections, for example, also for actions.
+Thus, an object file in eBPF can contain multiple entrance points.
+Always a specific entrance point, however, must be specified when
+configuring with tc. A license must be part of the restricted C code
+and the license string syntax is the same as with Linux kernel modules.
+The kernel reserves its right that some eBPF helper functions can be
+restricted to GPL compatible licenses only, and thus may reject a program
+from loading into the kernel when such a license mismatch occurs.
+
+The resulting object file from the compilation can be inspected with
+the usual set of tools that also operate on normal object files, for
+example
+.B objdump(1)
+for inspecting ELF section headers:
+
+.in +4n
+.nf
+.sp
+objdump -h bpf.o
+[...]
+3 classifier 000007f8 0000000000000000 0000000000000000 00000040 2**3
+ CONTENTS, ALLOC, LOAD, RELOC, READONLY, CODE
+4 action-mark 00000088 0000000000000000 0000000000000000 00000838 2**3
+ CONTENTS, ALLOC, LOAD, RELOC, READONLY, CODE
+5 action-rand 00000098 0000000000000000 0000000000000000 000008c0 2**3
+ CONTENTS, ALLOC, LOAD, RELOC, READONLY, CODE
+6 maps 00000030 0000000000000000 0000000000000000 00000958 2**2
+ CONTENTS, ALLOC, LOAD, DATA
+7 license 00000004 0000000000000000 0000000000000000 00000988 2**0
+ CONTENTS, ALLOC, LOAD, DATA
+[...]
+.fi
+.in
+
+Adding an eBPF classifier from an object file that contains a classifier
+in the default ELF section is trivial (note that instead of "object-file"
+also shortcuts such as "obj" can be used):
+
+.in +4n
+.B bcc bpf.c
+.br
+.B tc filter add dev em1 parent 1: bpf obj bpf.o flowid 1:1
+.in
+
+In case the classifier resides in ELF section "mycls", then that same
+command needs to be invoked as:
+
+.in +4n
+.B tc filter add dev em1 parent 1: bpf obj bpf.o sec mycls flowid 1:1
+.in
+
+Dumping the classifier configuration will tell the location of the
+classifier, in other words that it's from object file "bpf.o" under
+section "mycls":
+
+.in +4n
+.B tc filter show dev em1
+.br
+.B filter parent 1: protocol all pref 49152 bpf
+.br
+.B filter parent 1: protocol all pref 49152 bpf handle 0x1 flowid 1:1 bpf.o:[mycls]
+.in
+
+The same program can also be installed on ingress qdisc side as opposed
+to egress ...
+
+.in +4n
+.B tc qdisc add dev em1 handle ffff: ingress
+.br
+.B tc filter add dev em1 parent ffff: bpf obj bpf.o sec mycls flowid ffff:1
+.in
+
+\&... and again dumped from there:
+
+.in +4n
+.B tc filter show dev em1 parent ffff:
+.br
+.B filter protocol all pref 49152 bpf
+.br
+.B filter protocol all pref 49152 bpf handle 0x1 flowid ffff:1 bpf.o:[mycls]
+.in
+
+Attaching a classifier and action on ingress has the restriction that
+it doesn't have an actual underlying queueing discipline. What ingress
+can do is to classify, mangle, redirect or drop packets. When queueing
+is required on ingress side, then ingress must redirect packets to the
+.B ifb
+device, otherwise policing can be used. Moreover, ingress can be used to
+have an early drop point of unwanted packets before they hit upper layers
+of the networking stack, perform network accounting with eBPF maps that
+could be shared with egress, or have an early mangle and/or redirection
+point to different networking devices.
+
+Multiple eBPF actions and classifier can be placed into a single
+object file within various sections. In that case, non-default section
+names must be provided, which is the case for both actions in this
+example:
+
+.in +4n
+.B tc filter add dev em1 parent 1: bpf obj bpf.o flowid 1:1 \e
+.br
+.in +25n
+.B action bpf obj bpf.o sec action-mark \e
+.br
+.B action bpf obj bpf.o sec action-rand ok
+.in -25n
+.in -4n
+
+The advantage of this is that the classifier and the two actions can
+then share eBPF maps with each other, if implemented in the programs.
+
+In order to access eBPF maps from user space beyond
+.B tc(8)
+setup lifetime, the ownership can be transferred to an eBPF agent via
+Unix domain sockets. There are two possibilities for implementing this:
+
+.B 1)
+implementation of an own eBPF agent that takes care of setting up
+the Unix domain socket and implementing the protocol that
+.B tc(8)
+dictates. A code example of this can be found inside the iproute2
+source package under:
+.B examples/bpf/
+
+.B 2)
+use
+.B tc exec
+for transferring the eBPF map file descriptors through a Unix domain
+socket, and spawning an application such as
+.B sh(1)
+\&. This approach's advantage is that tc will place the file descriptors
+into the environment and thus make them available just like stdin, stdout,
+stderr file descriptors, meaning, in case user applications run from within
+this fd-owner shell, they can terminate and restart without losing eBPF
+maps file descriptors. Example invocation with the previous classifier and
+action mixture:
+
+.in +4n
+.B tc exec bpf imp /tmp/bpf
+.br
+.B tc filter add dev em1 parent 1: bpf obj bpf.o exp /tmp/bpf flowid 1:1 \e
+.br
+.in +25n
+.B action bpf obj bpf.o sec action-mark \e
+.br
+.B action bpf obj bpf.o sec action-rand ok
+.in -25n
+.in -4n
+
+Assuming that eBPF maps are shared with classifier and actions, it's
+enough to export them once, for example, from within the classifier
+or action command. tc will setup all eBPF map file descriptors at the
+time when the object file is first parsed.
+
+When a shell has been spawned, the environment will have a couple of
+eBPF related variables. BPF_NUM_MAPS provides the total number of maps
+that have been transferred over the Unix domain socket. BPF_MAP<X>'s
+value is the file descriptor number that can be accessed in eBPF agent
+applications, in other words, it can directly be used as the file
+descriptor value for the
+.B bpf(2)
+system call to retrieve or alter eBPF map values. <X> denotes the
+identifier of the eBPF map. It corresponds to the
+.B id
+member of
+.B struct bpf_elf_map
+\& from the tc eBPF map specification.
+
+The environment in this example looks as follows:
+
+.in +4n
+.nf
+.sp
+sh# env | grep BPF
+ BPF_NUM_MAPS=3
+ BPF_MAP1=6
+ BPF_MAP0=5
+ BPF_MAP2=7
+sh# ls -la /proc/self/fd
+ [...]
+ lrwx------. 1 root root 64 Apr 14 16:46 5 -> anon_inode:bpf-map
+ lrwx------. 1 root root 64 Apr 14 16:46 6 -> anon_inode:bpf-map
+ lrwx------. 1 root root 64 Apr 14 16:46 7 -> anon_inode:bpf-map
+sh# my_bpf_agent
+.fi
+.in
+
+eBPF agents are very useful in that they can prepopulate eBPF maps from
+user space, monitor statistics via maps and based on that feedback, for
+example, rewrite classids in eBPF map values during runtime. Given that eBPF
+agents are implemented as normal applications, they can also dynamically
+receive traffic control policies from external controllers and thus push
+them down into eBPF maps to dynamically adapt to network conditions. Moreover,
+eBPF maps can also be shared with other eBPF program types (e.g. tracing),
+thus very powerful combination can therefore be implemented.
+
+.SS eBPF PROGRAMMING
+
+eBPF classifier and actions are being implemented in restricted C syntax
+(in future, there could additionally be new language frontends supported).
+
+The header file
+.B linux/bpf.h
+provides eBPF helper functions that can be called from an eBPF program.
+This man page will only provide two minimal, stand-alone examples, have a
+look at
+.B examples/bpf
+from the iproute2 source package for a fully fledged flow dissector
+example to better demonstrate some of the possibilities with eBPF.
+
+Supported 32 bit classifier return codes from the C program and their meanings:
+.in +4n
+.B 0
+, denotes a mismatch
+.br
+.B -1
+, denotes the default classid configured from the command line
+.br
+.B else
+, everything else will override the default classid to provide a facility for
+non-linear matching
+.in
+
+Supported 32 bit action return codes from the C program and their meanings (
+.B linux/pkt_cls.h
+):
+.in +4n
+.B TC_ACT_OK (0)
+, will terminate the packet processing pipeline and allows the packet to
+proceed
+.br
+.B TC_ACT_SHOT (2)
+, will terminate the packet processing pipeline and drops the packet
+.br
+.B TC_ACT_UNSPEC (-1)
+, will use the default action configured from tc (similarly as returning
+.B -1
+from a classifier)
+.br
+.B TC_ACT_PIPE (3)
+, will iterate to the next action, if available
+.br
+.B TC_ACT_RECLASSIFY (1)
+, will terminate the packet processing pipeline and start classification
+from the beginning
+.br
+.B else
+, everything else is an unspecified return code
+.in
+
+Both classifier and action return codes are supported in eBPF and cBPF
+programs.
+
+To demonstrate restricted C syntax, a minimal toy classifier example is
+provided, which assumes that egress packets, for instance originating
+from a container, have previously been marked in interval [0, 255]. The
+program keeps statistics on different marks for user space and maps the
+classid to the root qdisc with the marking itself as the minor handle:
+
+.in +4n
+.nf
+.sp
+#include <stdint.h>
+#include <asm/types.h>
+
+#include <linux/bpf.h>
+#include <linux/pkt_sched.h>
+
+#include "helpers.h"
+
+struct tuple {
+ long packets;
+ long bytes;
+};
+
+#define BPF_MAP_ID_STATS 1 /* agent's map identifier */
+#define BPF_MAX_MARK 256
+
+struct bpf_elf_map __section("maps") map_stats = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .id = BPF_MAP_ID_STATS,
+ .size_key = sizeof(uint32_t),
+ .size_value = sizeof(struct tuple),
+ .max_elem = BPF_MAX_MARK,
+};
+
+static inline void cls_update_stats(const struct __sk_buff *skb,
+ uint32_t mark)
+{
+ struct tuple *tu;
+
+ tu = bpf_map_lookup_elem(&map_stats, &mark);
+ if (likely(tu)) {
+ __sync_fetch_and_add(&tu->packets, 1);
+ __sync_fetch_and_add(&tu->bytes, skb->len);
+ }
+}
+
+__section("cls") int cls_main(struct __sk_buff *skb)
+{
+ uint32_t mark = skb->mark;
+
+ if (unlikely(mark >= BPF_MAX_MARK))
+ return 0;
+
+ cls_update_stats(skb, mark);
+
+ return TC_H_MAKE(TC_H_ROOT, mark);
+}
+
+char __license[] __section("license") = "GPL";
+.fi
+.in
+
+Another small example is a port redirector which demuxes destination port
+80 into the interval [8080, 8087] steered by RSS, that can then be attached
+to ingress qdisc. The exercise of adding the egress counterpart and IPv6
+support is left to the reader:
+
+.in +4n
+.nf
+.sp
+#include <asm/types.h>
+#include <asm/byteorder.h>
+
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/tcp.h>
+
+#include "helpers.h"
+
+static inline void set_tcp_dport(struct __sk_buff *skb, int nh_off,
+ __u16 old_port, __u16 new_port)
+{
+ bpf_l4_csum_replace(skb, nh_off + offsetof(struct tcphdr, check),
+ old_port, new_port, sizeof(new_port));
+ bpf_skb_store_bytes(skb, nh_off + offsetof(struct tcphdr, dest),
+ &new_port, sizeof(new_port), 0);
+}
+
+static inline int lb_do_ipv4(struct __sk_buff *skb, int nh_off)
+{
+ __u16 dport, dport_new = 8080, off;
+ __u8 ip_proto, ip_vl;
+
+ ip_proto = load_byte(skb, nh_off +
+ offsetof(struct iphdr, protocol));
+ if (ip_proto != IPPROTO_TCP)
+ return 0;
+
+ ip_vl = load_byte(skb, nh_off);
+ if (likely(ip_vl == 0x45))
+ nh_off += sizeof(struct iphdr);
+ else
+ nh_off += (ip_vl & 0xF) << 2;
+
+ dport = load_half(skb, nh_off + offsetof(struct tcphdr, dest));
+ if (dport != 80)
+ return 0;
+
+ off = skb->queue_mapping & 7;
+ set_tcp_dport(skb, nh_off - BPF_LL_OFF, __constant_htons(80),
+ __cpu_to_be16(dport_new + off));
+ return -1;
+}
+
+__section("lb") int lb_main(struct __sk_buff *skb)
+{
+ int ret = 0, nh_off = BPF_LL_OFF + ETH_HLEN;
+
+ if (likely(skb->protocol == __constant_htons(ETH_P_IP)))
+ ret = lb_do_ipv4(skb, nh_off);
+
+ return ret;
+}
+
+char __license[] __section("license") = "GPL";
+.fi
+.in
+
+The related helper header file
+.B helpers.h
+in both examples was:
+
+.in +4n
+.nf
+.sp
+/* Misc helper macros. */
+#define __section(x) __attribute__((section(x), used))
+#define offsetof(x, y) __builtin_offsetof(x, y)
+#define likely(x) __builtin_expect(!!(x), 1)
+#define unlikely(x) __builtin_expect(!!(x), 0)
+
+/* Used map structure */
+struct bpf_elf_map {
+ __u32 type;
+ __u32 size_key;
+ __u32 size_value;
+ __u32 max_elem;
+ __u32 id;
+};
+
+/* Some used BPF function calls. */
+static int (*bpf_skb_store_bytes)(void *ctx, int off, void *from,
+ int len, int flags) =
+ (void *) BPF_FUNC_skb_store_bytes;
+static int (*bpf_l4_csum_replace)(void *ctx, int off, int from,
+ int to, int flags) =
+ (void *) BPF_FUNC_l4_csum_replace;
+static void *(*bpf_map_lookup_elem)(void *map, void *key) =
+ (void *) BPF_FUNC_map_lookup_elem;
+
+/* Some used BPF intrinsics. */
+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");
+.fi
+.in
+
+Best practice, we recommend to only have a single eBPF classifier loaded
+in tc and perform
+.B all
+necessary matching and mangling from there instead of a list of individual
+classifier and separate actions. Just a single classifier tailored for a
+given use-case will be most efficient to run.
+
+.SS eBPF DEBUGGING
+
+Both tc
+.B filter
+and
+.B action
+commands for
+.B bpf
+support an optional
+.B verbose
+parameter that can be used to inspect the eBPF verifier log. It is dumped
+by default in case of an error.
+
+In case the eBPF/cBPF JIT compiler has been enabled, it can also be
+instructed to emit a debug output of the resulting opcode image into
+the kernel log, which can be read via
+.B dmesg(1)
+:
+
+.in +4n
+.B echo 2 > /proc/sys/net/core/bpf_jit_enable
+.in
+
+The Linux kernel source tree ships additionally under
+.B tools/net/
+a small helper called
+.B bpf_jit_disasm
+that reads out the opcode image dump from the kernel log and dumps the
+resulting disassembly:
+
+.in +4n
+.B bpf_jit_disasm -o
+.in
+
+Other than that, the Linux kernel also contains an extensive eBPF/cBPF
+test suite module called
+.B test_bpf
+\&. Upon ...
+
+.in +4n
+.B modprobe test_bpf
+.in
+
+\&... it performs a diversity of test cases and dumps the results into
+the kernel log that can be inspected with
+.B dmesg(1)
+\&. The results can differ depending on whether the JIT compiler is enabled
+or not. In case of failed test cases, the module will fail to load. In
+such cases, we urge you to file a bug report to the related JIT authors,
+Linux kernel and networking mailing lists.
+
+.SS cBPF
+
+Although we generally recommend switching to implementing
+.B eBPF
+classifier and actions, for the sake of completeness, a few words on how to
+program in cBPF will be lost here.
+
+Likewise, the
+.B bpf_jit_enable
+switch can be enabled as mentioned already. Tooling such as
+.B bpf_jit_disasm
+is also independent whether eBPF or cBPF code is being loaded.
+
+Unlike in eBPF, classifier and action are not implemented in restricted C,
+but rather in a minimal assembler-like language or with the help of other
+tooling.
+
+The raw interface with tc takes opcodes directly. For example, the most
+minimal classifier matching on every packet resulting in the default
+classid of 1:1 looks like:
+
+.in +4n
+.B tc filter add dev em1 parent 1: bpf bytecode '1,6 0 0 4294967295,' flowid 1:1
+.in
+
+The first decimal of the bytecode sequence denotes the number of subsequent
+4-tuples of cBPF opcodes. As mentioned, such a 4-tuple consists of
+.B c t f k
+decimals, where
+.B c
+represents the cBPF opcode,
+.B t
+the jump true offset target,
+.B f
+the jump false offset target and
+.B k
+the immediate constant/literal. Here, this denotes an unconditional return
+from the program with immediate value of -1.
+
+Thus, for egress classification, Willem de Bruijn implemented a minimal stand-alone
+helper tool under the GNU General Public License version 2 for
+.B iptables(8)
+BPF extension, which abuses the
+.B libpcap
+internal classic BPF compiler, his code derived here for usage with
+.B tc(8)
+:
+
+.in +4n
+.nf
+.sp
+#include <pcap.h>
+#include <stdio.h>
+
+int main(int argc, char **argv)
+{
+ struct bpf_program prog;
+ struct bpf_insn *ins;
+ int i, ret, dlt = DLT_RAW;
+
+ if (argc < 2 || argc > 3)
+ return 1;
+ if (argc == 3) {
+ dlt = pcap_datalink_name_to_val(argv[1]);
+ if (dlt == -1)
+ return 1;
+ }
+
+ ret = pcap_compile_nopcap(-1, dlt, &prog, argv[argc - 1],
+ 1, PCAP_NETMASK_UNKNOWN);
+ if (ret)
+ return 1;
+
+ printf("%d,", prog.bf_len);
+ ins = prog.bf_insns;
+
+ for (i = 0; i < prog.bf_len - 1; ++ins, ++i)
+ printf("%u %u %u %u,", ins->code,
+ ins->jt, ins->jf, ins->k);
+ printf("%u %u %u %u",
+ ins->code, ins->jt, ins->jf, ins->k);
+
+ pcap_freecode(&prog);
+ return 0;
+}
+.fi
+.in
+
+Given this small helper, any
+.B tcpdump(8)
+filter expression can be abused as a classifier where a match will
+result in the default classid:
+
+.in +4n
+.B bpftool EN10MB 'tcp[tcpflags] & tcp-syn != 0' > /var/bpf/tcp-syn
+.br
+.B tc filter add dev em1 parent 1: bpf bytecode-file /var/bpf/tcp-syn flowid 1:1
+.in
+
+Basically, such a minimal generator is equivalent to:
+
+.in +4n
+.B tcpdump -iem1 -ddd 'tcp[tcpflags] & tcp-syn != 0' | tr '\\\\n' ',' > /var/bpf/tcp-syn
+.in
+
+Since
+.B libpcap
+does not support all Linux' specific cBPF extensions in its compiler, the
+Linux kernel also ships under
+.B tools/net/
+a minimal BPF assembler called
+.B bpf_asm
+for providing full control. For detailed syntax and semantics on implementing
+such programs by hand, see references under
+.B FURTHER READING
+\&.
+
+Trivial toy example in
+.B bpf_asm
+for classifying IPv4/TCP packets, saved in a text file called
+.B foobar
+:
+
+.in +4n
+.nf
+.sp
+ldh [12]
+jne #0x800, drop
+ldb [23]
+jneq #6, drop
+ret #-1
+drop: ret #0
+.fi
+.in
+
+Similarly, such a classifier can be loaded as:
+
+.in +4n
+.B bpf_asm foobar > /var/bpf/tcp-syn
+.br
+.B tc filter add dev em1 parent 1: bpf bytecode-file /var/bpf/tcp-syn flowid 1:1
+.in
+
+For BPF classifiers, the Linux kernel provides additionally under
+.B tools/net/
+a small BPF debugger called
+.B bpf_dbg
+, which can be used to test a classifier against pcap files, single-step
+or add various breakpoints into the classifier program and dump register
+contents during runtime.
+
+Implementing an action in classic BPF is rather limited in the sense that
+packet mangling is not supported. Therefore, it's generally recommended to
+make the switch to eBPF, whenever possible.
+
+.SH FURTHER READING
+Further and more technical details about the BPF architecture can be found
+in the Linux kernel source tree under
+.B Documentation/networking/filter.txt
+\&.
+
+Further details on eBPF
+.B tc(8)
+examples can be found in the iproute2 source
+tree under
+.B examples/bpf/
+\&.
+
+.SH SEE ALSO
+.BR tc (8),
+.BR tc-ematch (8)
+.BR bpf (2)
+.BR bpf (4)
+
+.SH AUTHORS
+Manpage written by Daniel Borkmann.
+
+Please report corrections or improvements to the Linux kernel networking
+mailing list:
+.B <netdev@vger.kernel.org>
diff --git a/iproute2/man/man8/tc-cbq-details.8 b/iproute2/man/man8/tc-cbq-details.8
new file mode 100644
index 0000000..9368103
--- /dev/null
+++ b/iproute2/man/man8/tc-cbq-details.8
@@ -0,0 +1,423 @@
+.TH CBQ 8 "8 December 2001" "iproute2" "Linux"
+.SH NAME
+CBQ \- Class Based Queueing
+.SH SYNOPSIS
+.B tc qdisc ... dev
+dev
+.B ( parent
+classid
+.B | root) [ handle
+major:
+.B ] cbq avpkt
+bytes
+.B bandwidth
+rate
+.B [ cell
+bytes
+.B ] [ ewma
+log
+.B ] [ mpu
+bytes
+.B ]
+
+.B tc class ... dev
+dev
+.B parent
+major:[minor]
+.B [ classid
+major:minor
+.B ] cbq allot
+bytes
+.B [ bandwidth
+rate
+.B ] [ rate
+rate
+.B ] prio
+priority
+.B [ weight
+weight
+.B ] [ minburst
+packets
+.B ] [ maxburst
+packets
+.B ] [ ewma
+log
+.B ] [ cell
+bytes
+.B ] avpkt
+bytes
+.B [ mpu
+bytes
+.B ] [ bounded isolated ] [ split
+handle
+.B & defmap
+defmap
+.B ] [ estimator
+interval timeconstant
+.B ]
+
+.SH DESCRIPTION
+Class Based Queueing is a classful qdisc that implements a rich
+linksharing hierarchy of classes. It contains shaping elements as
+well as prioritizing capabilities. Shaping is performed using link
+idle time calculations based on the timing of dequeue events and
+underlying link bandwidth.
+
+.SH SHAPING ALGORITHM
+Shaping is done using link idle time calculations, and actions taken if
+these calculations deviate from set limits.
+
+When shaping a 10mbit/s connection to 1mbit/s, the link will
+be idle 90% of the time. If it isn't, it needs to be throttled so that it
+IS idle 90% of the time.
+
+From the kernel's perspective, this is hard to measure, so CBQ instead
+derives the idle time from the number of microseconds (in fact, jiffies)
+that elapse between requests from the device driver for more data. Combined
+with the knowledge of packet sizes, this is used to approximate how full or
+empty the link is.
+
+This is rather circumspect and doesn't always arrive at proper
+results. For example, what is the actual link speed of an interface
+that is not really able to transmit the full 100mbit/s of data,
+perhaps because of a badly implemented driver? A PCMCIA network card
+will also never achieve 100mbit/s because of the way the bus is
+designed - again, how do we calculate the idle time?
+
+The physical link bandwidth may be ill defined in case of not-quite-real
+network devices like PPP over Ethernet or PPTP over TCP/IP. The effective
+bandwidth in that case is probably determined by the efficiency of pipes
+to userspace - which not defined.
+
+During operations, the effective idletime is measured using an
+exponential weighted moving average (EWMA), which considers recent
+packets to be exponentially more important than past ones. The Unix
+loadaverage is calculated in the same way.
+
+The calculated idle time is subtracted from the EWMA measured one,
+the resulting number is called 'avgidle'. A perfectly loaded link has
+an avgidle of zero: packets arrive exactly at the calculated
+interval.
+
+An overloaded link has a negative avgidle and if it gets too negative,
+CBQ throttles and is then 'overlimit'.
+
+Conversely, an idle link might amass a huge avgidle, which would then
+allow infinite bandwidths after a few hours of silence. To prevent
+this, avgidle is capped at
+.B maxidle.
+
+If overlimit, in theory, the CBQ could throttle itself for exactly the
+amount of time that was calculated to pass between packets, and then
+pass one packet, and throttle again. Due to timer resolution constraints,
+this may not be feasible, see the
+.B minburst
+parameter below.
+
+.SH CLASSIFICATION
+Within the one CBQ instance many classes may exist. Each of these classes
+contains another qdisc, by default
+.BR tc-pfifo (8).
+
+When enqueueing a packet, CBQ starts at the root and uses various methods to
+determine which class should receive the data. If a verdict is reached, this
+process is repeated for the recipient class which might have further
+means of classifying traffic to its children, if any.
+
+CBQ has the following methods available to classify a packet to any child
+classes.
+.TP
+(i)
+.B skb->priority class encoding.
+Can be set from userspace by an application with the
+.B SO_PRIORITY
+setsockopt.
+The
+.B skb->priority class encoding
+only applies if the skb->priority holds a major:minor handle of an existing
+class within this qdisc.
+.TP
+(ii)
+tc filters attached to the class.
+.TP
+(iii)
+The defmap of a class, as set with the
+.B split & defmap
+parameters. The defmap may contain instructions for each possible Linux packet
+priority.
+
+.P
+Each class also has a
+.B level.
+Leaf nodes, attached to the bottom of the class hierarchy, have a level of 0.
+.SH CLASSIFICATION ALGORITHM
+
+Classification is a loop, which terminates when a leaf class is found. At any
+point the loop may jump to the fallback algorithm.
+
+The loop consists of the following steps:
+.TP
+(i)
+If the packet is generated locally and has a valid classid encoded within its
+.B skb->priority,
+choose it and terminate.
+
+.TP
+(ii)
+Consult the tc filters, if any, attached to this child. If these return
+a class which is not a leaf class, restart loop from the class returned.
+If it is a leaf, choose it and terminate.
+.TP
+(iii)
+If the tc filters did not return a class, but did return a classid,
+try to find a class with that id within this qdisc.
+Check if the found class is of a lower
+.B level
+than the current class. If so, and the returned class is not a leaf node,
+restart the loop at the found class. If it is a leaf node, terminate.
+If we found an upward reference to a higher level, enter the fallback
+algorithm.
+.TP
+(iv)
+If the tc filters did not return a class, nor a valid reference to one,
+consider the minor number of the reference to be the priority. Retrieve
+a class from the defmap of this class for the priority. If this did not
+contain a class, consult the defmap of this class for the
+.B BEST_EFFORT
+class. If this is an upward reference, or no
+.B BEST_EFFORT
+class was defined,
+enter the fallback algorithm. If a valid class was found, and it is not a
+leaf node, restart the loop at this class. If it is a leaf, choose it and
+terminate. If
+neither the priority distilled from the classid, nor the
+.B BEST_EFFORT
+priority yielded a class, enter the fallback algorithm.
+.P
+The fallback algorithm resides outside of the loop and is as follows.
+.TP
+(i)
+Consult the defmap of the class at which the jump to fallback occurred. If
+the defmap contains a class for the
+.B
+priority
+of the class (which is related to the TOS field), choose this class and
+terminate.
+.TP
+(ii)
+Consult the map for a class for the
+.B BEST_EFFORT
+priority. If found, choose it, and terminate.
+.TP
+(iii)
+Choose the class at which break out to the fallback algorithm occurred. Terminate.
+.P
+The packet is enqueued to the class which was chosen when either algorithm
+terminated. It is therefore possible for a packet to be enqueued *not* at a
+leaf node, but in the middle of the hierarchy.
+
+.SH LINK SHARING ALGORITHM
+When dequeuing for sending to the network device, CBQ decides which of its
+classes will be allowed to send. It does so with a Weighted Round Robin process
+in which each class with packets gets a chance to send in turn. The WRR process
+starts by asking the highest priority classes (lowest numerically -
+highest semantically) for packets, and will continue to do so until they
+have no more data to offer, in which case the process repeats for lower
+priorities.
+
+.B CERTAINTY ENDS HERE, ANK PLEASE HELP
+
+Each class is not allowed to send at length though - they can only dequeue a
+configurable amount of data during each round.
+
+If a class is about to go overlimit, and it is not
+.B bounded
+it will try to borrow avgidle from siblings that are not
+.B isolated.
+This process is repeated from the bottom upwards. If a class is unable
+to borrow enough avgidle to send a packet, it is throttled and not asked
+for a packet for enough time for the avgidle to increase above zero.
+
+.B I REALLY NEED HELP FIGURING THIS OUT. REST OF DOCUMENT IS PRETTY CERTAIN
+.B AGAIN.
+
+.SH QDISC
+The root qdisc of a CBQ class tree has the following parameters:
+
+.TP
+parent major:minor | root
+This mandatory parameter determines the place of the CBQ instance, either at the
+.B root
+of an interface or within an existing class.
+.TP
+handle major:
+Like all other qdiscs, the CBQ can be assigned a handle. Should consist only
+of a major number, followed by a colon. Optional.
+.TP
+avpkt bytes
+For calculations, the average packet size must be known. It is silently capped
+at a minimum of 2/3 of the interface MTU. Mandatory.
+.TP
+bandwidth rate
+To determine the idle time, CBQ must know the bandwidth of your underlying
+physical interface, or parent qdisc. This is a vital parameter, more about it
+later. Mandatory.
+.TP
+cell
+The cell size determines he granularity of packet transmission time calculations. Has a sensible default.
+.TP
+mpu
+A zero sized packet may still take time to transmit. This value is the lower
+cap for packet transmission time calculations - packets smaller than this value
+are still deemed to have this size. Defaults to zero.
+.TP
+ewma log
+When CBQ needs to measure the average idle time, it does so using an
+Exponentially Weighted Moving Average which smooths out measurements into
+a moving average. The EWMA LOG determines how much smoothing occurs. Defaults
+to 5. Lower values imply greater sensitivity. Must be between 0 and 31.
+.P
+A CBQ qdisc does not shape out of its own accord. It only needs to know certain
+parameters about the underlying link. Actual shaping is done in classes.
+
+.SH CLASSES
+Classes have a host of parameters to configure their operation.
+
+.TP
+parent major:minor
+Place of this class within the hierarchy. If attached directly to a qdisc
+and not to another class, minor can be omitted. Mandatory.
+.TP
+classid major:minor
+Like qdiscs, classes can be named. The major number must be equal to the
+major number of the qdisc to which it belongs. Optional, but needed if this
+class is going to have children.
+.TP
+weight weight
+When dequeuing to the interface, classes are tried for traffic in a
+round-robin fashion. Classes with a higher configured qdisc will generally
+have more traffic to offer during each round, so it makes sense to allow
+it to dequeue more traffic. All weights under a class are normalized, so
+only the ratios matter. Defaults to the configured rate, unless the priority
+of this class is maximal, in which case it is set to 1.
+.TP
+allot bytes
+Allot specifies how many bytes a qdisc can dequeue
+during each round of the process. This parameter is weighted using the
+renormalized class weight described above.
+
+.TP
+priority priority
+In the round-robin process, classes with the lowest priority field are tried
+for packets first. Mandatory.
+
+.TP
+rate rate
+Maximum rate this class and all its children combined can send at. Mandatory.
+
+.TP
+bandwidth rate
+This is different from the bandwidth specified when creating a CBQ disc. Only
+used to determine maxidle and offtime, which are only calculated when
+specifying maxburst or minburst. Mandatory if specifying maxburst or minburst.
+
+.TP
+maxburst
+This number of packets is used to calculate maxidle so that when
+avgidle is at maxidle, this number of average packets can be burst
+before avgidle drops to 0. Set it higher to be more tolerant of
+bursts. You can't set maxidle directly, only via this parameter.
+
+.TP
+minburst
+As mentioned before, CBQ needs to throttle in case of
+overlimit. The ideal solution is to do so for exactly the calculated
+idle time, and pass 1 packet. However, Unix kernels generally have a
+hard time scheduling events shorter than 10ms, so it is better to
+throttle for a longer period, and then pass minburst packets in one
+go, and then sleep minburst times longer.
+
+The time to wait is called the offtime. Higher values of minburst lead
+to more accurate shaping in the long term, but to bigger bursts at
+millisecond timescales.
+
+.TP
+minidle
+If avgidle is below 0, we are overlimits and need to wait until
+avgidle will be big enough to send one packet. To prevent a sudden
+burst from shutting down the link for a prolonged period of time,
+avgidle is reset to minidle if it gets too low.
+
+Minidle is specified in negative microseconds, so 10 means that
+avgidle is capped at -10us.
+
+.TP
+bounded
+Signifies that this class will not borrow bandwidth from its siblings.
+.TP
+isolated
+Means that this class will not borrow bandwidth to its siblings
+
+.TP
+split major:minor & defmap bitmap[/bitmap]
+If consulting filters attached to a class did not give a verdict,
+CBQ can also classify based on the packet's priority. There are 16
+priorities available, numbered from 0 to 15.
+
+The defmap specifies which priorities this class wants to receive,
+specified as a bitmap. The Least Significant Bit corresponds to priority
+zero. The
+.B split
+parameter tells CBQ at which class the decision must be made, which should
+be a (grand)parent of the class you are adding.
+
+As an example, 'tc class add ... classid 10:1 cbq .. split 10:0 defmap c0'
+configures class 10:0 to send packets with priorities 6 and 7 to 10:1.
+
+The complimentary configuration would then
+be: 'tc class add ... classid 10:2 cbq ... split 10:0 defmap 3f'
+Which would send all packets 0, 1, 2, 3, 4 and 5 to 10:1.
+.TP
+estimator interval timeconstant
+CBQ can measure how much bandwidth each class is using, which tc filters
+can use to classify packets with. In order to determine the bandwidth
+it uses a very simple estimator that measures once every
+.B interval
+microseconds how much traffic has passed. This again is a EWMA, for which
+the time constant can be specified, also in microseconds. The
+.B time constant
+corresponds to the sluggishness of the measurement or, conversely, to the
+sensitivity of the average to short bursts. Higher values mean less
+sensitivity.
+
+
+
+.SH SOURCES
+.TP
+o
+Sally Floyd and Van Jacobson, "Link-sharing and Resource
+Management Models for Packet Networks",
+IEEE/ACM Transactions on Networking, Vol.3, No.4, 1995
+
+.TP
+o
+Sally Floyd, "Notes on CBQ and Guarantee Service", 1995
+
+.TP
+o
+Sally Floyd, "Notes on Class-Based Queueing: Setting
+Parameters", 1996
+
+.TP
+o
+Sally Floyd and Michael Speer, "Experimental Results
+for Class-Based Queueing", 1998, not published.
+
+
+
+.SH SEE ALSO
+.BR tc (8)
+
+.SH AUTHOR
+Alexey N. Kuznetsov, <kuznet@ms2.inr.ac.ru>. This manpage maintained by
+bert hubert <ahu@ds9a.nl>
diff --git a/iproute2/man/man8/tc-cbq.8 b/iproute2/man/man8/tc-cbq.8
new file mode 100644
index 0000000..301265d
--- /dev/null
+++ b/iproute2/man/man8/tc-cbq.8
@@ -0,0 +1,351 @@
+.TH CBQ 8 "16 December 2001" "iproute2" "Linux"
+.SH NAME
+CBQ \- Class Based Queueing
+.SH SYNOPSIS
+.B tc qdisc ... dev
+dev
+.B ( parent
+classid
+.B | root) [ handle
+major:
+.B ] cbq [ allot
+bytes
+.B ] avpkt
+bytes
+.B bandwidth
+rate
+.B [ cell
+bytes
+.B ] [ ewma
+log
+.B ] [ mpu
+bytes
+.B ]
+
+.B tc class ... dev
+dev
+.B parent
+major:[minor]
+.B [ classid
+major:minor
+.B ] cbq allot
+bytes
+.B [ bandwidth
+rate
+.B ] [ rate
+rate
+.B ] prio
+priority
+.B [ weight
+weight
+.B ] [ minburst
+packets
+.B ] [ maxburst
+packets
+.B ] [ ewma
+log
+.B ] [ cell
+bytes
+.B ] avpkt
+bytes
+.B [ mpu
+bytes
+.B ] [ bounded isolated ] [ split
+handle
+.B & defmap
+defmap
+.B ] [ estimator
+interval timeconstant
+.B ]
+
+.SH DESCRIPTION
+Class Based Queueing is a classful qdisc that implements a rich
+linksharing hierarchy of classes. It contains shaping elements as
+well as prioritizing capabilities. Shaping is performed using link
+idle time calculations based on the timing of dequeue events and
+underlying link bandwidth.
+
+.SH SHAPING ALGORITHM
+When shaping a 10mbit/s connection to 1mbit/s, the link will
+be idle 90% of the time. If it isn't, it needs to be throttled so that it
+IS idle 90% of the time.
+
+During operations, the effective idletime is measured using an
+exponential weighted moving average (EWMA), which considers recent
+packets to be exponentially more important than past ones. The Unix
+loadaverage is calculated in the same way.
+
+The calculated idle time is subtracted from the EWMA measured one,
+the resulting number is called 'avgidle'. A perfectly loaded link has
+an avgidle of zero: packets arrive exactly at the calculated
+interval.
+
+An overloaded link has a negative avgidle and if it gets too negative,
+CBQ throttles and is then 'overlimit'.
+
+Conversely, an idle link might amass a huge avgidle, which would then
+allow infinite bandwidths after a few hours of silence. To prevent
+this, avgidle is capped at
+.B maxidle.
+
+If overlimit, in theory, the CBQ could throttle itself for exactly the
+amount of time that was calculated to pass between packets, and then
+pass one packet, and throttle again. Due to timer resolution constraints,
+this may not be feasible, see the
+.B minburst
+parameter below.
+
+.SH CLASSIFICATION
+Within the one CBQ instance many classes may exist. Each of these classes
+contains another qdisc, by default
+.BR tc-pfifo (8).
+
+When enqueueing a packet, CBQ starts at the root and uses various methods to
+determine which class should receive the data.
+
+In the absence of uncommon configuration options, the process is rather easy.
+At each node we look for an instruction, and then go to the class the
+instruction refers us to. If the class found is a barren leaf-node (without
+children), we enqueue the packet there. If it is not yet a leaf node, we do
+the whole thing over again starting from that node.
+
+The following actions are performed, in order at each node we visit, until one
+sends us to another node, or terminates the process.
+.TP
+(i)
+Consult filters attached to the class. If sent to a leafnode, we are done.
+Otherwise, restart.
+.TP
+(ii)
+Consult the defmap for the priority assigned to this packet, which depends
+on the TOS bits. Check if the referral is leafless, otherwise restart.
+.TP
+(iii)
+Ask the defmap for instructions for the 'best effort' priority. Check the
+answer for leafness, otherwise restart.
+.TP
+(iv)
+If none of the above returned with an instruction, enqueue at this node.
+.P
+This algorithm makes sure that a packet always ends up somewhere, even while
+you are busy building your configuration.
+
+For more details, see
+.BR tc-cbq-details(8).
+
+.SH LINK SHARING ALGORITHM
+When dequeuing for sending to the network device, CBQ decides which of its
+classes will be allowed to send. It does so with a Weighted Round Robin process
+in which each class with packets gets a chance to send in turn. The WRR process
+starts by asking the highest priority classes (lowest numerically -
+highest semantically) for packets, and will continue to do so until they
+have no more data to offer, in which case the process repeats for lower
+priorities.
+
+Classes by default borrow bandwidth from their siblings. A class can be
+prevented from doing so by declaring it 'bounded'. A class can also indicate
+its unwillingness to lend out bandwidth by being 'isolated'.
+
+.SH QDISC
+The root of a CBQ qdisc class tree has the following parameters:
+
+.TP
+parent major:minor | root
+This mandatory parameter determines the place of the CBQ instance, either at the
+.B root
+of an interface or within an existing class.
+.TP
+handle major:
+Like all other qdiscs, the CBQ can be assigned a handle. Should consist only
+of a major number, followed by a colon. Optional, but very useful if classes
+will be generated within this qdisc.
+.TP
+allot bytes
+This allotment is the 'chunkiness' of link sharing and is used for determining packet
+transmission time tables. The qdisc allot differs slightly from the class allot discussed
+below. Optional. Defaults to a reasonable value, related to avpkt.
+.TP
+avpkt bytes
+The average size of a packet is needed for calculating maxidle, and is also used
+for making sure 'allot' has a safe value. Mandatory.
+.TP
+bandwidth rate
+To determine the idle time, CBQ must know the bandwidth of your underlying
+physical interface, or parent qdisc. This is a vital parameter, more about it
+later. Mandatory.
+.TP
+cell
+The cell size determines he granularity of packet transmission time calculations. Has a sensible default.
+.TP
+mpu
+A zero sized packet may still take time to transmit. This value is the lower
+cap for packet transmission time calculations - packets smaller than this value
+are still deemed to have this size. Defaults to zero.
+.TP
+ewma log
+When CBQ needs to measure the average idle time, it does so using an
+Exponentially Weighted Moving Average which smooths out measurements into
+a moving average. The EWMA LOG determines how much smoothing occurs. Lower
+values imply greater sensitivity. Must be between 0 and 31. Defaults
+to 5.
+.P
+A CBQ qdisc does not shape out of its own accord. It only needs to know certain
+parameters about the underlying link. Actual shaping is done in classes.
+
+.SH CLASSES
+Classes have a host of parameters to configure their operation.
+
+.TP
+parent major:minor
+Place of this class within the hierarchy. If attached directly to a qdisc
+and not to another class, minor can be omitted. Mandatory.
+.TP
+classid major:minor
+Like qdiscs, classes can be named. The major number must be equal to the
+major number of the qdisc to which it belongs. Optional, but needed if this
+class is going to have children.
+.TP
+weight weight
+When dequeuing to the interface, classes are tried for traffic in a
+round-robin fashion. Classes with a higher configured qdisc will generally
+have more traffic to offer during each round, so it makes sense to allow
+it to dequeue more traffic. All weights under a class are normalized, so
+only the ratios matter. Defaults to the configured rate, unless the priority
+of this class is maximal, in which case it is set to 1.
+.TP
+allot bytes
+Allot specifies how many bytes a qdisc can dequeue
+during each round of the process. This parameter is weighted using the
+renormalized class weight described above. Silently capped at a minimum of
+3/2 avpkt. Mandatory.
+
+.TP
+prio priority
+In the round-robin process, classes with the lowest priority field are tried
+for packets first. Mandatory.
+
+.TP
+avpkt
+See the QDISC section.
+
+.TP
+rate rate
+Maximum rate this class and all its children combined can send at. Mandatory.
+
+.TP
+bandwidth rate
+This is different from the bandwidth specified when creating a CBQ disc! Only
+used to determine maxidle and offtime, which are only calculated when
+specifying maxburst or minburst. Mandatory if specifying maxburst or minburst.
+
+.TP
+maxburst
+This number of packets is used to calculate maxidle so that when
+avgidle is at maxidle, this number of average packets can be burst
+before avgidle drops to 0. Set it higher to be more tolerant of
+bursts. You can't set maxidle directly, only via this parameter.
+
+.TP
+minburst
+As mentioned before, CBQ needs to throttle in case of
+overlimit. The ideal solution is to do so for exactly the calculated
+idle time, and pass 1 packet. However, Unix kernels generally have a
+hard time scheduling events shorter than 10ms, so it is better to
+throttle for a longer period, and then pass minburst packets in one
+go, and then sleep minburst times longer.
+
+The time to wait is called the offtime. Higher values of minburst lead
+to more accurate shaping in the long term, but to bigger bursts at
+millisecond timescales. Optional.
+
+.TP
+minidle
+If avgidle is below 0, we are overlimits and need to wait until
+avgidle will be big enough to send one packet. To prevent a sudden
+burst from shutting down the link for a prolonged period of time,
+avgidle is reset to minidle if it gets too low.
+
+Minidle is specified in negative microseconds, so 10 means that
+avgidle is capped at -10us. Optional.
+
+.TP
+bounded
+Signifies that this class will not borrow bandwidth from its siblings.
+.TP
+isolated
+Means that this class will not borrow bandwidth to its siblings
+
+.TP
+split major:minor & defmap bitmap[/bitmap]
+If consulting filters attached to a class did not give a verdict,
+CBQ can also classify based on the packet's priority. There are 16
+priorities available, numbered from 0 to 15.
+
+The defmap specifies which priorities this class wants to receive,
+specified as a bitmap. The Least Significant Bit corresponds to priority
+zero. The
+.B split
+parameter tells CBQ at which class the decision must be made, which should
+be a (grand)parent of the class you are adding.
+
+As an example, 'tc class add ... classid 10:1 cbq .. split 10:0 defmap c0'
+configures class 10:0 to send packets with priorities 6 and 7 to 10:1.
+
+The complimentary configuration would then
+be: 'tc class add ... classid 10:2 cbq ... split 10:0 defmap 3f'
+Which would send all packets 0, 1, 2, 3, 4 and 5 to 10:1.
+.TP
+estimator interval timeconstant
+CBQ can measure how much bandwidth each class is using, which tc filters
+can use to classify packets with. In order to determine the bandwidth
+it uses a very simple estimator that measures once every
+.B interval
+microseconds how much traffic has passed. This again is a EWMA, for which
+the time constant can be specified, also in microseconds. The
+.B time constant
+corresponds to the sluggishness of the measurement or, conversely, to the
+sensitivity of the average to short bursts. Higher values mean less
+sensitivity.
+
+.SH BUGS
+The actual bandwidth of the underlying link may not be known, for example
+in the case of PPoE or PPTP connections which in fact may send over a
+pipe, instead of over a physical device. CBQ is quite resilient to major
+errors in the configured bandwidth, probably a the cost of coarser shaping.
+
+Default kernels rely on coarse timing information for making decisions. These
+may make shaping precise in the long term, but inaccurate on second long scales.
+
+See
+.BR tc-cbq-details(8)
+for hints on how to improve this.
+
+.SH SOURCES
+.TP
+o
+Sally Floyd and Van Jacobson, "Link-sharing and Resource
+Management Models for Packet Networks",
+IEEE/ACM Transactions on Networking, Vol.3, No.4, 1995
+
+.TP
+o
+Sally Floyd, "Notes on CBQ and Guaranteed Service", 1995
+
+.TP
+o
+Sally Floyd, "Notes on Class-Based Queueing: Setting
+Parameters", 1996
+
+.TP
+o
+Sally Floyd and Michael Speer, "Experimental Results
+for Class-Based Queueing", 1998, not published.
+
+
+
+.SH SEE ALSO
+.BR tc (8)
+
+.SH AUTHOR
+Alexey N. Kuznetsov, <kuznet@ms2.inr.ac.ru>. This manpage maintained by
+bert hubert <ahu@ds9a.nl>
diff --git a/iproute2/man/man8/tc-cgroup.8 b/iproute2/man/man8/tc-cgroup.8
new file mode 100644
index 0000000..2bea7d4
--- /dev/null
+++ b/iproute2/man/man8/tc-cgroup.8
@@ -0,0 +1,80 @@
+.TH "Cgroup classifier in tc" 8 " 21 Oct 2015" "iproute2" "Linux"
+
+.SH NAME
+cgroup \- control group based traffic control filter
+.SH SYNOPSIS
+.in +8
+.ti -8
+.BR tc " " filter " ... " cgroup " [ " match
+.IR EMATCH_TREE " ] [ "
+.B action
+.IR ACTION_SPEC " ]"
+.SH DESCRIPTION
+This filter serves as a hint to
+.B tc
+that the assigned class ID of the net_cls control group the process the packet
+originates from belongs to should be used for classification. Obviously, it is
+useful for locally generated packets only.
+.SH OPTIONS
+.TP
+.BI action " ACTION_SPEC"
+Apply an action from the generic actions framework on matching packets.
+.TP
+.BI match " EMATCH_TREE"
+Match packets using the extended match infrastructure. See
+.BR tc-ematch (8)
+for a detailed description of the allowed syntax in
+.IR EMATCH_TREE .
+.SH EXAMPLES
+In order to use this filter, a net_cls control group has to be created first and
+class as well as process ID(s) assigned to it. The following creates a net_cls
+cgroup named "foobar":
+
+.RS
+.EX
+modprobe cls_cgroup
+mkdir /sys/fs/cgroup/net_cls
+mount -t cgroup -onet_cls net_cls /sys/fs/cgroup/net_cls
+mkdir /sys/fs/cgroup/net_cls/foobar
+.EE
+.RE
+
+To assign a class ID to the created cgroup, a file named
+.I net_cls.classid
+has to be created which contains the class ID to be assigned as a hexadecimal,
+64bit wide number. The upper 32bits are reserved for the major handle, the
+remaining hold the minor. So a class ID of e.g.
+.B ff:be
+has to be written like so:
+.B 0xff00be
+(leading zeroes may be omitted). To continue the above example, the following
+assigns class ID 1:2 to foobar cgroup:
+
+.RS
+.EX
+echo 0x10002 > /sys/fs/cgroup/net_cls/foobar/net_cls.classid
+.EE
+.RE
+
+Finally some PIDs can be assigned to the given cgroup:
+
+.RS
+.EX
+echo 1234 > /sys/fs/cgroup/net_cls/foobar/tasks
+echo 5678 > /sys/fs/cgroup/net_cls/foobar/tasks
+.EE
+.RE
+
+Now by simply attaching a
+.B cgroup
+filter to a
+.B qdisc
+makes packets from PIDs 1234 and 5678 be pushed into class 1:2.
+
+.SH SEE ALSO
+.BR tc (8),
+.BR tc-ematch (8),
+.br
+the file
+.I Documentation/cgroups/net_cls.txt
+of the Linux kernel tree
diff --git a/iproute2/man/man8/tc-choke.8 b/iproute2/man/man8/tc-choke.8
new file mode 100644
index 0000000..1916a3d
--- /dev/null
+++ b/iproute2/man/man8/tc-choke.8
@@ -0,0 +1,63 @@
+.TH TC 8 "August 2011" "iproute2" "Linux"
+.SH NAME
+choke \- choose and keep scheduler
+.SH SYNOPSIS
+.B tc qdisc ... choke
+.B limit
+packets
+.B min
+packets
+.B max
+packets
+.B avpkt
+bytes
+.B burst
+packets
+.B [ ecn ] [ bandwidth
+rate
+.B ] probability
+chance
+
+.SH DESCRIPTION
+
+CHOKe (CHOose and Keep for responsive flows, CHOose and Kill for unresponsive flows)
+is a classless qdisc designed to both identify and penalize flows that monopolize the
+queue. CHOKe is a variation of RED, and the configuration is similar to RED.
+
+.SH ALGORITHM
+Once the queue hits a certain average length, a random packet is drawn from the
+queue. If both the to-be-queued and the drawn packet belong to the same flow,
+both packets are dropped. Otherwise, if the queue length is still below the maximum length,
+the new packet has a configurable chance of being marked (which may mean dropped).
+If the queue length exceeds
+.BR max ,
+the new packet will always be marked (or dropped).
+If the queue length exceeds
+.BR limit ,
+the new packet is always dropped.
+
+The marking probability computation is the same as used by the RED qdisc.
+
+.SH PARAMETERS
+The parameters are the same as for RED, except that RED uses bytes whereas choke
+counts packets. See
+.BR tc-red (8)
+for a description.
+
+.SH SOURCE
+.TP
+o
+R. Pan, B. Prabhakar, and K. Psounis, "CHOKe, A Stateless
+Active Queue Management Scheme for Approximating Fair Bandwidth Allocation",
+IEEE INFOCOM, 2000.
+.TP
+o
+A. Tang, J. Wang, S. Low, "Understanding CHOKe: Throughput and Spatial
+Characteristics", IEEE/ACM Transactions on Networking, 2004
+
+.SH SEE ALSO
+.BR tc (8),
+.BR tc-red (8)
+
+.SH AUTHOR
+sched_choke was contributed by Stephen Hemminger.
diff --git a/iproute2/man/man8/tc-codel.8 b/iproute2/man/man8/tc-codel.8
new file mode 100644
index 0000000..a0e50a4
--- /dev/null
+++ b/iproute2/man/man8/tc-codel.8
@@ -0,0 +1,114 @@
+.TH CoDel 8 "23 May 2012" "iproute2" "Linux"
+.SH NAME
+CoDel \- Controlled-Delay Active Queue Management algorithm
+.SH SYNOPSIS
+.B tc qdisc ... codel
+[
+.B limit
+PACKETS ] [
+.B target
+TIME ] [
+.B interval
+TIME ] [
+.B ecn
+|
+.B noecn
+]
+
+.SH DESCRIPTION
+CoDel (pronounced "coddle") is an adaptive "no-knobs" active queue management
+algorithm (AQM) scheme that was developed to address the shortcomings of
+RED and its variants. It was developed with the following goals
+in mind:
+ o It should be parameterless.
+ o It should keep delays low while permitting bursts of traffic.
+ o It should control delay.
+ o It should adapt dynamically to changing link rates with no impact on
+utilization.
+ o It should be simple and efficient and should scale from simple to
+complex routers.
+
+.SH ALGORITHM
+CoDel comes with three major innovations. Instead of using queue size or queue
+average, it uses the local minimum queue as a measure of the standing/persistent queue.
+Second, it uses a single state-tracking variable of the minimum delay to see where it
+is relative to the standing queue delay. Third, instead of measuring queue size
+in bytes or packets, it is measured in packet-sojourn time in the queue.
+
+CoDel measures the minimum local queue delay (i.e. standing queue delay) and
+compares it to the value of the given acceptable queue delay
+.B target.
+As long as the minimum queue delay is less than
+.B target
+or the buffer contains fewer than MTU worth of bytes, packets are not dropped.
+Codel enters a dropping mode when the minimum queue delay has exceeded
+.B target
+for a time greater than
+.B interval.
+In this mode, packets are dropped at different drop times which is set by a
+control law. The control law ensures that the packet drops cause a linear change
+in the throughput. Once the minimum delay goes below
+.B target,
+packets are no longer dropped.
+
+Additional details can be found in the paper cited below.
+
+.SH PARAMETERS
+.SS limit
+hard limit on the real queue size. When this limit is reached, incoming packets
+are dropped. If the value is lowered, packets are dropped so that the new limit is
+met. Default is 1000 packets.
+
+.SS target
+is the acceptable minimum standing/persistent queue delay. This minimum delay
+is identified by tracking the local minimum queue delay that packets experience.
+Default and recommended value is 5ms.
+
+.SS interval
+is used to ensure that the measured minimum delay does not become too stale. The
+minimum delay must be experienced in the last epoch of length
+.B interval.
+It should be set on the order of the worst-case RTT through the bottleneck to
+give endpoints sufficient time to react. Default value is 100ms.
+
+.SS ecn | noecn
+can be used to mark packets instead of dropping them. If
+.B ecn
+has been enabled,
+.B noecn
+can be used to turn it off and vice-a-versa. By default,
+.B ecn
+is turned off.
+
+.SH EXAMPLES
+ # tc qdisc add dev eth0 root codel
+ # tc -s qdisc show
+ qdisc codel 801b: dev eth0 root refcnt 2 limit 1000p target 5.0ms
+interval 100.0ms
+ Sent 245801662 bytes 275853 pkt (dropped 0, overlimits 0 requeues 24)
+ backlog 0b 0p requeues 24
+ count 0 lastcount 0 ldelay 2us drop_next 0us
+ maxpacket 7306 ecn_mark 0 drop_overlimit 0
+
+ # tc qdisc add dev eth0 root codel limit 100 target 4ms interval 30ms ecn
+ # tc -s qdisc show
+ qdisc codel 801c: dev eth0 root refcnt 2 limit 100p target 4.0ms
+interval 30.0ms ecn
+ Sent 237573074 bytes 268561 pkt (dropped 0, overlimits 0 requeues 5)
+ backlog 0b 0p requeues 5
+ count 0 lastcount 0 ldelay 76us drop_next 0us
+ maxpacket 2962 ecn_mark 0 drop_overlimit 0
+
+
+.SH SEE ALSO
+.BR tc (8),
+.BR tc-red (8)
+
+.SH SOURCES
+o Kathleen Nichols and Van Jacobson, "Controlling Queue Delay", ACM Queue,
+http://queue.acm.org/detail.cfm?id=2209336
+
+.SH AUTHORS
+CoDel was implemented by Eric Dumazet and David Taht. This manpage was written
+by Vijay Subramanian. Please reports corrections to the Linux Networking
+mailing list <netdev@vger.kernel.org>.
diff --git a/iproute2/man/man8/tc-drr.8 b/iproute2/man/man8/tc-drr.8
new file mode 100644
index 0000000..2fea4ee
--- /dev/null
+++ b/iproute2/man/man8/tc-drr.8
@@ -0,0 +1,94 @@
+.TH TC 8 "January 2010" "iproute2" "Linux"
+.SH NAME
+drr \- deficit round robin scheduler
+.SH SYNOPSIS
+.B tc qdisc ... add drr
+.B [ quantum
+bytes
+.B ]
+
+.SH DESCRIPTION
+
+The Deficit Round Robin Scheduler is a classful queuing discipline as
+a more flexible replacement for Stochastic Fairness Queuing.
+
+Unlike SFQ, there are no built-in queues \-\- you need to add classes
+and then set up filters to classify packets accordingly.
+This can be useful e.g. for using RED qdiscs with different settings for particular
+traffic. There is no default class \-\- if a packet cannot be classified,
+it is dropped.
+
+.SH ALGORITHM
+Each class is assigned a deficit counter, initialized to
+.B quantum.
+
+DRR maintains an (internal) ''active'' list of classes whose qdiscs are
+non-empty. This list is used for dequeuing. A packet is dequeued from
+the class at the head of the list if the packet size is smaller or equal
+to the deficit counter. If the counter is too small, it is increased by
+.B quantum
+and the scheduler moves on to the next class in the active list.
+
+
+.SH PARAMETERS
+.TP
+quantum
+Amount of bytes a flow is allowed to dequeue before the scheduler moves to
+the next class. Defaults to the MTU of the interface. The minimum value is 1.
+
+.SH EXAMPLE & USAGE
+
+To attach to device eth0, using the interface MTU as its quantum:
+.P
+# tc qdisc add dev eth0 handle 1 root drr
+.P
+Adding two classes:
+.P
+# tc class add dev eth0 parent 1: classid 1:1 drr
+.br
+# tc class add dev eth0 parent 1: classid 1:2 drr
+.P
+You also need to add at least one filter to classify packets.
+.P
+# tc filter add dev eth0 protocol .. classid 1:1
+.P
+
+Like SFQ, DRR is only useful when it owns the queue \-\- it is a pure scheduler and does
+not delay packets. Attaching non-work-conserving qdiscs like tbf to it does not make
+sense \-\- other qdiscs in the active list will also become inactive until the dequeue
+operation succeeds. Embed DRR within another qdisc like HTB or HFSC to ensure it owns the queue.
+.P
+You can mimic SFQ behavior by assigning packets to the attached classes using the
+flow filter:
+
+.B tc qdisc add dev .. drr
+
+.B for i in .. 1024;do
+.br
+.B "\ttc class add dev .. classid $handle:$(print %x $i)"
+.br
+.B "\ttc qdisc add dev .. fifo limit 16"
+.br
+.B done
+
+.B tc filter add .. protocol ip .. $handle flow hash keys src,dst,proto,proto-src,proto-dst divisor 1024 perturb 10
+
+
+.SH SOURCE
+.TP
+o
+M. Shreedhar and George Varghese "Efficient Fair
+Queuing using Deficit Round Robin", Proc. SIGCOMM 95.
+
+.SH NOTES
+
+This implementation does not drop packets from the longest queue on overrun,
+as limits are handled by the individual child qdiscs.
+
+.SH SEE ALSO
+.BR tc (8),
+.BR tc-htb (8),
+.BR tc-sfq (8)
+
+.SH AUTHOR
+sched_drr was written by Patrick McHardy.
diff --git a/iproute2/man/man8/tc-ematch.8 b/iproute2/man/man8/tc-ematch.8
new file mode 100644
index 0000000..b9bf70c
--- /dev/null
+++ b/iproute2/man/man8/tc-ematch.8
@@ -0,0 +1,132 @@
+.TH ematch 8 "6 August 2012" iproute2 Linux
+.
+.SH NAME
+ematch \- extended matches for use with "basic" or "flow" filters
+.
+.SH SYNOPSIS
+.sp
+.ad l
+.B "tc filter add .. basic match"
+.RI EXPR
+.B .. flowid ..
+.sp
+
+.IR EXPR " := " TERM " [ { "
+.B and | or
+}
+.IR EXPR
+]
+
+.IR TERM " := [ " \fBnot " ] { " MATCH " | '(' " EXPR " ')' } "
+
+.IR MATCH " := " module " '(' " ARGS " ')' "
+
+.IR ARGS " := " ARG1 " " ARG2 " ..
+
+.SH MATCHES
+
+.SS cmp
+Simple comparison ematch: arithmetic compare of packet data to a given value.
+
+.IR cmp "( " ALIGN " at " OFFSET " [ " ATTRS " ] { " eq " | " lt " | " gt " } " VALUE " )
+
+.IR ALIGN " := { " u8 " | " u16 " | " u32 " } "
+
+.IR ATTRS " := [ layer " LAYER " ] [ mask " MASK " ] [ trans ]
+
+.IR LAYER " := { " link " | " network " | " transport " | " 0..2 " }
+
+.SS meta
+Metadata ematch
+
+.IR meta "( " OBJECT " { " eq " | " lt " |" gt " } " OBJECT " )
+
+.IR OBJECT " := { " META_ID " | " VALUE " }
+
+.IR META_ID " := " id " [ shift " SHIFT " ] [ mask " MASK " ]
+
+.TP
+meta attributes:
+
+\fBrandom\fP 32 bit random value
+
+\fBloadavg_1\fP Load average in last 5 minutes
+
+\fBnf_mark\fP Netfilter mark
+
+\fBvlan\fP Vlan tag
+
+\fBsk_rcvbuf\fP Receive buffer size
+
+\fBsk_snd_queue\fP Send queue length
+
+.PP
+A full list of meta attributes can be obtained via
+
+# tc filter add dev eth1 basic match 'meta(list)'
+
+.SS nbyte
+match packet data byte sequence
+
+.IR nbyte "( " NEEDLE " at " OFFSET " [ layer " LAYER " ] )
+
+.IR NEEDLE " := { " string " | " c-escape-sequence " } "
+
+.IR OFFSET " := " int
+
+.IR LAYER " := { " link " | " network " | " transport " | " 0..2 " }
+
+.SS u32
+u32 ematch
+
+.IR u32 "( " ALIGN " " VALUE " " MASK " at [ nexthdr+ ] " OFFSET " )
+
+.IR ALIGN " := { " u8 " | " u16 " | " u32 " }
+
+.SS ipset
+test packet against ipset membership
+
+.IR ipset "( " SETNAME " " FLAGS " )
+
+.IR SETNAME " := " string
+
+.IR FLAGS " := { " FLAG " [, " FLAGS "] }
+
+The flag options are the same as those used by the iptables "set" match.
+
+When using the ipset ematch with the "ip_set_hash:net,iface" set type,
+the interface can be queried using "src,dst (source ip address, outgoing interface) or
+"src,src" (source ip address, incoming interface) syntax.
+
+.SH CAVEATS
+
+The ematch syntax uses '(' and ')' to group expressions. All braces need to be
+escaped properly to prevent shell commandline from interpreting these directly.
+
+When using the ipset ematch with the "ifb" device, the outgoing device will be the
+ifb device itself, e.g. "ifb0".
+The original interface (i.e. the device the packet arrived on) is treated as the incoming interface.
+
+.SH EXAMPLE & USAGE
+
+# tc filter add .. basic match ...
+
+# 'cmp(u16 at 3 layer 2 mask 0xff00 gt 20)'
+
+# 'meta(nfmark gt 24)' and 'meta(tcindex mask 0xf0 eq 0xf0)'
+
+# 'nbyte("ababa" at 12 layer 1)'
+
+# 'u32(u16 0x1122 0xffff at nexthdr+4)'
+
+Check if packet source ip address is member of set named \fBbulk\fP:
+
+# 'ipset(bulk src)'
+
+Check if packet source ip and the interface the packet arrived on is member of "hash:net,iface" set named \fBinteractive\fP:
+
+# 'ipset(interactive src,src)'
+
+.SH "AUTHOR"
+
+The extended match infrastructure was added by Thomas Graf.
diff --git a/iproute2/man/man8/tc-flow.8 b/iproute2/man/man8/tc-flow.8
new file mode 100644
index 0000000..f1b7e2a
--- /dev/null
+++ b/iproute2/man/man8/tc-flow.8
@@ -0,0 +1,265 @@
+.TH "Flow filter in tc" 8 "20 Oct 2015" "iproute2" "Linux"
+
+.SH NAME
+flow \- flow based traffic control filter
+.SH SYNOPSIS
+.TP
+Mapping mode:
+
+.RS
+.in +8
+.ti -8
+.BR tc " " filter " ... " "flow map key "
+.IR KEY " [ " OPS " ] [ " OPTIONS " ] "
+.RE
+.TP
+Hashing mode:
+
+.RS
+.in +8
+.ti -8
+.BR tc " " filter " ... " "flow hash keys "
+.IR KEY_LIST " [ "
+.B perturb
+.IR secs " ] [ " OPTIONS " ] "
+.RE
+
+.in +8
+.ti -8
+.IR OPS " := [ " OPS " ] " OP
+
+.ti -8
+.IR OPTIONS " := [ "
+.B divisor
+.IR NUM " ] [ "
+.B baseclass
+.IR ID " ] [ "
+.B match
+.IR EMATCH_TREE " ] [ "
+.B action
+.IR ACTION_SPEC " ]"
+
+.ti -8
+.IR KEY_LIST " := [ " KEY_LIST " ] " KEY
+
+.ti -8
+.IR OP " := { "
+.BR or " | " and " | " xor " | " rshift " | " addend " } "
+.I NUM
+
+.ti -8
+.IR ID " := " X : Y
+
+.ti -8
+.IR KEY " := { "
+.BR src " | " dst " | " proto " | " proto-src " | " proto-dst " | " iif " | "
+.BR priority " | " mark " | " nfct " | " nfct-src " | " nfct-dst " | "
+.BR nfct-proto-src " | " nfct-proto-dst " | " rt-classid " | " sk-uid " | "
+.BR sk-gid " | " vlan-tag " | " rxhash " }"
+.SH DESCRIPTION
+The
+.B flow
+classifier is meant to extend the
+.B SFQ
+hashing capabilities without hard-coding new hash functions. It also allows
+deterministic mappings of keys to classes.
+.SH OPTIONS
+.TP
+.BI action " ACTION_SPEC"
+Apply an action from the generic actions framework on matching packets.
+.TP
+.BI baseclass " ID"
+An offset for the resulting class ID.
+.I ID
+may be
+.BR root ", " none
+or a hexadecimal class ID in the form [\fIX\fB:\fR]\fIY\fR. If \fIX\fR is
+omitted, it is assumed to be zero.
+.TP
+.BI divisor " NUM"
+Number of buckets to use for sorting into. Keys are calculated modulo
+.IR NUM .
+.TP
+.BI "hash keys " KEY-LIST
+Perform a
+.B jhash2
+operation over the keys in
+.IR KEY-LIST ,
+the result (modulo the
+.B divisor
+if given) is taken as class ID, optionally offset by the value of
+.BR baseclass .
+It is possible to specify an interval (in seconds) after which
+.BR jhash2 's
+entropy source is recreated using the
+.B perturb
+parameter.
+.TP
+.BI "map key " KEY
+Packet data identified by
+.I KEY
+is translated into class IDs to push the packet into. The value may be mangled by
+.I OPS
+before using it for the mapping. They are applied in the order listed here:
+.RS
+.TP 4
+.BI and " NUM"
+Perform bitwise
+.B AND
+operation with numeric value
+.IR NUM .
+.TP
+.BI or " NUM"
+Perform bitwise
+.B OR
+operation with numeric value
+.IR NUM .
+.TP
+.BI xor " NUM"
+Perform bitwise
+.B XOR
+operation with numeric value
+.IR NUM .
+.TP
+.BI rshift " NUM"
+Shift the value of
+.I KEY
+to the right by
+.I NUM
+bits.
+.TP
+.BI addend " NUM"
+Add
+.I NUM
+to the value of
+.IR KEY .
+
+.RE
+.RS
+For the
+.BR or ", " and ", " xor " and " rshift
+operations,
+.I NUM
+is assumed to be an unsigned, 32bit integer value. For the
+.B addend
+operation,
+.I NUM
+may be much more complex: It may be prefixed by a minus ('-') sign to cause
+subtraction instead of addition and for keys of
+.BR src ", " dst ", " nfct-src " and " nfct-dst
+it may be given in IP address notation. See below for an illustrating example.
+.RE
+.TP
+.BI match " EMATCH_TREE"
+Match packets using the extended match infrastructure. See
+.BR tc-ematch (8)
+for a detailed description of the allowed syntax in
+.IR EMATCH_TREE .
+.SH KEYS
+In mapping mode, a single key is used (after optional permutation) to build a
+class ID. The resulting ID is deducible in most cases. In hashing more, a number
+of keys may be specified which are then hashed and the output used as class ID.
+This ID is not deducible in beforehand, and may even change over time for a
+given flow if a
+.B perturb
+interval has been given.
+
+The range of class IDs can be limited by the
+.B divisor
+option, which is used for a modulus.
+.TP
+.BR src ", " dst
+Use source or destination address as key. In case of IPv4 and TIPC, this is the
+actual address value. For IPv6, the 128bit address is folded into a 32bit value
+by XOR'ing the four 32bit words. In all other cases, the kernel-internal socket
+address is used (after folding into 32bits on 64bit systems).
+.TP
+.B proto
+Use the layer four protocol number as key.
+.TP
+.B proto-src
+Use the layer four source port as key. If not available, the kernel-internal
+socket address is used instead.
+.TP
+.B proto-dst
+Use the layer four destination port as key. If not available, the associated
+kernel-internal dst_entry address is used after XOR'ing with the packet's
+layer three protocol number.
+.TP
+.B iif
+Use the incoming interface index as key.
+.TP
+.B priority
+Use the packet's priority as key. Usually this is the IP header's DSCP/ECN
+value.
+.TP
+.B mark
+Use the netfilter
+.B fwmark
+as key.
+.TP
+.B nfct
+Use the associated conntrack entry address as key.
+.TP
+.BR nfct-src ", " nfct-dst ", " nfct-proto-src ", " nfct-proto-dst
+These are conntrack-aware variants of
+.BR src ", " dst ", " proto-src " and " proto-dst .
+In case of NAT, these are basically the packet header's values before NAT was
+applied.
+.TP
+.B rt-classid
+Use the packet's destination routing table entry's realm as key.
+.TP
+.B sk-uid
+.TQ
+.B sk-gid
+For locally generated packets, use the user or group ID the originating socket
+belongs to as key.
+.TP
+.B vlan-tag
+Use the packet's vlan ID as key.
+.TP
+.B rxhash
+Use the flow hash as key.
+
+.SH EXAMPLES
+.TP
+Classic SFQ hash:
+
+.EX
+tc filter add ... flow hash \\
+ keys src,dst,proto,proto-src,proto-dst divisor 1024
+.EE
+.TP
+Classic SFQ hash, but using information from conntrack to work properly in combination with NAT:
+
+.EX
+tc filter add ... flow hash \\
+ keys nfct-src,nfct-dst,proto,nfct-proto-src,nfct-proto-dst \\
+ divisor 1024
+.EE
+.TP
+Map destination IPs of 192.168.0.0/24 to classids 1-257:
+
+.EX
+tc filter add ... flow map \\
+ key dst addend -192.168.0.0 divisor 256
+.EE
+.TP
+Alternative to the above:
+
+.EX
+tc filter add ... flow map \\
+ key dst and 0xff
+.EE
+.TP
+The same, but in reverse order:
+
+.EX
+tc filter add ... flow map \\
+ key dst and 0xff xor 0xff
+.EE
+.SH SEE ALSO
+.BR tc (8),
+.BR tc-ematch (8),
+.BR tc-sfq (8)
diff --git a/iproute2/man/man8/tc-flower.8 b/iproute2/man/man8/tc-flower.8
new file mode 100644
index 0000000..df4d8e1
--- /dev/null
+++ b/iproute2/man/man8/tc-flower.8
@@ -0,0 +1,113 @@
+.TH "Flower filter in tc" 8 "22 Oct 2015" "iproute2" "Linux"
+
+.SH NAME
+flower \- flow based traffic control filter
+.SH SYNOPSIS
+.in +8
+.ti -8
+.BR tc " " filter " ... " flower " [ "
+.IR MATCH_LIST " ] [ "
+.B action
+.IR ACTION_SPEC " ] [ "
+.B classid
+.IR CLASSID " ]"
+
+.ti -8
+.IR MATCH_LIST " := [ " MATCH_LIST " ] " MATCH
+
+.ti -8
+.IR MATCH " := { "
+.B indev
+.IR ifname " | { "
+.BR dst_mac " | " src_mac " } "
+.IR mac_address " | "
+.BR eth_type " { " ipv4 " | " ipv6 " | "
+.IR ETH_TYPE " } | "
+.BR ip_proto " { " tcp " | " udp " | "
+.IR IP_PROTO " } | { "
+.BR dst_ip " | " src_ip " } { "
+.IR ipv4_address " | " ipv6_address " } | { "
+.BR dst_port " | " src_port " } "
+.IR port_number " }"
+.SH DESCRIPTION
+The
+.B flower
+filter matches flows to the set of keys specified and assigns an arbitrarily
+chosen class ID to packets belonging to them. Additionally (or alternatively) an
+action from the generic action framework may be called.
+.SH OPTIONS
+.TP
+.BI action " ACTION_SPEC"
+Apply an action from the generic actions framework on matching packets.
+.TP
+.BI classid " CLASSID"
+Specify a class to pass matching packets on to.
+.I CLASSID
+is in the form
+.BR X : Y ", while " X " and " Y
+are interpreted as numbers in hexadecimal format.
+.TP
+.BI indev " ifname"
+Match on incoming interface name. Obviously this makes sense only for forwarded
+flows.
+.I ifname
+is the name of an interface which must exist at the time of
+.B tc
+invocation.
+.TP
+.BI dst_mac " mac_address"
+.TQ
+.BI src_mac " mac_address"
+Match on source or destination MAC address.
+.TP
+.BI eth_type " ETH_TYPE"
+Match on layer three protocol.
+.I ETH_TYPE
+may be either
+.BR ipv4 , ipv6
+or an unsigned 16bit value in hexadecimal format.
+.TP
+.BI ip_proto " IP_PROTO"
+Match on layer four protocol.
+.I IP_PROTO
+may be either
+.BR tcp , udp
+or an unsigned 8bit value in hexadecimal format.
+.TP
+.BI dst_ip " ADDRESS"
+.TQ
+.BI src_ip " ADDRESS"
+Match on source or destination IP address.
+.I ADDRESS
+must be a valid IPv4 or IPv6 address, depending on
+.BR ether_type ,
+which has to be specified in beforehand.
+.TP
+.BI dst_port " NUMBER"
+.TQ
+.BI src_port " NUMBER"
+Match on layer 4 protocol source or destination port number. Only available for
+.BR ip_proto " values " udp " and " tcp ,
+which has to be specified in beforehand.
+.SH NOTES
+As stated above where applicable, matches of a certain layer implicitly depend
+on the matches of the next lower layer. Precisely, layer one and two matches (
+.BR indev , dst_mac , src_mac " and " eth_type )
+have no dependency, layer three matches (
+.BR ip_proto , dst_ip " and " src_ip )
+require
+.B eth_type
+being set to either
+.BR ipv4 " or " ipv6 ,
+and finally layer four matches (
+.BR dst_port " and " src_port )
+depend on
+.B ip_proto
+being set to either
+.BR tcp " or " udp .
+.P
+There can be only used one mask per one prio. If user needs to specify different
+mask, he has to use different prio.
+.SH SEE ALSO
+.BR tc (8),
+.BR tc-flow (8)
diff --git a/iproute2/man/man8/tc-fq.8 b/iproute2/man/man8/tc-fq.8
new file mode 100644
index 0000000..f058a05
--- /dev/null
+++ b/iproute2/man/man8/tc-fq.8
@@ -0,0 +1,92 @@
+.TH FQ 8 "10 Sept 2015" "iproute2" "Linux"
+.SH NAME
+FQ \- Fair Queue traffic policing
+.SH SYNOPSIS
+.B tc qdisc ... fq
+[
+.B limit
+PACKETS ] [
+.B flow_limit
+PACKETS ] [
+.B quantum
+BYTES ] [
+.B initial_quantum
+BYTES ] [
+.B maxrate
+RATE ] [
+.B buckets
+NUMBER ] [
+.B pacing
+|
+.B nopacing
+]
+
+.SH DESCRIPTION
+FQ (Fair Queue) is a classless packet scheduler meant to be mostly
+used for locally generated traffic. It is designed to achieve per flow pacing.
+FQ does flow separation, and is able to respect pacing requirements set by TCP stack.
+All packets belonging to a socket are considered as a 'flow'.
+For non local packets (router workload), packet rxhash is used as fallback.
+
+An application can specify a maximum pacing rate using the
+.B SO_MAX_PACING_RATE
+setsockopt call. This packet scheduler adds delay between packets to
+respect rate limitation set by TCP stack.
+
+Dequeueing happens in a round-robin fashion.
+A special FIFO queue is reserved for high priority packets (
+.B TC_PRIO_CONTROL
+priority), such packets are always dequeued first.
+
+FQ is non-work-conserving.
+
+TCP pacing is good for flows having idle times, as the congestion
+window permits TCP stack to queue a possibly large number of packets.
+This removes the 'slow start after idle' choice, badly hitting
+large BDP flows and applications delivering chunks of data such as video streams.
+
+.SH PARAMETERS
+.SS limit
+Hard limit on the real queue size. When this limit is reached, new packets
+are dropped. If the value is lowered, packets are dropped so that the new limit is
+met. Default is 10000 packets.
+.SS flow_limit
+Hard limit on the maximum number of packets queued per flow.
+Default value is 100.
+.SS quantum
+The credit per dequeue RR round, i.e. the amount of bytes a flow is allowed to
+dequeue at once. A larger value means a longer time period before the next flow
+will be served.
+Default is 2 * interface MTU bytes.
+.SS initial_quantum
+The initial sending rate credit, i.e. the amount of bytes a new flow is allowed
+to dequeue initially.
+This is specifically meant to allow using IW10 without added delay.
+Default is 10 * interface MTU, i.e. 15140 for 'standard' ethernet.
+.SS maxrate
+Maximum sending rate of a flow. Default is unlimited.
+Application specific setting via
+.B SO_MAX_PACING_RATE
+is ignored only if it is larger than this value.
+.SS buckets
+The size of the hash table used for flow lookups. Each bucket is assigned a
+red-black tree for efficient collision sorting.
+Default: 1024.
+.SS [no]pacing
+Enable or disable flow pacing. Default is enabled.
+.SH EXAMPLES
+#tc qdisc add dev eth0 root fq
+.br
+#tc -s -d qdisc
+.br
+qdisc fq 8003: dev eth0 root refcnt 2 limit 10000p flow_limit 100p buckets 1024 quantum 3028 initial_quantum 15140
+ Sent 503727981 bytes 1146972 pkt (dropped 0, overlimits 0 requeues 54452)
+ backlog 0b 0p requeues 54452
+ 1289 flows (1289 inactive, 0 throttled)
+ 0 gc, 31 highprio, 27411 throttled
+.br
+.SH SEE ALSO
+.BR tc (8),
+.BR socket (7)
+.SH AUTHORS
+FQ was written by Eric Dumazet.
diff --git a/iproute2/man/man8/tc-fq_codel.8 b/iproute2/man/man8/tc-fq_codel.8
new file mode 100644
index 0000000..a80389a
--- /dev/null
+++ b/iproute2/man/man8/tc-fq_codel.8
@@ -0,0 +1,108 @@
+.TH FQ_CoDel 8 "4 June 2012" "iproute2" "Linux"
+.SH NAME
+CoDel \- Fair Queuing (FQ) with Controlled Delay (CoDel)
+.SH SYNOPSIS
+.B tc qdisc ... fq_codel
+[
+.B limit
+PACKETS ] [
+.B flows
+NUMBER ] [
+.B target
+TIME ] [
+.B interval
+TIME ] [
+.B quantum
+BYTES ] [
+.B ecn
+|
+.B noecn
+]
+
+.SH DESCRIPTION
+FQ_Codel (Fair Queuing Controlled Delay) is queuing discipline that combines Fair
+Queuing with the CoDel AQM scheme. FQ_Codel uses a stochastic model to classify
+incoming packets into different flows and is used to provide a fair share of the
+bandwidth to all the flows using the queue. Each such flow is managed by the
+CoDel queuing discipline. Reordering within a flow is avoided since Codel
+internally uses a FIFO queue.
+
+.SH PARAMETERS
+.SS limit
+has the same semantics as
+.B codel
+and is the hard limit on the real queue size.
+When this limit is reached, incoming packets are dropped. Default is 10240
+packets.
+
+.SS flows
+is the number of flows into which the incoming packets are classified. Due to
+the stochastic nature of hashing, multiple flows may end up being hashed into
+the same slot. Newer flows have priority over older ones. This parameter can be
+set only at load time since memory has to be allocated for the hash table.
+Default value is 1024.
+
+.SS target
+has the same semantics as
+.B codel
+and is the acceptable minimum
+standing/persistent queue delay. This minimum delay is identified by tracking
+the local minimum queue delay that packets experience. Default value is 5ms.
+
+.SS interval
+has the same semantics as
+.B codel
+and is used to ensure that the measured minimum delay does not become too stale.
+The minimum delay must be experienced in the last epoch of length .B interval.
+It should be set on the order of the worst-case RTT through the bottleneck to
+give endpoints sufficient time to react. Default value is 100ms.
+
+.SS quantum
+is the number of bytes used as 'deficit' in the fair queuing algorithm. Default
+is set to 1514 bytes which corresponds to the Ethernet MTU plus the hardware
+header length of 14 bytes.
+
+.SS ecn | noecn
+has the same semantics as
+.B codel
+and can be used to mark packets instead of dropping them. If
+.B ecn
+has been enabled,
+.B noecn
+can be used to turn it off and vice-a-versa. Unlike
+.B codel, ecn
+is turned on by default.
+
+.SH EXAMPLES
+#tc qdisc add dev eth0 root fq_codel
+.br
+#tc -s qdisc show
+.br
+qdisc fq_codel 8002: dev eth0 root refcnt 2 limit 10240p flows 1024 quantum 1514
+ target 5.0ms interval 100.0ms ecn
+ Sent 428514 bytes 2269 pkt (dropped 0, overlimits 0 requeues 0)
+ backlog 0b 0p requeues 0
+ maxpacket 256 drop_overlimit 0 new_flow_count 0 ecn_mark 0
+ new_flows_len 0 old_flows_len 0
+
+#tc qdisc add dev eth0 root fq_codel limit 2000 target 3ms interval 40ms noecn
+.br
+#tc -s qdisc show
+.br
+qdisc fq_codel 8003: dev eth0 root refcnt 2 limit 2000p flows 1024 quantum 1514
+target 3.0ms interval 40.0ms
+ Sent 2588985006 bytes 1783629 pkt (dropped 0, overlimits 0 requeues 34869)
+ backlog 0b 0p requeues 34869
+ maxpacket 65226 drop_overlimit 0 new_flow_count 73 ecn_mark 0
+ new_flows_len 1 old_flows_len 3
+
+
+.SH SEE ALSO
+.BR tc (8),
+.BR tc-codel (8),
+.BR tc-red (8)
+
+.SH AUTHORS
+FQ_CoDel was implemented by Eric Dumazet. This manpage was written
+by Vijay Subramanian. Please report corrections to the Linux Networking
+mailing list <netdev@vger.kernel.org>.
diff --git a/iproute2/man/man8/tc-fw.8 b/iproute2/man/man8/tc-fw.8
new file mode 100644
index 0000000..d742b47
--- /dev/null
+++ b/iproute2/man/man8/tc-fw.8
@@ -0,0 +1,66 @@
+.TH "Firewall mark classifier in tc" 8 "21 Oct 2015" "iproute2" "Linux"
+
+.SH NAME
+fw \- fwmark traffic control filter
+.SH SYNOPSIS
+.in +8
+.ti -8
+.BR tc " " filter " ... " fw " [ " classid
+.IR CLASSID " ] [ "
+.B action
+.IR ACTION_SPEC " ]"
+.SH DESCRIPTION
+the
+.B fw
+filter allows to classify packets based on a previously set
+.BR fwmark " by " iptables .
+If it is identical to the filter's
+.BR handle ,
+the filter matches.
+.B iptables
+allows to mark single packets with the
+.B MARK
+target, or whole connections using
+.BR CONNMARK .
+The benefit of using this filter instead of doing the
+heavy-lifting with
+.B tc
+itself is that on one hand it might be convenient to keep packet filtering and
+classification in one place, possibly having to match a packet just once, and on
+the other users familiar with
+.BR iptables " but not " tc
+will have a less hard time adding QoS to their setups.
+.SH OPTIONS
+.TP
+.BI classid " CLASSID"
+Push matching packets to the class identified by
+.IR CLASSID .
+.TP
+.BI action " ACTION_SPEC"
+Apply an action from the generic actions framework on matching packets.
+.SH EXAMPLES
+Take e.g. the following tc filter statement:
+
+.RS
+.EX
+tc filter add ... handle 6 fw classid 1:1
+.EE
+.RE
+
+will match if the packet's
+.B fwmark
+value is
+.BR 6 .
+This is a sample
+.B iptables
+statement marking packets coming in on eth0:
+
+.RS
+.EX
+iptables -t mangle -A PREROUTING -i eth0 -j MARK --set-mark 6
+.EE
+.RE
+.SH SEE ALSO
+.BR tc (8),
+.BR iptables (8),
+.BR iptables-extensions (8)
diff --git a/iproute2/man/man8/tc-hfsc.8 b/iproute2/man/man8/tc-hfsc.8
new file mode 100644
index 0000000..5444118
--- /dev/null
+++ b/iproute2/man/man8/tc-hfsc.8
@@ -0,0 +1,61 @@
+.TH HFSC 8 "31 October 2011" iproute2 Linux
+.
+.SH NAME
+HFSC \- Hierarchical Fair Service Curve's control under linux
+.
+.SH SYNOPSIS
+.nf
+tc qdisc add ... hfsc [ \fBdefault\fR CLASSID ]
+
+tc class add ... hfsc [ [ \fBrt\fR SC ] [ \fBls\fR SC ] | [ \fBsc\fR SC ] ] [ \fBul\fR SC ]
+
+\fBrt\fR : realtime service curve
+\fBls\fR : linkshare service curve
+\fBsc\fR : rt+ls service curve
+\fBul\fR : upperlimit service curve
+
+\(bu at least one of \fBrt\fR, \fBls\fR or \fBsc\fR must be specified
+\(bu \fBul\fR can only be specified with \fBls\fR or \fBsc\fR
+.
+.IP "SC := [ [ \fBm1\fR BPS ] \fBd\fR SEC ] \fBm2\fR BPS"
+\fBm1\fR : slope of the first segment
+\fBd\fR : x\-coordinate of intersection
+\fBm2\fR : slope of the second segment
+.PP
+.IP "SC := [ [ \fBumax\fR BYTE ] \fBdmax\fR SEC ] \fBrate\fR BPS"
+\fBumax\fR : maximum unit of work
+\fBdmax\fR : maximum delay
+\fBrate\fR : rate
+.PP
+.fi
+For description of BYTE, BPS and SEC \- please see \fBUNITS\fR
+section of \fBtc\fR(8).
+.
+.SH DESCRIPTION (qdisc)
+HFSC qdisc has only one optional parameter \- \fBdefault\fR. CLASSID specifies
+the minor part of the default classid, where packets not classified by other
+means (e.g. u32 filter, CLASSIFY target of iptables) will be enqueued. If
+\fBdefault\fR is not specified, unclassified packets will be dropped.
+.
+.SH DESCRIPTION (class)
+HFSC class is used to create a class hierarchy for HFSC scheduler. For
+explanation of the algorithm, and the meaning behind \fBrt\fR, \fBls\fR,
+\fBsc\fR and \fBul\fR service curves \- please refer to \fBtc\-hfsc\fR(7).
+
+As you can see in \fBSYNOPSIS\fR, service curve (SC) can be specified in two
+ways. Either as maximum delay for certain amount of work, or as a bandwidth
+assigned for certain amount of time. Obviously, \fBm1\fR is simply
+\fBumax\fR/\fBdmax\fR.
+
+Both \fBm2\fR and \fBrate\fR are mandatory. If you omit other
+parameters, you will specify linear service curve.
+.
+.SH "SEE ALSO"
+.
+\fBtc\fR(8), \fBtc\-hfsc\fR(7), \fBtc\-stab\fR(8)
+
+Please direct bugreports and patches to: <net...@vger.kernel.org>
+.
+.SH "AUTHOR"
+.
+Manpage created by Michal Soltys (sol...@ziu.info)
diff --git a/iproute2/man/man8/tc-htb.8 b/iproute2/man/man8/tc-htb.8
new file mode 100644
index 0000000..ae310f4
--- /dev/null
+++ b/iproute2/man/man8/tc-htb.8
@@ -0,0 +1,148 @@
+.TH HTB 8 "10 January 2002" "iproute2" "Linux"
+.SH NAME
+HTB \- Hierarchy Token Bucket
+.SH SYNOPSIS
+.B tc qdisc ... dev
+dev
+.B ( parent
+classid
+.B | root) [ handle
+major:
+.B ] htb [ default
+minor-id
+.B ]
+
+.B tc class ... dev
+dev
+.B parent
+major:[minor]
+.B [ classid
+major:minor
+.B ] htb rate
+rate
+.B [ ceil
+rate
+.B ] burst
+bytes
+.B [ cburst
+bytes
+.B ] [ prio
+priority
+.B ]
+
+.SH DESCRIPTION
+HTB is meant as a more understandable and intuitive replacement for
+the CBQ qdisc in Linux. Both CBQ and HTB help you to control the use
+of the outbound bandwidth on a given link. Both allow you to use one
+physical link to simulate several slower links and to send different
+kinds of traffic on different simulated links. In both cases, you have
+to specify how to divide the physical link into simulated links and
+how to decide which simulated link to use for a given packet to be sent.
+
+Unlike CBQ, HTB shapes traffic based on the Token Bucket Filter algorithm
+which does not depend on interface characteristics and so does not need to
+know the underlying bandwidth of the outgoing interface.
+
+.SH SHAPING ALGORITHM
+Shaping works as documented in
+.B tc-tbf (8).
+
+.SH CLASSIFICATION
+Within the one HTB instance many classes may exist. Each of these classes
+contains another qdisc, by default
+.BR tc-pfifo (8).
+
+When enqueueing a packet, HTB starts at the root and uses various methods to
+determine which class should receive the data.
+
+In the absence of uncommon configuration options, the process is rather easy.
+At each node we look for an instruction, and then go to the class the
+instruction refers us to. If the class found is a barren leaf-node (without
+children), we enqueue the packet there. If it is not yet a leaf node, we do
+the whole thing over again starting from that node.
+
+The following actions are performed, in order at each node we visit, until one
+sends us to another node, or terminates the process.
+.TP
+(i)
+Consult filters attached to the class. If sent to a leafnode, we are done.
+Otherwise, restart.
+.TP
+(ii)
+If none of the above returned with an instruction, enqueue at this node.
+.P
+This algorithm makes sure that a packet always ends up somewhere, even while
+you are busy building your configuration.
+
+.SH LINK SHARING ALGORITHM
+FIXME
+
+.SH QDISC
+The root of a HTB qdisc class tree has the following parameters:
+
+.TP
+parent major:minor | root
+This mandatory parameter determines the place of the HTB instance, either at the
+.B root
+of an interface or within an existing class.
+.TP
+handle major:
+Like all other qdiscs, the HTB can be assigned a handle. Should consist only
+of a major number, followed by a colon. Optional, but very useful if classes
+will be generated within this qdisc.
+.TP
+default minor-id
+Unclassified traffic gets sent to the class with this minor-id.
+
+.SH CLASSES
+Classes have a host of parameters to configure their operation.
+
+.TP
+parent major:minor
+Place of this class within the hierarchy. If attached directly to a qdisc
+and not to another class, minor can be omitted. Mandatory.
+.TP
+classid major:minor
+Like qdiscs, classes can be named. The major number must be equal to the
+major number of the qdisc to which it belongs. Optional, but needed if this
+class is going to have children.
+.TP
+prio priority
+In the round-robin process, classes with the lowest priority field are tried
+for packets first. Mandatory.
+
+.TP
+rate rate
+Maximum rate this class and all its children are guaranteed. Mandatory.
+
+.TP
+ceil rate
+Maximum rate at which a class can send, if its parent has bandwidth to spare.
+Defaults to the configured rate, which implies no borrowing
+
+.TP
+burst bytes
+Amount of bytes that can be burst at
+.B ceil
+speed, in excess of the configured
+.B rate.
+Should be at least as high as the highest burst of all children.
+
+.TP
+cburst bytes
+Amount of bytes that can be burst at 'infinite' speed, in other words, as fast
+as the interface can transmit them. For perfect evening out, should be equal to at most one average
+packet. Should be at least as high as the highest cburst of all children.
+
+.SH NOTES
+Due to Unix timing constraints, the maximum ceil rate is not infinite and may in fact be quite low. On Intel,
+there are 100 timer events per second, the maximum rate is that rate at which 'burst' bytes are sent each timer tick.
+From this, the minimum burst size for a specified rate can be calculated. For i386, a 10mbit rate requires a 12 kilobyte
+burst as 100*12kb*8 equals 10mbit.
+
+.SH SEE ALSO
+.BR tc (8)
+.P
+HTB website: http://luxik.cdi.cz/~devik/qos/htb/
+.SH AUTHOR
+Martin Devera <devik@cdi.cz>. This manpage maintained by bert hubert <ahu@ds9a.nl>
diff --git a/iproute2/man/man8/tc-mqprio.8 b/iproute2/man/man8/tc-mqprio.8
new file mode 100644
index 0000000..0e1d305
--- /dev/null
+++ b/iproute2/man/man8/tc-mqprio.8
@@ -0,0 +1,112 @@
+.TH MQPRIO 8 "24 Sept 2013" "iproute2" "Linux"
+.SH NAME
+MQPRIO \- Multiqueue Priority Qdisc (Offloaded Hardware QOS)
+.SH SYNOPSIS
+.B tc qdisc ... dev
+dev
+.B ( parent
+classid
+.B | root) [ handle
+major:
+.B ] mqprio [ numtc
+tcs
+.B ] [ map
+P0 P1 P2...
+.B ] [ queues
+count1@offset1 count2@offset2 ...
+.B ] [ hw
+1|0
+.B ]
+
+.SH DESCRIPTION
+The MQPRIO qdisc is a simple queuing discipline that allows mapping
+traffic flows to hardware queue ranges using priorities and a configurable
+priority to traffic class mapping. A traffic class in this context is
+a set of contiguous qdisc classes which map 1:1 to a set of hardware
+exposed queues.
+
+By default the qdisc allocates a pfifo qdisc (packet limited first in, first
+out queue) per TX queue exposed by the lower layer device. Other queuing
+disciplines may be added subsequently. Packets are enqueued using the
+.B map
+parameter and hashed across the indicated queues in the
+.B offset
+and
+.B count.
+By default these parameters are configured by the hardware
+driver to match the hardware QOS structures.
+
+Enabled hardware can provide hardware QOS with the ability to steer
+traffic flows to designated traffic classes provided by this qdisc.
+Configuring the hardware based QOS mechanism is outside the scope of
+this qdisc. Tools such as
+.B lldpad
+and
+.B ethtool
+exist to provide this functionality. Also further qdiscs may be added
+to the classes of MQPRIO to create more complex configurations.
+
+.SH ALGORITHM
+On creation with 'tc qdisc add', eight traffic classes are created mapping
+priorities 0..7 to traffic classes 0..7 and priorities greater than 7 to
+traffic class 0. This requires base driver support and the creation will
+fail on devices that do not support hardware QOS schemes.
+
+These defaults can be overridden using the qdisc parameters. Providing
+the 'hw 0' flag allows software to run without hardware coordination.
+
+If hardware coordination is being used and arguments are provided that
+the hardware can not support then an error is returned. For many users
+hardware defaults should work reasonably well.
+
+As one specific example numerous Ethernet cards support the 802.1Q
+link strict priority transmission selection algorithm (TSA). MQPRIO
+enabled hardware in conjunction with the classification methods below
+can provide hardware offloaded support for this TSA.
+
+.SH CLASSIFICATION
+Multiple methods are available to set the SKB priority which MQPRIO
+uses to select which traffic class to enqueue the packet.
+.TP
+From user space
+A process with sufficient privileges can encode the destination class
+directly with SO_PRIORITY, see
+.BR socket(7).
+.TP
+with iptables/nftables
+An iptables/nftables rule can be created to match traffic flows and
+set the priority.
+.BR iptables(8)
+.TP
+with net_prio cgroups
+The net_prio cgroup can be used to set the priority of all sockets
+belong to an application. See kernel and cgroup documentation for details.
+
+.SH QDISC PARAMETERS
+.TP
+num_tc
+Number of traffic classes to use. Up to 16 classes supported.
+
+.TP
+map
+The priority to traffic class map. Maps priorities 0..15 to a specified
+traffic class.
+
+.TP
+queues
+Provide count and offset of queue range for each traffic class. In the
+format,
+.B count@offset.
+Queue ranges for each traffic classes cannot overlap and must be a
+contiguous range of queues.
+
+.TP
+hw
+Set to
+.B 1
+to use hardware QOS defaults. Set to
+.B 0
+to override hardware defaults with user specified values.
+
+.SH AUTHORS
+John Fastabend, <john.r.fastabend@intel.com>
diff --git a/iproute2/man/man8/tc-netem.8 b/iproute2/man/man8/tc-netem.8
new file mode 100644
index 0000000..b31384f
--- /dev/null
+++ b/iproute2/man/man8/tc-netem.8
@@ -0,0 +1,198 @@
+.TH NETEM 8 "25 November 2011" "iproute2" "Linux"
+.SH NAME
+NetEm \- Network Emulator
+.SH SYNOPSIS
+.B "tc qdisc ... dev"
+.IR DEVICE " ] "
+.BR "add netem"
+.I OPTIONS
+
+.IR OPTIONS " := [ " LIMIT " ] [ " DELAY " ] [ " LOSS \
+" ] [ " CORRUPT " ] [ " DUPLICATION " ] [ " REORDERING " ][ " RATE " ]"
+
+.IR LIMIT " := "
+.B limit
+.I packets
+
+.IR DELAY " := "
+.BI delay
+.IR TIME " [ " JITTER " [ " CORRELATION " ]]]"
+.br
+ [
+.BR distribution " { "uniform " | " normal " | " pareto " | " paretonormal " } ]"
+
+.IR LOSS " := "
+.BR loss " { "
+.BI random
+.IR PERCENT " [ " CORRELATION " ] |"
+.br
+.RB " " state
+.IR p13 " [ " p31 " [ " p32 " [ " p23 " [ " p14 "]]]] |"
+.br
+.RB " " gemodel
+.IR p " [ " r " [ " 1-h " [ " 1-k " ]]] } "
+.RB " [ " ecn " ] "
+
+.IR CORRUPT " := "
+.B corrupt
+.IR PERCENT " [ " CORRELATION " ]]"
+
+.IR DUPLICATION " := "
+.B duplicate
+.IR PERCENT " [ " CORRELATION " ]]"
+
+.IR REORDERING " := "
+.B reorder
+.IR PERCENT " [ " CORRELATION " ] [ "
+.B gap
+.IR DISTANCE " ]"
+
+.IR RATE " := "
+.B rate
+.IR RATE " [ " PACKETOVERHEAD " [ " CELLSIZE " [ " CELLOVERHEAD " ]]]]"
+
+
+.SH DESCRIPTION
+NetEm is an enhancement of the Linux traffic control facilities
+that allow to add delay, packet loss, duplication and more other
+characteristics to packets outgoing from a selected network
+interface. NetEm is built using the existing Quality Of Service (QOS)
+and Differentiated Services (diffserv) facilities in the Linux
+kernel.
+
+.SH netem OPTIONS
+netem has the following options:
+
+.SS limit packets
+
+limits the effect of selected options to the indicated number of next packets.
+
+.SS delay
+adds the chosen delay to the packets outgoing to chosen network interface. The
+optional parameters allows to introduce a delay variation and a correlation.
+Delay and jitter values are expressed in ms while correlation is percentage.
+
+.SS distribution
+allow the user to choose the delay distribution. If not specified, the default
+distribution is Normal. Additional parameters allow to consider situations in
+which network has variable delays depending on traffic flows concurring on the
+same path, that causes several delay peaks and a tail.
+
+.SS loss random
+adds an independent loss probability to the packets outgoing from the chosen
+network interface. It is also possible to add a correlation, but this option
+is now deprecated due to the noticed bad behavior.
+
+.SS loss state
+adds packet losses according to the 4-state Markov using the transition
+probabilities as input parameters. The parameter p13 is mandatory and if used
+alone corresponds to the Bernoulli model. The optional parameters allows to
+extend the model to 2-state (p31), 3-state (p23 and p32) and 4-state (p14).
+State 1 corresponds to good reception, State 4 to independent losses, State 3
+to burst losses and State 2 to good reception within a burst.
+
+.SS loss gemodel
+adds packet losses according to the Gilbert-Elliot loss model or its special
+cases (Gilbert, Simple Gilbert and Bernoulli). To use the Bernoulli model, the
+only needed parameter is p while the others will be set to the default
+values r=1-p, 1-h=1 and 1-k=0. The parameters needed for the Simple Gilbert
+model are two (p and r), while three parameters (p, r, 1-h) are needed for the
+Gilbert model and four (p, r, 1-h and 1-k) are needed for the Gilbert-Elliot
+model. As known, p and r are the transition probabilities between the bad and
+the good states, 1-h is the loss probability in the bad state and 1-k is the
+loss probability in the good state.
+
+.SS ecn
+can be used optionally to mark packets instead of dropping them. A loss model
+has to be used for this to be enabled.
+
+.SS corrupt
+allows the emulation of random noise introducing an error in a random position
+for a chosen percent of packets. It is also possible to add a correlation
+through the proper parameter.
+
+.SS duplicate
+using this option the chosen percent of packets is duplicated before queuing
+them. It is also possible to add a correlation through the proper parameter.
+
+.SS reorder
+to use reordering, a delay option must be specified. There are two ways to use
+this option (assuming 'delay 10ms' in the options list).
+
+.B "reorder "
+.I 25% 50%
+.B "gap"
+.I 5
+.br
+in this first example, the first 4 (gap - 1) packets are delayed by 10ms and
+subsequent packets are sent immediately with a probability of 0.25 (with
+correlation of 50% ) or delayed with a probability of 0.75. After a packet is
+reordered, the process restarts i.e. the next 4 packets are delayed and
+subsequent packets are sent immediately or delayed based on reordering
+probability. To cause a repeatable pattern where every 5th packet is reordered
+reliably, a reorder probability of 100% can be used.
+
+.B reorder
+.I 25% 50%
+.br
+in this second example 25% of packets are sent immediately (with correlation of
+50%) while the others are delayed by 10 ms.
+
+.SS rate
+delay packets based on packet size and is a replacement for
+.IR TBF .
+Rate can be
+specified in common units (e.g. 100kbit). Optional
+.I PACKETOVERHEAD
+(in bytes) specify an per packet overhead and can be negative. A positive value can be
+used to simulate additional link layer headers. A negative value can be used to
+artificial strip the Ethernet header (e.g. -14) and/or simulate a link layer
+header compression scheme. The third parameter - an unsigned value - specify
+the cellsize. Cellsize can be used to simulate link layer schemes. ATM for
+example has an payload cellsize of 48 bytes and 5 byte per cell header. If a
+packet is 50 byte then ATM must use two cells: 2 * 48 bytes payload including 2
+* 5 byte header, thus consume 106 byte on the wire. The last optional value
+.I CELLOVERHEAD
+can be used to specify per cell overhead - for our ATM example 5.
+.I CELLOVERHEAD
+can be negative, but use negative values with caution.
+
+Note that rate throttling is limited by several factors: the kernel clock
+granularity avoid a perfect shaping at a specific level. This will show up in
+an artificial packet compression (bursts). Another influence factor are network
+adapter buffers which can also add artificial delay.
+
+.SH LIMITATIONS
+The main known limitation of Netem are related to timer granularity, since
+Linux is not a real-time operating system.
+
+.SH EXAMPLES
+.PP
+tc qdisc add dev eth0 root netem rate 5kbit 20 100 5
+.RS 4
+delay all outgoing packets on device eth0 with a rate of 5kbit, a per packet
+overhead of 20 byte, a cellsize of 100 byte and a per celloverhead of 5 byte:
+.RE
+
+.SH SOURCES
+.IP " 1. " 4
+Hemminger S. , "Network Emulation with NetEm", Open Source Development Lab,
+April 2005
+(http://devresources.linux-foundation.org/shemminger/netem/LCA2005_paper.pdf)
+
+.IP " 2. " 4
+Netem page from Linux foundation, (http://www.linuxfoundation.org/en/Net:Netem)
+
+.IP " 3. " 4
+Salsano S., Ludovici F., Ordine A., "Definition of a general and intuitive loss
+model for packet networks and its implementation in the Netem module in the
+Linux kernel", available at http://netgroup.uniroma2.it/NetemCLG
+
+.SH SEE ALSO
+.BR tc (8),
+.BR tc-tbf (8)
+
+.SH AUTHOR
+Netem was written by Stephen Hemminger at Linux foundation and is based on NISTnet.
+This manpage was created by Fabio Ludovici <fabio.ludovici at yahoo dot it> and
+Hagen Paul Pfeifer <hagen@jauu.net>
diff --git a/iproute2/man/man8/tc-pfifo.8 b/iproute2/man/man8/tc-pfifo.8
new file mode 100644
index 0000000..ed23850
--- /dev/null
+++ b/iproute2/man/man8/tc-pfifo.8
@@ -0,0 +1 @@
+.so man8/tc-bfifo.8
diff --git a/iproute2/man/man8/tc-pfifo_fast.8 b/iproute2/man/man8/tc-pfifo_fast.8
new file mode 100644
index 0000000..baf34b1
--- /dev/null
+++ b/iproute2/man/man8/tc-pfifo_fast.8
@@ -0,0 +1,57 @@
+.TH PFIFO_FAST 8 "10 January 2002" "iproute2" "Linux"
+.SH NAME
+pfifo_fast \- three-band first in, first out queue
+
+.SH DESCRIPTION
+pfifo_fast is the default qdisc of each interface.
+
+Whenever an interface is created, the pfifo_fast qdisc is automatically used
+as a queue. If another qdisc is attached, it preempts the default
+pfifo_fast, which automatically returns to function when an existing qdisc
+is detached.
+
+In this sense this qdisc is magic, and unlike other qdiscs.
+
+.SH ALGORITHM
+The algorithm is very similar to that of the classful
+.BR tc-prio (8)
+qdisc.
+.B pfifo_fast
+is like three
+.BR tc-pfifo (8)
+queues side by side, where packets can be enqueued in any of the three bands
+based on their Type of Service bits or assigned priority.
+
+Not all three bands are dequeued simultaneously - as long as lower bands
+have traffic, higher bands are never dequeued. This can be used to
+prioritize interactive traffic or penalize 'lowest cost' traffic.
+
+Each band can be txqueuelen packets long, as configured with
+.BR ifconfig (8)
+or
+.BR ip (8).
+Additional packets coming in are not enqueued but are instead dropped.
+
+See
+.BR tc-prio (8)
+for complete details on how TOS bits are translated into bands.
+.SH PARAMETERS
+.TP
+txqueuelen
+The length of the three bands depends on the interface txqueuelen, as
+specified with
+.BR ifconfig (8)
+or
+.BR ip (8).
+
+.SH BUGS
+Does not maintain statistics and does not show up in tc qdisc ls. This is because
+it is the automatic default in the absence of a configured qdisc.
+
+.SH SEE ALSO
+.BR tc (8)
+
+.SH AUTHORS
+Alexey N. Kuznetsov, <kuznet@ms2.inr.ac.ru>
+
+This manpage maintained by bert hubert <ahu@ds9a.nl>
diff --git a/iproute2/man/man8/tc-pie.8 b/iproute2/man/man8/tc-pie.8
new file mode 100644
index 0000000..278293b
--- /dev/null
+++ b/iproute2/man/man8/tc-pie.8
@@ -0,0 +1,131 @@
+.TH PIE 8 "16 January 2014" "iproute2" "Linux"
+.SH NAME
+PIE \- Proportional Integral controller-Enhanced AQM algorithm
+.SH SYNOPSIS
+.B tc qdisc ... pie
+[
+.B limit
+PACKETS ] [
+.B target
+TIME ] [
+.B tupdate
+TIME ] [
+.B alpha
+int ] [
+.B beta
+int ] [
+.B ecn
+|
+.B noecn
+] [
+.B bytemode
+|
+.B nobytemode
+]
+
+.SH DESCRIPTION
+Proportional Integral controller-Enhanced (PIE) is a control theoretic active
+queue management scheme. It is based on the proportional integral controller but
+aims to control delay. The main design goals are
+ o Low latency control
+ o High link utilization
+ o Simple implementation
+ o Guaranteed stability and fast responsiveness
+
+.SH ALGORITHM
+PIE is designed to control delay effectively. First, an average dequeue rate is
+estimated based on the standing queue. The rate is used to calculate the current
+delay. Then, on a periodic basis, the delay is used to calculate the dropping
+probabilty. Finally, on arrival, a packet is dropped (or marked) based on this
+probability.
+
+PIE makes adjustments to the probability based on the trend of the delay i.e.
+whether it is going up or down.The delay converges quickly to the target value
+specified.
+
+alpha and beta are statically chosen parameters chosen to control the drop probability
+growth and are determined through control theoretic approaches. alpha determines how
+the deviation between the current and target latency changes probability. beta exerts
+additional adjustments depending on the latency trend.
+
+The drop probabilty is used to mark packets in ecn mode. However, as in RED,
+beyond 10% packets are dropped based on this probability. The bytemode is used
+to drop packets proportional to the packet size.
+
+Additional details can be found in the paper cited below.
+
+.SH PARAMETERS
+.SS limit
+limit on the queue size in packets. Incoming packets are dropped when this limit
+is reached. Default is 1000 packets.
+
+.SS target
+is the expected queue delay. The default target delay is 20ms.
+
+.SS tupdate
+is the frequency at which the system drop probability is calculated. The default is 30ms.
+
+.SS alpha
+.SS beta
+alpha and beta are parameters chosen to control the drop probability. These
+should be in the range between 0 and 32.
+
+.SS ecn | noecn
+is used to mark packets instead of dropping
+.B ecn
+to turn on ecn mode,
+.B noecn
+to turn off ecn mode. By default,
+.B ecn
+is turned off.
+
+.SS bytemode | nobytemode
+is used to scale drop probability proportional to packet size
+.B bytemode
+to turn on bytemode,
+.B nobytemode
+to turn off bytemode. By default,
+.B bytemode
+is turned off.
+
+.SH EXAMPLES
+ # tc qdisc add dev eth0 root pie
+ # tc -s qdisc show
+ qdisc pie 8034: dev eth0 root refcnt 2 limit 200p target 19000us tupdate 29000us alpha 2 beta 20
+ Sent 7443524 bytes 7204 pkt (dropped 900, overlimits 0 requeues 0)
+ backlog 38998b 37p requeues 0
+ prob 0.123384 delay 25000us avg_dq_rate 1464840
+ pkts_in 7241 overlimit 900 dropped 0 maxq 186 ecn_mark 0
+
+ # tc qdisc add dev eth0 root pie limit 100 target 20ms tupdate 30ms ecn
+ # tc -s qdisc show
+ qdisc pie 8036: dev eth0 root refcnt 2 limit 200p target 19000 tupdate 29000 alpha 2 beta 20 ecn
+ Sent 2491922 bytes 2507 pkt (dropped 214, overlimits 0 requeues 0)
+ backlog 33728b 32p requeues 0
+ prob 0.102262 delay 24000us avg_dq_rate 1464840
+ pkts_in 2468 overlimit 214 dropped 0 maxq 192 ecn_mark 71
+
+
+ # tc qdisc add dev eth0 root pie limit 100 target 50ms tupdate 30ms bytemode
+ # tc -s qdisc show
+ qdisc pie 8036: dev eth0 root refcnt 2 limit 200p target 19000 tupdate 29000 alpha 2 beta 20 ecn
+ Sent 2491922 bytes 2507 pkt (dropped 214, overlimits 0 requeues 0)
+ backlog 33728b 32p requeues 0
+ prob 0.102262 delay 24000us avg_dq_rate 1464840
+ pkts_in 2468 overlimit 214 dropped 0 maxq 192 ecn_mark 71
+
+
+.SH SEE ALSO
+.BR tc (8),
+.BR tc-codel (8)
+.BR tc-red (8)
+
+.SH SOURCES
+ o IETF draft submission is at http://tools.ietf.org/html/draft-pan-tsvwg-pie-00
+ o IEEE Conference on High Performance Switching and Routing 2013 : "PIE: A
+Lightweight Control Scheme to Address the Bufferbloat Problem"
+
+.SH AUTHORS
+PIE was implemented by Vijay Subramanian and Mythili Prabhu, also the authors of
+this man page. Please report bugs and corrections to the Linux networking
+development mailing list at <netdev@vger.kernel.org>.
diff --git a/iproute2/man/man8/tc-prio.8 b/iproute2/man/man8/tc-prio.8
new file mode 100644
index 0000000..605f3d3
--- /dev/null
+++ b/iproute2/man/man8/tc-prio.8
@@ -0,0 +1,185 @@
+.TH PRIO 8 "16 December 2001" "iproute2" "Linux"
+.SH NAME
+PRIO \- Priority qdisc
+.SH SYNOPSIS
+.B tc qdisc ... dev
+dev
+.B ( parent
+classid
+.B | root) [ handle
+major:
+.B ] prio [ bands
+bands
+.B ] [ priomap
+band band band...
+.B ] [ estimator
+interval timeconstant
+.B ]
+
+.SH DESCRIPTION
+The PRIO qdisc is a simple classful queueing discipline that contains
+an arbitrary number of classes of differing priority. The classes are
+dequeued in numerical descending order of priority. PRIO is a scheduler
+and never delays packets - it is a work-conserving qdisc, though the qdiscs
+contained in the classes may not be.
+
+Very useful for lowering latency when there is no need for slowing down
+traffic.
+
+.SH ALGORITHM
+On creation with 'tc qdisc add', a fixed number of bands is created. Each
+band is a class, although is not possible to add classes with 'tc qdisc
+add', the number of bands to be created must instead be specified on the
+command line attaching PRIO to its root.
+
+When dequeueing, band 0 is tried first and only if it did not deliver a
+packet does PRIO try band 1, and so onwards. Maximum reliability packets
+should therefore go to band 0, minimum delay to band 1 and the rest to band
+2.
+
+As the PRIO qdisc itself will have minor number 0, band 0 is actually
+major:1, band 1 is major:2, etc. For major, substitute the major number
+assigned to the qdisc on 'tc qdisc add' with the
+.B handle
+parameter.
+
+.SH CLASSIFICATION
+Three methods are available to PRIO to determine in which band a packet will
+be enqueued.
+.TP
+From userspace
+A process with sufficient privileges can encode the destination class
+directly with SO_PRIORITY, see
+.BR socket(7).
+.TP
+with a tc filter
+A tc filter attached to the root qdisc can point traffic directly to a class
+.TP
+with the priomap
+Based on the packet priority, which in turn is derived from the Type of
+Service assigned to the packet.
+.P
+Only the priomap is specific to this qdisc.
+.SH QDISC PARAMETERS
+.TP
+bands
+Number of bands. If changed from the default of 3,
+.B priomap
+must be updated as well.
+.TP
+priomap
+The priomap maps the priority of
+a packet to a class. The priority can either be set directly from userspace,
+or be derived from the Type of Service of the packet.
+
+Determines how packet priorities, as assigned by the kernel, map to
+bands. Mapping occurs based on the TOS octet of the packet, which looks like
+this:
+
+.nf
+0 1 2 3 4 5 6 7
++---+---+---+---+---+---+---+---+
+| | | |
+|PRECEDENCE | TOS |MBZ|
+| | | |
++---+---+---+---+---+---+---+---+
+.fi
+
+The four TOS bits (the 'TOS field') are defined as:
+
+.nf
+Binary Decimal Meaning
+-----------------------------------------
+1000 8 Minimize delay (md)
+0100 4 Maximize throughput (mt)
+0010 2 Maximize reliability (mr)
+0001 1 Minimize monetary cost (mmc)
+0000 0 Normal Service
+.fi
+
+As there is 1 bit to the right of these four bits, the actual value of the
+TOS field is double the value of the TOS bits. Tcpdump -v -v shows you the
+value of the entire TOS field, not just the four bits. It is the value you
+see in the first column of this table:
+
+.nf
+TOS Bits Means Linux Priority Band
+------------------------------------------------------------
+0x0 0 Normal Service 0 Best Effort 1
+0x2 1 Minimize Monetary Cost 0 Best Effort 1
+0x4 2 Maximize Reliability 0 Best Effort 1
+0x6 3 mmc+mr 0 Best Effort 1
+0x8 4 Maximize Throughput 2 Bulk 2
+0xa 5 mmc+mt 2 Bulk 2
+0xc 6 mr+mt 2 Bulk 2
+0xe 7 mmc+mr+mt 2 Bulk 2
+0x10 8 Minimize Delay 6 Interactive 0
+0x12 9 mmc+md 6 Interactive 0
+0x14 10 mr+md 6 Interactive 0
+0x16 11 mmc+mr+md 6 Interactive 0
+0x18 12 mt+md 4 Int. Bulk 1
+0x1a 13 mmc+mt+md 4 Int. Bulk 1
+0x1c 14 mr+mt+md 4 Int. Bulk 1
+0x1e 15 mmc+mr+mt+md 4 Int. Bulk 1
+.fi
+
+The second column contains the value of the relevant
+four TOS bits, followed by their translated meaning. For example, 15 stands
+for a packet wanting Minimal Monetary Cost, Maximum Reliability, Maximum
+Throughput AND Minimum Delay.
+
+The fourth column lists the way the Linux kernel interprets the TOS bits, by
+showing to which Priority they are mapped.
+
+The last column shows the result of the default priomap. On the command line,
+the default priomap looks like this:
+
+ 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1
+
+This means that priority 4, for example, gets mapped to band number 1.
+The priomap also allows you to list higher priorities (> 7) which do not
+correspond to TOS mappings, but which are set by other means.
+
+This table from RFC 1349 (read it for more details) explains how
+applications might very well set their TOS bits:
+
+.nf
+TELNET 1000 (minimize delay)
+FTP
+ Control 1000 (minimize delay)
+ Data 0100 (maximize throughput)
+
+TFTP 1000 (minimize delay)
+
+SMTP
+ Command phase 1000 (minimize delay)
+ DATA phase 0100 (maximize throughput)
+
+Domain Name Service
+ UDP Query 1000 (minimize delay)
+ TCP Query 0000
+ Zone Transfer 0100 (maximize throughput)
+
+NNTP 0001 (minimize monetary cost)
+
+ICMP
+ Errors 0000
+ Requests 0000 (mostly)
+ Responses <same as request> (mostly)
+.fi
+
+
+.SH CLASSES
+PRIO classes cannot be configured further - they are automatically created
+when the PRIO qdisc is attached. Each class however can contain yet a
+further qdisc.
+
+.SH BUGS
+Large amounts of traffic in the lower bands can cause starvation of higher
+bands. Can be prevented by attaching a shaper (for example,
+.BR tc-tbf(8)
+to these bands to make sure they cannot dominate the link.
+
+.SH AUTHORS
+Alexey N. Kuznetsov, <kuznet@ms2.inr.ac.ru>, J Hadi Salim
+<hadi@cyberus.ca>. This manpage maintained by bert hubert <ahu@ds9a.nl>
diff --git a/iproute2/man/man8/tc-red.8 b/iproute2/man/man8/tc-red.8
new file mode 100644
index 0000000..dd1ab74
--- /dev/null
+++ b/iproute2/man/man8/tc-red.8
@@ -0,0 +1,160 @@
+.TH RED 8 "13 December 2001" "iproute2" "Linux"
+.SH NAME
+red \- Random Early Detection
+.SH SYNOPSIS
+.B tc qdisc ... red
+.B limit
+bytes
+.B [ min
+bytes
+.B ] [ max
+bytes
+.B ] avpkt
+bytes
+.B [ burst
+packets
+.B ] [ ecn ] [ harddrop] [ bandwidth
+rate
+.B ] [ probability
+chance
+.B ] [ adaptive ]
+
+.SH DESCRIPTION
+Random Early Detection is a classless qdisc which manages its queue size
+smartly. Regular queues simply drop packets from the tail when they are
+full, which may not be the optimal behaviour. RED also performs tail drop,
+but does so in a more gradual way.
+
+Once the queue hits a certain average length, packets enqueued have a
+configurable chance of being marked (which may mean dropped). This chance
+increases linearly up to a point called the
+.B max
+average queue length, although the queue might get bigger.
+
+This has a host of benefits over simple taildrop, while not being processor
+intensive. It prevents synchronous retransmits after a burst in traffic,
+which cause further retransmits, etc.
+
+The goal is to have a small queue size, which is good for interactivity
+while not disturbing TCP/IP traffic with too many sudden drops after a burst
+of traffic.
+
+Depending on if ECN is configured, marking either means dropping or
+purely marking a packet as overlimit.
+.SH ALGORITHM
+The average queue size is used for determining the marking
+probability. This is calculated using an Exponential Weighted Moving
+Average, which can be more or less sensitive to bursts.
+
+When the average queue size is below
+.B min
+bytes, no packet will ever be marked. When it exceeds
+.B min,
+the probability of doing so climbs linearly up
+to
+.B probability,
+until the average queue size hits
+.B max
+bytes. Because
+.B probability
+is normally not set to 100%, the queue size might
+conceivably rise above
+.B max
+bytes, so the
+.B limit
+parameter is provided to set a hard maximum for the size of the queue.
+
+.SH PARAMETERS
+.TP
+min
+Average queue size at which marking becomes a possibility. Defaults to
+.B max
+/3
+
+.TP
+max
+At this average queue size, the marking probability is maximal. Should be at
+least twice
+.B min
+to prevent synchronous retransmits, higher for low
+.B min.
+Default to
+.B limit
+/4
+.TP
+probability
+Maximum probability for marking, specified as a floating point
+number from 0.0 to 1.0. Suggested values are 0.01 or 0.02 (1 or 2%,
+respectively). Default : 0.02
+.TP
+limit
+Hard limit on the real (not average) queue size in bytes. Further packets
+are dropped. Should be set higher than max+burst. It is advised to set this
+a few times higher than
+.B max.
+.TP
+burst
+Used for determining how fast the average queue size is influenced by the
+real queue size. Larger values make the calculation more sluggish, allowing
+longer bursts of traffic before marking starts. Real life experiments
+support the following guideline: (min+min+max)/(3*avpkt).
+.TP
+avpkt
+Specified in bytes. Used with burst to determine the time constant for
+average queue size calculations. 1000 is a good value.
+.TP
+bandwidth
+This rate is used for calculating the average queue size after some
+idle time. Should be set to the bandwidth of your interface. Does not mean
+that RED will shape for you! Optional. Default : 10Mbit
+.TP
+ecn
+As mentioned before, RED can either 'mark' or 'drop'. Explicit Congestion
+Notification allows RED to notify remote hosts that their rate exceeds the
+amount of bandwidth available. Non-ECN capable hosts can only be notified by
+dropping a packet. If this parameter is specified, packets which indicate
+that their hosts honor ECN will only be marked and not dropped, unless the
+queue size hits
+.B limit
+bytes. Recommended.
+.TP
+harddrop
+If average flow queue size is above
+.B max
+bytes, this parameter forces a drop instead of ecn marking.
+.TP
+adaptive
+(Added in linux-3.3) Sets RED in adaptive mode as described in http://icir.org/floyd/papers/adaptiveRed.pdf
+.nf
+Goal of Adaptive RED is to make 'probability' dynamic value between 1% and 50% to reach the target average queue :
+.B (max - min) / 2
+.fi
+
+.SH EXAMPLE
+
+.P
+# tc qdisc add dev eth0 parent 1:1 handle 10: red
+ limit 400000 min 30000 max 90000 avpkt 1000
+ burst 55 ecn adaptive bandwidth 10Mbit
+
+.SH SEE ALSO
+.BR tc (8),
+.BR tc-choke (8)
+
+.SH SOURCES
+.TP
+o
+Floyd, S., and Jacobson, V., Random Early Detection gateways for
+Congestion Avoidance. http://www.aciri.org/floyd/papers/red/red.html
+.TP
+o
+Some changes to the algorithm by Alexey N. Kuznetsov.
+.TP
+o
+Adaptive RED : http://icir.org/floyd/papers/adaptiveRed.pdf
+
+.SH AUTHORS
+Alexey N. Kuznetsov, <kuznet@ms2.inr.ac.ru>, Alexey Makarenko
+<makar@phoenix.kharkov.ua>, J Hadi Salim <hadi@nortelnetworks.com>,
+Eric Dumazet <eric.dumazet@gmail.com>.
+This manpage maintained by bert hubert <ahu@ds9a.nl>
diff --git a/iproute2/man/man8/tc-route.8 b/iproute2/man/man8/tc-route.8
new file mode 100644
index 0000000..b865cd1
--- /dev/null
+++ b/iproute2/man/man8/tc-route.8
@@ -0,0 +1,74 @@
+.TH "Route classifier in tc" 8 "21 Oct 2015" "iproute2" "Linux"
+
+.SH NAME
+route \- route traffic control filter
+.SH SYNOPSIS
+.in +8
+.ti -8
+.BR tc " " filter " ... " route " [ " from
+.IR REALM " | "
+.B fromif
+.IR TAG " ] [ "
+.B to
+.IR REALM " ] [ "
+.B classid
+.IR CLASSID " ] [ "
+.B action
+.IR ACTION_SPEC " ]"
+.SH DESCRIPTION
+Match packets based on routing table entries. This filter centers around the
+possibility to assign a
+.B realm
+to routing table entries. For any packet to be classified by this filter, a
+routing table lookup is performed and the returned
+.B realm
+is used to decide on whether the packet is a match or not.
+.SH OPTIONS
+.TP
+.BI action " ACTION_SPEC"
+Apply an action from the generic actions framework on matching packets.
+.TP
+.BI classid " CLASSID"
+Push matching packets into the class identified by
+.IR CLASSID .
+.TP
+.BI from " REALM"
+.TQ
+.BI fromif " TAG"
+Perform source route lookups.
+.I TAG
+is the name of an interface which must be present on the system at the time of
+.B tc
+invocation.
+.TP
+.BI to " REALM"
+Match if normal (i.e., destination) routing returns the given
+.IR REALM .
+.SH EXAMPLES
+Consider the subnet 192.168.2.0/24 being attached to eth0:
+
+.RS
+.EX
+ip route add 192.168.2.0/24 dev eth0 realm 2
+.EE
+.RE
+
+The following
+.B route
+filter will then match packets from that subnet:
+
+.RS
+.EX
+tc filter add ... route from 2 classid 1:2
+.EE
+.RE
+
+and pass packets on to class 1:2.
+.SH NOTES
+Due to implementation details,
+.B realm
+values must be in a range from 0 to 255, inclusive. Alternatively, a verbose
+name defined in /etc/iproute2/rt_realms may be given instead.
+.SH SEE ALSO
+.BR tc (8),
+.BR ip-route (8)
diff --git a/iproute2/man/man8/tc-sfb.8 b/iproute2/man/man8/tc-sfb.8
new file mode 100644
index 0000000..aad19e1
--- /dev/null
+++ b/iproute2/man/man8/tc-sfb.8
@@ -0,0 +1,213 @@
+.TH SFB 8 "August 2011" "iproute2" "Linux"
+.SH NAME
+sfb \- Stochastic Fair Blue
+.SH SYNOPSIS
+.B tc qdisc ... blue
+.B rehash
+milliseconds
+.B db
+milliseconds
+.B limit
+packets
+.B max
+packets
+.B target
+packets
+.B increment
+float
+.B decrement
+float
+.B penalty_rate
+packets per second
+.B penalty_burst
+packets
+
+.SH DESCRIPTION
+Stochastic Fair Blue is a classless qdisc to manage congestion based on
+packet loss and link utilization history while trying to prevent
+non-responsive flows (i.e. flows that do not react to congestion marking
+or dropped packets) from impacting performance of responsive flows.
+Unlike RED, where the marking probability has to be configured, BLUE
+tries to determine the ideal marking probability automatically.
+
+.SH ALGORITHM
+
+The
+.B BLUE
+algorithm maintains a probability which is used to mark or drop packets
+that are to be queued. If the queue overflows, the mark/drop probability
+is increased. If the queue becomes empty, the probability is decreased. The
+.B Stochastic Fair Blue
+(SFB) algorithm is designed to protect TCP flows against non-responsive flows.
+
+This SFB implementation maintains 8 levels of 16 bins each for accounting.
+Each flow is mapped into a bin of each level using a per-level hash value.
+
+Every bin maintains a marking probability, which gets increased or decreased
+based on bin occupancy. If the number of packets exceeds the size of that
+bin, the marking probability is increased. If the number drops to zero, it
+is decreased.
+
+The marking probability is based on the minimum value of all bins a flow is
+mapped into, thus, when a flow does not respond to marking or gradual packet
+drops, the marking probability quickly reaches one.
+
+In this case, the flow is rate-limited to
+.B penalty_rate
+packets per second.
+
+.SH LIMITATIONS
+
+Due to SFBs nature, it is possible for responsive flows to share all of its bins
+with a non-responsive flow, causing the responsive flow to be misidentified as
+being non-responsive.
+
+The probability of a responsive flow to be misidentified is dependent on
+the number of non-responsive flows, M. It is (1 - (1 - (1 / 16.0)) ** M) **8,
+so for example with 10 non-responsive flows approximately 0.2% of responsive flows
+will be misidentified.
+
+To mitigate this, SFB performs performs periodic re-hashing to avoid
+misclassification for prolonged periods of time.
+
+The default hashing method will use source and destination ip addresses and port numbers
+if possible, and also supports tunneling protocols.
+Alternatively, an external classifier can be configured, too.
+
+.SH PARAMETERS
+.TP
+rehash
+Time interval in milliseconds when queue perturbation occurs to avoid erroneously
+detecting unrelated, responsive flows as being part of a non-responsive flow for
+prolonged periods of time.
+Defaults to 10 minutes.
+.TP
+db
+Double buffering warmup wait time, in milliseconds.
+To avoid destroying the probability history when rehashing is performed, this
+implementation maintains a second set of levels/bins as described in section
+4.4 of the SFB reference.
+While one set is used to manage the queue, a second set is warmed up:
+Whenever a flow is then determined to be non-responsive, the marking
+probabilities in the second set are updated. When the rehashing
+happens, these bins will be used to manage the queue and all non-responsive
+flows can be rate-limited immediately.
+This value determines how much time has to pass before the 2nd set
+will start to be warmed up.
+Defaults to one minute, should be lower than
+.B
+rehash.
+.TP
+limit
+Hard limit on the real (not average) total queue size in packets.
+Further packets are dropped. Defaults to the transmit queue length of the
+device the qdisc is attached to.
+.TP
+max
+Maximum length of a buckets queue, in packets, before packets start being
+dropped. Should be sightly larger than
+.B target
+, but should not be set to values exceeding 1.5 times that of
+.B target .
+Defaults to 25.
+.TP
+target
+The desired average bin length. If the bin queue length reaches this value,
+the marking probability is increased by
+.B increment.
+The default value depends on the
+.B max
+setting, with max set to 25
+.B target
+will default to 20.
+.TP
+increment
+A value used to increase the marking probability when the queue appears
+to be over-used. Must be between 0 and 1.0. Defaults to 0.00050.
+.TP
+decrement
+Value used to decrease the marking probability when the queue is found
+to be empty. Must be between 0 and 1.0.
+Defaults to 0.00005.
+.TP
+penalty_rate
+The maximum number of packets belonging to flows identified as being
+non-responsive that can be enqueued per second. Once this number has been
+reached, further packets of such non-responsive flows are dropped.
+Set this to a reasonable fraction of your uplink throughput; the
+default value of 10 packets is probably too small.
+.TP
+penalty_burst
+The number of packets a flow is permitted to exceed the penalty rate before packets
+start being dropped.
+Defaults to 20 packets.
+
+.SH STATISTICS
+
+This qdisc exposes additional statistics via 'tc -s qdisc' output.
+These are:
+.TP
+earlydrop
+The number of packets dropped before a per-flow queue was full.
+.TP
+ratedrop
+The number of packets dropped because of rate-limiting.
+If this value is high, there are many non-reactive flows being
+sent through sfb. In such cases, it might be better to
+embed sfb within a classful qdisc to better control such
+flows using a different, shaping qdisc.
+.TP
+bucketdrop
+The number of packets dropped because a per-flow queue was full.
+High bucketdrop may point to a high number of aggressive, short-lived
+flows.
+.TP
+queuedrop
+The number of packets dropped due to reaching limit. This should normally be 0.
+.TP
+marked
+The number of packets marked with ECN.
+.TP
+maxqlen
+The length of the current longest per-flow (virtual) queue.
+.TP
+maxprob
+The maximum per-flow drop probability. 1 means that some
+flows have been detected as non-reactive.
+
+.SH NOTES
+
+SFB automatically enables use of Explicit Congestion Notification (ECN).
+Also, this SFB implementation does not queue packets itself.
+Rather, packets are enqueued to the inner qdisc (defaults to pfifo).
+Because sfb maintains virtual queue states, the inner qdisc must not
+drop a packet previously queued.
+Furthermore, if a buckets queue has a very high marking rate,
+this implementation will start dropping packets instead of
+marking them, as such a situation points to either bad congestion, or an
+unresponsive flow.
+
+.SH EXAMPLE & USAGE
+
+To attach to interface $DEV, using default options:
+.P
+# tc qdisc add dev $DEV handle 1: root sfb
+
+Only use destination ip addresses for assigning packets to bins, perturbing
+hash results every 10 minutes:
+.P
+# tc filter add dev $DEV parent 1: handle 1 flow hash keys dst perturb 600
+
+.SH SEE ALSO
+.BR tc (8),
+.BR tc-red (8),
+.BR tc-sfq (8)
+.SH SOURCES
+.TP
+o
+W. Feng, D. Kandlur, D. Saha, K. Shin, BLUE: A New Class of Active Queue Management Algorithms,
+U. Michigan CSE-TR-387-99, April 1999.
+
+.SH AUTHORS
+
+This SFB implementation was contributed by Juliusz Chroboczek and Eric Dumazet.
diff --git a/iproute2/man/man8/tc-sfq.8 b/iproute2/man/man8/tc-sfq.8
new file mode 100644
index 0000000..ec4d8b8
--- /dev/null
+++ b/iproute2/man/man8/tc-sfq.8
@@ -0,0 +1,222 @@
+.TH TC 8 "24 January 2012" "iproute2" "Linux"
+.SH NAME
+sfq \- Stochastic Fairness Queueing
+.SH SYNOPSIS
+.B tc qdisc ...
+.B [ divisor
+hashtablesize
+.B ] [ limit
+packets
+.B ] [ perturb
+seconds
+.B ] [ quantum
+bytes
+.B ] [ flows
+number
+.B ] [ depth
+number
+.B ] [ headdrop
+.B ] [ redflowlimit
+bytes
+.B ] [ min
+bytes
+.B ] [ max
+bytes
+.B ] [ avpkt
+bytes
+.B ] [ burst
+packets
+.B ] [ probability
+P
+.B ] [ ecn
+.B ] [ harddrop ]
+.SH DESCRIPTION
+
+Stochastic Fairness Queueing is a classless queueing discipline available for
+traffic control with the
+.BR tc (8)
+command.
+
+SFQ does not shape traffic but only schedules the transmission of packets, based on 'flows'.
+The goal is to ensure fairness so that each flow is able to send data in turn, thus preventing
+any single flow from drowning out the rest.
+
+This may in fact have some effect in mitigating a Denial of Service attempt.
+
+SFQ is work-conserving and therefore always delivers a packet if it has one available.
+.SH ALGORITHM
+On enqueueing, each packet is assigned to a hash bucket, based on the packets hash value.
+This hash value is either obtained from an external flow classifier (use
+.B
+tc filter
+to set them), or a default internal classifier if no external classifier has been configured.
+
+When the internal classifier is used, sfq uses
+.TP
+(i)
+Source address
+.TP
+(ii)
+Destination address
+.TP
+(iii)
+Source and Destination port
+.P
+If these are available. SFQ knows about ipv4 and ipv6 and also UDP, TCP and ESP.
+Packets with other protocols are hashed based on the 32bits representation of their
+destination and source. A flow corresponds mostly to a TCP/IP connection.
+
+Each of these buckets should represent a unique flow. Because multiple flows may
+get hashed to the same bucket, sfqs internal hashing algorithm may be perturbed at configurable
+intervals so that the unfairness lasts only for a short while. Perturbation may
+however cause some inadvertent packet reordering to occur. After linux-3.3, there is
+no packet reordering problem, but possible packet drops if rehashing hits one limit
+(number of flows or packets per flow)
+
+When dequeuing, each hashbucket with data is queried in a round robin fashion.
+
+Before linux-3.3, the compile time maximum length of the SFQ is 128 packets, which can be spread over
+at most 128 buckets of 1024 available. In case of overflow, tail-drop is performed
+on the fullest bucket, thus maintaining fairness.
+
+After linux-3.3, maximum length of SFQ is 65535 packets, and divisor limit is 65536.
+In case of overflow, tail-drop is performed on the fullest bucket, unless headdrop was requested.
+
+.SH PARAMETERS
+.TP
+divisor
+Can be used to set a different hash table size, available from kernel 2.6.39 onwards.
+The specified divisor must be a power of two and cannot be larger than 65536.
+Default value: 1024.
+.TP
+limit
+Upper limit of the SFQ. Can be used to reduce the default length of 127 packets.
+After linux-3.3, it can be raised.
+.TP
+depth
+Limit of packets per flow (after linux-3.3). Default to 127 and can be lowered.
+.TP
+perturb
+Interval in seconds for queue algorithm perturbation. Defaults to 0, which means that
+no perturbation occurs. Do not set too low for each perturbation may cause some packet
+reordering or losses. Advised value: 60
+This value has no effect when external flow classification is used.
+Its better to increase divisor value to lower risk of hash collisions.
+.TP
+quantum
+Amount of bytes a flow is allowed to dequeue during a round of the round robin process.
+Defaults to the MTU of the interface which is also the advised value and the minimum value.
+.TP
+flows
+After linux-3.3, it is possible to change the default limit of flows.
+Default value is 127
+.TP
+headdrop
+Default SFQ behavior is to perform tail-drop of packets from a flow.
+You can ask a headdrop instead, as this is known to provide a better feedback for TCP flows.
+.TP
+redflowlimit
+Configure the optional RED module on top of each SFQ flow.
+Random Early Detection principle is to perform packet marks or drops in a probabilistic way.
+(man tc-red for details about RED)
+.nf
+redflowlimit configures the hard limit on the real (not average) queue size per SFQ flow in bytes.
+.fi
+.TP
+min
+Average queue size at which marking becomes a possibility. Defaults to
+.B max
+/3
+.TP
+max
+At this average queue size, the marking probability is maximal. Defaults to
+.B redflowlimit
+/4
+.TP
+probability
+Maximum probability for marking, specified as a floating point number from 0.0 to 1.0. Default value is 0.02
+.TP
+avpkt
+Specified in bytes. Used with burst to determine the time constant for average queue size calculations. Default value is 1000
+.TP
+burst
+Used for determining how fast the average queue size is influenced by the real queue size.
+.nf
+Default value is :
+.B (2 * min + max) / (3 * avpkt)
+.fi
+.TP
+ecn
+RED can either 'mark' or 'drop'. Explicit Congestion
+Notification allows RED to notify remote hosts that their rate exceeds the
+amount of bandwidth available. Non-ECN capable hosts can only be notified by
+dropping a packet. If this parameter is specified, packets which indicate
+that their hosts honor ECN will only be marked and not dropped, unless the
+queue size hits
+.B depth
+packets.
+.TP
+harddrop
+If average flow queue size is above
+.B max
+bytes, this parameter forces a drop instead of ecn marking.
+.SH EXAMPLE & USAGE
+
+To attach to device ppp0:
+.P
+# tc qdisc add dev ppp0 root sfq
+.P
+Please note that SFQ, like all non-shaping (work-conserving) qdiscs, is only useful
+if it owns the queue.
+This is the case when the link speed equals the actually available bandwidth. This holds
+for regular phone modems, ISDN connections and direct non-switched ethernet links.
+.P
+Most often, cable modems and DSL devices do not fall into this category. The same holds
+for when connected to a switch and trying to send data to a congested segment also
+connected to the switch.
+.P
+In this case, the effective queue does not reside within Linux and is therefore not
+available for scheduling.
+.P
+Embed SFQ in a classful qdisc to make sure it owns the queue.
+
+It is possible to use external classifiers with sfq, for example to hash traffic based only
+on source/destination ip addresses:
+.P
+# tc filter add ... flow hash keys src,dst perturb 30 divisor 1024
+.P
+Note that the given divisor should match the one used by sfq. If you have
+changed the sfq default of 1024, use the same value for the flow hash filter, too.
+
+.P
+Example of sfq with optional RED mode :
+.P
+# tc qdisc add dev eth0 parent 1:1 handle 10: sfq limit 3000 flows 512 divisor 16384
+ redflowlimit 100000 min 8000 max 60000 probability 0.20 ecn headdrop
+
+.SH SOURCE
+.TP
+o
+Paul E. McKenney "Stochastic Fairness Queuing",
+IEEE INFOCOMM'90 Proceedings, San Francisco, 1990.
+
+.TP
+o
+Paul E. McKenney "Stochastic Fairness Queuing",
+"Interworking: Research and Experience", v.2, 1991, p.113-131.
+
+.TP
+o
+See also:
+M. Shreedhar and George Varghese "Efficient Fair
+Queuing using Deficit Round Robin", Proc. SIGCOMM 95.
+
+.SH SEE ALSO
+.BR tc (8),
+.BR tc-red (8)
+
+.SH AUTHORS
+Alexey N. Kuznetsov, <kuznet@ms2.inr.ac.ru>,
+Eric Dumazet <eric.dumazet@gmail.com>.
+.P
+This manpage maintained by bert hubert <ahu@ds9a.nl>
diff --git a/iproute2/man/man8/tc-stab.8 b/iproute2/man/man8/tc-stab.8
new file mode 100644
index 0000000..02caa7d
--- /dev/null
+++ b/iproute2/man/man8/tc-stab.8
@@ -0,0 +1,163 @@
+.TH STAB 8 "31 October 2011" iproute2 Linux
+.
+.SH NAME
+tc\-stab \- Generic size table manipulations
+.
+.SH SYNOPSIS
+.nf
+tc qdisc add ... stab
+.RS 4
+[ \fBmtu\fR BYTES ] [ \fBtsize\fR SLOTS ]
+[ \fBmpu\fR BYTES ] [ \fBoverhead\fR BYTES ]
+[ \fBlinklayer\fR { adsl | atm | ethernet } ] ...
+.RE
+.fi
+
+.SH OPTIONS
+For the description of BYTES \- please refer to the \fBUNITS\fR
+section of \fBtc\fR(8).
+
+.IP \fBmtu\fR 4
+.br
+maximum packet size we create size table for, assumed 2048 if not specified explicitly
+.IP \fBtsize\fR
+.br
+required table size, assumed 512 if not specified explicitly
+.IP \fBmpu\fR
+.br
+minimum packet size used in computations
+.IP \fBoverhead\fR
+.br
+per\-packet size overhead (can be negative) used in computations
+.IP \fBlinklayer\fR
+.br
+required linklayer specification.
+.PP
+.
+.SH DESCRIPTION
+.
+Size tables allow manipulation of packet sizes, as seen by the whole scheduler
+framework (of course, the actual packet size remains the same). Adjusted packet
+size is calculated only once \- when a qdisc enqueues the packet. Initial root
+enqueue initializes it to the real packet's size.
+
+Each qdisc can use a different size table, but the adjusted size is stored in
+an area shared by whole qdisc hierarchy attached to the interface. The effect is
+that if you have such a setup, the last qdisc with a stab in a chain "wins". For
+example, consider HFSC with simple pfifo attached to one of its leaf classes.
+If that pfifo qdisc has stab defined, it will override lengths calculated
+during HFSC's enqueue; and in turn, whenever HFSC tries to dequeue a packet, it
+will use a potentially invalid size in its calculations. Normal setups will
+usually include stab defined only on root qdisc, but further overriding gives
+extra flexibility for less usual setups.
+
+The initial size table is calculated by \fBtc\fR tool using \fBmtu\fR and
+\fBtsize\fR parameters. The algorithm sets each slot's size to the smallest
+power of 2 value, so the whole \fBmtu\fR is covered by the size table. Neither
+\fBtsize\fR, nor \fBmtu\fR have to be power of 2 value, so the size
+table will usually support more than is required by \fBmtu\fR.
+
+For example, with \fBmtu\fR\~=\~1500 and \fBtsize\fR\~=\~128, a table with 128
+slots will be created, where slot 0 will correspond to sizes 0\-16, slot 1 to
+17\~\-\~32, \&..., slot 127 to 2033\~\-\~2048. Sizes assigned to each slot
+depend on \fBlinklayer\fR parameter.
+
+Stab calculation is also safe for an unusual case, when a size assigned to a
+slot would be larger than 2^16\-1 (you will lose the accuracy though).
+
+During the kernel part of packet size adjustment, \fBoverhead\fR will be added
+to original size, and then slot will be calculated. If the size would cause
+overflow, more than 1 slot will be used to get the final size. This of course
+will affect accuracy, but it's only a guard against unusual situations.
+
+Currently there are two methods of creating values stored in the size table \-
+ethernet and atm (adsl):
+
+.IP ethernet 4
+.br
+This is basically 1\-1 mapping, so following our example from above
+(disregarding \fBmpu\fR for a moment) slot 0 would have 8, slot 1 would have 16
+and so on, up to slot 127 with 2048. Note, that \fBmpu\fR\~>\~0 must be
+specified, and slots that would get less than specified by \fBmpu\fR will get
+\fBmpu\fR instead. If you don't specify \fBmpu\fR, the size table will not be
+created at all (it wouldn't make any difference), although any \fBoverhead\fR
+value will be respected during calculations.
+.IP "atm, adsl"
+.br
+ATM linklayer consists of 53 byte cells, where each of them provides 48 bytes
+for payload. Also all the cells must be fully utilized, thus the last one is
+padded if/as necessary.
+
+When the size table is calculated, adjusted size that fits properly into lowest
+amount of cells is assigned to a slot. For example, a 100 byte long packet
+requires three 48\-byte payloads, so the final size would require 3 ATM cells
+\- 159 bytes.
+
+For ATM size tables, 16\~bytes sized slots are perfectly enough. The default
+values of \fBmtu\fR and \fBtsize\fR create 4\~bytes sized slots.
+.PP
+.
+.SH "TYPICAL OVERHEADS"
+The following values are typical for different adsl scenarios (based on
+\fB[1]\fR and \fB[2]\fR):
+
+.nf
+LLC based:
+.RS 4
+PPPoA \- 14 (PPP \- 2, ATM \- 12)
+PPPoE \- 40+ (PPPoE \- 8, ATM \- 18, ethernet 14, possibly FCS \- 4+padding)
+Bridged \- 32 (ATM \- 18, ethernet 14, possibly FCS \- 4+padding)
+IPoA \- 16 (ATM \- 16)
+.RE
+
+VC Mux based:
+.RS 4
+PPPoA \- 10 (PPP \- 2, ATM \- 8)
+PPPoE \- 32+ (PPPoE \- 8, ATM \- 10, ethernet 14, possibly FCS \- 4+padding)
+Bridged \- 24+ (ATM \- 10, ethernet 14, possibly FCS \- 4+padding)
+IPoA \- 8 (ATM \- 8)
+.RE
+.fi
+There are a few important things regarding the above overheads:
+.
+.IP \(bu 4
+IPoA in LLC case requires SNAP, instead of LLC\-NLPID (see rfc2684) \- this is
+the reason why it actually takes more space than PPPoA.
+.IP \(bu
+In rare cases, FCS might be preserved on protocols that include Ethernet frames
+(Bridged and PPPoE). In such situation, any Ethernet specific padding
+guaranteeing 64 bytes long frame size has to be included as well (see RFC2684).
+In the other words, it also guarantees that any packet you send will take
+minimum 2 atm cells. You should set \fBmpu\fR accordingly for that.
+.IP \(bu
+When the size table is consulted, and you're shaping traffic for the sake of
+another modem/router, an Ethernet header (without padding) will already be added
+to initial packet's length. You should compensate for that by subtracting 14
+from the above overheads in this case. If you're shaping directly on the router
+(for example, with speedtouch usb modem) using ppp daemon, you're using raw ip
+interface without underlying layer2, so nothing will be added.
+
+For more thorough explanations, please see \fB[1]\fR and \fB[2]\fR.
+.
+.SH "ETHERNET CARDS CONSIDERATIONS"
+.
+It's often forgotten that modern network cards (even cheap ones on desktop
+motherboards) and/or their drivers often support different offloading
+mechanisms. In the context of traffic shaping, 'tso' and 'gso' might cause
+undesirable effects, due to massive TCP segments being considered during
+traffic shaping (including stab calculations). For slow uplink interfaces,
+it's good to use \fBethtool\fR to turn off offloading features.
+.
+.SH "SEE ALSO"
+.
+\fBtc\fR(8), \fBtc\-hfsc\fR(7), \fBtc\-hfsc\fR(8),
+.br
+\fB[1]\fR http://ace\-host.stuart.id.au/russell/files/tc/tc\-atm/
+.br
+\fB[2]\fR http://www.faqs.org/rfcs/rfc2684.html
+
+Please direct bugreports and patches to: <net...@vger.kernel.org>
+.
+.SH "AUTHOR"
+.
+Manpage created by Michal Soltys (sol...@ziu.info)
diff --git a/iproute2/man/man8/tc-tbf.8 b/iproute2/man/man8/tc-tbf.8
new file mode 100644
index 0000000..d721b5d
--- /dev/null
+++ b/iproute2/man/man8/tc-tbf.8
@@ -0,0 +1,141 @@
+.TH TC 8 "13 December 2001" "iproute2" "Linux"
+.SH NAME
+tbf \- Token Bucket Filter
+.SH SYNOPSIS
+.B tc qdisc ... tbf rate
+rate
+.B burst
+bytes/cell
+.B ( latency
+ms
+.B | limit
+bytes
+.B ) [ mpu
+bytes
+.B [ peakrate
+rate
+.B mtu
+bytes/cell
+.B ] ]
+.P
+burst is also known as buffer and maxburst. mtu is also known as minburst.
+.SH DESCRIPTION
+
+The Token Bucket Filter is a classful queueing discipline available for
+traffic control with the
+.BR tc (8)
+command.
+
+TBF is a pure shaper and never schedules traffic. It is non-work-conserving and may throttle
+itself, although packets are available, to ensure that the configured rate is not exceeded.
+It is able to shape up to 1mbit/s of normal traffic with ideal minimal burstiness,
+sending out data exactly at the configured rates.
+
+Much higher rates are possible but at the cost of losing the minimal burstiness. In that
+case, data is on average dequeued at the configured rate but may be sent much faster at millisecond
+timescales. Because of further queues living in network adaptors, this is often not a problem.
+
+.SH ALGORITHM
+As the name implies, traffic is filtered based on the expenditure of
+.B tokens.
+Tokens roughly correspond to bytes, with the additional constraint
+that each packet consumes some tokens, no matter how small it is. This
+reflects the fact that even a zero-sized packet occupies the link for
+some time.
+
+On creation, the TBF is stocked with tokens which correspond to the amount of traffic that can be burst
+in one go. Tokens arrive at a steady rate, until the bucket is full.
+
+If no tokens are available, packets are queued, up to a configured limit. The TBF now
+calculates the token deficit, and throttles until the first packet in the queue can be sent.
+
+If it is not acceptable to burst out packets at maximum speed, a peakrate can be configured
+to limit the speed at which the bucket empties. This peakrate is implemented as a second TBF
+with a very small bucket, so that it doesn't burst.
+
+To achieve perfection, the second bucket may contain only a single packet, which leads to
+the earlier mentioned 1mbit/s limit.
+
+This limit is caused by the fact that the kernel can only throttle for at minimum 1 'jiffy', which depends
+on HZ as 1/HZ. For perfect shaping, only a single packet can get sent per jiffy - for HZ=100, this means 100
+packets of on average 1000 bytes each, which roughly corresponds to 1mbit/s.
+
+.SH PARAMETERS
+See
+.BR tc (8)
+for how to specify the units of these values.
+.TP
+limit or latency
+Limit is the number of bytes that can be queued waiting for tokens to become
+available. You can also specify this the other way around by setting the
+latency parameter, which specifies the maximum amount of time a packet can
+sit in the TBF. The latter calculation takes into account the size of the
+bucket, the rate and possibly the peakrate (if set). These two parameters
+are mutually exclusive.
+.TP
+burst
+Also known as buffer or maxburst.
+Size of the bucket, in bytes. This is the maximum amount of bytes that tokens can be available for instantaneously.
+In general, larger shaping rates require a larger buffer. For 10mbit/s on Intel, you need at least 10kbyte buffer
+if you want to reach your configured rate!
+
+If your buffer is too small, packets may be dropped because more tokens arrive per timer tick than fit in your bucket.
+The minimum buffer size can be calculated by dividing the rate by HZ.
+
+Token usage calculations are performed using a table which by default has a resolution of 8 packets.
+This resolution can be changed by specifying the
+.B cell
+size with the burst. For example, to specify a 6000 byte buffer with a 16
+byte cell size, set a burst of 6000/16. You will probably never have to set
+this. Must be an integral power of 2.
+.TP
+mpu
+A zero-sized packet does not use zero bandwidth. For ethernet, no packet uses less than 64 bytes. The Minimum Packet Unit
+determines the minimal token usage (specified in bytes) for a packet. Defaults to zero.
+.TP
+rate
+The speed knob. See remarks above about limits! See
+.BR tc (8)
+for units.
+.PP
+Furthermore, if a peakrate is desired, the following parameters are available:
+
+.TP
+peakrate
+Maximum depletion rate of the bucket. The peakrate does not
+need to be set, it is only necessary if perfect millisecond timescale
+shaping is required.
+
+.TP
+mtu/minburst
+Specifies the size of the peakrate bucket. For perfect accuracy, should be set to the MTU of the interface.
+If a peakrate is needed, but some burstiness is acceptable, this size can be raised. A 3000 byte minburst
+allows around 3mbit/s of peakrate, given 1000 byte packets.
+
+Like the regular burstsize you can also specify a
+.B cell
+size.
+.SH EXAMPLE & USAGE
+
+To attach a TBF with a sustained maximum rate of 0.5mbit/s, a peakrate of 1.0mbit/s,
+a 5kilobyte buffer, with a pre-bucket queue size limit calculated so the TBF causes
+at most 70ms of latency, with perfect peakrate behaviour, issue:
+.P
+# tc qdisc add dev eth0 handle 10: root tbf rate 0.5mbit \\
+ burst 5kb latency 70ms peakrate 1mbit \\
+ minburst 1540
+.P
+To attach an inner qdisc, for example sfq, issue:
+.P
+# tc qdisc add dev eth0 parent 10:1 handle 100: sfq
+.P
+Without inner qdisc TBF queue acts as bfifo. If the inner qdisc is changed
+the limit/latency is not effective anymore.
+.P
+
+.SH SEE ALSO
+.BR tc (8)
+
+.SH AUTHOR
+Alexey N. Kuznetsov, <kuznet@ms2.inr.ac.ru>. This manpage maintained by
+bert hubert <ahu@ds9a.nl>
diff --git a/iproute2/man/man8/tc-tcindex.8 b/iproute2/man/man8/tc-tcindex.8
new file mode 100644
index 0000000..7fcf825
--- /dev/null
+++ b/iproute2/man/man8/tc-tcindex.8
@@ -0,0 +1,58 @@
+.TH "Traffic control index filter" 8 "21 Oct 2015" "iproute2" "Linux"
+
+.SH NAME
+tcindex \- traffic control index filter
+.SH SYNOPSIS
+.in +8
+.ti -8
+.BR tc " " filter " ... " tcindex " [ " hash
+.IR SIZE " ] [ "
+.B mask
+.IR MASK " ] [ "
+.B shift
+.IR SHIFT " ] [ "
+.BR pas_on " | " fall_through " ] [ " classid
+.IR CLASSID " ] [ "
+.B action
+.BR ACTION_SPEC " ]"
+.SH DESCRIPTION
+This filter allows to match packets based on their
+.B tcindex
+field value, i.e. the combination of the DSCP and ECN fields as present in IPv4
+and IPv6 headers.
+.SH OPTIONS
+.TP
+.BI action " ACTION_SPEC"
+Apply an action from the generic actions framework on matching packets.
+.TP
+.BI classid " CLASSID"
+Push matching packets into the class identified by
+.IR CLASSID .
+.TP
+.BI hash " SIZE"
+Hash table size in entries to use. Defaults to 64.
+.TP
+.BI mask " MASK"
+An optional bitmask to binary
+.BR AND " to the packet's " tcindex
+field before use.
+.TP
+.BI shift " SHIFT"
+The number of bits to right-shift a packet's
+.B tcindex
+value before use. If a
+.B mask
+has been set, masking is done before shifting.
+.TP
+.B pass_on
+If this flag is set, failure to find a class for the resulting ID will make the
+filter fail and lead to the next filter being consulted.
+.TP
+.B fall_through
+This is the opposite of
+.B pass_on
+and the default. The filter will classify the packet even if there is no class
+present for the resulting class ID.
+
+.SH SEE ALSO
+.BR tc (8)
diff --git a/iproute2/man/man8/tc-u32.8 b/iproute2/man/man8/tc-u32.8
new file mode 100644
index 0000000..47c8f2d
--- /dev/null
+++ b/iproute2/man/man8/tc-u32.8
@@ -0,0 +1,663 @@
+.TH "Universal 32bit classifier in tc" 8 "25 Sep 2015" "iproute2" "Linux"
+
+.SH NAME
+u32 \- universal 32bit traffic control filter
+.SH SYNOPSIS
+.in +8
+.ti -8
+.BR tc " " filter " ... [ " handle
+.IR HANDLE " ] "
+.B u32
+.IR OPTION_LIST " [ "
+.B offset
+.IR OFFSET " ] [ "
+.B hashkey
+.IR HASHKEY " ] [ "
+.B classid
+.IR CLASSID " ] [ "
+.B divisor
+.IR uint_value " ] [ "
+.B order
+.IR u32_value " ] [ "
+.B ht
+.IR HANDLE " ] [ "
+.B sample
+.IR SELECTOR " [ "
+.B divisor
+.IR uint_value " ] ] [ "
+.B link
+.IR HANDLE " ] [ "
+.B indev
+.IR ifname " ] [ "
+.BR help " ]"
+
+.ti -8
+.IR HANDLE " := { "
+\fIu12_hex_htid\fB:\fR[\fIu8_hex_hash\fB:\fR[\fIu12_hex_nodeid\fR] | \fB0x\fIu32_hex_value\fR }
+
+.ti -8
+.IR OPTION_LIST " := [ " OPTION_LIST " ] " OPTION
+
+.ti -8
+.IR HASHKEY " := [ "
+.B mask
+.IR u32_hex_value " ] [ "
+.B at
+.IR 4*int_value " ]"
+
+.ti -8
+.IR CLASSID " := { "
+.BR root " | "
+.BR none " | "
+[\fIu16_major\fR]\fB:\fIu16_minor\fR | \fIu32_hex_value\fR }
+
+.ti -8
+.IR OFFSET " := [ "
+.B plus
+.IR int_value " ] [ "
+.B at
+.IR 2*int_value " ] [ "
+.B mask
+.IR u16_hex_value " ] [ "
+.B shift
+.IR int_value " ] [ "
+.BR eat " ]"
+
+.ti -8
+.IR OPTION " := { "
+.B match
+.IR SELECTOR " | "
+.B action
+.IR ACTION " } "
+
+.ti -8
+.IR SELECTOR " := { "
+.B u32
+.IR VAL_MASK_32 " | "
+.B u16
+.IR VAL_MASK_16 " | "
+.B u8
+.IR VAL_MASK_8 " | "
+.B ip
+.IR IP " | "
+.B ip6
+.IR IP6 " | { "
+.BR tcp " | " udp " } "
+.IR TCPUDP " | "
+.B icmp
+.IR ICMP " | "
+.B mark
+.IR VAL_MASK_32 " | "
+.B ether
+.IR ETHER " }"
+
+.ti -8
+.IR IP " := { { "
+.BR src " | " dst " } { " default " | " any " | " all " | "
+.IR ip_address " [ "
+.BR / " { "
+.IR prefixlen " | " netmask " } ] } " AT " | { "
+.BR dsfield " | " ihl " | " protocol " | " precedence " | "
+.BR icmp_type " | " icmp_code " } "
+.IR VAL_MASK_8 " | { "
+.BR sport " | " dport " } "
+.IR VAL_MASK_16 " | "
+.BR nofrag " | " firstfrag " | " df " | " mf " }"
+
+.ti -8
+.IR IP6 " := { { "
+.BR src " | " dst " } { " default " | " any " | " all " | "
+.IR ip6_address " [/" prefixlen " ] } " AT " | "
+.B priority
+.IR VAL_MASK_8 " | { "
+.BR protocol " | " icmp_type " | " icmp_code " } "
+.IR VAL_MASK_8 " | "
+.B flowlabel
+.IR VAL_MASK_32 " | { "
+.BR sport " | " dport " } "
+.IR VAL_MASK_16 " }"
+
+.ti -8
+.IR TCPUDP " := { "
+.BR src " | " dst " } "
+.I VAL_MASK_16
+
+.ti -8
+.IR ICMP " := { "
+.B type
+.IR VAL_MASK_8 " | "
+.B code
+.IR VAL_MASK_8 " }"
+
+.ti -8
+.IR ETHER " := { "
+.BR src " | " dst " } "
+.IR ether_address " " AT
+
+.ti -8
+.IR VAL_MASK_32 " := " u32_value " " u32_hex_mask " [ " AT " ]"
+
+.ti -8
+.IR VAL_MASK_16 " := " u16_value " " u16_hex_mask " [ " AT " ]"
+
+.ti -8
+.IR VAL_MASK_8 " := " u8_value " " u8_hex_mask " [ " AT " ]"
+
+.ti -8
+.IR AT " := [ "
+.BR at " [ " nexthdr+ " ] "
+.IR int_value " ]"
+.SH DESCRIPTION
+The Universal/Ugly 32bit filter allows to match arbitrary bitfields in the
+packet. Due to breaking everything down to values, masks and offsets, It is
+equally powerful and hard to use. Luckily many abstracting directives are
+present which allow defining rules on a higher level and therefore free the
+user from having to fiddle with bits and masks in many cases.
+
+There are two general modes of invocation: The first mode creates a new filter
+to delegate packets to different destinations. Apart from the obvious ones,
+namely classifying the packet by specifying a
+.I CLASSID
+or calling an
+.BR action ,
+one may
+.B link
+one filter to another one (or even a list of them), effectively organizing
+filters into a tree-like hierarchy.
+
+Typically filter delegation is done by means of a hash table, which leads to the
+second mode of invocation: it merely serves to set up these hash tables. Filters
+can select a hash table and provide a key selector from which a hash is to be
+computed and used as key to lookup the table's bucket which contains filters for
+further processing. This is useful if a high number of filters is in use, as the
+overhead of performing the hash operation and table lookup becomes negligible in
+that case. Using hashtables with
+.B u32
+basically involves the following pattern:
+.IP (1) 4
+Creating a new hash table, specifying it's size using the
+.B divisor
+parameter and ideally a handle by which the table can be identified. If the
+latter is not given, the kernel chooses one on it's own, which has to be
+guessed later.
+.IP (2) 4
+Creating filters which link to the created table in
+.I (1)
+using the
+.B link
+parameter and defining the packet data which the kernel will use to calculate
+the
+.BR hashkey .
+.IP (3) 4
+Adding filters to buckets in the hash table from
+.IR (1) .
+In order to avoid having to know how exactly the kernel creates the hash key,
+there is the
+.B sample
+parameter, which gives sample data to hash and thereby define the table bucket
+the filter should be added to.
+
+.RE
+In fact, even if not explicitly requested
+.B u32
+creates a hash table for every
+.B priority
+a filter is being added with. The table's size is 1 though, so it is in fact
+merely a linked list.
+.SH VALUES
+Options and selectors require values to be specified in a specific format, which
+is often non-intuitive. Therefore the terminals in
+.I SYNOPSIS
+have been given descriptive names to indicate the required format and/or maximum
+allowed numeric value: Prefixes
+.IR u32 ", " u16 " and " u8
+indicate four, two and single byte unsigned values. E.g.
+.I u16
+indicates a two byte-sized value in range between 0 and 65535 (0xFFFF)
+inclusive. A prefix of
+.I int
+indicates a four byte signed value. A middle part of
+.I _hex_
+indicates that the value is parsed in hexadecimal format. Otherwise, the
+value's base is automatically detected, i.e. values prefixed with
+.I 0x
+are considered hexadecimal, a leading
+.I 0
+indicates octal format and decimal format otherwise. There are some values with
+special formatting as well:
+.IR ip_address " and " netmask
+are in dotted-quad formatting as usual for IPv4 addresses. An
+.I ip6_address
+is specified in common, colon-separated hexadecimal format. Finally,
+.I prefixlen
+is an unsigned, decimal integer value in range from 0 to the address width in
+bits (32 for IPv4 and 128 for IPv6).
+
+Sometimes values need to be dividable by a certain number. In that case a name
+of the form
+.I N*val
+was chosen, indicating that
+.I val
+must be dividable by
+.IR N .
+Or the other way around: the resulting value must be a multiple of
+.IR N .
+.SH OPTIONS
+.B U32
+recognizes the following options:
+.TP
+.BI handle " HANDLE"
+The handle is used to reference a filter and therefore must be unique. It
+consists of a hash table identifier
+.B htid
+and optional
+.B hash
+(which identifies the hash table's bucket) and
+.BR nodeid .
+All these values are parsed as unsigned, hexadecimal numbers with length 12bits
+(
+.BR htid " and " nodeid )
+or 8bits (
+.BR hash ).
+Alternatively one may specify a single, 32bit long hex number which contains
+the three fields bits in concatenated form. Other than the fields themselves, it
+has to be prefixed by
+.BR 0x .
+.TP
+.BI offset " OFFSET"
+Set an offset which defines where matches of subsequent filters are applied to.
+Therefore this option is useful only when combined with
+.BR link " or a combination of " ht " and " sample .
+The offset may be given explicitly by using the
+.B plus
+keyword, or extracted from the packet data with
+.BR at .
+It is possible to mangle the latter using
+.BR mask " and/or " shift
+keywords. By default, this offset is recorded but not implicitly applied. It is
+used only to substitute the
+.B nexthdr+
+statement. Using the keyword
+.B eat
+though inverses this behaviour: the offset is applied always, and
+.B nexthdr+
+will fall back to zero.
+.TP
+.BI hashkey " HASHKEY"
+Spefify what packet data to use to calculate a hash key for bucket lookup. The
+kernel adjusts the value according to the hash table's size. For this to work,
+the option
+.B link
+must be given.
+.TP
+.BI classid " CLASSID"
+Classify matching packets into the given
+.IR CLASSID ,
+which consists of either 16bit
+.BR major " and " minor
+numbers or a single 32bit value combining both.
+.TP
+.BI divisor " u32_value"
+Specify a modulo value. Used when creating hash tables to define their size or
+for declaring a
+.B sample
+to calculate hash table keys from. Must be a power of two with exponent not
+exceeding eight.
+.TP
+.BI order " u32_value"
+A value to order filters by, ascending. Conflicts with
+.B handle
+which serves the same purpose.
+.TP
+.BI sample " SELECTOR"
+Used together with
+.B ht
+to specify which bucket to add this filter to. This allows one to avoid having
+to know how exactly the kernel calculates hashes. The additional
+.B divisor
+defaults to 256, so must be given for hash tables of different size.
+.TP
+.BI link " HANDLE"
+Delegate matching packets to filters in a hash table.
+.I HANDLE
+is used to only specify the hash table, so only
+.BR htid " may be given, " hash " and " nodeid
+have to be omitted. By default, bucket number 0 will be used and can be
+overridden by the
+.B hashkey
+option.
+.TP
+.BI indev " ifname"
+Filter on the incoming interface of the packet. Obviously works only for
+forwarded traffic.
+.TP
+.BI help
+Print a brief help text about possible options.
+.SH SELECTORS
+Basically the only real selector is
+.B u32 .
+All others merely provide a higher level syntax and are internally translated
+into
+.B u32 .
+.TP
+.BI u32 " VAL_MASK_32"
+.TQ
+.BI u16 " VAL_MASK_16"
+.TQ
+.BI u8 " VAL_MASK_8"
+Match packet data to a given value. The selector name defines the sample length
+to extract (32bits for
+.BR u32 ,
+16bits for
+.B u16
+and 8bits for
+.BR u8 ).
+Before comparing, the sample is binary AND'ed with the given mask. This way
+uninteresting bits can be cleared before comparison. The position of the sample
+is defined by the offset specified in
+.IR AT .
+.TP
+.BI ip " IP"
+.TQ
+.BI ip6 " IP6"
+Assume packet starts with an IPv4 (
+.BR ip )
+or IPv6 (
+.BR ip6 )
+header.
+.IR IP / IP6
+then allows to match various header fields:
+.RS
+.TP
+.BI src " ADDR"
+.BI dst " ADDR"
+Compare Source or Destination Address fields against the value of
+.IR ADDR .
+The reserved words
+.BR default ", " any " and " all
+effectively match any address. Otherwise an IP address of the particular
+protocol is expected, optionally suffixed by a prefix length to match whole
+subnets. In case of IPv4 a netmask may also be given.
+.TP
+.BI dsfield " VAL_MASK_8"
+IPv4 only. Match the packet header's DSCP/ECN field. Synonyms to this are
+.BR tos " and " precedence .
+.TP
+.BI ihl " VAL_MASK_8"
+IPv4 only. Match the Internet Header Length field. Note that the value's unit is
+32bits, so to match a packet with 24byte header length
+.I u8_value
+has to be 6.
+.TP
+.BI protocol " VAL_MASK_8"
+Match the Protocol (IPv4) or Next Header (IPv6) field value, e.g. 6 for TCP.
+.TP
+.BI icmp_type " VAL_MASK_8"
+.TQ
+.BI icmp_code " VAL_MASK_8"
+Assume a next-header protocol of icmp or ipv6-icmp and match Type or Code
+field values. This is dangerous, as the code assumes minimal header size for
+IPv4 and lack of extension headers for IPv6.
+.TP
+.BI sport " VAL_MASK_16"
+.TQ
+.BI dport " VAL_MASK_16"
+Match layer four source or destination ports. This is dangerous as well, as it
+assumes a suitable layer four protocol is present (which has Source and
+Destination Port fields right at the start of the header and 16bit in size).
+Also minimal header size for IPv4 and lack of IPv6 extension headers is assumed.
+.TP
+.B nofrag
+.TQ
+.B firstfrag
+.TQ
+.B df
+.TQ
+.B mf
+IPv4 only, check certain flags and fragment offset values. Match if the packet
+is not a fragment
+.RB ( nofrag ),
+the first fragment
+.RB ( firstfrag ),
+if Don't Fragment
+.RB ( df )
+or More Fragments
+.RB ( mf )
+bits are set.
+.TP
+.BI priority " VAL_MASK_8"
+IPv6 only. Match the header's Traffic Class field, which has the same purpose
+and semantics of IPv4's ToS field since RFC 3168: upper six bits are DSCP, the
+lower two ECN.
+.TP
+.BI flowlabel " VAL_MASK_32"
+IPv6 only. Match the Flow Label field's value. Note that Flow Label itself is
+only 20bytes long, which are the least significant ones here. The remaining
+upper 12bytes match Version and Traffic Class fields.
+.RE
+.TP
+.BI tcp " TCPUDP"
+.TQ
+.BI udp " TCPUDP"
+Match fields of next header of protocol TCP or UDP. The possible values for
+.I TCPDUP
+are:
+.RS
+.TP
+.BI src " VAL_MASK_16"
+Match on Source Port field value.
+.TP
+.BI dst " VALMASK_16"
+Match on Destination Port field value.
+.RE
+.TP
+.BI icmp " ICMP"
+Match fields of next header of protocol ICMP. The possible values for
+.I ICMP
+are:
+.RS
+.TP
+.BI type " VAL_MASK_8"
+Match on ICMP Type field.
+.TP
+.BI code " VAL_MASK_8"
+Match on ICMP Code field.
+.RE
+.TP
+.BI mark " VAL_MASK_32"
+Match on netfilter fwmark value.
+.TP
+.BI ether " ETHER"
+Match on ethernet header fields. Possible values for
+.I ETHER
+are:
+.RS
+.TP
+.BI src " ether_address" " " AT
+.TQ
+.BI dst " ether_address" " " AT
+Match on source or destination ethernet address. This is dangerous: It assumes
+an ethernet header is present at the start of the packet. This will probably
+lead to unexpected things if used with layer three interfaces like e.g. tun or
+ppp.
+.SH EXAMPLES
+.RS
+.EX
+tc filter add dev eth0 parent 999:0 prio 99 protocol ip u32 \\
+ match ip src 192.168.8.0/24 classid 1:1
+.EE
+.RE
+
+This attaches a filter to the qdisc identified by
+.BR 999:0.
+It's priority is
+.BR 99 ,
+which affects in which order multiple filters attached to the same
+.B parent
+are consulted (the lower the earlier). The filter handles packets of
+.B protocol
+type
+.BR ip ,
+and
+.BR match es
+if the IP header's source address is within the
+.B 192.168.8.0/24
+subnet. Matching packets are classified into class
+.BR 1.1 .
+The effect of this command might be surprising at first glance:
+
+.RS
+.EX
+filter parent 1: protocol ip pref 99 u32
+filter parent 1: protocol ip pref 99 u32 \\
+ fh 800: ht divisor 1
+filter parent 1: protocol ip pref 99 u32 \\
+ fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:1 \\
+ match c0a80800/ffffff00 at 12
+.EE
+.RE
+
+So parent
+.B 1:
+is assigned a new
+.B u32
+filter, which contains a hash table of size 1 (as the
+.B divisor
+indicates). The table ID is
+.BR 800 .
+The third line then shows the actual filter which was added above: it sits in
+table
+.B 800
+and bucket
+.BR 0 ,
+classifies packets into class ID
+.B 1:1
+and matches the upper three bytes of the four byte value at offset
+.B 12
+to be
+.BR 0xc0a808 ,
+which is 192, 168 and 8.
+
+Now for something more complicated, namely creating a custom hash table:
+
+.RS
+.EX
+tc filter add dev eth0 prio 99 handle 1: u32 divisor 256
+.EE
+.RE
+
+This creates a table of size 256 with handle
+.B 1:
+in priority
+.BR 99 .
+The effect is as follows:
+
+.RS
+.EX
+filter parent 1: protocol all pref 99 u32
+filter parent 1: protocol all pref 99 u32 fh 1: ht divisor 256
+filter parent 1: protocol all pref 99 u32 fh 800: ht divisor 1
+.EE
+.RE
+
+So along with the requested hash table (handle
+.BR 1: ),
+the kernel has created his own table of size 1 to hold other filters of the same
+priority.
+
+The next step is to create a filter which links to the created hash table:
+
+.RS
+.EX
+tc filter add dev eth0 parent 1: prio 1 u32 \\
+ link 1: hashkey mask 0x0000ff00 at 12 \\
+ match ip src 192.168.0.0/16
+.EE
+.RE
+
+The filter is given a lower priority than the hash table itself so
+.B u32
+consults it before manually traversing the hash table. The options
+.BR link " and " hashkey
+determine which table and bucket to redirect to. In this case the hash key
+should be constructed out of the second byte at offset 12, which corresponds to
+an IP packet's third byte of the source address field. Along with the
+.B match
+statement, this effectively maps all class C networks below 192.168.0.0/16 to
+different buckets of the hash table.
+
+Filters for certain subnets can be created like so:
+
+.RS
+.EX
+tc filter add dev eth0 parent 1: prio 99 u32 \\
+ ht 1: sample u32 0x00000800 0x0000ff00 at 12 \\
+ match ip src 192.168.8.0/24 classid 1:1
+.EE
+.RE
+
+The bucket is defined using the
+.B sample
+option: In this case, the second byte at offset 12 must be 0x08, exactly. In
+this case, the resulting bucket ID is obviously 8, but as soon as
+.B sample
+selects an amount of data which could exceed the
+.BR divisor ,
+one would have to know the kernel-internal algorithm to deduce the destination
+bucket. This filter's
+.B match
+statement is redundant in this case, as the entropy for the hash key does not
+exceed the table size and therefore no collisions can occur. Otherwise it's
+necessary to prevent matching unwanted packets.
+
+Matching upper layer fields is problematic since IPv4 header length is variable
+and IPv6 supports extension headers which affect upper layer header offset. To
+overcome this, there is the possibility to specify
+.B nexthdr+
+when giving an offset, and to make things easier there are the
+.BR tcp " and " udp
+matches which use
+.B nexthdr+
+implicitly. This offset has to be calculated in beforehand though, and the only
+way to achieve that is by doing it in a separate filter which then links to the
+filter which wants to use it. Here is an example of doing so:
+
+.RS
+.EX
+tc filter add dev eth0 parent 1:0 protocol ip handle 1: \\
+ u32 divisor 1
+tc filter add dev eth0 parent 1:0 protocol ip \\
+ u32 ht 1: \\
+ match tcp src 22 FFFF \\
+ classid 1:2
+tc filter add dev eth0 parent 1:0 protocol ip \\
+ u32 ht 800: \\
+ match ip protocol 6 FF \\
+ match ip firstfrag \\
+ offset at 0 mask 0f00 shift 6 \\
+ link 1:
+.EE
+.RE
+
+This is what is being done: In the first call, a single element sized hash table
+is created so there is a place to hold the linked to filter and a known handle
+.RB ( 1: )
+to reference to it. The second call then adds the actual filter, which pushes
+packets with TCP source port 22 into class
+.BR 1:2 .
+Using
+.BR ht ,
+it is moved into the hash table created by the first call. The third call then
+does the actual magic: It matches IPv4 packets with next layer protocol 6 (TCP),
+only if it's the first fragment (usually TCP sets DF bit, but if it doesn't and
+the packet is fragmented, only the first one contains the TCP header), and then
+sets the offset based on the IP header's IHL field (right-shifting by 6
+eliminates the offset of the field and at the same time converts the value into
+byte unit). Finally, using
+.BR link ,
+the hash table from first call is referenced which holds the filter from second
+call.
+.SH SEE ALSO
+.BR tc (8),
+.br
+.BR cls_u32.txt " at " http://linux-tc-notes.sourceforge.net/
diff --git a/iproute2/man/man8/tc.8 b/iproute2/man/man8/tc.8
new file mode 100644
index 0000000..4e99dca
--- /dev/null
+++ b/iproute2/man/man8/tc.8
@@ -0,0 +1,734 @@
+.TH TC 8 "16 December 2001" "iproute2" "Linux"
+.SH NAME
+tc \- show / manipulate traffic control settings
+.SH SYNOPSIS
+.B tc
+.RI "[ " OPTIONS " ]"
+.B qdisc [ add | change | replace | link | delete ] dev
+DEV
+.B
+[ parent
+qdisc-id
+.B | root ]
+.B [ handle
+qdisc-id ] qdisc
+[ qdisc specific parameters ]
+.P
+
+.B tc
+.RI "[ " OPTIONS " ]"
+.B class [ add | change | replace | delete ] dev
+DEV
+.B parent
+qdisc-id
+.B [ classid
+class-id ] qdisc
+[ qdisc specific parameters ]
+.P
+
+.B tc
+.RI "[ " OPTIONS " ]"
+.B filter [ add | change | replace | delete ] dev
+DEV
+.B [ parent
+qdisc-id
+.B | root ] protocol
+protocol
+.B prio
+priority filtertype
+[ filtertype specific parameters ]
+.B flowid
+flow-id
+
+.B tc
+.RI "[ " OPTIONS " ]"
+.RI "[ " FORMAT " ]"
+.B qdisc show [ dev
+DEV
+.B ]
+.P
+.B tc
+.RI "[ " OPTIONS " ]"
+.RI "[ " FORMAT " ]"
+.B class show dev
+DEV
+.P
+.B tc
+.RI "[ " OPTIONS " ]"
+.B filter show dev
+DEV
+
+.P
+.ti 8
+.IR OPTIONS " := {"
+\fB[ -force ] -b\fR[\fIatch\fR] \fB[ filename ] \fR|
+\fB[ \fB-n\fR[\fIetns\fR] name \fB] \fR|
+\fB[ \fB-nm \fR| \fB-nam\fR[\fIes\fR] \fB] \fR|
+\fB[ \fR{ \fB-cf \fR| \fB-c\fR[\fIonf\fR] \fR} \fB[ filename ] \fB] \fR}
+
+.ti 8
+.IR FORMAT " := {"
+\fB\-s\fR[\fItatistics\fR] |
+\fB\-d\fR[\fIetails\fR] |
+\fB\-r\fR[\fIaw\fR] |
+\fB\-p\fR[\fIretty\fR] |
+\fB\-i\fR[\fIec\fR] |
+\fB\-g\fR[\fIraph\fR] }
+
+.SH DESCRIPTION
+.B Tc
+is used to configure Traffic Control in the Linux kernel. Traffic Control consists
+of the following:
+
+.TP
+SHAPING
+When traffic is shaped, its rate of transmission is under control. Shaping may
+be more than lowering the available bandwidth - it is also used to smooth out
+bursts in traffic for better network behaviour. Shaping occurs on egress.
+
+.TP
+SCHEDULING
+By scheduling the transmission of packets it is possible to improve interactivity
+for traffic that needs it while still guaranteeing bandwidth to bulk transfers. Reordering
+is also called prioritizing, and happens only on egress.
+
+.TP
+POLICING
+Whereas shaping deals with transmission of traffic, policing pertains to traffic
+arriving. Policing thus occurs on ingress.
+
+.TP
+DROPPING
+Traffic exceeding a set bandwidth may also be dropped forthwith, both on
+ingress and on egress.
+
+.P
+Processing of traffic is controlled by three kinds of objects: qdiscs,
+classes and filters.
+
+.SH QDISCS
+.B qdisc
+is short for 'queueing discipline' and it is elementary to
+understanding traffic control. Whenever the kernel needs to send a
+packet to an interface, it is
+.B enqueued
+to the qdisc configured for that interface. Immediately afterwards, the kernel
+tries to get as many packets as possible from the qdisc, for giving them
+to the network adaptor driver.
+
+A simple QDISC is the 'pfifo' one, which does no processing at all and is a pure
+First In, First Out queue. It does however store traffic when the network interface
+can't handle it momentarily.
+
+.SH CLASSES
+Some qdiscs can contain classes, which contain further qdiscs - traffic may
+then be enqueued in any of the inner qdiscs, which are within the
+.B classes.
+When the kernel tries to dequeue a packet from such a
+.B classful qdisc
+it can come from any of the classes. A qdisc may for example prioritize
+certain kinds of traffic by trying to dequeue from certain classes
+before others.
+
+.SH FILTERS
+A
+.B filter
+is used by a classful qdisc to determine in which class a packet will
+be enqueued. Whenever traffic arrives at a class with subclasses, it needs
+to be classified. Various methods may be employed to do so, one of these
+are the filters. All filters attached to the class are called, until one of
+them returns with a verdict. If no verdict was made, other criteria may be
+available. This differs per qdisc.
+
+It is important to notice that filters reside
+.B within
+qdiscs - they are not masters of what happens.
+
+The available filters are:
+.TP
+basic
+Filter packets based on an ematch expression. See
+.BR tc-ematch (8)
+for details.
+.TP
+bpf
+Filter packets using (e)BPF, see
+.BR tc-bpf (8)
+for details.
+.TP
+cgroup
+Filter packets based on the control group of their process. See
+. BR tc-cgroup (8)
+for details.
+.TP
+flow, flower
+Flow-based classifiers, filtering packets based on their flow (identified by selectable keys). See
+.BR tc-flow "(8) and"
+.BR tc-flower (8)
+for details.
+.TP
+fw
+Filter based on fwmark. Directly maps fwmark value to traffic class. See
+.BR tc-fw (8).
+.TP
+route
+Filter packets based on routing table. See
+.BR tc-route (8)
+for details.
+.TP
+rsvp
+Match Resource Reservation Protocol (RSVP) packets.
+.TP
+tcindex
+Filter packets based on traffic control index. See
+.BR tc-tcindex (8).
+.TP
+u32
+Generic filtering on arbitrary packet data, assisted by syntax to abstract common operations. See
+.BR tc-u32 (8)
+for details.
+
+.SH CLASSLESS QDISCS
+The classless qdiscs are:
+.TP
+choke
+CHOKe (CHOose and Keep for responsive flows, CHOose and Kill for unresponsive
+flows) is a classless qdisc designed to both identify and penalize flows that
+monopolize the queue. CHOKe is a variation of RED, and the configuration is
+similar to RED.
+.TP
+codel
+CoDel (pronounced "coddle") is an adaptive "no-knobs" active queue management
+algorithm (AQM) scheme that was developed to address the shortcomings of
+RED and its variants.
+.TP
+[p|b]fifo
+Simplest usable qdisc, pure First In, First Out behaviour. Limited in
+packets or in bytes.
+.TP
+fq
+Fair Queue Scheduler realises TCP pacing and scales to millions of concurrent
+flows per qdisc.
+.TP
+fq_codel
+Fair Queuing Controlled Delay is queuing discipline that combines Fair
+Queuing with the CoDel AQM scheme. FQ_Codel uses a stochastic model to classify
+incoming packets into different flows and is used to provide a fair share of the
+bandwidth to all the flows using the queue. Each such flow is managed by the
+CoDel queuing discipline. Reordering within a flow is avoided since Codel
+internally uses a FIFO queue.
+.TP
+gred
+Generalized Random Early Detection combines multiple RED queues in order to
+achieve multiple drop priorities. This is required to realize Assured
+Forwarding (RFC 2597).
+.TP
+hhf
+Heavy-Hitter Filter differentiates between small flows and the opposite,
+heavy-hitters. The goal is to catch the heavy-hitters and move them to a
+separate queue with less priority so that bulk traffic does not affect the
+latency of critical traffic.
+.TP
+ingress
+This is a special qdisc as it applies to incoming traffic on an interface, allowing for it to be filtered and policed.
+.TP
+mqprio
+The Multiqueue Priority Qdisc is a simple queuing discipline that allows
+mapping traffic flows to hardware queue ranges using priorities and a
+configurable priority to traffic class mapping. A traffic class in this context
+is a set of contiguous qdisc classes which map 1:1 to a set of hardware exposed
+queues.
+.TP
+multiq
+Multiqueue is a qdisc optimized for devices with multiple Tx queues. It has
+been added for hardware that wishes to avoid head-of-line blocking. It will
+cycle though the bands and verify that the hardware queue associated with the
+band is not stopped prior to dequeuing a packet.
+.TP
+netem
+Network Emulator is an enhancement of the Linux traffic control facilities that
+allow to add delay, packet loss, duplication and more other characteristics to
+packets outgoing from a selected network interface.
+.TP
+pfifo_fast
+Standard qdisc for 'Advanced Router' enabled kernels. Consists of a three-band
+queue which honors Type of Service flags, as well as the priority that may be
+assigned to a packet.
+.TP
+pie
+Proportional Integral controller-Enhanced (PIE) is a control theoretic active
+queue management scheme. It is based on the proportional integral controller but
+aims to control delay.
+.TP
+red
+Random Early Detection simulates physical congestion by randomly dropping
+packets when nearing configured bandwidth allocation. Well suited to very
+large bandwidth applications.
+.TP
+rr
+Round-Robin qdisc with support for multiqueue network devices. Removed from
+Linux since kernel version 2.6.27.
+.TP
+sfb
+Stochastic Fair Blue is a classless qdisc to manage congestion based on
+packet loss and link utilization history while trying to prevent
+non-responsive flows (i.e. flows that do not react to congestion marking
+or dropped packets) from impacting performance of responsive flows.
+Unlike RED, where the marking probability has to be configured, BLUE
+tries to determine the ideal marking probability automatically.
+.TP
+sfq
+Stochastic Fairness Queueing reorders queued traffic so each 'session'
+gets to send a packet in turn.
+.TP
+tbf
+The Token Bucket Filter is suited for slowing traffic down to a precisely
+configured rate. Scales well to large bandwidths.
+.SH CONFIGURING CLASSLESS QDISCS
+In the absence of classful qdiscs, classless qdiscs can only be attached at
+the root of a device. Full syntax:
+.P
+.B tc qdisc add dev
+DEV
+.B root
+QDISC QDISC-PARAMETERS
+
+To remove, issue
+.P
+.B tc qdisc del dev
+DEV
+.B root
+
+The
+.B pfifo_fast
+qdisc is the automatic default in the absence of a configured qdisc.
+
+.SH CLASSFUL QDISCS
+The classful qdiscs are:
+.TP
+ATM
+Map flows to virtual circuits of an underlying asynchronous transfer mode
+device.
+.TP
+CBQ
+Class Based Queueing implements a rich linksharing hierarchy of classes.
+It contains shaping elements as well as prioritizing capabilities. Shaping is
+performed using link idle time calculations based on average packet size and
+underlying link bandwidth. The latter may be ill-defined for some interfaces.
+.TP
+DRR
+The Deficit Round Robin Scheduler is a more flexible replacement for Stochastic
+Fairness Queuing. Unlike SFQ, there are no built-in queues \-\- you need to add
+classes and then set up filters to classify packets accordingly. This can be
+useful e.g. for using RED qdiscs with different settings for particular
+traffic. There is no default class \-\- if a packet cannot be classified, it is
+dropped.
+.TP
+DSMARK
+Classify packets based on TOS field, change TOS field of packets based on
+classification.
+.TP
+HFSC
+Hierarchical Fair Service Curve guarantees precise bandwidth and delay allocation for leaf classes and allocates excess bandwidth fairly. Unlike HTB, it makes use of packet dropping to achieve low delays which interactive sessions benefit from.
+.TP
+HTB
+The Hierarchy Token Bucket implements a rich linksharing hierarchy of
+classes with an emphasis on conforming to existing practices. HTB facilitates
+guaranteeing bandwidth to classes, while also allowing specification of upper
+limits to inter-class sharing. It contains shaping elements, based on TBF and
+can prioritize classes.
+.TP
+PRIO
+The PRIO qdisc is a non-shaping container for a configurable number of
+classes which are dequeued in order. This allows for easy prioritization
+of traffic, where lower classes are only able to send if higher ones have
+no packets available. To facilitate configuration, Type Of Service bits are
+honored by default.
+.TP
+QFQ
+Quick Fair Queueing is an O(1) scheduler that provides near-optimal guarantees,
+and is the first to achieve that goal with a constant cost also with respect to
+the number of groups and the packet length. The QFQ algorithm has no loops, and
+uses very simple instructions and data structures that lend themselves very
+well to a hardware implementation.
+.SH THEORY OF OPERATION
+Classes form a tree, where each class has a single parent.
+A class may have multiple children. Some qdiscs allow for runtime addition
+of classes (CBQ, HTB) while others (PRIO) are created with a static number of
+children.
+
+Qdiscs which allow dynamic addition of classes can have zero or more
+subclasses to which traffic may be enqueued.
+
+Furthermore, each class contains a
+.B leaf qdisc
+which by default has
+.B pfifo
+behaviour, although another qdisc can be attached in place. This qdisc may again
+contain classes, but each class can have only one leaf qdisc.
+
+When a packet enters a classful qdisc it can be
+.B classified
+to one of the classes within. Three criteria are available, although not all
+qdiscs will use all three:
+.TP
+tc filters
+If tc filters are attached to a class, they are consulted first
+for relevant instructions. Filters can match on all fields of a packet header,
+as well as on the firewall mark applied by ipchains or iptables.
+.TP
+Type of Service
+Some qdiscs have built in rules for classifying packets based on the TOS field.
+.TP
+skb->priority
+Userspace programs can encode a class-id in the 'skb->priority' field using
+the SO_PRIORITY option.
+.P
+Each node within the tree can have its own filters but higher level filters
+may also point directly to lower classes.
+
+If classification did not succeed, packets are enqueued to the leaf qdisc
+attached to that class. Check qdisc specific manpages for details, however.
+
+.SH NAMING
+All qdiscs, classes and filters have IDs, which can either be specified
+or be automatically assigned.
+
+IDs consist of a
+.BR major " number and a " minor
+number, separated by a colon -
+.BR major ":" minor "."
+Both
+.BR major " and " minor
+are hexadecimal numbers and are limited to 16 bits. There are two special
+values: root is signified by
+.BR major " and " minor
+of all ones, and unspecified is all zeros.
+
+.TP
+QDISCS
+A qdisc, which potentially can have children, gets assigned a
+.B major
+number, called a 'handle', leaving the
+.B minor
+number namespace available for classes. The handle is expressed as '10:'.
+It is customary to explicitly assign a handle to qdiscs expected to have children.
+
+.TP
+CLASSES
+Classes residing under a qdisc share their qdisc
+.B major
+number, but each have a separate
+.B minor
+number called a 'classid' that has no relation to their
+parent classes, only to their parent qdisc. The same naming custom as for
+qdiscs applies.
+
+.TP
+FILTERS
+Filters have a three part ID, which is only needed when using a hashed
+filter hierarchy.
+
+.SH PARAMETERS
+The following parameters are widely used in TC. For other parameters,
+see the man pages for individual qdiscs.
+
+.TP
+RATES
+Bandwidths or rates.
+These parameters accept a floating point number, possibly followed by
+a unit (both SI and IEC units supported).
+.RS
+.TP
+bit or a bare number
+Bits per second
+.TP
+kbit
+Kilobits per second
+.TP
+mbit
+Megabits per second
+.TP
+gbit
+Gigabits per second
+.TP
+tbit
+Terabits per second
+.TP
+bps
+Bytes per second
+.TP
+kbps
+Kilobytes per second
+.TP
+mbps
+Megabytes per second
+.TP
+gbps
+Gigabytes per second
+.TP
+tbps
+Terabytes per second
+
+.P
+To specify in IEC units, replace the SI prefix (k-, m-, g-, t-) with
+IEC prefix (ki-, mi-, gi- and ti-) respectively.
+
+.P
+TC store rates as a 32-bit unsigned integer in bps internally,
+so we can specify a max rate of 4294967295 bps.
+.RE
+
+.TP
+TIMES
+Length of time. Can be specified as a floating point number
+followed by an optional unit:
+.RS
+.TP
+s, sec or secs
+Whole seconds
+.TP
+ms, msec or msecs
+Milliseconds
+.TP
+us, usec, usecs or a bare number
+Microseconds.
+
+.P
+TC defined its own time unit (equal to microsecond) and stores
+time values as 32-bit unsigned integer, thus we can specify a max time value
+of 4294967295 usecs.
+.RE
+
+.TP
+SIZES
+Amounts of data. Can be specified as a floating point number
+followed by an optional unit:
+.RS
+.TP
+b or a bare number
+Bytes.
+.TP
+kbit
+Kilobits
+.TP
+kb or k
+Kilobytes
+.TP
+mbit
+Megabits
+.TP
+mb or m
+Megabytes
+.TP
+gbit
+Gigabits
+.TP
+gb or g
+Gigabytes
+
+.P
+TC stores sizes internally as 32-bit unsigned integer in byte,
+so we can specify a max size of 4294967295 bytes.
+.RE
+
+.TP
+VALUES
+Other values without a unit.
+These parameters are interpreted as decimal by default, but you can
+indicate TC to interpret them as octal and hexadecimal by adding a '0'
+or '0x' prefix respectively.
+
+.SH TC COMMANDS
+The following commands are available for qdiscs, classes and filter:
+.TP
+add
+Add a qdisc, class or filter to a node. For all entities, a
+.B parent
+must be passed, either by passing its ID or by attaching directly to the root of a device.
+When creating a qdisc or a filter, it can be named with the
+.B handle
+parameter. A class is named with the
+.B classid
+parameter.
+
+.TP
+delete
+A qdisc can be deleted by specifying its handle, which may also be 'root'. All subclasses and their leaf qdiscs
+are automatically deleted, as well as any filters attached to them.
+
+.TP
+change
+Some entities can be modified 'in place'. Shares the syntax of 'add', with the exception
+that the handle cannot be changed and neither can the parent. In other words,
+.B
+change
+cannot move a node.
+
+.TP
+replace
+Performs a nearly atomic remove/add on an existing node id. If the node does not exist yet
+it is created.
+
+.TP
+link
+Only available for qdiscs and performs a replace where the node
+must exist already.
+
+.SH OPTIONS
+
+.TP
+.BR "\-b", " \-b filename", " \-batch", " \-batch filename"
+read commands from provided file or standard input and invoke them.
+First failure will cause termination of tc.
+
+.TP
+.BR "\-force"
+don't terminate tc on errors in batch mode.
+If there were any errors during execution of the commands, the application return code will be non zero.
+
+.TP
+.BR "\-n" , " \-net" , " \-netns " <NETNS>
+switches
+.B tc
+to the specified network namespace
+.IR NETNS .
+Actually it just simplifies executing of:
+
+.B ip netns exec
+.IR NETNS
+.B tc
+.RI "[ " OPTIONS " ] " OBJECT " { " COMMAND " | "
+.BR help " }"
+
+to
+
+.B tc
+.RI "-n[etns] " NETNS " [ " OPTIONS " ] " OBJECT " { " COMMAND " | "
+.BR help " }"
+
+.TP
+.BR "\-cf" , " \-conf " <FILENAME>
+specifies path to the config file. This option is used in conjunction with other options (e.g.
+.BR -nm ")."
+
+.SH FORMAT
+The show command has additional formatting options:
+
+.TP
+.BR "\-s" , " \-stats", " \-statistics"
+output more statistics about packet usage.
+
+.TP
+.BR "\-d", " \-details"
+output more detailed information about rates and cell sizes.
+
+.TP
+.BR "\-r", " \-raw"
+output raw hex values for handles.
+
+.TP
+.BR "\-p", " \-pretty"
+decode filter offset and mask values to equivalent filter commands based on TCP/IP.
+
+.TP
+.BR "\-iec"
+print rates in IEC units (ie. 1K = 1024).
+
+.TP
+.BR "\-g", " \-graph"
+shows classes as ASCII graph. Prints generic stats info under each class if
+.BR "-s"
+option was specified. Classes can be filtered only by
+.BR "dev"
+option.
+
+.TP
+.BR "\-nm" , " \-name"
+resolve class name from
+.B /etc/iproute2/tc_cls
+file or from file specified by
+.B -cf
+option. This file is just a mapping of
+.B classid
+to class name:
+
+.RS 10
+# Here is comment
+.RE
+.RS 10
+1:40 voip # Here is another comment
+.RE
+.RS 10
+1:50 web
+.RE
+.RS 10
+1:60 ftp
+.RE
+.RS 10
+1:2 home
+.RE
+
+.RS
+.B tc
+will not fail if
+.B -nm
+was specified without
+.B -cf
+option but
+.B /etc/iproute2/tc_cls
+file does not exist, which makes it possible to pass
+.B -nm
+option for creating
+.B tc
+alias.
+.RE
+
+.SH "EXAMPLES"
+.PP
+tc -g class show dev eth0
+.RS 4
+Shows classes as ASCII graph on eth0 interface.
+.RE
+.PP
+tc -g -s class show dev eth0
+.RS 4
+Shows classes as ASCII graph with stats info under each class.
+
+.SH HISTORY
+.B tc
+was written by Alexey N. Kuznetsov and added in Linux 2.2.
+.SH SEE ALSO
+.BR tc-basic (8),
+.BR tc-bfifo (8),
+.BR tc-bpf (8),
+.BR tc-cbq (8),
+.BR tc-cgroup (8),
+.BR tc-choke (8),
+.BR tc-codel (8),
+.BR tc-drr (8),
+.BR tc-ematch (8),
+.BR tc-flow (8),
+.BR tc-flower (8),
+.BR tc-fq (8),
+.BR tc-fq_codel (8),
+.BR tc-fw (8),
+.BR tc-hfsc (7),
+.BR tc-hfsc (8),
+.BR tc-htb (8),
+.BR tc-mqprio (8),
+.BR tc-pfifo (8),
+.BR tc-pfifo_fast (8),
+.BR tc-red (8),
+.BR tc-route (8),
+.BR tc-sfb (8),
+.BR tc-sfq (8),
+.BR tc-stab (8),
+.BR tc-tbf (8),
+.BR tc-tcindex (8),
+.BR tc-u32 (8),
+.br
+.RB "User documentation at " http://lartc.org/ ", but please direct bugreports and patches to: " <netdev@vger.kernel.org>
+
+.SH AUTHOR
+Manpage maintained by bert hubert (ahu@ds9a.nl)
diff --git a/iproute2/man/man8/tipc-bearer.8 b/iproute2/man/man8/tipc-bearer.8
new file mode 100644
index 0000000..565ee01
--- /dev/null
+++ b/iproute2/man/man8/tipc-bearer.8
@@ -0,0 +1,231 @@
+.TH TIPC-BEARER 8 "02 Jun 2015" "iproute2" "Linux"
+
+.\" For consistency, please keep padding right aligned.
+.\" For example '.B "foo " bar' and not '.B foo " bar"'
+
+.SH NAME
+tipc-bearer \- show or modify TIPC bearers
+
+.SH SYNOPSIS
+.ad l
+.in +8
+
+.ti -8
+.B tipc bearer enable
+.RB "[ " domain
+.IR DOMAIN " ]"
+.RB "[ " priority
+.IR PRIORITY " ]"
+.BR media
+.br
+.RB "{ { " eth " | " ib " } " device
+.IR "DEVICE" " }"
+.RB "|"
+.br
+.RB "{ " udp
+.B name
+.IR NAME
+.B localip
+.IR LOCALIP
+.RB "[ " localport
+.IR LOCALPORT " ]"
+.RB "[ " remoteip
+.IR REMOTEIP " ]"
+.RB "[ " remoteport
+.IR REMOTEPORT " ] }"
+.br
+
+.ti -8
+.B tipc bearer disable media
+.br
+.RB "{ { " eth " | " ib " } " device
+.IR DEVICE
+.RB "|"
+.br
+.RB "{ " udp
+.B name
+.IR NAME
+.B localip
+.IR LOCALIP " } }"
+.br
+
+.ti -8
+.B tipc bearer set
+.RB "{ " "priority "
+.IR PRIORITY
+.RB "| " tolerance
+.IR TOLERANCE
+.RB "| " window
+.IR WINDOW
+.RB "} " media
+.br
+.RB "{ { " eth " | " ib " } " device
+.IR "DEVICE" " }"
+.RB "|"
+.br
+.RB "{ " udp
+.B name
+.IR NAME
+.B localip
+.IR LOCALIP " } }"
+.br
+
+.ti -8
+.B tipc bearer get
+.RB "{ " "priority" " | " tolerance " | " window " } " media
+.br
+.RB "{ { " eth " | " ib " } " device
+.IR "DEVICE" " }"
+.RB "|"
+.br
+.RB "{ " udp
+.B name
+.IR NAME
+.B localip
+.IR LOCALIP " } }"
+.br
+
+.ti -8
+.B tipc bearer list
+.br
+
+.SH OPTIONS
+Options (flags) that can be passed anywhere in the command chain.
+.TP
+.BR "\-h" , " --help"
+Show help about last valid command. For example
+.B tipc bearer --help
+will show bearer help and
+.B tipc --help
+will show general help. The position of the option in the string is irrelevant.
+.SH DESCRIPTION
+
+.SS Bearer identification
+.TP
+.BI "media " MEDIA
+.br
+Specifies the TIPC media type for a particular bearer to operate on.
+Different media types have different ways of identifying a unique bearer.
+For example,
+.BR "ib " "and " eth
+identify a bearer with a
+.I DEVICE
+while
+.B udp
+identify a bearer with a
+.IR "LOCALIP " "and a " NAME
+
+.B ib
+- Infiniband
+.sp
+.B eth
+- Ethernet
+.sp
+.B udp
+- User Datagram Protocol (UDP)
+.sp
+
+.TP
+.BI "name " NAME
+.br
+Logical bearer identifier valid for bearers on
+.B udp
+media.
+
+.TP
+.BI "device " DEVICE
+.br
+Physical bearer device valid for bearers on
+.B eth
+and
+.B ib
+media.
+
+.SS Bearer properties
+
+.TP
+.B domain
+.br
+The addressing domain (region) in which a bearer will establish links and accept
+link establish requests.
+
+.TP
+.B priority
+.br
+Default link priority inherited by all links subsequently established over a
+bearer. A single bearer can only host one link to a particular node. This means
+the default link priority for a bearer typically affects which bearer to use
+when communicating with a particular node in an multi bearer setup. For more
+info about link priority see
+.BR tipc-link (8)
+
+.TP
+.B tolerance
+.br
+Default link tolerance inherited by all links subsequently established over a
+bearer. For more info about link tolerance see
+.BR tipc-link (8)
+
+.TP
+.B window
+.br
+Default link window inherited by all links subsequently established over a
+bearer. For more info about the link window size see
+.BR tipc-link (8)
+
+.SS UDP bearer options
+
+.TP
+.BI "localip " LOCALIP
+.br
+Specify a local IP v4/v6 address for a
+.B udp
+bearer.
+
+.TP
+.BI "localport " LOCALPORT
+.br
+Specify the local port for a
+.B udp
+bearer. The default port 6118 is used if no port is specified.
+
+.TP
+.BI "remoteip " REMOTEIP
+.br
+Specify a remote IP for a
+.B udp
+bearer. If no remote IP is specified a
+.B udp
+bearer runs in multicast mode and tries to auto-discover its neighbours.
+The multicast IP address is generated based on the TIPC network ID. If a remote
+IP is specified the
+.B udp
+bearer runs in point-to-point mode.
+
+.TP
+.BI "remoteport " REMOTEPORT
+.br
+Specify the remote port for a
+.B udp
+bearer. The default port 6118 is used if no port is specified.
+
+.SH EXIT STATUS
+Exit status is 0 if command was successful or a positive integer upon failure.
+
+.SH SEE ALSO
+.BR tipc (8),
+.BR tipc-link (8),
+.BR tipc-media (8),
+.BR tipc-nametable (8),
+.BR tipc-node (8),
+.BR tipc-peer (8),
+.BR tipc-socket (8)
+.br
+.SH REPORTING BUGS
+Report any bugs to the Network Developers mailing list
+.B <netdev@vger.kernel.org>
+where the development and maintenance is primarily done.
+You do not have to be subscribed to the list to send a message there.
+
+.SH AUTHOR
+Richard Alpe <richard.alpe@ericsson.com>
diff --git a/iproute2/man/man8/tipc-link.8 b/iproute2/man/man8/tipc-link.8
new file mode 100644
index 0000000..2ee03a0
--- /dev/null
+++ b/iproute2/man/man8/tipc-link.8
@@ -0,0 +1,226 @@
+.TH TIPC-LINK 8 "02 Jun 2015" "iproute2" "Linux"
+
+.\" For consistency, please keep padding right aligned.
+.\" For example '.B "foo " bar' and not '.B foo " bar"'
+
+.SH NAME
+tipc-link \- show links or modify link properties
+
+.SH SYNOPSIS
+.ad l
+.in +8
+
+.ti -8
+
+.ti -8
+.B tipc link set
+.RB "{ " "priority "
+.IR PRIORITY
+.RB "| " tolerance
+.IR TOLERANCE
+.RB "| " window
+.IR "WINDOW " }
+.BI "link " LINK
+
+.ti -8
+.B tipc link get
+.RB "{ " "priority" " | " tolerance " | " window " } " link
+.I LINK
+
+.ti -8
+.B tipc link statistics
+.RB "{ " "show " "[ " link
+.I LINK
+.RB "] | " "reset
+.BI "link " "LINK "
+}
+
+.ti -8
+.B tipc link list
+.br
+
+.SH OPTIONS
+Options (flags) that can be passed anywhere in the command chain.
+.TP
+.BR "\-h" , " --help"
+Show help about last valid command. For example
+.B tipc link --help
+will show link help and
+.B tipc --help
+will show general help. The position of the option in the string is irrelevant.
+.SH DESCRIPTION
+
+.SS Link statistics
+
+.TP
+.BR "ACTIVE " "link state"
+.br
+An
+.B ACTIVE
+link is serving traffic. Two links to the same node can become
+.B ACTIVE
+if they have the same link
+.BR priority .
+If there is more than two links with the same priority the additional links will
+be put in
+.B STANDBY
+state.
+
+.TP
+.BR "STANDBY " "link state"
+.br
+A
+.B STANDBY
+link has lower link priority than an
+.B ACTIVE
+link. A
+.B STANDBY
+link has control traffic flowing and is ready to take over should the
+.B ACTIVE
+link(s) go down.
+
+.TP
+.B MTU
+.br
+The Maximum Transmission Unit. The two endpoints advertise their default or
+configured
+.B MTU
+at initial link setup and will agree to use the lower of the two values should
+they differ.
+
+.TP
+.B Packets
+.br
+The total amount of transmitted or received TIPC packets on a link. Including
+.BR "fragmented " "and " "bundled " packets.
+
+.TP
+.B Fragments
+.br
+Represented in the form
+.BR fragments / fragmented .
+Where
+.B fragmented
+is the amount of data messages which have been broken into
+.BR fragments .
+Subsequently the
+.B fragments
+are the total amount of packets that the
+.B fragmented
+messages has been broken into.
+
+.TP
+.B Bundles
+.br
+Represented in the form
+.BR bundles / bundled .
+If a link becomes congested the link will attempt to bundle data from small
+.B bundled
+packets into
+.B bundles
+of full MTU size packets before they are transmitted.
+
+.TP
+.B Profile
+.br
+Shows the
+.B average
+packet size in octets/bytes for a
+.B sample
+of packets. It also shows the packet size distribution of the
+.B sampled
+packets in the intervals
+
+0-64 bytes
+.br
+64-256 bytes
+.br
+256-1024 bytes
+.br
+1024-4096 bytes
+.br
+4096-16384 bytes
+.br
+16384-32768 bytes
+.br
+32768-66000 bytes
+
+.TP
+.B Message counters
+
+.B states
+- Number of link state messages
+.sp
+
+.B probes
+- Link state messages with probe flag set. Typically sent when a link is idle
+.sp
+
+.B nacks
+- Number of negative acknowledgement (NACK) packets sent and received by the
+link
+.sp
+
+.B defs
+- Number of packets received out of order
+.sp
+
+.B dups
+- Number of duplicate packets received
+
+.TP
+.B Congestion link
+The number of times an application has tried to send data when the TIPC link
+was congested
+
+.TP
+.B Send queue
+.B Max
+is the maximum amount of messages that has resided in the out queue during the
+statistics collection period of a link.
+
+.B Avg
+is the average outqueue size during the lifetime of a link.
+
+.SS Link properties
+
+.TP
+.B priority
+.br
+The priority between logical TIPC links to a particular node. Link priority can
+range from 0 (lowest) to 31 (highest).
+
+.TP
+.B tolerance
+.br
+Link tolerance specifies the maximum time in milliseconds that TIPC will allow
+a communication problem to exist before taking the link down. The default value
+is 1500 milliseconds.
+
+.TP
+.B window
+.br
+The link window controls how many unacknowledged messages a link endpoint can
+have in its transmit queue before TIPC's congestion control mechanism is
+activated.
+
+.SH EXIT STATUS
+Exit status is 0 if command was successful or a positive integer upon failure.
+
+.SH SEE ALSO
+.BR tipc (8),
+.BR tipc-media (8),
+.BR tipc-bearer (8),
+.BR tipc-nametable (8),
+.BR tipc-node (8),
+.BR tipc-peer (8),
+.BR tipc-socket (8)
+.br
+.SH REPORTING BUGS
+Report any bugs to the Network Developers mailing list
+.B <netdev@vger.kernel.org>
+where the development and maintenance is primarily done.
+You do not have to be subscribed to the list to send a message there.
+
+.SH AUTHOR
+Richard Alpe <richard.alpe@ericsson.com>
diff --git a/iproute2/man/man8/tipc-media.8 b/iproute2/man/man8/tipc-media.8
new file mode 100644
index 0000000..4689cb3
--- /dev/null
+++ b/iproute2/man/man8/tipc-media.8
@@ -0,0 +1,87 @@
+.TH TIPC-MEDIA 8 "02 Jun 2015" "iproute2" "Linux"
+
+.\" For consistency, please keep padding right aligned.
+.\" For example '.B "foo " bar' and not '.B foo " bar"'
+
+.SH NAME
+tipc-media \- list or modify media properties
+
+.SH SYNOPSIS
+.ad l
+.in +8
+
+.ti -8
+
+.ti -8
+.B tipc media set
+.RB "{ " "priority "
+.IR PRIORITY
+.RB "| " tolerance
+.IR TOLERANCE
+.RB "| " window
+.IR "WINDOW " }
+.BI "media " MEDIA
+
+.ti -8
+.B tipc media get
+.RB "{ " "priority" " | " tolerance " | " window " } " media
+.I MEDIA
+
+.ti -8
+.B tipc media list
+.br
+
+.SH OPTIONS
+Options (flags) that can be passed anywhere in the command chain.
+.TP
+.BR "\-h" , " --help"
+Show help about last valid command. For example
+.B tipc media --help
+will show media help and
+.B tipc --help
+will show general help. The position of the option in the string is irrelevant.
+.SH DESCRIPTION
+
+.SS Media properties
+
+.TP
+.B priority
+.br
+Default link priority inherited by all bearers subsequently enabled on a
+media. For more info about link priority see
+.BR tipc-link (8)
+
+.TP
+.B tolerance
+.br
+Default link tolerance inherited by all bearers subsequently enabled on a
+media. For more info about link tolerance see
+.BR tipc-link (8)
+
+.TP
+.B window
+.br
+Default link window inherited by all bearers subsequently enabled on a
+media. For more info about link window see
+.BR tipc-link (8)
+
+.SH EXIT STATUS
+Exit status is 0 if command was successful or a positive integer upon failure.
+
+.SH SEE ALSO
+.BR tipc (8),
+.BR tipc-bearer (8),
+.BR tipc-link (8),
+.BR tipc-nametable (8),
+.BR tipc-node (8),
+.BR tipc-peer (8),
+.BR tipc-socket (8)
+.br
+.SH REPORTING BUGS
+Report any bugs to the Network Developers mailing list
+.B <netdev@vger.kernel.org>
+where the development and maintenance is primarily done.
+You do not have to be subscribed to the list to send a message there.
+
+.SH AUTHOR
+Richard Alpe <richard.alpe@ericsson.com>
diff --git a/iproute2/man/man8/tipc-nametable.8 b/iproute2/man/man8/tipc-nametable.8
new file mode 100644
index 0000000..4bcefe4
--- /dev/null
+++ b/iproute2/man/man8/tipc-nametable.8
@@ -0,0 +1,100 @@
+.TH TIPC-NAMETABLE 8 "02 Jun 2015" "iproute2" "Linux"
+
+.\" For consistency, please keep padding right aligned.
+.\" For example '.B "foo " bar' and not '.B foo " bar"'
+
+.SH NAME
+tipc-nametable \- show TIPC nametable
+
+.SH SYNOPSIS
+.ad l
+.in +8
+
+.ti -8
+.B tipc nametable show
+.br
+
+.SH OPTIONS
+Options (flags) that can be passed anywhere in the command chain.
+.TP
+.BR "\-h" , " --help"
+Show help about last valid command. For example
+.B tipc nametable --help
+will show nametable help and
+.B tipc --help
+will show general help. The position of the option in the string is irrelevant.
+
+.SH DESCRIPTION
+The nametable shows TIPC publication information.
+
+.SS Nametable format
+
+.TP
+.B Type
+.br
+The 32-bit type field of the port name. The type field often indicates the class of service
+provided by a port.
+
+.TP
+.B Lower
+.br
+The lower bound of the 32-bit instance field of the port name.
+The instance field is often used as as a sub-class indicator.
+
+.TP
+.B Upper
+.br
+The upper bound of the 32-bit instance field of the port name.
+The instance field is often used as as a sub-class indicator.
+A difference in
+.BR "lower " "and " upper
+means the socket is bound to the port name range [lower,upper]
+
+.TP
+.B Port Identity
+.br
+The unique socket (port) identifier within the TIPC cluster. The
+.B port identity
+consists of a node identity followed by a socket reference number.
+
+.TP
+.B Publication
+.br
+The
+.B publication
+ID is a random number used internally to represent a publication.
+
+.TP
+.B Scope
+.br
+The publication
+.B scope
+specifies the visibility of a bound port name.
+The
+.B scope
+can be specified to comprise three different domains:
+.BR node ", " "cluster " "and " zone.
+Applications residing within the specified
+.B scope
+can see and access the port using the displayed port name.
+
+.SH EXIT STATUS
+Exit status is 0 if command was successful or a positive integer upon failure.
+
+.SH SEE ALSO
+.BR tipc (8),
+.BR tipc-bearer (8),
+.BR tipc-link (8),
+.BR tipc-media (8),
+.BR tipc-node (8),
+.BR tipc-peer (8),
+.BR tipc-socket (8)
+.br
+.SH REPORTING BUGS
+Report any bugs to the Network Developers mailing list
+.B <netdev@vger.kernel.org>
+where the development and maintenance is primarily done.
+You do not have to be subscribed to the list to send a message there.
+
+.SH AUTHOR
+Richard Alpe <richard.alpe@ericsson.com>
diff --git a/iproute2/man/man8/tipc-node.8 b/iproute2/man/man8/tipc-node.8
new file mode 100644
index 0000000..a72a409
--- /dev/null
+++ b/iproute2/man/man8/tipc-node.8
@@ -0,0 +1,72 @@
+.TH TIPC-NODE 8 "02 Jun 2015" "iproute2" "Linux"
+
+.\" For consistency, please keep padding right aligned.
+.\" For example '.B "foo " bar' and not '.B foo " bar"'
+
+.SH NAME
+tipc-node \- modify and show local node parameters or list peer nodes
+
+.SH SYNOPSIS
+.ad l
+.in +8
+
+.ti -8
+.B tipc node set
+.RB "{ " "address "
+.IR ADDRESS
+.RB "| " netid
+.IR NETID
+.RB "} "
+
+.ti -8
+.B tipc node get
+.RB "{ " "address" " | " netid " } "
+
+.ti -8
+.B tipc node list
+.br
+
+.SH OPTIONS
+Options (flags) that can be passed anywhere in the command chain.
+.TP
+.BR "\-h" , " --help"
+Show help about last valid command. For example
+.B tipc node --help
+will show node help and
+.B tipc --help
+will show general help. The position of the option in the string is irrelevant.
+.SH DESCRIPTION
+
+.SS Node parameters
+.TP
+.BI address
+.br
+The TIPC logical address. On the form x.y.z where x, y and z are unsigned
+integers.
+
+.TP
+.BI netid
+.br
+Network identity. Can by used to create individual TIPC clusters on the same
+media.
+
+.SH EXIT STATUS
+Exit status is 0 if command was successful or a positive integer upon failure.
+
+.SH SEE ALSO
+.BR tipc (8),
+.BR tipc-bearer (8),
+.BR tipc-link (8),
+.BR tipc-media (8),
+.BR tipc-nametable (8),
+.BR tipc-peer (8),
+.BR tipc-socket (8)
+.br
+.SH REPORTING BUGS
+Report any bugs to the Network Developers mailing list
+.B <netdev@vger.kernel.org>
+where the development and maintenance is primarily done.
+You do not have to be subscribed to the list to send a message there.
+
+.SH AUTHOR
+Richard Alpe <richard.alpe@ericsson.com>
diff --git a/iproute2/man/man8/tipc-peer.8 b/iproute2/man/man8/tipc-peer.8
new file mode 100644
index 0000000..430651f
--- /dev/null
+++ b/iproute2/man/man8/tipc-peer.8
@@ -0,0 +1,52 @@
+.TH TIPC-PEER 8 "04 Dec 2015" "iproute2" "Linux"
+
+.\" For consistency, please keep padding right aligned.
+.\" For example '.B "foo " bar' and not '.B foo " bar"'
+
+.SH NAME
+tipc-peer \- modify peer information
+
+.SH SYNOPSIS
+.ad l
+.in +8
+
+.ti -8
+.B tipc peer remove address
+.IR ADDRESS
+
+.SH OPTIONS
+Options (flags) that can be passed anywhere in the command chain.
+.TP
+.BR "\-h" , " --help"
+Show help about last valid command. For example
+.B tipc peer --help
+will show peer help and
+.B tipc --help
+will show general help. The position of the option in the string is irrelevant.
+.SH DESCRIPTION
+
+.SS Peer remove
+Remove an offline peer node from the local data structures. The peer is
+identified by its
+.B address
+
+.SH EXIT STATUS
+Exit status is 0 if command was successful or a positive integer upon failure.
+
+.SH SEE ALSO
+.BR tipc (8),
+.BR tipc-bearer (8),
+.BR tipc-link (8),
+.BR tipc-media (8),
+.BR tipc-nametable (8),
+.BR tipc-node (8),
+.BR tipc-socket (8)
+.br
+.SH REPORTING BUGS
+Report any bugs to the Network Developers mailing list
+.B <netdev@vger.kernel.org>
+where the development and maintenance is primarily done.
+You do not have to be subscribed to the list to send a message there.
+
+.SH AUTHOR
+Richard Alpe <richard.alpe@ericsson.com>
diff --git a/iproute2/man/man8/tipc-socket.8 b/iproute2/man/man8/tipc-socket.8
new file mode 100644
index 0000000..23ec1e5
--- /dev/null
+++ b/iproute2/man/man8/tipc-socket.8
@@ -0,0 +1,59 @@
+.TH TIPC-SOCKET 8 "02 Jun 2015" "iproute2" "Linux"
+
+.\" For consistency, please keep padding right aligned.
+.\" For example '.B "foo " bar' and not '.B foo " bar"'
+
+.SH NAME
+tipc-socket \- show TIPC socket (port) information
+
+.SH SYNOPSIS
+.ad l
+.in +8
+
+.ti -8
+.B tipc socket list
+
+.SH OPTIONS
+Options (flags) that can be passed anywhere in the command chain.
+.TP
+.BR "\-h" , " --help"
+Show help about last valid command. For example
+.B tipc socket --help
+will show socket help and
+.B tipc --help
+will show general help. The position of the option in the string is irrelevant.
+
+.SH DESCRIPTION
+A TIPC socket is represented by an unsigned integer.
+
+.TP
+.SS Bound state
+A bound socket has a logical TIPC port name associated with it.
+
+.TP
+.SS Connected state
+A connected socket is directly connected to another socket creating a point
+to point connection between TIPC sockets. If the connection to X was made using
+a logical port name Y that name will show up as
+.BR "connected to " "X " "via " Y
+.
+
+.SH EXIT STATUS
+Exit status is 0 if command was successful or a positive integer upon failure.
+
+.SH SEE ALSO
+.BR tipc (8),
+.BR tipc-bearer (8)
+.BR tipc-link (8),
+.BR tipc-media (8),
+.BR tipc-nametable (8),
+.BR tipc-node (8),
+.br
+.SH REPORTING BUGS
+Report any bugs to the Network Developers mailing list
+.B <netdev@vger.kernel.org>
+where the development and maintenance is primarily done.
+You do not have to be subscribed to the list to send a message there.
+
+.SH AUTHOR
+Richard Alpe <richard.alpe@ericsson.com>
diff --git a/iproute2/man/man8/tipc.8 b/iproute2/man/man8/tipc.8
new file mode 100644
index 0000000..32943fa
--- /dev/null
+++ b/iproute2/man/man8/tipc.8
@@ -0,0 +1,100 @@
+.TH TIPC 8 "02 Jun 2015" "iproute2" "Linux"
+.SH NAME
+tipc \- a TIPC configuration and management tool
+.SH SYNOPSIS
+
+.ad l
+.in +8
+.ti -8
+.B tipc
+.RI "[ " OPTIONS " ] " COMMAND " " ARGUMENTS "
+.sp
+
+.ti -8
+.IR COMMAND " := { "
+.BR bearer " | " link " | " media " | " nametable " | " node " | " socket " }
+.sp
+
+.ti -8
+.IR OPTIONS " := { "
+\fB\-h\fR[\fIhelp\fR] }
+
+.SH DESCRIPTION
+The Transparent Inter-Process Communication (TIPC) protocol offers total address
+transparency between processes which allows applications in a clustered computer
+environment to communicate quickly and reliably with each other, regardless of
+their location within the cluster.
+
+TIPC originated at the telecommunications manufacturer Ericsson. The first open
+source version of TIPC was created in 2000 when Ericsson released its first
+Linux version of TIPC. TIPC was introduced in the mainline Linux kernel in 2006
+and is now widely used both within and outside of Ericsson.
+
+.SH OPTIONS
+
+.TP
+.BR "\-h" , " --help"
+Show help about last given command. For example
+.B tipc bearer --help
+will show bearer help and
+.B tipc --help
+will show general help. The position of the option in the string is irrelevant.
+
+.SH COMMANDS
+
+.TP
+.B BEARER
+- Show or modify TIPC bearers
+
+.TP
+.B LINK
+- Show or modify TIPC links
+
+.TP
+.B MEDIA
+- Show or modify TIPC media
+
+.TP
+.B NAMETABLE
+- Show TIPC nametable
+
+.TP
+.B NODE
+- Show or modify TIPC node parameters
+
+.TP
+.B SOCKET
+- Show TIPC sockets
+
+.SH ARGUMENTS
+
+Command arguments are described in a command specific man page and typically
+consists of nested commands along with key value pairs.
+If no arguments are given a command typically shows its help text. The explicit
+help option
+.B -h
+or
+.B --help
+can occur anywhere among the arguments and will show help for the last valid
+command given.
+
+.SH EXIT STATUS
+Exit status is 0 if command was successful or a positive integer upon failure.
+
+.SH SEE ALSO
+.BR tipc-bearer (8),
+.BR tipc-link (8),
+.BR tipc-media (8),
+.BR tipc-nametable (8),
+.BR tipc-node (8),
+.BR tipc-peer (8),
+.BR tipc-socket (8)
+.br
+.SH REPORTING BUGS
+Report any bugs to the Network Developers mailing list
+.B <netdev@vger.kernel.org>
+where the development and maintenance is primarily done.
+You do not have to be subscribed to the list to send a message there.
+
+.SH AUTHOR
+Richard Alpe <richard.alpe@ericsson.com>
diff --git a/iproute2/misc/Android.mk b/iproute2/misc/Android.mk
new file mode 100644
index 0000000..6867895
--- /dev/null
+++ b/iproute2/misc/Android.mk
@@ -0,0 +1,37 @@
+LOCAL_PATH := $(call my-dir)
+
+include $(CLEAR_VARS)
+LOCAL_CLANG := true
+
+LOCAL_SRC_FILES := ss.c ssfilter.y
+
+LOCAL_MODULE := ss
+
+LOCAL_MODULE_TAGS := debug
+
+LOCAL_SHARED_LIBRARIES += libiprouteutil libnetlink
+
+LOCAL_C_INCLUDES := $(LOCAL_PATH)/../include
+
+##
+# "-x c" forces the lex/yacc files to be compiled as c the build system
+# otherwise forces them to be c++.
+yacc_flags := -x c
+
+LOCAL_CFLAGS := \
+ -O2 -g \
+ -W -Wall \
+ -Wno-missing-field-initializers \
+ -Wno-sign-compare \
+ -Wno-tautological-pointer-compare \
+ -Wno-unused-parameter \
+ -Werror \
+ '-Dsethostent(x)=' \
+ $(yacc_flags) \
+ -DHAVE_SETNS
+
+LOCAL_CPPFLAGS := $(yacc_flags)
+
+LOCAL_LDFLAGS := -Wl,-export-dynamic
+include $(BUILD_EXECUTABLE)
+
diff --git a/iproute2/misc/Makefile b/iproute2/misc/Makefile
new file mode 100644
index 0000000..f50e740
--- /dev/null
+++ b/iproute2/misc/Makefile
@@ -0,0 +1,48 @@
+SSOBJ=ss.o ssfilter.o
+LNSTATOBJ=lnstat.o lnstat_util.o
+
+TARGETS=ss nstat ifstat rtacct lnstat
+
+include ../Config
+
+ifeq ($(HAVE_BERKELEY_DB),y)
+ TARGETS += arpd
+endif
+
+ifeq ($(HAVE_SELINUX),y)
+ LDLIBS += $(shell $(PKG_CONFIG) --libs libselinux)
+ CFLAGS += $(shell $(PKG_CONFIG) --cflags libselinux) -DHAVE_SELINUX
+endif
+
+ifeq ($(IP_CONFIG_SETNS),y)
+ CFLAGS += -DHAVE_SETNS
+endif
+
+all: $(TARGETS)
+
+ss: $(SSOBJ)
+
+nstat: nstat.c
+ $(CC) $(CFLAGS) $(LDFLAGS) -o nstat nstat.c $(LIBNETLINK) -lm
+
+ifstat: ifstat.c
+ $(CC) $(CFLAGS) $(LDFLAGS) -o ifstat ifstat.c $(LIBNETLINK) -lm
+
+rtacct: rtacct.c
+ $(CC) $(CFLAGS) $(LDFLAGS) -o rtacct rtacct.c $(LIBNETLINK) -lm
+
+arpd: arpd.c
+ $(CC) $(CFLAGS) -I$(DBM_INCLUDE) $(LDFLAGS) -o arpd arpd.c $(LIBNETLINK) -ldb -lpthread
+
+ssfilter.c: ssfilter.y
+ bison ssfilter.y -o ssfilter.c
+
+lnstat: $(LNSTATOBJ)
+
+install: all
+ install -m 0755 $(TARGETS) $(DESTDIR)$(SBINDIR)
+ ln -sf lnstat $(DESTDIR)$(SBINDIR)/rtstat
+ ln -sf lnstat $(DESTDIR)$(SBINDIR)/ctstat
+
+clean:
+ rm -f *.o $(TARGETS) ssfilter.c
diff --git a/iproute2/misc/arpd.c b/iproute2/misc/arpd.c
new file mode 100644
index 0000000..6bb9bd1
--- /dev/null
+++ b/iproute2/misc/arpd.c
@@ -0,0 +1,841 @@
+/*
+ * arpd.c ARP helper daemon.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ */
+
+#include <stdio.h>
+#include <syslog.h>
+#include <malloc.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <netdb.h>
+#include <db_185.h>
+#include <sys/ioctl.h>
+#include <sys/poll.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <sys/uio.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <time.h>
+#include <signal.h>
+#include <linux/if.h>
+#include <linux/if_ether.h>
+#include <linux/if_arp.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <linux/if_packet.h>
+#include <linux/filter.h>
+
+#include "libnetlink.h"
+#include "utils.h"
+#include "rt_names.h"
+
+int resolve_hosts;
+
+DB *dbase;
+char *dbname = "/var/lib/arpd/arpd.db";
+
+int ifnum;
+int *ifvec;
+char **ifnames;
+
+struct dbkey
+{
+ __u32 iface;
+ __u32 addr;
+};
+
+#define IS_NEG(x) (((__u8*)(x))[0] == 0xFF)
+#define NEG_TIME(x) (((x)[2]<<24)|((x)[3]<<16)|((x)[4]<<8)|(x)[5])
+#define NEG_AGE(x) ((__u32)time(NULL) - NEG_TIME((__u8*)x))
+#define NEG_VALID(x) (NEG_AGE(x) < negative_timeout)
+#define NEG_CNT(x) (((__u8*)(x))[1])
+
+struct rtnl_handle rth;
+
+struct pollfd pset[2];
+int udp_sock = -1;
+
+volatile int do_exit;
+volatile int do_sync;
+volatile int do_stats;
+
+struct {
+ unsigned long arp_new;
+ unsigned long arp_change;
+
+ unsigned long app_recv;
+ unsigned long app_success;
+ unsigned long app_bad;
+ unsigned long app_neg;
+ unsigned long app_suppressed;
+
+ unsigned long kern_neg;
+ unsigned long kern_new;
+ unsigned long kern_change;
+
+ unsigned long probes_sent;
+ unsigned long probes_suppressed;
+} stats;
+
+int active_probing;
+int negative_timeout = 60;
+int no_kernel_broadcasts;
+int broadcast_rate = 1000;
+int broadcast_burst = 3000;
+int poll_timeout = 30000;
+
+static void usage(void)
+{
+ fprintf(stderr,
+ "Usage: arpd [ -lkh? ] [ -a N ] [ -b dbase ] [ -B number ]"
+ " [ -f file ] [ -n time ] [-p interval ] [ -R rate ] [ interfaces ]\n");
+ exit(1);
+}
+
+static int handle_if(int ifindex)
+{
+ int i;
+
+ if (ifnum == 0)
+ return 1;
+
+ for (i=0; i<ifnum; i++)
+ if (ifvec[i] == ifindex)
+ return 1;
+ return 0;
+}
+
+int sysctl_adjusted;
+
+static void do_sysctl_adjustments(void)
+{
+ int i;
+
+ if (!ifnum)
+ return;
+
+ for (i=0; i<ifnum; i++) {
+ char buf[128];
+ FILE *fp;
+
+ if (active_probing) {
+ sprintf(buf, "/proc/sys/net/ipv4/neigh/%s/mcast_solicit", ifnames[i]);
+ if ((fp = fopen(buf, "w")) != NULL) {
+ if (no_kernel_broadcasts)
+ strcpy(buf, "0\n");
+ else
+ sprintf(buf, "%d\n", active_probing>=2 ? 1 : 3-active_probing);
+ fputs(buf, fp);
+ fclose(fp);
+ }
+ }
+
+ sprintf(buf, "/proc/sys/net/ipv4/neigh/%s/app_solicit", ifnames[i]);
+ if ((fp = fopen(buf, "w")) != NULL) {
+ sprintf(buf, "%d\n", active_probing<=1 ? 1 : active_probing);
+ fputs(buf, fp);
+ fclose(fp);
+ }
+ }
+ sysctl_adjusted = 1;
+}
+
+static void undo_sysctl_adjustments(void)
+{
+ int i;
+
+ if (!sysctl_adjusted)
+ return;
+
+ for (i=0; i<ifnum; i++) {
+ char buf[128];
+ FILE *fp;
+
+ if (active_probing) {
+ sprintf(buf, "/proc/sys/net/ipv4/neigh/%s/mcast_solicit", ifnames[i]);
+ if ((fp = fopen(buf, "w")) != NULL) {
+ strcpy(buf, "3\n");
+ fputs(buf, fp);
+ fclose(fp);
+ }
+ }
+ sprintf(buf, "/proc/sys/net/ipv4/neigh/%s/app_solicit", ifnames[i]);
+ if ((fp = fopen(buf, "w")) != NULL) {
+ strcpy(buf, "0\n");
+ fputs(buf, fp);
+ fclose(fp);
+ }
+ }
+ sysctl_adjusted = 0;
+}
+
+
+static int send_probe(int ifindex, __u32 addr)
+{
+ struct ifreq ifr;
+ struct sockaddr_in dst;
+ socklen_t len;
+ unsigned char buf[256];
+ struct arphdr *ah = (struct arphdr*)buf;
+ unsigned char *p = (unsigned char *)(ah+1);
+ struct sockaddr_ll sll;
+
+ memset(&ifr, 0, sizeof(ifr));
+ ifr.ifr_ifindex = ifindex;
+ if (ioctl(udp_sock, SIOCGIFNAME, &ifr))
+ return -1;
+ if (ioctl(udp_sock, SIOCGIFHWADDR, &ifr))
+ return -1;
+ if (ifr.ifr_hwaddr.sa_family != ARPHRD_ETHER)
+ return -1;
+ if (setsockopt(udp_sock, SOL_SOCKET, SO_BINDTODEVICE, ifr.ifr_name, strlen(ifr.ifr_name)+1) < 0)
+ return -1;
+
+ dst.sin_family = AF_INET;
+ dst.sin_port = htons(1025);
+ dst.sin_addr.s_addr = addr;
+ if (connect(udp_sock, (struct sockaddr*)&dst, sizeof(dst)) < 0)
+ return -1;
+ len = sizeof(dst);
+ if (getsockname(udp_sock, (struct sockaddr*)&dst, &len) < 0)
+ return -1;
+
+ ah->ar_hrd = htons(ifr.ifr_hwaddr.sa_family);
+ ah->ar_pro = htons(ETH_P_IP);
+ ah->ar_hln = 6;
+ ah->ar_pln = 4;
+ ah->ar_op = htons(ARPOP_REQUEST);
+
+ memcpy(p, ifr.ifr_hwaddr.sa_data, ah->ar_hln);
+ p += ah->ar_hln;
+
+ memcpy(p, &dst.sin_addr, 4);
+ p+=4;
+
+ sll.sll_family = AF_PACKET;
+ memset(sll.sll_addr, 0xFF, sizeof(sll.sll_addr));
+ sll.sll_ifindex = ifindex;
+ sll.sll_protocol = htons(ETH_P_ARP);
+ memcpy(p, &sll.sll_addr, ah->ar_hln);
+ p+=ah->ar_hln;
+
+ memcpy(p, &addr, 4);
+ p+=4;
+
+ if (sendto(pset[0].fd, buf, p-buf, 0, (struct sockaddr*)&sll, sizeof(sll)) < 0)
+ return -1;
+ stats.probes_sent++;
+ return 0;
+}
+
+/* Be very tough on sending probes: 1 per second with burst of 3. */
+
+static int queue_active_probe(int ifindex, __u32 addr)
+{
+ static struct timeval prev;
+ static int buckets;
+ struct timeval now;
+
+ gettimeofday(&now, NULL);
+ if (prev.tv_sec) {
+ int diff = (now.tv_sec-prev.tv_sec)*1000+(now.tv_usec-prev.tv_usec)/1000;
+ buckets += diff;
+ } else {
+ buckets = broadcast_burst;
+ }
+ if (buckets > broadcast_burst)
+ buckets = broadcast_burst;
+ if (buckets >= broadcast_rate && !send_probe(ifindex, addr)) {
+ buckets -= broadcast_rate;
+ prev = now;
+ return 0;
+ }
+ stats.probes_suppressed++;
+ return -1;
+}
+
+static int respond_to_kernel(int ifindex, __u32 addr, char *lla, int llalen)
+{
+ struct {
+ struct nlmsghdr n;
+ struct ndmsg ndm;
+ char buf[256];
+ } req;
+
+ memset(&req.n, 0, sizeof(req.n));
+ memset(&req.ndm, 0, sizeof(req.ndm));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ndmsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = RTM_NEWNEIGH;
+ req.ndm.ndm_family = AF_INET;
+ req.ndm.ndm_state = NUD_STALE;
+ req.ndm.ndm_ifindex = ifindex;
+ req.ndm.ndm_type = RTN_UNICAST;
+
+ addattr_l(&req.n, sizeof(req), NDA_DST, &addr, 4);
+ addattr_l(&req.n, sizeof(req), NDA_LLADDR, lla, llalen);
+ return rtnl_send(&rth, &req, req.n.nlmsg_len) <= 0;
+}
+
+static void prepare_neg_entry(__u8 *ndata, __u32 stamp)
+{
+ ndata[0] = 0xFF;
+ ndata[1] = 0;
+ ndata[2] = stamp>>24;
+ ndata[3] = stamp>>16;
+ ndata[4] = stamp>>8;
+ ndata[5] = stamp;
+}
+
+
+static int do_one_request(struct nlmsghdr *n)
+{
+ struct ndmsg *ndm = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr * tb[NDA_MAX+1];
+ struct dbkey key;
+ DBT dbkey, dbdat;
+ int do_acct = 0;
+
+ if (n->nlmsg_type == NLMSG_DONE) {
+ dbase->sync(dbase, 0);
+
+ /* Now we have at least mirror of kernel db, so that
+ * may start real resolution.
+ */
+ do_sysctl_adjustments();
+ return 0;
+ }
+
+ if (n->nlmsg_type != RTM_GETNEIGH && n->nlmsg_type != RTM_NEWNEIGH)
+ return 0;
+
+ len -= NLMSG_LENGTH(sizeof(*ndm));
+ if (len < 0)
+ return -1;
+
+ if (ndm->ndm_family != AF_INET ||
+ (ifnum && !handle_if(ndm->ndm_ifindex)) ||
+ ndm->ndm_flags ||
+ ndm->ndm_type != RTN_UNICAST ||
+ !(ndm->ndm_state&~NUD_NOARP))
+ return 0;
+
+ parse_rtattr(tb, NDA_MAX, NDA_RTA(ndm), len);
+
+ if (!tb[NDA_DST])
+ return 0;
+
+ key.iface = ndm->ndm_ifindex;
+ memcpy(&key.addr, RTA_DATA(tb[NDA_DST]), 4);
+ dbkey.data = &key;
+ dbkey.size = sizeof(key);
+
+ if (dbase->get(dbase, &dbkey, &dbdat, 0) != 0) {
+ dbdat.data = 0;
+ dbdat.size = 0;
+ }
+
+ if (n->nlmsg_type == RTM_GETNEIGH) {
+ if (!(n->nlmsg_flags&NLM_F_REQUEST))
+ return 0;
+
+ if (!(ndm->ndm_state&(NUD_PROBE|NUD_INCOMPLETE))) {
+ stats.app_bad++;
+ return 0;
+ }
+
+ if (ndm->ndm_state&NUD_PROBE) {
+ /* If we get this, kernel still has some valid
+ * address, but unicast probing failed and host
+ * is either dead or changed its mac address.
+ * Kernel is going to initiate broadcast resolution.
+ * OK, we invalidate our information as well.
+ */
+ if (dbdat.data && !IS_NEG(dbdat.data))
+ stats.app_neg++;
+
+ dbase->del(dbase, &dbkey, 0);
+ } else {
+ /* If we get this kernel does not have any information.
+ * If we have something tell this to kernel. */
+ stats.app_recv++;
+ if (dbdat.data && !IS_NEG(dbdat.data)) {
+ stats.app_success++;
+ respond_to_kernel(key.iface, key.addr, dbdat.data, dbdat.size);
+ return 0;
+ }
+
+ /* Sheeit! We have nothing to tell. */
+ /* If we have recent negative entry, be silent. */
+ if (dbdat.data && NEG_VALID(dbdat.data)) {
+ if (NEG_CNT(dbdat.data) >= active_probing) {
+ stats.app_suppressed++;
+ return 0;
+ }
+ do_acct = 1;
+ }
+ }
+
+ if (active_probing &&
+ queue_active_probe(ndm->ndm_ifindex, key.addr) == 0 &&
+ do_acct) {
+ NEG_CNT(dbdat.data)++;
+ dbase->put(dbase, &dbkey, &dbdat, 0);
+ }
+ } else if (n->nlmsg_type == RTM_NEWNEIGH) {
+ if (n->nlmsg_flags&NLM_F_REQUEST)
+ return 0;
+
+ if (ndm->ndm_state&NUD_FAILED) {
+ /* Kernel was not able to resolve. Host is dead.
+ * Create negative entry if it is not present
+ * or renew it if it is too old. */
+ if (!dbdat.data ||
+ !IS_NEG(dbdat.data) ||
+ !NEG_VALID(dbdat.data)) {
+ __u8 ndata[6];
+ stats.kern_neg++;
+ prepare_neg_entry(ndata, time(NULL));
+ dbdat.data = ndata;
+ dbdat.size = sizeof(ndata);
+ dbase->put(dbase, &dbkey, &dbdat, 0);
+ }
+ } else if (tb[NDA_LLADDR]) {
+ if (dbdat.data && !IS_NEG(dbdat.data)) {
+ if (memcmp(RTA_DATA(tb[NDA_LLADDR]), dbdat.data, dbdat.size) == 0)
+ return 0;
+ stats.kern_change++;
+ } else {
+ stats.kern_new++;
+ }
+ dbdat.data = RTA_DATA(tb[NDA_LLADDR]);
+ dbdat.size = RTA_PAYLOAD(tb[NDA_LLADDR]);
+ dbase->put(dbase, &dbkey, &dbdat, 0);
+ }
+ }
+ return 0;
+}
+
+static void load_initial_table(void)
+{
+ if (rtnl_wilddump_request(&rth, AF_INET, RTM_GETNEIGH) < 0) {
+ perror("dump request failed");
+ exit(1);
+ }
+
+}
+
+static void get_kern_msg(void)
+{
+ int status;
+ struct nlmsghdr *h;
+ struct sockaddr_nl nladdr;
+ struct iovec iov;
+ char buf[8192];
+ struct msghdr msg = {
+ (void*)&nladdr, sizeof(nladdr),
+ &iov, 1,
+ NULL, 0,
+ 0
+ };
+
+ memset(&nladdr, 0, sizeof(nladdr));
+
+ iov.iov_base = buf;
+ iov.iov_len = sizeof(buf);
+
+ status = recvmsg(rth.fd, &msg, MSG_DONTWAIT);
+
+ if (status <= 0)
+ return;
+
+ if (msg.msg_namelen != sizeof(nladdr))
+ return;
+
+ if (nladdr.nl_pid)
+ return;
+
+ for (h = (struct nlmsghdr*)buf; status >= sizeof(*h); ) {
+ int len = h->nlmsg_len;
+ int l = len - sizeof(*h);
+
+ if (l < 0 || len > status)
+ return;
+
+ if (do_one_request(h) < 0)
+ return;
+
+ status -= NLMSG_ALIGN(len);
+ h = (struct nlmsghdr*)((char*)h + NLMSG_ALIGN(len));
+ }
+}
+
+/* Receive gratuitous ARP messages and store them, that's all. */
+static void get_arp_pkt(void)
+{
+ unsigned char buf[1024];
+ struct sockaddr_ll sll;
+ socklen_t sll_len = sizeof(sll);
+ struct arphdr *a = (struct arphdr*)buf;
+ struct dbkey key;
+ DBT dbkey, dbdat;
+ int n;
+
+ n = recvfrom(pset[0].fd, buf, sizeof(buf), MSG_DONTWAIT,
+ (struct sockaddr*)&sll, &sll_len);
+ if (n < 0) {
+ if (errno != EINTR && errno != EAGAIN)
+ syslog(LOG_ERR, "recvfrom: %m");
+ return;
+ }
+
+ if (ifnum && !handle_if(sll.sll_ifindex))
+ return;
+
+ /* Sanity checks */
+
+ if (n < sizeof(*a) ||
+ (a->ar_op != htons(ARPOP_REQUEST) &&
+ a->ar_op != htons(ARPOP_REPLY)) ||
+ a->ar_pln != 4 ||
+ a->ar_pro != htons(ETH_P_IP) ||
+ a->ar_hln != sll.sll_halen ||
+ sizeof(*a) + 2*4 + 2*a->ar_hln > n)
+ return;
+
+ key.iface = sll.sll_ifindex;
+ memcpy(&key.addr, (char*)(a+1) + a->ar_hln, 4);
+
+ /* DAD message, ignore. */
+ if (key.addr == 0)
+ return;
+
+ dbkey.data = &key;
+ dbkey.size = sizeof(key);
+
+ if (dbase->get(dbase, &dbkey, &dbdat, 0) == 0 && !IS_NEG(dbdat.data)) {
+ if (memcmp(dbdat.data, a+1, dbdat.size) == 0)
+ return;
+ stats.arp_change++;
+ } else {
+ stats.arp_new++;
+ }
+
+ dbdat.data = a+1;
+ dbdat.size = a->ar_hln;
+ dbase->put(dbase, &dbkey, &dbdat, 0);
+}
+
+static void catch_signal(int sig, void (*handler)(int))
+{
+ struct sigaction sa;
+
+ memset(&sa, 0, sizeof(sa));
+ sa.sa_handler = handler;
+#ifdef SA_INTERRUPT
+ sa.sa_flags = SA_INTERRUPT;
+#endif
+ sigaction(sig, &sa, NULL);
+}
+
+#include <setjmp.h>
+sigjmp_buf env;
+volatile int in_poll;
+
+static void sig_exit(int signo)
+{
+ do_exit = 1;
+ if (in_poll)
+ siglongjmp(env, 1);
+}
+
+static void sig_sync(int signo)
+{
+ do_sync = 1;
+ if (in_poll)
+ siglongjmp(env, 1);
+}
+
+static void sig_stats(int signo)
+{
+ do_sync = 1;
+ do_stats = 1;
+ if (in_poll)
+ siglongjmp(env, 1);
+}
+
+static void send_stats(void)
+{
+ syslog(LOG_INFO, "arp_rcv: n%lu c%lu app_rcv: tot %lu hits %lu bad %lu neg %lu sup %lu",
+ stats.arp_new, stats.arp_change,
+
+ stats.app_recv, stats.app_success,
+ stats.app_bad, stats.app_neg, stats.app_suppressed
+ );
+ syslog(LOG_INFO, "kern: n%lu c%lu neg %lu arp_send: %lu rlim %lu",
+ stats.kern_new, stats.kern_change, stats.kern_neg,
+
+ stats.probes_sent, stats.probes_suppressed
+ );
+ do_stats = 0;
+}
+
+
+int main(int argc, char **argv)
+{
+ int opt;
+ int do_list = 0;
+ char *do_load = NULL;
+
+ while ((opt = getopt(argc, argv, "h?b:lf:a:n:p:kR:B:")) != EOF) {
+ switch (opt) {
+ case 'b':
+ dbname = optarg;
+ break;
+ case 'f':
+ if (do_load) {
+ fprintf(stderr, "Duplicate option -f\n");
+ usage();
+ }
+ do_load = optarg;
+ break;
+ case 'l':
+ do_list = 1;
+ break;
+ case 'a':
+ active_probing = atoi(optarg);
+ break;
+ case 'n':
+ negative_timeout = atoi(optarg);
+ break;
+ case 'k':
+ no_kernel_broadcasts = 1;
+ break;
+ case 'p':
+ if ((poll_timeout = 1000 * strtod(optarg, NULL)) < 100) {
+ fprintf(stderr,"Invalid poll timeout\n");
+ exit(-1);
+ }
+ break;
+ case 'R':
+ if ((broadcast_rate = atoi(optarg)) <= 0 ||
+ (broadcast_rate = 1000/broadcast_rate) <= 0) {
+ fprintf(stderr, "Invalid ARP rate\n");
+ exit(-1);
+ }
+ break;
+ case 'B':
+ if ((broadcast_burst = atoi(optarg)) <= 0 ||
+ (broadcast_burst = 1000*broadcast_burst) <= 0) {
+ fprintf(stderr, "Invalid ARP burst\n");
+ exit(-1);
+ }
+ break;
+ case 'h':
+ case '?':
+ default:
+ usage();
+ }
+ }
+ argc -= optind;
+ argv += optind;
+
+ if (argc > 0) {
+ ifnum = argc;
+ ifnames = argv;
+ ifvec = malloc(argc*sizeof(int));
+ if (!ifvec) {
+ perror("malloc");
+ exit(-1);
+ }
+ }
+
+ if ((udp_sock = socket(AF_INET, SOCK_DGRAM, 0)) < 0) {
+ perror("socket");
+ exit(-1);
+ }
+
+ if (ifnum) {
+ int i;
+ struct ifreq ifr;
+ memset(&ifr, 0, sizeof(ifr));
+ for (i=0; i<ifnum; i++) {
+ strncpy(ifr.ifr_name, ifnames[i], IFNAMSIZ);
+ if (ioctl(udp_sock, SIOCGIFINDEX, &ifr)) {
+ perror("ioctl(SIOCGIFINDEX)");
+ exit(-1);;
+ }
+ ifvec[i] = ifr.ifr_ifindex;
+ }
+ }
+
+ dbase = dbopen(dbname, O_CREAT|O_RDWR, 0644, DB_HASH, NULL);
+ if (dbase == NULL) {
+ perror("db_open");
+ exit(-1);
+ }
+
+ if (do_load) {
+ char buf[128];
+ FILE *fp;
+ struct dbkey k;
+ DBT dbkey, dbdat;
+
+ dbkey.data = &k;
+ dbkey.size = sizeof(k);
+
+ if (strcmp(do_load, "-") == 0 || strcmp(do_load, "--") == 0) {
+ fp = stdin;
+ } else if ((fp = fopen(do_load, "r")) == NULL) {
+ perror("fopen");
+ goto do_abort;
+ }
+
+ buf[sizeof(buf)-1] = 0;
+ while (fgets(buf, sizeof(buf), fp)) {
+ __u8 b1[6];
+ char ipbuf[128];
+ char macbuf[128];
+
+ if (buf[0] == '#')
+ continue;
+
+ if (sscanf(buf, "%u%s%s", &k.iface, ipbuf, macbuf) != 3) {
+ fprintf(stderr, "Wrong format of input file \"%s\"\n", do_load);
+ goto do_abort;
+ }
+ if (strncmp(macbuf, "FAILED:", 7) == 0)
+ continue;
+ if (!inet_aton(ipbuf, (struct in_addr*)&k.addr)) {
+ fprintf(stderr, "Invalid IP address: \"%s\"\n", ipbuf);
+ goto do_abort;
+ }
+
+ if (ll_addr_a2n((char *) b1, 6, macbuf) != 6)
+ goto do_abort;
+ dbdat.size = 6;
+
+ if (dbase->put(dbase, &dbkey, &dbdat, 0)) {
+ perror("hash->put");
+ goto do_abort;
+ }
+ }
+ dbase->sync(dbase, 0);
+ if (fp != stdin)
+ fclose(fp);
+ }
+
+ if (do_list) {
+ DBT dbkey, dbdat;
+ printf("%-8s %-15s %s\n", "#Ifindex", "IP", "MAC");
+ while (dbase->seq(dbase, &dbkey, &dbdat, R_NEXT) == 0) {
+ struct dbkey *key = dbkey.data;
+ if (handle_if(key->iface)) {
+ if (!IS_NEG(dbdat.data)) {
+ char b1[18];
+ printf("%-8d %-15s %s\n",
+ key->iface,
+ inet_ntoa(*(struct in_addr*)&key->addr),
+ ll_addr_n2a(dbdat.data, 6, ARPHRD_ETHER, b1, 18));
+ } else {
+ printf("%-8d %-15s FAILED: %dsec ago\n",
+ key->iface,
+ inet_ntoa(*(struct in_addr*)&key->addr),
+ NEG_AGE(dbdat.data));
+ }
+ }
+ }
+ }
+
+ if (do_load || do_list)
+ goto out;
+
+ pset[0].fd = socket(PF_PACKET, SOCK_DGRAM, 0);
+ if (pset[0].fd < 0) {
+ perror("socket");
+ exit(-1);
+ }
+
+ if (1) {
+ struct sockaddr_ll sll;
+ memset(&sll, 0, sizeof(sll));
+ sll.sll_family = AF_PACKET;
+ sll.sll_protocol = htons(ETH_P_ARP);
+ sll.sll_ifindex = (ifnum == 1 ? ifvec[0] : 0);
+ if (bind(pset[0].fd, (struct sockaddr*)&sll, sizeof(sll)) < 0) {
+ perror("bind");
+ goto do_abort;
+ }
+ }
+
+ if (rtnl_open(&rth, RTMGRP_NEIGH) < 0) {
+ perror("rtnl_open");
+ goto do_abort;
+ }
+ pset[1].fd = rth.fd;
+
+ load_initial_table();
+
+ if (daemon(0, 0)) {
+ perror("arpd: daemon");
+ goto do_abort;
+ }
+
+ openlog("arpd", LOG_PID | LOG_CONS, LOG_DAEMON);
+ catch_signal(SIGINT, sig_exit);
+ catch_signal(SIGTERM, sig_exit);
+ catch_signal(SIGHUP, sig_sync);
+ catch_signal(SIGUSR1, sig_stats);
+
+#define EVENTS (POLLIN|POLLPRI|POLLERR|POLLHUP)
+ pset[0].events = EVENTS;
+ pset[0].revents = 0;
+ pset[1].events = EVENTS;
+ pset[1].revents = 0;
+
+ sigsetjmp(env, 1);
+
+ for (;;) {
+ in_poll = 1;
+
+ if (do_exit)
+ break;
+ if (do_sync) {
+ in_poll = 0;
+ dbase->sync(dbase, 0);
+ do_sync = 0;
+ in_poll = 1;
+ }
+ if (do_stats)
+ send_stats();
+ if (poll(pset, 2, poll_timeout) > 0) {
+ in_poll = 0;
+ if (pset[0].revents&EVENTS)
+ get_arp_pkt();
+ if (pset[1].revents&EVENTS)
+ get_kern_msg();
+ } else {
+ do_sync = 1;
+ }
+ }
+
+ undo_sysctl_adjustments();
+out:
+ dbase->close(dbase);
+ exit(0);
+
+do_abort:
+ dbase->close(dbase);
+ exit(-1);
+}
diff --git a/iproute2/misc/ifstat.c b/iproute2/misc/ifstat.c
new file mode 100644
index 0000000..ac5c29c
--- /dev/null
+++ b/iproute2/misc/ifstat.c
@@ -0,0 +1,875 @@
+/*
+ * ifstat.c handy utility to read net interface statistics
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <string.h>
+#include <errno.h>
+#include <time.h>
+#include <sys/time.h>
+#include <fnmatch.h>
+#include <sys/file.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+#include <sys/poll.h>
+#include <sys/wait.h>
+#include <sys/stat.h>
+#include <signal.h>
+#include <math.h>
+#include <getopt.h>
+
+#include <libnetlink.h>
+#include <json_writer.h>
+#include <linux/if.h>
+#include <linux/if_link.h>
+
+#include <SNAPSHOT.h>
+
+int dump_zeros = 0;
+int reset_history = 0;
+int ignore_history = 0;
+int no_output = 0;
+int json_output = 0;
+int no_update = 0;
+int scan_interval = 0;
+int time_constant = 0;
+int show_errors = 0;
+int pretty;
+double W;
+char **patterns;
+int npatterns;
+
+char info_source[128];
+int source_mismatch;
+
+#define MAXS (sizeof(struct rtnl_link_stats)/sizeof(__u32))
+
+struct ifstat_ent
+{
+ struct ifstat_ent *next;
+ char *name;
+ int ifindex;
+ unsigned long long val[MAXS];
+ double rate[MAXS];
+ __u32 ival[MAXS];
+};
+
+static const char *stats[MAXS] = {
+ "rx_packets",
+ "tx_packets",
+ "rx_bytes",
+ "tx_bytes",
+ "rx_errors",
+ "tx_errors",
+ "rx_dropped",
+ "tx_dropped",
+ "multicast",
+ "collisions",
+ "rx_length_errors",
+ "rx_over_errors",
+ "rx_crc_errors",
+ "rx_frame_errors",
+ "rx_fifo_errors",
+ "rx_missed_errors",
+ "tx_aborted_errors",
+ "tx_carrier_errors",
+ "tx_fifo_errors",
+ "tx_heartbeat_errors",
+ "tx_window_errors",
+ "rx_compressed",
+ "tx_compressed"
+};
+
+struct ifstat_ent *kern_db;
+struct ifstat_ent *hist_db;
+
+static int match(const char *id)
+{
+ int i;
+
+ if (npatterns == 0)
+ return 1;
+
+ for (i=0; i<npatterns; i++) {
+ if (!fnmatch(patterns[i], id, 0))
+ return 1;
+ }
+ return 0;
+}
+
+static int get_nlmsg(const struct sockaddr_nl *who,
+ struct nlmsghdr *m, void *arg)
+{
+ struct ifinfomsg *ifi = NLMSG_DATA(m);
+ struct rtattr * tb[IFLA_MAX+1];
+ int len = m->nlmsg_len;
+ struct ifstat_ent *n;
+ int i;
+
+ if (m->nlmsg_type != RTM_NEWLINK)
+ return 0;
+
+ len -= NLMSG_LENGTH(sizeof(*ifi));
+ if (len < 0)
+ return -1;
+
+ if (!(ifi->ifi_flags&IFF_UP))
+ return 0;
+
+ parse_rtattr(tb, IFLA_MAX, IFLA_RTA(ifi), len);
+ if (tb[IFLA_IFNAME] == NULL || tb[IFLA_STATS] == NULL)
+ return 0;
+
+ n = malloc(sizeof(*n));
+ if (!n)
+ abort();
+ n->ifindex = ifi->ifi_index;
+ n->name = strdup(RTA_DATA(tb[IFLA_IFNAME]));
+ memcpy(&n->ival, RTA_DATA(tb[IFLA_STATS]), sizeof(n->ival));
+ memset(&n->rate, 0, sizeof(n->rate));
+ for (i=0; i<MAXS; i++)
+ n->val[i] = n->ival[i];
+ n->next = kern_db;
+ kern_db = n;
+ return 0;
+}
+
+static void load_info(void)
+{
+ struct ifstat_ent *db, *n;
+ struct rtnl_handle rth;
+
+ if (rtnl_open(&rth, 0) < 0)
+ exit(1);
+
+ if (rtnl_wilddump_request(&rth, AF_INET, RTM_GETLINK) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+
+ if (rtnl_dump_filter(&rth, get_nlmsg, NULL) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ exit(1);
+ }
+
+ rtnl_close(&rth);
+
+ db = kern_db;
+ kern_db = NULL;
+
+ while (db) {
+ n = db;
+ db = db->next;
+ n->next = kern_db;
+ kern_db = n;
+ }
+}
+
+static void load_raw_table(FILE *fp)
+{
+ char buf[4096];
+ struct ifstat_ent *db = NULL;
+ struct ifstat_ent *n;
+
+ while (fgets(buf, sizeof(buf), fp) != NULL) {
+ char *p;
+ char *next;
+ int i;
+
+ if (buf[0] == '#') {
+ buf[strlen(buf)-1] = 0;
+ if (info_source[0] && strcmp(info_source, buf+1))
+ source_mismatch = 1;
+ strncpy(info_source, buf+1, sizeof(info_source)-1);
+ continue;
+ }
+ if ((n = malloc(sizeof(*n))) == NULL)
+ abort();
+
+ if (!(p = strchr(buf, ' ')))
+ abort();
+ *p++ = 0;
+
+ if (sscanf(buf, "%d", &n->ifindex) != 1)
+ abort();
+ if (!(next = strchr(p, ' ')))
+ abort();
+ *next++ = 0;
+
+ n->name = strdup(p);
+ p = next;
+
+ for (i=0; i<MAXS; i++) {
+ unsigned rate;
+ if (!(next = strchr(p, ' ')))
+ abort();
+ *next++ = 0;
+ if (sscanf(p, "%llu", n->val+i) != 1)
+ abort();
+ n->ival[i] = (__u32)n->val[i];
+ p = next;
+ if (!(next = strchr(p, ' ')))
+ abort();
+ *next++ = 0;
+ if (sscanf(p, "%u", &rate) != 1)
+ abort();
+ n->rate[i] = rate;
+ p = next;
+ }
+ n->next = db;
+ db = n;
+ }
+
+ while (db) {
+ n = db;
+ db = db->next;
+ n->next = kern_db;
+ kern_db = n;
+ }
+}
+
+static void dump_raw_db(FILE *fp, int to_hist)
+{
+ json_writer_t *jw = json_output ? jsonw_new(fp) : NULL;
+ struct ifstat_ent *n, *h;
+
+ h = hist_db;
+ if (jw) {
+ jsonw_pretty(jw, pretty);
+ jsonw_name(jw, info_source);
+ jsonw_start_object(jw);
+ } else
+ fprintf(fp, "#%s\n", info_source);
+
+ for (n=kern_db; n; n=n->next) {
+ int i;
+ unsigned long long *vals = n->val;
+ double *rates = n->rate;
+ if (!match(n->name)) {
+ struct ifstat_ent *h1;
+ if (!to_hist)
+ continue;
+ for (h1 = h; h1; h1 = h1->next) {
+ if (h1->ifindex == n->ifindex) {
+ vals = h1->val;
+ rates = h1->rate;
+ h = h1->next;
+ break;
+ }
+ }
+ }
+
+ if (jw) {
+ jsonw_name(jw, n->name);
+ jsonw_start_object(jw);
+
+ for (i=0; i<MAXS && stats[i]; i++)
+ jsonw_uint_field(jw, stats[i], vals[i]);
+ jsonw_end_object(jw);
+ } else {
+ fprintf(fp, "%d %s ", n->ifindex, n->name);
+ for (i=0; i<MAXS; i++)
+ fprintf(fp, "%llu %u ", vals[i],
+ (unsigned)rates[i]);
+ fprintf(fp, "\n");
+ }
+ }
+ if (jw) {
+ jsonw_end_object(jw);
+ jsonw_destroy(&jw);
+ }
+}
+
+/* use communication definitions of meg/kilo etc */
+static const unsigned long long giga = 1000000000ull;
+static const unsigned long long mega = 1000000;
+static const unsigned long long kilo = 1000;
+
+static void format_rate(FILE *fp, const unsigned long long *vals,
+ const double *rates, int i)
+{
+ char temp[64];
+
+ if (vals[i] > giga)
+ fprintf(fp, "%7lluM ", vals[i]/mega);
+ else if (vals[i] > mega)
+ fprintf(fp, "%7lluK ", vals[i]/kilo);
+ else
+ fprintf(fp, "%8llu ", vals[i]);
+
+ if (rates[i] > mega) {
+ sprintf(temp, "%uM", (unsigned)(rates[i]/mega));
+ fprintf(fp, "%-6s ", temp);
+ } else if (rates[i] > kilo) {
+ sprintf(temp, "%uK", (unsigned)(rates[i]/kilo));
+ fprintf(fp, "%-6s ", temp);
+ } else
+ fprintf(fp, "%-6u ", (unsigned)rates[i]);
+}
+
+static void format_pair(FILE *fp, const unsigned long long *vals, int i, int k)
+{
+ char temp[64];
+ if (vals[i] > giga)
+ fprintf(fp, "%7lluM ", vals[i]/mega);
+ else if (vals[i] > mega)
+ fprintf(fp, "%7lluK ", vals[i]/kilo);
+ else
+ fprintf(fp, "%8llu ", vals[i]);
+
+ if (vals[k] > giga) {
+ sprintf(temp, "%uM", (unsigned)(vals[k]/mega));
+ fprintf(fp, "%-6s ", temp);
+ } else if (vals[k] > mega) {
+ sprintf(temp, "%uK", (unsigned)(vals[k]/kilo));
+ fprintf(fp, "%-6s ", temp);
+ } else
+ fprintf(fp, "%-6u ", (unsigned)vals[k]);
+}
+
+static void print_head(FILE *fp)
+{
+ fprintf(fp, "#%s\n", info_source);
+ fprintf(fp, "%-15s ", "Interface");
+
+ fprintf(fp, "%8s/%-6s ", "RX Pkts", "Rate");
+ fprintf(fp, "%8s/%-6s ", "TX Pkts", "Rate");
+ fprintf(fp, "%8s/%-6s ", "RX Data", "Rate");
+ fprintf(fp, "%8s/%-6s\n","TX Data", "Rate");
+
+ if (!show_errors) {
+ fprintf(fp, "%-15s ", "");
+ fprintf(fp, "%8s/%-6s ", "RX Errs", "Drop");
+ fprintf(fp, "%8s/%-6s ", "TX Errs", "Drop");
+ fprintf(fp, "%8s/%-6s ", "RX Over", "Rate");
+ fprintf(fp, "%8s/%-6s\n","TX Coll", "Rate");
+ } else {
+ fprintf(fp, "%-15s ", "");
+ fprintf(fp, "%8s/%-6s ", "RX Errs", "Rate");
+ fprintf(fp, "%8s/%-6s ", "RX Drop", "Rate");
+ fprintf(fp, "%8s/%-6s ", "RX Over", "Rate");
+ fprintf(fp, "%8s/%-6s\n","RX Leng", "Rate");
+
+ fprintf(fp, "%-15s ", "");
+ fprintf(fp, "%8s/%-6s ", "RX Crc", "Rate");
+ fprintf(fp, "%8s/%-6s ", "RX Frm", "Rate");
+ fprintf(fp, "%8s/%-6s ", "RX Fifo", "Rate");
+ fprintf(fp, "%8s/%-6s\n","RX Miss", "Rate");
+
+ fprintf(fp, "%-15s ", "");
+ fprintf(fp, "%8s/%-6s ", "TX Errs", "Rate");
+ fprintf(fp, "%8s/%-6s ", "TX Drop", "Rate");
+ fprintf(fp, "%8s/%-6s ", "TX Coll", "Rate");
+ fprintf(fp, "%8s/%-6s\n","TX Carr", "Rate");
+
+ fprintf(fp, "%-15s ", "");
+ fprintf(fp, "%8s/%-6s ", "TX Abrt", "Rate");
+ fprintf(fp, "%8s/%-6s ", "TX Fifo", "Rate");
+ fprintf(fp, "%8s/%-6s ", "TX Hear", "Rate");
+ fprintf(fp, "%8s/%-6s\n","TX Wind", "Rate");
+ }
+}
+
+static void print_one_json(json_writer_t *jw, const struct ifstat_ent *n,
+ const unsigned long long *vals)
+{
+ int i, m = show_errors ? 20 : 10;
+
+ jsonw_name(jw, n->name);
+ jsonw_start_object(jw);
+
+ for (i=0; i < m && stats[i]; i++)
+ jsonw_uint_field(jw, stats[i], vals[i]);
+
+ jsonw_end_object(jw);
+}
+
+static void print_one_if(FILE *fp, const struct ifstat_ent *n,
+ const unsigned long long *vals)
+{
+ int i;
+
+ fprintf(fp, "%-15s ", n->name);
+ for (i=0; i<4; i++)
+ format_rate(fp, vals, n->rate, i);
+ fprintf(fp, "\n");
+
+ if (!show_errors) {
+ fprintf(fp, "%-15s ", "");
+ format_pair(fp, vals, 4, 6);
+ format_pair(fp, vals, 5, 7);
+ format_rate(fp, vals, n->rate, 11);
+ format_rate(fp, vals, n->rate, 9);
+ fprintf(fp, "\n");
+ } else {
+ fprintf(fp, "%-15s ", "");
+ format_rate(fp, vals, n->rate, 4);
+ format_rate(fp, vals, n->rate, 6);
+ format_rate(fp, vals, n->rate, 11);
+ format_rate(fp, vals, n->rate, 10);
+ fprintf(fp, "\n");
+
+ fprintf(fp, "%-15s ", "");
+ format_rate(fp, vals, n->rate, 12);
+ format_rate(fp, vals, n->rate, 13);
+ format_rate(fp, vals, n->rate, 14);
+ format_rate(fp, vals, n->rate, 15);
+ fprintf(fp, "\n");
+
+ fprintf(fp, "%-15s ", "");
+ format_rate(fp, vals, n->rate, 5);
+ format_rate(fp, vals, n->rate, 7);
+ format_rate(fp, vals, n->rate, 9);
+ format_rate(fp, vals, n->rate, 17);
+ fprintf(fp, "\n");
+
+ fprintf(fp, "%-15s ", "");
+ format_rate(fp, vals, n->rate, 16);
+ format_rate(fp, vals, n->rate, 18);
+ format_rate(fp, vals, n->rate, 19);
+ format_rate(fp, vals, n->rate, 20);
+ fprintf(fp, "\n");
+ }
+}
+
+static void dump_kern_db(FILE *fp)
+{
+ json_writer_t *jw = json_output ? jsonw_new(fp) : NULL;
+ struct ifstat_ent *n;
+
+ if (jw) {
+ jsonw_pretty(jw, pretty);
+ jsonw_name(jw, info_source);
+ jsonw_start_object(jw);
+ } else
+ print_head(fp);
+
+ for (n=kern_db; n; n=n->next) {
+ if (!match(n->name))
+ continue;
+
+ if (jw)
+ print_one_json(jw, n, n->val);
+ else
+ print_one_if(fp, n, n->val);
+ }
+ if (json_output)
+ fprintf(fp, "\n} }\n");
+}
+
+static void dump_incr_db(FILE *fp)
+{
+ struct ifstat_ent *n, *h;
+ json_writer_t *jw = json_output ? jsonw_new(fp) : NULL;
+
+ h = hist_db;
+ if (jw) {
+ jsonw_pretty(jw, pretty);
+ jsonw_name(jw, info_source);
+ jsonw_start_object(jw);
+ } else
+ print_head(fp);
+
+ for (n=kern_db; n; n=n->next) {
+ int i;
+ unsigned long long vals[MAXS];
+ struct ifstat_ent *h1;
+
+ memcpy(vals, n->val, sizeof(vals));
+
+ for (h1 = h; h1; h1 = h1->next) {
+ if (h1->ifindex == n->ifindex) {
+ for (i = 0; i < MAXS; i++)
+ vals[i] -= h1->val[i];
+ h = h1->next;
+ break;
+ }
+ }
+ if (!match(n->name))
+ continue;
+
+ if (jw)
+ print_one_json(jw, n, n->val);
+ else
+ print_one_if(fp, n, vals);
+ }
+
+ if (jw) {
+ jsonw_end_object(jw);
+ jsonw_destroy(&jw);
+ }
+}
+
+static int children;
+
+static void sigchild(int signo)
+{
+}
+
+static void update_db(int interval)
+{
+ struct ifstat_ent *n, *h;
+
+ n = kern_db;
+ kern_db = NULL;
+
+ load_info();
+
+ h = kern_db;
+ kern_db = n;
+
+ for (n = kern_db; n; n = n->next) {
+ struct ifstat_ent *h1;
+ for (h1 = h; h1; h1 = h1->next) {
+ if (h1->ifindex == n->ifindex) {
+ int i;
+ for (i = 0; i < MAXS; i++) {
+ if ((long)(h1->ival[i] - n->ival[i]) < 0) {
+ memset(n->ival, 0, sizeof(n->ival));
+ break;
+ }
+ }
+ for (i = 0; i < MAXS; i++) {
+ double sample;
+ unsigned long incr = h1->ival[i] - n->ival[i];
+ n->val[i] += incr;
+ n->ival[i] = h1->ival[i];
+ sample = (double)(incr*1000)/interval;
+ if (interval >= scan_interval) {
+ n->rate[i] += W*(sample-n->rate[i]);
+ } else if (interval >= 1000) {
+ if (interval >= time_constant) {
+ n->rate[i] = sample;
+ } else {
+ double w = W*(double)interval/scan_interval;
+ n->rate[i] += w*(sample-n->rate[i]);
+ }
+ }
+ }
+
+ while (h != h1) {
+ struct ifstat_ent *tmp = h;
+ h = h->next;
+ free(tmp->name);
+ free(tmp);
+ };
+ h = h1->next;
+ free(h1->name);
+ free(h1);
+ break;
+ }
+ }
+ }
+}
+
+#define T_DIFF(a,b) (((a).tv_sec-(b).tv_sec)*1000 + ((a).tv_usec-(b).tv_usec)/1000)
+
+
+static void server_loop(int fd)
+{
+ struct timeval snaptime = { 0 };
+ struct pollfd p;
+ p.fd = fd;
+ p.events = p.revents = POLLIN;
+
+ sprintf(info_source, "%d.%lu sampling_interval=%d time_const=%d",
+ getpid(), (unsigned long)random(), scan_interval/1000, time_constant/1000);
+
+ load_info();
+
+ for (;;) {
+ int status;
+ int tdiff;
+ struct timeval now;
+
+ gettimeofday(&now, NULL);
+ tdiff = T_DIFF(now, snaptime);
+ if (tdiff >= scan_interval) {
+ update_db(tdiff);
+ snaptime = now;
+ tdiff = 0;
+ }
+
+ if (poll(&p, 1, tdiff + scan_interval) > 0
+ && (p.revents&POLLIN)) {
+ int clnt = accept(fd, NULL, NULL);
+ if (clnt >= 0) {
+ pid_t pid;
+ if (children >= 5) {
+ close(clnt);
+ } else if ((pid = fork()) != 0) {
+ if (pid>0)
+ children++;
+ close(clnt);
+ } else {
+ FILE *fp = fdopen(clnt, "w");
+ if (fp) {
+ if (tdiff > 0)
+ update_db(tdiff);
+ dump_raw_db(fp, 0);
+ }
+ exit(0);
+ }
+ }
+ }
+ while (children && waitpid(-1, &status, WNOHANG) > 0)
+ children--;
+ }
+}
+
+static int verify_forging(int fd)
+{
+ struct ucred cred;
+ socklen_t olen = sizeof(cred);
+
+ if (getsockopt(fd, SOL_SOCKET, SO_PEERCRED, (void*)&cred, &olen) ||
+ olen < sizeof(cred))
+ return -1;
+ if (cred.uid == getuid() || cred.uid == 0)
+ return 0;
+ return -1;
+}
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr,
+"Usage: ifstat [OPTION] [ PATTERN [ PATTERN ] ]\n"
+" -h, --help this message\n"
+" -a, --ignore ignore history\n"
+" -d, --scan=SECS sample every statistics every SECS\n"
+" -e, --errors show errors\n"
+" -j, --json format output in JSON\n"
+" -n, --nooutput do history only\n"
+" -p, --pretty pretty print\n"
+" -r, --reset reset history\n"
+" -s, --noupdate don\'t update history\n"
+" -t, --interval=SECS report average over the last SECS\n"
+" -V, --version output version information\n"
+" -z, --zeros show entries with zero activity\n");
+
+ exit(-1);
+}
+
+static const struct option longopts[] = {
+ { "help", 0, 0, 'h' },
+ { "ignore", 0, 0, 'a' },
+ { "scan", 1, 0, 'd'},
+ { "errors", 0, 0, 'e' },
+ { "nooutput", 0, 0, 'n' },
+ { "json", 0, 0, 'j' },
+ { "reset", 0, 0, 'r' },
+ { "pretty", 0, 0, 'p' },
+ { "noupdate", 0, 0, 's' },
+ { "interval", 1, 0, 't' },
+ { "version", 0, 0, 'V' },
+ { "zeros", 0, 0, 'z' },
+ { 0 }
+};
+
+int main(int argc, char *argv[])
+{
+ char hist_name[128];
+ struct sockaddr_un sun;
+ FILE *hist_fp = NULL;
+ int ch;
+ int fd;
+
+ while ((ch = getopt_long(argc, argv, "hjpvVzrnasd:t:e",
+ longopts, NULL)) != EOF) {
+ switch(ch) {
+ case 'z':
+ dump_zeros = 1;
+ break;
+ case 'r':
+ reset_history = 1;
+ break;
+ case 'a':
+ ignore_history = 1;
+ break;
+ case 's':
+ no_update = 1;
+ break;
+ case 'n':
+ no_output = 1;
+ break;
+ case 'e':
+ show_errors = 1;
+ break;
+ case 'j':
+ json_output = 1;
+ break;
+ case 'p':
+ pretty = 1;
+ break;
+ case 'd':
+ scan_interval = atoi(optarg) * 1000;
+ if (scan_interval <= 0) {
+ fprintf(stderr, "ifstat: invalid scan interval\n");
+ exit(-1);
+ }
+ break;
+ case 't':
+ time_constant = atoi(optarg);
+ if (time_constant <= 0) {
+ fprintf(stderr, "ifstat: invalid time constant divisor\n");
+ exit(-1);
+ }
+ break;
+ case 'v':
+ case 'V':
+ printf("ifstat utility, iproute2-ss%s\n", SNAPSHOT);
+ exit(0);
+ case 'h':
+ case '?':
+ default:
+ usage();
+ }
+ }
+
+ argc -= optind;
+ argv += optind;
+
+ sun.sun_family = AF_UNIX;
+ sun.sun_path[0] = 0;
+ sprintf(sun.sun_path+1, "ifstat%d", getuid());
+
+ if (scan_interval > 0) {
+ if (time_constant == 0)
+ time_constant = 60;
+ time_constant *= 1000;
+ W = 1 - 1/exp(log(10)*(double)scan_interval/time_constant);
+ if ((fd = socket(AF_UNIX, SOCK_STREAM, 0)) < 0) {
+ perror("ifstat: socket");
+ exit(-1);
+ }
+ if (bind(fd, (struct sockaddr*)&sun, 2+1+strlen(sun.sun_path+1)) < 0) {
+ perror("ifstat: bind");
+ exit(-1);
+ }
+ if (listen(fd, 5) < 0) {
+ perror("ifstat: listen");
+ exit(-1);
+ }
+ if (daemon(0, 0)) {
+ perror("ifstat: daemon");
+ exit(-1);
+ }
+ signal(SIGPIPE, SIG_IGN);
+ signal(SIGCHLD, sigchild);
+ server_loop(fd);
+ exit(0);
+ }
+
+ patterns = argv;
+ npatterns = argc;
+
+ if (getenv("IFSTAT_HISTORY"))
+ snprintf(hist_name, sizeof(hist_name),
+ "%s", getenv("IFSTAT_HISTORY"));
+ else
+ snprintf(hist_name, sizeof(hist_name),
+ "%s/.ifstat.u%d", P_tmpdir, getuid());
+
+ if (reset_history)
+ unlink(hist_name);
+
+ if (!ignore_history || !no_update) {
+ struct stat stb;
+
+ fd = open(hist_name, O_RDWR|O_CREAT|O_NOFOLLOW, 0600);
+ if (fd < 0) {
+ perror("ifstat: open history file");
+ exit(-1);
+ }
+ if ((hist_fp = fdopen(fd, "r+")) == NULL) {
+ perror("ifstat: fdopen history file");
+ exit(-1);
+ }
+ if (flock(fileno(hist_fp), LOCK_EX)) {
+ perror("ifstat: flock history file");
+ exit(-1);
+ }
+ if (fstat(fileno(hist_fp), &stb) != 0) {
+ perror("ifstat: fstat history file");
+ exit(-1);
+ }
+ if (stb.st_nlink != 1 || stb.st_uid != getuid()) {
+ fprintf(stderr, "ifstat: something is so wrong with history file, that I prefer not to proceed.\n");
+ exit(-1);
+ }
+ if (!ignore_history) {
+ FILE *tfp;
+ long uptime = -1;
+ if ((tfp = fopen("/proc/uptime", "r")) != NULL) {
+ if (fscanf(tfp, "%ld", &uptime) != 1)
+ uptime = -1;
+ fclose(tfp);
+ }
+ if (uptime >= 0 && time(NULL) >= stb.st_mtime+uptime) {
+ fprintf(stderr, "ifstat: history is aged out, resetting\n");
+ if (ftruncate(fileno(hist_fp), 0))
+ perror("ifstat: ftruncate");
+ }
+ }
+
+ load_raw_table(hist_fp);
+
+ hist_db = kern_db;
+ kern_db = NULL;
+ }
+
+ if ((fd = socket(AF_UNIX, SOCK_STREAM, 0)) >= 0 &&
+ (connect(fd, (struct sockaddr*)&sun, 2+1+strlen(sun.sun_path+1)) == 0
+ || (strcpy(sun.sun_path+1, "ifstat0"),
+ connect(fd, (struct sockaddr*)&sun, 2+1+strlen(sun.sun_path+1)) == 0))
+ && verify_forging(fd) == 0) {
+ FILE *sfp = fdopen(fd, "r");
+ load_raw_table(sfp);
+ if (hist_db && source_mismatch) {
+ fprintf(stderr, "ifstat: history is stale, ignoring it.\n");
+ hist_db = NULL;
+ }
+ fclose(sfp);
+ } else {
+ if (fd >= 0)
+ close(fd);
+ if (hist_db && info_source[0] && strcmp(info_source, "kernel")) {
+ fprintf(stderr, "ifstat: history is stale, ignoring it.\n");
+ hist_db = NULL;
+ info_source[0] = 0;
+ }
+ load_info();
+ if (info_source[0] == 0)
+ strcpy(info_source, "kernel");
+ }
+
+ if (!no_output) {
+ if (ignore_history || hist_db == NULL)
+ dump_kern_db(stdout);
+ else
+ dump_incr_db(stdout);
+ }
+
+ if (!no_update) {
+ if (ftruncate(fileno(hist_fp), 0))
+ perror("ifstat: ftruncate");
+ rewind(hist_fp);
+
+ json_output = 0;
+ dump_raw_db(hist_fp, 1);
+ fclose(hist_fp);
+ }
+ exit(0);
+}
diff --git a/iproute2/misc/lnstat.c b/iproute2/misc/lnstat.c
new file mode 100644
index 0000000..264c953
--- /dev/null
+++ b/iproute2/misc/lnstat.c
@@ -0,0 +1,380 @@
+/* lnstat - Unified linux network statistics
+ *
+ * Copyright (C) 2004 by Harald Welte <laforge@gnumonks.org>
+ *
+ * Development of this code was funded by Astaro AG, http://www.astaro.com/
+ *
+ * Based on original concept and ideas from predecessor rtstat.c:
+ *
+ * Copyright 2001 by Robert Olsson <robert.olsson@its.uu.se>
+ * Uppsala University, Sweden
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+/* Maximum number of fields that can be displayed */
+#define MAX_FIELDS 128
+
+/* Maximum number of header lines */
+#define HDR_LINES 10
+
+/* default field width if none specified */
+#define FIELD_WIDTH_DEFAULT 8
+#define FIELD_WIDTH_MAX 20
+
+#define DEFAULT_INTERVAL 2
+
+#define HDR_LINE_LENGTH (MAX_FIELDS*FIELD_WIDTH_MAX)
+
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <getopt.h>
+
+#include <json_writer.h>
+#include "lnstat.h"
+
+static struct option opts[] = {
+ { "version", 0, NULL, 'V' },
+ { "count", 1, NULL, 'c' },
+ { "dump", 0, NULL, 'd' },
+ { "json", 0, NULL, 'j' },
+ { "file", 1, NULL, 'f' },
+ { "help", 0, NULL, 'h' },
+ { "interval", 1, NULL, 'i' },
+ { "keys", 1, NULL, 'k' },
+ { "subject", 1, NULL, 's' },
+ { "width", 1, NULL, 'w' },
+ { "oneline", 0, NULL, 0 },
+};
+
+static int usage(char *name, int exit_code)
+{
+ fprintf(stderr, "%s Version %s\n", name, LNSTAT_VERSION);
+ fprintf(stderr, "Copyright (C) 2004 by Harald Welte "
+ "<laforge@gnumonks.org>\n");
+ fprintf(stderr, "This program is free software licensed under GNU GPLv2"
+ "\nwith ABSOLUTELY NO WARRANTY.\n\n");
+ fprintf(stderr, "Parameters:\n");
+ fprintf(stderr, "\t-V --version\t\tPrint Version of Program\n");
+ fprintf(stderr, "\t-c --count <count>\t"
+ "Print <count> number of intervals\n");
+ fprintf(stderr, "\t-d --dump\t\t"
+ "Dump list of available files/keys\n");
+ fprintf(stderr, "\t-j --json\t\t"
+ "Display in JSON format\n");
+ fprintf(stderr, "\t-f --file <file>\tStatistics file to use\n");
+ fprintf(stderr, "\t-h --help\t\tThis help message\n");
+ fprintf(stderr, "\t-i --interval <intv>\t"
+ "Set interval to 'intv' seconds\n");
+ fprintf(stderr, "\t-k --keys k,k,k,...\tDisplay only keys specified\n");
+ fprintf(stderr, "\t-s --subject [0-2]\tControl header printing:\n");
+ fprintf(stderr, "\t\t\t\t0 = never\n");
+ fprintf(stderr, "\t\t\t\t1 = once\n");
+ fprintf(stderr, "\t\t\t\t2 = every 20 lines (default))\n");
+ fprintf(stderr, "\t-w --width n,n,n,...\tWidth for each field\n");
+ fprintf(stderr, "\n");
+
+ exit(exit_code);
+}
+
+struct field_param {
+ const char *name;
+ struct lnstat_field *lf;
+ struct {
+ unsigned int width;
+ } print;
+};
+
+struct field_params {
+ unsigned int num;
+ struct field_param params[MAX_FIELDS];
+};
+
+static void print_line(FILE *of, const struct lnstat_file *lnstat_files,
+ const struct field_params *fp)
+{
+ int i;
+
+ for (i = 0; i < fp->num; i++) {
+ const struct lnstat_field *lf = fp->params[i].lf;
+
+ fprintf(of, "%*lu|", fp->params[i].print.width, lf->result);
+ }
+ fputc('\n', of);
+}
+
+static void print_json(FILE *of, const struct lnstat_file *lnstat_files,
+ const struct field_params *fp)
+{
+ json_writer_t *jw = jsonw_new(of);
+ int i;
+
+ jsonw_start_object(jw);
+ for (i = 0; i < fp->num; i++) {
+ const struct lnstat_field *lf = fp->params[i].lf;
+
+ jsonw_uint_field(jw, lf->name, lf->result);
+ }
+ jsonw_end_object(jw);
+ jsonw_destroy(&jw);
+}
+
+/* find lnstat_field according to user specification */
+static int map_field_params(struct lnstat_file *lnstat_files,
+ struct field_params *fps, int interval)
+{
+ int i, j = 0;
+ struct lnstat_file *lf;
+
+ /* no field specification on commandline, need to build default */
+ if (!fps->num) {
+ for (lf = lnstat_files; lf; lf = lf->next) {
+ for (i = 0; i < lf->num_fields; i++) {
+ fps->params[j].lf = &lf->fields[i];
+ fps->params[j].lf->file->interval.tv_sec =
+ interval;
+ if (!fps->params[j].print.width)
+ fps->params[j].print.width =
+ FIELD_WIDTH_DEFAULT;
+
+ if (++j >= MAX_FIELDS - 1) {
+ fprintf(stderr,
+ "WARN: MAX_FIELDS (%d) reached,"
+ " truncating number of keys\n",
+ MAX_FIELDS);
+ goto full;
+ }
+ }
+ }
+ full:
+ fps->num = j;
+ return 1;
+ }
+
+ for (i = 0; i < fps->num; i++) {
+ fps->params[i].lf = lnstat_find_field(lnstat_files,
+ fps->params[i].name);
+ if (!fps->params[i].lf) {
+ fprintf(stderr, "Field `%s' unknown\n",
+ fps->params[i].name);
+ return 0;
+ }
+ fps->params[i].lf->file->interval.tv_sec = interval;
+ if (!fps->params[i].print.width)
+ fps->params[i].print.width = FIELD_WIDTH_DEFAULT;
+ }
+ return 1;
+}
+
+struct table_hdr {
+ int num_lines;
+ char *hdr[HDR_LINES];
+};
+
+static struct table_hdr *build_hdr_string(struct lnstat_file *lnstat_files,
+ struct field_params *fps,
+ int linewidth)
+{
+ int h,i;
+ static struct table_hdr th;
+ int ofs = 0;
+
+ for (i = 0; i < HDR_LINES; i++) {
+ th.hdr[i] = malloc(HDR_LINE_LENGTH);
+ memset(th.hdr[i], 0, HDR_LINE_LENGTH);
+ }
+
+ for (i = 0; i < fps->num; i++) {
+ char *cname, *fname = fps->params[i].lf->name;
+ unsigned int width = fps->params[i].print.width;
+
+ snprintf(th.hdr[0]+ofs, width+2, "%*.*s|", width, width,
+ fps->params[i].lf->file->basename);
+
+ cname = fname;
+ for (h = 1; h < HDR_LINES; h++) {
+ if (cname - fname >= strlen(fname))
+ snprintf(th.hdr[h]+ofs, width+2,
+ "%*.*s|", width, width, "");
+ else {
+ th.num_lines = h+1;
+ snprintf(th.hdr[h]+ofs, width+2,
+ "%*.*s|", width, width, cname);
+ }
+ cname += width;
+ }
+ ofs += width+1;
+ }
+ /* fill in spaces */
+ for (h = 1; h <= th.num_lines; h++) {
+ for (i = 0; i < ofs; i++) {
+ if (th.hdr[h][i] == '\0')
+ th.hdr[h][i] = ' ';
+ }
+ }
+
+ return &th;
+}
+
+static int print_hdr(FILE *of, struct table_hdr *th)
+{
+ int i;
+
+ for (i = 0; i < th->num_lines; i++) {
+ fputs(th->hdr[i], of);
+ fputc('\n', of);
+ }
+ return 0;
+}
+
+
+int main(int argc, char **argv)
+{
+ struct lnstat_file *lnstat_files;
+ const char *basename;
+ int i, c;
+ int interval = DEFAULT_INTERVAL;
+ int hdr = 2;
+ enum {
+ MODE_DUMP,
+ MODE_JSON,
+ MODE_NORMAL,
+ } mode = MODE_NORMAL;
+ unsigned long count = 0;
+ struct table_hdr *header;
+ static struct field_params fp;
+ int num_req_files = 0;
+ char *req_files[LNSTAT_MAX_FILES];
+
+ /* backwards compatibility mode for old tools */
+ basename = strrchr(argv[0], '/');
+ if (basename)
+ basename += 1; /* name after slash */
+ else
+ basename = argv[0]; /* no slash */
+
+ if (!strcmp(basename, "rtstat")) {
+ /* rtstat compatibility mode */
+ req_files[0] = "rt_cache";
+ num_req_files = 1;
+ } else if (!strcmp(basename, "ctstat")) {
+ /* ctstat compatibility mode */
+ req_files[0] = "ip_conntrack";
+ num_req_files = 1;
+ }
+
+ while ((c = getopt_long(argc, argv,"Vc:djpf:h?i:k:s:w:",
+ opts, NULL)) != -1) {
+ int len = 0;
+ char *tmp, *tok;
+
+ switch (c) {
+ case 'c':
+ count = strtoul(optarg, NULL, 0);
+ break;
+ case 'd':
+ mode = MODE_DUMP;
+ break;
+ case 'j':
+ mode = MODE_JSON;
+ break;
+ case 'f':
+ req_files[num_req_files++] = strdup(optarg);
+ break;
+ case '?':
+ case 'h':
+ usage(argv[0], 0);
+ break;
+ case 'i':
+ sscanf(optarg, "%u", &interval);
+ break;
+ case 'k':
+ tmp = strdup(optarg);
+ if (!tmp)
+ break;
+ for (tok = strtok(tmp, ",");
+ tok;
+ tok = strtok(NULL, ",")) {
+ if (fp.num >= MAX_FIELDS) {
+ fprintf(stderr,
+ "WARN: too many keys"
+ " requested: (%d max)\n",
+ MAX_FIELDS);
+ break;
+ }
+ fp.params[fp.num++].name = tok;
+ }
+ break;
+ case 's':
+ sscanf(optarg, "%u", &hdr);
+ break;
+ case 'w':
+ tmp = strdup(optarg);
+ if (!tmp)
+ break;
+ i = 0;
+ for (tok = strtok(tmp, ",");
+ tok;
+ tok = strtok(NULL, ",")) {
+ len = strtoul(tok, NULL, 0);
+ if (len > FIELD_WIDTH_MAX)
+ len = FIELD_WIDTH_MAX;
+ fp.params[i].print.width = len;
+ i++;
+ }
+ if (i == 1) {
+ for (i = 0; i < MAX_FIELDS; i++)
+ fp.params[i].print.width = len;
+ }
+ break;
+ default:
+ usage(argv[0], 1);
+ break;
+ }
+ }
+
+ lnstat_files = lnstat_scan_dir(PROC_NET_STAT, num_req_files,
+ (const char **) req_files);
+
+ switch (mode) {
+ case MODE_DUMP:
+ lnstat_dump(stdout, lnstat_files);
+ break;
+
+ case MODE_NORMAL:
+ case MODE_JSON:
+ if (!map_field_params(lnstat_files, &fp, interval))
+ exit(1);
+
+ header = build_hdr_string(lnstat_files, &fp, 80);
+ if (!header)
+ exit(1);
+
+ if (interval < 1 )
+ interval = 1;
+
+ for (i = 0; i < count || !count; i++) {
+ lnstat_update(lnstat_files);
+ if (mode == MODE_JSON)
+ print_json(stdout, lnstat_files, &fp);
+ else {
+ if ((hdr > 1 && !(i % 20)) ||
+ (hdr == 1 && i == 0))
+ print_hdr(stdout, header);
+ print_line(stdout, lnstat_files, &fp);
+ }
+ fflush(stdout);
+ if (i < count - 1 || !count)
+ sleep(interval);
+ }
+ break;
+ }
+
+ return 1;
+}
diff --git a/iproute2/misc/lnstat.h b/iproute2/misc/lnstat.h
new file mode 100644
index 0000000..83dad97
--- /dev/null
+++ b/iproute2/misc/lnstat.h
@@ -0,0 +1,44 @@
+#ifndef _LNSTAT_H
+#define _LNSTAT_H
+
+#include <limits.h>
+#include <sys/select.h>
+
+#define LNSTAT_VERSION "0.02 041002"
+
+#define PROC_NET_STAT "/proc/net/stat"
+
+#define LNSTAT_MAX_FILES 32
+#define LNSTAT_MAX_FIELDS_PER_LINE 32
+#define LNSTAT_MAX_FIELD_NAME_LEN 32
+
+struct lnstat_file;
+
+struct lnstat_field {
+ struct lnstat_file *file;
+ unsigned int num; /* field number in line */
+ char name[LNSTAT_MAX_FIELD_NAME_LEN+1];
+ unsigned long values[2]; /* two buffers for values */
+ unsigned long result;
+};
+
+struct lnstat_file {
+ struct lnstat_file *next;
+ char path[PATH_MAX+1];
+ char basename[NAME_MAX+1];
+ struct timeval last_read; /* last time of read */
+ struct timeval interval; /* interval */
+ int compat; /* 1 == backwards compat mode */
+ FILE *fp;
+ unsigned int num_fields; /* number of fields */
+ struct lnstat_field fields[LNSTAT_MAX_FIELDS_PER_LINE];
+};
+
+
+struct lnstat_file *lnstat_scan_dir(const char *path, const int num_req_files,
+ const char **req_files);
+int lnstat_update(struct lnstat_file *lnstat_files);
+int lnstat_dump(FILE *outfd, struct lnstat_file *lnstat_files);
+struct lnstat_field *lnstat_find_field(struct lnstat_file *lnstat_files,
+ const char *name);
+#endif /* _LNSTAT_H */
diff --git a/iproute2/misc/lnstat_util.c b/iproute2/misc/lnstat_util.c
new file mode 100644
index 0000000..a258366
--- /dev/null
+++ b/iproute2/misc/lnstat_util.c
@@ -0,0 +1,332 @@
+/* lnstat.c: Unified linux network statistics
+ *
+ * Copyright (C) 2004 by Harald Welte <laforge@gnumonks.org>
+ *
+ * Development of this code was funded by Astaro AG, http://www.astaro.com/
+ *
+ * Based on original concept and ideas from predecessor rtstat.c:
+ *
+ * Copyright 2001 by Robert Olsson <robert.olsson@its.uu.se>
+ * Uppsala University, Sweden
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <dirent.h>
+#include <limits.h>
+#include <time.h>
+
+#include <sys/time.h>
+#include <sys/types.h>
+
+#include "lnstat.h"
+
+/* size of temp buffer used to read lines from procfiles */
+#define FGETS_BUF_SIZE 1024
+
+
+#define RTSTAT_COMPAT_LINE "entries in_hit in_slow_tot in_no_route in_brd in_martian_dst in_martian_src out_hit out_slow_tot out_slow_mc gc_total gc_ignored gc_goal_miss gc_dst_overflow in_hlist_search out_hlist_search\n"
+
+/* Read (and summarize for SMP) the different stats vars. */
+static int scan_lines(struct lnstat_file *lf, int i)
+{
+ char buf[FGETS_BUF_SIZE];
+ int j, num_lines = 0;
+
+ for (j = 0; j < lf->num_fields; j++)
+ lf->fields[j].values[i] = 0;
+
+ rewind(lf->fp);
+ /* skip first line */
+ if (!lf->compat && !fgets(buf, sizeof(buf)-1, lf->fp))
+ return -1;
+
+ while(!feof(lf->fp) && fgets(buf, sizeof(buf)-1, lf->fp)) {
+ char *ptr = buf;
+
+ num_lines++;
+
+ gettimeofday(&lf->last_read, NULL);
+
+ for (j = 0; j < lf->num_fields; j++) {
+ unsigned long f = strtoul(ptr, &ptr, 16);
+ if (j == 0)
+ lf->fields[j].values[i] = f;
+ else
+ lf->fields[j].values[i] += f;
+ }
+ }
+ return num_lines;
+}
+
+static int time_after(struct timeval *last,
+ struct timeval *tout,
+ struct timeval *now)
+{
+ if (now->tv_sec > last->tv_sec + tout->tv_sec)
+ return 1;
+
+ if (now->tv_sec == last->tv_sec + tout->tv_sec) {
+ if (now->tv_usec > last->tv_usec + tout->tv_usec)
+ return 1;
+ }
+
+ return 0;
+}
+
+int lnstat_update(struct lnstat_file *lnstat_files)
+{
+ struct lnstat_file *lf;
+ struct timeval tv;
+
+ gettimeofday(&tv, NULL);
+
+ for (lf = lnstat_files; lf; lf = lf->next) {
+ if (time_after(&lf->last_read, &lf->interval, &tv)) {
+ int i;
+ struct lnstat_field *lfi;
+
+ scan_lines(lf, 1);
+
+ for (i = 0, lfi = &lf->fields[i];
+ i < lf->num_fields; i++, lfi = &lf->fields[i]) {
+ if (i == 0)
+ lfi->result = lfi->values[1];
+ else
+ lfi->result = (lfi->values[1]-lfi->values[0])
+ / lf->interval.tv_sec;
+ }
+
+ scan_lines(lf, 0);
+ }
+ }
+
+ return 0;
+}
+
+/* scan first template line and fill in per-field data structures */
+static int __lnstat_scan_fields(struct lnstat_file *lf, char *buf)
+{
+ char *tok;
+ int i;
+
+ tok = strtok(buf, " \t\n");
+ for (i = 0; i < LNSTAT_MAX_FIELDS_PER_LINE; i++) {
+ lf->fields[i].file = lf;
+ strncpy(lf->fields[i].name, tok, LNSTAT_MAX_FIELD_NAME_LEN);
+ /* has to be null-terminate since we initialize to zero
+ * and field size is NAME_LEN + 1 */
+ tok = strtok(NULL, " \t\n");
+ if (!tok) {
+ lf->num_fields = i+1;
+ return 0;
+ }
+ }
+ return 0;
+}
+
+static int lnstat_scan_fields(struct lnstat_file *lf)
+{
+ char buf[FGETS_BUF_SIZE];
+
+ rewind(lf->fp);
+ if (!fgets(buf, sizeof(buf)-1, lf->fp))
+ return -1;
+
+ return __lnstat_scan_fields(lf, buf);
+}
+
+/* fake function emulating lnstat_scan_fields() for old kernels */
+static int lnstat_scan_compat_rtstat_fields(struct lnstat_file *lf)
+{
+ char buf[FGETS_BUF_SIZE];
+
+ strncpy(buf, RTSTAT_COMPAT_LINE, sizeof(buf)-1);
+
+ return __lnstat_scan_fields(lf, buf);
+}
+
+/* find out whether string 'name; is in given string array */
+static int name_in_array(const int num, const char **arr, const char *name)
+{
+ int i;
+ for (i = 0; i < num; i++) {
+ if (!strcmp(arr[i], name))
+ return 1;
+ }
+ return 0;
+}
+
+/* allocate lnstat_file and open given file */
+static struct lnstat_file *alloc_and_open(const char *path, const char *file)
+{
+ struct lnstat_file *lf;
+
+ /* allocate */
+ lf = malloc(sizeof(*lf));
+ if (!lf) {
+ fprintf(stderr, "out of memory\n");
+ return NULL;
+ }
+
+ /* initialize */
+ memset(lf, 0, sizeof(*lf));
+
+ /* de->d_name is guaranteed to be <= NAME_MAX */
+ strcpy(lf->basename, file);
+ strcpy(lf->path, path);
+ strcat(lf->path, "/");
+ strcat(lf->path, lf->basename);
+
+ /* initialize to default */
+ lf->interval.tv_sec = 1;
+
+ /* open */
+ lf->fp = fopen(lf->path, "r");
+ if (!lf->fp) {
+ perror(lf->path);
+ free(lf);
+ return NULL;
+ }
+
+ return lf;
+}
+
+
+/* lnstat_scan_dir - find and parse all available statistics files/fields */
+struct lnstat_file *lnstat_scan_dir(const char *path, const int num_req_files,
+ const char **req_files)
+{
+ DIR *dir;
+ struct lnstat_file *lnstat_files = NULL;
+ struct dirent *de;
+
+ if (!path)
+ path = PROC_NET_STAT;
+
+ dir = opendir(path);
+ if (!dir) {
+ struct lnstat_file *lf;
+ /* Old kernel, before /proc/net/stat was introduced */
+ fprintf(stderr, "Your kernel doesn't have lnstat support. ");
+
+ /* we only support rtstat, not multiple files */
+ if (num_req_files >= 2) {
+ fputc('\n', stderr);
+ return NULL;
+ }
+
+ /* we really only accept rt_cache */
+ if (num_req_files && !name_in_array(num_req_files,
+ req_files, "rt_cache")) {
+ fputc('\n', stderr);
+ return NULL;
+ }
+
+ fprintf(stderr, "Fallback to old rtstat-only operation\n");
+
+ lf = alloc_and_open("/proc/net", "rt_cache_stat");
+ if (!lf)
+ return NULL;
+ lf->compat = 1;
+ strncpy(lf->basename, "rt_cache", sizeof(lf->basename));
+
+ /* FIXME: support for old files */
+ if (lnstat_scan_compat_rtstat_fields(lf) < 0)
+ return NULL;
+
+ lf->next = lnstat_files;
+ lnstat_files = lf;
+ return lnstat_files;
+ }
+
+ while ((de = readdir(dir))) {
+ struct lnstat_file *lf;
+
+ if (de->d_type != DT_REG)
+ continue;
+
+ if (num_req_files && !name_in_array(num_req_files,
+ req_files, de->d_name))
+ continue;
+
+ lf = alloc_and_open(path, de->d_name);
+ if (!lf) {
+ closedir(dir);
+ return NULL;
+ }
+
+ /* fill in field structure */
+ if (lnstat_scan_fields(lf) < 0) {
+ closedir(dir);
+ return NULL;
+ }
+
+ /* prepend to global list */
+ lf->next = lnstat_files;
+ lnstat_files = lf;
+ }
+ closedir(dir);
+
+ return lnstat_files;
+}
+
+int lnstat_dump(FILE *outfd, struct lnstat_file *lnstat_files)
+{
+ struct lnstat_file *lf;
+
+ for (lf = lnstat_files; lf; lf = lf->next) {
+ int i;
+
+ fprintf(outfd, "%s:\n", lf->path);
+
+ for (i = 0; i < lf->num_fields; i++)
+ fprintf(outfd, "\t%2u: %s\n", i+1, lf->fields[i].name);
+
+ }
+ return 0;
+}
+
+struct lnstat_field *lnstat_find_field(struct lnstat_file *lnstat_files,
+ const char *name)
+{
+ struct lnstat_file *lf;
+ struct lnstat_field *ret = NULL;
+ const char *colon = strchr(name, ':');
+ char *file;
+ const char *field;
+
+ if (colon) {
+ file = strndup(name, colon-name);
+ field = colon+1;
+ } else {
+ file = NULL;
+ field = name;
+ }
+
+ for (lf = lnstat_files; lf; lf = lf->next) {
+ int i;
+
+ if (file && strcmp(file, lf->basename))
+ continue;
+
+ for (i = 0; i < lf->num_fields; i++) {
+ if (!strcmp(field, lf->fields[i].name)) {
+ ret = &lf->fields[i];
+ goto out;
+ }
+ }
+ }
+out:
+ free(file);
+
+ return ret;
+}
diff --git a/iproute2/misc/nstat.c b/iproute2/misc/nstat.c
new file mode 100644
index 0000000..9970528
--- /dev/null
+++ b/iproute2/misc/nstat.c
@@ -0,0 +1,706 @@
+/*
+ * nstat.c handy utility to read counters /proc/net/netstat and snmp
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <string.h>
+#include <errno.h>
+#include <time.h>
+#include <sys/time.h>
+#include <fnmatch.h>
+#include <sys/file.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+#include <sys/poll.h>
+#include <sys/wait.h>
+#include <sys/stat.h>
+#include <signal.h>
+#include <math.h>
+#include <getopt.h>
+
+#include <json_writer.h>
+#include <SNAPSHOT.h>
+
+int dump_zeros = 0;
+int reset_history = 0;
+int ignore_history = 0;
+int no_output = 0;
+int json_output = 0;
+int pretty = 0;
+int no_update = 0;
+int scan_interval = 0;
+int time_constant = 0;
+double W;
+char **patterns;
+int npatterns;
+
+char info_source[128];
+int source_mismatch;
+
+static int generic_proc_open(const char *env, char *name)
+{
+ char store[128];
+ char *p = getenv(env);
+ if (!p) {
+ p = getenv("PROC_ROOT") ? : "/proc";
+ snprintf(store, sizeof(store)-1, "%s/%s", p, name);
+ p = store;
+ }
+ return open(p, O_RDONLY);
+}
+
+static int net_netstat_open(void)
+{
+ return generic_proc_open("PROC_NET_NETSTAT", "net/netstat");
+}
+
+static int net_snmp_open(void)
+{
+ return generic_proc_open("PROC_NET_SNMP", "net/snmp");
+}
+
+static int net_snmp6_open(void)
+{
+ return generic_proc_open("PROC_NET_SNMP6", "net/snmp6");
+}
+
+struct nstat_ent
+{
+ struct nstat_ent *next;
+ char *id;
+ unsigned long long val;
+ double rate;
+};
+
+struct nstat_ent *kern_db;
+struct nstat_ent *hist_db;
+
+static const char *useless_numbers[] = {
+ "IpForwarding", "IpDefaultTTL",
+ "TcpRtoAlgorithm", "TcpRtoMin", "TcpRtoMax",
+ "TcpMaxConn", "TcpCurrEstab"
+};
+
+static int useless_number(const char *id)
+{
+ int i;
+ for (i=0; i<sizeof(useless_numbers)/sizeof(*useless_numbers); i++)
+ if (strcmp(id, useless_numbers[i]) == 0)
+ return 1;
+ return 0;
+}
+
+static int match(const char *id)
+{
+ int i;
+
+ if (npatterns == 0)
+ return 1;
+
+ for (i=0; i<npatterns; i++) {
+ if (!fnmatch(patterns[i], id, 0))
+ return 1;
+ }
+ return 0;
+}
+
+static void load_good_table(FILE *fp)
+{
+ char buf[4096];
+ struct nstat_ent *db = NULL;
+ struct nstat_ent *n;
+
+ while (fgets(buf, sizeof(buf), fp) != NULL) {
+ int nr;
+ unsigned long long val;
+ double rate;
+ char idbuf[sizeof(buf)];
+ if (buf[0] == '#') {
+ buf[strlen(buf)-1] = 0;
+ if (info_source[0] && strcmp(info_source, buf+1))
+ source_mismatch = 1;
+ info_source[0] = 0;
+ strncat(info_source, buf+1, sizeof(info_source)-1);
+ continue;
+ }
+ /* idbuf is as big as buf, so this is safe */
+ nr = sscanf(buf, "%s%llu%lg", idbuf, &val, &rate);
+ if (nr < 2)
+ abort();
+ if (nr < 3)
+ rate = 0;
+ if (useless_number(idbuf))
+ continue;
+ if ((n = malloc(sizeof(*n))) == NULL)
+ abort();
+ n->id = strdup(idbuf);
+ n->val = val;
+ n->rate = rate;
+ n->next = db;
+ db = n;
+ }
+
+ while (db) {
+ n = db;
+ db = db->next;
+ n->next = kern_db;
+ kern_db = n;
+ }
+}
+
+static int count_spaces(const char *line)
+{
+ int count = 0;
+ char c;
+
+ while ((c = *line++) != 0)
+ count += c == ' ' || c == '\n';
+ return count;
+}
+
+static void load_ugly_table(FILE *fp)
+{
+ char buf[4096];
+ struct nstat_ent *db = NULL;
+ struct nstat_ent *n;
+
+ while (fgets(buf, sizeof(buf), fp) != NULL) {
+ char idbuf[sizeof(buf)];
+ int off;
+ char *p;
+ int count1, count2, skip = 0;
+
+ p = strchr(buf, ':');
+ if (!p)
+ abort();
+ count1 = count_spaces(buf);
+ *p = 0;
+ idbuf[0] = 0;
+ strncat(idbuf, buf, sizeof(idbuf) - 1);
+ off = p - buf;
+ p += 2;
+
+ while (*p) {
+ char *next;
+ if ((next = strchr(p, ' ')) != NULL)
+ *next++ = 0;
+ else if ((next = strchr(p, '\n')) != NULL)
+ *next++ = 0;
+ if (off < sizeof(idbuf)) {
+ idbuf[off] = 0;
+ strncat(idbuf, p, sizeof(idbuf) - off - 1);
+ }
+ n = malloc(sizeof(*n));
+ if (!n)
+ abort();
+ n->id = strdup(idbuf);
+ n->rate = 0;
+ n->next = db;
+ db = n;
+ p = next;
+ }
+ n = db;
+ if (fgets(buf, sizeof(buf), fp) == NULL)
+ abort();
+ count2 = count_spaces(buf);
+ if (count2 > count1)
+ skip = count2 - count1;
+ do {
+ p = strrchr(buf, ' ');
+ if (!p)
+ abort();
+ *p = 0;
+ if (sscanf(p+1, "%llu", &n->val) != 1)
+ abort();
+ /* Trick to skip "dummy" trailing ICMP MIB in 2.4 */
+ if (skip)
+ skip--;
+ else
+ n = n->next;
+ } while (p > buf + off + 2);
+ }
+
+ while (db) {
+ n = db;
+ db = db->next;
+ if (useless_number(n->id)) {
+ free(n->id);
+ free(n);
+ } else {
+ n->next = kern_db;
+ kern_db = n;
+ }
+ }
+}
+
+static void load_snmp(void)
+{
+ FILE *fp = fdopen(net_snmp_open(), "r");
+ if (fp) {
+ load_ugly_table(fp);
+ fclose(fp);
+ }
+}
+
+static void load_snmp6(void)
+{
+ FILE *fp = fdopen(net_snmp6_open(), "r");
+ if (fp) {
+ load_good_table(fp);
+ fclose(fp);
+ }
+}
+
+static void load_netstat(void)
+{
+ FILE *fp = fdopen(net_netstat_open(), "r");
+ if (fp) {
+ load_ugly_table(fp);
+ fclose(fp);
+ }
+}
+
+
+static void dump_kern_db(FILE *fp, int to_hist)
+{
+ json_writer_t *jw = json_output ? jsonw_new(fp) : NULL;
+ struct nstat_ent *n, *h;
+
+ h = hist_db;
+ if (jw) {
+ jsonw_pretty(jw, pretty);
+ jsonw_name(jw, info_source);
+ jsonw_start_object(jw);
+ } else
+ fprintf(fp, "#%s\n", info_source);
+
+ for (n=kern_db; n; n=n->next) {
+ unsigned long long val = n->val;
+ if (!dump_zeros && !val && !n->rate)
+ continue;
+ if (!match(n->id)) {
+ struct nstat_ent *h1;
+ if (!to_hist)
+ continue;
+ for (h1 = h; h1; h1 = h1->next) {
+ if (strcmp(h1->id, n->id) == 0) {
+ val = h1->val;
+ h = h1->next;
+ break;
+ }
+ }
+ }
+
+ if (jw)
+ jsonw_uint_field(jw, n->id, val);
+ else
+ fprintf(fp, "%-32s%-16llu%6.1f\n", n->id, val, n->rate);
+ }
+
+ if (jw) {
+ jsonw_end_object(jw);
+ jsonw_destroy(&jw);
+ }
+}
+
+static void dump_incr_db(FILE *fp)
+{
+ json_writer_t *jw = json_output ? jsonw_new(fp) : NULL;
+ struct nstat_ent *n, *h;
+
+ h = hist_db;
+ if (jw) {
+ jsonw_pretty(jw, pretty);
+ jsonw_name(jw, info_source);
+ jsonw_start_object(jw);
+ } else
+ fprintf(fp, "#%s\n", info_source);
+
+ for (n=kern_db; n; n=n->next) {
+ int ovfl = 0;
+ unsigned long long val = n->val;
+ struct nstat_ent *h1;
+ for (h1 = h; h1; h1 = h1->next) {
+ if (strcmp(h1->id, n->id) == 0) {
+ if (val < h1->val) {
+ ovfl = 1;
+ val = h1->val;
+ }
+ val -= h1->val;
+ h = h1->next;
+ break;
+ }
+ }
+ if (!dump_zeros && !val && !n->rate)
+ continue;
+ if (!match(n->id))
+ continue;
+
+ if (jw)
+ jsonw_uint_field(jw, n->id, val);
+ else
+ fprintf(fp, "%-32s%-16llu%6.1f%s\n", n->id, val,
+ n->rate, ovfl?" (overflow)":"");
+ }
+
+ if (jw) {
+ jsonw_end_object(jw);
+ jsonw_destroy(&jw);
+ }
+}
+
+static int children;
+
+static void sigchild(int signo)
+{
+}
+
+static void update_db(int interval)
+{
+ struct nstat_ent *n, *h;
+
+ n = kern_db;
+ kern_db = NULL;
+
+ load_netstat();
+ load_snmp6();
+ load_snmp();
+
+ h = kern_db;
+ kern_db = n;
+
+ for (n = kern_db; n; n = n->next) {
+ struct nstat_ent *h1;
+ for (h1 = h; h1; h1 = h1->next) {
+ if (strcmp(h1->id, n->id) == 0) {
+ double sample;
+ unsigned long long incr = h1->val - n->val;
+
+ n->val = h1->val;
+ sample = (double)incr * 1000.0 / interval;
+ if (interval >= scan_interval) {
+ n->rate += W*(sample-n->rate);
+ } else if (interval >= 1000) {
+ if (interval >= time_constant) {
+ n->rate = sample;
+ } else {
+ double w = W*(double)interval/scan_interval;
+ n->rate += w*(sample-n->rate);
+ }
+ }
+
+ while (h != h1) {
+ struct nstat_ent *tmp = h;
+ h = h->next;
+ free(tmp->id);
+ free(tmp);
+ };
+ h = h1->next;
+ free(h1->id);
+ free(h1);
+ break;
+ }
+ }
+ }
+}
+
+#define T_DIFF(a,b) (((a).tv_sec-(b).tv_sec)*1000 + ((a).tv_usec-(b).tv_usec)/1000)
+
+
+static void server_loop(int fd)
+{
+ struct timeval snaptime = { 0 };
+ struct pollfd p;
+ p.fd = fd;
+ p.events = p.revents = POLLIN;
+
+ sprintf(info_source, "%d.%lu sampling_interval=%d time_const=%d",
+ getpid(), (unsigned long)random(), scan_interval/1000, time_constant/1000);
+
+ load_netstat();
+ load_snmp6();
+ load_snmp();
+
+ for (;;) {
+ int status;
+ int tdiff;
+ struct timeval now;
+ gettimeofday(&now, NULL);
+ tdiff = T_DIFF(now, snaptime);
+ if (tdiff >= scan_interval) {
+ update_db(tdiff);
+ snaptime = now;
+ tdiff = 0;
+ }
+ if (poll(&p, 1, tdiff + scan_interval) > 0
+ && (p.revents&POLLIN)) {
+ int clnt = accept(fd, NULL, NULL);
+ if (clnt >= 0) {
+ pid_t pid;
+ if (children >= 5) {
+ close(clnt);
+ } else if ((pid = fork()) != 0) {
+ if (pid>0)
+ children++;
+ close(clnt);
+ } else {
+ FILE *fp = fdopen(clnt, "w");
+ if (fp) {
+ if (tdiff > 0)
+ update_db(tdiff);
+ dump_kern_db(fp, 0);
+ }
+ exit(0);
+ }
+ }
+ }
+ while (children && waitpid(-1, &status, WNOHANG) > 0)
+ children--;
+ }
+}
+
+static int verify_forging(int fd)
+{
+ struct ucred cred;
+ socklen_t olen = sizeof(cred);
+
+ if (getsockopt(fd, SOL_SOCKET, SO_PEERCRED, (void*)&cred, &olen) ||
+ olen < sizeof(cred))
+ return -1;
+ if (cred.uid == getuid() || cred.uid == 0)
+ return 0;
+ return -1;
+}
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr,
+"Usage: nstat [OPTION] [ PATTERN [ PATTERN ] ]\n"
+" -h, --help this message\n"
+" -a, --ignore ignore history\n"
+" -d, --scan=SECS sample every statistics every SECS\n"
+" -j, --json format output in JSON\n"
+" -n, --nooutput do history only\n"
+" -p, --pretty pretty print\n"
+" -r, --reset reset history\n"
+" -s, --noupdate don\'t update history\n"
+" -t, --interval=SECS report average over the last SECS\n"
+" -V, --version output version information\n"
+" -z, --zeros show entries with zero activity\n");
+ exit(-1);
+}
+
+static const struct option longopts[] = {
+ { "help", 0, 0, 'h' },
+ { "ignore", 0, 0, 'a' },
+ { "scan", 1, 0, 'd'},
+ { "nooutput", 0, 0, 'n' },
+ { "json", 0, 0, 'j' },
+ { "reset", 0, 0, 'r' },
+ { "noupdate", 0, 0, 's' },
+ { "pretty", 0, 0, 'p' },
+ { "interval", 1, 0, 't' },
+ { "version", 0, 0, 'V' },
+ { "zeros", 0, 0, 'z' },
+ { 0 }
+};
+
+int main(int argc, char *argv[])
+{
+ char *hist_name;
+ struct sockaddr_un sun;
+ FILE *hist_fp = NULL;
+ int ch;
+ int fd;
+
+ while ((ch = getopt_long(argc, argv, "h?vVzrnasd:t:jp",
+ longopts, NULL)) != EOF) {
+ switch(ch) {
+ case 'z':
+ dump_zeros = 1;
+ break;
+ case 'r':
+ reset_history = 1;
+ break;
+ case 'a':
+ ignore_history = 1;
+ break;
+ case 's':
+ no_update = 1;
+ break;
+ case 'n':
+ no_output = 1;
+ break;
+ case 'd':
+ scan_interval = 1000*atoi(optarg);
+ break;
+ case 't':
+ if (sscanf(optarg, "%d", &time_constant) != 1 ||
+ time_constant <= 0) {
+ fprintf(stderr, "nstat: invalid time constant divisor\n");
+ exit(-1);
+ }
+ break;
+ case 'j':
+ json_output = 1;
+ break;
+ case 'p':
+ pretty = 1;
+ break;
+ case 'v':
+ case 'V':
+ printf("nstat utility, iproute2-ss%s\n", SNAPSHOT);
+ exit(0);
+ case 'h':
+ case '?':
+ default:
+ usage();
+ }
+ }
+
+ argc -= optind;
+ argv += optind;
+
+ sun.sun_family = AF_UNIX;
+ sun.sun_path[0] = 0;
+ sprintf(sun.sun_path+1, "nstat%d", getuid());
+
+ if (scan_interval > 0) {
+ if (time_constant == 0)
+ time_constant = 60;
+ time_constant *= 1000;
+ W = 1 - 1/exp(log(10)*(double)scan_interval/time_constant);
+ if ((fd = socket(AF_UNIX, SOCK_STREAM, 0)) < 0) {
+ perror("nstat: socket");
+ exit(-1);
+ }
+ if (bind(fd, (struct sockaddr*)&sun, 2+1+strlen(sun.sun_path+1)) < 0) {
+ perror("nstat: bind");
+ exit(-1);
+ }
+ if (listen(fd, 5) < 0) {
+ perror("nstat: listen");
+ exit(-1);
+ }
+ if (daemon(0, 0)) {
+ perror("nstat: daemon");
+ exit(-1);
+ }
+ signal(SIGPIPE, SIG_IGN);
+ signal(SIGCHLD, sigchild);
+ server_loop(fd);
+ exit(0);
+ }
+
+ patterns = argv;
+ npatterns = argc;
+
+ if ((hist_name = getenv("NSTAT_HISTORY")) == NULL) {
+ hist_name = malloc(128);
+ sprintf(hist_name, "/tmp/.nstat.u%d", getuid());
+ }
+
+ if (reset_history)
+ unlink(hist_name);
+
+ if (!ignore_history || !no_update) {
+ struct stat stb;
+
+ fd = open(hist_name, O_RDWR|O_CREAT|O_NOFOLLOW, 0600);
+ if (fd < 0) {
+ perror("nstat: open history file");
+ exit(-1);
+ }
+ if ((hist_fp = fdopen(fd, "r+")) == NULL) {
+ perror("nstat: fdopen history file");
+ exit(-1);
+ }
+ if (flock(fileno(hist_fp), LOCK_EX)) {
+ perror("nstat: flock history file");
+ exit(-1);
+ }
+ if (fstat(fileno(hist_fp), &stb) != 0) {
+ perror("nstat: fstat history file");
+ exit(-1);
+ }
+ if (stb.st_nlink != 1 || stb.st_uid != getuid()) {
+ fprintf(stderr, "nstat: something is so wrong with history file, that I prefer not to proceed.\n");
+ exit(-1);
+ }
+ if (!ignore_history) {
+ FILE *tfp;
+ long uptime = -1;
+ if ((tfp = fopen("/proc/uptime", "r")) != NULL) {
+ if (fscanf(tfp, "%ld", &uptime) != 1)
+ uptime = -1;
+ fclose(tfp);
+ }
+ if (uptime >= 0 && time(NULL) >= stb.st_mtime+uptime) {
+ fprintf(stderr, "nstat: history is aged out, resetting\n");
+ if (ftruncate(fileno(hist_fp), 0) < 0)
+ perror("nstat: ftruncate");
+ }
+ }
+
+ load_good_table(hist_fp);
+
+ hist_db = kern_db;
+ kern_db = NULL;
+ }
+
+ if ((fd = socket(AF_UNIX, SOCK_STREAM, 0)) >= 0 &&
+ (connect(fd, (struct sockaddr*)&sun, 2+1+strlen(sun.sun_path+1)) == 0
+ || (strcpy(sun.sun_path+1, "nstat0"),
+ connect(fd, (struct sockaddr*)&sun, 2+1+strlen(sun.sun_path+1)) == 0))
+ && verify_forging(fd) == 0) {
+ FILE *sfp = fdopen(fd, "r");
+ load_good_table(sfp);
+ if (hist_db && source_mismatch) {
+ fprintf(stderr, "nstat: history is stale, ignoring it.\n");
+ hist_db = NULL;
+ }
+ fclose(sfp);
+ } else {
+ if (fd >= 0)
+ close(fd);
+ if (hist_db && info_source[0] && strcmp(info_source, "kernel")) {
+ fprintf(stderr, "nstat: history is stale, ignoring it.\n");
+ hist_db = NULL;
+ info_source[0] = 0;
+ }
+ load_netstat();
+ load_snmp6();
+ load_snmp();
+ if (info_source[0] == 0)
+ strcpy(info_source, "kernel");
+ }
+
+ if (!no_output) {
+ if (ignore_history || hist_db == NULL)
+ dump_kern_db(stdout, 0);
+ else
+ dump_incr_db(stdout);
+ }
+ if (!no_update) {
+ if (ftruncate(fileno(hist_fp), 0) < 0)
+ perror("nstat: ftruncate");
+ rewind(hist_fp);
+
+ json_output = 0;
+ dump_kern_db(hist_fp, 1);
+ fclose(hist_fp);
+ }
+ exit(0);
+}
diff --git a/iproute2/misc/rtacct.c b/iproute2/misc/rtacct.c
new file mode 100644
index 0000000..bb8c90f
--- /dev/null
+++ b/iproute2/misc/rtacct.c
@@ -0,0 +1,630 @@
+/*
+ * rtacct.c Applet to display contents of /proc/net/rt_acct.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <string.h>
+#include <errno.h>
+#include <time.h>
+#include <sys/time.h>
+#include <fnmatch.h>
+#include <sys/file.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+#include <sys/poll.h>
+#include <sys/wait.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+#include <signal.h>
+#include <math.h>
+
+#include "rt_names.h"
+
+#include <SNAPSHOT.h>
+
+int reset_history = 0;
+int ignore_history = 0;
+int no_output = 0;
+int no_update = 0;
+int scan_interval = 0;
+int time_constant = 0;
+int dump_zeros = 0;
+unsigned long magic_number = 0;
+double W;
+
+static int generic_proc_open(const char *env, const char *name)
+{
+ char store[1024];
+ char *p = getenv(env);
+ if (!p) {
+ p = getenv("PROC_ROOT") ? : "/proc";
+ snprintf(store, sizeof(store)-1, "%s/%s", p, name);
+ p = store;
+ }
+ return open(p, O_RDONLY);
+}
+
+static int net_rtacct_open(void)
+{
+ return generic_proc_open("PROC_NET_RTACCT", "net/rt_acct");
+}
+
+static __u32 rmap[256/4];
+
+struct rtacct_data
+{
+ __u32 ival[256*4];
+
+ unsigned long long val[256*4];
+ double rate[256*4];
+ char signature[128];
+};
+
+static struct rtacct_data kern_db_static;
+
+static struct rtacct_data *kern_db = &kern_db_static;
+static struct rtacct_data *hist_db;
+
+static void nread(int fd, char *buf, int tot)
+{
+ int count = 0;
+
+ while (count < tot) {
+ int n = read(fd, buf+count, tot-count);
+ if (n < 0) {
+ if (errno == EINTR)
+ continue;
+ exit(-1);
+ }
+ if (n == 0)
+ exit(-1);
+ count += n;
+ }
+}
+
+static __u32 *read_kern_table(__u32 *tbl)
+{
+ static __u32 *tbl_ptr;
+ int fd;
+
+ if (magic_number) {
+ if (tbl_ptr != NULL)
+ return tbl_ptr;
+
+ fd = open("/dev/mem", O_RDONLY);
+ if (fd < 0) {
+ perror("magic open");
+ exit(-1);
+ }
+ tbl_ptr = mmap(NULL, 4096,
+ PROT_READ,
+ MAP_SHARED,
+ fd, magic_number);
+ if ((unsigned long)tbl_ptr == ~0UL) {
+ perror("magic mmap");
+ exit(-1);
+ }
+ close(fd);
+ return tbl_ptr;
+ }
+
+ fd = net_rtacct_open();
+ if (fd >= 0) {
+ nread(fd, (char*)tbl, 256*16);
+ close(fd);
+ } else {
+ memset(tbl, 0, 256*16);
+ }
+ return tbl;
+}
+
+static void format_rate(FILE *fp, double rate)
+{
+ char temp[64];
+
+ if (rate > 1024*1024) {
+ sprintf(temp, "%uM", (unsigned)rint(rate/(1024*1024)));
+ fprintf(fp, " %-10s", temp);
+ } else if (rate > 1024) {
+ sprintf(temp, "%uK", (unsigned)rint(rate/1024));
+ fprintf(fp, " %-10s", temp);
+ } else
+ fprintf(fp, " %-10u", (unsigned)rate);
+}
+
+static void format_count(FILE *fp, unsigned long long val)
+{
+ if (val > 1024*1024*1024)
+ fprintf(fp, " %10lluM", val/(1024*1024));
+ else if (val > 1024*1024)
+ fprintf(fp, " %10lluK", val/1024);
+ else
+ fprintf(fp, " %10llu", val);
+}
+
+static void dump_abs_db(FILE *fp)
+{
+ int realm;
+ char b1[16];
+
+ if (!no_output) {
+ fprintf(fp, "#%s\n", kern_db->signature);
+ fprintf(fp,
+"%-10s "
+"%-10s "
+"%-10s "
+"%-10s "
+"%-10s "
+"\n"
+ , "Realm", "BytesTo", "PktsTo", "BytesFrom", "PktsFrom");
+ fprintf(fp,
+"%-10s "
+"%-10s "
+"%-10s "
+"%-10s "
+"%-10s "
+"\n"
+ , "", "BPSTo", "PPSTo", "BPSFrom", "PPSFrom");
+
+ }
+
+ for (realm=0; realm<256; realm++) {
+ int i;
+ unsigned long long *val;
+ double *rate;
+
+ if (!(rmap[realm>>5] & (1<<(realm&0x1f))))
+ continue;
+
+ val = &kern_db->val[realm*4];
+ rate = &kern_db->rate[realm*4];
+
+ if (!dump_zeros &&
+ !val[0] && !rate[0] &&
+ !val[1] && !rate[1] &&
+ !val[2] && !rate[2] &&
+ !val[3] && !rate[3])
+ continue;
+
+ if (hist_db) {
+ memcpy(&hist_db->val[realm*4], val, sizeof(*val)*4);
+ }
+
+ if (no_output)
+ continue;
+
+ fprintf(fp, "%-10s", rtnl_rtrealm_n2a(realm, b1, sizeof(b1)));
+ for (i = 0; i < 4; i++)
+ format_count(fp, val[i]);
+ fprintf(fp, "\n%-10s", "");
+ for (i = 0; i < 4; i++)
+ format_rate(fp, rate[i]);
+ fprintf(fp, "\n");
+ }
+}
+
+
+static void dump_incr_db(FILE *fp)
+{
+ int k, realm;
+ char b1[16];
+
+ if (!no_output) {
+ fprintf(fp, "#%s\n", kern_db->signature);
+ fprintf(fp,
+"%-10s "
+"%-10s "
+"%-10s "
+"%-10s "
+"%-10s "
+"\n"
+ , "Realm", "BytesTo", "PktsTo", "BytesFrom", "PktsFrom");
+ fprintf(fp,
+"%-10s "
+"%-10s "
+"%-10s "
+"%-10s "
+"%-10s "
+"\n"
+ , "", "BPSTo", "PPSTo", "BPSFrom", "PPSFrom");
+ }
+
+ for (realm=0; realm<256; realm++) {
+ int ovfl = 0;
+ int i;
+ unsigned long long *val;
+ double *rate;
+ unsigned long long rval[4];
+
+ if (!(rmap[realm>>5] & (1<<(realm&0x1f))))
+ continue;
+
+ val = &kern_db->val[realm*4];
+ rate = &kern_db->rate[realm*4];
+
+ for (k=0; k<4; k++) {
+ rval[k] = val[k];
+ if (rval[k] < hist_db->val[realm*4+k])
+ ovfl = 1;
+ else
+ rval[k] -= hist_db->val[realm*4+k];
+ }
+ if (ovfl) {
+ for (k=0; k<4; k++)
+ rval[k] = val[k];
+ }
+ if (hist_db) {
+ memcpy(&hist_db->val[realm*4], val, sizeof(*val)*4);
+ }
+
+ if (no_output)
+ continue;
+
+ if (!dump_zeros &&
+ !rval[0] && !rate[0] &&
+ !rval[1] && !rate[1] &&
+ !rval[2] && !rate[2] &&
+ !rval[3] && !rate[3])
+ continue;
+
+
+ fprintf(fp, "%-10s", rtnl_rtrealm_n2a(realm, b1, sizeof(b1)));
+ for (i = 0; i < 4; i++)
+ format_count(fp, rval[i]);
+ fprintf(fp, "\n%-10s", "");
+ for (i = 0; i < 4; i++)
+ format_rate(fp, rate[i]);
+ fprintf(fp, "\n");
+ }
+}
+
+
+static int children;
+
+static void sigchild(int signo)
+{
+}
+
+/* Server side only: read kernel data, update tables, calculate rates. */
+
+static void update_db(int interval)
+{
+ int i;
+ __u32 *ival;
+ __u32 _ival[256*4];
+
+ ival = read_kern_table(_ival);
+
+ for (i=0; i<256*4; i++) {
+ double sample;
+ __u32 incr = ival[i] - kern_db->ival[i];
+
+ if (ival[i] == 0 && incr == 0 &&
+ kern_db->val[i] == 0 && kern_db->rate[i] == 0)
+ continue;
+
+ kern_db->val[i] += incr;
+ kern_db->ival[i] = ival[i];
+ sample = (double)(incr*1000)/interval;
+ if (interval >= scan_interval) {
+ kern_db->rate[i] += W*(sample-kern_db->rate[i]);
+ } else if (interval >= 1000) {
+ if (interval >= time_constant) {
+ kern_db->rate[i] = sample;
+ } else {
+ double w = W*(double)interval/scan_interval;
+ kern_db->rate[i] += w*(sample-kern_db->rate[i]);
+ }
+ }
+ }
+}
+
+static void send_db(int fd)
+{
+ int tot = 0;
+
+ while (tot < sizeof(*kern_db)) {
+ int n = write(fd, ((char*)kern_db) + tot, sizeof(*kern_db)-tot);
+ if (n < 0) {
+ if (errno == EINTR)
+ continue;
+ return;
+ }
+ tot += n;
+ }
+}
+
+
+
+#define T_DIFF(a,b) (((a).tv_sec-(b).tv_sec)*1000 + ((a).tv_usec-(b).tv_usec)/1000)
+
+
+static void pad_kern_table(struct rtacct_data *dat, __u32 *ival)
+{
+ int i;
+ memset(dat->rate, 0, sizeof(dat->rate));
+ if (dat->ival != ival)
+ memcpy(dat->ival, ival, sizeof(dat->ival));
+ for (i=0; i<256*4; i++)
+ dat->val[i] = ival[i];
+}
+
+static void server_loop(int fd)
+{
+ struct timeval snaptime = { 0 };
+ struct pollfd p;
+ p.fd = fd;
+ p.events = p.revents = POLLIN;
+
+ sprintf(kern_db->signature,
+ "%u.%lu sampling_interval=%d time_const=%d",
+ (unsigned) getpid(), (unsigned long)random(),
+ scan_interval/1000, time_constant/1000);
+
+ pad_kern_table(kern_db, read_kern_table(kern_db->ival));
+
+ for (;;) {
+ int status;
+ int tdiff;
+ struct timeval now;
+ gettimeofday(&now, NULL);
+ tdiff = T_DIFF(now, snaptime);
+ if (tdiff >= scan_interval) {
+ update_db(tdiff);
+ snaptime = now;
+ tdiff = 0;
+ }
+ if (poll(&p, 1, tdiff + scan_interval) > 0
+ && (p.revents&POLLIN)) {
+ int clnt = accept(fd, NULL, NULL);
+ if (clnt >= 0) {
+ pid_t pid;
+ if (children >= 5) {
+ close(clnt);
+ } else if ((pid = fork()) != 0) {
+ if (pid>0)
+ children++;
+ close(clnt);
+ } else {
+ if (tdiff > 0)
+ update_db(tdiff);
+ send_db(clnt);
+ exit(0);
+ }
+ }
+ }
+ while (children && waitpid(-1, &status, WNOHANG) > 0)
+ children--;
+ }
+}
+
+static int verify_forging(int fd)
+{
+ struct ucred cred;
+ socklen_t olen = sizeof(cred);
+
+ if (getsockopt(fd, SOL_SOCKET, SO_PEERCRED, (void*)&cred, &olen) ||
+ olen < sizeof(cred))
+ return -1;
+ if (cred.uid == getuid() || cred.uid == 0)
+ return 0;
+ return -1;
+}
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr,
+"Usage: rtacct [ -h?vVzrnasd:t: ] [ ListOfRealms ]\n"
+ );
+ exit(-1);
+}
+
+int main(int argc, char *argv[])
+{
+ char hist_name[128];
+ struct sockaddr_un sun;
+ int ch;
+ int fd;
+
+ while ((ch = getopt(argc, argv, "h?vVzrM:nasd:t:")) != EOF) {
+ switch(ch) {
+ case 'z':
+ dump_zeros = 1;
+ break;
+ case 'r':
+ reset_history = 1;
+ break;
+ case 'a':
+ ignore_history = 1;
+ break;
+ case 's':
+ no_update = 1;
+ break;
+ case 'n':
+ no_output = 1;
+ break;
+ case 'd':
+ scan_interval = 1000*atoi(optarg);
+ break;
+ case 't':
+ if (sscanf(optarg, "%d", &time_constant) != 1 ||
+ time_constant <= 0) {
+ fprintf(stderr, "rtacct: invalid time constant divisor\n");
+ exit(-1);
+ }
+ break;
+ case 'v':
+ case 'V':
+ printf("rtacct utility, iproute2-ss%s\n", SNAPSHOT);
+ exit(0);
+ case 'M':
+ /* Some secret undocumented option, nobody
+ * is expected to ask about its sense. See?
+ */
+ sscanf(optarg, "%lx", &magic_number);
+ break;
+ case 'h':
+ case '?':
+ default:
+ usage();
+ }
+ }
+
+ argc -= optind;
+ argv += optind;
+
+ if (argc) {
+ while (argc > 0) {
+ __u32 realm;
+ if (rtnl_rtrealm_a2n(&realm, argv[0])) {
+ fprintf(stderr, "Warning: realm \"%s\" does not exist.\n", argv[0]);
+ exit(-1);
+ }
+ rmap[realm>>5] |= (1<<(realm&0x1f));
+ argc--; argv++;
+ }
+ } else {
+ memset(rmap, ~0, sizeof(rmap));
+ /* Always suppress zeros. */
+ dump_zeros = 0;
+ }
+
+ sun.sun_family = AF_UNIX;
+ sun.sun_path[0] = 0;
+ sprintf(sun.sun_path+1, "rtacct%d", getuid());
+
+ if (scan_interval > 0) {
+ if (time_constant == 0)
+ time_constant = 60;
+ time_constant *= 1000;
+ W = 1 - 1/exp(log(10)*(double)scan_interval/time_constant);
+ if ((fd = socket(AF_UNIX, SOCK_STREAM, 0)) < 0) {
+ perror("rtacct: socket");
+ exit(-1);
+ }
+ if (bind(fd, (struct sockaddr*)&sun, 2+1+strlen(sun.sun_path+1)) < 0) {
+ perror("rtacct: bind");
+ exit(-1);
+ }
+ if (listen(fd, 5) < 0) {
+ perror("rtacct: listen");
+ exit(-1);
+ }
+ if (daemon(0, 0)) {
+ perror("rtacct: daemon");
+ exit(-1);
+ }
+ signal(SIGPIPE, SIG_IGN);
+ signal(SIGCHLD, sigchild);
+ server_loop(fd);
+ exit(0);
+ }
+
+ if (getenv("RTACCT_HISTORY"))
+ snprintf(hist_name, sizeof(hist_name), "%s", getenv("RTACCT_HISTORY"));
+ else
+ sprintf(hist_name, "/tmp/.rtacct.u%d", getuid());
+
+ if (reset_history)
+ unlink(hist_name);
+
+ if (!ignore_history || !no_update) {
+ struct stat stb;
+
+ fd = open(hist_name, O_RDWR|O_CREAT|O_NOFOLLOW, 0600);
+ if (fd < 0) {
+ perror("rtacct: open history file");
+ exit(-1);
+ }
+ if (flock(fd, LOCK_EX)) {
+ perror("rtacct: flock history file");
+ exit(-1);
+ }
+ if (fstat(fd, &stb) != 0) {
+ perror("rtacct: fstat history file");
+ exit(-1);
+ }
+ if (stb.st_nlink != 1 || stb.st_uid != getuid()) {
+ fprintf(stderr, "rtacct: something is so wrong with history file, that I prefer not to proceed.\n");
+ exit(-1);
+ }
+ if (stb.st_size != sizeof(*hist_db))
+ if (write(fd, kern_db, sizeof(*hist_db)) < 0) {
+ perror("rtacct: write history file");
+ exit(-1);
+ }
+
+ hist_db = mmap(NULL, sizeof(*hist_db),
+ PROT_READ|PROT_WRITE,
+ no_update ? MAP_PRIVATE : MAP_SHARED,
+ fd, 0);
+
+ if ((unsigned long)hist_db == ~0UL) {
+ perror("mmap");
+ exit(-1);
+ }
+
+ if (!ignore_history) {
+ FILE *tfp;
+ long uptime = -1;
+ if ((tfp = fopen("/proc/uptime", "r")) != NULL) {
+ if (fscanf(tfp, "%ld", &uptime) != 1)
+ uptime = -1;
+ fclose(tfp);
+ }
+
+ if (uptime >= 0 && time(NULL) >= stb.st_mtime+uptime) {
+ fprintf(stderr, "rtacct: history is aged out, resetting\n");
+ memset(hist_db, 0, sizeof(*hist_db));
+ }
+ }
+
+ close(fd);
+ }
+
+ if ((fd = socket(AF_UNIX, SOCK_STREAM, 0)) >= 0 &&
+ (connect(fd, (struct sockaddr*)&sun, 2+1+strlen(sun.sun_path+1)) == 0
+ || (strcpy(sun.sun_path+1, "rtacct0"),
+ connect(fd, (struct sockaddr*)&sun, 2+1+strlen(sun.sun_path+1)) == 0))
+ && verify_forging(fd) == 0) {
+ nread(fd, (char*)kern_db, sizeof(*kern_db));
+ if (hist_db && hist_db->signature[0] &&
+ strcmp(kern_db->signature, hist_db->signature)) {
+ fprintf(stderr, "rtacct: history is stale, ignoring it.\n");
+ hist_db = NULL;
+ }
+ close(fd);
+ } else {
+ if (fd >= 0)
+ close(fd);
+
+ if (hist_db && hist_db->signature[0] &&
+ strcmp(hist_db->signature, "kernel")) {
+ fprintf(stderr, "rtacct: history is stale, ignoring it.\n");
+ hist_db = NULL;
+ }
+
+ pad_kern_table(kern_db, read_kern_table(kern_db->ival));
+ strcpy(kern_db->signature, "kernel");
+ }
+
+ if (ignore_history || hist_db == NULL)
+ dump_abs_db(stdout);
+ else
+ dump_incr_db(stdout);
+
+ exit(0);
+}
diff --git a/iproute2/misc/ss.c b/iproute2/misc/ss.c
new file mode 100644
index 0000000..13fcc8f
--- /dev/null
+++ b/iproute2/misc/ss.c
@@ -0,0 +1,3985 @@
+/*
+ * ss.c "sockstat", socket statistics
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/uio.h>
+#include <netinet/in.h>
+#include <string.h>
+#include <errno.h>
+#include <netdb.h>
+#include <arpa/inet.h>
+#include <dirent.h>
+#include <fnmatch.h>
+#include <getopt.h>
+#include <stdbool.h>
+
+#include "utils.h"
+#include "rt_names.h"
+#include "ll_map.h"
+#include "libnetlink.h"
+#include "namespace.h"
+#include "SNAPSHOT.h"
+
+#include <linux/tcp.h>
+#include <linux/sock_diag.h>
+#include <linux/inet_diag.h>
+#include <linux/unix_diag.h>
+#include <linux/netdevice.h> /* for MAX_ADDR_LEN */
+#include <linux/filter.h>
+#include <linux/packet_diag.h>
+#include <linux/netlink_diag.h>
+
+#define MAGIC_SEQ 123456
+
+#define DIAG_REQUEST(_req, _r) \
+ struct { \
+ struct nlmsghdr nlh; \
+ _r; \
+ } _req = { \
+ .nlh = { \
+ .nlmsg_type = SOCK_DIAG_BY_FAMILY, \
+ .nlmsg_flags = NLM_F_ROOT|NLM_F_MATCH|NLM_F_REQUEST,\
+ .nlmsg_seq = MAGIC_SEQ, \
+ .nlmsg_len = sizeof(_req), \
+ }, \
+ }
+
+#if HAVE_SELINUX
+#include <selinux/selinux.h>
+#else
+/* Stubs for SELinux functions */
+static int is_selinux_enabled(void)
+{
+ return -1;
+}
+
+static int getpidcon(pid_t pid, char **context)
+{
+ *context = NULL;
+ return -1;
+}
+
+static int getfilecon(char *path, char **context)
+{
+ *context = NULL;
+ return -1;
+}
+
+static int security_get_initial_context(char *name, char **context)
+{
+ *context = NULL;
+ return -1;
+}
+#endif
+
+int resolve_hosts = 0;
+int resolve_services = 1;
+int preferred_family = AF_UNSPEC;
+int show_options = 0;
+int show_details = 0;
+int show_users = 0;
+int show_mem = 0;
+int show_tcpinfo = 0;
+int show_bpf = 0;
+int show_proc_ctx = 0;
+int show_sock_ctx = 0;
+/* If show_users & show_proc_ctx only do user_ent_hash_build() once */
+int user_ent_hash_build_init = 0;
+int follow_events = 0;
+
+int netid_width;
+int state_width;
+int addrp_width;
+int addr_width;
+int serv_width;
+int screen_width;
+
+static const char *TCP_PROTO = "tcp";
+static const char *UDP_PROTO = "udp";
+static const char *RAW_PROTO = "raw";
+static const char *dg_proto = NULL;
+
+enum
+{
+ TCP_DB,
+ DCCP_DB,
+ UDP_DB,
+ RAW_DB,
+ UNIX_DG_DB,
+ UNIX_ST_DB,
+ UNIX_SQ_DB,
+ PACKET_DG_DB,
+ PACKET_R_DB,
+ NETLINK_DB,
+ MAX_DB
+};
+
+#define PACKET_DBM ((1<<PACKET_DG_DB)|(1<<PACKET_R_DB))
+#define UNIX_DBM ((1<<UNIX_DG_DB)|(1<<UNIX_ST_DB)|(1<<UNIX_SQ_DB))
+#define ALL_DB ((1<<MAX_DB)-1)
+#define INET_DBM ((1<<TCP_DB)|(1<<UDP_DB)|(1<<DCCP_DB)|(1<<RAW_DB))
+
+enum {
+ SS_UNKNOWN,
+ SS_ESTABLISHED,
+ SS_SYN_SENT,
+ SS_SYN_RECV,
+ SS_FIN_WAIT1,
+ SS_FIN_WAIT2,
+ SS_TIME_WAIT,
+ SS_CLOSE,
+ SS_CLOSE_WAIT,
+ SS_LAST_ACK,
+ SS_LISTEN,
+ SS_CLOSING,
+ SS_MAX
+};
+
+#define SS_ALL ((1 << SS_MAX) - 1)
+#define SS_CONN (SS_ALL & ~((1<<SS_LISTEN)|(1<<SS_CLOSE)|(1<<SS_TIME_WAIT)|(1<<SS_SYN_RECV)))
+
+#include "ssfilter.h"
+
+struct filter
+{
+ int dbs;
+ int states;
+ int families;
+ struct ssfilter *f;
+ bool kill;
+};
+
+static const struct filter default_dbs[MAX_DB] = {
+ [TCP_DB] = {
+ .states = SS_CONN,
+ .families = (1 << AF_INET) | (1 << AF_INET6),
+ },
+ [DCCP_DB] = {
+ .states = SS_CONN,
+ .families = (1 << AF_INET) | (1 << AF_INET6),
+ },
+ [UDP_DB] = {
+ .states = (1 << SS_ESTABLISHED),
+ .families = (1 << AF_INET) | (1 << AF_INET6),
+ },
+ [RAW_DB] = {
+ .states = (1 << SS_ESTABLISHED),
+ .families = (1 << AF_INET) | (1 << AF_INET6),
+ },
+ [UNIX_DG_DB] = {
+ .states = (1 << SS_CLOSE),
+ .families = (1 << AF_UNIX),
+ },
+ [UNIX_ST_DB] = {
+ .states = SS_CONN,
+ .families = (1 << AF_UNIX),
+ },
+ [UNIX_SQ_DB] = {
+ .states = SS_CONN,
+ .families = (1 << AF_UNIX),
+ },
+ [PACKET_DG_DB] = {
+ .states = (1 << SS_CLOSE),
+ .families = (1 << AF_PACKET),
+ },
+ [PACKET_R_DB] = {
+ .states = (1 << SS_CLOSE),
+ .families = (1 << AF_PACKET),
+ },
+ [NETLINK_DB] = {
+ .states = (1 << SS_CLOSE),
+ .families = (1 << AF_NETLINK),
+ },
+};
+
+static const struct filter default_afs[AF_MAX] = {
+ [AF_INET] = {
+ .dbs = INET_DBM,
+ .states = SS_CONN,
+ },
+ [AF_INET6] = {
+ .dbs = INET_DBM,
+ .states = SS_CONN,
+ },
+ [AF_UNIX] = {
+ .dbs = UNIX_DBM,
+ .states = SS_CONN,
+ },
+ [AF_PACKET] = {
+ .dbs = PACKET_DBM,
+ .states = (1 << SS_CLOSE),
+ },
+ [AF_NETLINK] = {
+ .dbs = (1 << NETLINK_DB),
+ .states = (1 << SS_CLOSE),
+ },
+};
+
+static int do_default = 1;
+static struct filter current_filter;
+
+static void filter_db_set(struct filter *f, int db)
+{
+ f->states |= default_dbs[db].states;
+ f->dbs |= 1 << db;
+ do_default = 0;
+}
+
+static void filter_af_set(struct filter *f, int af)
+{
+ f->states |= default_afs[af].states;
+ f->families |= 1 << af;
+ do_default = 0;
+ preferred_family = af;
+}
+
+static int filter_af_get(struct filter *f, int af)
+{
+ return f->families & (1 << af);
+}
+
+static void filter_default_dbs(struct filter *f)
+{
+ filter_db_set(f, UDP_DB);
+ filter_db_set(f, DCCP_DB);
+ filter_db_set(f, TCP_DB);
+ filter_db_set(f, RAW_DB);
+ filter_db_set(f, UNIX_ST_DB);
+ filter_db_set(f, UNIX_DG_DB);
+ filter_db_set(f, UNIX_SQ_DB);
+ filter_db_set(f, PACKET_R_DB);
+ filter_db_set(f, PACKET_DG_DB);
+ filter_db_set(f, NETLINK_DB);
+}
+
+static void filter_states_set(struct filter *f, int states)
+{
+ if (states)
+ f->states = (f->states | states) & states;
+}
+
+static void filter_merge_defaults(struct filter *f)
+{
+ int db;
+ int af;
+
+ for (db = 0; db < MAX_DB; db++) {
+ if (!(f->dbs & (1 << db)))
+ continue;
+
+ if (!(default_dbs[db].families & f->families))
+ f->families |= default_dbs[db].families;
+ }
+ for (af = 0; af < AF_MAX; af++) {
+ if (!(f->families & (1 << af)))
+ continue;
+
+ if (!(default_afs[af].dbs & f->dbs))
+ f->dbs |= default_afs[af].dbs;
+ }
+}
+
+static FILE *generic_proc_open(const char *env, const char *name)
+{
+ const char *p = getenv(env);
+ char store[128];
+
+ if (!p) {
+ p = getenv("PROC_ROOT") ? : "/proc";
+ snprintf(store, sizeof(store)-1, "%s/%s", p, name);
+ p = store;
+ }
+
+ return fopen(p, "r");
+}
+
+static FILE *net_tcp_open(void)
+{
+ return generic_proc_open("PROC_NET_TCP", "net/tcp");
+}
+
+static FILE *net_tcp6_open(void)
+{
+ return generic_proc_open("PROC_NET_TCP6", "net/tcp6");
+}
+
+static FILE *net_udp_open(void)
+{
+ return generic_proc_open("PROC_NET_UDP", "net/udp");
+}
+
+static FILE *net_udp6_open(void)
+{
+ return generic_proc_open("PROC_NET_UDP6", "net/udp6");
+}
+
+static FILE *net_raw_open(void)
+{
+ return generic_proc_open("PROC_NET_RAW", "net/raw");
+}
+
+static FILE *net_raw6_open(void)
+{
+ return generic_proc_open("PROC_NET_RAW6", "net/raw6");
+}
+
+static FILE *net_unix_open(void)
+{
+ return generic_proc_open("PROC_NET_UNIX", "net/unix");
+}
+
+static FILE *net_packet_open(void)
+{
+ return generic_proc_open("PROC_NET_PACKET", "net/packet");
+}
+
+static FILE *net_netlink_open(void)
+{
+ return generic_proc_open("PROC_NET_NETLINK", "net/netlink");
+}
+
+static FILE *slabinfo_open(void)
+{
+ return generic_proc_open("PROC_SLABINFO", "slabinfo");
+}
+
+static FILE *net_sockstat_open(void)
+{
+ return generic_proc_open("PROC_NET_SOCKSTAT", "net/sockstat");
+}
+
+static FILE *net_sockstat6_open(void)
+{
+ return generic_proc_open("PROC_NET_SOCKSTAT6", "net/sockstat6");
+}
+
+static FILE *net_snmp_open(void)
+{
+ return generic_proc_open("PROC_NET_SNMP", "net/snmp");
+}
+
+static FILE *ephemeral_ports_open(void)
+{
+ return generic_proc_open("PROC_IP_LOCAL_PORT_RANGE", "sys/net/ipv4/ip_local_port_range");
+}
+
+struct user_ent {
+ struct user_ent *next;
+ unsigned int ino;
+ int pid;
+ int fd;
+ char *process;
+ char *process_ctx;
+ char *socket_ctx;
+};
+
+#define USER_ENT_HASH_SIZE 256
+struct user_ent *user_ent_hash[USER_ENT_HASH_SIZE];
+
+static int user_ent_hashfn(unsigned int ino)
+{
+ int val = (ino >> 24) ^ (ino >> 16) ^ (ino >> 8) ^ ino;
+
+ return val & (USER_ENT_HASH_SIZE - 1);
+}
+
+static void user_ent_add(unsigned int ino, char *process,
+ int pid, int fd,
+ char *proc_ctx,
+ char *sock_ctx)
+{
+ struct user_ent *p, **pp;
+
+ p = malloc(sizeof(struct user_ent));
+ if (!p) {
+ fprintf(stderr, "ss: failed to malloc buffer\n");
+ abort();
+ }
+ p->next = NULL;
+ p->ino = ino;
+ p->pid = pid;
+ p->fd = fd;
+ p->process = strdup(process);
+ p->process_ctx = strdup(proc_ctx);
+ p->socket_ctx = strdup(sock_ctx);
+
+ pp = &user_ent_hash[user_ent_hashfn(ino)];
+ p->next = *pp;
+ *pp = p;
+}
+
+static void user_ent_destroy(void)
+{
+ struct user_ent *p, *p_next;
+ int cnt = 0;
+
+ while (cnt != USER_ENT_HASH_SIZE) {
+ p = user_ent_hash[cnt];
+ while (p) {
+ free(p->process);
+ free(p->process_ctx);
+ free(p->socket_ctx);
+ p_next = p->next;
+ free(p);
+ p = p_next;
+ }
+ cnt++;
+ }
+}
+
+static void user_ent_hash_build(void)
+{
+ const char *root = getenv("PROC_ROOT") ? : "/proc/";
+ struct dirent *d;
+ char name[1024];
+ int nameoff;
+ DIR *dir;
+ char *pid_context;
+ char *sock_context;
+ const char *no_ctx = "unavailable";
+
+ /* If show_users & show_proc_ctx set only do this once */
+ if (user_ent_hash_build_init != 0)
+ return;
+
+ user_ent_hash_build_init = 1;
+
+ strncpy(name, root, sizeof(name)-1);
+ name[sizeof(name)-1] = 0;
+
+ if (strlen(name) == 0 || name[strlen(name)-1] != '/')
+ strcat(name, "/");
+
+ nameoff = strlen(name);
+
+ dir = opendir(name);
+ if (!dir)
+ return;
+
+ while ((d = readdir(dir)) != NULL) {
+ struct dirent *d1;
+ char process[16];
+ char *p;
+ int pid, pos;
+ DIR *dir1;
+ char crap;
+
+ if (sscanf(d->d_name, "%d%c", &pid, &crap) != 1)
+ continue;
+
+ if (getpidcon(pid, &pid_context) != 0)
+ pid_context = strdup(no_ctx);
+
+ snprintf(name + nameoff, sizeof(name) - nameoff, "%d/fd/", pid);
+ pos = strlen(name);
+ if ((dir1 = opendir(name)) == NULL) {
+ free(pid_context);
+ continue;
+ }
+
+ process[0] = '\0';
+ p = process;
+
+ while ((d1 = readdir(dir1)) != NULL) {
+ const char *pattern = "socket:[";
+ unsigned int ino;
+ char lnk[64];
+ int fd;
+ ssize_t link_len;
+ char tmp[1024];
+
+ if (sscanf(d1->d_name, "%d%c", &fd, &crap) != 1)
+ continue;
+
+ snprintf(name+pos, sizeof(name) - pos, "%d", fd);
+
+ link_len = readlink(name, lnk, sizeof(lnk)-1);
+ if (link_len == -1)
+ continue;
+ lnk[link_len] = '\0';
+
+ if (strncmp(lnk, pattern, strlen(pattern)))
+ continue;
+
+ sscanf(lnk, "socket:[%u]", &ino);
+
+ snprintf(tmp, sizeof(tmp), "%s/%d/fd/%s",
+ root, pid, d1->d_name);
+
+ if (getfilecon(tmp, &sock_context) <= 0)
+ sock_context = strdup(no_ctx);
+
+ if (*p == '\0') {
+ FILE *fp;
+
+ snprintf(tmp, sizeof(tmp), "%s/%d/stat",
+ root, pid);
+ if ((fp = fopen(tmp, "r")) != NULL) {
+ if (fscanf(fp, "%*d (%[^)])", p) < 1)
+ ; /* ignore */
+ fclose(fp);
+ }
+ }
+ user_ent_add(ino, p, pid, fd,
+ pid_context, sock_context);
+ free(sock_context);
+ }
+ free(pid_context);
+ closedir(dir1);
+ }
+ closedir(dir);
+}
+
+enum entry_types {
+ USERS,
+ PROC_CTX,
+ PROC_SOCK_CTX
+};
+
+#define ENTRY_BUF_SIZE 512
+static int find_entry(unsigned ino, char **buf, int type)
+{
+ struct user_ent *p;
+ int cnt = 0;
+ char *ptr;
+ char *new_buf;
+ int len, new_buf_len;
+ int buf_used = 0;
+ int buf_len = 0;
+
+ if (!ino)
+ return 0;
+
+ p = user_ent_hash[user_ent_hashfn(ino)];
+ ptr = *buf = NULL;
+ while (p) {
+ if (p->ino != ino)
+ goto next;
+
+ while (1) {
+ ptr = *buf + buf_used;
+ switch (type) {
+ case USERS:
+ len = snprintf(ptr, buf_len - buf_used,
+ "(\"%s\",pid=%d,fd=%d),",
+ p->process, p->pid, p->fd);
+ break;
+ case PROC_CTX:
+ len = snprintf(ptr, buf_len - buf_used,
+ "(\"%s\",pid=%d,proc_ctx=%s,fd=%d),",
+ p->process, p->pid,
+ p->process_ctx, p->fd);
+ break;
+ case PROC_SOCK_CTX:
+ len = snprintf(ptr, buf_len - buf_used,
+ "(\"%s\",pid=%d,proc_ctx=%s,fd=%d,sock_ctx=%s),",
+ p->process, p->pid,
+ p->process_ctx, p->fd,
+ p->socket_ctx);
+ break;
+ default:
+ fprintf(stderr, "ss: invalid type: %d\n", type);
+ abort();
+ }
+
+ if (len < 0 || len >= buf_len - buf_used) {
+ new_buf_len = buf_len + ENTRY_BUF_SIZE;
+ new_buf = realloc(*buf, new_buf_len);
+ if (!new_buf) {
+ fprintf(stderr, "ss: failed to malloc buffer\n");
+ abort();
+ }
+ *buf = new_buf;
+ buf_len = new_buf_len;
+ continue;
+ } else {
+ buf_used += len;
+ break;
+ }
+ }
+ cnt++;
+next:
+ p = p->next;
+ }
+ if (buf_used) {
+ ptr = *buf + buf_used;
+ ptr[-1] = '\0';
+ }
+ return cnt;
+}
+
+/* Get stats from slab */
+
+struct slabstat
+{
+ int socks;
+ int tcp_ports;
+ int tcp_tws;
+ int tcp_syns;
+ int skbs;
+};
+
+static struct slabstat slabstat;
+
+static const char *slabstat_ids[] =
+{
+ "sock",
+ "tcp_bind_bucket",
+ "tcp_tw_bucket",
+ "tcp_open_request",
+ "skbuff_head_cache",
+};
+
+static int get_slabstat(struct slabstat *s)
+{
+ char buf[256];
+ FILE *fp;
+ int cnt;
+ static int slabstat_valid;
+
+ if (slabstat_valid)
+ return 0;
+
+ memset(s, 0, sizeof(*s));
+
+ fp = slabinfo_open();
+ if (!fp)
+ return -1;
+
+ cnt = sizeof(*s)/sizeof(int);
+
+ if (!fgets(buf, sizeof(buf), fp)) {
+ fclose(fp);
+ return -1;
+ }
+ while(fgets(buf, sizeof(buf), fp) != NULL) {
+ int i;
+ for (i=0; i<sizeof(slabstat_ids)/sizeof(slabstat_ids[0]); i++) {
+ if (memcmp(buf, slabstat_ids[i], strlen(slabstat_ids[i])) == 0) {
+ sscanf(buf, "%*s%d", ((int *)s) + i);
+ cnt--;
+ break;
+ }
+ }
+ if (cnt <= 0)
+ break;
+ }
+
+ slabstat_valid = 1;
+
+ fclose(fp);
+ return 0;
+}
+
+static unsigned long long cookie_sk_get(const uint32_t *cookie)
+{
+ return (((unsigned long long)cookie[1] << 31) << 1) | cookie[0];
+}
+
+static const char *sstate_name[] = {
+ "UNKNOWN",
+ [SS_ESTABLISHED] = "ESTAB",
+ [SS_SYN_SENT] = "SYN-SENT",
+ [SS_SYN_RECV] = "SYN-RECV",
+ [SS_FIN_WAIT1] = "FIN-WAIT-1",
+ [SS_FIN_WAIT2] = "FIN-WAIT-2",
+ [SS_TIME_WAIT] = "TIME-WAIT",
+ [SS_CLOSE] = "UNCONN",
+ [SS_CLOSE_WAIT] = "CLOSE-WAIT",
+ [SS_LAST_ACK] = "LAST-ACK",
+ [SS_LISTEN] = "LISTEN",
+ [SS_CLOSING] = "CLOSING",
+};
+
+static const char *sstate_namel[] = {
+ "UNKNOWN",
+ [SS_ESTABLISHED] = "established",
+ [SS_SYN_SENT] = "syn-sent",
+ [SS_SYN_RECV] = "syn-recv",
+ [SS_FIN_WAIT1] = "fin-wait-1",
+ [SS_FIN_WAIT2] = "fin-wait-2",
+ [SS_TIME_WAIT] = "time-wait",
+ [SS_CLOSE] = "unconnected",
+ [SS_CLOSE_WAIT] = "close-wait",
+ [SS_LAST_ACK] = "last-ack",
+ [SS_LISTEN] = "listening",
+ [SS_CLOSING] = "closing",
+};
+
+struct sockstat
+{
+ struct sockstat *next;
+ unsigned int type;
+ uint16_t prot;
+ inet_prefix local;
+ inet_prefix remote;
+ int lport;
+ int rport;
+ int state;
+ int rq, wq;
+ unsigned ino;
+ unsigned uid;
+ int refcnt;
+ unsigned int iface;
+ unsigned long long sk;
+ char *name;
+ char *peer_name;
+};
+
+struct dctcpstat
+{
+ unsigned int ce_state;
+ unsigned int alpha;
+ unsigned int ab_ecn;
+ unsigned int ab_tot;
+ bool enabled;
+};
+
+struct tcpstat
+{
+ struct sockstat ss;
+ int timer;
+ int timeout;
+ int probes;
+ char cong_alg[16];
+ double rto, ato, rtt, rttvar;
+ int qack, cwnd, ssthresh, backoff;
+ double send_bps;
+ int snd_wscale;
+ int rcv_wscale;
+ int mss;
+ unsigned int lastsnd;
+ unsigned int lastrcv;
+ unsigned int lastack;
+ double pacing_rate;
+ double pacing_rate_max;
+ unsigned long long bytes_acked;
+ unsigned long long bytes_received;
+ unsigned int segs_out;
+ unsigned int segs_in;
+ unsigned int unacked;
+ unsigned int retrans;
+ unsigned int retrans_total;
+ unsigned int lost;
+ unsigned int sacked;
+ unsigned int fackets;
+ unsigned int reordering;
+ double rcv_rtt;
+ int rcv_space;
+ bool has_ts_opt;
+ bool has_sack_opt;
+ bool has_ecn_opt;
+ bool has_ecnseen_opt;
+ bool has_fastopen_opt;
+ bool has_wscale_opt;
+ struct dctcpstat *dctcp;
+};
+
+static void sock_state_print(struct sockstat *s, const char *sock_name)
+{
+ if (netid_width)
+ printf("%-*s ", netid_width, sock_name);
+ if (state_width)
+ printf("%-*s ", state_width, sstate_name[s->state]);
+
+ printf("%-6d %-6d ", s->rq, s->wq);
+}
+
+static void sock_details_print(struct sockstat *s)
+{
+ if (s->uid)
+ printf(" uid:%u", s->uid);
+
+ printf(" ino:%u", s->ino);
+ printf(" sk:%llx", s->sk);
+}
+
+static void sock_addr_print_width(int addr_len, const char *addr, char *delim,
+ int port_len, const char *port, const char *ifname)
+{
+ if (ifname) {
+ printf("%*s%%%s%s%-*s ", addr_len, addr, ifname, delim,
+ port_len, port);
+ }
+ else {
+ printf("%*s%s%-*s ", addr_len, addr, delim, port_len, port);
+ }
+}
+
+static void sock_addr_print(const char *addr, char *delim, const char *port,
+ const char *ifname)
+{
+ sock_addr_print_width(addr_width, addr, delim, serv_width, port, ifname);
+}
+
+static const char *tmr_name[] = {
+ "off",
+ "on",
+ "keepalive",
+ "timewait",
+ "persist",
+ "unknown"
+};
+
+static const char *print_ms_timer(int timeout)
+{
+ static char buf[64];
+ int secs, msecs, minutes;
+ if (timeout < 0)
+ timeout = 0;
+ secs = timeout/1000;
+ minutes = secs/60;
+ secs = secs%60;
+ msecs = timeout%1000;
+ buf[0] = 0;
+ if (minutes) {
+ msecs = 0;
+ snprintf(buf, sizeof(buf)-16, "%dmin", minutes);
+ if (minutes > 9)
+ secs = 0;
+ }
+ if (secs) {
+ if (secs > 9)
+ msecs = 0;
+ sprintf(buf+strlen(buf), "%d%s", secs, msecs ? "." : "sec");
+ }
+ if (msecs)
+ sprintf(buf+strlen(buf), "%03dms", msecs);
+ return buf;
+}
+
+struct scache {
+ struct scache *next;
+ int port;
+ char *name;
+ const char *proto;
+};
+
+struct scache *rlist;
+
+static void init_service_resolver(void)
+{
+ char buf[128];
+ FILE *fp = popen("/usr/sbin/rpcinfo -p 2>/dev/null", "r");
+
+ if (!fp)
+ return;
+
+ if (!fgets(buf, sizeof(buf), fp)) {
+ pclose(fp);
+ return;
+ }
+ while (fgets(buf, sizeof(buf), fp) != NULL) {
+ unsigned int progn, port;
+ char proto[128], prog[128] = "rpc.";
+ struct scache *c;
+
+ if (sscanf(buf, "%u %*d %s %u %s",
+ &progn, proto, &port, prog+4) != 4)
+ continue;
+
+ if (!(c = malloc(sizeof(*c))))
+ continue;
+
+ c->port = port;
+ c->name = strdup(prog);
+ if (strcmp(proto, TCP_PROTO) == 0)
+ c->proto = TCP_PROTO;
+ else if (strcmp(proto, UDP_PROTO) == 0)
+ c->proto = UDP_PROTO;
+ else
+ c->proto = NULL;
+ c->next = rlist;
+ rlist = c;
+ }
+ pclose(fp);
+}
+
+/* Even do not try default linux ephemeral port ranges:
+ * default /etc/services contains so much of useless crap
+ * wouldbe "allocated" to this area that resolution
+ * is really harmful. I shrug each time when seeing
+ * "socks" or "cfinger" in dumps.
+ */
+static int is_ephemeral(int port)
+{
+ static int min = 0, max = 0;
+
+ if (!min) {
+ FILE *f = ephemeral_ports_open();
+ if (!f || fscanf(f, "%d %d", &min, &max) < 2) {
+ min = 1024;
+ max = 4999;
+ }
+ if (f)
+ fclose(f);
+ }
+ return port >= min && port <= max;
+}
+
+
+static const char *__resolve_service(int port)
+{
+ struct scache *c;
+
+ for (c = rlist; c; c = c->next) {
+ if (c->port == port && c->proto == dg_proto)
+ return c->name;
+ }
+
+ if (!is_ephemeral(port)) {
+ static int notfirst;
+ struct servent *se;
+ if (!notfirst) {
+ setservent(1);
+ notfirst = 1;
+ }
+ se = getservbyport(htons(port), dg_proto);
+ if (se)
+ return se->s_name;
+ }
+
+ return NULL;
+}
+
+#define SCACHE_BUCKETS 1024
+static struct scache *cache_htab[SCACHE_BUCKETS];
+
+static const char *resolve_service(int port)
+{
+ static char buf[128];
+ struct scache *c;
+ const char *res;
+ int hash;
+
+ if (port == 0) {
+ buf[0] = '*';
+ buf[1] = 0;
+ return buf;
+ }
+
+ if (!resolve_services)
+ goto do_numeric;
+
+ if (dg_proto == RAW_PROTO)
+ return inet_proto_n2a(port, buf, sizeof(buf));
+
+
+ hash = (port^(((unsigned long)dg_proto)>>2)) % SCACHE_BUCKETS;
+
+ for (c = cache_htab[hash]; c; c = c->next) {
+ if (c->port == port && c->proto == dg_proto)
+ goto do_cache;
+ }
+
+ c = malloc(sizeof(*c));
+ if (!c)
+ goto do_numeric;
+ res = __resolve_service(port);
+ c->port = port;
+ c->name = res ? strdup(res) : NULL;
+ c->proto = dg_proto;
+ c->next = cache_htab[hash];
+ cache_htab[hash] = c;
+
+do_cache:
+ if (c->name)
+ return c->name;
+
+do_numeric:
+ sprintf(buf, "%u", port);
+ return buf;
+}
+
+static void inet_addr_print(const inet_prefix *a, int port, unsigned int ifindex)
+{
+ char buf[1024];
+ const char *ap = buf;
+ int est_len = addr_width;
+ const char *ifname = NULL;
+
+ if (a->family == AF_INET) {
+ if (a->data[0] == 0) {
+ buf[0] = '*';
+ buf[1] = 0;
+ } else {
+ ap = format_host(AF_INET, 4, a->data, buf, sizeof(buf));
+ }
+ } else {
+ ap = format_host(a->family, 16, a->data, buf, sizeof(buf));
+ est_len = strlen(ap);
+ if (est_len <= addr_width)
+ est_len = addr_width;
+ else
+ est_len = addr_width + ((est_len-addr_width+3)/4)*4;
+ }
+
+ if (ifindex) {
+ ifname = ll_index_to_name(ifindex);
+ est_len -= strlen(ifname) + 1; /* +1 for percent char */
+ if (est_len < 0)
+ est_len = 0;
+ }
+
+ sock_addr_print_width(est_len, ap, ":", serv_width, resolve_service(port),
+ ifname);
+}
+
+struct aafilter
+{
+ inet_prefix addr;
+ int port;
+ struct aafilter *next;
+};
+
+static int inet2_addr_match(const inet_prefix *a, const inet_prefix *p,
+ int plen)
+{
+ if (!inet_addr_match(a, p, plen))
+ return 0;
+
+ /* Cursed "v4 mapped" addresses: v4 mapped socket matches
+ * pure IPv4 rule, but v4-mapped rule selects only v4-mapped
+ * sockets. Fair? */
+ if (p->family == AF_INET && a->family == AF_INET6) {
+ if (a->data[0] == 0 && a->data[1] == 0 &&
+ a->data[2] == htonl(0xffff)) {
+ inet_prefix tmp = *a;
+ tmp.data[0] = a->data[3];
+ return inet_addr_match(&tmp, p, plen);
+ }
+ }
+ return 1;
+}
+
+static int unix_match(const inet_prefix *a, const inet_prefix *p)
+{
+ char *addr, *pattern;
+ memcpy(&addr, a->data, sizeof(addr));
+ memcpy(&pattern, p->data, sizeof(pattern));
+ if (pattern == NULL)
+ return 1;
+ if (addr == NULL)
+ addr = "";
+ return !fnmatch(pattern, addr, 0);
+}
+
+static int run_ssfilter(struct ssfilter *f, struct sockstat *s)
+{
+ switch (f->type) {
+ case SSF_S_AUTO:
+ {
+ if (s->local.family == AF_UNIX) {
+ char *p;
+ memcpy(&p, s->local.data, sizeof(p));
+ return p == NULL || (p[0] == '@' && strlen(p) == 6 &&
+ strspn(p+1, "0123456789abcdef") == 5);
+ }
+ if (s->local.family == AF_PACKET)
+ return s->lport == 0 && s->local.data[0] == 0;
+ if (s->local.family == AF_NETLINK)
+ return s->lport < 0;
+
+ return is_ephemeral(s->lport);
+ }
+ case SSF_DCOND:
+ {
+ struct aafilter *a = (void*)f->pred;
+ if (a->addr.family == AF_UNIX)
+ return unix_match(&s->remote, &a->addr);
+ if (a->port != -1 && a->port != s->rport)
+ return 0;
+ if (a->addr.bitlen) {
+ do {
+ if (!inet2_addr_match(&s->remote, &a->addr, a->addr.bitlen))
+ return 1;
+ } while ((a = a->next) != NULL);
+ return 0;
+ }
+ return 1;
+ }
+ case SSF_SCOND:
+ {
+ struct aafilter *a = (void*)f->pred;
+ if (a->addr.family == AF_UNIX)
+ return unix_match(&s->local, &a->addr);
+ if (a->port != -1 && a->port != s->lport)
+ return 0;
+ if (a->addr.bitlen) {
+ do {
+ if (!inet2_addr_match(&s->local, &a->addr, a->addr.bitlen))
+ return 1;
+ } while ((a = a->next) != NULL);
+ return 0;
+ }
+ return 1;
+ }
+ case SSF_D_GE:
+ {
+ struct aafilter *a = (void*)f->pred;
+ return s->rport >= a->port;
+ }
+ case SSF_D_LE:
+ {
+ struct aafilter *a = (void*)f->pred;
+ return s->rport <= a->port;
+ }
+ case SSF_S_GE:
+ {
+ struct aafilter *a = (void*)f->pred;
+ return s->lport >= a->port;
+ }
+ case SSF_S_LE:
+ {
+ struct aafilter *a = (void*)f->pred;
+ return s->lport <= a->port;
+ }
+
+ /* Yup. It is recursion. Sorry. */
+ case SSF_AND:
+ return run_ssfilter(f->pred, s) && run_ssfilter(f->post, s);
+ case SSF_OR:
+ return run_ssfilter(f->pred, s) || run_ssfilter(f->post, s);
+ case SSF_NOT:
+ return !run_ssfilter(f->pred, s);
+ default:
+ abort();
+ }
+}
+
+/* Relocate external jumps by reloc. */
+static void ssfilter_patch(char *a, int len, int reloc)
+{
+ while (len > 0) {
+ struct inet_diag_bc_op *op = (struct inet_diag_bc_op*)a;
+ if (op->no == len+4)
+ op->no += reloc;
+ len -= op->yes;
+ a += op->yes;
+ }
+ if (len < 0)
+ abort();
+}
+
+static int ssfilter_bytecompile(struct ssfilter *f, char **bytecode)
+{
+ switch (f->type) {
+ case SSF_S_AUTO:
+ {
+ if (!(*bytecode=malloc(4))) abort();
+ ((struct inet_diag_bc_op*)*bytecode)[0] = (struct inet_diag_bc_op){ INET_DIAG_BC_AUTO, 4, 8 };
+ return 4;
+ }
+ case SSF_DCOND:
+ case SSF_SCOND:
+ {
+ struct aafilter *a = (void*)f->pred;
+ struct aafilter *b;
+ char *ptr;
+ int code = (f->type == SSF_DCOND ? INET_DIAG_BC_D_COND : INET_DIAG_BC_S_COND);
+ int len = 0;
+
+ for (b=a; b; b=b->next) {
+ len += 4 + sizeof(struct inet_diag_hostcond);
+ if (a->addr.family == AF_INET6)
+ len += 16;
+ else
+ len += 4;
+ if (b->next)
+ len += 4;
+ }
+ if (!(ptr = malloc(len))) abort();
+ *bytecode = ptr;
+ for (b=a; b; b=b->next) {
+ struct inet_diag_bc_op *op = (struct inet_diag_bc_op *)ptr;
+ int alen = (a->addr.family == AF_INET6 ? 16 : 4);
+ int oplen = alen + 4 + sizeof(struct inet_diag_hostcond);
+ struct inet_diag_hostcond *cond = (struct inet_diag_hostcond*)(ptr+4);
+
+ *op = (struct inet_diag_bc_op){ code, oplen, oplen+4 };
+ cond->family = a->addr.family;
+ cond->port = a->port;
+ cond->prefix_len = a->addr.bitlen;
+ memcpy(cond->addr, a->addr.data, alen);
+ ptr += oplen;
+ if (b->next) {
+ op = (struct inet_diag_bc_op *)ptr;
+ *op = (struct inet_diag_bc_op){ INET_DIAG_BC_JMP, 4, len - (ptr-*bytecode)};
+ ptr += 4;
+ }
+ }
+ return ptr - *bytecode;
+ }
+ case SSF_D_GE:
+ {
+ struct aafilter *x = (void*)f->pred;
+ if (!(*bytecode=malloc(8))) abort();
+ ((struct inet_diag_bc_op*)*bytecode)[0] = (struct inet_diag_bc_op){ INET_DIAG_BC_D_GE, 8, 12 };
+ ((struct inet_diag_bc_op*)*bytecode)[1] = (struct inet_diag_bc_op){ 0, 0, x->port };
+ return 8;
+ }
+ case SSF_D_LE:
+ {
+ struct aafilter *x = (void*)f->pred;
+ if (!(*bytecode=malloc(8))) abort();
+ ((struct inet_diag_bc_op*)*bytecode)[0] = (struct inet_diag_bc_op){ INET_DIAG_BC_D_LE, 8, 12 };
+ ((struct inet_diag_bc_op*)*bytecode)[1] = (struct inet_diag_bc_op){ 0, 0, x->port };
+ return 8;
+ }
+ case SSF_S_GE:
+ {
+ struct aafilter *x = (void*)f->pred;
+ if (!(*bytecode=malloc(8))) abort();
+ ((struct inet_diag_bc_op*)*bytecode)[0] = (struct inet_diag_bc_op){ INET_DIAG_BC_S_GE, 8, 12 };
+ ((struct inet_diag_bc_op*)*bytecode)[1] = (struct inet_diag_bc_op){ 0, 0, x->port };
+ return 8;
+ }
+ case SSF_S_LE:
+ {
+ struct aafilter *x = (void*)f->pred;
+ if (!(*bytecode=malloc(8))) abort();
+ ((struct inet_diag_bc_op*)*bytecode)[0] = (struct inet_diag_bc_op){ INET_DIAG_BC_S_LE, 8, 12 };
+ ((struct inet_diag_bc_op*)*bytecode)[1] = (struct inet_diag_bc_op){ 0, 0, x->port };
+ return 8;
+ }
+
+ case SSF_AND:
+ {
+ char *a1, *a2, *a;
+ int l1, l2;
+ l1 = ssfilter_bytecompile(f->pred, &a1);
+ l2 = ssfilter_bytecompile(f->post, &a2);
+ if (!(a = malloc(l1+l2))) abort();
+ memcpy(a, a1, l1);
+ memcpy(a+l1, a2, l2);
+ free(a1); free(a2);
+ ssfilter_patch(a, l1, l2);
+ *bytecode = a;
+ return l1+l2;
+ }
+ case SSF_OR:
+ {
+ char *a1, *a2, *a;
+ int l1, l2;
+ l1 = ssfilter_bytecompile(f->pred, &a1);
+ l2 = ssfilter_bytecompile(f->post, &a2);
+ if (!(a = malloc(l1+l2+4))) abort();
+ memcpy(a, a1, l1);
+ memcpy(a+l1+4, a2, l2);
+ free(a1); free(a2);
+ *(struct inet_diag_bc_op*)(a+l1) = (struct inet_diag_bc_op){ INET_DIAG_BC_JMP, 4, l2+4 };
+ *bytecode = a;
+ return l1+l2+4;
+ }
+ case SSF_NOT:
+ {
+ char *a1, *a;
+ int l1;
+ l1 = ssfilter_bytecompile(f->pred, &a1);
+ if (!(a = malloc(l1+4))) abort();
+ memcpy(a, a1, l1);
+ free(a1);
+ *(struct inet_diag_bc_op*)(a+l1) = (struct inet_diag_bc_op){ INET_DIAG_BC_JMP, 4, 8 };
+ *bytecode = a;
+ return l1+4;
+ }
+ default:
+ abort();
+ }
+}
+
+static int remember_he(struct aafilter *a, struct hostent *he)
+{
+ char **ptr = he->h_addr_list;
+ int cnt = 0;
+ int len;
+
+ if (he->h_addrtype == AF_INET)
+ len = 4;
+ else if (he->h_addrtype == AF_INET6)
+ len = 16;
+ else
+ return 0;
+
+ while (*ptr) {
+ struct aafilter *b = a;
+ if (a->addr.bitlen) {
+ if ((b = malloc(sizeof(*b))) == NULL)
+ return cnt;
+ *b = *a;
+ b->next = a->next;
+ a->next = b;
+ }
+ memcpy(b->addr.data, *ptr, len);
+ b->addr.bytelen = len;
+ b->addr.bitlen = len*8;
+ b->addr.family = he->h_addrtype;
+ ptr++;
+ cnt++;
+ }
+ return cnt;
+}
+
+static int get_dns_host(struct aafilter *a, const char *addr, int fam)
+{
+ static int notfirst;
+ int cnt = 0;
+ struct hostent *he;
+
+ a->addr.bitlen = 0;
+ if (!notfirst) {
+ sethostent(1);
+ notfirst = 1;
+ }
+ he = gethostbyname2(addr, fam == AF_UNSPEC ? AF_INET : fam);
+ if (he)
+ cnt = remember_he(a, he);
+ if (fam == AF_UNSPEC) {
+ he = gethostbyname2(addr, AF_INET6);
+ if (he)
+ cnt += remember_he(a, he);
+ }
+ return !cnt;
+}
+
+static int xll_initted = 0;
+
+static void xll_init(void)
+{
+ struct rtnl_handle rth;
+ if (rtnl_open(&rth, 0) < 0)
+ exit(1);
+
+ ll_init_map(&rth);
+ rtnl_close(&rth);
+ xll_initted = 1;
+}
+
+static const char *xll_index_to_name(int index)
+{
+ if (!xll_initted)
+ xll_init();
+ return ll_index_to_name(index);
+}
+
+static int xll_name_to_index(const char *dev)
+{
+ if (!xll_initted)
+ xll_init();
+ return ll_name_to_index(dev);
+}
+
+void *parse_hostcond(char *addr, bool is_port)
+{
+ char *port = NULL;
+ struct aafilter a = { .port = -1 };
+ struct aafilter *res;
+ int fam = preferred_family;
+ struct filter *f = ¤t_filter;
+
+ if (fam == AF_UNIX || strncmp(addr, "unix:", 5) == 0) {
+ char *p;
+ a.addr.family = AF_UNIX;
+ if (strncmp(addr, "unix:", 5) == 0)
+ addr+=5;
+ p = strdup(addr);
+ a.addr.bitlen = 8*strlen(p);
+ memcpy(a.addr.data, &p, sizeof(p));
+ fam = AF_UNIX;
+ goto out;
+ }
+
+ if (fam == AF_PACKET || strncmp(addr, "link:", 5) == 0) {
+ a.addr.family = AF_PACKET;
+ a.addr.bitlen = 0;
+ if (strncmp(addr, "link:", 5) == 0)
+ addr+=5;
+ port = strchr(addr, ':');
+ if (port) {
+ *port = 0;
+ if (port[1] && strcmp(port+1, "*")) {
+ if (get_integer(&a.port, port+1, 0)) {
+ if ((a.port = xll_name_to_index(port+1)) <= 0)
+ return NULL;
+ }
+ }
+ }
+ if (addr[0] && strcmp(addr, "*")) {
+ unsigned short tmp;
+ a.addr.bitlen = 32;
+ if (ll_proto_a2n(&tmp, addr))
+ return NULL;
+ a.addr.data[0] = ntohs(tmp);
+ }
+ fam = AF_PACKET;
+ goto out;
+ }
+
+ if (fam == AF_NETLINK || strncmp(addr, "netlink:", 8) == 0) {
+ a.addr.family = AF_NETLINK;
+ a.addr.bitlen = 0;
+ if (strncmp(addr, "netlink:", 8) == 0)
+ addr+=8;
+ port = strchr(addr, ':');
+ if (port) {
+ *port = 0;
+ if (port[1] && strcmp(port+1, "*")) {
+ if (get_integer(&a.port, port+1, 0)) {
+ if (strcmp(port+1, "kernel") == 0)
+ a.port = 0;
+ else
+ return NULL;
+ }
+ }
+ }
+ if (addr[0] && strcmp(addr, "*")) {
+ a.addr.bitlen = 32;
+ if (nl_proto_a2n(&a.addr.data[0], addr) == -1)
+ return NULL;
+ }
+ fam = AF_NETLINK;
+ goto out;
+ }
+
+ if (fam == AF_INET || !strncmp(addr, "inet:", 5)) {
+ fam = AF_INET;
+ if (!strncmp(addr, "inet:", 5))
+ addr += 5;
+ } else if (fam == AF_INET6 || !strncmp(addr, "inet6:", 6)) {
+ fam = AF_INET6;
+ if (!strncmp(addr, "inet6:", 6))
+ addr += 6;
+ }
+
+ /* URL-like literal [] */
+ if (addr[0] == '[') {
+ addr++;
+ if ((port = strchr(addr, ']')) == NULL)
+ return NULL;
+ *port++ = 0;
+ } else if (addr[0] == '*') {
+ port = addr+1;
+ } else {
+ port = strrchr(strchr(addr, '/') ? : addr, ':');
+ }
+
+ if (is_port)
+ port = addr;
+
+ if (port && *port) {
+ if (*port == ':')
+ *port++ = 0;
+
+ if (*port && *port != '*') {
+ if (get_integer(&a.port, port, 0)) {
+ struct servent *se1 = NULL;
+ struct servent *se2 = NULL;
+ if (current_filter.dbs&(1<<UDP_DB))
+ se1 = getservbyname(port, UDP_PROTO);
+ if (current_filter.dbs&(1<<TCP_DB))
+ se2 = getservbyname(port, TCP_PROTO);
+ if (se1 && se2 && se1->s_port != se2->s_port) {
+ fprintf(stderr, "Error: ambiguous port \"%s\".\n", port);
+ return NULL;
+ }
+ if (!se1)
+ se1 = se2;
+ if (se1) {
+ a.port = ntohs(se1->s_port);
+ } else {
+ struct scache *s;
+ for (s = rlist; s; s = s->next) {
+ if ((s->proto == UDP_PROTO &&
+ (current_filter.dbs&(1<<UDP_DB))) ||
+ (s->proto == TCP_PROTO &&
+ (current_filter.dbs&(1<<TCP_DB)))) {
+ if (s->name && strcmp(s->name, port) == 0) {
+ if (a.port > 0 && a.port != s->port) {
+ fprintf(stderr, "Error: ambiguous port \"%s\".\n", port);
+ return NULL;
+ }
+ a.port = s->port;
+ }
+ }
+ }
+ if (a.port <= 0) {
+ fprintf(stderr, "Error: \"%s\" does not look like a port.\n", port);
+ return NULL;
+ }
+ }
+ }
+ }
+ }
+ if (!is_port && addr && *addr && *addr != '*') {
+ if (get_prefix_1(&a.addr, addr, fam)) {
+ if (get_dns_host(&a, addr, fam)) {
+ fprintf(stderr, "Error: an inet prefix is expected rather than \"%s\".\n", addr);
+ return NULL;
+ }
+ }
+ }
+
+out:
+ if (fam != AF_UNSPEC) {
+ f->families = 0;
+ filter_af_set(f, fam);
+ filter_states_set(f, 0);
+ }
+
+ res = malloc(sizeof(*res));
+ if (res)
+ memcpy(res, &a, sizeof(a));
+ return res;
+}
+
+static char *proto_name(int protocol)
+{
+ switch (protocol) {
+ case 0:
+ return "raw";
+ case IPPROTO_UDP:
+ return "udp";
+ case IPPROTO_TCP:
+ return "tcp";
+ case IPPROTO_DCCP:
+ return "dccp";
+ }
+
+ return "???";
+}
+
+static void inet_stats_print(struct sockstat *s, int protocol)
+{
+ char *buf = NULL;
+
+ sock_state_print(s, proto_name(protocol));
+
+ inet_addr_print(&s->local, s->lport, s->iface);
+ inet_addr_print(&s->remote, s->rport, 0);
+
+ if (show_proc_ctx || show_sock_ctx) {
+ if (find_entry(s->ino, &buf,
+ (show_proc_ctx & show_sock_ctx) ?
+ PROC_SOCK_CTX : PROC_CTX) > 0) {
+ printf(" users:(%s)", buf);
+ free(buf);
+ }
+ } else if (show_users) {
+ if (find_entry(s->ino, &buf, USERS) > 0) {
+ printf(" users:(%s)", buf);
+ free(buf);
+ }
+ }
+}
+
+static int proc_parse_inet_addr(char *loc, char *rem, int family, struct
+ sockstat *s)
+{
+ s->local.family = s->remote.family = family;
+ if (family == AF_INET) {
+ sscanf(loc, "%x:%x", s->local.data, (unsigned*)&s->lport);
+ sscanf(rem, "%x:%x", s->remote.data, (unsigned*)&s->rport);
+ s->local.bytelen = s->remote.bytelen = 4;
+ return 0;
+ } else {
+ sscanf(loc, "%08x%08x%08x%08x:%x",
+ s->local.data,
+ s->local.data + 1,
+ s->local.data + 2,
+ s->local.data + 3,
+ &s->lport);
+ sscanf(rem, "%08x%08x%08x%08x:%x",
+ s->remote.data,
+ s->remote.data + 1,
+ s->remote.data + 2,
+ s->remote.data + 3,
+ &s->rport);
+ s->local.bytelen = s->remote.bytelen = 16;
+ return 0;
+ }
+ return -1;
+}
+
+static int proc_inet_split_line(char *line, char **loc, char **rem, char **data)
+{
+ char *p;
+
+ if ((p = strchr(line, ':')) == NULL)
+ return -1;
+
+ *loc = p+2;
+ if ((p = strchr(*loc, ':')) == NULL)
+ return -1;
+
+ p[5] = 0;
+ *rem = p+6;
+ if ((p = strchr(*rem, ':')) == NULL)
+ return -1;
+
+ p[5] = 0;
+ *data = p+6;
+ return 0;
+}
+
+static char *sprint_bw(char *buf, double bw)
+{
+ if (bw > 1000000.)
+ sprintf(buf,"%.1fM", bw / 1000000.);
+ else if (bw > 1000.)
+ sprintf(buf,"%.1fK", bw / 1000.);
+ else
+ sprintf(buf, "%g", bw);
+
+ return buf;
+}
+
+static void tcp_stats_print(struct tcpstat *s)
+{
+ char b1[64];
+
+ if (s->has_ts_opt)
+ printf(" ts");
+ if (s->has_sack_opt)
+ printf(" sack");
+ if (s->has_ecn_opt)
+ printf(" ecn");
+ if (s->has_ecnseen_opt)
+ printf(" ecnseen");
+ if (s->has_fastopen_opt)
+ printf(" fastopen");
+ if (s->cong_alg[0])
+ printf(" %s", s->cong_alg);
+ if (s->has_wscale_opt)
+ printf(" wscale:%d,%d", s->snd_wscale, s->rcv_wscale);
+ if (s->rto)
+ printf(" rto:%g", s->rto);
+ if (s->backoff)
+ printf(" backoff:%u", s->backoff);
+ if (s->rtt)
+ printf(" rtt:%g/%g", s->rtt, s->rttvar);
+ if (s->ato)
+ printf(" ato:%g", s->ato);
+
+ if (s->qack)
+ printf(" qack:%d", s->qack);
+ if (s->qack & 1)
+ printf(" bidir");
+
+ if (s->mss)
+ printf(" mss:%d", s->mss);
+ if (s->cwnd)
+ printf(" cwnd:%d", s->cwnd);
+ if (s->ssthresh)
+ printf(" ssthresh:%d", s->ssthresh);
+
+ if (s->bytes_acked)
+ printf(" bytes_acked:%llu", s->bytes_acked);
+ if (s->bytes_received)
+ printf(" bytes_received:%llu", s->bytes_received);
+ if (s->segs_out)
+ printf(" segs_out:%u", s->segs_out);
+ if (s->segs_in)
+ printf(" segs_in:%u", s->segs_in);
+
+ if (s->dctcp && s->dctcp->enabled) {
+ struct dctcpstat *dctcp = s->dctcp;
+
+ printf(" dctcp:(ce_state:%u,alpha:%u,ab_ecn:%u,ab_tot:%u)",
+ dctcp->ce_state, dctcp->alpha, dctcp->ab_ecn,
+ dctcp->ab_tot);
+ } else if (s->dctcp) {
+ printf(" dctcp:fallback_mode");
+ }
+
+ if (s->send_bps)
+ printf(" send %sbps", sprint_bw(b1, s->send_bps));
+ if (s->lastsnd)
+ printf(" lastsnd:%u", s->lastsnd);
+ if (s->lastrcv)
+ printf(" lastrcv:%u", s->lastrcv);
+ if (s->lastack)
+ printf(" lastack:%u", s->lastack);
+
+ if (s->pacing_rate) {
+ printf(" pacing_rate %sbps", sprint_bw(b1, s->pacing_rate));
+ if (s->pacing_rate_max)
+ printf("/%sbps", sprint_bw(b1,
+ s->pacing_rate_max));
+ }
+
+ if (s->unacked)
+ printf(" unacked:%u", s->unacked);
+ if (s->retrans || s->retrans_total)
+ printf(" retrans:%u/%u", s->retrans, s->retrans_total);
+ if (s->lost)
+ printf(" lost:%u", s->lost);
+ if (s->sacked && s->ss.state != SS_LISTEN)
+ printf(" sacked:%u", s->sacked);
+ if (s->fackets)
+ printf(" fackets:%u", s->fackets);
+ if (s->reordering != 3)
+ printf(" reordering:%d", s->reordering);
+ if (s->rcv_rtt)
+ printf(" rcv_rtt:%g", s->rcv_rtt);
+ if (s->rcv_space)
+ printf(" rcv_space:%d", s->rcv_space);
+}
+
+static void tcp_timer_print(struct tcpstat *s)
+{
+ if (s->timer) {
+ if (s->timer > 4)
+ s->timer = 5;
+ printf(" timer:(%s,%s,%d)",
+ tmr_name[s->timer],
+ print_ms_timer(s->timeout),
+ s->retrans);
+ }
+}
+
+static int tcp_show_line(char *line, const struct filter *f, int family)
+{
+ int rto = 0, ato = 0;
+ struct tcpstat s = {};
+ char *loc, *rem, *data;
+ char opt[256];
+ int n;
+ int hz = get_user_hz();
+
+ if (proc_inet_split_line(line, &loc, &rem, &data))
+ return -1;
+
+ int state = (data[1] >= 'A') ? (data[1] - 'A' + 10) : (data[1] - '0');
+ if (!(f->states & (1 << state)))
+ return 0;
+
+ proc_parse_inet_addr(loc, rem, family, &s.ss);
+
+ if (f->f && run_ssfilter(f->f, &s.ss) == 0)
+ return 0;
+
+ opt[0] = 0;
+ n = sscanf(data, "%x %x:%x %x:%x %x %d %d %u %d %llx %d %d %d %d %d %[^\n]\n",
+ &s.ss.state, &s.ss.wq, &s.ss.rq,
+ &s.timer, &s.timeout, &s.retrans, &s.ss.uid, &s.probes,
+ &s.ss.ino, &s.ss.refcnt, &s.ss.sk, &rto, &ato, &s.qack, &s.cwnd,
+ &s.ssthresh, opt);
+
+ if (n < 17)
+ opt[0] = 0;
+
+ if (n < 12) {
+ rto = 0;
+ s.cwnd = 2;
+ s.ssthresh = -1;
+ ato = s.qack = 0;
+ }
+
+ s.retrans = s.timer != 1 ? s.probes : s.retrans;
+ s.timeout = (s.timeout * 1000 + hz - 1) / hz;
+ s.ato = (double)ato / hz;
+ s.qack /= 2;
+ s.rto = (double)rto;
+ s.ssthresh = s.ssthresh == -1 ? 0 : s.ssthresh;
+ s.rto = s.rto != 3 * hz ? s.rto / hz : 0;
+
+ inet_stats_print(&s.ss, IPPROTO_TCP);
+
+ if (show_options)
+ tcp_timer_print(&s);
+
+ if (show_details) {
+ sock_details_print(&s.ss);
+ if (opt[0])
+ printf(" opt:\"%s\"", opt);
+ }
+
+ if (show_tcpinfo)
+ tcp_stats_print(&s);
+
+ printf("\n");
+ return 0;
+}
+
+static int generic_record_read(FILE *fp,
+ int (*worker)(char*, const struct filter *, int),
+ const struct filter *f, int fam)
+{
+ char line[256];
+
+ /* skip header */
+ if (fgets(line, sizeof(line), fp) == NULL)
+ goto outerr;
+
+ while (fgets(line, sizeof(line), fp) != NULL) {
+ int n = strlen(line);
+ if (n == 0 || line[n-1] != '\n') {
+ errno = -EINVAL;
+ return -1;
+ }
+ line[n-1] = 0;
+
+ if (worker(line, f, fam) < 0)
+ return 0;
+ }
+outerr:
+
+ return ferror(fp) ? -1 : 0;
+}
+
+static void print_skmeminfo(struct rtattr *tb[], int attrtype)
+{
+ const __u32 *skmeminfo;
+
+ if (!tb[attrtype]) {
+ if (attrtype == INET_DIAG_SKMEMINFO) {
+ if (!tb[INET_DIAG_MEMINFO])
+ return;
+
+ const struct inet_diag_meminfo *minfo =
+ RTA_DATA(tb[INET_DIAG_MEMINFO]);
+
+ printf(" mem:(r%u,w%u,f%u,t%u)",
+ minfo->idiag_rmem,
+ minfo->idiag_wmem,
+ minfo->idiag_fmem,
+ minfo->idiag_tmem);
+ }
+ return;
+ }
+
+ skmeminfo = RTA_DATA(tb[attrtype]);
+
+ printf(" skmem:(r%u,rb%u,t%u,tb%u,f%u,w%u,o%u",
+ skmeminfo[SK_MEMINFO_RMEM_ALLOC],
+ skmeminfo[SK_MEMINFO_RCVBUF],
+ skmeminfo[SK_MEMINFO_WMEM_ALLOC],
+ skmeminfo[SK_MEMINFO_SNDBUF],
+ skmeminfo[SK_MEMINFO_FWD_ALLOC],
+ skmeminfo[SK_MEMINFO_WMEM_QUEUED],
+ skmeminfo[SK_MEMINFO_OPTMEM]);
+
+ if (RTA_PAYLOAD(tb[attrtype]) >=
+ (SK_MEMINFO_BACKLOG + 1) * sizeof(__u32))
+ printf(",bl%u", skmeminfo[SK_MEMINFO_BACKLOG]);
+
+ printf(")");
+}
+
+#define TCPI_HAS_OPT(info, opt) !!(info->tcpi_options & (opt))
+
+static void tcp_show_info(const struct nlmsghdr *nlh, struct inet_diag_msg *r,
+ struct rtattr *tb[])
+{
+ double rtt = 0;
+ struct tcpstat s = {};
+
+ s.ss.state = r->idiag_state;
+
+ print_skmeminfo(tb, INET_DIAG_SKMEMINFO);
+
+ if (tb[INET_DIAG_INFO]) {
+ struct tcp_info *info;
+ int len = RTA_PAYLOAD(tb[INET_DIAG_INFO]);
+
+ /* workaround for older kernels with less fields */
+ if (len < sizeof(*info)) {
+ info = alloca(sizeof(*info));
+ memcpy(info, RTA_DATA(tb[INET_DIAG_INFO]), len);
+ memset((char *)info + len, 0, sizeof(*info) - len);
+ } else
+ info = RTA_DATA(tb[INET_DIAG_INFO]);
+
+ if (show_options) {
+ s.has_ts_opt = TCPI_HAS_OPT(info, TCPI_OPT_TIMESTAMPS);
+ s.has_sack_opt = TCPI_HAS_OPT(info, TCPI_OPT_SACK);
+ s.has_ecn_opt = TCPI_HAS_OPT(info, TCPI_OPT_ECN);
+ s.has_ecnseen_opt = TCPI_HAS_OPT(info, TCPI_OPT_ECN_SEEN);
+ s.has_fastopen_opt = TCPI_HAS_OPT(info, TCPI_OPT_SYN_DATA);
+ }
+
+ if (tb[INET_DIAG_CONG])
+ strncpy(s.cong_alg,
+ rta_getattr_str(tb[INET_DIAG_CONG]),
+ sizeof(s.cong_alg) - 1);
+
+ if (TCPI_HAS_OPT(info, TCPI_OPT_WSCALE)) {
+ s.has_wscale_opt = true;
+ s.snd_wscale = info->tcpi_snd_wscale;
+ s.rcv_wscale = info->tcpi_rcv_wscale;
+ }
+
+ if (info->tcpi_rto && info->tcpi_rto != 3000000)
+ s.rto = (double)info->tcpi_rto / 1000;
+
+ s.backoff = info->tcpi_backoff;
+ s.rtt = (double)info->tcpi_rtt / 1000;
+ s.rttvar = (double)info->tcpi_rttvar / 1000;
+ s.ato = (double)info->tcpi_ato / 1000;
+ s.mss = info->tcpi_snd_mss;
+ s.rcv_space = info->tcpi_rcv_space;
+ s.rcv_rtt = (double)info->tcpi_rcv_rtt / 1000;
+ s.lastsnd = info->tcpi_last_data_sent;
+ s.lastrcv = info->tcpi_last_data_recv;
+ s.lastack = info->tcpi_last_ack_recv;
+ s.unacked = info->tcpi_unacked;
+ s.retrans = info->tcpi_retrans;
+ s.retrans_total = info->tcpi_total_retrans;
+ s.lost = info->tcpi_lost;
+ s.sacked = info->tcpi_sacked;
+ s.reordering = info->tcpi_reordering;
+ s.rcv_space = info->tcpi_rcv_space;
+ s.cwnd = info->tcpi_snd_cwnd;
+
+ if (info->tcpi_snd_ssthresh < 0xFFFF)
+ s.ssthresh = info->tcpi_snd_ssthresh;
+
+ rtt = (double) info->tcpi_rtt;
+ if (tb[INET_DIAG_VEGASINFO]) {
+ const struct tcpvegas_info *vinfo
+ = RTA_DATA(tb[INET_DIAG_VEGASINFO]);
+
+ if (vinfo->tcpv_enabled &&
+ vinfo->tcpv_rtt && vinfo->tcpv_rtt != 0x7fffffff)
+ rtt = vinfo->tcpv_rtt;
+ }
+
+ if (tb[INET_DIAG_DCTCPINFO]) {
+ struct dctcpstat *dctcp = malloc(sizeof(struct
+ dctcpstat));
+
+ const struct tcp_dctcp_info *dinfo
+ = RTA_DATA(tb[INET_DIAG_DCTCPINFO]);
+
+ dctcp->enabled = !!dinfo->dctcp_enabled;
+ dctcp->ce_state = dinfo->dctcp_ce_state;
+ dctcp->alpha = dinfo->dctcp_alpha;
+ dctcp->ab_ecn = dinfo->dctcp_ab_ecn;
+ dctcp->ab_tot = dinfo->dctcp_ab_tot;
+ s.dctcp = dctcp;
+ }
+
+ if (rtt > 0 && info->tcpi_snd_mss && info->tcpi_snd_cwnd) {
+ s.send_bps = (double) info->tcpi_snd_cwnd *
+ (double)info->tcpi_snd_mss * 8000000. / rtt;
+ }
+
+ if (info->tcpi_pacing_rate &&
+ info->tcpi_pacing_rate != ~0ULL) {
+ s.pacing_rate = info->tcpi_pacing_rate * 8.;
+
+ if (info->tcpi_max_pacing_rate &&
+ info->tcpi_max_pacing_rate != ~0ULL)
+ s.pacing_rate_max = info->tcpi_max_pacing_rate * 8.;
+ }
+ s.bytes_acked = info->tcpi_bytes_acked;
+ s.bytes_received = info->tcpi_bytes_received;
+ s.segs_out = info->tcpi_segs_out;
+ s.segs_in = info->tcpi_segs_in;
+ tcp_stats_print(&s);
+ free(s.dctcp);
+ }
+}
+
+static int inet_show_sock(struct nlmsghdr *nlh, struct filter *f, int protocol)
+{
+ struct rtattr * tb[INET_DIAG_MAX+1];
+ struct inet_diag_msg *r = NLMSG_DATA(nlh);
+ struct sockstat s = {};
+
+ parse_rtattr(tb, INET_DIAG_MAX, (struct rtattr*)(r+1),
+ nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)));
+
+ s.state = r->idiag_state;
+ s.local.family = s.remote.family = r->idiag_family;
+ s.lport = ntohs(r->id.idiag_sport);
+ s.rport = ntohs(r->id.idiag_dport);
+ s.wq = r->idiag_wqueue;
+ s.rq = r->idiag_rqueue;
+ s.ino = r->idiag_inode;
+ s.uid = r->idiag_uid;
+ s.iface = r->id.idiag_if;
+ s.sk = cookie_sk_get(&r->id.idiag_cookie[0]);
+
+ if (s.local.family == AF_INET) {
+ s.local.bytelen = s.remote.bytelen = 4;
+ } else {
+ s.local.bytelen = s.remote.bytelen = 16;
+ }
+
+ memcpy(s.local.data, r->id.idiag_src, s.local.bytelen);
+ memcpy(s.remote.data, r->id.idiag_dst, s.local.bytelen);
+
+ if (f && f->f && run_ssfilter(f->f, &s) == 0)
+ return 0;
+
+ if (tb[INET_DIAG_PROTOCOL])
+ protocol = *(__u8 *)RTA_DATA(tb[INET_DIAG_PROTOCOL]);
+
+ inet_stats_print(&s, protocol);
+
+ if (show_options) {
+ struct tcpstat t = {};
+
+ t.timer = r->idiag_timer;
+ t.timeout = r->idiag_expires;
+ t.retrans = r->idiag_retrans;
+ tcp_timer_print(&t);
+ }
+
+ if (show_details) {
+ sock_details_print(&s);
+ if (s.local.family == AF_INET6 && tb[INET_DIAG_SKV6ONLY]) {
+ unsigned char v6only;
+ v6only = *(__u8 *)RTA_DATA(tb[INET_DIAG_SKV6ONLY]);
+ printf(" v6only:%u", v6only);
+ }
+ if (tb[INET_DIAG_SHUTDOWN]) {
+ unsigned char mask;
+ mask = *(__u8 *)RTA_DATA(tb[INET_DIAG_SHUTDOWN]);
+ printf(" %c-%c", mask & 1 ? '-' : '<', mask & 2 ? '-' : '>');
+ }
+ }
+
+ if (show_mem || show_tcpinfo) {
+ printf("\n\t");
+ tcp_show_info(nlh, r, tb);
+ }
+
+ printf("\n");
+ return 0;
+}
+
+static int tcpdiag_send(int fd, int protocol, struct filter *f)
+{
+ struct sockaddr_nl nladdr;
+ struct {
+ struct nlmsghdr nlh;
+ struct inet_diag_req r;
+ } req;
+ char *bc = NULL;
+ int bclen;
+ struct msghdr msg;
+ struct rtattr rta;
+ struct iovec iov[3];
+
+ if (protocol == IPPROTO_UDP)
+ return -1;
+
+ memset(&nladdr, 0, sizeof(nladdr));
+ nladdr.nl_family = AF_NETLINK;
+
+ req.nlh.nlmsg_len = sizeof(req);
+ if (protocol == IPPROTO_TCP)
+ req.nlh.nlmsg_type = TCPDIAG_GETSOCK;
+ else
+ req.nlh.nlmsg_type = DCCPDIAG_GETSOCK;
+ req.nlh.nlmsg_flags = NLM_F_ROOT|NLM_F_MATCH|NLM_F_REQUEST;
+ req.nlh.nlmsg_pid = 0;
+ req.nlh.nlmsg_seq = MAGIC_SEQ;
+ memset(&req.r, 0, sizeof(req.r));
+ req.r.idiag_family = AF_INET;
+ req.r.idiag_states = f->states;
+ if (show_mem) {
+ req.r.idiag_ext |= (1<<(INET_DIAG_MEMINFO-1));
+ req.r.idiag_ext |= (1<<(INET_DIAG_SKMEMINFO-1));
+ }
+
+ if (show_tcpinfo) {
+ req.r.idiag_ext |= (1<<(INET_DIAG_INFO-1));
+ req.r.idiag_ext |= (1<<(INET_DIAG_VEGASINFO-1));
+ req.r.idiag_ext |= (1<<(INET_DIAG_CONG-1));
+ }
+
+ iov[0] = (struct iovec){
+ .iov_base = &req,
+ .iov_len = sizeof(req)
+ };
+ if (f->f) {
+ bclen = ssfilter_bytecompile(f->f, &bc);
+ rta.rta_type = INET_DIAG_REQ_BYTECODE;
+ rta.rta_len = RTA_LENGTH(bclen);
+ iov[1] = (struct iovec){ &rta, sizeof(rta) };
+ iov[2] = (struct iovec){ bc, bclen };
+ req.nlh.nlmsg_len += RTA_LENGTH(bclen);
+ }
+
+ msg = (struct msghdr) {
+ .msg_name = (void*)&nladdr,
+ .msg_namelen = sizeof(nladdr),
+ .msg_iov = iov,
+ .msg_iovlen = f->f ? 3 : 1,
+ };
+
+ if (sendmsg(fd, &msg, 0) < 0) {
+ close(fd);
+ return -1;
+ }
+
+ return 0;
+}
+
+static int sockdiag_send(int family, int fd, int protocol, struct filter *f)
+{
+ struct sockaddr_nl nladdr;
+ DIAG_REQUEST(req, struct inet_diag_req_v2 r);
+ char *bc = NULL;
+ int bclen;
+ struct msghdr msg;
+ struct rtattr rta;
+ struct iovec iov[3];
+
+ if (family == PF_UNSPEC)
+ return tcpdiag_send(fd, protocol, f);
+
+ memset(&nladdr, 0, sizeof(nladdr));
+ nladdr.nl_family = AF_NETLINK;
+
+ memset(&req.r, 0, sizeof(req.r));
+ req.r.sdiag_family = family;
+ req.r.sdiag_protocol = protocol;
+ req.r.idiag_states = f->states;
+ if (show_mem) {
+ req.r.idiag_ext |= (1<<(INET_DIAG_MEMINFO-1));
+ req.r.idiag_ext |= (1<<(INET_DIAG_SKMEMINFO-1));
+ }
+
+ if (show_tcpinfo) {
+ req.r.idiag_ext |= (1<<(INET_DIAG_INFO-1));
+ req.r.idiag_ext |= (1<<(INET_DIAG_VEGASINFO-1));
+ req.r.idiag_ext |= (1<<(INET_DIAG_CONG-1));
+ }
+
+ iov[0] = (struct iovec){
+ .iov_base = &req,
+ .iov_len = sizeof(req)
+ };
+ if (f->f) {
+ bclen = ssfilter_bytecompile(f->f, &bc);
+ rta.rta_type = INET_DIAG_REQ_BYTECODE;
+ rta.rta_len = RTA_LENGTH(bclen);
+ iov[1] = (struct iovec){ &rta, sizeof(rta) };
+ iov[2] = (struct iovec){ bc, bclen };
+ req.nlh.nlmsg_len += RTA_LENGTH(bclen);
+ }
+
+ msg = (struct msghdr) {
+ .msg_name = (void*)&nladdr,
+ .msg_namelen = sizeof(nladdr),
+ .msg_iov = iov,
+ .msg_iovlen = f->f ? 3 : 1,
+ };
+
+ if (sendmsg(fd, &msg, 0) < 0) {
+ close(fd);
+ return -1;
+ }
+
+ return 0;
+}
+
+struct inet_diag_arg {
+ struct filter *f;
+ int protocol;
+ struct rtnl_handle *rth;
+};
+
+static int kill_inet_sock(const struct sockaddr_nl *addr,
+ struct nlmsghdr *h, void *arg)
+{
+ struct inet_diag_msg *d = NLMSG_DATA(h);
+ struct inet_diag_arg *diag_arg = arg;
+ struct rtnl_handle *rth = diag_arg->rth;
+ DIAG_REQUEST(req, struct inet_diag_req_v2 r);
+
+ req.nlh.nlmsg_type = SOCK_DESTROY;
+ req.nlh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+ req.nlh.nlmsg_seq = ++rth->seq;
+ req.r.sdiag_family = d->idiag_family;
+ req.r.sdiag_protocol = diag_arg->protocol;
+ req.r.id = d->id;
+
+ return rtnl_talk(rth, &req.nlh, NULL, 0);
+}
+
+static int show_one_inet_sock(const struct sockaddr_nl *addr,
+ struct nlmsghdr *h, void *arg)
+{
+ int err;
+ struct inet_diag_arg *diag_arg = arg;
+ struct inet_diag_msg *r = NLMSG_DATA(h);
+
+ if (!(diag_arg->f->families & (1 << r->idiag_family)))
+ return 0;
+ if (diag_arg->f->kill && kill_inet_sock(addr, h, arg) != 0) {
+ if (errno == EOPNOTSUPP || errno == ENOENT) {
+ /* Socket can't be closed, or is already closed. */
+ return 0;
+ } else {
+ perror("SOCK_DESTROY answers");
+ return -1;
+ }
+ }
+ if ((err = inet_show_sock(h, diag_arg->f, diag_arg->protocol)) < 0)
+ return err;
+
+ return 0;
+}
+
+static int inet_show_netlink(struct filter *f, FILE *dump_fp, int protocol)
+{
+ int err = 0;
+ struct rtnl_handle rth, rth2;
+ int family = PF_INET;
+ struct inet_diag_arg arg = { .f = f, .protocol = protocol };
+
+ if (rtnl_open_byproto(&rth, 0, NETLINK_SOCK_DIAG))
+ return -1;
+
+ if (f->kill) {
+ if (rtnl_open_byproto(&rth2, 0, NETLINK_SOCK_DIAG)) {
+ rtnl_close(&rth);
+ return -1;
+ }
+ arg.rth = &rth2;
+ }
+
+ rth.dump = MAGIC_SEQ;
+ rth.dump_fp = dump_fp;
+ if (preferred_family == PF_INET6)
+ family = PF_INET6;
+
+again:
+ if ((err = sockdiag_send(family, rth.fd, protocol, f)))
+ goto Exit;
+
+ if ((err = rtnl_dump_filter(&rth, show_one_inet_sock, &arg))) {
+ if (family != PF_UNSPEC) {
+ family = PF_UNSPEC;
+ goto again;
+ }
+ goto Exit;
+ }
+ if (family == PF_INET && preferred_family != PF_INET) {
+ family = PF_INET6;
+ goto again;
+ }
+
+Exit:
+ rtnl_close(&rth);
+ if (arg.rth)
+ rtnl_close(arg.rth);
+ return err;
+}
+
+static int tcp_show_netlink_file(struct filter *f)
+{
+ FILE *fp;
+ char buf[16384];
+
+ if ((fp = fopen(getenv("TCPDIAG_FILE"), "r")) == NULL) {
+ perror("fopen($TCPDIAG_FILE)");
+ return -1;
+ }
+
+ while (1) {
+ int status, err;
+ struct nlmsghdr *h = (struct nlmsghdr*)buf;
+
+ status = fread(buf, 1, sizeof(*h), fp);
+ if (status < 0) {
+ perror("Reading header from $TCPDIAG_FILE");
+ return -1;
+ }
+ if (status != sizeof(*h)) {
+ perror("Unexpected EOF reading $TCPDIAG_FILE");
+ return -1;
+ }
+
+ status = fread(h+1, 1, NLMSG_ALIGN(h->nlmsg_len-sizeof(*h)), fp);
+
+ if (status < 0) {
+ perror("Reading $TCPDIAG_FILE");
+ return -1;
+ }
+ if (status + sizeof(*h) < h->nlmsg_len) {
+ perror("Unexpected EOF reading $TCPDIAG_FILE");
+ return -1;
+ }
+
+ /* The only legal exit point */
+ if (h->nlmsg_type == NLMSG_DONE)
+ return 0;
+
+ if (h->nlmsg_type == NLMSG_ERROR) {
+ struct nlmsgerr *err = (struct nlmsgerr*)NLMSG_DATA(h);
+ if (h->nlmsg_len < NLMSG_LENGTH(sizeof(struct nlmsgerr))) {
+ fprintf(stderr, "ERROR truncated\n");
+ } else {
+ errno = -err->error;
+ perror("TCPDIAG answered");
+ }
+ return -1;
+ }
+
+ err = inet_show_sock(h, f, IPPROTO_TCP);
+ if (err < 0)
+ return err;
+ }
+}
+
+static int tcp_show(struct filter *f, int socktype)
+{
+ FILE *fp = NULL;
+ char *buf = NULL;
+ int bufsize = 64*1024;
+
+ if (!filter_af_get(f, AF_INET) && !filter_af_get(f, AF_INET6))
+ return 0;
+
+ dg_proto = TCP_PROTO;
+
+ if (getenv("TCPDIAG_FILE"))
+ return tcp_show_netlink_file(f);
+
+ if (!getenv("PROC_NET_TCP") && !getenv("PROC_ROOT")
+ && inet_show_netlink(f, NULL, socktype) == 0)
+ return 0;
+
+ /* Sigh... We have to parse /proc/net/tcp... */
+
+
+ /* Estimate amount of sockets and try to allocate
+ * huge buffer to read all the table at one read.
+ * Limit it by 16MB though. The assumption is: as soon as
+ * kernel was able to hold information about N connections,
+ * it is able to give us some memory for snapshot.
+ */
+ if (1) {
+ get_slabstat(&slabstat);
+
+ int guess = slabstat.socks+slabstat.tcp_syns;
+ if (f->states&(1<<SS_TIME_WAIT))
+ guess += slabstat.tcp_tws;
+ if (guess > (16*1024*1024)/128)
+ guess = (16*1024*1024)/128;
+ guess *= 128;
+ if (guess > bufsize)
+ bufsize = guess;
+ }
+ while (bufsize >= 64*1024) {
+ if ((buf = malloc(bufsize)) != NULL)
+ break;
+ bufsize /= 2;
+ }
+ if (buf == NULL) {
+ errno = ENOMEM;
+ return -1;
+ }
+
+ if (f->families & (1<<AF_INET)) {
+ if ((fp = net_tcp_open()) == NULL)
+ goto outerr;
+
+ setbuffer(fp, buf, bufsize);
+ if (generic_record_read(fp, tcp_show_line, f, AF_INET))
+ goto outerr;
+ fclose(fp);
+ }
+
+ if ((f->families & (1<<AF_INET6)) &&
+ (fp = net_tcp6_open()) != NULL) {
+ setbuffer(fp, buf, bufsize);
+ if (generic_record_read(fp, tcp_show_line, f, AF_INET6))
+ goto outerr;
+ fclose(fp);
+ }
+
+ free(buf);
+ return 0;
+
+outerr:
+ do {
+ int saved_errno = errno;
+ free(buf);
+ if (fp)
+ fclose(fp);
+ errno = saved_errno;
+ return -1;
+ } while (0);
+}
+
+
+static int dgram_show_line(char *line, const struct filter *f, int family)
+{
+ struct sockstat s = {};
+ char *loc, *rem, *data;
+ char opt[256];
+ int n;
+
+ if (proc_inet_split_line(line, &loc, &rem, &data))
+ return -1;
+
+ int state = (data[1] >= 'A') ? (data[1] - 'A' + 10) : (data[1] - '0');
+ if (!(f->states & (1 << state)))
+ return 0;
+
+ proc_parse_inet_addr(loc, rem, family, &s);
+
+ if (f->f && run_ssfilter(f->f, &s) == 0)
+ return 0;
+
+ opt[0] = 0;
+ n = sscanf(data, "%x %x:%x %*x:%*x %*x %d %*d %u %d %llx %[^\n]\n",
+ &s.state, &s.wq, &s.rq,
+ &s.uid, &s.ino,
+ &s.refcnt, &s.sk, opt);
+
+ if (n < 9)
+ opt[0] = 0;
+
+ inet_stats_print(&s, dg_proto == UDP_PROTO ? IPPROTO_UDP : 0);
+
+ if (show_details && opt[0])
+ printf(" opt:\"%s\"", opt);
+
+ printf("\n");
+ return 0;
+}
+
+static int udp_show(struct filter *f)
+{
+ FILE *fp = NULL;
+
+ if (!filter_af_get(f, AF_INET) && !filter_af_get(f, AF_INET6))
+ return 0;
+
+ dg_proto = UDP_PROTO;
+
+ if (!getenv("PROC_NET_UDP") && !getenv("PROC_ROOT")
+ && inet_show_netlink(f, NULL, IPPROTO_UDP) == 0)
+ return 0;
+
+ if (f->families&(1<<AF_INET)) {
+ if ((fp = net_udp_open()) == NULL)
+ goto outerr;
+ if (generic_record_read(fp, dgram_show_line, f, AF_INET))
+ goto outerr;
+ fclose(fp);
+ }
+
+ if ((f->families&(1<<AF_INET6)) &&
+ (fp = net_udp6_open()) != NULL) {
+ if (generic_record_read(fp, dgram_show_line, f, AF_INET6))
+ goto outerr;
+ fclose(fp);
+ }
+ return 0;
+
+outerr:
+ do {
+ int saved_errno = errno;
+ if (fp)
+ fclose(fp);
+ errno = saved_errno;
+ return -1;
+ } while (0);
+}
+
+static int raw_show(struct filter *f)
+{
+ FILE *fp = NULL;
+
+ if (!filter_af_get(f, AF_INET) && !filter_af_get(f, AF_INET6))
+ return 0;
+
+ dg_proto = RAW_PROTO;
+
+ if (f->families&(1<<AF_INET)) {
+ if ((fp = net_raw_open()) == NULL)
+ goto outerr;
+ if (generic_record_read(fp, dgram_show_line, f, AF_INET))
+ goto outerr;
+ fclose(fp);
+ }
+
+ if ((f->families&(1<<AF_INET6)) &&
+ (fp = net_raw6_open()) != NULL) {
+ if (generic_record_read(fp, dgram_show_line, f, AF_INET6))
+ goto outerr;
+ fclose(fp);
+ }
+ return 0;
+
+outerr:
+ do {
+ int saved_errno = errno;
+ if (fp)
+ fclose(fp);
+ errno = saved_errno;
+ return -1;
+ } while (0);
+}
+
+int unix_state_map[] = { SS_CLOSE, SS_SYN_SENT,
+ SS_ESTABLISHED, SS_CLOSING };
+
+#define MAX_UNIX_REMEMBER (1024*1024/sizeof(struct sockstat))
+
+static void unix_list_free(struct sockstat *list)
+{
+ while (list) {
+ struct sockstat *s = list;
+
+ list = list->next;
+ free(s->name);
+ free(s);
+ }
+}
+
+static const char *unix_netid_name(int type)
+{
+ const char *netid;
+
+ switch (type) {
+ case SOCK_STREAM:
+ netid = "u_str";
+ break;
+ case SOCK_SEQPACKET:
+ netid = "u_seq";
+ break;
+ case SOCK_DGRAM:
+ default:
+ netid = "u_dgr";
+ break;
+ }
+ return netid;
+}
+
+static bool unix_type_skip(struct sockstat *s, struct filter *f)
+{
+ if (s->type == SOCK_STREAM && !(f->dbs&(1<<UNIX_ST_DB)))
+ return true;
+ if (s->type == SOCK_DGRAM && !(f->dbs&(1<<UNIX_DG_DB)))
+ return true;
+ if (s->type == SOCK_SEQPACKET && !(f->dbs&(1<<UNIX_SQ_DB)))
+ return true;
+ return false;
+}
+
+static bool unix_use_proc(void)
+{
+ return getenv("PROC_NET_UNIX") || getenv("PROC_ROOT");
+}
+
+static void unix_stats_print(struct sockstat *list, struct filter *f)
+{
+ struct sockstat *s;
+ char *peer;
+ char *ctx_buf = NULL;
+ bool use_proc = unix_use_proc();
+ char port_name[30] = {};
+
+ for (s = list; s; s = s->next) {
+ if (!(f->states & (1 << s->state)))
+ continue;
+ if (unix_type_skip(s, f))
+ continue;
+
+ peer = "*";
+ if (s->peer_name)
+ peer = s->peer_name;
+
+ if (s->rport && use_proc) {
+ struct sockstat *p;
+
+ for (p = list; p; p = p->next) {
+ if (s->rport == p->lport)
+ break;
+ }
+
+ if (!p) {
+ peer = "?";
+ } else {
+ peer = p->name ? : "*";
+ }
+ }
+
+ if (use_proc && f->f) {
+ struct sockstat st;
+ st.local.family = AF_UNIX;
+ st.remote.family = AF_UNIX;
+ memcpy(st.local.data, &s->name, sizeof(s->name));
+ if (strcmp(peer, "*") == 0)
+ memset(st.remote.data, 0, sizeof(peer));
+ else
+ memcpy(st.remote.data, &peer, sizeof(peer));
+ if (run_ssfilter(f->f, &st) == 0)
+ continue;
+ }
+
+ sock_state_print(s, unix_netid_name(s->type));
+
+ sock_addr_print(s->name ?: "*", " ",
+ int_to_str(s->lport, port_name), NULL);
+ sock_addr_print(peer, " ", int_to_str(s->rport, port_name),
+ NULL);
+
+ if (show_proc_ctx || show_sock_ctx) {
+ if (find_entry(s->ino, &ctx_buf,
+ (show_proc_ctx & show_sock_ctx) ?
+ PROC_SOCK_CTX : PROC_CTX) > 0) {
+ printf(" users:(%s)", ctx_buf);
+ free(ctx_buf);
+ }
+ } else if (show_users) {
+ if (find_entry(s->ino, &ctx_buf, USERS) > 0) {
+ printf(" users:(%s)", ctx_buf);
+ free(ctx_buf);
+ }
+ }
+ printf("\n");
+ }
+}
+
+static int unix_show_sock(const struct sockaddr_nl *addr, struct nlmsghdr *nlh,
+ void *arg)
+{
+ struct filter *f = (struct filter *)arg;
+ struct unix_diag_msg *r = NLMSG_DATA(nlh);
+ struct rtattr *tb[UNIX_DIAG_MAX+1];
+ char name[128];
+ struct sockstat stat = { .name = "*", .peer_name = "*" };
+
+ parse_rtattr(tb, UNIX_DIAG_MAX, (struct rtattr*)(r+1),
+ nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)));
+
+ stat.type = r->udiag_type;
+ stat.state = r->udiag_state;
+ stat.ino = stat.lport = r->udiag_ino;
+ stat.local.family = stat.remote.family = AF_UNIX;
+
+ if (unix_type_skip(&stat, f))
+ return 0;
+
+ if (tb[UNIX_DIAG_RQLEN]) {
+ struct unix_diag_rqlen *rql = RTA_DATA(tb[UNIX_DIAG_RQLEN]);
+ stat.rq = rql->udiag_rqueue;
+ stat.wq = rql->udiag_wqueue;
+ }
+ if (tb[UNIX_DIAG_NAME]) {
+ int len = RTA_PAYLOAD(tb[UNIX_DIAG_NAME]);
+
+ memcpy(name, RTA_DATA(tb[UNIX_DIAG_NAME]), len);
+ name[len] = '\0';
+ if (name[0] == '\0')
+ name[0] = '@';
+ stat.name = &name[0];
+ memcpy(stat.local.data, &stat.name, sizeof(stat.name));
+ }
+ if (tb[UNIX_DIAG_PEER])
+ stat.rport = rta_getattr_u32(tb[UNIX_DIAG_PEER]);
+
+ if (f->f && run_ssfilter(f->f, &stat) == 0)
+ return 0;
+
+ unix_stats_print(&stat, f);
+
+ if (show_mem) {
+ printf("\t");
+ print_skmeminfo(tb, UNIX_DIAG_MEMINFO);
+ }
+ if (show_details) {
+ if (tb[UNIX_DIAG_SHUTDOWN]) {
+ unsigned char mask;
+ mask = *(__u8 *)RTA_DATA(tb[UNIX_DIAG_SHUTDOWN]);
+ printf(" %c-%c", mask & 1 ? '-' : '<', mask & 2 ? '-' : '>');
+ }
+ }
+ if (show_mem || show_details)
+ printf("\n");
+
+ return 0;
+}
+
+static int handle_netlink_request(struct filter *f, struct nlmsghdr *req,
+ size_t size, rtnl_filter_t show_one_sock)
+{
+ int ret = -1;
+ struct rtnl_handle rth;
+
+ if (rtnl_open_byproto(&rth, 0, NETLINK_SOCK_DIAG))
+ return -1;
+
+ rth.dump = MAGIC_SEQ;
+
+ if (rtnl_send(&rth, req, size) < 0)
+ goto Exit;
+
+ if (rtnl_dump_filter(&rth, show_one_sock, f))
+ goto Exit;
+
+ ret = 0;
+Exit:
+ rtnl_close(&rth);
+ return ret;
+}
+
+static int unix_show_netlink(struct filter *f)
+{
+ DIAG_REQUEST(req, struct unix_diag_req r);
+
+ req.r.sdiag_family = AF_UNIX;
+ req.r.udiag_states = f->states;
+ req.r.udiag_show = UDIAG_SHOW_NAME | UDIAG_SHOW_PEER | UDIAG_SHOW_RQLEN;
+ if (show_mem)
+ req.r.udiag_show |= UDIAG_SHOW_MEMINFO;
+
+ return handle_netlink_request(f, &req.nlh, sizeof(req), unix_show_sock);
+}
+
+static int unix_show(struct filter *f)
+{
+ FILE *fp;
+ char buf[256];
+ char name[128];
+ int newformat = 0;
+ int cnt;
+ struct sockstat *list = NULL;
+
+ if (!filter_af_get(f, AF_UNIX))
+ return 0;
+
+ if (!unix_use_proc() && unix_show_netlink(f) == 0)
+ return 0;
+
+ if ((fp = net_unix_open()) == NULL)
+ return -1;
+ if (!fgets(buf, sizeof(buf), fp)) {
+ fclose(fp);
+ return -1;
+ }
+
+ if (memcmp(buf, "Peer", 4) == 0)
+ newformat = 1;
+ cnt = 0;
+
+ while (fgets(buf, sizeof(buf), fp)) {
+ struct sockstat *u, **insp;
+ int flags;
+
+ if (!(u = calloc(1, sizeof(*u))))
+ break;
+ u->name = NULL;
+ u->peer_name = NULL;
+
+ if (sscanf(buf, "%x: %x %x %x %x %x %d %s",
+ &u->rport, &u->rq, &u->wq, &flags, &u->type,
+ &u->state, &u->ino, name) < 8)
+ name[0] = 0;
+
+ u->lport = u->ino;
+ u->local.family = u->remote.family = AF_UNIX;
+
+ if (flags & (1 << 16)) {
+ u->state = SS_LISTEN;
+ } else {
+ u->state = unix_state_map[u->state-1];
+ if (u->type == SOCK_DGRAM && u->state == SS_CLOSE && u->rport)
+ u->state = SS_ESTABLISHED;
+ }
+
+ if (!newformat) {
+ u->rport = 0;
+ u->rq = 0;
+ u->wq = 0;
+ }
+
+ insp = &list;
+ while (*insp) {
+ if (u->type < (*insp)->type ||
+ (u->type == (*insp)->type &&
+ u->ino < (*insp)->ino))
+ break;
+ insp = &(*insp)->next;
+ }
+ u->next = *insp;
+ *insp = u;
+
+ if (name[0]) {
+ if ((u->name = malloc(strlen(name)+1)) == NULL)
+ break;
+ strcpy(u->name, name);
+ }
+ if (++cnt > MAX_UNIX_REMEMBER) {
+ unix_stats_print(list, f);
+ unix_list_free(list);
+ list = NULL;
+ cnt = 0;
+ }
+ }
+ fclose(fp);
+ if (list) {
+ unix_stats_print(list, f);
+ unix_list_free(list);
+ list = NULL;
+ cnt = 0;
+ }
+
+ return 0;
+}
+
+static int packet_stats_print(struct sockstat *s, const struct filter *f)
+{
+ char *buf = NULL;
+ const char *addr, *port;
+ char ll_name[16];
+
+ if (f->f) {
+ s->local.family = AF_PACKET;
+ s->remote.family = AF_PACKET;
+ s->local.data[0] = s->prot;
+ if (run_ssfilter(f->f, s) == 0)
+ return 1;
+ }
+
+ sock_state_print(s, s->type == SOCK_RAW ? "p_raw" : "p_dgr");
+
+ if (s->prot == 3)
+ addr = "*";
+ else
+ addr = ll_proto_n2a(htons(s->prot), ll_name, sizeof(ll_name));
+
+ if (s->iface == 0)
+ port = "*";
+ else
+ port = xll_index_to_name(s->iface);
+
+ sock_addr_print(addr, ":", port, NULL);
+ sock_addr_print("", "*", "", NULL);
+
+ if (show_proc_ctx || show_sock_ctx) {
+ if (find_entry(s->ino, &buf,
+ (show_proc_ctx & show_sock_ctx) ?
+ PROC_SOCK_CTX : PROC_CTX) > 0) {
+ printf(" users:(%s)", buf);
+ free(buf);
+ }
+ } else if (show_users) {
+ if (find_entry(s->ino, &buf, USERS) > 0) {
+ printf(" users:(%s)", buf);
+ free(buf);
+ }
+ }
+
+ if (show_details)
+ sock_details_print(s);
+
+ return 0;
+}
+
+static void packet_show_ring(struct packet_diag_ring *ring)
+{
+ printf("blk_size:%d", ring->pdr_block_size);
+ printf(",blk_nr:%d", ring->pdr_block_nr);
+ printf(",frm_size:%d", ring->pdr_frame_size);
+ printf(",frm_nr:%d", ring->pdr_frame_nr);
+ printf(",tmo:%d", ring->pdr_retire_tmo);
+ printf(",features:0x%x", ring->pdr_features);
+}
+
+static int packet_show_sock(const struct sockaddr_nl *addr,
+ struct nlmsghdr *nlh, void *arg)
+{
+ const struct filter *f = arg;
+ struct packet_diag_msg *r = NLMSG_DATA(nlh);
+ struct packet_diag_info *pinfo = NULL;
+ struct packet_diag_ring *ring_rx = NULL, *ring_tx = NULL;
+ struct rtattr *tb[PACKET_DIAG_MAX+1];
+ struct sockstat stat = {};
+ uint32_t fanout = 0;
+ bool has_fanout = false;
+
+ parse_rtattr(tb, PACKET_DIAG_MAX, (struct rtattr*)(r+1),
+ nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)));
+
+ /* use /proc/net/packet if all info are not available */
+ if (!tb[PACKET_DIAG_MEMINFO])
+ return -1;
+
+ stat.type = r->pdiag_type;
+ stat.prot = r->pdiag_num;
+ stat.ino = r->pdiag_ino;
+ stat.state = SS_CLOSE;
+ stat.sk = cookie_sk_get(&r->pdiag_cookie[0]);
+
+ if (tb[PACKET_DIAG_MEMINFO]) {
+ __u32 *skmeminfo = RTA_DATA(tb[PACKET_DIAG_MEMINFO]);
+ stat.rq = skmeminfo[SK_MEMINFO_RMEM_ALLOC];
+ }
+
+ if (tb[PACKET_DIAG_INFO]) {
+ pinfo = RTA_DATA(tb[PACKET_DIAG_INFO]);
+ stat.lport = stat.iface = pinfo->pdi_index;
+ }
+
+ if (tb[PACKET_DIAG_UID])
+ stat.uid = *(__u32 *)RTA_DATA(tb[PACKET_DIAG_UID]);
+
+ if (tb[PACKET_DIAG_RX_RING])
+ ring_rx = RTA_DATA(tb[PACKET_DIAG_RX_RING]);
+
+ if (tb[PACKET_DIAG_TX_RING])
+ ring_tx = RTA_DATA(tb[PACKET_DIAG_TX_RING]);
+
+ if (tb[PACKET_DIAG_FANOUT]) {
+ has_fanout = true;
+ fanout = *(uint32_t *)RTA_DATA(tb[PACKET_DIAG_FANOUT]);
+ }
+
+ if (packet_stats_print(&stat, f))
+ return 0;
+
+ if (show_details) {
+ if (pinfo) {
+ printf("\n\tver:%d", pinfo->pdi_version);
+ printf(" cpy_thresh:%d", pinfo->pdi_copy_thresh);
+ printf(" flags( ");
+ if (pinfo->pdi_flags & PDI_RUNNING)
+ printf("running");
+ if (pinfo->pdi_flags & PDI_AUXDATA)
+ printf(" auxdata");
+ if (pinfo->pdi_flags & PDI_ORIGDEV)
+ printf(" origdev");
+ if (pinfo->pdi_flags & PDI_VNETHDR)
+ printf(" vnethdr");
+ if (pinfo->pdi_flags & PDI_LOSS)
+ printf(" loss");
+ if (!pinfo->pdi_flags)
+ printf("0");
+ printf(" )");
+ }
+ if (ring_rx) {
+ printf("\n\tring_rx(");
+ packet_show_ring(ring_rx);
+ printf(")");
+ }
+ if (ring_tx) {
+ printf("\n\tring_tx(");
+ packet_show_ring(ring_tx);
+ printf(")");
+ }
+ if (has_fanout) {
+ uint16_t type = (fanout >> 16) & 0xffff;
+
+ printf("\n\tfanout(");
+ printf("id:%d,", fanout & 0xffff);
+ printf("type:");
+
+ if (type == 0)
+ printf("hash");
+ else if (type == 1)
+ printf("lb");
+ else if (type == 2)
+ printf("cpu");
+ else if (type == 3)
+ printf("roll");
+ else if (type == 4)
+ printf("random");
+ else if (type == 5)
+ printf("qm");
+ else
+ printf("0x%x", type);
+
+ printf(")");
+ }
+ }
+
+ if (show_bpf && tb[PACKET_DIAG_FILTER]) {
+ struct sock_filter *fil =
+ RTA_DATA(tb[PACKET_DIAG_FILTER]);
+ int num = RTA_PAYLOAD(tb[PACKET_DIAG_FILTER]) /
+ sizeof(struct sock_filter);
+
+ printf("\n\tbpf filter (%d): ", num);
+ while (num) {
+ printf(" 0x%02x %u %u %u,",
+ fil->code, fil->jt, fil->jf, fil->k);
+ num--;
+ fil++;
+ }
+ }
+ printf("\n");
+ return 0;
+}
+
+static int packet_show_netlink(struct filter *f)
+{
+ DIAG_REQUEST(req, struct packet_diag_req r);
+
+ req.r.sdiag_family = AF_PACKET;
+ req.r.pdiag_show = PACKET_SHOW_INFO | PACKET_SHOW_MEMINFO |
+ PACKET_SHOW_FILTER | PACKET_SHOW_RING_CFG | PACKET_SHOW_FANOUT;
+
+ return handle_netlink_request(f, &req.nlh, sizeof(req), packet_show_sock);
+}
+
+static int packet_show_line(char *buf, const struct filter *f, int fam)
+{
+ unsigned long long sk;
+ struct sockstat stat = {};
+ int type, prot, iface, state, rq, uid, ino;
+
+ sscanf(buf, "%llx %*d %d %x %d %d %u %u %u",
+ &sk,
+ &type, &prot, &iface, &state,
+ &rq, &uid, &ino);
+
+ if (stat.type == SOCK_RAW && !(f->dbs&(1<<PACKET_R_DB)))
+ return 0;
+ if (stat.type == SOCK_DGRAM && !(f->dbs&(1<<PACKET_DG_DB)))
+ return 0;
+
+ stat.type = type;
+ stat.prot = prot;
+ stat.lport = stat.iface = iface;
+ stat.state = state;
+ stat.rq = rq;
+ stat.uid = uid;
+ stat.ino = ino;
+ stat.state = SS_CLOSE;
+
+ if (packet_stats_print(&stat, f))
+ return 0;
+
+ printf("\n");
+ return 0;
+}
+
+static int packet_show(struct filter *f)
+{
+ FILE *fp;
+ int rc = 0;
+
+ if (!filter_af_get(f, AF_PACKET) || !(f->states & (1 << SS_CLOSE)))
+ return 0;
+
+ if (!getenv("PROC_NET_PACKET") && !getenv("PROC_ROOT") &&
+ packet_show_netlink(f) == 0)
+ return 0;
+
+ if ((fp = net_packet_open()) == NULL)
+ return -1;
+ if (generic_record_read(fp, packet_show_line, f, AF_PACKET))
+ rc = -1;
+
+ fclose(fp);
+ return rc;
+}
+
+static int netlink_show_one(struct filter *f,
+ int prot, int pid, unsigned groups,
+ int state, int dst_pid, unsigned dst_group,
+ int rq, int wq,
+ unsigned long long sk, unsigned long long cb)
+{
+ struct sockstat st;
+ SPRINT_BUF(prot_buf) = {};
+ const char *prot_name;
+ char procname[64] = {};
+
+ st.state = SS_CLOSE;
+ st.rq = rq;
+ st.wq = wq;
+
+ if (f->f) {
+ st.local.family = AF_NETLINK;
+ st.remote.family = AF_NETLINK;
+ st.rport = -1;
+ st.lport = pid;
+ st.local.data[0] = prot;
+ if (run_ssfilter(f->f, &st) == 0)
+ return 1;
+ }
+
+ sock_state_print(&st, "nl");
+
+ if (resolve_services)
+ prot_name = nl_proto_n2a(prot, prot_buf, sizeof(prot_buf));
+ else
+ prot_name = int_to_str(prot, prot_buf);
+
+ if (pid == -1) {
+ procname[0] = '*';
+ } else if (resolve_services) {
+ int done = 0;
+ if (!pid) {
+ done = 1;
+ strncpy(procname, "kernel", 6);
+ } else if (pid > 0) {
+ FILE *fp;
+ snprintf(procname, sizeof(procname), "%s/%d/stat",
+ getenv("PROC_ROOT") ? : "/proc", pid);
+ if ((fp = fopen(procname, "r")) != NULL) {
+ if (fscanf(fp, "%*d (%[^)])", procname) == 1) {
+ snprintf(procname+strlen(procname),
+ sizeof(procname)-strlen(procname),
+ "/%d", pid);
+ done = 1;
+ }
+ fclose(fp);
+ }
+ }
+ if (!done)
+ int_to_str(pid, procname);
+ } else {
+ int_to_str(pid, procname);
+ }
+
+ sock_addr_print(prot_name, ":", procname, NULL);
+
+ if (state == NETLINK_CONNECTED) {
+ char dst_group_buf[30];
+ char dst_pid_buf[30];
+ sock_addr_print(int_to_str(dst_group, dst_group_buf), ":",
+ int_to_str(dst_pid, dst_pid_buf), NULL);
+ } else {
+ sock_addr_print("", "*", "", NULL);
+ }
+
+ char *pid_context = NULL;
+ if (show_proc_ctx) {
+ /* The pid value will either be:
+ * 0 if destination kernel - show kernel initial context.
+ * A valid process pid - use getpidcon.
+ * A unique value allocated by the kernel or netlink user
+ * to the process - show context as "not available".
+ */
+ if (!pid)
+ security_get_initial_context("kernel", &pid_context);
+ else if (pid > 0)
+ getpidcon(pid, &pid_context);
+
+ if (pid_context != NULL) {
+ printf("proc_ctx=%-*s ", serv_width, pid_context);
+ free(pid_context);
+ } else {
+ printf("proc_ctx=%-*s ", serv_width, "unavailable");
+ }
+ }
+
+ if (show_details) {
+ printf(" sk=%llx cb=%llx groups=0x%08x", sk, cb, groups);
+ }
+ printf("\n");
+
+ return 0;
+}
+
+static int netlink_show_sock(const struct sockaddr_nl *addr,
+ struct nlmsghdr *nlh, void *arg)
+{
+ struct filter *f = (struct filter *)arg;
+ struct netlink_diag_msg *r = NLMSG_DATA(nlh);
+ struct rtattr *tb[NETLINK_DIAG_MAX+1];
+ int rq = 0, wq = 0;
+ unsigned long groups = 0;
+
+ parse_rtattr(tb, NETLINK_DIAG_MAX, (struct rtattr*)(r+1),
+ nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)));
+
+ if (tb[NETLINK_DIAG_GROUPS] && RTA_PAYLOAD(tb[NETLINK_DIAG_GROUPS]))
+ groups = *(unsigned long *) RTA_DATA(tb[NETLINK_DIAG_GROUPS]);
+
+ if (tb[NETLINK_DIAG_MEMINFO]) {
+ const __u32 *skmeminfo;
+ skmeminfo = RTA_DATA(tb[NETLINK_DIAG_MEMINFO]);
+
+ rq = skmeminfo[SK_MEMINFO_RMEM_ALLOC];
+ wq = skmeminfo[SK_MEMINFO_WMEM_ALLOC];
+ }
+
+ if (netlink_show_one(f, r->ndiag_protocol, r->ndiag_portid, groups,
+ r->ndiag_state, r->ndiag_dst_portid, r->ndiag_dst_group,
+ rq, wq, 0, 0)) {
+ return 0;
+ }
+
+ if (show_mem) {
+ printf("\t");
+ print_skmeminfo(tb, NETLINK_DIAG_MEMINFO);
+ printf("\n");
+ }
+
+ return 0;
+}
+
+static int netlink_show_netlink(struct filter *f)
+{
+ DIAG_REQUEST(req, struct netlink_diag_req r);
+
+ req.r.sdiag_family = AF_NETLINK;
+ req.r.sdiag_protocol = NDIAG_PROTO_ALL;
+ req.r.ndiag_show = NDIAG_SHOW_GROUPS | NDIAG_SHOW_MEMINFO;
+
+ return handle_netlink_request(f, &req.nlh, sizeof(req), netlink_show_sock);
+}
+
+static int netlink_show(struct filter *f)
+{
+ FILE *fp;
+ char buf[256];
+ int prot, pid;
+ unsigned groups;
+ int rq, wq, rc;
+ unsigned long long sk, cb;
+
+ if (!filter_af_get(f, AF_NETLINK) || !(f->states & (1 << SS_CLOSE)))
+ return 0;
+
+ if (!getenv("PROC_NET_NETLINK") && !getenv("PROC_ROOT") &&
+ netlink_show_netlink(f) == 0)
+ return 0;
+
+ if ((fp = net_netlink_open()) == NULL)
+ return -1;
+ if (!fgets(buf, sizeof(buf), fp)) {
+ fclose(fp);
+ return -1;
+ }
+
+ while (fgets(buf, sizeof(buf), fp)) {
+ sscanf(buf, "%llx %d %d %x %d %d %llx %d",
+ &sk,
+ &prot, &pid, &groups, &rq, &wq, &cb, &rc);
+
+ netlink_show_one(f, prot, pid, groups, 0, 0, 0, rq, wq, sk, cb);
+ }
+
+ fclose(fp);
+ return 0;
+}
+
+struct sock_diag_msg {
+ __u8 sdiag_family;
+};
+
+static int generic_show_sock(const struct sockaddr_nl *addr,
+ struct nlmsghdr *nlh, void *arg)
+{
+ struct sock_diag_msg *r = NLMSG_DATA(nlh);
+ struct inet_diag_arg inet_arg = { .f = arg, .protocol = IPPROTO_MAX };
+
+ switch (r->sdiag_family) {
+ case AF_INET:
+ case AF_INET6:
+ return show_one_inet_sock(addr, nlh, &inet_arg);
+ case AF_UNIX:
+ return unix_show_sock(addr, nlh, arg);
+ case AF_PACKET:
+ return packet_show_sock(addr, nlh, arg);
+ case AF_NETLINK:
+ return netlink_show_sock(addr, nlh, arg);
+ default:
+ return -1;
+ }
+}
+
+static int handle_follow_request(struct filter *f)
+{
+ int ret = -1;
+ int groups = 0;
+ struct rtnl_handle rth;
+
+ if (f->families & (1 << AF_INET) && f->dbs & (1 << TCP_DB))
+ groups |= 1 << (SKNLGRP_INET_TCP_DESTROY - 1);
+ if (f->families & (1 << AF_INET) && f->dbs & (1 << UDP_DB))
+ groups |= 1 << (SKNLGRP_INET_UDP_DESTROY - 1);
+ if (f->families & (1 << AF_INET6) && f->dbs & (1 << TCP_DB))
+ groups |= 1 << (SKNLGRP_INET6_TCP_DESTROY - 1);
+ if (f->families & (1 << AF_INET6) && f->dbs & (1 << UDP_DB))
+ groups |= 1 << (SKNLGRP_INET6_UDP_DESTROY - 1);
+
+ if (groups == 0)
+ return -1;
+
+ if (rtnl_open_byproto(&rth, groups, NETLINK_SOCK_DIAG))
+ return -1;
+
+ rth.dump = 0;
+ rth.local.nl_pid = 0;
+
+ if (rtnl_dump_filter(&rth, generic_show_sock, f))
+ goto Exit;
+
+ ret = 0;
+Exit:
+ rtnl_close(&rth);
+ return ret;
+}
+
+struct snmpstat
+{
+ int tcp_estab;
+};
+
+static int get_snmp_int(char *proto, char *key, int *result)
+{
+ char buf[1024];
+ FILE *fp;
+ int protolen = strlen(proto);
+ int keylen = strlen(key);
+
+ *result = 0;
+
+ if ((fp = net_snmp_open()) == NULL)
+ return -1;
+
+ while (fgets(buf, sizeof(buf), fp) != NULL) {
+ char *p = buf;
+ int pos = 0;
+ if (memcmp(buf, proto, protolen))
+ continue;
+ while ((p = strchr(p, ' ')) != NULL) {
+ pos++;
+ p++;
+ if (memcmp(p, key, keylen) == 0 &&
+ (p[keylen] == ' ' || p[keylen] == '\n'))
+ break;
+ }
+ if (fgets(buf, sizeof(buf), fp) == NULL)
+ break;
+ if (memcmp(buf, proto, protolen))
+ break;
+ p = buf;
+ while ((p = strchr(p, ' ')) != NULL) {
+ p++;
+ if (--pos == 0) {
+ sscanf(p, "%d", result);
+ fclose(fp);
+ return 0;
+ }
+ }
+ }
+
+ fclose(fp);
+ errno = ESRCH;
+ return -1;
+}
+
+
+/* Get stats from sockstat */
+
+struct ssummary
+{
+ int socks;
+ int tcp_mem;
+ int tcp_total;
+ int tcp_orphans;
+ int tcp_tws;
+ int tcp4_hashed;
+ int udp4;
+ int raw4;
+ int frag4;
+ int frag4_mem;
+ int tcp6_hashed;
+ int udp6;
+ int raw6;
+ int frag6;
+ int frag6_mem;
+};
+
+static void get_sockstat_line(char *line, struct ssummary *s)
+{
+ char id[256], rem[256];
+
+ if (sscanf(line, "%[^ ] %[^\n]\n", id, rem) != 2)
+ return;
+
+ if (strcmp(id, "sockets:") == 0)
+ sscanf(rem, "%*s%d", &s->socks);
+ else if (strcmp(id, "UDP:") == 0)
+ sscanf(rem, "%*s%d", &s->udp4);
+ else if (strcmp(id, "UDP6:") == 0)
+ sscanf(rem, "%*s%d", &s->udp6);
+ else if (strcmp(id, "RAW:") == 0)
+ sscanf(rem, "%*s%d", &s->raw4);
+ else if (strcmp(id, "RAW6:") == 0)
+ sscanf(rem, "%*s%d", &s->raw6);
+ else if (strcmp(id, "TCP6:") == 0)
+ sscanf(rem, "%*s%d", &s->tcp6_hashed);
+ else if (strcmp(id, "FRAG:") == 0)
+ sscanf(rem, "%*s%d%*s%d", &s->frag4, &s->frag4_mem);
+ else if (strcmp(id, "FRAG6:") == 0)
+ sscanf(rem, "%*s%d%*s%d", &s->frag6, &s->frag6_mem);
+ else if (strcmp(id, "TCP:") == 0)
+ sscanf(rem, "%*s%d%*s%d%*s%d%*s%d%*s%d",
+ &s->tcp4_hashed,
+ &s->tcp_orphans, &s->tcp_tws, &s->tcp_total, &s->tcp_mem);
+}
+
+static int get_sockstat(struct ssummary *s)
+{
+ char buf[256];
+ FILE *fp;
+
+ memset(s, 0, sizeof(*s));
+
+ if ((fp = net_sockstat_open()) == NULL)
+ return -1;
+ while(fgets(buf, sizeof(buf), fp) != NULL)
+ get_sockstat_line(buf, s);
+ fclose(fp);
+
+ if ((fp = net_sockstat6_open()) == NULL)
+ return 0;
+ while(fgets(buf, sizeof(buf), fp) != NULL)
+ get_sockstat_line(buf, s);
+ fclose(fp);
+
+ return 0;
+}
+
+static int print_summary(void)
+{
+ struct ssummary s;
+ struct snmpstat sn;
+
+ if (get_sockstat(&s) < 0)
+ perror("ss: get_sockstat");
+ if (get_snmp_int("Tcp:", "CurrEstab", &sn.tcp_estab) < 0)
+ perror("ss: get_snmpstat");
+
+ get_slabstat(&slabstat);
+
+ printf("Total: %d (kernel %d)\n", s.socks, slabstat.socks);
+
+ printf("TCP: %d (estab %d, closed %d, orphaned %d, synrecv %d, timewait %d/%d), ports %d\n",
+ s.tcp_total + slabstat.tcp_syns + s.tcp_tws,
+ sn.tcp_estab,
+ s.tcp_total - (s.tcp4_hashed+s.tcp6_hashed-s.tcp_tws),
+ s.tcp_orphans,
+ slabstat.tcp_syns,
+ s.tcp_tws, slabstat.tcp_tws,
+ slabstat.tcp_ports
+ );
+
+ printf("\n");
+ printf("Transport Total IP IPv6\n");
+ printf("* %-9d %-9s %-9s\n", slabstat.socks, "-", "-");
+ printf("RAW %-9d %-9d %-9d\n", s.raw4+s.raw6, s.raw4, s.raw6);
+ printf("UDP %-9d %-9d %-9d\n", s.udp4+s.udp6, s.udp4, s.udp6);
+ printf("TCP %-9d %-9d %-9d\n", s.tcp4_hashed+s.tcp6_hashed, s.tcp4_hashed, s.tcp6_hashed);
+ printf("INET %-9d %-9d %-9d\n",
+ s.raw4+s.udp4+s.tcp4_hashed+
+ s.raw6+s.udp6+s.tcp6_hashed,
+ s.raw4+s.udp4+s.tcp4_hashed,
+ s.raw6+s.udp6+s.tcp6_hashed);
+ printf("FRAG %-9d %-9d %-9d\n", s.frag4+s.frag6, s.frag4, s.frag6);
+
+ printf("\n");
+
+ return 0;
+}
+
+static void _usage(FILE *dest)
+{
+ fprintf(dest,
+"Usage: ss [ OPTIONS ]\n"
+" ss [ OPTIONS ] [ FILTER ]\n"
+" -h, --help this message\n"
+" -V, --version output version information\n"
+" -n, --numeric don't resolve service names\n"
+" -r, --resolve resolve host names\n"
+" -a, --all display all sockets\n"
+" -l, --listening display listening sockets\n"
+" -o, --options show timer information\n"
+" -e, --extended show detailed socket information\n"
+" -m, --memory show socket memory usage\n"
+" -p, --processes show process using socket\n"
+" -i, --info show internal TCP information\n"
+" -s, --summary show socket usage summary\n"
+" -b, --bpf show bpf filter socket information\n"
+" -E, --events continually display sockets as they are destroyed\n"
+" -Z, --context display process SELinux security contexts\n"
+" -z, --contexts display process and socket SELinux security contexts\n"
+" -N, --net switch to the specified network namespace name\n"
+"\n"
+" -4, --ipv4 display only IP version 4 sockets\n"
+" -6, --ipv6 display only IP version 6 sockets\n"
+" -0, --packet display PACKET sockets\n"
+" -t, --tcp display only TCP sockets\n"
+" -u, --udp display only UDP sockets\n"
+" -d, --dccp display only DCCP sockets\n"
+" -w, --raw display only RAW sockets\n"
+" -x, --unix display only Unix domain sockets\n"
+" -f, --family=FAMILY display sockets of type FAMILY\n"
+"\n"
+" -K, --kill forcibly close sockets, display what was closed\n"
+"\n"
+" -A, --query=QUERY, --socket=QUERY\n"
+" QUERY := {all|inet|tcp|udp|raw|unix|unix_dgram|unix_stream|unix_seqpacket|packet|netlink}[,QUERY]\n"
+"\n"
+" -D, --diag=FILE Dump raw information about TCP sockets to FILE\n"
+" -F, --filter=FILE read filter information from FILE\n"
+" FILTER := [ state STATE-FILTER ] [ EXPRESSION ]\n"
+" STATE-FILTER := {all|connected|synchronized|bucket|big|TCP-STATES}\n"
+" TCP-STATES := {established|syn-sent|syn-recv|fin-wait-{1,2}|time-wait|closed|close-wait|last-ack|listen|closing}\n"
+" connected := {established|syn-sent|syn-recv|fin-wait-{1,2}|time-wait|close-wait|last-ack|closing}\n"
+" synchronized := {established|syn-recv|fin-wait-{1,2}|time-wait|close-wait|last-ack|closing}\n"
+" bucket := {syn-recv|time-wait}\n"
+" big := {established|syn-sent|fin-wait-{1,2}|closed|close-wait|last-ack|listen|closing}\n"
+ );
+}
+
+static void help(void) __attribute__((noreturn));
+static void help(void)
+{
+ _usage(stdout);
+ exit(0);
+}
+
+static void usage(void) __attribute__((noreturn));
+static void usage(void)
+{
+ _usage(stderr);
+ exit(-1);
+}
+
+
+static int scan_state(const char *state)
+{
+ int i;
+ if (strcasecmp(state, "close") == 0 ||
+ strcasecmp(state, "closed") == 0)
+ return (1<<SS_CLOSE);
+ if (strcasecmp(state, "syn-rcv") == 0)
+ return (1<<SS_SYN_RECV);
+ if (strcasecmp(state, "established") == 0)
+ return (1<<SS_ESTABLISHED);
+ if (strcasecmp(state, "all") == 0)
+ return SS_ALL;
+ if (strcasecmp(state, "connected") == 0)
+ return SS_ALL & ~((1<<SS_CLOSE)|(1<<SS_LISTEN));
+ if (strcasecmp(state, "synchronized") == 0)
+ return SS_ALL & ~((1<<SS_CLOSE)|(1<<SS_LISTEN)|(1<<SS_SYN_SENT));
+ if (strcasecmp(state, "bucket") == 0)
+ return (1<<SS_SYN_RECV)|(1<<SS_TIME_WAIT);
+ if (strcasecmp(state, "big") == 0)
+ return SS_ALL & ~((1<<SS_SYN_RECV)|(1<<SS_TIME_WAIT));
+ for (i=0; i<SS_MAX; i++) {
+ if (strcasecmp(state, sstate_namel[i]) == 0)
+ return (1<<i);
+ }
+
+ fprintf(stderr, "ss: wrong state name: %s\n", state);
+ exit(-1);
+}
+
+static const struct option long_opts[] = {
+ { "numeric", 0, 0, 'n' },
+ { "resolve", 0, 0, 'r' },
+ { "options", 0, 0, 'o' },
+ { "extended", 0, 0, 'e' },
+ { "memory", 0, 0, 'm' },
+ { "info", 0, 0, 'i' },
+ { "processes", 0, 0, 'p' },
+ { "bpf", 0, 0, 'b' },
+ { "events", 0, 0, 'E' },
+ { "dccp", 0, 0, 'd' },
+ { "tcp", 0, 0, 't' },
+ { "udp", 0, 0, 'u' },
+ { "raw", 0, 0, 'w' },
+ { "unix", 0, 0, 'x' },
+ { "all", 0, 0, 'a' },
+ { "listening", 0, 0, 'l' },
+ { "ipv4", 0, 0, '4' },
+ { "ipv6", 0, 0, '6' },
+ { "packet", 0, 0, '0' },
+ { "family", 1, 0, 'f' },
+ { "socket", 1, 0, 'A' },
+ { "query", 1, 0, 'A' },
+ { "summary", 0, 0, 's' },
+ { "diag", 1, 0, 'D' },
+ { "filter", 1, 0, 'F' },
+ { "version", 0, 0, 'V' },
+ { "help", 0, 0, 'h' },
+ { "context", 0, 0, 'Z' },
+ { "contexts", 0, 0, 'z' },
+ { "net", 1, 0, 'N' },
+ { "kill", 0, 0, 'K' },
+ { 0 }
+
+};
+
+int main(int argc, char *argv[])
+{
+ int saw_states = 0;
+ int saw_query = 0;
+ int do_summary = 0;
+ const char *dump_tcpdiag = NULL;
+ FILE *filter_fp = NULL;
+ int ch;
+ int state_filter = 0;
+
+ while ((ch = getopt_long(argc, argv, "dhaletuwxnro460spbEf:miA:D:F:vVzZN:K",
+ long_opts, NULL)) != EOF) {
+ switch(ch) {
+ case 'n':
+ resolve_services = 0;
+ break;
+ case 'r':
+ resolve_hosts = 1;
+ break;
+ case 'o':
+ show_options = 1;
+ break;
+ case 'e':
+ show_options = 1;
+ show_details++;
+ break;
+ case 'm':
+ show_mem = 1;
+ break;
+ case 'i':
+ show_tcpinfo = 1;
+ break;
+ case 'p':
+ show_users++;
+ user_ent_hash_build();
+ break;
+ case 'b':
+ show_options = 1;
+ show_bpf++;
+ break;
+ case 'E':
+ follow_events = 1;
+ break;
+ case 'd':
+ filter_db_set(¤t_filter, DCCP_DB);
+ break;
+ case 't':
+ filter_db_set(¤t_filter, TCP_DB);
+ break;
+ case 'u':
+ filter_db_set(¤t_filter, UDP_DB);
+ break;
+ case 'w':
+ filter_db_set(¤t_filter, RAW_DB);
+ break;
+ case 'x':
+ filter_af_set(¤t_filter, AF_UNIX);
+ break;
+ case 'a':
+ state_filter = SS_ALL;
+ break;
+ case 'l':
+ state_filter = (1 << SS_LISTEN) | (1 << SS_CLOSE);
+ break;
+ case '4':
+ filter_af_set(¤t_filter, AF_INET);
+ break;
+ case '6':
+ filter_af_set(¤t_filter, AF_INET6);
+ break;
+ case '0':
+ filter_af_set(¤t_filter, AF_PACKET);
+ break;
+ case 'f':
+ if (strcmp(optarg, "inet") == 0)
+ filter_af_set(¤t_filter, AF_INET);
+ else if (strcmp(optarg, "inet6") == 0)
+ filter_af_set(¤t_filter, AF_INET6);
+ else if (strcmp(optarg, "link") == 0)
+ filter_af_set(¤t_filter, AF_PACKET);
+ else if (strcmp(optarg, "unix") == 0)
+ filter_af_set(¤t_filter, AF_UNIX);
+ else if (strcmp(optarg, "netlink") == 0)
+ filter_af_set(¤t_filter, AF_NETLINK);
+ else if (strcmp(optarg, "help") == 0)
+ help();
+ else {
+ fprintf(stderr, "ss: \"%s\" is invalid family\n",
+ optarg);
+ usage();
+ }
+ break;
+ case 'A':
+ {
+ char *p, *p1;
+ if (!saw_query) {
+ current_filter.dbs = 0;
+ state_filter = state_filter ?
+ state_filter : SS_CONN;
+ saw_query = 1;
+ do_default = 0;
+ }
+ p = p1 = optarg;
+ do {
+ if ((p1 = strchr(p, ',')) != NULL)
+ *p1 = 0;
+ if (strcmp(p, "all") == 0) {
+ filter_default_dbs(¤t_filter);
+ } else if (strcmp(p, "inet") == 0) {
+ filter_db_set(¤t_filter, UDP_DB);
+ filter_db_set(¤t_filter, DCCP_DB);
+ filter_db_set(¤t_filter, TCP_DB);
+ filter_db_set(¤t_filter, RAW_DB);
+ } else if (strcmp(p, "udp") == 0) {
+ filter_db_set(¤t_filter, UDP_DB);
+ } else if (strcmp(p, "dccp") == 0) {
+ filter_db_set(¤t_filter, DCCP_DB);
+ } else if (strcmp(p, "tcp") == 0) {
+ filter_db_set(¤t_filter, TCP_DB);
+ } else if (strcmp(p, "raw") == 0) {
+ filter_db_set(¤t_filter, RAW_DB);
+ } else if (strcmp(p, "unix") == 0) {
+ filter_db_set(¤t_filter, UNIX_ST_DB);
+ filter_db_set(¤t_filter, UNIX_DG_DB);
+ filter_db_set(¤t_filter, UNIX_SQ_DB);
+ } else if (strcasecmp(p, "unix_stream") == 0 ||
+ strcmp(p, "u_str") == 0) {
+ filter_db_set(¤t_filter, UNIX_ST_DB);
+ } else if (strcasecmp(p, "unix_dgram") == 0 ||
+ strcmp(p, "u_dgr") == 0) {
+ filter_db_set(¤t_filter, UNIX_DG_DB);
+ } else if (strcasecmp(p, "unix_seqpacket") == 0 ||
+ strcmp(p, "u_seq") == 0) {
+ filter_db_set(¤t_filter, UNIX_SQ_DB);
+ } else if (strcmp(p, "packet") == 0) {
+ filter_db_set(¤t_filter, PACKET_R_DB);
+ filter_db_set(¤t_filter, PACKET_DG_DB);
+ } else if (strcmp(p, "packet_raw") == 0 ||
+ strcmp(p, "p_raw") == 0) {
+ filter_db_set(¤t_filter, PACKET_R_DB);
+ } else if (strcmp(p, "packet_dgram") == 0 ||
+ strcmp(p, "p_dgr") == 0) {
+ filter_db_set(¤t_filter, PACKET_DG_DB);
+ } else if (strcmp(p, "netlink") == 0) {
+ filter_db_set(¤t_filter, NETLINK_DB);
+ } else {
+ fprintf(stderr, "ss: \"%s\" is illegal socket table id\n", p);
+ usage();
+ }
+ p = p1 + 1;
+ } while (p1);
+ break;
+ }
+ case 's':
+ do_summary = 1;
+ break;
+ case 'D':
+ dump_tcpdiag = optarg;
+ break;
+ case 'F':
+ if (filter_fp) {
+ fprintf(stderr, "More than one filter file\n");
+ exit(-1);
+ }
+ if (optarg[0] == '-')
+ filter_fp = stdin;
+ else
+ filter_fp = fopen(optarg, "r");
+ if (!filter_fp) {
+ perror("fopen filter file");
+ exit(-1);
+ }
+ break;
+ case 'v':
+ case 'V':
+ printf("ss utility, iproute2-ss%s\n", SNAPSHOT);
+ exit(0);
+ case 'z':
+ show_sock_ctx++;
+ case 'Z':
+ if (is_selinux_enabled() <= 0) {
+ fprintf(stderr, "ss: SELinux is not enabled.\n");
+ exit(1);
+ }
+ show_proc_ctx++;
+ user_ent_hash_build();
+ break;
+ case 'N':
+ if (netns_switch(optarg))
+ exit(1);
+ break;
+ case 'K':
+ current_filter.kill = 1;
+ break;
+ case 'h':
+ help();
+ case '?':
+ default:
+ usage();
+ }
+ }
+
+ argc -= optind;
+ argv += optind;
+
+ if (do_summary) {
+ print_summary();
+ if (do_default && argc == 0)
+ exit(0);
+ }
+
+ while (argc > 0) {
+ if (strcmp(*argv, "state") == 0) {
+ NEXT_ARG();
+ if (!saw_states)
+ state_filter = 0;
+ state_filter |= scan_state(*argv);
+ saw_states = 1;
+ } else if (strcmp(*argv, "exclude") == 0 ||
+ strcmp(*argv, "excl") == 0) {
+ NEXT_ARG();
+ if (!saw_states)
+ state_filter = SS_ALL;
+ state_filter &= ~scan_state(*argv);
+ saw_states = 1;
+ } else {
+ break;
+ }
+ argc--; argv++;
+ }
+
+ if (do_default) {
+ state_filter = state_filter ? state_filter : SS_CONN;
+ filter_default_dbs(¤t_filter);
+ }
+
+ filter_states_set(¤t_filter, state_filter);
+ filter_merge_defaults(¤t_filter);
+
+ if (resolve_services && resolve_hosts &&
+ (current_filter.dbs&(UNIX_DBM|(1<<TCP_DB)|(1<<UDP_DB)|(1<<DCCP_DB))))
+ init_service_resolver();
+
+
+ if (current_filter.dbs == 0) {
+ fprintf(stderr, "ss: no socket tables to show with such filter.\n");
+ exit(0);
+ }
+ if (current_filter.families == 0) {
+ fprintf(stderr, "ss: no families to show with such filter.\n");
+ exit(0);
+ }
+ if (current_filter.states == 0) {
+ fprintf(stderr, "ss: no socket states to show with such filter.\n");
+ exit(0);
+ }
+
+ if (dump_tcpdiag) {
+ FILE *dump_fp = stdout;
+ if (!(current_filter.dbs & (1<<TCP_DB))) {
+ fprintf(stderr, "ss: tcpdiag dump requested and no tcp in filter.\n");
+ exit(0);
+ }
+ if (dump_tcpdiag[0] != '-') {
+ dump_fp = fopen(dump_tcpdiag, "w");
+ if (!dump_tcpdiag) {
+ perror("fopen dump file");
+ exit(-1);
+ }
+ }
+ inet_show_netlink(¤t_filter, dump_fp, IPPROTO_TCP);
+ fflush(dump_fp);
+ exit(0);
+ }
+
+ if (ssfilter_parse(¤t_filter.f, argc, argv, filter_fp))
+ usage();
+
+ netid_width = 0;
+ if (current_filter.dbs&(current_filter.dbs-1))
+ netid_width = 5;
+
+ state_width = 0;
+ if (current_filter.states&(current_filter.states-1))
+ state_width = 10;
+
+ screen_width = 80;
+ if (isatty(STDOUT_FILENO)) {
+ struct winsize w;
+
+ if (ioctl(STDOUT_FILENO, TIOCGWINSZ, &w) != -1) {
+ if (w.ws_col > 0)
+ screen_width = w.ws_col;
+ }
+ }
+
+ addrp_width = screen_width;
+ addrp_width -= netid_width+1;
+ addrp_width -= state_width+1;
+ addrp_width -= 14;
+
+ if (addrp_width&1) {
+ if (netid_width)
+ netid_width++;
+ else if (state_width)
+ state_width++;
+ }
+
+ addrp_width /= 2;
+ addrp_width--;
+
+ serv_width = resolve_services ? 7 : 5;
+
+ if (addrp_width < 15+serv_width+1)
+ addrp_width = 15+serv_width+1;
+
+ addr_width = addrp_width - serv_width - 1;
+
+ if (netid_width)
+ printf("%-*s ", netid_width, "Netid");
+ if (state_width)
+ printf("%-*s ", state_width, "State");
+ printf("%-6s %-6s ", "Recv-Q", "Send-Q");
+
+ /* Make enough space for the local/remote port field */
+ addr_width -= 13;
+ serv_width += 13;
+
+ printf("%*s:%-*s %*s:%-*s\n",
+ addr_width, "Local Address", serv_width, "Port",
+ addr_width, "Peer Address", serv_width, "Port");
+
+ fflush(stdout);
+
+ if (follow_events)
+ exit(handle_follow_request(¤t_filter));
+
+ if (current_filter.dbs & (1<<NETLINK_DB))
+ netlink_show(¤t_filter);
+ if (current_filter.dbs & PACKET_DBM)
+ packet_show(¤t_filter);
+ if (current_filter.dbs & UNIX_DBM)
+ unix_show(¤t_filter);
+ if (current_filter.dbs & (1<<RAW_DB))
+ raw_show(¤t_filter);
+ if (current_filter.dbs & (1<<UDP_DB))
+ udp_show(¤t_filter);
+ if (current_filter.dbs & (1<<TCP_DB))
+ tcp_show(¤t_filter, IPPROTO_TCP);
+ if (current_filter.dbs & (1<<DCCP_DB))
+ tcp_show(¤t_filter, IPPROTO_DCCP);
+
+ if (show_users || show_proc_ctx || show_sock_ctx)
+ user_ent_destroy();
+
+ return 0;
+}
diff --git a/iproute2/misc/ssfilter.h b/iproute2/misc/ssfilter.h
new file mode 100644
index 0000000..53922a8
--- /dev/null
+++ b/iproute2/misc/ssfilter.h
@@ -0,0 +1,22 @@
+#define SSF_DCOND 0
+#define SSF_SCOND 1
+#define SSF_OR 2
+#define SSF_AND 3
+#define SSF_NOT 4
+#define SSF_D_GE 5
+#define SSF_D_LE 6
+#define SSF_S_GE 7
+#define SSF_S_LE 8
+#define SSF_S_AUTO 9
+
+#include <stdbool.h>
+
+struct ssfilter
+{
+ int type;
+ struct ssfilter *post;
+ struct ssfilter *pred;
+};
+
+int ssfilter_parse(struct ssfilter **f, int argc, char **argv, FILE *fp);
+void *parse_hostcond(char *addr, bool is_port);
diff --git a/iproute2/misc/ssfilter.y b/iproute2/misc/ssfilter.y
new file mode 100644
index 0000000..9906ad8
--- /dev/null
+++ b/iproute2/misc/ssfilter.y
@@ -0,0 +1,289 @@
+%{
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <malloc.h>
+#include <string.h>
+/* NOTE: Android yacc build rules transform ssfilter.y into ssfilter.h, and
+ * #include "ssfilter.h" gets this file instead of the ssfilter.h in the
+ * source tree. This does not work. #include <ssfilter.h> instead. */
+#include <ssfilter.h>
+
+typedef struct ssfilter * ssfilter_t;
+
+#define YYSTYPE ssfilter_t
+
+static struct ssfilter * alloc_node(int type, void *pred)
+{
+ struct ssfilter *n = malloc(sizeof(*n));
+ if (n == NULL)
+ abort();
+ n->type = type;
+ n->pred = pred;
+ n->post = NULL;
+ return n;
+}
+
+static char **yy_argv;
+static int yy_argc;
+static FILE *yy_fp;
+static ssfilter_t *yy_ret;
+static int tok_type = -1;
+
+static int yylex(void);
+
+static void yyerror(char *s)
+{
+ fprintf(stderr, "ss: bison bellows (while parsing filter): \"%s!\"", s);
+}
+
+%}
+
+%token HOSTCOND DCOND SCOND DPORT SPORT LEQ GEQ NEQ AUTOBOUND
+%left '|'
+%left '&'
+%nonassoc '!'
+
+%%
+applet: null expr
+ {
+ *yy_ret = $2;
+ $$ = $2;
+ }
+ | null
+ ;
+null: /* NOTHING */ { $$ = NULL; }
+ ;
+expr: DCOND HOSTCOND
+ {
+ $$ = alloc_node(SSF_DCOND, $2);
+ }
+ | SCOND HOSTCOND
+ {
+ $$ = alloc_node(SSF_SCOND, $2);
+ }
+ | DPORT GEQ HOSTCOND
+ {
+ $$ = alloc_node(SSF_D_GE, $3);
+ }
+ | DPORT LEQ HOSTCOND
+ {
+ $$ = alloc_node(SSF_D_LE, $3);
+ }
+ | DPORT '>' HOSTCOND
+ {
+ $$ = alloc_node(SSF_NOT, alloc_node(SSF_D_LE, $3));
+ }
+ | DPORT '<' HOSTCOND
+ {
+ $$ = alloc_node(SSF_NOT, alloc_node(SSF_D_GE, $3));
+ }
+ | DPORT '=' HOSTCOND
+ {
+ $$ = alloc_node(SSF_DCOND, $3);
+ }
+ | DPORT NEQ HOSTCOND
+ {
+ $$ = alloc_node(SSF_NOT, alloc_node(SSF_DCOND, $3));
+ }
+
+ | SPORT GEQ HOSTCOND
+ {
+ $$ = alloc_node(SSF_S_GE, $3);
+ }
+ | SPORT LEQ HOSTCOND
+ {
+ $$ = alloc_node(SSF_S_LE, $3);
+ }
+ | SPORT '>' HOSTCOND
+ {
+ $$ = alloc_node(SSF_NOT, alloc_node(SSF_S_LE, $3));
+ }
+ | SPORT '<' HOSTCOND
+ {
+ $$ = alloc_node(SSF_NOT, alloc_node(SSF_S_GE, $3));
+ }
+ | SPORT '=' HOSTCOND
+ {
+ $$ = alloc_node(SSF_SCOND, $3);
+ }
+ | SPORT NEQ HOSTCOND
+ {
+ $$ = alloc_node(SSF_NOT, alloc_node(SSF_SCOND, $3));
+ }
+
+ | AUTOBOUND
+ {
+ $$ = alloc_node(SSF_S_AUTO, NULL);
+ }
+ | expr '|' expr
+ {
+ $$ = alloc_node(SSF_OR, $1);
+ $$->post = $3;
+ }
+ | expr expr
+ {
+ $$ = alloc_node(SSF_AND, $1);
+ $$->post = $2;
+ }
+ | expr '&' expr
+
+ {
+ $$ = alloc_node(SSF_AND, $1);
+ $$->post = $3;
+ }
+ | '!' expr
+ {
+ $$ = alloc_node(SSF_NOT, $2);
+ }
+ | '(' expr ')'
+ {
+ $$ = $2;
+ }
+;
+%%
+
+static char *get_token_from_line(char **ptr)
+{
+ char *tok, *cp = *ptr;
+
+ while (*cp == ' ' || *cp == '\t') cp++;
+
+ if (*cp == 0) {
+ *ptr = cp;
+ return NULL;
+ }
+
+ tok = cp;
+
+ while (*cp != 0 && *cp != ' ' && *cp != '\t') {
+ /* Backslash escapes everything. */
+ if (*cp == '\\') {
+ char *tp;
+ for (tp = cp; tp != tok; tp--)
+ *tp = *(tp-1);
+ cp++;
+ tok++;
+ if (*cp == 0)
+ break;
+ }
+ cp++;
+ }
+ if (*cp)
+ *cp++ = 0;
+ *ptr = cp;
+ return tok;
+}
+
+int yylex(void)
+{
+ static char argbuf[1024];
+ static char *tokptr = argbuf;
+ static int argc;
+ char *curtok;
+
+ do {
+ while (*tokptr == 0) {
+ tokptr = NULL;
+ if (argc < yy_argc) {
+ tokptr = yy_argv[argc];
+ argc++;
+ } else if (yy_fp) {
+ while (tokptr == NULL) {
+ if (fgets(argbuf, sizeof(argbuf)-1, yy_fp) == NULL)
+ return 0;
+ argbuf[sizeof(argbuf)-1] = 0;
+ if (strlen(argbuf) == sizeof(argbuf) - 1) {
+ fprintf(stderr, "Too long line in filter");
+ exit(-1);
+ }
+ if (argbuf[strlen(argbuf)-1] == '\n')
+ argbuf[strlen(argbuf)-1] = 0;
+ if (argbuf[0] == '#' || argbuf[0] == '0')
+ continue;
+ tokptr = argbuf;
+ }
+ } else {
+ return 0;
+ }
+ }
+ } while ((curtok = get_token_from_line(&tokptr)) == NULL);
+
+ if (strcmp(curtok, "!") == 0 ||
+ strcmp(curtok, "not") == 0)
+ return '!';
+ if (strcmp(curtok, "&") == 0 ||
+ strcmp(curtok, "&&") == 0 ||
+ strcmp(curtok, "and") == 0)
+ return '&';
+ if (strcmp(curtok, "|") == 0 ||
+ strcmp(curtok, "||") == 0 ||
+ strcmp(curtok, "or") == 0)
+ return '|';
+ if (strcmp(curtok, "(") == 0)
+ return '(';
+ if (strcmp(curtok, ")") == 0)
+ return ')';
+ if (strcmp(curtok, "dst") == 0) {
+ tok_type = DCOND;
+ return DCOND;
+ }
+ if (strcmp(curtok, "src") == 0) {
+ tok_type = SCOND;
+ return SCOND;
+ }
+ if (strcmp(curtok, "dport") == 0) {
+ tok_type = DPORT;
+ return DPORT;
+ }
+ if (strcmp(curtok, "sport") == 0) {
+ tok_type = SPORT;
+ return SPORT;
+ }
+ if (strcmp(curtok, ">=") == 0 ||
+ strcmp(curtok, "ge") == 0 ||
+ strcmp(curtok, "geq") == 0)
+ return GEQ;
+ if (strcmp(curtok, "<=") == 0 ||
+ strcmp(curtok, "le") == 0 ||
+ strcmp(curtok, "leq") == 0)
+ return LEQ;
+ if (strcmp(curtok, "!=") == 0 ||
+ strcmp(curtok, "ne") == 0 ||
+ strcmp(curtok, "neq") == 0)
+ return NEQ;
+ if (strcmp(curtok, "=") == 0 ||
+ strcmp(curtok, "==") == 0 ||
+ strcmp(curtok, "eq") == 0)
+ return '=';
+ if (strcmp(curtok, ">") == 0 ||
+ strcmp(curtok, "gt") == 0)
+ return '>';
+ if (strcmp(curtok, "<") == 0 ||
+ strcmp(curtok, "lt") == 0)
+ return '<';
+ if (strcmp(curtok, "autobound") == 0) {
+ tok_type = AUTOBOUND;
+ return AUTOBOUND;
+ }
+ yylval = (void*)parse_hostcond(curtok, tok_type == SPORT || tok_type == DPORT);
+ if (yylval == NULL) {
+ fprintf(stderr, "Cannot parse dst/src address.\n");
+ exit(1);
+ }
+ return HOSTCOND;
+}
+
+int ssfilter_parse(struct ssfilter **f, int argc, char **argv, FILE *fp)
+{
+ yy_argc = argc;
+ yy_argv = argv;
+ yy_fp = fp;
+ yy_ret = f;
+
+ if (yyparse()) {
+ fprintf(stderr, " Sorry.\n");
+ return -1;
+ }
+ return 0;
+}
diff --git a/iproute2/netem/Makefile b/iproute2/netem/Makefile
new file mode 100644
index 0000000..e52e125
--- /dev/null
+++ b/iproute2/netem/Makefile
@@ -0,0 +1,29 @@
+DISTGEN = maketable normal pareto paretonormal
+DISTDATA = normal.dist pareto.dist paretonormal.dist experimental.dist
+
+HOSTCC ?= $(CC)
+CCOPTS = $(CBUILD_CFLAGS)
+LDLIBS += -lm
+
+all: $(DISTGEN) $(DISTDATA)
+
+$(DISTGEN):
+ $(HOSTCC) $(CCOPTS) -I../include -o $@ $@.c -lm
+
+%.dist: %
+ ./$* > $@
+
+experimental.dist: maketable experimental.dat
+ ./maketable experimental.dat > experimental.dist
+
+stats: stats.c
+ $(HOSTCC) $(CCOPTS) -I../include -o $@ $@.c -lm
+
+install: all
+ mkdir -p $(DESTDIR)$(LIBDIR)/tc
+ for i in $(DISTDATA); \
+ do install -m 644 $$i $(DESTDIR)$(LIBDIR)/tc; \
+ done
+
+clean:
+ rm -f $(DISTDATA) $(DISTGEN)
diff --git a/iproute2/netem/README.distribution b/iproute2/netem/README.distribution
new file mode 100644
index 0000000..23f7ecb
--- /dev/null
+++ b/iproute2/netem/README.distribution
@@ -0,0 +1,97 @@
+Notes about distribution tables from Nistnet
+-------------------------------------------------------------------------------
+I. About the distribution tables
+
+The table used for "synthesizing" the distribution is essentially a scaled,
+translated, inverse to the cumulative distribution function.
+
+Here's how to think about it: Let F() be the cumulative distribution
+function for a probability distribution X. We'll assume we've scaled
+things so that X has mean 0 and standard deviation 1, though that's not
+so important here. Then:
+
+ F(x) = P(X <= x) = \int_{-inf}^x f
+
+where f is the probability density function.
+
+F is monotonically increasing, so has an inverse function G, with range
+0 to 1. Here, G(t) = the x such that P(X <= x) = t. (In general, G may
+have singularities if X has point masses, i.e., points x such that
+P(X = x) > 0.)
+
+Now we create a tabular representation of G as follows: Choose some table
+size N, and for the ith entry, put in G(i/N). Let's call this table T.
+
+The claim now is, I can create a (discrete) random variable Y whose
+distribution has the same approximate "shape" as X, simply by letting
+Y = T(U), where U is a discrete uniform random variable with range 1 to N.
+To see this, it's enough to show that Y's cumulative distribution function,
+(let's call it H), is a discrete approximation to F. But
+
+ H(x) = P(Y <= x)
+ = (# of entries in T <= x) / N -- as Y chosen uniformly from T
+ = i/N, where i is the largest integer such that G(i/N) <= x
+ = i/N, where i is the largest integer such that i/N <= F(x)
+ -- since G and F are inverse functions (and F is
+ increasing)
+ = floor(N*F(x))/N
+
+as desired.
+
+II. How to create distribution tables (in theory)
+
+How can we create this table in practice? In some cases, F may have a
+simple expression which allows evaluating its inverse directly. The
+pareto distribution is one example of this. In other cases, and
+especially for matching an experimentally observed distribution, it's
+easiest simply to create a table for F and "invert" it. Here, we give
+a concrete example, namely how the new "experimental" distribution was
+created.
+
+1. Collect enough data points to characterize the distribution. Here, I
+collected 25,000 "ping" roundtrip times to a "distant" point (time.nist.gov).
+That's far more data than is really necessary, but it was fairly painless to
+collect it, so...
+
+2. Normalize the data so that it has mean 0 and standard deviation 1.
+
+3. Determine the cumulative distribution. The code I wrote creates a table
+covering the range -10 to +10, with granularity .00005. Obviously, this
+is absurdly over-precise, but since it's a one-time only computation, I
+figured it hardly mattered.
+
+4. Invert the table: for each table entry F(x) = y, make the y*TABLESIZE
+(here, 4096) entry be x*TABLEFACTOR (here, 8192). This creates a table
+for the ("normalized") inverse of size TABLESIZE, covering its domain 0
+to 1 with granularity 1/TABLESIZE. Note that even with the granularity
+used in creating the table for F, it's possible not all the entries in
+the table for G will be filled in. So, make a pass through the
+inverse's table, filling in any missing entries by linear interpolation.
+
+III. How to create distribution tables (in practice)
+
+If you want to do all this yourself, I've provided several tools to help:
+
+1. maketable does the steps 2-4 above, and then generates the appropriate
+header file. So if you have your own time distribution, you can generate
+the header simply by:
+
+ maketable < time.values > header.h
+
+2. As explained in the other README file, the somewhat sleazy way I have
+of generating correlated values needs correction. You can generate your
+own correction tables by compiling makesigtable and makemutable with
+your header file. Check the Makefile to see how this is done.
+
+3. Warning: maketable, makesigtable and especially makemutable do
+enormous amounts of floating point arithmetic. Don't try running
+these on an old 486. (NIST Net itself will run fine on such a
+system, since in operation, it just needs to do a few simple integral
+calculations. But getting there takes some work.)
+
+4. The tables produced are all normalized for mean 0 and standard
+deviation 1. How do you know what values to use for real? Here, I've
+provided a simple "stats" utility. Give it a series of floating point
+values, and it will return their mean (mu), standard deviation (sigma),
+and correlation coefficient (rho). You can then plug these values
+directly into NIST Net.
diff --git a/iproute2/netem/experimental.dat b/iproute2/netem/experimental.dat
new file mode 100644
index 0000000..3663a3e
--- /dev/null
+++ b/iproute2/netem/experimental.dat
@@ -0,0 +1,13448 @@
+211.6
+205.6
+203.0
+218.6
+213.9
+199.1
+208.7
+207.7
+203.4
+201.7
+200.3
+213.8
+213.4
+209.8
+204.3
+201.8
+196.3
+216.2
+208.9
+202.4
+205.2
+211.1
+210.9
+208.5
+199.9
+211.6
+211.9
+204.6
+215.4
+202.5
+206.5
+201.1
+198.4
+220.2
+203.7
+219.5
+199.1
+207.6
+205.3
+202.3
+219.7
+230.0
+211.0
+202.7
+209.9
+215.4
+202.9
+209.6
+200.5
+197.3
+212.3
+207.6
+210.5
+202.7
+205.7
+211.2
+208.0
+211.0
+209.4
+204.8
+204.8
+208.7
+210.1
+205.3
+202.5
+210.4
+209.4
+204.5
+204.7
+215.0
+202.6
+209.9
+220.2
+203.8
+206.3
+199.4
+221.8
+200.0
+199.6
+209.3
+206.2
+215.8
+196.9
+211.6
+198.4
+201.2
+209.4
+204.3
+219.0
+212.7
+214.6
+196.3
+202.0
+201.9
+197.5
+229.5
+207.5
+213.8
+209.2
+212.9
+193.9
+200.8
+208.6
+196.8
+201.3
+204.9
+204.7
+209.5
+211.3
+215.3
+203.7
+190.1
+235.6
+203.8
+210.0
+209.7
+214.3
+213.0
+206.3
+197.7
+208.2
+226.3
+216.5
+198.0
+201.3
+211.3
+195.8
+210.9
+208.1
+201.2
+201.7
+213.1
+207.9
+206.6
+207.1
+202.2
+199.6
+205.5
+207.3
+219.7
+204.1
+204.4
+209.0
+212.7
+196.4
+214.0
+208.8
+209.7
+217.2
+196.2
+195.0
+227.7
+207.2
+233.3
+207.9
+204.0
+194.4
+219.2
+208.7
+198.6
+205.0
+204.0
+223.7
+207.4
+209.2
+208.7
+205.4
+212.8
+207.8
+203.0
+204.1
+221.0
+198.4
+217.7
+218.4
+374.2
+220.1
+210.8
+212.1
+214.3
+213.3
+210.3
+202.4
+209.7
+218.1
+205.0
+204.5
+220.3
+209.8
+218.3
+216.6
+206.0
+208.9
+221.0
+213.0
+202.1
+204.2
+220.6
+212.4
+226.1
+208.8
+206.1
+220.7
+219.3
+210.9
+211.2
+213.0
+201.4
+210.5
+206.2
+201.9
+224.5
+219.3
+201.1
+195.6
+223.6
+196.7
+213.7
+202.3
+215.6
+211.4
+209.6
+207.6
+212.4
+203.4
+205.4
+216.1
+216.7
+205.3
+213.9
+208.9
+208.4
+205.1
+199.3
+200.6
+199.1
+203.2
+207.6
+203.8
+201.9
+208.5
+196.4
+213.6
+217.6
+201.5
+210.1
+213.5
+203.8
+214.1
+211.9
+201.5
+186.9
+199.7
+209.1
+200.2
+205.8
+206.7
+200.0
+198.1
+209.3
+207.8
+208.7
+208.0
+208.6
+231.3
+214.5
+210.1
+200.8
+208.9
+216.9
+205.7
+214.9
+236.8
+200.9
+219.1
+204.6
+210.0
+214.0
+222.6
+209.6
+207.0
+196.3
+207.7
+207.9
+208.0
+220.2
+198.2
+204.9
+204.1
+201.0
+204.8
+213.3
+203.9
+222.5
+205.2
+203.5
+209.7
+212.1
+210.1
+221.1
+210.2
+208.0
+201.4
+209.0
+211.9
+201.6
+214.4
+199.6
+198.8
+210.2
+207.3
+206.5
+204.8
+196.3
+199.8
+206.4
+195.3
+202.8
+202.7
+203.8
+211.2
+208.4
+198.6
+202.0
+214.9
+204.2
+201.1
+195.9
+196.1
+211.2
+197.0
+207.7
+196.6
+205.7
+211.4
+201.4
+205.0
+195.5
+198.9
+214.4
+207.3
+204.2
+207.2
+198.5
+220.7
+214.1
+213.2
+207.7
+203.6
+265.8
+221.0
+213.1
+195.4
+197.3
+213.0
+207.7
+206.0
+198.4
+202.3
+213.9
+218.6
+207.6
+206.1
+212.8
+216.8
+213.7
+209.8
+198.1
+202.4
+205.3
+207.0
+209.2
+209.9
+204.4
+199.6
+205.5
+203.9
+216.0
+213.1
+202.4
+199.0
+219.5
+193.9
+197.3
+212.2
+216.7
+217.5
+201.0
+206.2
+202.9
+211.3
+203.1
+218.0
+208.6
+217.8
+209.0
+211.8
+220.1
+212.7
+207.2
+221.2
+215.2
+196.9
+216.6
+203.1
+207.1
+216.7
+206.7
+215.0
+219.3
+204.3
+219.6
+207.1
+211.8
+210.2
+217.2
+207.9
+219.9
+205.4
+201.1
+214.1
+205.8
+212.5
+222.8
+211.9
+217.4
+203.8
+222.9
+206.6
+207.6
+197.5
+206.2
+218.5
+220.3
+207.7
+203.5
+226.4
+216.8
+206.0
+193.2
+198.2
+201.3
+202.4
+208.5
+212.6
+205.0
+202.2
+210.0
+202.4
+203.9
+193.3
+212.4
+203.4
+212.1
+206.1
+206.9
+207.0
+216.1
+201.1
+204.7
+202.4
+207.5
+203.9
+200.9
+210.0
+207.1
+217.2
+197.4
+199.2
+210.8
+209.2
+218.4
+200.2
+211.7
+213.6
+203.3
+197.9
+203.0
+204.2
+207.9
+209.4
+225.4
+237.3
+209.5
+208.2
+207.5
+207.0
+203.0
+219.3
+228.3
+213.5
+205.1
+198.9
+212.7
+201.5
+210.0
+206.5
+203.3
+206.1
+210.1
+219.7
+206.8
+215.4
+220.4
+217.3
+211.4
+206.0
+208.3
+207.3
+205.5
+210.8
+209.3
+197.2
+207.2
+191.7
+204.2
+207.2
+216.1
+209.1
+203.8
+201.8
+208.7
+212.4
+214.5
+213.8
+201.3
+219.7
+214.8
+211.9
+223.8
+208.6
+203.5
+207.4
+207.0
+198.0
+208.2
+218.6
+205.1
+214.6
+215.2
+215.3
+204.3
+210.1
+221.9
+210.7
+198.2
+205.2
+201.1
+219.0
+207.2
+205.9
+203.8
+200.5
+217.5
+208.7
+208.4
+192.6
+211.0
+209.1
+206.5
+197.4
+202.1
+210.0
+198.3
+222.2
+211.9
+212.3
+222.2
+195.1
+200.7
+212.1
+208.3
+211.8
+211.7
+206.5
+211.8
+207.6
+214.2
+207.7
+204.7
+208.2
+208.4
+207.9
+212.1
+223.2
+206.3
+205.6
+201.8
+211.9
+207.6
+203.0
+221.2
+206.3
+222.4
+253.5
+204.4
+218.9
+211.9
+210.9
+214.0
+226.7
+214.4
+199.7
+213.8
+207.0
+201.8
+206.6
+203.1
+202.1
+203.6
+213.9
+196.9
+200.4
+204.6
+333.4
+204.5
+220.9
+207.3
+212.1
+203.7
+200.9
+198.2
+204.0
+201.4
+198.2
+209.6
+211.5
+201.2
+200.4
+207.4
+200.7
+213.8
+207.7
+188.0
+210.0
+210.5
+207.3
+198.6
+206.1
+186.9
+201.4
+204.0
+200.8
+207.8
+211.7
+198.7
+206.1
+213.0
+214.8
+212.8
+208.8
+210.4
+206.5
+210.1
+201.7
+202.7
+201.3
+194.1
+200.8
+196.8
+204.2
+217.5
+209.0
+198.7
+203.2
+213.8
+198.0
+207.1
+204.0
+215.3
+199.5
+214.1
+200.1
+206.9
+219.9
+204.8
+208.6
+207.8
+207.5
+203.8
+210.9
+210.6
+205.3
+202.1
+212.9
+214.8
+210.9
+217.2
+218.3
+221.5
+201.8
+212.7
+215.0
+206.7
+222.8
+210.9
+211.5
+202.0
+208.1
+268.9
+205.8
+204.0
+198.4
+206.3
+209.3
+206.4
+207.4
+226.9
+209.9
+199.6
+206.5
+210.9
+224.1
+211.9
+214.4
+212.2
+211.5
+209.4
+205.3
+204.8
+207.7
+208.9
+213.7
+201.0
+217.4
+198.1
+219.0
+206.5
+229.1
+220.1
+196.8
+203.1
+208.8
+201.7
+195.7
+207.0
+202.4
+206.6
+204.9
+196.6
+204.3
+198.6
+203.9
+215.8
+194.9
+202.7
+225.5
+205.9
+201.4
+213.1
+214.2
+218.8
+209.4
+204.4
+206.7
+209.8
+198.4
+211.8
+212.1
+209.1
+202.3
+213.7
+215.5
+218.3
+209.1
+216.6
+214.8
+206.4
+205.6
+214.4
+209.2
+211.7
+211.3
+211.0
+205.6
+204.2
+191.7
+213.8
+204.9
+205.3
+212.0
+199.9
+198.3
+211.8
+203.0
+212.2
+203.0
+201.8
+214.4
+214.1
+199.6
+205.3
+208.2
+196.7
+196.7
+209.1
+205.1
+212.5
+213.1
+197.3
+208.8
+218.0
+220.0
+198.4
+206.3
+206.9
+253.2
+194.3
+202.6
+210.6
+219.1
+197.8
+197.1
+194.0
+211.6
+209.6
+198.3
+213.0
+207.7
+207.0
+213.3
+206.9
+197.6
+204.8
+202.0
+200.0
+215.2
+204.5
+206.3
+206.7
+203.2
+194.9
+206.3
+209.9
+210.6
+214.2
+208.6
+207.4
+213.9
+210.4
+210.0
+200.6
+203.8
+202.7
+204.2
+202.7
+210.2
+192.5
+215.4
+211.7
+208.3
+204.8
+203.3
+197.7
+216.7
+200.9
+203.6
+208.6
+206.5
+209.9
+200.1
+198.4
+203.3
+210.4
+211.6
+202.0
+203.1
+204.0
+204.0
+215.0
+211.4
+202.0
+197.2
+197.6
+209.9
+205.4
+213.1
+199.1
+212.4
+216.1
+218.3
+214.6
+224.1
+206.9
+199.4
+213.4
+261.2
+199.4
+208.8
+209.9
+205.7
+203.1
+203.2
+204.6
+201.6
+210.6
+213.2
+214.8
+203.8
+204.9
+220.7
+201.5
+212.5
+216.8
+209.7
+203.1
+213.3
+204.7
+218.2
+215.5
+215.6
+211.6
+214.2
+205.1
+216.6
+216.3
+203.5
+200.8
+213.7
+221.9
+215.0
+210.2
+217.1
+214.7
+208.8
+217.4
+231.1
+213.7
+215.0
+213.5
+216.7
+207.7
+201.0
+210.4
+210.9
+206.7
+203.7
+199.2
+209.3
+206.3
+202.4
+210.1
+212.3
+202.2
+207.2
+197.8
+205.9
+202.0
+214.2
+203.5
+204.4
+200.0
+204.0
+193.8
+192.3
+229.0
+204.5
+194.8
+213.6
+215.9
+214.8
+221.6
+208.5
+201.5
+204.4
+206.4
+194.5
+199.4
+201.5
+209.7
+212.5
+202.1
+208.2
+205.4
+204.5
+199.4
+194.5
+199.6
+201.5
+206.2
+219.9
+198.5
+216.2
+195.7
+205.0
+208.0
+204.9
+195.9
+207.4
+216.9
+195.9
+204.4
+208.3
+206.1
+188.5
+202.3
+201.7
+200.5
+206.2
+191.5
+218.6
+206.5
+208.9
+209.9
+201.5
+212.7
+203.2
+209.7
+212.1
+208.4
+207.2
+206.5
+204.5
+222.7
+207.6
+207.4
+210.3
+212.2
+219.1
+215.2
+211.1
+205.9
+205.5
+205.9
+203.1
+205.4
+184.5
+205.0
+194.8
+213.5
+209.8
+195.4
+202.9
+205.3
+196.3
+202.0
+198.2
+201.5
+195.3
+230.9
+207.8
+212.6
+202.7
+204.8
+205.0
+202.8
+206.2
+200.2
+202.7
+203.5
+205.5
+196.9
+209.4
+212.1
+200.8
+205.0
+208.0
+207.1
+198.0
+204.8
+205.8
+200.9
+202.1
+202.4
+206.9
+209.1
+199.7
+197.1
+206.9
+200.2
+193.7
+195.0
+250.8
+207.5
+204.5
+208.8
+209.8
+194.8
+200.2
+205.1
+197.3
+208.3
+200.4
+204.7
+211.1
+203.4
+218.2
+194.6
+201.5
+202.2
+202.9
+198.8
+218.2
+201.7
+189.8
+210.1
+208.0
+204.3
+205.8
+204.2
+207.8
+200.2
+197.9
+198.9
+208.1
+202.4
+196.2
+195.5
+204.6
+211.0
+205.0
+193.6
+197.2
+198.6
+193.8
+198.9
+232.4
+201.8
+212.2
+208.6
+204.5
+199.3
+211.2
+203.1
+209.7
+214.3
+203.9
+200.3
+203.3
+206.1
+206.9
+209.1
+209.1
+199.3
+199.4
+198.8
+198.9
+199.9
+193.7
+204.6
+203.4
+199.7
+212.6
+200.7
+208.1
+198.8
+200.5
+209.2
+208.4
+205.7
+197.1
+202.6
+199.5
+208.4
+200.1
+204.9
+202.9
+201.5
+207.6
+200.6
+204.2
+210.0
+207.1
+205.1
+198.5
+204.9
+196.5
+208.0
+202.4
+202.7
+196.2
+206.9
+201.5
+203.3
+198.7
+211.9
+208.4
+206.7
+209.4
+204.0
+202.3
+205.0
+205.3
+206.0
+213.1
+205.7
+199.3
+206.2
+204.6
+209.3
+205.7
+202.7
+213.3
+202.3
+197.8
+196.5
+193.4
+211.6
+209.9
+195.5
+196.2
+210.2
+207.1
+207.0
+221.8
+217.2
+215.4
+207.0
+200.1
+207.5
+206.0
+200.7
+190.9
+209.8
+213.5
+206.3
+196.0
+213.1
+202.7
+211.6
+196.5
+209.9
+212.3
+199.9
+206.8
+225.1
+203.9
+204.3
+197.7
+203.5
+203.2
+193.5
+200.9
+201.4
+189.1
+203.9
+194.5
+205.4
+204.8
+204.9
+201.3
+208.4
+196.9
+206.8
+207.7
+201.6
+210.3
+211.6
+209.8
+200.2
+205.2
+197.6
+195.9
+212.8
+206.4
+201.0
+208.2
+207.5
+202.5
+193.3
+206.5
+221.2
+198.8
+216.6
+217.0
+209.1
+206.6
+197.7
+211.0
+199.9
+198.0
+210.4
+200.5
+211.7
+219.6
+206.8
+207.2
+210.6
+205.4
+203.8
+207.4
+206.2
+205.1
+208.7
+196.3
+204.7
+210.8
+214.4
+196.3
+206.5
+210.8
+193.2
+203.3
+203.9
+207.7
+194.9
+203.7
+195.5
+218.7
+201.1
+199.5
+207.6
+209.3
+207.5
+205.7
+203.9
+205.4
+201.3
+205.8
+205.4
+208.8
+214.3
+203.4
+207.5
+188.9
+205.5
+200.7
+212.5
+197.9
+219.0
+213.6
+197.3
+202.7
+216.3
+205.0
+210.2
+203.2
+203.9
+206.8
+213.6
+200.1
+204.4
+211.4
+213.4
+200.2
+208.4
+209.1
+198.8
+207.4
+195.0
+205.6
+200.5
+204.3
+201.9
+206.4
+199.0
+196.1
+207.6
+195.4
+197.2
+200.7
+190.8
+211.9
+191.5
+201.4
+193.5
+205.1
+206.8
+199.5
+207.4
+209.8
+199.1
+194.6
+201.6
+211.6
+206.8
+203.9
+196.8
+206.3
+210.1
+200.6
+227.4
+201.9
+210.8
+205.8
+217.2
+205.8
+196.1
+200.7
+213.8
+205.4
+211.6
+212.3
+213.6
+201.7
+199.9
+203.2
+212.6
+211.0
+208.1
+198.1
+201.7
+211.6
+207.4
+212.4
+207.3
+214.9
+214.5
+214.5
+202.7
+200.1
+206.4
+213.4
+189.7
+203.4
+202.2
+198.2
+206.5
+213.7
+207.6
+202.8
+209.2
+205.5
+196.4
+207.6
+207.4
+207.3
+188.8
+215.6
+195.4
+207.7
+208.2
+200.9
+208.4
+203.3
+210.8
+199.6
+208.3
+206.7
+201.6
+202.9
+197.5
+206.4
+209.0
+208.4
+211.6
+204.4
+210.0
+190.9
+199.3
+207.6
+202.5
+197.0
+200.8
+203.1
+204.0
+199.0
+208.0
+204.6
+196.6
+200.8
+205.2
+198.8
+203.0
+208.3
+200.1
+205.5
+203.7
+202.2
+203.8
+211.5
+201.8
+213.2
+207.4
+207.8
+202.2
+208.2
+204.2
+200.4
+186.1
+188.5
+220.4
+212.8
+193.3
+196.9
+203.0
+207.3
+202.4
+201.7
+204.8
+192.2
+218.7
+226.3
+209.5
+201.4
+207.3
+202.6
+210.7
+208.4
+208.4
+207.4
+210.4
+191.2
+203.6
+197.1
+207.5
+197.8
+206.2
+214.5
+208.2
+207.3
+204.7
+199.6
+206.3
+189.0
+214.4
+209.4
+208.1
+199.9
+190.5
+223.0
+198.8
+201.1
+192.4
+204.0
+209.0
+206.7
+204.3
+198.7
+210.9
+212.0
+204.8
+204.2
+199.5
+203.5
+203.0
+190.6
+207.9
+207.9
+193.2
+210.9
+200.1
+207.6
+193.6
+204.9
+197.7
+200.9
+213.0
+215.0
+204.4
+196.6
+209.6
+209.9
+199.8
+198.8
+202.1
+203.4
+205.4
+204.4
+196.2
+190.7
+210.9
+197.7
+194.7
+204.0
+201.5
+195.3
+209.0
+203.6
+196.1
+205.2
+206.7
+206.6
+191.4
+193.4
+206.6
+205.9
+207.9
+201.7
+213.3
+199.4
+202.8
+196.1
+208.3
+206.4
+205.2
+191.9
+207.3
+191.5
+210.8
+200.9
+210.4
+208.3
+211.0
+202.7
+198.8
+196.8
+202.7
+196.9
+214.6
+210.2
+226.1
+220.8
+213.5
+194.9
+210.4
+203.7
+203.7
+180.8
+213.7
+208.0
+209.8
+209.7
+213.8
+185.5
+208.5
+203.5
+212.8
+193.1
+199.2
+211.0
+217.4
+211.0
+202.7
+205.0
+208.6
+197.5
+197.1
+201.0
+195.9
+208.4
+205.7
+205.8
+194.0
+204.4
+194.5
+194.3
+200.1
+209.5
+218.0
+202.8
+197.5
+206.7
+199.8
+205.2
+201.4
+205.2
+186.0
+208.4
+218.4
+206.7
+201.9
+209.7
+208.0
+203.9
+193.1
+202.0
+198.0
+199.5
+211.0
+191.8
+198.7
+197.3
+195.6
+202.9
+203.4
+206.1
+205.6
+207.5
+220.8
+204.7
+207.7
+252.5
+203.9
+203.2
+201.3
+200.1
+201.1
+196.8
+197.6
+206.4
+209.6
+197.9
+199.4
+212.6
+205.4
+200.9
+197.5
+202.2
+199.5
+206.7
+215.1
+216.4
+221.9
+199.2
+246.4
+196.0
+205.1
+205.4
+207.8
+192.6
+204.6
+209.2
+213.4
+198.9
+205.3
+205.8
+201.1
+195.2
+199.4
+200.8
+210.5
+202.3
+217.9
+208.4
+220.8
+218.4
+195.7
+199.4
+198.8
+192.0
+210.9
+218.5
+194.5
+203.6
+195.0
+208.8
+197.4
+204.1
+200.7
+201.0
+206.6
+202.2
+208.7
+213.1
+198.3
+212.2
+201.9
+206.3
+203.4
+198.0
+198.0
+205.3
+199.6
+196.6
+202.8
+201.7
+208.7
+195.6
+199.4
+205.4
+205.2
+202.2
+193.3
+191.9
+195.1
+201.1
+210.5
+208.7
+196.9
+193.4
+200.8
+199.6
+204.1
+200.4
+197.6
+204.1
+206.9
+205.2
+206.9
+194.7
+200.4
+198.8
+201.7
+201.8
+207.0
+193.2
+199.9
+201.3
+192.5
+197.9
+206.9
+190.0
+203.8
+208.8
+200.9
+203.3
+194.5
+192.6
+204.9
+205.5
+196.6
+194.8
+197.9
+198.1
+211.2
+198.8
+202.2
+205.9
+199.5
+204.7
+201.6
+201.2
+203.4
+204.2
+190.7
+206.7
+205.4
+208.4
+203.1
+204.2
+198.4
+194.3
+191.6
+198.9
+203.5
+198.7
+192.2
+198.4
+194.5
+181.1
+200.9
+200.0
+209.2
+210.4
+200.0
+201.1
+193.9
+207.0
+193.4
+202.6
+192.8
+196.0
+203.8
+184.2
+179.3
+202.3
+191.4
+199.7
+195.4
+189.9
+197.0
+187.5
+192.1
+198.3
+202.2
+205.0
+212.3
+198.0
+205.5
+210.1
+197.6
+198.7
+206.6
+203.4
+194.3
+181.2
+199.0
+202.4
+189.1
+181.6
+200.4
+188.1
+180.1
+203.1
+201.1
+195.5
+201.6
+201.3
+197.6
+196.0
+205.5
+184.9
+186.5
+190.8
+188.6
+207.2
+199.5
+198.6
+199.8
+212.2
+208.1
+196.9
+199.6
+205.3
+196.9
+188.9
+205.4
+212.5
+197.5
+201.8
+188.8
+187.1
+199.9
+195.4
+188.7
+198.7
+185.0
+191.6
+193.3
+191.8
+209.4
+197.4
+195.2
+189.4
+189.7
+199.9
+199.3
+188.7
+188.3
+190.9
+181.6
+209.8
+194.6
+198.2
+199.9
+198.1
+186.8
+195.3
+190.9
+198.8
+189.3
+207.5
+179.2
+188.8
+185.6
+206.2
+184.8
+190.7
+203.5
+199.2
+202.0
+197.6
+197.2
+196.4
+210.4
+200.1
+194.8
+186.7
+198.2
+197.8
+186.5
+200.2
+192.7
+192.7
+190.4
+220.9
+207.5
+188.6
+198.5
+203.0
+202.2
+189.6
+177.3
+194.8
+195.2
+243.9
+196.5
+180.6
+214.6
+196.4
+220.6
+194.7
+200.5
+193.7
+199.7
+203.0
+201.4
+187.7
+199.8
+191.8
+203.9
+203.8
+191.3
+206.6
+201.7
+202.1
+202.6
+200.0
+203.6
+195.9
+204.8
+212.8
+199.2
+203.3
+206.6
+192.2
+205.0
+198.9
+205.3
+195.0
+198.1
+190.4
+203.7
+188.2
+204.2
+211.1
+192.5
+194.5
+198.3
+205.7
+198.5
+210.2
+206.8
+195.4
+200.8
+202.7
+220.0
+204.1
+209.5
+200.2
+187.1
+205.4
+202.6
+203.3
+214.1
+193.8
+207.4
+208.2
+204.9
+215.9
+202.6
+198.0
+193.8
+198.2
+206.2
+203.9
+190.6
+210.8
+195.6
+207.6
+206.6
+195.4
+189.9
+199.7
+203.1
+207.1
+192.2
+197.3
+197.6
+193.3
+207.9
+201.3
+206.8
+201.9
+195.7
+204.1
+201.1
+192.5
+206.7
+213.1
+195.2
+205.1
+196.2
+203.5
+195.5
+200.3
+194.7
+194.5
+200.6
+211.2
+202.1
+194.6
+199.9
+212.6
+206.8
+196.2
+205.8
+202.8
+201.6
+205.2
+205.8
+193.1
+202.0
+196.2
+208.1
+209.5
+199.8
+208.8
+192.3
+207.9
+201.3
+205.7
+205.9
+208.6
+210.3
+202.2
+212.1
+210.3
+199.6
+200.8
+209.1
+202.5
+215.0
+201.5
+209.2
+207.0
+215.3
+205.6
+213.7
+203.7
+199.8
+201.4
+194.7
+194.3
+188.7
+200.9
+203.8
+203.2
+212.5
+207.0
+211.3
+204.3
+204.5
+194.0
+210.7
+207.1
+207.5
+200.7
+200.8
+200.7
+200.1
+203.7
+191.1
+201.8
+194.8
+195.2
+197.4
+190.5
+192.7
+206.6
+200.8
+204.3
+206.5
+209.8
+202.5
+207.6
+198.4
+203.3
+202.1
+200.6
+198.4
+191.0
+203.5
+198.6
+184.3
+183.7
+189.1
+205.4
+187.8
+194.5
+199.2
+196.4
+210.9
+176.8
+191.6
+182.7
+181.3
+205.7
+203.2
+186.3
+187.6
+189.1
+180.8
+180.2
+187.6
+194.9
+192.8
+185.2
+198.3
+209.3
+177.5
+193.9
+193.1
+203.4
+192.1
+200.9
+182.6
+204.9
+197.6
+212.8
+206.9
+193.3
+201.0
+195.3
+197.1
+189.6
+198.5
+190.4
+188.8
+197.7
+189.9
+200.7
+196.8
+186.3
+181.5
+184.9
+200.2
+198.7
+205.8
+200.2
+198.3
+207.9
+206.1
+201.5
+197.8
+199.5
+198.1
+211.3
+201.6
+202.4
+196.0
+197.7
+209.2
+199.3
+205.5
+191.6
+206.4
+196.5
+209.5
+203.4
+201.4
+200.1
+205.2
+190.9
+205.1
+197.5
+196.1
+194.4
+194.7
+188.9
+180.8
+206.5
+199.8
+193.1
+195.2
+192.7
+199.2
+199.5
+188.1
+180.2
+191.0
+206.9
+208.2
+202.5
+200.0
+207.0
+201.6
+195.6
+195.6
+195.0
+196.3
+190.2
+194.0
+182.9
+192.1
+206.5
+181.4
+192.3
+199.6
+201.6
+192.4
+200.5
+207.1
+198.5
+198.8
+190.8
+200.3
+199.3
+200.5
+187.7
+208.3
+205.6
+189.3
+198.4
+204.9
+197.4
+198.7
+190.6
+214.5
+212.5
+207.6
+196.9
+183.4
+185.1
+205.8
+226.5
+202.5
+201.8
+202.9
+210.4
+189.7
+195.6
+198.7
+193.0
+198.8
+193.1
+202.5
+195.2
+195.0
+198.3
+203.6
+208.3
+195.9
+200.8
+189.4
+207.9
+182.8
+194.9
+199.7
+180.7
+187.2
+189.5
+196.1
+190.1
+192.5
+185.7
+212.2
+204.2
+191.9
+184.5
+182.5
+198.5
+191.0
+192.0
+195.6
+201.1
+193.7
+203.8
+200.5
+199.1
+190.3
+209.5
+195.0
+184.0
+193.6
+203.3
+191.4
+194.9
+195.5
+193.5
+182.7
+189.7
+196.1
+178.9
+199.5
+195.3
+185.9
+199.1
+210.0
+195.7
+193.8
+196.4
+195.3
+201.4
+209.5
+205.6
+197.5
+188.9
+193.8
+185.3
+193.3
+198.1
+201.4
+184.7
+182.5
+183.7
+185.5
+199.8
+200.3
+194.1
+176.9
+192.2
+200.0
+186.4
+191.6
+200.1
+202.3
+205.1
+186.4
+182.3
+194.7
+177.5
+201.4
+189.6
+195.5
+185.4
+194.8
+204.1
+188.0
+182.1
+181.7
+184.5
+234.2
+209.4
+193.3
+204.0
+184.7
+194.3
+193.4
+191.1
+188.3
+193.9
+198.2
+202.8
+198.1
+191.2
+200.9
+205.4
+203.6
+193.8
+215.8
+185.8
+195.4
+204.7
+190.3
+190.7
+177.7
+182.1
+193.2
+178.3
+199.3
+203.5
+187.3
+198.8
+187.8
+187.7
+186.7
+200.0
+190.0
+203.1
+181.7
+207.2
+183.8
+180.3
+193.5
+190.2
+193.7
+198.6
+195.6
+192.1
+200.5
+188.6
+190.9
+188.0
+192.8
+191.4
+179.9
+197.6
+200.6
+206.1
+201.3
+199.6
+198.8
+201.0
+180.2
+202.9
+197.3
+186.1
+200.5
+182.4
+192.7
+194.5
+182.8
+193.9
+195.1
+187.7
+201.0
+196.1
+194.0
+198.8
+192.8
+186.1
+200.6
+186.3
+187.6
+178.0
+175.8
+198.9
+199.3
+193.4
+193.3
+198.7
+194.5
+180.9
+197.3
+189.7
+193.0
+208.2
+200.1
+193.9
+211.2
+206.6
+210.2
+185.5
+180.8
+206.8
+185.5
+195.8
+199.3
+187.9
+194.9
+175.8
+198.1
+199.0
+200.6
+300.8
+194.0
+199.7
+181.2
+189.9
+195.3
+209.6
+198.1
+184.9
+192.5
+188.8
+193.8
+201.4
+208.2
+192.5
+199.9
+185.0
+207.5
+196.5
+198.8
+193.3
+200.1
+186.7
+194.4
+194.3
+197.2
+198.4
+192.8
+194.3
+188.6
+194.7
+190.7
+192.1
+194.5
+185.7
+194.6
+177.5
+203.6
+180.8
+185.0
+178.9
+205.7
+187.4
+185.9
+192.9
+182.7
+197.3
+198.0
+194.5
+194.7
+194.7
+198.2
+184.7
+199.0
+200.9
+195.4
+198.7
+188.1
+187.5
+190.6
+179.2
+190.2
+195.9
+188.8
+205.7
+191.9
+204.0
+193.3
+199.5
+200.7
+179.3
+190.4
+206.4
+199.8
+189.5
+194.1
+203.3
+196.9
+200.1
+179.6
+217.2
+199.0
+184.0
+177.4
+200.5
+205.3
+193.2
+198.8
+187.2
+191.2
+186.6
+188.3
+199.4
+192.8
+209.8
+181.5
+192.8
+176.0
+189.9
+203.5
+192.5
+193.1
+190.3
+193.1
+203.0
+194.6
+188.4
+199.8
+199.6
+195.0
+200.3
+195.5
+198.5
+203.1
+193.4
+203.6
+195.6
+186.2
+206.4
+197.3
+265.4
+203.7
+205.7
+197.0
+194.9
+193.6
+201.1
+200.6
+197.1
+196.0
+196.3
+195.4
+194.2
+198.4
+202.6
+197.1
+209.4
+204.7
+195.9
+192.8
+203.4
+193.3
+188.5
+190.7
+190.3
+197.6
+197.7
+199.1
+193.0
+198.3
+205.0
+191.4
+197.2
+201.3
+197.6
+197.7
+202.9
+203.4
+198.5
+198.8
+205.4
+194.6
+189.5
+193.3
+190.4
+193.0
+202.5
+198.2
+194.7
+198.5
+184.3
+187.8
+193.3
+190.8
+194.9
+190.3
+201.8
+192.9
+198.5
+195.9
+195.8
+210.1
+194.2
+202.6
+194.5
+197.6
+200.1
+191.8
+192.8
+199.4
+199.7
+199.3
+194.2
+196.9
+195.7
+189.9
+197.1
+205.9
+191.1
+196.5
+200.9
+200.6
+199.1
+203.0
+204.2
+198.7
+192.2
+194.9
+188.6
+194.3
+198.5
+190.6
+189.4
+205.8
+207.0
+200.9
+198.0
+196.9
+196.6
+187.3
+199.9
+196.1
+196.5
+200.0
+186.0
+182.7
+193.3
+195.2
+190.0
+195.9
+190.0
+201.7
+187.1
+199.1
+203.5
+191.8
+199.5
+195.1
+207.3
+205.6
+191.9
+200.1
+196.5
+205.4
+190.8
+195.9
+194.6
+190.2
+197.4
+204.4
+210.5
+289.6
+197.2
+191.4
+199.2
+196.6
+201.4
+191.7
+194.4
+191.9
+193.1
+182.9
+191.5
+202.0
+186.8
+195.5
+193.4
+189.8
+181.3
+199.9
+200.3
+193.5
+196.5
+190.5
+200.6
+209.8
+197.7
+199.5
+200.9
+205.0
+199.4
+206.3
+205.7
+202.7
+189.0
+203.6
+198.9
+188.4
+193.7
+204.1
+198.4
+208.8
+201.4
+198.0
+188.7
+208.9
+196.9
+235.5
+198.1
+202.8
+195.8
+193.2
+203.0
+204.2
+201.2
+201.4
+202.8
+213.8
+197.2
+197.0
+191.2
+196.2
+210.8
+203.5
+193.4
+211.7
+194.0
+204.6
+197.0
+200.0
+197.9
+204.2
+196.6
+184.4
+188.6
+194.4
+188.1
+202.4
+203.0
+204.4
+194.1
+195.8
+195.3
+201.9
+194.7
+205.8
+201.9
+208.6
+195.5
+209.5
+194.8
+202.7
+202.2
+204.4
+197.1
+205.9
+196.2
+197.1
+197.4
+198.6
+198.8
+201.1
+203.9
+200.3
+199.5
+224.5
+199.2
+196.2
+197.7
+194.7
+194.1
+202.5
+191.2
+203.1
+199.1
+197.5
+201.0
+198.7
+207.9
+191.7
+192.1
+191.7
+208.7
+178.3
+202.0
+200.4
+202.1
+206.8
+194.2
+197.0
+203.3
+195.1
+210.0
+193.9
+191.1
+200.1
+192.9
+202.3
+189.5
+193.9
+200.8
+205.5
+198.7
+205.4
+184.7
+198.6
+189.7
+187.8
+202.5
+196.2
+203.5
+213.4
+199.7
+207.5
+207.3
+204.7
+190.5
+194.9
+184.7
+198.0
+200.9
+189.8
+208.9
+189.5
+218.6
+202.8
+189.0
+202.2
+204.3
+191.5
+193.6
+201.6
+204.6
+197.0
+200.9
+186.0
+205.9
+194.1
+203.3
+197.3
+200.3
+195.9
+207.3
+206.7
+206.7
+193.0
+203.1
+238.1
+192.2
+193.3
+197.4
+212.3
+202.5
+197.5
+204.1
+196.6
+183.8
+204.5
+188.1
+217.6
+194.5
+199.1
+210.9
+200.9
+187.7
+199.2
+195.0
+191.0
+198.3
+194.1
+191.9
+213.8
+199.0
+201.8
+197.5
+201.5
+195.6
+207.5
+200.6
+194.2
+210.5
+192.7
+188.1
+203.0
+237.1
+204.7
+205.1
+205.2
+200.3
+188.5
+202.2
+213.1
+195.0
+201.4
+204.2
+195.9
+186.5
+192.2
+206.5
+177.5
+189.9
+192.0
+214.9
+204.0
+194.2
+200.9
+197.1
+200.0
+196.4
+197.2
+189.0
+194.3
+206.5
+192.5
+190.5
+204.1
+196.7
+194.4
+181.9
+193.0
+190.6
+193.6
+178.0
+178.2
+200.9
+189.5
+194.2
+182.1
+183.6
+183.7
+176.9
+181.7
+194.9
+190.7
+187.4
+178.6
+182.0
+186.5
+183.7
+182.1
+186.2
+199.6
+192.4
+189.2
+194.7
+176.3
+184.6
+203.2
+201.9
+195.2
+192.7
+186.7
+195.2
+187.0
+201.1
+202.1
+187.7
+195.9
+181.7
+189.7
+179.9
+177.3
+180.3
+198.3
+184.6
+183.3
+196.9
+178.6
+184.3
+185.3
+183.2
+193.9
+194.7
+195.5
+199.6
+192.0
+189.4
+195.0
+193.6
+200.5
+177.6
+181.0
+200.0
+190.3
+189.7
+205.5
+178.5
+201.7
+192.7
+196.8
+189.2
+177.6
+198.0
+191.8
+178.6
+206.8
+190.0
+192.3
+180.1
+194.6
+179.7
+207.1
+195.6
+200.5
+186.7
+190.1
+178.6
+205.7
+346.2
+188.8
+204.4
+200.7
+176.5
+193.8
+195.9
+193.0
+186.5
+189.5
+190.6
+178.0
+188.6
+186.7
+180.9
+193.8
+194.0
+180.6
+196.7
+178.7
+180.1
+187.7
+179.6
+201.3
+219.2
+184.0
+206.3
+186.7
+192.0
+179.4
+190.1
+187.0
+191.6
+194.7
+195.5
+194.2
+195.8
+200.6
+180.3
+195.6
+209.9
+197.2
+201.1
+196.9
+186.3
+202.7
+182.7
+200.4
+201.2
+196.2
+181.1
+182.6
+187.2
+225.3
+186.8
+197.6
+192.0
+185.0
+199.8
+191.7
+187.4
+192.5
+189.1
+210.9
+187.0
+191.2
+190.9
+207.1
+198.7
+208.8
+190.6
+193.7
+186.5
+182.9
+178.7
+194.1
+184.3
+194.0
+185.4
+215.7
+194.6
+207.9
+204.7
+183.7
+189.3
+196.0
+202.6
+206.2
+190.1
+216.6
+179.8
+206.9
+188.4
+190.8
+181.7
+197.7
+195.7
+178.3
+179.0
+179.3
+203.2
+178.4
+180.1
+175.7
+194.1
+193.0
+203.2
+192.6
+194.0
+190.7
+193.0
+194.2
+183.7
+197.2
+188.4
+176.1
+184.3
+192.2
+195.7
+186.0
+193.7
+196.2
+183.7
+180.7
+181.0
+189.4
+199.3
+201.5
+199.8
+197.2
+201.7
+199.9
+192.2
+188.2
+187.5
+176.6
+205.3
+199.0
+190.0
+202.4
+201.8
+216.8
+208.2
+197.4
+194.3
+205.9
+179.0
+193.5
+182.9
+188.0
+198.3
+197.7
+177.6
+183.8
+182.3
+198.8
+192.5
+183.2
+208.4
+192.4
+193.8
+198.6
+196.2
+183.9
+186.2
+197.8
+180.6
+204.7
+195.3
+182.8
+192.5
+216.3
+203.8
+197.4
+179.5
+188.5
+196.8
+194.4
+189.2
+199.8
+200.7
+205.1
+183.4
+181.5
+193.6
+207.9
+177.4
+191.5
+197.3
+189.8
+191.9
+189.5
+201.2
+211.0
+201.4
+205.5
+201.1
+199.3
+193.5
+203.5
+191.6
+194.0
+196.7
+188.5
+189.8
+195.9
+181.1
+193.2
+197.2
+201.0
+186.2
+200.9
+183.5
+183.0
+207.9
+189.7
+193.8
+182.9
+232.1
+186.2
+200.3
+194.6
+184.2
+192.2
+182.9
+193.6
+207.4
+203.3
+185.6
+197.6
+205.9
+193.0
+182.3
+190.1
+193.3
+200.2
+183.9
+195.7
+186.9
+200.1
+189.6
+194.2
+195.5
+178.3
+183.9
+183.0
+179.2
+209.8
+199.6
+185.4
+210.9
+188.6
+188.9
+185.4
+177.0
+183.0
+186.1
+191.7
+190.7
+192.1
+195.2
+185.0
+186.6
+194.2
+189.5
+187.7
+187.9
+191.8
+181.1
+180.2
+180.0
+185.6
+181.8
+187.9
+192.9
+198.7
+182.0
+182.7
+175.8
+202.0
+190.6
+195.3
+191.0
+201.4
+194.3
+179.5
+185.0
+240.3
+187.1
+197.8
+204.8
+210.7
+203.2
+202.0
+197.8
+203.5
+205.1
+190.0
+190.3
+204.1
+197.9
+198.6
+199.3
+182.1
+200.8
+196.0
+197.1
+203.5
+198.6
+200.7
+201.1
+189.1
+175.8
+199.9
+203.7
+192.2
+182.5
+185.0
+195.9
+204.1
+197.0
+195.5
+202.0
+201.5
+187.1
+186.7
+198.2
+211.8
+197.6
+178.5
+198.5
+196.4
+188.1
+185.0
+199.5
+200.9
+201.7
+193.5
+188.3
+180.9
+190.6
+202.8
+183.9
+190.1
+205.3
+198.6
+183.2
+198.0
+200.9
+198.8
+194.8
+198.3
+195.8
+204.6
+202.6
+207.0
+185.9
+201.9
+195.9
+207.6
+197.4
+206.7
+188.2
+184.7
+183.9
+198.3
+186.4
+191.0
+208.8
+209.4
+187.7
+208.0
+198.4
+191.9
+187.1
+188.5
+189.2
+190.7
+179.9
+204.1
+195.5
+183.7
+183.1
+183.7
+194.6
+187.9
+183.5
+184.7
+203.2
+197.8
+179.4
+185.8
+205.3
+179.8
+194.8
+186.7
+191.5
+197.4
+197.0
+209.2
+194.1
+187.8
+192.9
+202.2
+194.4
+206.6
+191.6
+190.8
+187.5
+193.5
+205.2
+185.1
+185.6
+189.9
+196.0
+203.6
+195.4
+209.9
+196.5
+200.8
+190.1
+191.5
+232.8
+209.2
+193.1
+183.4
+199.5
+187.2
+199.4
+203.6
+198.3
+204.1
+196.4
+202.0
+180.6
+191.6
+202.9
+184.9
+180.8
+192.3
+205.2
+205.5
+179.0
+183.3
+203.1
+184.1
+188.6
+180.9
+195.8
+195.0
+181.1
+198.3
+190.7
+191.8
+192.1
+191.5
+257.4
+197.3
+206.5
+213.4
+184.2
+193.5
+208.6
+209.8
+192.0
+201.5
+198.6
+205.2
+198.9
+212.6
+195.9
+213.7
+215.9
+209.2
+215.2
+207.4
+208.9
+192.2
+192.3
+193.8
+185.1
+206.0
+179.1
+199.9
+198.3
+201.6
+186.8
+202.3
+190.4
+183.6
+191.8
+190.6
+194.7
+184.1
+184.4
+193.8
+194.0
+195.6
+204.5
+194.9
+196.1
+201.1
+196.1
+210.9
+198.7
+192.1
+208.3
+192.8
+193.6
+205.1
+191.5
+190.7
+179.2
+191.6
+192.1
+182.3
+176.1
+185.5
+187.1
+183.4
+191.9
+176.1
+178.0
+185.2
+191.3
+181.3
+178.1
+181.7
+200.3
+187.5
+201.6
+192.3
+177.7
+180.6
+192.9
+185.4
+183.1
+178.4
+196.9
+191.9
+186.1
+195.7
+177.7
+184.1
+195.4
+184.2
+188.8
+179.6
+182.0
+182.9
+185.1
+183.8
+189.3
+216.9
+196.6
+185.7
+235.5
+184.9
+181.8
+180.0
+186.6
+188.4
+190.7
+185.4
+210.9
+184.1
+203.0
+203.5
+198.9
+204.2
+199.7
+182.1
+178.1
+205.1
+179.4
+184.5
+180.7
+200.5
+197.3
+178.2
+178.8
+180.9
+219.2
+180.2
+192.5
+198.6
+238.0
+201.1
+182.4
+203.3
+182.0
+188.9
+201.2
+184.6
+182.7
+187.7
+188.5
+202.5
+199.8
+189.4
+191.1
+181.2
+191.7
+194.6
+181.3
+185.3
+192.8
+182.4
+191.6
+188.3
+202.6
+212.1
+179.6
+185.9
+183.4
+187.8
+184.4
+186.8
+197.0
+191.3
+186.7
+201.9
+187.2
+195.7
+178.5
+187.3
+190.8
+198.4
+198.8
+189.1
+189.6
+197.6
+201.0
+185.0
+182.2
+184.2
+193.2
+191.6
+187.4
+196.3
+190.7
+184.5
+206.1
+200.7
+193.0
+196.2
+195.1
+177.1
+180.7
+187.3
+188.3
+181.5
+180.7
+216.9
+185.7
+196.1
+193.2
+185.5
+186.9
+190.4
+189.7
+196.1
+193.9
+193.6
+185.7
+190.3
+199.8
+190.4
+187.4
+195.5
+190.0
+188.7
+190.2
+195.6
+195.2
+184.7
+186.9
+187.4
+179.3
+184.7
+206.7
+194.3
+198.9
+179.0
+185.7
+185.2
+206.7
+184.3
+202.8
+183.5
+178.9
+238.3
+181.1
+189.5
+176.7
+178.7
+183.4
+180.3
+192.4
+193.6
+186.6
+190.0
+184.0
+188.5
+188.6
+196.3
+182.2
+191.9
+191.1
+197.7
+188.4
+194.2
+201.7
+204.3
+199.6
+190.7
+183.0
+189.9
+192.9
+187.6
+182.8
+203.3
+189.3
+194.0
+189.4
+188.0
+194.4
+211.7
+186.3
+185.3
+187.2
+182.9
+194.9
+187.4
+190.4
+197.5
+184.5
+184.8
+180.0
+197.9
+205.9
+189.2
+196.5
+188.1
+185.4
+195.5
+185.0
+203.1
+188.6
+202.3
+180.6
+191.3
+204.4
+208.2
+189.2
+226.9
+200.0
+178.8
+181.5
+197.7
+204.1
+184.8
+178.5
+186.5
+190.9
+190.4
+181.4
+189.8
+179.2
+189.8
+179.6
+203.8
+205.4
+184.2
+192.8
+204.7
+186.6
+195.5
+203.7
+197.2
+178.0
+180.3
+187.0
+179.1
+187.5
+187.9
+183.4
+181.8
+184.1
+181.3
+184.0
+180.6
+230.8
+193.0
+190.5
+200.4
+187.9
+175.9
+204.2
+206.5
+183.2
+194.2
+187.2
+200.2
+189.6
+188.6
+188.6
+175.4
+184.2
+174.0
+177.2
+180.6
+181.5
+182.3
+187.1
+180.0
+184.7
+179.3
+195.7
+180.5
+179.5
+184.8
+204.0
+202.1
+178.7
+189.4
+196.4
+190.8
+184.3
+189.2
+182.8
+184.6
+178.4
+183.9
+185.0
+184.6
+179.2
+179.0
+182.4
+197.0
+188.4
+188.5
+196.0
+179.6
+188.1
+180.3
+196.1
+189.0
+178.4
+176.5
+186.4
+179.3
+187.7
+187.9
+184.8
+176.9
+188.7
+182.8
+192.3
+190.0
+197.2
+191.6
+197.8
+182.3
+184.2
+187.3
+188.2
+207.3
+189.2
+190.7
+202.3
+191.7
+195.4
+196.2
+190.1
+204.2
+194.8
+187.8
+209.1
+192.1
+193.1
+199.3
+192.1
+204.9
+190.8
+186.5
+189.3
+181.9
+193.3
+182.4
+195.2
+189.1
+196.8
+200.8
+187.6
+201.1
+197.0
+196.6
+177.7
+188.9
+186.2
+186.0
+199.9
+203.8
+190.2
+190.2
+186.3
+179.1
+198.8
+186.3
+192.4
+201.5
+190.2
+191.0
+178.0
+194.1
+197.9
+189.9
+180.2
+176.2
+193.5
+201.9
+201.3
+200.7
+190.3
+198.4
+186.0
+190.2
+182.7
+186.0
+190.0
+196.8
+193.0
+201.5
+184.7
+187.7
+190.8
+187.2
+183.5
+178.1
+178.9
+195.8
+178.2
+188.0
+177.2
+182.5
+184.2
+180.7
+189.6
+203.4
+181.7
+185.1
+177.5
+180.9
+194.0
+190.1
+190.1
+182.9
+184.4
+201.8
+191.1
+184.9
+197.7
+193.3
+190.3
+197.2
+188.2
+191.5
+190.0
+188.0
+187.5
+182.5
+186.6
+183.6
+193.9
+187.5
+186.9
+197.3
+187.2
+177.2
+186.8
+191.9
+186.9
+198.7
+179.7
+191.7
+193.6
+184.2
+178.4
+187.4
+203.3
+196.8
+195.4
+182.9
+187.7
+189.4
+192.5
+190.0
+190.0
+185.4
+194.6
+183.7
+180.2
+199.6
+190.5
+205.9
+176.4
+182.8
+179.0
+199.9
+186.7
+188.8
+189.5
+189.8
+193.5
+203.0
+183.8
+204.2
+176.4
+206.5
+184.7
+174.9
+183.2
+174.4
+196.2
+179.1
+183.7
+180.2
+174.5
+185.5
+203.5
+174.7
+186.1
+175.1
+198.2
+200.3
+184.2
+180.4
+187.9
+194.3
+194.9
+181.3
+180.2
+186.0
+187.6
+180.2
+188.1
+196.5
+175.9
+184.0
+194.4
+186.3
+207.6
+188.1
+185.2
+207.5
+177.7
+204.2
+203.3
+180.8
+176.0
+181.5
+202.3
+191.6
+186.8
+183.0
+189.7
+191.2
+179.2
+196.2
+185.9
+184.3
+183.3
+186.8
+179.3
+188.6
+184.8
+176.7
+189.6
+177.5
+186.3
+197.2
+178.1
+189.8
+175.8
+178.9
+191.9
+176.9
+186.8
+186.6
+194.1
+179.3
+178.7
+183.9
+220.3
+181.6
+183.7
+196.7
+180.2
+176.9
+189.5
+187.5
+185.8
+184.3
+179.9
+186.0
+178.5
+179.5
+227.6
+187.1
+199.2
+183.4
+177.2
+181.3
+190.7
+197.8
+180.1
+203.4
+198.1
+196.8
+184.3
+188.5
+189.6
+187.9
+200.7
+187.1
+193.3
+183.0
+199.1
+187.3
+181.8
+184.0
+178.0
+198.7
+177.4
+195.6
+184.1
+183.4
+186.0
+183.1
+181.8
+190.6
+188.8
+184.8
+196.5
+186.2
+184.7
+182.6
+187.4
+194.1
+185.3
+181.6
+198.4
+190.1
+200.2
+214.9
+195.1
+192.9
+190.8
+179.4
+194.9
+206.0
+193.2
+186.6
+214.1
+216.1
+189.0
+184.2
+201.1
+182.1
+200.2
+188.5
+193.0
+184.8
+188.8
+186.6
+188.3
+193.9
+202.4
+196.8
+214.5
+202.1
+186.7
+197.3
+184.2
+186.5
+202.6
+187.3
+204.3
+176.1
+183.9
+189.2
+189.7
+180.8
+199.4
+185.7
+193.3
+192.7
+192.8
+204.9
+188.7
+196.5
+187.9
+177.4
+189.6
+177.2
+197.3
+183.9
+189.7
+184.6
+191.0
+195.4
+175.7
+179.1
+184.4
+193.2
+180.4
+191.2
+187.2
+181.1
+203.5
+189.2
+186.4
+176.3
+191.5
+193.6
+187.0
+186.8
+187.3
+184.8
+197.6
+207.3
+191.8
+187.1
+196.3
+206.9
+199.9
+186.3
+189.9
+179.8
+200.0
+193.8
+190.9
+180.9
+176.3
+189.1
+180.4
+190.9
+182.4
+182.8
+181.1
+193.9
+184.0
+185.9
+199.1
+199.5
+204.2
+181.9
+199.0
+184.1
+207.4
+194.8
+216.5
+188.4
+206.7
+199.2
+179.3
+186.7
+200.7
+186.3
+195.5
+204.9
+194.0
+187.5
+196.3
+181.4
+186.0
+197.8
+198.1
+196.1
+184.3
+183.3
+211.3
+192.8
+187.9
+183.4
+192.9
+187.4
+194.2
+177.1
+200.0
+199.3
+177.2
+180.1
+178.6
+182.3
+189.1
+191.3
+197.7
+187.6
+187.3
+203.9
+204.4
+180.4
+186.5
+188.4
+176.1
+206.5
+187.7
+194.1
+193.5
+203.7
+186.8
+200.1
+187.0
+203.3
+196.3
+208.1
+192.7
+202.1
+204.7
+183.9
+186.7
+198.2
+189.4
+186.4
+188.3
+195.2
+203.3
+202.3
+201.1
+180.1
+191.3
+180.4
+187.7
+193.4
+196.5
+208.8
+185.3
+186.8
+203.6
+179.0
+185.0
+181.1
+193.8
+196.9
+201.0
+187.3
+189.6
+190.8
+188.9
+197.6
+203.0
+193.2
+185.6
+195.6
+199.1
+191.8
+178.7
+183.6
+184.1
+192.0
+182.4
+183.8
+209.5
+205.7
+187.0
+187.6
+200.6
+187.1
+187.2
+184.9
+180.3
+189.4
+182.7
+196.8
+184.7
+185.8
+184.0
+194.1
+180.5
+199.1
+181.7
+205.3
+182.6
+186.8
+180.2
+181.9
+187.4
+187.9
+191.8
+204.8
+178.5
+181.6
+181.6
+179.5
+181.9
+190.1
+194.1
+180.0
+179.1
+181.2
+175.0
+186.3
+184.8
+182.6
+186.8
+185.3
+181.2
+190.0
+195.3
+186.9
+190.6
+187.3
+193.4
+176.9
+190.5
+194.6
+181.0
+175.8
+187.9
+183.2
+187.7
+191.4
+183.1
+178.6
+193.4
+185.5
+190.1
+194.6
+191.0
+177.7
+187.3
+201.3
+188.6
+182.5
+196.3
+176.2
+184.9
+189.6
+186.9
+227.9
+188.1
+185.0
+182.9
+196.4
+183.1
+179.8
+186.5
+185.2
+199.7
+187.7
+191.6
+191.9
+194.8
+183.9
+185.3
+188.2
+192.7
+180.8
+183.5
+199.8
+196.8
+184.2
+179.5
+204.2
+183.5
+175.4
+207.3
+192.5
+191.9
+208.6
+194.7
+195.2
+190.3
+180.8
+182.6
+203.2
+191.4
+189.7
+183.9
+185.7
+192.3
+190.7
+206.8
+182.9
+195.2
+193.1
+201.2
+177.0
+188.1
+182.3
+185.0
+198.5
+186.4
+183.9
+189.4
+181.8
+199.9
+198.7
+183.7
+191.8
+187.5
+209.4
+201.8
+178.0
+201.8
+198.0
+187.2
+185.5
+178.1
+195.7
+200.1
+174.8
+176.4
+187.6
+177.3
+178.1
+197.5
+183.7
+207.7
+180.6
+176.6
+190.8
+191.0
+180.1
+180.4
+178.8
+185.5
+194.8
+188.1
+185.8
+179.5
+181.0
+196.1
+192.6
+179.2
+180.7
+206.3
+175.9
+196.8
+179.4
+195.1
+187.5
+183.9
+183.8
+184.6
+208.6
+195.5
+202.9
+191.9
+187.0
+189.2
+178.5
+176.1
+186.6
+195.1
+181.6
+201.0
+192.1
+192.9
+202.2
+191.0
+205.8
+204.3
+191.8
+185.1
+190.1
+193.6
+192.4
+185.2
+180.6
+192.6
+185.7
+187.5
+189.2
+184.0
+189.1
+200.6
+185.2
+182.8
+182.0
+185.4
+178.3
+188.4
+193.2
+194.9
+197.1
+194.4
+184.8
+179.2
+195.6
+182.6
+204.3
+203.1
+180.0
+187.7
+187.7
+197.8
+178.7
+186.5
+194.6
+194.8
+176.4
+202.5
+195.4
+180.5
+220.0
+191.0
+217.1
+178.4
+196.1
+182.5
+190.8
+191.7
+202.0
+196.8
+199.4
+183.8
+183.2
+186.5
+178.1
+198.6
+186.1
+195.4
+196.6
+199.3
+196.5
+177.9
+186.3
+180.5
+198.9
+190.2
+188.5
+184.1
+188.6
+201.4
+185.4
+176.4
+182.0
+176.9
+184.4
+179.0
+178.4
+183.8
+190.9
+185.5
+184.4
+179.6
+197.5
+184.3
+179.1
+193.4
+194.2
+179.1
+189.0
+191.2
+180.8
+184.5
+187.9
+191.7
+177.2
+185.4
+183.6
+190.7
+187.5
+188.8
+199.7
+190.0
+176.0
+204.4
+191.1
+188.3
+182.1
+181.6
+191.4
+191.8
+193.1
+186.0
+188.1
+178.4
+193.7
+175.1
+179.0
+186.7
+185.3
+179.7
+182.7
+198.0
+180.2
+189.5
+183.1
+177.1
+182.3
+174.7
+175.6
+186.4
+189.2
+178.9
+180.4
+181.3
+182.3
+180.3
+180.8
+180.1
+197.2
+204.7
+181.6
+182.3
+184.0
+176.5
+214.9
+194.7
+178.3
+175.1
+174.3
+176.5
+190.9
+183.1
+176.8
+177.1
+183.8
+178.5
+189.2
+180.8
+177.6
+175.3
+185.3
+183.4
+175.2
+183.6
+177.0
+181.9
+180.3
+185.1
+179.1
+188.1
+184.4
+181.6
+188.0
+181.6
+190.6
+177.9
+182.7
+177.4
+183.2
+189.3
+187.6
+179.8
+192.3
+188.1
+194.6
+186.7
+181.6
+191.8
+195.6
+187.4
+185.5
+190.0
+184.0
+178.5
+178.0
+200.8
+199.2
+186.5
+174.9
+181.3
+181.0
+187.6
+186.8
+183.3
+183.8
+195.6
+190.6
+193.8
+176.4
+179.1
+182.9
+193.4
+184.4
+186.2
+180.3
+194.7
+182.6
+186.7
+196.4
+196.7
+196.2
+192.3
+189.1
+178.4
+182.3
+195.2
+184.1
+189.0
+184.7
+189.3
+184.1
+177.3
+189.5
+186.1
+186.4
+180.5
+196.1
+187.5
+188.4
+195.8
+192.0
+192.9
+182.4
+199.6
+189.6
+180.2
+176.1
+220.4
+206.6
+195.5
+176.5
+202.2
+187.5
+185.0
+205.6
+195.7
+192.8
+192.8
+174.9
+187.3
+181.9
+180.4
+183.9
+187.6
+192.5
+202.1
+185.2
+200.2
+184.1
+189.9
+194.7
+185.1
+191.9
+176.0
+197.7
+177.5
+178.6
+179.3
+206.0
+193.3
+196.2
+179.3
+181.3
+205.5
+178.1
+186.9
+183.5
+178.5
+193.1
+179.4
+186.1
+174.3
+194.4
+187.1
+195.8
+176.0
+187.6
+176.1
+183.7
+182.0
+183.7
+176.3
+201.0
+185.8
+180.6
+186.1
+180.1
+204.4
+186.1
+182.9
+181.7
+184.6
+177.3
+186.2
+188.7
+180.5
+182.1
+185.3
+177.7
+185.4
+188.2
+194.1
+185.6
+177.8
+192.7
+198.1
+196.0
+187.5
+186.4
+206.8
+207.4
+177.3
+181.3
+185.0
+175.7
+174.2
+191.5
+194.0
+190.8
+199.2
+176.4
+202.7
+193.1
+182.6
+186.0
+196.0
+186.1
+189.4
+203.4
+184.8
+194.3
+187.2
+183.5
+199.4
+196.7
+180.2
+195.2
+180.9
+182.7
+193.5
+200.0
+193.3
+184.4
+199.1
+206.2
+199.0
+195.8
+189.4
+194.1
+196.4
+201.5
+180.7
+189.7
+193.3
+200.3
+205.5
+189.9
+192.6
+187.1
+205.7
+194.9
+188.0
+189.2
+197.9
+188.5
+185.0
+182.7
+205.8
+186.7
+189.2
+185.1
+182.4
+205.1
+181.4
+185.6
+188.5
+195.9
+199.8
+185.4
+194.7
+201.2
+185.0
+202.1
+200.0
+181.9
+186.8
+195.9
+182.2
+186.6
+187.1
+184.9
+181.1
+190.1
+191.0
+186.7
+184.6
+181.8
+190.4
+185.7
+183.4
+187.0
+182.6
+183.5
+173.9
+181.8
+194.1
+182.2
+182.6
+181.8
+187.0
+192.2
+178.9
+206.9
+197.1
+180.7
+183.4
+176.7
+187.9
+194.5
+182.0
+182.0
+190.9
+177.9
+180.3
+190.8
+187.7
+179.1
+187.9
+183.7
+187.9
+183.5
+175.9
+186.5
+178.2
+180.7
+194.3
+184.8
+181.4
+182.8
+179.8
+187.0
+179.1
+178.8
+187.2
+185.9
+182.0
+187.7
+181.3
+186.0
+181.0
+183.2
+186.5
+189.3
+187.8
+182.8
+179.4
+199.0
+180.9
+193.8
+202.6
+185.8
+177.5
+182.7
+202.4
+213.8
+190.6
+189.8
+190.5
+185.0
+183.7
+191.0
+185.7
+182.2
+194.8
+183.1
+191.8
+186.6
+185.2
+181.7
+182.1
+185.7
+195.0
+181.5
+185.1
+181.5
+187.3
+186.5
+188.7
+185.2
+180.7
+178.3
+191.8
+185.4
+188.6
+184.5
+187.5
+191.5
+191.5
+195.8
+197.9
+194.2
+184.9
+182.7
+182.1
+185.6
+188.4
+178.8
+190.4
+179.3
+186.2
+206.0
+191.2
+195.1
+198.4
+189.9
+180.8
+181.1
+198.5
+203.4
+190.8
+177.1
+184.0
+181.0
+192.2
+175.9
+200.4
+192.2
+181.1
+202.0
+198.6
+203.6
+191.7
+193.4
+192.6
+186.5
+182.4
+195.8
+184.9
+191.0
+176.7
+182.7
+194.8
+181.9
+191.1
+205.5
+176.3
+200.1
+184.1
+208.8
+184.3
+196.2
+190.2
+197.1
+186.8
+181.7
+188.5
+188.6
+187.2
+195.3
+198.6
+205.7
+185.4
+187.5
+176.2
+186.1
+199.4
+294.6
+232.7
+200.5
+181.8
+189.1
+186.9
+190.7
+179.7
+181.3
+181.5
+200.5
+181.2
+181.7
+185.4
+195.5
+201.9
+199.7
+194.2
+179.6
+181.4
+205.5
+183.1
+499.4
+188.5
+184.5
+194.5
+195.5
+193.6
+189.0
+196.4
+188.3
+186.7
+190.6
+176.9
+188.1
+189.4
+198.2
+178.8
+196.5
+203.1
+192.3
+193.8
+188.4
+180.2
+192.3
+187.1
+195.2
+181.6
+185.5
+190.9
+185.2
+200.5
+190.0
+180.2
+194.4
+196.5
+187.7
+184.3
+189.5
+188.2
+189.5
+194.5
+192.4
+202.1
+177.9
+193.8
+191.7
+182.2
+190.1
+197.4
+196.6
+193.7
+195.9
+200.9
+178.8
+181.4
+193.6
+193.5
+177.7
+192.9
+190.9
+201.2
+184.9
+175.8
+197.9
+202.4
+192.3
+202.5
+198.3
+196.8
+185.2
+184.8
+198.1
+191.3
+174.0
+180.5
+193.4
+183.0
+185.1
+177.0
+190.4
+181.3
+179.0
+180.6
+179.1
+188.8
+207.2
+183.7
+186.6
+198.3
+176.6
+186.5
+187.4
+179.5
+189.2
+197.7
+181.5
+194.6
+195.5
+181.6
+197.3
+190.7
+202.0
+183.9
+193.0
+183.9
+196.9
+203.5
+189.4
+187.1
+185.2
+184.8
+199.8
+175.7
+180.6
+187.6
+185.4
+178.5
+185.5
+178.7
+187.5
+185.7
+191.9
+180.2
+186.7
+183.0
+196.7
+197.6
+197.1
+187.4
+194.8
+194.7
+191.0
+185.1
+187.0
+185.8
+197.6
+204.2
+187.9
+189.9
+217.5
+202.8
+192.4
+176.4
+178.8
+199.8
+192.5
+199.9
+190.8
+202.8
+187.0
+180.2
+196.6
+176.5
+187.6
+181.3
+191.0
+180.6
+184.7
+195.8
+191.5
+182.7
+181.3
+189.3
+182.5
+184.2
+187.9
+202.4
+195.7
+189.5
+195.4
+201.2
+186.1
+208.8
+199.6
+189.4
+180.5
+194.2
+184.5
+187.5
+196.6
+188.0
+210.1
+193.3
+187.6
+191.6
+188.5
+179.2
+192.5
+189.7
+181.6
+180.9
+187.9
+180.6
+181.1
+178.7
+175.7
+176.2
+187.1
+185.0
+186.9
+186.5
+190.0
+185.6
+201.2
+189.3
+189.3
+189.7
+188.2
+187.2
+175.0
+185.5
+185.0
+205.2
+187.3
+177.2
+179.2
+190.2
+183.0
+192.9
+183.2
+185.4
+179.2
+186.2
+183.1
+183.8
+186.6
+185.7
+192.4
+179.6
+196.2
+180.2
+185.9
+197.4
+192.2
+177.5
+180.7
+190.2
+176.9
+193.6
+186.2
+184.9
+182.0
+186.1
+187.4
+184.3
+196.2
+203.1
+180.6
+192.5
+196.2
+195.9
+181.6
+189.9
+183.3
+192.7
+187.3
+191.0
+200.2
+180.1
+187.0
+175.7
+179.9
+193.1
+190.2
+202.1
+174.1
+179.5
+185.1
+182.7
+196.7
+179.8
+186.7
+192.5
+189.2
+193.7
+184.1
+185.6
+184.6
+193.6
+181.0
+189.2
+179.9
+181.4
+183.7
+184.5
+193.1
+191.5
+182.9
+190.2
+185.2
+185.9
+216.6
+184.1
+195.7
+181.2
+182.8
+199.3
+187.4
+184.9
+177.6
+206.2
+184.1
+201.5
+200.7
+192.2
+187.0
+182.1
+196.6
+181.6
+189.2
+191.6
+188.8
+186.9
+193.6
+184.2
+191.3
+194.9
+194.6
+188.7
+179.2
+205.1
+181.0
+177.3
+183.7
+184.8
+183.7
+204.3
+190.7
+181.6
+191.6
+189.5
+195.5
+176.0
+193.0
+192.1
+195.9
+205.8
+192.2
+190.6
+198.3
+185.8
+186.7
+198.6
+184.2
+203.1
+199.6
+187.0
+204.3
+207.2
+190.8
+196.7
+188.8
+193.2
+188.7
+199.8
+204.3
+188.6
+192.0
+209.8
+180.3
+203.7
+196.4
+185.7
+182.1
+193.3
+200.9
+196.6
+181.9
+182.2
+179.2
+197.3
+189.3
+200.9
+184.5
+185.8
+185.6
+187.5
+187.5
+189.5
+186.9
+187.2
+195.7
+182.0
+179.0
+191.4
+188.5
+177.7
+185.7
+182.0
+189.0
+198.7
+188.4
+186.6
+180.4
+185.1
+184.2
+207.6
+184.2
+190.0
+181.5
+190.9
+191.2
+187.8
+177.8
+182.7
+191.8
+206.2
+201.4
+182.2
+189.2
+195.4
+187.9
+195.7
+190.4
+183.3
+183.2
+178.2
+189.0
+179.2
+175.5
+187.3
+181.1
+180.1
+188.1
+184.4
+183.9
+200.2
+185.4
+180.4
+184.0
+183.8
+181.2
+203.6
+201.1
+197.1
+192.3
+182.7
+182.4
+183.0
+177.3
+181.3
+185.3
+184.6
+188.7
+179.1
+179.1
+184.6
+176.0
+177.8
+186.9
+189.8
+180.3
+177.2
+184.2
+179.2
+177.4
+182.0
+186.6
+188.7
+194.2
+184.0
+178.9
+175.3
+191.6
+182.9
+188.3
+178.7
+201.6
+186.4
+180.8
+184.7
+186.7
+196.9
+177.7
+178.8
+175.3
+182.7
+184.0
+182.4
+196.6
+174.7
+178.0
+181.5
+198.1
+185.1
+177.5
+181.2
+188.1
+196.0
+183.6
+196.2
+185.9
+193.2
+186.7
+179.7
+195.3
+190.1
+206.8
+186.2
+178.5
+192.0
+187.6
+176.9
+191.8
+190.8
+193.6
+200.0
+192.3
+178.0
+184.6
+179.4
+178.2
+183.2
+179.9
+184.9
+183.7
+189.1
+176.4
+185.5
+184.8
+192.5
+185.3
+193.9
+179.6
+181.7
+179.1
+210.8
+185.6
+184.2
+181.3
+198.8
+180.2
+182.5
+191.9
+196.4
+186.6
+185.3
+182.5
+175.8
+182.0
+186.9
+186.6
+176.0
+175.4
+186.5
+175.4
+182.4
+199.5
+192.7
+182.0
+199.9
+181.1
+196.7
+186.2
+182.0
+175.9
+184.4
+183.8
+178.4
+191.3
+177.8
+196.1
+200.8
+200.6
+191.1
+190.4
+180.3
+200.6
+201.4
+181.3
+176.9
+183.2
+185.0
+178.4
+187.8
+172.7
+182.8
+186.3
+193.9
+179.2
+194.9
+176.8
+188.1
+190.7
+192.3
+178.4
+191.9
+196.6
+183.5
+197.8
+192.0
+176.0
+192.1
+191.5
+193.3
+209.5
+185.2
+187.6
+186.3
+190.9
+183.9
+190.2
+186.3
+184.7
+177.3
+185.0
+178.3
+193.0
+181.7
+190.9
+185.3
+174.9
+192.3
+194.5
+194.1
+177.0
+185.2
+193.2
+202.4
+202.0
+197.2
+199.3
+176.9
+185.7
+188.1
+186.8
+184.4
+204.5
+196.4
+181.3
+190.9
+177.2
+192.4
+179.9
+177.0
+194.1
+203.5
+189.1
+194.7
+181.5
+183.6
+199.8
+187.3
+185.1
+195.7
+177.8
+178.3
+189.8
+200.1
+176.9
+177.9
+188.9
+190.9
+198.7
+197.7
+186.9
+190.8
+201.4
+188.5
+180.4
+196.2
+185.8
+194.9
+193.3
+181.3
+195.4
+197.5
+201.3
+179.5
+177.7
+201.9
+199.9
+183.5
+177.6
+190.4
+183.7
+178.4
+203.6
+195.9
+199.5
+193.2
+175.0
+184.5
+190.6
+194.3
+178.2
+177.5
+188.4
+179.7
+183.8
+174.2
+186.5
+179.8
+196.9
+194.9
+178.4
+185.7
+190.1
+181.3
+180.0
+179.9
+181.7
+187.4
+185.9
+178.9
+184.6
+189.5
+186.6
+185.8
+188.4
+188.3
+174.7
+184.9
+192.5
+185.3
+174.9
+180.6
+179.5
+183.4
+177.7
+177.5
+187.4
+183.7
+188.0
+177.6
+180.7
+180.9
+181.9
+188.9
+201.1
+186.6
+176.3
+177.3
+177.6
+175.6
+201.5
+175.5
+188.2
+181.8
+176.9
+185.3
+179.6
+192.7
+203.8
+183.4
+179.4
+177.9
+182.8
+182.3
+174.9
+180.5
+180.2
+187.1
+190.4
+185.5
+184.6
+185.4
+190.3
+183.9
+180.0
+201.8
+198.1
+184.2
+192.8
+184.2
+195.7
+191.4
+188.8
+192.9
+184.8
+174.3
+191.8
+185.4
+183.8
+192.7
+192.6
+194.8
+177.9
+178.7
+181.5
+177.3
+192.5
+176.0
+178.9
+199.7
+181.0
+178.8
+177.1
+183.0
+176.7
+182.3
+180.9
+183.1
+183.9
+174.2
+178.7
+173.8
+174.4
+179.1
+178.4
+175.4
+181.4
+180.9
+178.2
+182.5
+184.2
+183.7
+182.6
+176.2
+177.2
+180.5
+183.9
+193.4
+174.9
+178.8
+176.0
+178.1
+176.1
+177.3
+178.7
+182.2
+191.0
+186.8
+188.4
+180.3
+177.8
+198.8
+176.7
+198.3
+178.5
+177.9
+179.9
+186.7
+178.0
+175.4
+186.6
+190.8
+190.7
+183.5
+196.3
+182.1
+184.4
+188.8
+186.3
+184.8
+191.3
+186.2
+191.0
+188.3
+178.8
+176.3
+181.2
+183.1
+180.4
+178.6
+176.2
+176.1
+177.5
+180.6
+178.1
+176.4
+195.4
+178.8
+179.6
+178.1
+179.7
+178.3
+181.9
+177.4
+181.4
+186.7
+174.6
+179.4
+177.5
+197.6
+196.5
+193.1
+179.2
+182.2
+178.1
+186.3
+182.1
+175.4
+177.5
+188.1
+182.9
+179.8
+179.2
+180.0
+176.9
+177.4
+192.5
+177.5
+177.4
+181.8
+175.6
+178.9
+180.6
+176.8
+182.8
+186.7
+182.5
+188.3
+183.7
+185.1
+195.4
+179.2
+180.7
+190.0
+187.5
+180.3
+183.0
+184.2
+184.3
+189.4
+180.1
+179.6
+182.3
+177.6
+186.3
+188.0
+182.1
+187.1
+186.2
+184.2
+202.3
+187.0
+188.0
+180.5
+194.6
+188.8
+190.7
+181.9
+182.1
+185.3
+183.1
+197.3
+195.0
+208.3
+195.7
+179.1
+196.3
+185.5
+185.4
+186.9
+193.9
+187.1
+184.2
+180.0
+184.8
+189.6
+192.3
+185.6
+185.8
+185.9
+187.9
+186.2
+177.3
+192.2
+201.9
+185.9
+181.7
+192.8
+185.4
+187.3
+187.5
+178.9
+187.6
+181.3
+186.9
+179.6
+179.3
+189.4
+177.5
+184.5
+176.4
+193.3
+178.7
+191.6
+182.7
+194.6
+187.4
+190.4
+199.1
+191.6
+193.1
+187.0
+181.7
+180.3
+196.6
+180.5
+180.0
+184.9
+176.9
+176.3
+179.3
+189.1
+180.4
+176.0
+174.9
+181.2
+177.6
+177.4
+177.6
+179.0
+178.7
+178.7
+184.8
+177.9
+179.4
+183.8
+181.9
+177.1
+175.8
+182.9
+183.2
+176.8
+181.7
+183.7
+192.1
+178.2
+181.4
+180.0
+176.8
+179.8
+194.3
+181.6
+180.7
+177.5
+187.4
+179.0
+180.0
+186.0
+182.0
+175.4
+178.9
+181.9
+192.0
+179.5
+178.5
+175.3
+184.1
+178.3
+177.1
+186.2
+196.9
+182.0
+178.0
+181.4
+181.4
+179.6
+180.2
+180.4
+183.1
+176.6
+182.9
+176.3
+191.5
+179.9
+178.1
+178.4
+189.3
+196.8
+188.2
+180.5
+185.2
+188.0
+176.3
+181.0
+187.4
+178.9
+179.1
+185.3
+183.4
+185.8
+178.5
+176.1
+188.9
+200.9
+193.9
+193.4
+184.0
+187.2
+178.1
+193.5
+182.0
+180.1
+182.8
+176.8
+177.0
+184.0
+185.2
+197.3
+180.8
+190.4
+177.3
+183.4
+191.3
+175.4
+176.8
+192.3
+177.3
+191.1
+185.1
+179.7
+190.8
+175.9
+181.2
+194.0
+176.5
+180.3
+175.1
+185.1
+181.3
+200.0
+187.0
+182.6
+182.0
+176.8
+190.1
+182.1
+181.7
+192.3
+177.0
+185.1
+181.3
+179.2
+182.1
+176.6
+185.0
+177.4
+183.5
+196.5
+184.2
+179.2
+180.5
+180.8
+181.9
+176.9
+178.6
+175.9
+192.0
+198.7
+189.6
+190.5
+186.3
+192.6
+196.0
+176.2
+175.9
+176.5
+195.4
+174.8
+177.4
+186.7
+174.9
+176.1
+183.0
+178.1
+177.4
+192.9
+179.7
+198.5
+178.1
+178.6
+195.4
+181.6
+179.9
+179.5
+186.4
+180.6
+180.3
+187.3
+193.9
+192.5
+178.1
+184.8
+194.9
+194.6
+181.4
+177.6
+180.4
+175.5
+180.5
+177.2
+186.6
+176.8
+176.3
+186.0
+179.8
+178.2
+177.9
+178.9
+190.1
+180.8
+180.1
+181.3
+193.5
+185.0
+198.7
+199.9
+183.4
+177.3
+176.2
+182.7
+178.2
+175.2
+177.7
+186.9
+182.1
+195.1
+181.3
+182.4
+175.7
+185.5
+180.8
+181.4
+181.6
+190.1
+183.7
+186.4
+194.3
+176.4
+176.7
+189.9
+175.6
+206.6
+178.9
+180.0
+178.8
+180.1
+184.1
+176.3
+177.9
+194.3
+188.5
+182.6
+178.6
+177.5
+190.9
+178.9
+180.3
+193.9
+187.4
+186.4
+190.1
+184.7
+199.2
+187.9
+177.7
+180.5
+189.4
+176.5
+192.8
+181.4
+178.0
+193.6
+175.8
+184.4
+184.1
+191.9
+176.2
+184.5
+180.4
+185.1
+180.0
+192.6
+187.6
+190.2
+183.0
+176.5
+194.4
+178.4
+184.5
+176.6
+179.0
+182.6
+187.2
+180.4
+183.3
+180.8
+179.1
+193.9
+181.9
+188.8
+180.0
+175.2
+194.5
+194.8
+187.7
+182.5
+199.3
+175.0
+175.9
+177.9
+179.6
+179.4
+176.0
+176.4
+175.8
+177.2
+176.8
+179.0
+180.4
+177.1
+174.9
+177.9
+180.6
+187.3
+176.6
+177.3
+184.4
+179.2
+177.2
+175.7
+183.3
+177.4
+180.7
+175.6
+173.6
+179.6
+177.2
+180.8
+176.4
+187.7
+178.4
+176.0
+192.5
+181.4
+183.5
+178.5
+186.6
+179.4
+180.1
+181.6
+178.3
+178.2
+184.1
+180.6
+178.3
+184.1
+181.6
+177.4
+183.4
+180.6
+178.8
+179.0
+175.1
+177.0
+180.8
+179.9
+177.7
+176.3
+177.3
+184.2
+176.9
+190.8
+183.0
+181.0
+184.0
+178.6
+175.2
+177.2
+177.9
+183.2
+180.9
+176.3
+177.0
+182.8
+178.5
+176.9
+178.1
+175.5
+184.7
+176.6
+177.2
+182.4
+189.5
+197.3
+179.9
+190.4
+182.4
+188.7
+185.5
+181.1
+182.6
+187.0
+184.4
+179.1
+180.1
+180.9
+187.2
+175.9
+194.1
+177.9
+177.4
+200.7
+201.4
+183.5
+180.8
+195.5
+181.0
+180.2
+181.5
+175.9
+175.3
+180.1
+182.1
+180.1
+176.5
+178.9
+200.5
+178.6
+176.6
+175.8
+175.8
+176.0
+199.3
+177.5
+180.9
+185.1
+200.3
+194.0
+177.7
+181.2
+182.1
+185.1
+183.4
+180.7
+188.8
+187.3
+179.1
+177.5
+185.5
+185.5
+177.2
+175.3
+178.6
+184.5
+180.0
+179.9
+177.1
+178.0
+187.8
+183.6
+189.6
+181.5
+179.7
+179.0
+188.8
+185.1
+177.0
+177.1
+176.3
+176.4
+199.6
+178.1
+188.2
+176.9
+191.5
+194.0
+182.6
+184.0
+186.4
+184.1
+180.0
+181.1
+187.3
+176.1
+174.5
+189.3
+188.9
+178.7
+177.2
+191.0
+194.3
+187.7
+177.0
+176.4
+183.3
+176.2
+181.3
+181.0
+176.8
+187.8
+178.2
+202.3
+191.6
+180.3
+174.8
+187.8
+176.9
+176.9
+181.1
+177.5
+186.1
+179.3
+187.2
+176.6
+178.6
+178.7
+179.0
+188.7
+188.5
+183.8
+192.2
+178.8
+180.4
+182.1
+177.0
+175.1
+180.1
+176.7
+176.0
+188.1
+191.3
+186.6
+202.0
+182.5
+175.9
+182.1
+195.6
+174.8
+194.5
+181.2
+191.8
+180.4
+178.7
+186.1
+180.9
+186.4
+177.0
+183.6
+179.7
+208.1
+179.4
+179.1
+178.5
+179.2
+180.7
+183.3
+180.4
+187.6
+176.9
+185.4
+187.5
+184.3
+183.5
+181.0
+190.8
+178.6
+180.0
+180.4
+191.0
+182.8
+186.9
+179.6
+189.1
+186.9
+202.3
+181.1
+192.1
+194.3
+176.7
+185.8
+177.3
+179.5
+177.2
+177.8
+190.5
+190.1
+184.1
+191.8
+178.7
+185.9
+178.3
+177.4
+176.4
+177.8
+179.0
+177.6
+179.7
+178.1
+190.5
+177.8
+180.4
+181.6
+181.3
+177.3
+182.1
+189.7
+178.2
+179.7
+181.3
+178.8
+194.0
+200.6
+179.6
+177.9
+181.0
+184.7
+180.8
+181.1
+187.8
+183.4
+186.2
+181.8
+175.8
+176.8
+176.3
+177.0
+186.7
+178.5
+183.0
+177.1
+182.3
+182.2
+180.6
+180.6
+185.2
+178.9
+192.3
+177.6
+212.1
+180.5
+186.4
+187.4
+196.4
+181.9
+194.5
+188.5
+179.4
+179.3
+181.4
+185.7
+176.9
+182.6
+185.0
+181.7
+178.9
+184.4
+180.4
+189.2
+187.5
+204.6
+189.7
+182.6
+182.1
+180.0
+182.3
+180.1
+189.3
+178.1
+183.8
+180.9
+184.8
+182.2
+177.7
+176.1
+197.5
+195.8
+183.3
+183.4
+199.0
+205.4
+183.6
+182.5
+182.2
+199.1
+187.1
+179.5
+182.9
+180.2
+177.5
+183.4
+189.4
+196.2
+181.2
+183.3
+178.6
+181.5
+185.5
+179.8
+184.3
+198.8
+184.9
+178.0
+177.7
+181.0
+186.0
+196.3
+178.1
+192.4
+178.7
+181.4
+192.5
+181.4
+192.5
+182.2
+178.9
+183.9
+185.3
+192.2
+186.0
+193.4
+178.4
+194.5
+179.9
+187.6
+185.9
+179.2
+185.0
+188.1
+189.4
+187.9
+190.0
+191.9
+187.5
+186.0
+189.6
+182.4
+185.6
+187.0
+192.4
+183.3
+189.2
+194.6
+195.9
+190.7
+186.4
+185.9
+185.3
+177.1
+184.6
+186.4
+183.1
+186.2
+180.0
+181.8
+184.7
+176.6
+178.0
+178.5
+182.2
+200.3
+184.2
+186.9
+178.2
+190.3
+194.9
+193.1
+193.5
+188.5
+177.9
+185.4
+177.6
+179.7
+193.0
+200.3
+182.0
+192.3
+183.3
+183.6
+183.2
+190.8
+182.6
+177.7
+177.1
+183.7
+177.5
+175.4
+180.3
+181.3
+178.8
+182.3
+176.5
+177.4
+176.0
+178.8
+184.3
+183.0
+180.2
+184.9
+188.1
+187.6
+182.8
+183.0
+180.0
+177.5
+196.1
+185.1
+175.5
+175.9
+178.6
+201.5
+177.1
+191.7
+184.8
+176.2
+184.4
+175.9
+182.6
+182.0
+180.8
+178.7
+191.3
+179.5
+178.7
+174.8
+185.1
+174.9
+189.8
+191.3
+191.9
+190.7
+175.8
+177.3
+183.6
+178.0
+185.1
+177.2
+178.6
+188.7
+179.0
+186.0
+202.6
+177.2
+179.8
+196.0
+195.8
+186.8
+183.6
+202.2
+182.0
+175.8
+186.6
+178.2
+181.3
+180.8
+183.6
+181.9
+192.4
+190.8
+179.2
+184.6
+186.2
+183.0
+196.5
+179.6
+183.4
+187.2
+179.5
+185.3
+182.2
+177.8
+176.6
+177.2
+179.3
+177.1
+181.9
+178.9
+180.2
+179.8
+175.0
+176.8
+180.5
+175.7
+176.3
+180.6
+181.6
+176.6
+175.4
+177.4
+176.2
+180.8
+188.0
+178.2
+205.6
+177.8
+176.5
+179.4
+176.4
+183.3
+177.9
+174.2
+176.1
+182.8
+180.8
+186.9
+179.4
+195.8
+178.8
+181.6
+199.7
+175.8
+186.7
+179.1
+182.4
+179.1
+176.3
+180.5
+174.7
+180.8
+178.2
+185.2
+183.3
+192.7
+184.9
+205.8
+177.0
+182.5
+187.3
+185.9
+184.3
+177.0
+193.2
+179.0
+177.5
+181.3
+176.2
+178.8
+197.3
+180.8
+180.8
+189.7
+188.3
+179.5
+179.3
+185.3
+184.8
+192.3
+180.4
+186.7
+180.0
+178.9
+177.9
+179.4
+177.3
+181.9
+175.4
+174.1
+180.2
+176.9
+178.6
+177.5
+176.4
+177.7
+180.6
+182.2
+178.0
+179.3
+176.9
+188.6
+180.4
+179.8
+180.7
+177.2
+176.7
+175.3
+176.4
+178.4
+177.8
+180.1
+193.5
+181.0
+183.6
+177.9
+181.9
+186.9
+197.3
+175.7
+177.6
+184.7
+179.6
+182.2
+181.9
+181.2
+176.7
+185.5
+196.8
+185.9
+182.4
+178.1
+180.2
+178.3
+181.7
+186.4
+175.6
+182.6
+179.6
+181.0
+188.0
+178.1
+176.9
+181.0
+179.6
+185.0
+177.7
+179.4
+178.0
+185.7
+179.0
+194.2
+175.4
+178.5
+175.0
+176.7
+179.3
+188.8
+181.0
+177.3
+188.0
+178.5
+180.0
+175.9
+180.7
+181.2
+177.0
+179.2
+179.3
+193.1
+176.0
+179.4
+185.4
+177.4
+177.2
+177.9
+176.4
+186.7
+178.0
+178.7
+180.5
+186.7
+176.4
+185.8
+182.5
+177.3
+180.3
+179.5
+174.6
+184.2
+184.0
+176.3
+176.0
+211.4
+184.5
+182.1
+180.5
+188.1
+177.9
+179.7
+177.5
+184.5
+180.6
+191.1
+187.4
+176.3
+180.4
+183.2
+184.8
+178.6
+189.8
+180.9
+176.6
+176.9
+176.4
+182.0
+178.2
+177.3
+189.9
+191.1
+178.0
+179.5
+176.7
+194.2
+211.7
+175.9
+177.9
+176.0
+179.7
+180.6
+176.4
+180.3
+177.2
+183.6
+180.6
+187.4
+189.4
+189.6
+177.1
+179.4
+184.3
+186.4
+181.9
+180.1
+184.8
+182.0
+188.2
+181.4
+184.8
+177.5
+180.3
+195.4
+185.7
+176.8
+176.0
+187.3
+202.2
+194.5
+181.1
+182.9
+197.6
+186.9
+181.3
+180.9
+183.9
+191.0
+182.5
+186.9
+179.7
+179.2
+185.6
+184.3
+180.4
+190.9
+183.6
+183.1
+175.0
+180.9
+186.3
+174.8
+176.4
+176.1
+175.7
+178.1
+178.0
+180.5
+182.6
+180.0
+179.2
+186.8
+188.3
+179.8
+179.6
+180.5
+176.9
+204.2
+195.2
+180.2
+177.9
+187.9
+191.3
+183.9
+185.3
+186.8
+182.5
+189.5
+176.8
+180.5
+189.3
+185.9
+178.0
+176.0
+179.2
+181.3
+175.6
+179.9
+179.4
+183.8
+178.8
+177.9
+180.1
+182.3
+180.9
+175.7
+178.1
+173.7
+177.9
+180.0
+176.2
+177.7
+179.4
+192.3
+175.7
+185.7
+188.6
+195.5
+182.5
+184.1
+177.9
+177.8
+183.0
+174.9
+174.9
+179.7
+186.4
+185.9
+175.2
+179.2
+176.8
+181.5
+178.3
+180.6
+176.8
+175.8
+175.9
+180.3
+179.7
+175.8
+174.1
+180.6
+176.7
+179.7
+175.7
+179.2
+178.3
+203.4
+177.9
+186.9
+175.7
+177.0
+178.8
+180.2
+180.1
+185.5
+175.0
+178.6
+183.3
+177.2
+178.3
+180.1
+175.9
+175.6
+179.3
+179.8
+178.0
+186.5
+176.4
+187.2
+181.6
+175.4
+177.5
+179.1
+179.2
+175.9
+174.3
+175.5
+177.4
+178.5
+182.0
+181.4
+184.4
+183.4
+174.4
+177.5
+175.0
+175.4
+174.1
+182.8
+184.9
+178.3
+182.9
+182.3
+186.6
+180.9
+191.6
+185.6
+184.8
+190.2
+175.8
+185.2
+175.5
+176.9
+176.7
+176.9
+176.5
+179.2
+179.9
+179.2
+177.8
+188.9
+180.3
+186.8
+182.0
+180.8
+176.6
+180.5
+175.3
+185.0
+181.1
+181.1
+176.5
+176.5
+178.0
+175.9
+180.2
+178.3
+188.0
+185.9
+178.6
+179.5
+187.6
+180.2
+181.3
+182.5
+182.8
+175.0
+184.9
+181.7
+178.5
+177.5
+177.1
+176.8
+179.0
+179.2
+175.5
+177.1
+178.9
+174.8
+179.0
+177.3
+179.2
+178.2
+177.5
+191.8
+177.6
+182.1
+178.7
+177.2
+182.5
+181.5
+185.6
+179.5
+183.9
+177.6
+179.6
+193.9
+175.9
+216.0
+180.4
+177.3
+178.8
+176.7
+177.3
+178.3
+188.8
+175.8
+175.7
+176.0
+178.3
+185.1
+179.0
+191.3
+180.0
+178.8
+189.8
+182.7
+176.7
+178.0
+184.2
+185.0
+190.3
+178.0
+178.7
+177.4
+186.0
+176.4
+179.6
+178.0
+182.2
+175.9
+175.7
+178.3
+174.7
+193.6
+177.2
+186.6
+183.7
+181.0
+192.1
+176.4
+188.6
+205.9
+199.0
+194.6
+193.4
+190.4
+178.1
+188.0
+183.8
+180.5
+180.5
+190.5
+194.5
+180.8
+185.3
+193.4
+183.1
+178.1
+197.4
+190.2
+181.0
+184.9
+189.0
+184.6
+183.7
+187.7
+187.9
+182.5
+192.6
+184.3
+178.7
+179.8
+196.8
+184.4
+195.5
+183.9
+186.6
+181.0
+188.7
+185.0
+197.1
+204.2
+176.8
+179.6
+185.3
+182.1
+178.6
+180.6
+183.0
+199.1
+180.5
+180.7
+189.2
+194.5
+187.1
+192.3
+179.3
+196.8
+197.3
+180.3
+177.0
+178.8
+183.2
+183.1
+176.6
+201.6
+183.8
+182.7
+177.0
+185.2
+180.1
+199.4
+203.2
+187.4
+185.7
+184.1
+183.0
+198.7
+186.3
+187.9
+199.4
+185.9
+190.3
+202.8
+204.6
+178.1
+187.6
+196.5
+180.3
+181.7
+182.9
+199.2
+198.8
+190.5
+219.6
+180.0
+203.5
+182.0
+184.1
+176.8
+200.9
+201.9
+180.9
+177.9
+183.4
+179.5
+197.8
+188.0
+204.1
+185.6
+179.3
+190.6
+184.3
+195.2
+188.0
+200.9
+187.7
+183.0
+180.9
+180.0
+184.7
+176.8
+181.9
+180.6
+180.0
+177.7
+182.2
+175.2
+182.9
+186.3
+203.4
+183.3
+175.8
+186.2
+179.8
+178.4
+178.2
+420.1
+177.9
+193.8
+183.8
+180.0
+188.8
+187.2
+192.0
+180.8
+182.3
+191.8
+183.2
+176.6
+179.5
+215.2
+193.8
+188.3
+180.3
+186.4
+181.8
+205.8
+175.1
+186.5
+205.9
+185.5
+187.1
+191.7
+189.4
+188.3
+180.1
+179.8
+178.9
+179.3
+181.9
+184.9
+188.4
+176.2
+177.0
+181.8
+179.5
+177.3
+176.0
+208.3
+185.6
+180.6
+180.3
+195.0
+177.7
+175.7
+214.3
+188.2
+177.7
+187.1
+197.1
+184.8
+178.2
+182.1
+178.4
+176.3
+190.6
+187.3
+177.8
+177.2
+191.7
+200.2
+188.4
+177.3
+177.0
+178.5
+180.3
+177.0
+182.2
+184.4
+175.8
+185.6
+179.6
+180.8
+179.9
+199.4
+175.1
+196.3
+185.5
+182.5
+179.4
+191.2
+192.4
+180.3
+186.8
+194.7
+180.5
+178.0
+180.8
+184.9
+180.7
+179.0
+184.5
+180.5
+176.2
+182.9
+178.8
+183.5
+194.6
+182.0
+198.5
+176.5
+185.0
+187.6
+196.9
+194.2
+185.0
+190.8
+179.6
+175.8
+198.5
+180.0
+177.9
+203.3
+183.3
+181.4
+183.8
+176.5
+175.1
+193.9
+178.9
+183.0
+180.2
+178.0
+178.9
+188.1
+181.3
+179.3
+181.6
+183.1
+175.0
+178.8
+175.7
+179.4
+180.6
+185.9
+176.7
+190.8
+189.6
+180.1
+176.7
+181.7
+180.7
+191.9
+175.5
+180.1
+185.1
+182.0
+181.0
+184.3
+196.6
+188.8
+191.0
+184.2
+184.1
+180.1
+189.0
+178.2
+182.6
+190.4
+182.5
+186.3
+182.9
+191.5
+183.6
+193.2
+183.3
+201.4
+215.5
+182.4
+196.6
+183.6
+190.7
+180.8
+190.9
+178.2
+189.8
+194.8
+180.9
+184.2
+184.1
+185.3
+176.7
+181.5
+181.0
+191.1
+195.9
+192.0
+178.0
+179.9
+184.7
+181.3
+188.5
+187.6
+184.7
+193.9
+198.5
+188.5
+186.5
+184.4
+188.1
+183.0
+190.8
+184.9
+183.8
+184.5
+185.5
+180.2
+181.3
+181.8
+177.5
+178.6
+205.8
+188.5
+188.1
+183.9
+182.9
+192.0
+181.9
+181.5
+190.2
+185.2
+188.1
+174.3
+190.1
+185.6
+183.3
+182.1
+192.2
+179.6
+179.7
+187.5
+187.3
+187.1
+180.0
+184.2
+180.6
+311.7
+185.9
+185.9
+185.1
+176.8
+176.4
+177.7
+177.1
+188.2
+174.8
+184.0
+178.6
+180.2
+183.4
+182.9
+189.8
+187.3
+176.8
+192.5
+186.1
+212.1
+179.4
+181.3
+188.4
+177.7
+200.4
+182.7
+177.5
+183.5
+187.5
+182.6
+194.0
+179.6
+181.6
+201.6
+183.0
+185.5
+177.8
+200.1
+182.7
+182.1
+192.5
+185.6
+188.8
+180.8
+179.5
+181.1
+185.1
+178.1
+178.9
+183.1
+180.8
+178.7
+184.8
+180.1
+179.7
+187.2
+187.1
+182.5
+187.0
+185.6
+191.9
+187.7
+186.3
+188.0
+180.1
+179.3
+181.3
+193.7
+176.8
+184.4
+176.7
+183.1
+189.4
+178.8
+211.4
+182.2
+190.8
+194.1
+179.4
+176.3
+178.6
+175.5
+182.9
+186.0
+184.1
+187.8
+181.3
+188.4
+178.3
+178.7
+200.4
+176.0
+187.7
+197.2
+188.2
+188.6
+192.3
+180.3
+186.3
+187.6
+201.5
+183.8
+182.9
+185.8
+185.9
+181.9
+180.2
+177.3
+183.3
+186.4
+181.3
+195.4
+194.0
+182.7
+178.3
+190.5
+178.6
+194.5
+175.4
+176.8
+177.4
+191.1
+180.6
+175.5
+175.2
+186.9
+176.1
+183.6
+187.1
+178.4
+196.0
+201.0
+183.0
+179.7
+179.9
+184.1
+179.9
+193.1
+180.8
+187.2
+182.0
+176.1
+183.4
+188.4
+177.6
+177.3
+183.8
+179.5
+184.4
+179.8
+181.5
+178.6
+186.5
+183.1
+175.7
+177.3
+177.5
+194.3
+190.9
+175.4
+198.2
+182.6
+180.9
+182.7
+177.0
+190.4
+186.8
+199.4
+183.6
+180.4
+196.3
+205.0
+178.0
+182.0
+185.0
+180.0
+200.6
+185.4
+186.6
+188.4
+199.1
+183.3
+211.8
+182.2
+186.0
+186.5
+185.4
+183.8
+182.3
+179.9
+182.0
+186.9
+184.6
+187.9
+182.4
+187.3
+199.6
+187.9
+196.6
+189.9
+190.9
+180.9
+177.5
+180.2
+188.4
+181.4
+178.0
+190.8
+198.7
+191.5
+189.8
+191.4
+188.6
+186.2
+198.8
+207.4
+192.2
+185.0
+194.7
+198.7
+191.4
+197.4
+184.9
+202.5
+178.6
+180.3
+186.9
+184.5
+178.3
+179.4
+201.3
+193.5
+184.2
+193.9
+177.1
+185.8
+188.5
+183.6
+201.0
+183.6
+190.9
+190.3
+185.4
+180.2
+185.9
+182.6
+184.7
+182.1
+188.7
+180.5
+178.0
+198.6
+188.8
+183.8
+178.1
+176.4
+179.4
+179.5
+186.5
+180.4
+179.8
+180.2
+195.0
+177.2
+180.0
+195.5
+181.7
+183.6
+187.1
+180.7
+180.7
+181.2
+184.5
+181.0
+199.1
+197.4
+183.6
+189.0
+183.2
+196.4
+183.7
+191.4
+185.3
+202.8
+177.9
+182.1
+179.5
+176.3
+193.1
+184.6
+178.8
+191.8
+224.8
+180.5
+182.0
+178.8
+178.2
+178.8
+185.4
+186.5
+178.6
+188.4
+179.7
+190.9
+181.6
+179.8
+190.1
+188.0
+179.7
+204.8
+184.8
+179.7
+182.5
+184.1
+176.1
+181.1
+177.2
+185.8
+177.7
+179.1
+186.7
+183.8
+177.5
+180.2
+200.9
+181.0
+182.7
+177.7
+191.7
+176.8
+190.9
+178.6
+182.3
+178.8
+186.1
+176.8
+180.0
+182.5
+175.0
+183.2
+177.4
+189.5
+177.7
+179.1
+180.8
+177.9
+180.0
+181.6
+178.6
+178.1
+184.7
+176.8
+176.0
+175.7
+175.9
+180.3
+176.3
+180.4
+178.8
+182.5
+177.9
+187.7
+182.2
+187.2
+178.5
+179.9
+181.1
+180.9
+182.5
+179.8
+178.6
+176.0
+179.0
+189.5
+183.5
+182.5
+183.6
+186.0
+181.7
+191.1
+187.4
+194.0
+197.2
+197.3
+177.9
+179.4
+178.0
+176.9
+178.6
+189.0
+183.3
+188.5
+184.0
+184.0
+185.5
+180.7
+176.3
+180.2
+179.9
+186.7
+177.5
+181.0
+189.3
+190.3
+178.3
+188.1
+189.5
+183.6
+190.7
+178.9
+179.1
+179.5
+196.1
+180.8
+178.9
+177.9
+184.6
+178.0
+181.9
+185.3
+187.5
+183.9
+187.0
+180.1
+198.9
+182.6
+181.1
+191.1
+190.7
+183.6
+181.2
+184.5
+177.3
+179.5
+178.7
+181.5
+180.1
+185.0
+178.6
+182.8
+182.7
+192.6
+181.5
+176.5
+178.4
+187.0
+180.2
+187.5
+182.5
+178.0
+184.6
+180.3
+187.2
+177.6
+187.5
+190.6
+188.2
+187.8
+182.6
+186.8
+179.0
+211.0
+176.2
+180.5
+183.4
+215.3
+181.6
+208.2
+215.6
+207.8
+189.1
+176.5
+190.9
+187.0
+178.8
+190.2
+183.0
+193.6
+175.3
+184.4
+184.2
+181.7
+175.4
+177.4
+176.1
+187.1
+194.1
+181.3
+193.1
+182.1
+184.7
+183.1
+186.0
+180.6
+181.7
+181.7
+184.9
+191.4
+201.1
+181.7
+192.9
+177.6
+187.6
+177.6
+183.6
+195.4
+187.2
+184.2
+185.4
+178.0
+201.0
+180.0
+205.9
+201.9
+199.2
+185.2
+182.7
+181.0
+187.4
+181.5
+186.6
+180.4
+176.7
+177.9
+178.2
+179.3
+186.5
+175.7
+185.5
+195.1
+181.9
+183.3
+182.0
+176.7
+181.0
+176.1
+179.4
+186.2
+194.1
+191.1
+184.0
+185.1
+188.6
+183.2
+176.1
+179.3
+183.6
+177.5
+192.7
+180.6
+191.3
+182.6
+189.3
+183.6
+182.4
+178.8
+175.5
+179.3
+193.2
+181.3
+183.9
+185.1
+183.3
+184.9
+188.6
+185.7
+194.9
+199.5
+175.7
+202.6
+194.2
+185.3
+178.0
+182.5
+202.3
+187.5
+192.9
+181.8
+183.2
+183.5
+187.8
+179.6
+178.7
+197.1
+182.2
+202.2
+194.8
+184.9
+192.6
+175.5
+178.0
+184.7
+177.8
+178.7
+179.7
+181.4
+186.6
+179.3
+178.9
+182.3
+180.8
+180.5
+182.4
+184.0
+183.2
+181.2
+183.6
+186.2
+179.7
+178.6
+200.2
+189.2
+177.5
+188.0
+191.1
+183.2
+183.4
+191.0
+186.9
+198.9
+180.0
+175.3
+261.0
+178.7
+181.1
+181.2
+178.7
+179.1
+201.6
+178.4
+181.6
+176.2
+181.7
+192.2
+184.5
+179.1
+191.8
+181.3
+184.4
+185.0
+186.6
+178.6
+180.2
+185.2
+190.0
+177.3
+178.5
+193.7
+178.7
+184.8
+179.9
+192.0
+186.2
+194.7
+181.5
+183.9
+188.0
+183.4
+181.3
+187.2
+184.6
+188.7
+185.3
+180.1
+183.4
+182.4
+176.9
+177.6
+191.1
+180.8
+176.0
+175.4
+180.0
+179.6
+188.3
+191.3
+183.2
+181.7
+177.9
+180.0
+182.0
+181.3
+180.1
+187.7
+177.5
+186.7
+183.4
+189.1
+199.9
+203.9
+184.1
+179.2
+187.4
+185.7
+181.8
+179.7
+179.1
+175.6
+200.8
+181.2
+175.9
+179.3
+176.9
+183.8
+195.7
+185.6
+181.9
+184.0
+190.1
+188.6
+179.0
+181.7
+179.2
+212.9
+181.3
+192.8
+180.8
+180.4
+190.8
+178.1
+181.2
+183.4
+189.4
+191.6
+196.7
+179.2
+203.5
+197.4
+180.5
+184.2
+194.9
+182.6
+183.3
+177.9
+200.4
+191.9
+175.4
+214.3
+184.1
+180.8
+182.9
+181.3
+182.4
+181.4
+191.0
+178.9
+188.3
+195.6
+182.1
+193.5
+180.3
+196.3
+177.9
+198.8
+190.9
+179.1
+185.4
+188.7
+181.0
+177.8
+178.0
+203.4
+179.4
+180.8
+183.6
+179.0
+184.8
+178.0
+188.3
+203.1
+194.9
+196.8
+187.9
+185.7
+178.0
+180.8
+176.8
+181.0
+180.9
+187.0
+179.5
+186.9
+175.9
+174.7
+177.1
+187.9
+193.2
+177.3
+177.9
+181.2
+180.1
+176.1
+179.4
+176.7
+183.2
+191.8
+184.7
+180.8
+183.2
+176.9
+182.8
+187.5
+187.3
+185.7
+184.6
+178.8
+183.0
+176.7
+177.6
+198.0
+194.7
+188.8
+180.9
+187.9
+175.9
+193.1
+183.4
+186.2
+184.4
+182.3
+175.6
+224.3
+186.0
+184.0
+179.0
+176.6
+183.9
+190.9
+188.5
+183.9
+184.7
+198.6
+184.1
+182.0
+181.3
+183.3
+181.6
+182.8
+186.6
+181.4
+179.0
+192.0
+186.3
+202.8
+190.0
+182.1
+186.4
+186.0
+187.0
+192.8
+185.4
+185.4
+181.2
+182.3
+183.2
+190.4
+184.9
+186.4
+180.9
+181.4
+179.8
+191.3
+182.4
+193.0
+202.1
+187.9
+222.0
+196.9
+201.9
+197.8
+198.7
+184.1
+192.7
+203.2
+197.1
+193.7
+196.5
+186.3
+198.4
+181.2
+192.3
+190.4
+183.3
+181.9
+201.8
+198.5
+194.7
+182.3
+184.9
+186.0
+185.9
+190.8
+179.4
+182.2
+181.7
+180.6
+179.2
+180.9
+189.7
+195.7
+200.7
+191.6
+191.1
+187.6
+181.6
+185.9
+188.3
+183.5
+187.7
+190.3
+186.1
+181.1
+178.7
+178.0
+179.0
+191.5
+186.8
+184.9
+181.0
+183.4
+181.3
+180.1
+188.2
+204.3
+180.1
+185.8
+184.9
+187.4
+176.0
+184.2
+177.6
+179.0
+178.9
+188.3
+179.8
+180.9
+177.5
+188.9
+191.1
+184.7
+189.5
+178.4
+189.3
+184.7
+186.2
+178.9
+176.6
+180.8
+177.3
+183.3
+180.0
+188.8
+186.8
+179.5
+179.6
+181.6
+177.4
+176.5
+178.0
+182.6
+184.7
+189.3
+183.6
+180.6
+186.6
+180.7
+185.6
+178.2
+176.3
+181.2
+177.6
+175.7
+177.3
+184.0
+178.2
+182.9
+201.6
+175.0
+179.3
+181.6
+176.2
+180.4
+176.0
+183.7
+177.5
+183.5
+193.5
+192.7
+179.0
+182.2
+179.6
+179.3
+176.8
+177.9
+177.2
+176.5
+177.4
+177.9
+186.5
+178.9
+181.0
+178.0
+176.6
+176.5
+179.2
+187.2
+178.2
+184.6
+178.9
+177.8
+182.1
+187.2
+188.8
+184.5
+181.0
+188.4
+193.1
+178.7
+186.2
+181.1
+183.2
+181.4
+177.6
+176.7
+177.1
+179.0
+181.0
+177.9
+183.5
+181.6
+178.9
+179.4
+175.8
+175.6
+179.0
+180.1
+175.9
+179.9
+178.1
+186.0
+208.0
+178.6
+182.7
+186.3
+174.5
+178.6
+184.3
+185.4
+178.3
+178.5
+190.5
+180.8
+188.2
+177.3
+190.1
+175.5
+188.5
+185.4
+179.6
+181.4
+177.4
+217.5
+196.9
+180.8
+179.9
+192.5
+178.0
+178.4
+175.8
+175.3
+184.8
+197.2
+186.0
+176.9
+176.5
+178.4
+180.8
+185.5
+203.5
+183.3
+180.0
+177.6
+181.2
+180.2
+179.7
+194.4
+180.8
+181.3
+176.9
+187.2
+178.5
+178.7
+185.4
+183.0
+181.3
+261.7
+178.1
+175.9
+175.9
+189.8
+185.9
+184.1
+181.7
+182.7
+177.6
+176.6
+183.6
+178.4
+178.5
+185.8
+184.5
+178.5
+178.0
+181.7
+177.4
+179.3
+177.5
+175.7
+176.6
+176.4
+180.8
+184.9
+177.6
+178.0
+178.7
+178.0
+177.8
+176.7
+183.6
+196.4
+182.4
+182.2
+178.0
+175.9
+179.2
+175.6
+178.3
+176.2
+178.8
+183.1
+175.2
+182.4
+180.6
+177.6
+176.6
+180.2
+180.4
+181.1
+176.2
+188.7
+187.2
+181.6
+181.5
+177.2
+176.9
+177.4
+176.3
+185.2
+178.3
+184.6
+178.3
+189.7
+179.5
+201.1
+176.2
+185.5
+182.2
+183.4
+174.5
+176.8
+180.1
+179.8
+182.2
+178.8
+186.5
+188.2
+180.4
+182.1
+182.8
+194.7
+182.3
+177.6
+176.2
+180.7
+193.6
+178.9
+177.8
+178.7
+179.8
+176.3
+180.8
+184.2
+181.5
+179.2
+178.2
+179.9
+176.7
+180.0
+183.0
+180.6
+177.3
+186.7
+180.8
+181.5
+190.3
+186.8
+184.2
+180.4
+181.6
+182.2
+183.0
+173.3
+187.5
+185.7
+180.1
+177.8
+189.2
+194.9
+176.8
+194.9
+187.0
+209.2
+185.4
+177.7
+178.0
+175.4
+178.0
+183.1
+177.9
+182.4
+177.2
+177.7
+178.9
+183.5
+178.1
+179.2
+191.5
+182.6
+179.8
+182.5
+176.9
+180.2
+176.0
+178.6
+184.7
+279.2
+179.0
+176.5
+180.0
+182.9
+178.3
+188.1
+179.6
+177.8
+175.6
+180.0
+178.6
+181.0
+184.0
+178.2
+191.6
+176.8
+187.7
+179.1
+183.3
+203.5
+178.7
+178.6
+175.4
+187.5
+179.7
+181.6
+177.9
+180.5
+186.7
+182.3
+187.9
+182.2
+187.8
+181.1
+266.6
+186.3
+185.9
+178.0
+180.6
+176.9
+176.5
+177.0
+184.1
+182.7
+179.0
+182.6
+180.8
+179.9
+179.0
+183.1
+178.6
+176.4
+177.3
+176.4
+180.2
+177.2
+177.0
+177.5
+178.3
+175.2
+177.8
+176.7
+181.4
+177.7
+177.1
+176.5
+180.8
+177.2
+178.1
+177.9
+187.1
+183.8
+187.0
+184.4
+180.2
+179.2
+179.2
+178.6
+188.0
+184.7
+178.0
+176.3
+175.3
+181.6
+191.8
+176.9
+182.0
+183.3
+177.5
+185.0
+181.5
+182.6
+179.0
+188.4
+203.6
+184.3
+183.8
+188.0
+189.7
+184.7
+185.9
+195.0
+185.3
+178.8
+190.6
+181.6
+180.1
+187.1
+182.3
+176.8
+179.1
+185.8
+180.1
+180.3
+182.7
+185.3
+175.6
+182.8
+188.5
+175.6
+182.7
+182.0
+179.5
+180.9
+179.4
+183.2
+182.7
+182.5
+182.0
+190.1
+199.7
+177.8
+177.6
+180.9
+181.6
+183.3
+186.1
+188.0
+184.9
+185.4
+182.6
+182.5
+178.7
+185.6
+175.4
+176.7
+182.5
+180.6
+178.3
+179.7
+184.4
+180.9
+184.5
+187.2
+181.6
+192.7
+185.9
+179.6
+184.3
+182.3
+175.0
+180.3
+177.2
+177.9
+178.4
+179.7
+174.6
+190.4
+193.1
+186.8
+180.6
+176.0
+177.4
+188.4
+179.2
+180.9
+178.7
+180.9
+178.2
+176.6
+185.0
+182.1
+181.7
+175.2
+175.1
+183.2
+192.0
+188.3
+182.1
+176.7
+177.6
+177.3
+192.6
+189.3
+178.2
+177.5
+183.1
+183.4
+181.2
+179.5
+175.4
+176.8
+178.2
+175.8
+179.4
+184.7
+184.6
+191.9
+177.4
+176.7
+179.3
+181.6
+183.3
+176.6
+218.6
+175.7
+174.4
+186.4
+185.1
+176.0
+195.2
+180.3
+178.1
+179.2
+178.0
+181.5
+182.9
+179.0
+191.3
+185.1
+186.5
+177.2
+180.3
+191.0
+175.7
+179.8
+182.0
+181.6
+185.0
+183.2
+174.8
+184.5
+182.1
+178.7
+186.7
+186.9
+176.5
+184.5
+188.9
+180.4
+190.1
+181.4
+188.0
+193.5
+187.7
+180.0
+183.5
+176.7
+177.5
+179.2
+206.2
+178.4
+183.2
+181.7
+200.9
+193.1
+176.1
+181.8
+183.6
+193.5
+201.7
+188.0
+178.9
+180.5
+180.8
+176.5
+178.0
+180.6
+181.4
+184.7
+192.4
+177.4
+182.4
+202.8
+189.7
+177.3
+181.5
+178.7
+180.0
+180.6
+178.0
+178.3
+183.9
+177.4
+180.0
+189.7
+175.4
+185.2
+179.3
+184.1
+177.5
+182.1
+174.8
+179.8
+187.5
+216.9
+182.9
+183.5
+203.3
+181.5
+184.0
+181.3
+183.4
+180.3
+176.1
+180.3
+180.1
+180.2
+181.2
+182.3
+176.2
+189.5
+219.7
+180.1
+176.6
+177.3
+178.8
+181.2
+175.1
+183.3
+182.1
+178.7
+180.9
+183.3
+188.1
+225.2
+185.8
+184.3
+187.5
+187.3
+190.7
+181.0
+180.2
+184.6
+177.9
+180.1
+187.6
+181.1
+177.5
+184.5
+176.5
+182.7
+174.5
+183.2
+176.5
+183.0
+177.0
+179.2
+182.9
+184.9
+176.4
+179.9
+183.2
+178.1
+177.0
+205.5
+182.5
+175.2
+185.0
+182.7
+178.2
+189.0
+190.5
+178.8
+183.5
+185.1
+181.3
+181.3
+194.5
+187.8
+184.9
+177.2
+179.6
+195.1
+181.2
+188.8
+180.4
+180.8
+180.0
+177.6
+198.3
+180.6
+179.5
+178.4
+179.3
+177.5
+176.8
+181.6
+183.8
+181.8
+175.6
+181.0
+178.4
+179.4
+179.8
+181.3
+181.1
+193.3
+180.1
+182.8
+179.3
+181.1
+188.3
+177.6
+178.5
+178.8
+177.1
+179.2
+181.6
+185.6
+191.8
+176.3
+187.8
+184.5
+197.3
+183.1
+179.7
+178.1
+181.3
+177.6
+178.2
+179.5
+177.5
+185.4
+184.4
+186.4
+177.4
+178.0
+179.7
+177.9
+184.6
+189.1
+184.5
+197.2
+192.6
+188.0
+186.5
+177.3
+183.7
+183.7
+192.8
+181.2
+199.4
+179.7
+187.7
+192.8
+208.5
+184.1
+175.6
+185.3
+188.6
+183.7
+180.7
+182.1
+176.0
+183.1
+179.6
+175.7
+187.0
+179.9
+184.8
+179.4
+187.6
+181.6
+201.1
+193.5
+186.2
+190.3
+197.9
+208.2
+192.9
+193.1
+184.9
+210.5
+178.6
+198.2
+177.9
+192.2
+181.6
+185.1
+189.1
+188.3
+204.7
+186.2
+179.6
+189.2
+176.9
+180.5
+183.3
+193.1
+178.4
+203.8
+185.2
+180.6
+183.3
+186.7
+188.8
+184.4
+181.7
+186.4
+185.8
+180.1
+182.7
+179.8
+198.9
+180.4
+178.3
+195.6
+184.0
+179.5
+181.8
+187.4
+181.7
+181.8
+175.1
+200.0
+181.6
+203.0
+176.0
+184.9
+199.3
+178.2
+184.3
+176.6
+192.9
+188.1
+185.7
+181.0
+179.5
+183.4
+186.7
+178.6
+183.2
+179.6
+182.6
+177.3
+179.0
+197.0
+182.0
+174.8
+179.4
+180.7
+210.3
+211.3
+235.3
+255.7
+275.7
+286.8
+306.7
+347.2
+381.2
+184.5
+186.7
+190.1
+193.3
+177.9
+188.0
+184.0
+180.6
+178.5
+235.8
+179.6
+178.1
+196.0
+180.5
+179.0
+185.8
+230.8
+211.1
+178.3
+179.4
+186.5
+180.6
+181.4
+183.2
+188.7
+184.8
+175.0
+179.2
+185.4
+180.8
+182.7
+183.1
+177.3
+177.4
+181.3
+190.9
+182.7
+198.2
+180.9
+200.5
+188.4
+207.5
+190.2
+178.9
+184.1
+193.6
+321.3
+183.8
+181.4
+174.6
+185.1
+198.9
+202.2
+183.3
+187.3
+183.0
+184.5
+178.3
+183.8
+176.7
+178.3
+186.0
+181.0
+176.0
+181.3
+202.8
+179.7
+180.3
+191.6
+176.8
+182.6
+183.7
+181.3
+186.2
+205.7
+186.4
+181.9
+189.9
+188.9
+193.6
+203.2
+212.3
+178.9
+181.5
+189.6
+178.9
+177.6
+189.0
+177.3
+177.2
+178.0
+178.5
+177.9
+197.8
+182.0
+185.7
+193.6
+185.8
+183.1
+183.1
+192.7
+183.0
+187.0
+193.4
+186.9
+182.3
+183.9
+201.6
+199.5
+182.7
+184.6
+181.8
+179.1
+189.8
+183.1
+187.8
+185.7
+192.9
+179.3
+179.7
+180.2
+177.6
+180.8
+178.0
+190.2
+177.5
+199.2
+192.7
+181.2
+185.2
+183.5
+198.1
+178.9
+183.7
+191.6
+187.4
+180.5
+211.9
+206.2
+183.2
+182.1
+176.7
+187.4
+176.6
+183.2
+195.5
+178.7
+180.7
+181.2
+189.1
+187.8
+183.1
+181.9
+186.3
+197.1
+184.7
+177.2
+180.5
+179.5
+181.6
+177.9
+187.7
+196.2
+189.5
+180.5
+183.3
+180.6
+186.7
+186.2
+177.7
+192.1
+182.4
+177.5
+179.7
+193.6
+200.1
+179.9
+188.4
+182.3
+190.4
+179.4
+182.4
+181.7
+195.7
+177.2
+181.3
+182.9
+188.3
+183.6
+180.3
+192.7
+183.1
+210.5
+185.1
+183.4
+191.6
+187.9
+183.1
+175.5
+177.4
+183.7
+182.9
+188.5
+180.7
+186.2
+182.4
+186.3
+182.4
+188.1
+180.2
+195.4
+181.8
+192.9
+176.3
+177.7
+178.8
+179.4
+182.6
+180.3
+187.4
+185.3
+183.5
+180.5
+180.8
+182.0
+178.9
+176.2
+197.0
+181.5
+177.1
+189.1
+188.0
+176.5
+181.7
+184.9
+192.2
+181.5
+189.0
+204.6
+177.5
+176.6
+202.2
+176.9
+181.9
+177.9
+180.6
+197.2
+175.9
+175.6
+183.4
+182.7
+191.2
+178.8
+187.2
+178.9
+192.4
+178.6
+178.4
+184.5
+216.4
+190.7
+182.7
+181.6
+199.5
+182.0
+179.1
+189.1
+180.3
+182.0
+185.6
+196.1
+182.5
+180.4
+190.9
+178.9
+186.3
+209.4
+181.7
+186.6
+192.0
+200.0
+205.7
+191.0
+186.0
+185.5
+176.2
+191.4
+184.4
+186.1
+186.6
+180.0
+180.8
+178.0
+180.0
+198.8
+183.9
+183.5
+176.4
+176.7
+181.4
+186.4
+186.8
+186.0
+179.5
+187.2
+179.5
+185.2
+179.4
+183.6
+188.6
+179.8
+179.0
+184.4
+178.4
+177.4
+195.2
+207.0
+184.3
+179.6
+183.1
+184.0
+187.2
+181.4
+178.4
+182.7
+189.4
+183.1
+179.7
+181.8
+181.5
+181.9
+182.6
+178.2
+189.2
+189.1
+190.3
+184.1
+195.3
+176.1
+177.3
+186.8
+183.7
+188.5
+179.7
+177.4
+181.4
+180.7
+206.9
+179.2
+177.8
+180.5
+180.6
+191.9
+181.7
+190.3
+183.5
+186.2
+175.8
+179.1
+181.6
+181.6
+183.0
+179.1
+179.3
+183.7
+181.2
+185.2
+176.8
+177.8
+175.3
+184.6
+179.2
+176.9
+188.0
+184.6
+184.6
+180.9
+189.9
+396.3
+176.1
+183.1
+179.2
+184.6
+181.5
+181.3
+176.2
+177.4
+174.3
+179.4
+178.8
+184.6
+182.1
+183.4
+178.4
+184.1
+182.7
+181.4
+177.7
+185.0
+177.2
+179.4
+183.5
+183.1
+187.6
+181.1
+179.7
+189.6
+183.6
+177.1
+181.5
+193.1
+196.8
+180.2
+177.3
+178.8
+176.6
+177.8
+190.0
+176.3
+180.1
+177.5
+187.2
+186.7
+176.5
+179.6
+177.2
+177.5
+196.4
+181.9
+179.9
+178.2
+181.5
+177.5
+179.9
+183.1
+181.5
+181.8
+177.4
+177.6
+174.5
+178.4
+183.8
+181.6
+186.4
+178.1
+177.3
+179.1
+183.6
+191.2
+181.7
+187.6
+186.1
+183.5
+185.0
+186.5
+187.5
+190.5
+224.7
+177.3
+189.2
+191.7
+188.0
+182.8
+187.8
+182.2
+241.9
+197.6
+188.3
+181.7
+195.5
+184.4
+190.9
+187.4
+195.0
+190.0
+180.5
+179.1
+180.3
+195.0
+176.7
+191.8
+200.2
+180.3
+180.6
+186.1
+178.2
+182.5
+183.2
+178.9
+177.6
+185.6
+203.5
+179.7
+179.6
+190.8
+187.4
+184.7
+185.1
+195.1
+191.9
+181.1
+183.1
+177.1
+177.9
+178.5
+178.8
+186.0
+189.9
+184.7
+190.4
+192.9
+178.6
+176.1
+189.2
+186.1
+178.6
+186.9
+181.5
+181.5
+181.2
+178.1
+181.8
+187.6
+183.3
+188.5
+179.6
+183.5
+187.9
+179.6
+192.4
+182.6
+192.1
+255.4
+266.2
+191.5
+194.8
+179.7
+190.8
+182.8
+182.3
+186.7
+186.4
+178.1
+182.5
+175.0
+187.7
+199.4
+182.1
+180.5
+182.9
+175.9
+219.6
+207.0
+196.5
+190.7
+199.1
+185.4
+174.5
+180.5
+182.7
+181.8
+189.2
+181.0
+198.2
+191.9
+185.3
+182.9
+188.5
+178.7
+179.2
+188.7
+188.5
+178.2
+197.6
+178.3
+192.7
+181.9
+191.2
+181.7
+176.1
+196.5
+187.7
+190.5
+187.8
+182.9
+189.9
+192.3
+177.4
+184.7
+178.3
+185.8
+182.0
+180.1
+183.1
+182.0
+176.1
+185.2
+196.0
+185.5
+179.1
+198.1
+197.5
+182.0
+177.0
+178.3
+202.9
+177.0
+180.6
+181.6
+191.6
+179.6
+180.9
+183.7
+188.4
+182.6
+185.7
+191.5
+178.6
+188.4
+184.0
+183.8
+189.3
+185.2
+192.9
+195.4
+197.1
+190.4
+186.5
+196.0
+189.8
+191.9
+187.3
+185.7
+198.0
+175.8
+183.7
+176.0
+179.9
+183.1
+186.7
+177.9
+179.2
+181.7
+184.9
+181.6
+178.5
+176.5
+176.7
+178.4
+184.7
+181.3
+182.3
+182.8
+182.6
+190.2
+177.0
+187.9
+188.1
+186.4
+187.8
+181.3
+187.7
+191.8
+182.5
+182.0
+180.1
+185.8
+177.8
+192.5
+185.2
+179.7
+179.3
+191.0
+181.3
+192.9
+180.3
+194.5
+187.6
+184.3
+194.7
+182.7
+177.7
+181.2
+177.2
+184.0
+181.8
+188.5
+187.8
+184.7
+181.7
+184.6
+177.4
+193.0
+178.7
+176.5
+176.9
+180.9
+180.8
+187.8
+179.8
+175.2
+177.5
+180.5
+186.6
+177.0
+177.8
+177.8
+182.5
+180.0
+182.4
+188.6
+192.5
+177.5
+179.8
+178.8
+178.9
+182.0
+180.6
+184.5
+179.9
+175.4
+183.1
+177.8
+177.2
+191.7
+184.6
+183.1
+175.6
+200.6
+221.5
+177.2
+177.6
+184.0
+183.4
+199.2
+184.6
+186.1
+180.3
+188.1
+184.1
+185.9
+178.0
+183.7
+186.7
+186.1
+177.8
+183.5
+178.0
+177.0
+185.6
+187.0
+178.9
+178.9
+200.5
+180.2
+181.6
+187.8
+179.8
+182.0
+184.3
+176.3
+182.8
+184.3
+181.9
+185.3
+189.2
+177.3
+183.6
+186.7
+184.0
+243.9
+175.9
+184.3
+176.0
+179.6
+178.5
+182.3
+189.7
+179.6
+190.3
+188.8
+175.2
+179.8
+181.0
+175.6
+175.3
+187.5
+175.3
+186.8
+176.6
+177.3
+175.7
+178.5
+178.8
+178.5
+178.9
+183.7
+182.2
+182.3
+178.9
+182.0
+178.6
+184.2
+178.8
+176.7
+176.9
+176.2
+181.1
+177.9
+177.2
+178.6
+194.8
+185.4
+188.3
+178.9
+187.1
+184.3
+184.2
+190.3
+193.8
+185.0
+181.0
+181.4
+181.0
+191.8
+177.4
+178.6
+179.6
+180.2
+179.0
+187.4
+177.1
+182.7
+181.9
+177.9
+184.8
+195.1
+181.2
+182.1
+187.4
+186.8
+184.7
+181.9
+188.7
+191.8
+184.7
+185.5
+183.5
+180.8
+206.1
+179.1
+194.3
+178.0
+177.4
+181.0
+181.7
+190.6
+189.3
+176.3
+183.5
+178.9
+179.4
+187.3
+182.5
+181.7
+183.3
+188.9
+181.3
+195.6
+180.4
+194.0
+182.6
+176.6
+190.8
+176.3
+186.1
+185.1
+181.5
+179.2
+178.3
+179.6
+181.5
+181.0
+183.2
+182.6
+202.6
+183.7
+188.2
+200.6
+177.9
+184.2
+192.0
+180.9
+177.3
+177.2
+188.1
+184.2
+199.4
+185.3
+189.7
+199.8
+176.6
+189.2
+186.3
+182.8
+180.0
+190.8
+188.5
+194.6
+184.8
+202.7
+189.8
+183.2
+206.2
+175.3
+202.1
+193.5
+210.1
+200.5
+194.8
+190.0
+189.3
+182.5
+183.3
+187.1
+186.1
+208.1
+191.4
+207.5
+188.6
+176.7
+190.8
+189.1
+177.2
+189.3
+177.3
+196.2
+195.3
+188.0
+194.1
+181.3
+177.8
+186.2
+184.4
+182.0
+182.5
+187.1
+179.8
+177.4
+184.0
+180.5
+182.9
+176.4
+175.9
+176.8
+182.8
+208.0
+196.3
+183.4
+178.5
+189.7
+183.3
+182.5
+182.7
+182.5
+195.7
+183.8
+182.6
+190.0
+191.0
+191.7
+177.2
+184.1
+202.9
+189.8
+185.0
+183.3
+194.2
+182.8
+178.9
+184.9
+189.1
+192.8
+181.1
+190.5
+205.2
+179.1
+191.3
+186.8
+188.9
+178.8
+188.0
+184.1
+183.1
+182.1
+181.9
+191.6
+183.4
+189.9
+180.2
+186.6
+180.3
+182.7
+184.8
+178.4
+180.3
+193.7
+181.5
+186.6
+179.1
+184.3
+192.1
+189.5
+182.2
+296.4
+194.8
+179.0
+183.4
+194.3
+199.5
+182.7
+181.0
+181.8
+186.9
+186.4
+188.3
+179.2
+190.1
+184.9
+187.8
+186.3
+183.4
+183.1
+191.3
+188.5
+188.5
+187.9
+188.7
+175.3
+178.4
+197.5
+185.3
+201.3
+190.9
+210.1
+179.0
+176.3
+179.4
+195.0
+179.0
+176.4
+188.5
+180.5
+179.5
+179.4
+177.5
+185.2
+179.9
+178.3
+183.8
+193.9
+183.1
+187.7
+192.7
+181.3
+184.1
+182.5
+178.2
+184.0
+195.4
+179.7
+191.7
+183.7
+185.6
+188.4
+195.0
+184.8
+181.8
+186.2
+177.4
+189.8
+192.1
+192.9
+187.5
+191.5
+189.1
+195.7
+188.0
+192.7
+190.1
+190.1
+196.3
+192.4
+193.1
+178.9
+181.9
+179.2
+188.4
+179.2
+187.5
+179.7
+185.3
+177.2
+180.5
+182.2
+203.8
+186.1
+181.7
+180.8
+187.9
+177.4
+189.5
+189.3
+176.5
+179.2
+190.5
+180.0
+177.1
+183.7
+188.8
+180.6
+220.6
+190.9
+197.9
+182.8
+183.0
+177.9
+182.2
+182.4
+201.5
+181.1
+177.8
+189.6
+193.4
+180.3
+180.2
+175.3
+177.8
+178.3
+178.8
+190.7
+181.8
+185.1
+190.2
+179.1
+179.9
+179.8
+180.6
+181.6
+180.8
+184.6
+184.9
+181.7
+176.3
+182.2
+186.9
+227.1
+184.9
+184.5
+177.5
+180.2
+187.5
+186.1
+183.8
+177.4
+184.1
+188.1
+180.4
+197.4
+209.6
+198.3
+179.5
+183.9
+183.5
+181.8
+178.9
+195.5
+184.7
+191.3
+193.5
+196.8
+197.0
+184.2
+181.9
+187.5
+188.7
+177.7
+186.7
+191.6
+192.8
+194.8
+193.6
+194.7
+187.6
+197.2
+187.5
+176.0
+194.4
+199.9
+188.2
+184.5
+183.2
+186.0
+183.6
+210.5
+183.7
+190.4
+188.6
+179.8
+183.9
+210.2
+194.0
+190.8
+188.3
+186.2
+178.0
+178.3
+194.4
+184.5
+182.3
+179.1
+183.4
+182.9
+185.1
+180.6
+182.1
+189.4
+181.6
+180.5
+190.4
+182.1
+204.0
+192.7
+180.4
+190.7
+179.5
+179.2
+181.5
+186.1
+195.1
+189.7
+189.9
+185.9
+206.2
+187.5
+178.5
+206.2
+208.5
+187.4
+182.0
+192.9
+193.0
+196.5
+190.1
+179.7
+205.9
+187.7
+211.5
+177.5
+185.1
+205.3
+178.9
+179.6
+178.8
+185.9
+180.1
+179.0
+178.2
+181.9
+182.9
+191.5
+194.8
+184.9
+177.9
+186.0
+178.7
+175.2
+178.1
+183.9
+176.2
+196.3
+195.0
+214.4
+177.2
+175.2
+181.4
+191.4
+189.0
+179.6
+181.8
+177.8
+175.9
+176.1
+183.8
+182.1
+178.4
+182.1
+180.6
+177.4
+178.9
+178.7
+182.0
+176.5
+182.1
+189.2
+188.3
+184.6
+177.6
+184.6
+183.6
+182.6
+181.5
+198.4
+179.6
+179.3
+185.1
+189.8
+183.5
+180.9
+175.7
+182.6
+179.1
+181.3
+181.4
+189.8
+183.7
+185.8
+185.9
+178.1
+182.3
+196.3
+220.0
+199.4
+191.3
+186.7
+181.7
+180.7
+180.9
+176.2
+185.3
+180.3
+182.5
+177.5
+182.4
+184.8
+191.3
+185.5
+184.4
+193.8
+186.5
+178.9
+180.6
+182.7
+180.1
+184.8
+179.7
+187.8
+183.7
+190.9
+192.5
+205.5
+193.1
+180.7
+186.4
+179.3
+194.2
+187.8
+190.6
+178.8
+176.7
+181.2
+187.6
+191.3
+182.4
+204.9
+191.0
+193.8
+194.0
+198.4
+181.7
+186.5
+186.4
+182.5
+182.2
+179.0
+180.6
+180.0
+181.1
+178.6
+178.6
+183.3
+189.1
+179.9
+190.2
+187.3
+185.3
+185.0
+185.9
+189.3
+182.6
+183.5
+190.8
+183.4
+185.2
+197.1
+187.5
+182.2
+180.4
+181.3
+178.8
+182.5
+183.2
+174.8
+180.4
+200.9
+181.5
+185.5
+176.6
+179.0
+187.4
+173.8
+192.6
+179.3
+188.7
+198.9
+177.8
+185.5
+177.1
+213.1
+185.7
+189.7
+186.6
+189.2
+188.1
+184.0
+184.5
+178.7
+183.9
+186.3
+199.0
+188.2
+191.9
+181.6
+177.4
+183.8
+179.2
+182.7
+182.1
+178.2
+187.3
+189.0
+188.1
+190.8
+184.1
+188.0
+178.9
+195.8
+179.3
+204.6
+183.3
+178.8
+178.8
+176.9
+179.9
+186.0
+181.6
+199.5
+179.6
+189.0
+204.2
+189.7
+181.2
+184.5
+193.4
+183.7
+180.2
+186.2
+191.0
+195.1
+179.9
+182.6
+188.7
+184.5
+178.9
+194.1
+191.5
+179.9
+198.8
+183.4
+212.7
+179.0
+181.8
+176.5
+181.9
+179.7
+186.2
+187.0
+181.6
+184.9
+199.7
+185.4
+186.1
+179.3
+200.6
+187.7
+195.2
+185.5
+182.2
+189.4
+184.6
+177.9
+182.5
+182.9
+191.4
+192.5
+186.2
+178.4
+197.8
+175.7
+183.2
+187.5
+192.9
+175.8
+195.1
+185.7
+188.6
+191.6
+177.0
+181.8
+188.2
+202.4
+183.8
+184.5
+198.6
+186.4
+180.7
+188.6
+181.4
+178.9
+186.5
+185.5
+187.7
+187.7
+179.1
+184.2
+185.1
+178.0
+182.0
+197.0
+194.9
+193.6
+177.0
+186.6
+179.8
+186.1
+177.7
+182.1
+181.3
+178.0
+184.8
+208.3
+193.1
+187.2
+207.7
+188.2
+186.1
+178.1
+193.3
+182.1
+199.8
+182.7
+196.4
+197.9
+178.8
+191.4
+180.9
+180.5
+184.6
+177.2
+182.4
+183.7
+178.2
+187.1
+178.5
+181.3
+190.5
+179.0
+181.0
+178.0
+185.5
+179.1
+184.9
+184.7
+177.7
+176.7
+183.5
+196.3
+184.2
+190.0
+189.4
+186.0
+181.7
+186.0
+188.7
+187.5
+184.6
+176.3
+177.4
+185.9
+183.4
+179.4
+175.8
+186.1
+178.8
+179.0
+181.6
+175.2
+177.4
+176.8
+177.9
+197.6
+184.9
+176.0
+177.6
+178.4
+184.6
+178.1
+183.2
+180.2
+191.3
+180.0
+176.2
+180.3
+181.8
+187.4
+181.7
+177.1
+182.9
+190.6
+183.9
+177.9
+187.4
+174.9
+186.4
+192.0
+190.2
+198.4
+183.6
+206.3
+184.2
+181.0
+195.6
+277.2
+189.9
+187.0
+196.6
+180.6
+183.0
+208.8
+193.1
+188.9
+186.4
+179.9
+181.7
+185.2
+189.5
+188.0
+181.2
+182.5
+183.5
+190.3
+179.3
+182.3
+179.5
+184.2
+193.3
+178.5
+178.5
+182.3
+184.7
+181.9
+185.0
+181.6
+180.0
+202.6
+178.9
+176.4
+185.0
+190.3
+179.4
+182.9
+194.1
+185.2
+198.6
+177.6
+181.1
+179.8
+183.1
+187.7
+187.5
+185.9
+191.2
+183.1
+184.6
+193.0
+197.6
+183.3
+184.4
+181.6
+184.9
+178.0
+177.4
+181.0
+178.9
+180.4
+181.4
+188.0
+178.2
+181.2
+179.0
+188.1
+176.0
+176.4
+179.6
+179.1
+182.2
+185.6
+176.2
+180.0
+195.4
+177.4
+185.2
+177.5
+181.3
+187.8
+176.7
+200.8
+179.8
+183.8
+179.9
+190.4
+180.3
+178.5
+182.7
+180.3
+179.1
+178.8
+184.3
+176.7
+181.8
+179.9
+175.7
+181.6
+184.5
+183.3
+214.3
+175.7
+188.8
+180.1
+179.9
+182.8
+175.0
+177.4
+217.5
+183.7
+178.3
+184.0
+182.2
+175.4
+184.0
+181.2
+184.5
+174.6
+176.0
+180.1
+173.6
+190.4
+177.5
+181.3
+176.1
+181.5
+199.2
+176.2
+186.0
+178.6
+186.9
+187.1
+172.8
+175.5
+182.1
+175.9
+200.4
+193.1
+178.0
+177.1
+180.6
+182.2
+179.0
+175.8
+182.0
+188.0
+180.1
+207.1
+187.0
+180.6
+183.8
+192.9
+175.7
+193.6
+178.3
+182.2
+179.9
+177.2
+181.3
+177.0
+201.1
+176.2
+175.5
+183.1
+181.3
+176.0
+187.7
+185.7
+179.2
+183.4
+184.8
+176.3
+179.3
+175.2
+185.4
+181.2
+177.2
+179.9
+175.1
+175.7
+193.8
+179.7
+184.6
+181.2
+187.8
+184.9
+182.3
+184.9
+181.7
+186.0
+187.0
+178.5
+174.9
+180.7
+188.9
+181.4
+181.3
+176.2
+182.0
+183.4
+181.3
+181.3
+175.0
+179.7
+186.6
+183.7
+185.1
+180.8
+179.6
+180.6
+193.6
+187.6
+181.0
+176.3
+191.0
+177.5
+186.9
+173.8
+184.1
+178.1
+183.2
+180.2
+194.2
+175.8
+183.6
+175.4
+176.6
+183.7
+177.9
+176.4
+180.8
+179.9
+177.9
+183.0
+176.9
+181.3
+182.2
+182.3
+183.8
+181.1
+180.6
+189.9
+185.6
+184.5
+185.3
+175.3
+192.4
+195.5
+188.2
+180.3
+196.3
+184.1
+178.7
+179.7
+187.0
+177.1
+180.7
+177.5
+177.1
+180.8
+182.0
+177.0
+177.0
+193.1
+194.6
+190.0
+183.5
+180.5
+178.4
+177.4
+178.7
+184.6
+189.6
+188.1
+186.1
+184.2
+178.9
+176.7
+195.8
+178.1
+187.6
+175.4
+180.3
+185.3
+189.0
+177.2
+188.9
+179.0
+184.0
+179.1
+187.3
+199.7
+178.2
+179.1
+175.8
+179.8
+178.8
+196.3
+185.0
+196.3
+181.1
+185.5
+175.8
+189.2
+179.4
+192.0
+182.6
+177.9
+181.1
+179.6
+184.2
+194.6
+185.9
+181.4
+176.5
+178.3
+176.3
+179.1
+175.3
+180.5
+186.7
+177.5
+192.3
+187.7
+178.4
+189.4
+180.4
+180.5
+189.9
+183.8
+190.3
+195.5
+185.6
+177.2
+177.7
+178.7
+189.9
+183.8
+193.1
+185.2
+180.5
+180.5
+191.6
+175.0
+176.6
+178.6
+188.8
+180.7
+185.5
+181.2
+199.5
+193.2
+193.8
+185.8
+182.0
+178.5
+188.7
+190.1
+178.7
+181.5
+180.9
+186.6
+189.8
+194.4
+180.1
+193.0
+178.2
+183.2
+182.6
+177.8
+212.2
+177.5
+178.5
+181.9
+185.8
+177.2
+182.9
+176.7
+175.1
+180.4
+186.0
+179.1
+179.5
+177.2
+182.1
+177.8
+180.1
+180.1
+177.9
+183.6
+189.2
+193.2
+179.6
+176.9
+181.3
+178.4
+177.4
+189.2
+182.1
+195.2
+193.0
+184.5
+180.4
+184.1
+176.2
+180.1
+179.0
+174.8
+181.1
+190.0
+179.9
+192.2
+204.9
+179.2
+180.5
+174.7
+181.6
+181.5
+185.1
+176.7
+184.9
+191.9
+182.2
+182.7
+210.5
+186.1
+181.1
+179.3
+186.4
+176.0
+177.4
+180.9
+187.0
+192.2
+182.9
+182.2
+184.0
+180.3
+177.4
+178.7
+176.8
+176.4
+176.1
+182.0
+178.8
+175.2
+187.6
+184.9
+184.3
+188.7
+178.3
+190.9
+186.3
+175.2
+185.8
+175.6
+184.8
+181.1
+176.8
+179.0
+179.2
+196.5
+175.0
+182.6
+194.4
+173.7
+180.0
+178.3
+181.1
+179.5
+177.6
+185.1
+183.2
+188.6
+186.8
+182.5
+176.4
+175.1
+176.9
+182.4
+180.1
+181.7
+182.8
+184.1
+175.7
+178.7
+177.1
+178.3
+177.3
+176.7
+179.8
+176.8
+177.2
+200.5
+175.7
+181.1
+174.5
+179.3
+183.1
+178.4
+189.2
+186.0
+177.4
+178.3
+187.1
+181.0
+183.3
+191.4
+182.9
+182.6
+199.2
+181.4
+180.5
+180.4
+176.7
+184.4
+189.0
+188.1
+197.0
+181.2
+176.1
+181.0
+180.5
+176.5
+214.9
+178.3
+178.7
+181.4
+180.9
+178.0
+185.8
+182.5
+181.8
+177.4
+186.7
+183.2
+183.2
+183.1
+173.9
+181.1
+179.1
+180.3
+177.7
+181.5
+176.5
+177.1
+189.6
+191.5
+183.2
+180.0
+180.9
+183.3
+188.3
+178.4
+185.4
+176.1
+183.2
+181.1
+180.3
+176.4
+177.5
+186.8
+176.3
+338.9
+184.9
+177.0
+187.1
+175.8
+180.0
+182.5
+184.9
+175.2
+179.6
+176.9
+178.7
+177.5
+178.3
+178.9
+180.7
+182.6
+179.3
+177.0
+180.5
+179.2
+177.2
+188.0
+194.8
+183.6
+177.3
+179.1
+185.3
+177.5
+187.6
+180.9
+188.0
+174.8
+183.6
+183.0
+182.9
+178.1
+182.0
+185.9
+176.5
+182.1
+188.5
+179.9
+176.0
+184.3
+185.9
+179.2
+184.3
+181.3
+186.3
+186.7
+177.5
+188.9
+178.8
+211.3
+188.0
+178.5
+192.6
+176.4
+187.1
+189.5
+195.7
+188.5
+185.1
+182.5
+176.6
+182.5
+187.3
+180.5
+191.9
+178.3
+177.1
+188.3
+181.0
+178.0
+187.1
+175.1
+182.3
+177.4
+177.6
+181.2
+179.2
+183.8
+183.2
+173.3
+177.6
+178.6
+179.4
+180.5
+183.9
+176.3
+178.4
+178.9
+175.9
+179.2
+175.4
+183.5
+188.9
+176.5
+185.8
+179.7
+196.8
+185.9
+178.4
+176.4
+177.6
+176.0
+177.9
+181.7
+176.2
+180.6
+179.9
+186.0
+177.2
+178.9
+179.1
+186.6
+176.0
+194.6
+179.2
+181.5
+176.2
+177.2
+179.3
+181.3
+179.2
+181.7
+177.5
+186.6
+179.5
+177.4
+179.4
+177.9
+181.9
+181.3
+177.4
+176.0
+177.8
+185.2
+180.8
+181.3
+182.1
+178.2
+179.5
+185.6
+179.5
+182.5
+186.1
+188.7
+178.7
+186.8
+179.2
+197.7
+180.8
+181.4
+178.1
+207.1
+182.7
+185.5
+186.1
+180.1
+176.1
+177.6
+174.9
+176.1
+180.6
+184.5
+179.2
+186.1
+180.5
+179.5
+179.3
+182.2
+181.8
+184.6
+180.0
+177.1
+176.7
+177.6
+180.8
+176.5
+177.3
+176.8
+176.4
+188.7
+187.6
+178.5
+178.0
+179.3
+181.4
+183.2
+193.8
+178.3
+181.2
+180.4
+183.5
+179.8
+177.4
+183.2
+183.3
+176.6
+176.2
+216.9
+177.8
+177.0
+178.0
+175.3
+189.4
+182.6
+182.9
+183.6
+180.4
+177.2
+176.0
+177.9
+175.1
+182.1
+178.3
+178.5
+186.2
+177.7
+178.0
+183.3
+180.4
+197.6
+181.7
+179.9
+184.0
+194.8
+184.8
+189.4
+191.8
+176.6
+186.2
+180.3
+177.7
+197.0
+187.0
+188.1
+190.1
+176.8
+179.3
+185.4
+174.7
+189.6
+184.2
+178.0
+180.4
+183.4
+179.5
+177.7
+178.7
+186.9
+183.7
+177.2
+173.6
+184.7
+180.4
+183.1
+175.6
+179.6
+184.8
+185.6
+176.2
+177.7
+180.0
+174.7
+183.1
+181.6
+178.0
+178.8
+185.4
+181.2
+178.0
+188.7
+177.1
+189.3
+177.6
+180.6
+181.6
+175.9
+180.7
+179.1
+182.4
+186.7
+175.8
+185.1
+176.7
+180.3
+195.7
+191.3
+191.1
+181.3
+180.5
+179.3
+184.3
+177.1
+182.4
+179.4
+188.8
+174.5
+177.2
+178.4
+179.8
+183.3
+175.4
+184.1
+176.8
+182.4
+177.8
+178.7
+178.6
+189.6
+182.0
+191.2
+179.8
+179.3
+178.6
+183.0
+188.8
+205.3
+180.1
+190.6
+184.4
+179.9
+178.6
+174.7
+180.6
+193.3
+175.3
+175.5
+193.9
+180.4
+177.2
+175.6
+177.0
+182.3
+183.5
+181.9
+179.6
+182.8
+180.9
+180.6
+183.7
+185.0
+176.7
+190.5
+176.2
+179.0
+178.8
+180.0
+181.5
+174.3
+177.3
+179.2
+178.3
+184.7
+174.2
+177.3
+178.0
+178.9
+182.9
+189.8
+183.3
+183.0
+182.5
+176.3
+176.8
+177.5
+176.2
+183.1
+175.4
+175.0
+182.5
+174.9
+185.8
+181.4
+178.4
+183.8
+178.0
+265.0
+178.5
+185.0
+177.4
+179.2
+175.8
+183.0
+184.5
+195.3
+178.5
+178.2
+179.7
+175.0
+187.5
+182.7
+180.3
+181.0
+177.5
+181.5
+179.9
+179.0
+180.0
+182.6
+178.5
+179.6
+181.4
+188.0
+188.2
+179.1
+180.8
+178.5
+181.3
+179.9
+182.0
+181.8
+181.3
+186.6
+197.8
+205.8
+188.2
+194.9
+182.2
+184.6
+188.9
+189.4
+183.4
+179.2
+182.6
+184.6
+183.6
+184.3
+182.5
+181.1
+181.6
+178.9
+179.7
+176.3
+179.4
+180.2
+178.4
+179.6
+190.1
+178.5
+174.4
+177.3
+176.1
+175.3
+175.0
+178.9
+175.1
+181.3
+175.0
+176.0
+192.2
+189.2
+182.4
+179.2
+173.4
+177.9
+178.4
+175.5
+175.9
+199.0
+196.6
+181.7
+181.2
+177.6
+174.7
+174.3
+181.3
+178.9
+203.2
+176.3
+175.8
+192.3
+180.8
+184.8
+179.9
+182.4
+180.0
+174.3
+187.2
+181.4
+176.0
+174.4
+182.4
+186.8
+191.1
+177.1
+178.2
+176.8
+182.6
+184.6
+181.5
+185.4
+178.9
+176.6
+179.6
+175.1
+179.9
+176.9
+176.7
+186.2
+192.9
+183.5
+182.4
+175.5
+176.9
+180.6
+185.7
+174.2
+174.2
+178.9
+178.8
+179.2
+194.9
+177.5
+174.0
+179.0
+180.7
+174.0
+180.0
+178.3
+179.8
+180.0
+175.6
+174.9
+180.9
+177.3
+212.6
+196.0
+183.1
+186.5
+178.4
+185.9
+185.5
+176.8
+178.7
+174.0
+176.6
+179.0
+182.3
+176.6
+185.0
+175.7
+178.5
+176.4
+176.3
+186.3
+222.5
+185.7
+177.1
+183.6
+176.9
+184.0
+175.7
+174.4
+184.2
+269.8
+182.5
+174.6
+178.5
+176.1
+178.9
+177.9
+181.9
+176.8
+174.2
+181.6
+191.2
+179.1
+175.3
+182.2
+180.1
+175.2
+182.3
+175.6
+177.1
+175.1
+174.7
+188.2
+176.9
+183.6
+175.9
+175.5
+174.7
+182.4
+181.2
+179.5
+190.3
+184.8
+237.1
+178.3
+178.7
+184.1
+174.5
+178.3
+178.6
+181.8
+182.2
+190.2
+179.9
+181.0
+180.3
+177.2
+179.2
+179.2
+178.2
+183.0
+177.7
+180.1
+182.6
+196.6
+178.9
+177.0
+176.1
+178.3
+182.9
+176.5
+209.4
+181.1
+199.5
+186.3
+177.6
+182.7
+185.4
+180.2
+186.2
+187.4
+176.4
+182.8
+221.0
+179.0
+178.9
+178.4
+186.8
+174.1
+174.9
+176.8
+190.0
+178.9
+182.4
+178.7
+177.6
+179.4
+173.6
+178.1
+179.8
+177.8
+177.5
+187.5
+209.5
+178.0
+177.2
+179.3
+179.8
+179.8
+174.4
+177.1
+180.2
+182.5
+181.1
+184.7
+179.6
+193.0
+182.7
+181.6
+177.7
+178.2
+181.6
+186.6
+177.2
+178.1
+189.3
+174.3
+180.2
+186.2
+189.8
+185.9
+176.8
+178.8
+175.1
+175.5
+179.1
+180.9
+186.1
+187.0
+186.2
+187.6
+187.5
+197.8
+180.4
+196.7
+176.5
+177.6
+176.2
+180.8
+175.9
+182.8
+178.8
+184.6
+179.5
+175.6
+187.5
+175.7
+201.6
+188.2
+183.4
+184.2
+178.7
+177.0
+174.9
+181.9
+177.6
+177.7
+179.6
+176.0
+178.3
+181.5
+177.5
+184.7
+183.9
+180.9
+178.9
+177.8
+176.6
+188.4
+191.0
+189.6
+178.1
+177.9
+186.1
+178.7
+184.3
+176.5
+179.6
+174.1
+184.4
+176.8
+182.3
+179.5
+188.8
+180.2
+176.1
+198.4
+178.4
+188.6
+191.0
+180.4
+179.5
+176.0
+188.1
+189.6
+192.6
+177.0
+189.1
+177.5
+178.8
+186.8
+178.6
+180.5
+184.0
+178.7
+179.0
+176.2
+176.7
+185.2
+192.3
+178.0
+175.7
+181.0
+183.0
+175.7
+174.6
+176.7
+177.8
+179.0
+177.4
+176.7
+182.5
+194.0
+181.4
+178.7
+176.2
+176.7
+204.2
+178.3
+190.6
+188.5
+177.5
+180.6
+178.1
+175.2
+276.8
+353.6
+297.8
+235.1
+211.7
+213.4
+213.5
+191.5
+178.8
+186.2
+175.4
+178.2
+184.5
+179.9
+182.0
+179.3
+178.6
+192.5
+177.7
+179.2
+194.9
+183.1
+178.6
+179.9
+192.5
+184.1
+186.6
+181.2
+175.4
+197.2
+179.6
+184.6
+197.6
+180.6
+189.6
+175.3
+185.6
+174.5
+178.9
+174.2
+179.6
+173.9
+182.5
+185.6
+177.4
+191.4
+183.8
+177.0
+181.2
+176.3
+177.3
+173.7
+177.5
+178.9
+178.2
+177.3
+177.7
+187.8
+181.6
+178.4
+176.4
+180.8
+178.5
+189.5
+186.0
+188.4
+182.2
+184.0
+176.5
+179.5
+185.3
+173.8
+190.0
+180.2
+189.1
+184.9
+175.8
+182.2
+177.9
+176.4
+184.1
+179.5
+181.8
+175.7
+179.7
+178.7
+185.9
+180.5
+180.9
+175.5
+176.1
+174.4
+175.1
+195.2
+174.9
+190.5
+183.8
+188.7
+182.5
+179.5
+177.0
+174.9
+185.6
+180.8
+192.8
+185.2
+184.0
+177.7
+191.7
+185.3
+185.4
+186.6
+182.9
+181.1
+191.2
+183.0
+176.6
+187.7
+181.9
+179.5
+178.7
+176.9
+178.5
+182.1
+175.4
+175.9
+183.8
+180.6
+191.1
+177.0
+184.6
+188.7
+176.0
+181.4
+188.2
+181.1
+180.0
+178.9
+182.1
+179.6
+179.5
+174.5
+177.6
+179.9
+175.3
+185.2
+175.4
+185.1
+184.9
+182.0
+178.4
+177.0
+182.3
+193.8
+181.6
+197.4
+180.4
+180.9
+182.0
+181.0
+185.8
+178.5
+180.5
+182.3
+175.7
+176.5
+182.8
+176.8
+178.3
+179.5
+181.8
+175.1
+180.2
+179.6
+176.7
+174.6
+180.5
+179.7
+178.9
+177.1
+184.2
+178.4
+175.0
+183.7
+178.3
+179.1
+175.3
+187.5
+189.2
+176.7
+205.6
+179.6
+179.6
+179.1
+182.1
+178.6
+182.2
+181.6
+181.9
+188.8
+184.7
+185.3
+182.5
+174.2
+176.5
+190.1
+180.6
+182.7
+182.2
+179.5
+179.0
+184.4
+175.4
+178.2
+174.6
+179.0
+188.4
+175.9
+173.8
+180.2
+187.3
+186.3
+176.3
+174.9
+178.6
+178.2
+177.0
+180.0
+177.2
+173.5
+195.4
+180.5
+181.6
+177.2
+176.7
+175.3
+174.8
+179.7
+175.0
+176.4
+181.8
+183.0
+180.0
+177.0
+185.8
+183.2
+181.0
+176.8
+177.9
+186.1
+182.5
+174.4
+177.1
+176.7
+176.3
+180.3
+178.9
+178.3
+175.8
+179.9
+190.6
+182.8
+183.4
+177.9
+177.7
+180.0
+202.0
+184.5
+179.5
+181.5
+174.8
+194.2
+185.8
+177.0
+183.9
+177.6
+202.4
+179.9
+175.4
+174.8
+176.7
+177.9
+176.6
+176.5
+181.2
+181.3
+177.4
+179.3
+177.8
+176.2
+197.2
+180.9
+178.2
+184.6
+184.7
+191.0
+182.9
+179.9
+180.3
+177.4
+182.1
+181.9
+182.2
+174.9
+193.4
+175.1
+203.2
+176.0
+180.3
+180.0
+186.3
+174.8
+177.9
+196.1
+177.6
+183.5
+176.2
+187.6
+178.5
+180.6
+178.2
+180.7
+177.6
+176.6
+173.5
+178.7
+175.0
+179.0
+175.5
+174.2
+178.2
+176.6
+176.3
+179.4
+178.6
+175.2
+175.9
+175.0
+179.5
+176.9
+184.0
+184.6
+179.9
+175.3
+176.2
+179.1
+182.8
+180.5
+173.4
+176.0
+198.9
+177.0
+189.7
+183.6
+179.5
+176.5
+175.5
+175.5
+176.4
+182.9
+178.7
+177.5
+180.6
+175.0
+178.9
+177.7
+178.0
+178.6
+176.0
+177.6
+180.8
+179.6
+184.3
+190.2
+177.7
+178.1
+175.0
+178.6
+179.6
+185.1
+193.7
+179.8
+179.3
+178.6
+180.4
+174.9
+177.8
+187.4
+183.7
+181.6
+177.7
+185.4
+180.6
+178.5
+182.8
+179.9
+177.8
+178.0
+184.3
+191.0
+181.1
+197.9
+181.1
+197.8
+175.6
+176.9
+177.9
+187.4
+180.8
+180.6
+174.9
+180.8
+175.7
+176.4
+179.9
+178.3
+178.3
+178.4
+196.4
+177.3
+184.3
+177.3
+176.5
+181.0
+175.0
+179.2
+178.1
+183.3
+177.0
+175.2
+177.2
+173.5
+176.5
+177.0
+178.6
+181.3
+189.2
+186.4
+177.4
+181.7
+176.2
+194.1
+177.9
+186.6
+182.6
+176.6
+175.4
+250.3
+178.7
+183.0
+182.7
+183.1
+183.6
+178.8
+178.3
+179.1
+177.7
+177.9
+186.2
+195.4
+179.2
+183.3
+183.8
+186.3
+182.7
+178.9
+196.0
+177.1
+184.5
+188.3
+188.4
+181.5
+190.1
+179.0
+177.2
+189.1
+184.1
+184.2
+178.7
+187.4
+182.5
+189.8
+181.1
+186.0
+178.8
+178.0
+176.9
+180.6
+174.3
+180.4
+176.7
+175.5
+193.7
+189.7
+196.6
+178.9
+186.3
+182.5
+185.7
+175.7
+176.0
+194.1
+181.0
+178.6
+178.4
+186.8
+175.6
+185.4
+180.7
+184.7
+188.1
+180.4
+183.0
+178.4
+185.1
+181.8
+175.8
+178.9
+177.9
+177.9
+176.5
+290.3
+181.8
+180.8
+183.9
+190.8
+179.0
+183.7
+181.9
+177.5
+178.4
+179.4
+179.9
+174.2
+182.7
+182.9
+178.8
+179.2
+183.2
+181.8
+175.6
+179.0
+175.7
+178.1
+179.2
+183.8
+187.8
+187.3
+175.7
+175.0
+185.5
+175.3
+181.9
+176.7
+184.6
+185.8
+181.1
+186.6
+178.8
+183.4
+175.1
+178.4
+179.6
+176.7
+177.1
+176.5
+181.7
+199.1
+194.8
+176.5
+182.2
+189.9
+177.6
+179.3
+184.9
+178.1
+176.4
+184.6
+174.6
+188.6
+183.7
+178.1
+177.7
+186.1
+176.3
+180.9
+180.3
+181.0
+180.0
+180.0
+180.4
+174.8
+179.5
+176.5
+179.9
+175.6
+184.0
+176.4
+191.6
+178.4
+184.8
+186.7
+197.0
diff --git a/iproute2/netem/maketable.c b/iproute2/netem/maketable.c
new file mode 100644
index 0000000..a5452b6
--- /dev/null
+++ b/iproute2/netem/maketable.c
@@ -0,0 +1,232 @@
+/*
+ * Experimental data distribution table generator
+ * Taken from the uncopyrighted NISTnet code (public domain).
+ *
+ * Read in a series of "random" data values, either
+ * experimentally or generated from some probability distribution.
+ * From this, create the inverse distribution table used to approximate
+ * the distribution.
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <math.h>
+#include <malloc.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+
+double *
+readdoubles(FILE *fp, int *number)
+{
+ struct stat info;
+ double *x;
+ int limit;
+ int n=0, i;
+
+ fstat(fileno(fp), &info);
+ if (info.st_size > 0) {
+ limit = 2*info.st_size/sizeof(double); /* @@ approximate */
+ } else {
+ limit = 10000;
+ }
+
+ x = calloc(limit, sizeof(double));
+ if (!x) {
+ perror("double alloc");
+ exit(3);
+ }
+
+ for (i=0; i<limit; ++i){
+ fscanf(fp, "%lf", &x[i]);
+ if (feof(fp))
+ break;
+ ++n;
+ }
+ *number = n;
+ return x;
+}
+
+void
+arraystats(double *x, int limit, double *mu, double *sigma, double *rho)
+{
+ int n=0, i;
+ double sumsquare=0.0, sum=0.0, top=0.0;
+ double sigma2=0.0;
+
+ for (i=0; i<limit; ++i){
+ sumsquare += x[i]*x[i];
+ sum += x[i];
+ ++n;
+ }
+ *mu = sum/(double)n;
+ *sigma = sqrt((sumsquare - (double)n*(*mu)*(*mu))/(double)(n-1));
+
+ for (i=1; i < n; ++i){
+ top += ((double)x[i]- *mu)*((double)x[i-1]- *mu);
+ sigma2 += ((double)x[i-1] - *mu)*((double)x[i-1] - *mu);
+
+ }
+ *rho = top/sigma2;
+}
+
+/* Create a (normalized) distribution table from a set of observed
+ * values. The table is fixed to run from (as it happens) -4 to +4,
+ * with granularity .00002.
+ */
+
+#define TABLESIZE 16384/4
+#define TABLEFACTOR 8192
+#ifndef MINSHORT
+#define MINSHORT -32768
+#define MAXSHORT 32767
+#endif
+
+/* Since entries in the inverse are scaled by TABLEFACTOR, and can't be bigger
+ * than MAXSHORT, we don't bother looking at a larger domain than this:
+ */
+#define DISTTABLEDOMAIN ((MAXSHORT/TABLEFACTOR)+1)
+#define DISTTABLEGRANULARITY 50000
+#define DISTTABLESIZE (DISTTABLEDOMAIN*DISTTABLEGRANULARITY*2)
+
+static int *
+makedist(double *x, int limit, double mu, double sigma)
+{
+ int *table;
+ int i, index, first=DISTTABLESIZE, last=0;
+ double input;
+
+ table = calloc(DISTTABLESIZE, sizeof(int));
+ if (!table) {
+ perror("table alloc");
+ exit(3);
+ }
+
+ for (i=0; i < limit; ++i) {
+ /* Normalize value */
+ input = (x[i]-mu)/sigma;
+
+ index = (int)rint((input+DISTTABLEDOMAIN)*DISTTABLEGRANULARITY);
+ if (index < 0) index = 0;
+ if (index >= DISTTABLESIZE) index = DISTTABLESIZE-1;
+ ++table[index];
+ if (index > last)
+ last = index +1;
+ if (index < first)
+ first = index;
+ }
+ return table;
+}
+
+/* replace an array by its cumulative distribution */
+static void
+cumulativedist(int *table, int limit, int *total)
+{
+ int accum=0;
+
+ while (--limit >= 0) {
+ accum += *table;
+ *table++ = accum;
+ }
+ *total = accum;
+}
+
+static short *
+inverttable(int *table, int inversesize, int tablesize, int cumulative)
+{
+ int i, inverseindex, inversevalue;
+ short *inverse;
+ double findex, fvalue;
+
+ inverse = (short *)malloc(inversesize*sizeof(short));
+ for (i=0; i < inversesize; ++i) {
+ inverse[i] = MINSHORT;
+ }
+ for (i=0; i < tablesize; ++i) {
+ findex = ((double)i/(double)DISTTABLEGRANULARITY) - DISTTABLEDOMAIN;
+ fvalue = (double)table[i]/(double)cumulative;
+ inverseindex = (int)rint(fvalue*inversesize);
+ inversevalue = (int)rint(findex*TABLEFACTOR);
+ if (inversevalue <= MINSHORT) inversevalue = MINSHORT+1;
+ if (inversevalue > MAXSHORT) inversevalue = MAXSHORT;
+ inverse[inverseindex] = inversevalue;
+ }
+ return inverse;
+
+}
+
+/* Run simple linear interpolation over the table to fill in missing entries */
+static void
+interpolatetable(short *table, int limit)
+{
+ int i, j, last, lasti = -1;
+
+ last = MINSHORT;
+ for (i=0; i < limit; ++i) {
+ if (table[i] == MINSHORT) {
+ for (j=i; j < limit; ++j)
+ if (table[j] != MINSHORT)
+ break;
+ if (j < limit) {
+ table[i] = last + (i-lasti)*(table[j]-last)/(j-lasti);
+ } else {
+ table[i] = last + (i-lasti)*(MAXSHORT-last)/(limit-lasti);
+ }
+ } else {
+ last = table[i];
+ lasti = i;
+ }
+ }
+}
+
+static void
+printtable(const short *table, int limit)
+{
+ int i;
+
+ printf("# This is the distribution table for the experimental distribution.\n");
+
+ for (i=0 ; i < limit; ++i) {
+ printf("%d%c", table[i],
+ (i % 8) == 7 ? '\n' : ' ');
+ }
+}
+
+int
+main(int argc, char **argv)
+{
+ FILE *fp;
+ double *x;
+ double mu, sigma, rho;
+ int limit;
+ int *table;
+ short *inverse;
+ int total;
+
+ if (argc > 1) {
+ if (!(fp = fopen(argv[1], "r"))) {
+ perror(argv[1]);
+ exit(1);
+ }
+ } else {
+ fp = stdin;
+ }
+ x = readdoubles(fp, &limit);
+ if (limit <= 0) {
+ fprintf(stderr, "Nothing much read!\n");
+ exit(2);
+ }
+ arraystats(x, limit, &mu, &sigma, &rho);
+#ifdef DEBUG
+ fprintf(stderr, "%d values, mu %10.4f, sigma %10.4f, rho %10.4f\n",
+ limit, mu, sigma, rho);
+#endif
+
+ table = makedist(x, limit, mu, sigma);
+ free((void *) x);
+ cumulativedist(table, DISTTABLESIZE, &total);
+ inverse = inverttable(table, TABLESIZE, DISTTABLESIZE, total);
+ interpolatetable(inverse, TABLESIZE);
+ printtable(inverse, TABLESIZE);
+ return 0;
+}
diff --git a/iproute2/netem/normal.c b/iproute2/netem/normal.c
new file mode 100644
index 0000000..dbdebb1
--- /dev/null
+++ b/iproute2/netem/normal.c
@@ -0,0 +1,51 @@
+/*
+ * Normal distribution table generator
+ * Taken from the uncopyrighted NISTnet code.
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <math.h>
+#include <string.h>
+#include <limits.h>
+
+#include <linux/types.h>
+#include <linux/pkt_sched.h>
+
+#define TABLESIZE 16384
+#define TABLEFACTOR NETEM_DIST_SCALE
+
+static double
+normal(double x, double mu, double sigma)
+{
+ return .5 + .5*erf((x-mu)/(sqrt(2.0)*sigma));
+}
+
+
+int
+main(int argc, char **argv)
+{
+ int i, n;
+ double x;
+ double table[TABLESIZE+1];
+
+ for (x = -10.0; x < 10.05; x += .00005) {
+ i = rint(TABLESIZE * normal(x, 0.0, 1.0));
+ table[i] = x;
+ }
+
+
+ printf("# This is the distribution table for the normal distribution.\n");
+ for (i = n = 0; i < TABLESIZE; i += 4) {
+ int value = (int) rint(table[i]*TABLEFACTOR);
+ if (value < SHRT_MIN) value = SHRT_MIN;
+ if (value > SHRT_MAX) value = SHRT_MAX;
+
+ printf(" %d", value);
+ if (++n == 8) {
+ putchar('\n');
+ n = 0;
+ }
+ }
+
+ return 0;
+}
diff --git a/iproute2/netem/pareto.c b/iproute2/netem/pareto.c
new file mode 100644
index 0000000..8aa647b
--- /dev/null
+++ b/iproute2/netem/pareto.c
@@ -0,0 +1,41 @@
+/*
+ * Pareto distribution table generator
+ * Taken from the uncopyrighted NISTnet code.
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <math.h>
+#include <limits.h>
+
+#include <linux/types.h>
+#include <linux/pkt_sched.h>
+
+static const double a=3.0;
+#define TABLESIZE 16384
+#define TABLEFACTOR NETEM_DIST_SCALE
+
+int
+main(int argc, char **argv)
+{
+ int i, n;
+ double dvalue;
+
+ printf("# This is the distribution table for the pareto distribution.\n");
+
+ for (i = 65536, n = 0; i > 0; i -= 16) {
+ dvalue = (double)i/(double)65536;
+ dvalue = 1.0/pow(dvalue, 1.0/a);
+ dvalue -= 1.5;
+ dvalue *= (4.0/3.0)*(double)TABLEFACTOR;
+ if (dvalue > 32767)
+ dvalue = 32767;
+
+ printf(" %d", (int)rint(dvalue));
+ if (++n == 8) {
+ putchar('\n');
+ n = 0;
+ }
+ }
+
+ return 0;
+}
diff --git a/iproute2/netem/paretonormal.c b/iproute2/netem/paretonormal.c
new file mode 100644
index 0000000..ed75f28
--- /dev/null
+++ b/iproute2/netem/paretonormal.c
@@ -0,0 +1,82 @@
+/*
+ * Paretoormal distribution table generator
+ *
+ * This distribution is simply .25*normal + .75*pareto; a combination
+ * which seems to match experimentally observed distributions reasonably
+ * well, but is computationally easy to handle.
+ * The entries represent a scaled inverse of the cumulative distribution
+ * function.
+ *
+ * Taken from the uncopyrighted NISTnet code.
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdlib.h>
+#include <string.h>
+#include <math.h>
+#include <limits.h>
+#include <malloc.h>
+
+#include <linux/types.h>
+#include <linux/pkt_sched.h>
+
+#define TABLESIZE 16384
+#define TABLEFACTOR NETEM_DIST_SCALE
+
+static double
+normal(double x, double mu, double sigma)
+{
+ return .5 + .5*erf((x-mu)/(sqrt(2.0)*sigma));
+}
+
+static const double a=3.0;
+
+static int
+paretovalue(int i)
+{
+ double dvalue;
+
+ i = 65536-4*i;
+ dvalue = (double)i/(double)65536;
+ dvalue = 1.0/pow(dvalue, 1.0/a);
+ dvalue -= 1.5;
+ dvalue *= (4.0/3.0)*(double)TABLEFACTOR;
+ if (dvalue > 32767)
+ dvalue = 32767;
+ return (int)rint(dvalue);
+}
+
+int
+main(int argc, char **argv)
+{
+ int i,n;
+ double x;
+ double table[TABLESIZE+1];
+
+ for (x = -10.0; x < 10.05; x += .00005) {
+ i = rint(TABLESIZE*normal(x, 0.0, 1.0));
+ table[i] = x;
+ }
+ printf(
+"# This is the distribution table for the paretonormal distribution.\n"
+ );
+
+ for (i = n = 0; i < TABLESIZE; i += 4) {
+ int normvalue, parvalue, value;
+
+ normvalue = (int) rint(table[i]*TABLEFACTOR);
+ parvalue = paretovalue(i);
+
+ value = (normvalue+3*parvalue)/4;
+ if (value < SHRT_MIN) value = SHRT_MIN;
+ if (value > SHRT_MAX) value = SHRT_MAX;
+
+ printf(" %d", value);
+ if (++n == 8) {
+ putchar('\n');
+ n = 0;
+ }
+ }
+
+ return 0;
+}
diff --git a/iproute2/netem/stats.c b/iproute2/netem/stats.c
new file mode 100644
index 0000000..ed70f16
--- /dev/null
+++ b/iproute2/netem/stats.c
@@ -0,0 +1,77 @@
+/*
+ * Experimental data distribution table generator
+ * Taken from the uncopyrighted NISTnet code (public domain).
+ *
+ * Rread in a series of "random" data values, either
+ * experimentally or generated from some probability distribution.
+ * From this, report statistics.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <math.h>
+#include <malloc.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+void
+stats(FILE *fp)
+{
+ struct stat info;
+ double *x;
+ int limit;
+ int n=0, i;
+ double mu=0.0, sigma=0.0, sumsquare=0.0, sum=0.0, top=0.0, rho=0.0;
+ double sigma2=0.0;
+
+ fstat(fileno(fp), &info);
+ if (info.st_size > 0) {
+ limit = 2*info.st_size/sizeof(double); /* @@ approximate */
+ } else {
+ limit = 10000;
+ }
+ x = (double *)malloc(limit*sizeof(double));
+
+ for (i=0; i<limit; ++i){
+ fscanf(fp, "%lf", &x[i]);
+ if (feof(fp))
+ break;
+ sumsquare += x[i]*x[i];
+ sum += x[i];
+ ++n;
+ }
+ mu = sum/(double)n;
+ sigma = sqrt((sumsquare - (double)n*mu*mu)/(double)(n-1));
+
+ for (i=1; i < n; ++i){
+ top += ((double)x[i]-mu)*((double)x[i-1]-mu);
+ sigma2 += ((double)x[i-1] - mu)*((double)x[i-1] - mu);
+
+ }
+ rho = top/sigma2;
+
+ printf("mu = %12.6f\n", mu);
+ printf("sigma = %12.6f\n", sigma);
+ printf("rho = %12.6f\n", rho);
+ /*printf("sigma2 = %10.4f\n", sqrt(sigma2/(double)(n-1)));*/
+ /*printf("correlation rho = %10.6f\n", top/((double)(n-1)*sigma*sigma));*/
+}
+
+
+int
+main(int argc, char **argv)
+{
+ FILE *fp;
+
+ if (argc > 1) {
+ fp = fopen(argv[1], "r");
+ if (!fp) {
+ perror(argv[1]);
+ exit(1);
+ }
+ } else {
+ fp = stdin;
+ }
+ stats(fp);
+ return 0;
+}
diff --git a/iproute2/tc/Android.mk b/iproute2/tc/Android.mk
new file mode 100644
index 0000000..467b08a
--- /dev/null
+++ b/iproute2/tc/Android.mk
@@ -0,0 +1,25 @@
+LOCAL_PATH := $(call my-dir)
+
+include $(CLEAR_VARS)
+LOCAL_SRC_FILES := tc.c tc_exec.c tc_qdisc.c q_cbq.c tc_util.c tc_class.c tc_core.c m_action.c \
+ m_estimator.c tc_filter.c tc_monitor.c tc_stab.c tc_cbq.c \
+ tc_estimator.c f_u32.c m_police.c q_ingress.c m_mirred.c q_htb.c
+
+LOCAL_MODULE := tc
+
+LOCAL_SYSTEM_SHARED_LIBRARIES := \
+ libc libm libdl
+
+LOCAL_SHARED_LIBRARIES += libiprouteutil libnetlink
+
+LOCAL_C_INCLUDES := $(LOCAL_PATH)/../include
+
+LOCAL_CFLAGS := -O2 -g -W -Wall -Wno-pointer-arith -Wno-sign-compare -Werror \
+ -Wno-unused-parameter \
+ -Wno-missing-field-initializers
+
+# This is a work around for b/18403920
+LOCAL_LDFLAGS := -Wl,--no-gc-sections
+
+include $(BUILD_EXECUTABLE)
+
diff --git a/iproute2/tc/MODULE_LICENSE_GPL b/iproute2/tc/MODULE_LICENSE_GPL
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/iproute2/tc/MODULE_LICENSE_GPL
diff --git a/iproute2/tc/Makefile b/iproute2/tc/Makefile
new file mode 100644
index 0000000..f5bea87
--- /dev/null
+++ b/iproute2/tc/Makefile
@@ -0,0 +1,187 @@
+TCOBJ= tc.o tc_qdisc.o tc_class.o tc_filter.o tc_util.o tc_monitor.o \
+ tc_exec.o tc_bpf.o m_police.o m_estimator.o m_action.o m_ematch.o \
+ emp_ematch.yacc.o emp_ematch.lex.o
+
+include ../Config
+
+ifeq ($(IP_CONFIG_SETNS),y)
+ CFLAGS += -DHAVE_SETNS
+endif
+
+SHARED_LIBS ?= y
+
+TCMODULES :=
+TCMODULES += q_fifo.o
+TCMODULES += q_sfq.o
+TCMODULES += q_red.o
+TCMODULES += q_prio.o
+TCMODULES += q_tbf.o
+TCMODULES += q_cbq.o
+TCMODULES += q_rr.o
+TCMODULES += q_multiq.o
+TCMODULES += q_netem.o
+TCMODULES += q_choke.o
+TCMODULES += q_sfb.o
+TCMODULES += f_rsvp.o
+TCMODULES += f_u32.o
+TCMODULES += f_route.o
+TCMODULES += f_fw.o
+TCMODULES += f_basic.o
+TCMODULES += f_bpf.o
+TCMODULES += f_flow.o
+TCMODULES += f_cgroup.o
+TCMODULES += f_flower.o
+TCMODULES += q_dsmark.o
+TCMODULES += q_gred.o
+TCMODULES += f_tcindex.o
+TCMODULES += q_ingress.o
+TCMODULES += q_hfsc.o
+TCMODULES += q_htb.o
+TCMODULES += q_drr.o
+TCMODULES += q_qfq.o
+TCMODULES += m_gact.o
+TCMODULES += m_mirred.o
+TCMODULES += m_nat.o
+TCMODULES += m_pedit.o
+TCMODULES += m_skbedit.o
+TCMODULES += m_csum.o
+TCMODULES += m_simple.o
+TCMODULES += m_vlan.o
+TCMODULES += m_connmark.o
+TCMODULES += m_bpf.o
+TCMODULES += p_ip.o
+TCMODULES += p_icmp.o
+TCMODULES += p_tcp.o
+TCMODULES += p_udp.o
+TCMODULES += em_nbyte.o
+TCMODULES += em_cmp.o
+TCMODULES += em_u32.o
+TCMODULES += em_canid.o
+TCMODULES += em_meta.o
+TCMODULES += q_mqprio.o
+TCMODULES += q_codel.o
+TCMODULES += q_fq_codel.o
+TCMODULES += q_fq.o
+TCMODULES += q_pie.o
+TCMODULES += q_hhf.o
+TCMODULES += q_clsact.o
+TCMODULES += e_bpf.o
+
+ifeq ($(TC_CONFIG_IPSET), y)
+ ifeq ($(TC_CONFIG_XT), y)
+ TCMODULES += em_ipset.o
+ endif
+endif
+
+TCSO :=
+ifeq ($(TC_CONFIG_ATM),y)
+ TCSO += q_atm.so
+endif
+
+ifeq ($(TC_CONFIG_XT),y)
+ TCSO += m_xt.so
+else
+ ifeq ($(TC_CONFIG_XT_OLD),y)
+ TCSO += m_xt_old.so
+ else
+ ifeq ($(TC_CONFIG_XT_OLD_H),y)
+ CFLAGS += -DTC_CONFIG_XT_H
+ TCSO += m_xt_old.so
+ else
+ TCMODULES += m_ipt.o
+ endif
+ endif
+endif
+
+ifeq ($(TC_CONFIG_ELF),y)
+ CFLAGS += -DHAVE_ELF
+ LDLIBS += -lelf
+endif
+
+TCOBJ += $(TCMODULES)
+LDLIBS += -L. -ltc -lm
+
+ifeq ($(SHARED_LIBS),y)
+LDLIBS += -ldl
+LDFLAGS += -Wl,-export-dynamic
+endif
+
+TCLIB := tc_core.o
+TCLIB += tc_red.o
+TCLIB += tc_cbq.o
+TCLIB += tc_estimator.o
+TCLIB += tc_stab.o
+
+CFLAGS += -DCONFIG_GACT -DCONFIG_GACT_PROB
+ifneq ($(IPT_LIB_DIR),)
+ CFLAGS += -DIPT_LIB_DIR=\"$(IPT_LIB_DIR)\"
+endif
+
+YACC := bison
+LEX := flex
+CFLAGS += -DYY_NO_INPUT
+
+MODDESTDIR := $(DESTDIR)$(LIBDIR)/tc
+
+%.so: %.c
+ $(CC) $(CFLAGS) $(LDFLAGS) -shared -fpic $< -o $@
+
+
+all: libtc.a tc $(TCSO)
+
+tc: $(TCOBJ) $(TCLIB)
+
+libtc.a: $(TCLIB)
+ $(AR) rcs $@ $(TCLIB)
+
+install: all
+ mkdir -p $(MODDESTDIR)
+ install -m 0755 tc $(DESTDIR)$(SBINDIR)
+ for i in $(TCSO); \
+ do install -m 755 $$i $(MODDESTDIR); \
+ done
+ if [ ! -f $(MODDESTDIR)/m_ipt.so ]; then \
+ if [ -f $(MODDESTDIR)/m_xt.so ]; \
+ then ln -s m_xt.so $(MODDESTDIR)/m_ipt.so ; \
+ elif [ -f $(MODDESTDIR)/m_xt_old.so ]; \
+ then ln -s m_xt_old.so $(MODDESTDIR)/m_ipt.so ; \
+ fi; \
+ fi
+
+clean:
+ rm -f $(TCOBJ) $(TCLIB) libtc.a tc *.so emp_ematch.yacc.h; \
+ rm -f emp_ematch.yacc.*
+
+q_atm.so: q_atm.c
+ $(CC) $(CFLAGS) $(LDFLAGS) -shared -fpic -o q_atm.so q_atm.c -latm
+
+m_xt.so: m_xt.c
+ $(CC) $(CFLAGS) $(LDFLAGS) -shared -fpic -o m_xt.so m_xt.c $$($(PKG_CONFIG) xtables --cflags --libs)
+
+m_xt_old.so: m_xt_old.c
+ $(CC) $(CFLAGS) $(LDFLAGS) -shared -fpic -o m_xt_old.so m_xt_old.c $$($(PKG_CONFIG) xtables --cflags --libs)
+
+em_ipset.o: CFLAGS += $$($(PKG_CONFIG) xtables --cflags)
+
+%.yacc.c: %.y
+ $(YACC) $(YACCFLAGS) -o $@ $<
+
+%.lex.c: %.l
+ $(LEX) $(LEXFLAGS) -o$@ $<
+
+# our lexer includes the header from yacc, so make sure
+# we don't attempt to compile it before the header has
+# been generated as part of the yacc step.
+emp_ematch.lex.o: emp_ematch.yacc.c
+
+ifneq ($(SHARED_LIBS),y)
+
+tc: static-syms.o
+static-syms.o: static-syms.h
+static-syms.h: $(wildcard *.c)
+ files="$^" ; \
+ for s in `grep -B 3 '\<dlsym' $$files | sed -n '/snprintf/{s:.*"\([^"]*\)".*:\1:;s:%s::;p}'` ; do \
+ sed -n '/'$$s'[^ ]* =/{s:.* \([^ ]*'$$s'[^ ]*\) .*:extern char \1[] __attribute__((weak)); if (!strcmp(sym, "\1")) return \1;:;p}' $$files ; \
+ done > $@
+
+endif
diff --git a/iproute2/tc/NOTICE b/iproute2/tc/NOTICE
new file mode 100644
index 0000000..3912109
--- /dev/null
+++ b/iproute2/tc/NOTICE
@@ -0,0 +1,340 @@
+ GNU GENERAL PUBLIC LICENSE
+ Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.
+ 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+ Preamble
+
+ The licenses for most software are designed to take away your
+freedom to share and change it. By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users. This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it. (Some other Free Software Foundation software is covered by
+the GNU Library General Public License instead.) You can apply it to
+your programs, too.
+
+ When we speak of free software, we are referring to freedom, not
+price. Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+ To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+ For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have. You must make sure that they, too, receive or can get the
+source code. And you must show them these terms so they know their
+rights.
+
+ We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+ Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software. If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+ Finally, any free program is threatened constantly by software
+patents. We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary. To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+ The precise terms and conditions for copying, distribution and
+modification follow.
+
+ GNU GENERAL PUBLIC LICENSE
+ TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+ 0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License. The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language. (Hereinafter, translation is included without limitation in
+the term "modification".) Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope. The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+ 1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+ 2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+ a) You must cause the modified files to carry prominent notices
+ stating that you changed the files and the date of any change.
+
+ b) You must cause any work that you distribute or publish, that in
+ whole or in part contains or is derived from the Program or any
+ part thereof, to be licensed as a whole at no charge to all third
+ parties under the terms of this License.
+
+ c) If the modified program normally reads commands interactively
+ when run, you must cause it, when started running for such
+ interactive use in the most ordinary way, to print or display an
+ announcement including an appropriate copyright notice and a
+ notice that there is no warranty (or else, saying that you provide
+ a warranty) and that users may redistribute the program under
+ these conditions, and telling the user how to view a copy of this
+ License. (Exception: if the Program itself is interactive but
+ does not normally print such an announcement, your work based on
+ the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole. If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works. But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+ 3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+ a) Accompany it with the complete corresponding machine-readable
+ source code, which must be distributed under the terms of Sections
+ 1 and 2 above on a medium customarily used for software interchange; or,
+
+ b) Accompany it with a written offer, valid for at least three
+ years, to give any third party, for a charge no more than your
+ cost of physically performing source distribution, a complete
+ machine-readable copy of the corresponding source code, to be
+ distributed under the terms of Sections 1 and 2 above on a medium
+ customarily used for software interchange; or,
+
+ c) Accompany it with the information you received as to the offer
+ to distribute corresponding source code. (This alternative is
+ allowed only for noncommercial distribution and only if you
+ received the program in object code or executable form with such
+ an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it. For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable. However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+ 4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License. Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+ 5. You are not required to accept this License, since you have not
+signed it. However, nothing else grants you permission to modify or
+distribute the Program or its derivative works. These actions are
+prohibited by law if you do not accept this License. Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+ 6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions. You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+ 7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License. If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all. For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices. Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+ 8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded. In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+ 9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time. Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number. If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation. If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+ 10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission. For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this. Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+ NO WARRANTY
+
+ 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+ 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+ END OF TERMS AND CONDITIONS
+
+ How to Apply These Terms to Your New Programs
+
+ If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+ To do so, attach the following notices to the program. It is safest
+to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+ <one line to give the program's name and a brief idea of what it does.>
+ Copyright (C) <year> <name of author>
+
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 2 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+ Gnomovision version 69, Copyright (C) year name of author
+ Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+ This is free software, and you are welcome to redistribute it
+ under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License. Of course, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary. Here is a sample; alter the names:
+
+ Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+ `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+ <signature of Ty Coon>, 1 April 1989
+ Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs. If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library. If this is what you want to do, use the GNU Library General
+Public License instead of this License.
diff --git a/iproute2/tc/README.last b/iproute2/tc/README.last
new file mode 100644
index 0000000..63f6f7b
--- /dev/null
+++ b/iproute2/tc/README.last
@@ -0,0 +1,45 @@
+Kernel code and interface.
+--------------------------
+
+* Compile time switches
+
+There is only one, but very important, compile time switch.
+It is not settable by "make config", but should be selected
+manually and after a bit of thinking in <include/net/pkt_sched.h>
+
+PSCHED_CLOCK_SOURCE can take three values:
+
+ PSCHED_GETTIMEOFDAY
+ PSCHED_JIFFIES
+ PSCHED_CPU
+
+
+ PSCHED_GETTIMEOFDAY
+
+Default setting is the most conservative PSCHED_GETTIMEOFDAY.
+It is very slow both because of weird slowness of do_gettimeofday()
+and because it forces code to use unnatural "timeval" format,
+where microseconds and seconds fields are separate.
+Besides that, it will misbehave, when delays exceed 2 seconds
+(f.e. very slow links or classes bounded to small slice of bandwidth)
+To resume: as only you will get it working, select correct clock
+source and forget about PSCHED_GETTIMEOFDAY forever.
+
+
+ PSCHED_JIFFIES
+
+Clock is derived from jiffies. On architectures with HZ=100
+granularity of this clock is not enough to make reasonable
+bindings to real time. However, taking into account Linux
+architecture problems, which force us to use artificial
+integrated clock in any case, this switch is not so bad
+for schduling even on high speed networks, though policing
+is not reliable.
+
+
+ PSCHED_CPU
+
+It is available only for alpha and pentiums with correct
+CPU timestamp. It is the fastest way, use it when it is available,
+but remember: not all pentiums have this facility, and
+a lot of them have clock, broken by APM etc. etc.
diff --git a/iproute2/tc/e_bpf.c b/iproute2/tc/e_bpf.c
new file mode 100644
index 0000000..2d650a4
--- /dev/null
+++ b/iproute2/tc/e_bpf.c
@@ -0,0 +1,179 @@
+/*
+ * e_bpf.c BPF exec proxy
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Daniel Borkmann <daniel@iogearbox.net>
+ */
+
+#include <stdio.h>
+#include <unistd.h>
+
+#include "utils.h"
+
+#include "tc_util.h"
+#include "tc_bpf.h"
+
+#include "bpf_elf.h"
+#include "bpf_scm.h"
+
+#define BPF_DEFAULT_CMD "/bin/sh"
+
+static char *argv_default[] = { BPF_DEFAULT_CMD, NULL };
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... bpf [ import UDS_FILE ] [ run CMD ]\n");
+ fprintf(stderr, " ... bpf [ debug ]\n");
+ fprintf(stderr, " ... bpf [ graft MAP_FILE ] [ key KEY ]\n");
+ fprintf(stderr, " `... [ object-file OBJ_FILE ] [ type TYPE ] [ section NAME ] [ verbose ]\n");
+ fprintf(stderr, " `... [ object-pinned PROG_FILE ]\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "Where UDS_FILE provides the name of a unix domain socket file\n");
+ fprintf(stderr, "to import eBPF maps and the optional CMD denotes the command\n");
+ fprintf(stderr, "to be executed (default: \'%s\').\n", BPF_DEFAULT_CMD);
+ fprintf(stderr, "Where MAP_FILE points to a pinned map, OBJ_FILE to an object file\n");
+ fprintf(stderr, "and PROG_FILE to a pinned program. TYPE can be {cls, act}, where\n");
+ fprintf(stderr, "\'cls\' is default. KEY is optional and can be inferred from the\n");
+ fprintf(stderr, "section name, otherwise it needs to be provided.\n");
+}
+
+static int bpf_num_env_entries(void)
+{
+ char **envp;
+ int num;
+
+ for (num = 0, envp = environ; *envp != NULL; envp++)
+ num++;
+ return num;
+}
+
+static int parse_bpf(struct exec_util *eu, int argc, char **argv)
+{
+ char **argv_run = argv_default, **envp_run, *tmp;
+ int ret, i, env_old, env_num, env_map;
+ const char *bpf_uds_name = NULL;
+ int fds[BPF_SCM_MAX_FDS];
+ struct bpf_map_aux aux;
+
+ if (argc == 0)
+ return 0;
+
+ while (argc > 0) {
+ if (matches(*argv, "run") == 0) {
+ NEXT_ARG();
+ argv_run = argv;
+ break;
+ } else if (matches(*argv, "import") == 0) {
+ NEXT_ARG();
+ bpf_uds_name = *argv;
+ } else if (matches(*argv, "debug") == 0 ||
+ matches(*argv, "dbg") == 0) {
+ if (bpf_trace_pipe())
+ fprintf(stderr,
+ "No trace pipe, tracefs not mounted?\n");
+ return -1;
+ } else if (matches(*argv, "graft") == 0) {
+ const char *bpf_map_path;
+ bool has_key = false;
+ uint32_t key;
+
+ NEXT_ARG();
+ bpf_map_path = *argv;
+ NEXT_ARG();
+ if (matches(*argv, "key") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&key, *argv, 0)) {
+ fprintf(stderr, "Illegal \"key\"\n");
+ return -1;
+ }
+ has_key = true;
+ NEXT_ARG();
+ }
+ return bpf_graft_map(bpf_map_path, has_key ?
+ &key : NULL, argc, argv);
+ } else {
+ explain();
+ return -1;
+ }
+
+ NEXT_ARG_FWD();
+ }
+
+ if (!bpf_uds_name) {
+ fprintf(stderr, "bpf: No import parameter provided!\n");
+ explain();
+ return -1;
+ }
+
+ if (argv_run != argv_default && argc == 0) {
+ fprintf(stderr, "bpf: No run command provided!\n");
+ explain();
+ return -1;
+ }
+
+ memset(fds, 0, sizeof(fds));
+ memset(&aux, 0, sizeof(aux));
+
+ ret = bpf_recv_map_fds(bpf_uds_name, fds, &aux, ARRAY_SIZE(fds));
+ if (ret < 0) {
+ fprintf(stderr, "bpf: Could not receive fds!\n");
+ return -1;
+ }
+
+ if (aux.num_ent == 0) {
+ envp_run = environ;
+ goto out;
+ }
+
+ env_old = bpf_num_env_entries();
+ env_num = env_old + aux.num_ent + 2;
+ env_map = env_old + 1;
+
+ envp_run = malloc(sizeof(*envp_run) * env_num);
+ if (!envp_run) {
+ fprintf(stderr, "bpf: No memory left to allocate env!\n");
+ goto err;
+ }
+
+ for (i = 0; i < env_old; i++)
+ envp_run[i] = environ[i];
+
+ ret = asprintf(&tmp, "BPF_NUM_MAPS=%u", aux.num_ent);
+ if (ret < 0)
+ goto err_free;
+
+ envp_run[env_old] = tmp;
+
+ for (i = env_map; i < env_num - 1; i++) {
+ ret = asprintf(&tmp, "BPF_MAP%u=%u",
+ aux.ent[i - env_map].id,
+ fds[i - env_map]);
+ if (ret < 0)
+ goto err_free_env;
+
+ envp_run[i] = tmp;
+ }
+
+ envp_run[env_num - 1] = NULL;
+out:
+ return execvpe(argv_run[0], argv_run, envp_run);
+
+err_free_env:
+ for (--i; i >= env_old; i--)
+ free(envp_run[i]);
+err_free:
+ free(envp_run);
+err:
+ for (i = 0; i < aux.num_ent; i++)
+ close(fds[i]);
+ return -1;
+}
+
+struct exec_util bpf_exec_util = {
+ .id = "bpf",
+ .parse_eopt = parse_bpf,
+};
diff --git a/iproute2/tc/em_canid.c b/iproute2/tc/em_canid.c
new file mode 100644
index 0000000..16f6ed5
--- /dev/null
+++ b/iproute2/tc/em_canid.c
@@ -0,0 +1,191 @@
+/*
+ * em_canid.c Ematch rule to match CAN frames according to their CAN identifiers
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Idea: Oliver Hartkopp <oliver.hartkopp@volkswagen.de>
+ * Copyright: (c) 2011 Czech Technical University in Prague
+ * (c) 2011 Volkswagen Group Research
+ * Authors: Michal Sojka <sojkam1@fel.cvut.cz>
+ * Pavel Pisa <pisa@cmp.felk.cvut.cz>
+ * Rostislav Lisovy <lisovy@gmail.cz>
+ * Funded by: Volkswagen Group Research
+ *
+ * Documentation: http://rtime.felk.cvut.cz/can/socketcan-qdisc-final.pdf
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <errno.h>
+#include <linux/can.h>
+#include <inttypes.h>
+#include "m_ematch.h"
+
+#define EM_CANID_RULES_MAX 400 /* Main reason for this number is Nelink
+ message size limit equal to Single memory page size. When dump()
+ is invoked, there are even some ematch related headers sent from
+ kernel to userspace together with em_canid configuration --
+ 400*sizeof(struct can_filter) should fit without any problems */
+
+extern struct ematch_util canid_ematch_util;
+struct rules {
+ struct can_filter *rules_raw;
+ int rules_capacity; /* Size of array allocated for rules_raw */
+ int rules_cnt; /* Actual number of rules stored in rules_raw */
+};
+
+static void canid_print_usage(FILE *fd)
+{
+ fprintf(fd,
+ "Usage: canid(IDLIST)\n" \
+ "where: IDLIST := IDSPEC [ IDLIST ]\n" \
+ " IDSPEC := { ’sff’ CANID | ’eff’ CANID }\n" \
+ " CANID := ID[:MASK]\n" \
+ " ID, MASK := hexadecimal number (i.e. 0x123)\n" \
+ "Example: canid(sff 0x123 sff 0x124 sff 0x125:0xf)\n");
+}
+
+static int canid_parse_rule(struct rules *rules, struct bstr *a, int iseff)
+{
+ unsigned int can_id = 0;
+ unsigned int can_mask = 0;
+
+ if (sscanf(a->data, "%"SCNx32 ":" "%"SCNx32, &can_id, &can_mask) != 2) {
+ if (sscanf(a->data, "%"SCNx32, &can_id) != 1) {
+ return -1;
+ } else {
+ can_mask = (iseff) ? CAN_EFF_MASK : CAN_SFF_MASK;
+ }
+ }
+
+ /* Stretch rules array up to EM_CANID_RULES_MAX if necessary */
+ if (rules->rules_cnt == rules->rules_capacity) {
+ if (rules->rules_capacity <= EM_CANID_RULES_MAX/2) {
+ rules->rules_capacity *= 2;
+ rules->rules_raw = realloc(rules->rules_raw,
+ sizeof(struct can_filter) * rules->rules_capacity);
+ } else {
+ return -2;
+ }
+ }
+
+ rules->rules_raw[rules->rules_cnt].can_id =
+ can_id | ((iseff) ? CAN_EFF_FLAG : 0);
+ rules->rules_raw[rules->rules_cnt].can_mask =
+ can_mask | CAN_EFF_FLAG;
+
+ rules->rules_cnt++;
+
+ return 0;
+}
+
+static int canid_parse_eopt(struct nlmsghdr *n, struct tcf_ematch_hdr *hdr,
+ struct bstr *args)
+{
+ int iseff = 0;
+ int ret = 0;
+ struct rules rules = {
+ .rules_capacity = 25, /* Denominator of EM_CANID_RULES_MAX
+ Will be multiplied by 2 to calculate the size for realloc() */
+ .rules_cnt = 0
+ };
+
+#define PARSE_ERR(CARG, FMT, ARGS...) \
+ em_parse_error(EINVAL, args, CARG, &canid_ematch_util, FMT, ##ARGS)
+
+ if (args == NULL)
+ return PARSE_ERR(args, "canid: missing arguments");
+
+ rules.rules_raw = malloc(sizeof(struct can_filter) * rules.rules_capacity);
+ memset(rules.rules_raw, 0, sizeof(struct can_filter) * rules.rules_capacity);
+
+ do {
+ if (!bstrcmp(args, "sff")) {
+ iseff = 0;
+ } else if (!bstrcmp(args, "eff")) {
+ iseff = 1;
+ } else {
+ ret = PARSE_ERR(args, "canid: invalid key");
+ goto exit;
+ }
+
+ args = bstr_next(args);
+ if (args == NULL) {
+ ret = PARSE_ERR(args, "canid: missing argument");
+ goto exit;
+ }
+
+ ret = canid_parse_rule(&rules, args, iseff);
+ if (ret == -1) {
+ ret = PARSE_ERR(args, "canid: Improperly formed CAN ID & mask\n");
+ goto exit;
+ } else if (ret == -2) {
+ ret = PARSE_ERR(args, "canid: Too many arguments on input\n");
+ goto exit;
+ }
+ } while ((args = bstr_next(args)) != NULL);
+
+ addraw_l(n, MAX_MSG, hdr, sizeof(*hdr));
+ addraw_l(n, MAX_MSG, rules.rules_raw,
+ sizeof(struct can_filter) * rules.rules_cnt);
+
+#undef PARSE_ERR
+exit:
+ free(rules.rules_raw);
+ return ret;
+}
+
+static int canid_print_eopt(FILE *fd, struct tcf_ematch_hdr *hdr, void *data,
+ int data_len)
+{
+ struct can_filter *conf = data; /* Array with rules */
+ int rules_count;
+ int i;
+
+ rules_count = data_len / sizeof(struct can_filter);
+
+ for (i = 0; i < rules_count; i++) {
+ struct can_filter *pcfltr = &conf[i];
+
+ if (pcfltr->can_id & CAN_EFF_FLAG) {
+ if (pcfltr->can_mask == (CAN_EFF_FLAG | CAN_EFF_MASK))
+ fprintf(fd, "eff 0x%"PRIX32,
+ pcfltr->can_id & CAN_EFF_MASK);
+ else
+ fprintf(fd, "eff 0x%"PRIX32":0x%"PRIX32,
+ pcfltr->can_id & CAN_EFF_MASK,
+ pcfltr->can_mask & CAN_EFF_MASK);
+ } else {
+ if (pcfltr->can_mask == (CAN_EFF_FLAG | CAN_SFF_MASK))
+ fprintf(fd, "sff 0x%"PRIX32,
+ pcfltr->can_id & CAN_SFF_MASK);
+ else
+ fprintf(fd, "sff 0x%"PRIX32":0x%"PRIX32,
+ pcfltr->can_id & CAN_SFF_MASK,
+ pcfltr->can_mask & CAN_SFF_MASK);
+ }
+
+ if ((i + 1) < rules_count)
+ fprintf(fd, " ");
+ }
+
+ return 0;
+}
+
+struct ematch_util canid_ematch_util = {
+ .kind = "canid",
+ .kind_num = TCF_EM_CANID,
+ .parse_eopt = canid_parse_eopt,
+ .print_eopt = canid_print_eopt,
+ .print_usage = canid_print_usage
+};
diff --git a/iproute2/tc/em_cmp.c b/iproute2/tc/em_cmp.c
new file mode 100644
index 0000000..3e6d00e
--- /dev/null
+++ b/iproute2/tc/em_cmp.c
@@ -0,0 +1,187 @@
+/*
+ * em_cmp.c Simple comparison Ematch
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Thomas Graf <tgraf@suug.ch>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <errno.h>
+
+#include "m_ematch.h"
+#include <linux/tc_ematch/tc_em_cmp.h>
+
+extern struct ematch_util cmp_ematch_util;
+
+static void cmp_print_usage(FILE *fd)
+{
+ fprintf(fd,
+ "Usage: cmp(ALIGN at OFFSET [ ATTRS ] { eq | lt | gt } VALUE)\n" \
+ "where: ALIGN := { u8 | u16 | u32 }\n" \
+ " ATTRS := [ layer LAYER ] [ mask MASK ] [ trans ]\n" \
+ " LAYER := { link | network | transport | 0..%d }\n" \
+ "\n" \
+ "Example: cmp(u16 at 3 layer 2 mask 0xff00 gt 20)\n",
+ TCF_LAYER_MAX);
+}
+
+static int cmp_parse_eopt(struct nlmsghdr *n, struct tcf_ematch_hdr *hdr,
+ struct bstr *args)
+{
+ struct bstr *a;
+ int align, opnd = 0;
+ unsigned long offset = 0, layer = TCF_LAYER_NETWORK, mask = 0, value = 0;
+ int offset_present = 0, value_present = 0;
+ struct tcf_em_cmp cmp;
+
+ memset(&cmp, 0, sizeof(cmp));
+
+#define PARSE_ERR(CARG, FMT, ARGS...) \
+ em_parse_error(EINVAL, args, CARG, &cmp_ematch_util, FMT ,##ARGS)
+
+ if (args == NULL)
+ return PARSE_ERR(args, "cmp: missing arguments");
+
+ if (!bstrcmp(args, "u8"))
+ align = TCF_EM_ALIGN_U8;
+ else if (!bstrcmp(args, "u16"))
+ align = TCF_EM_ALIGN_U16;
+ else if (!bstrcmp(args, "u32"))
+ align = TCF_EM_ALIGN_U32;
+ else
+ return PARSE_ERR(args, "cmp: invalid alignment");
+
+ for (a = bstr_next(args); a; a = bstr_next(a)) {
+ if (!bstrcmp(a, "at")) {
+ if (a->next == NULL)
+ return PARSE_ERR(a, "cmp: missing argument");
+ a = bstr_next(a);
+
+ offset = bstrtoul(a);
+ if (offset == ULONG_MAX)
+ return PARSE_ERR(a, "cmp: invalid offset, " \
+ "must be numeric");
+
+ offset_present = 1;
+ } else if (!bstrcmp(a, "layer")) {
+ if (a->next == NULL)
+ return PARSE_ERR(a, "cmp: missing argument");
+ a = bstr_next(a);
+
+ layer = parse_layer(a);
+ if (layer == INT_MAX) {
+ layer = bstrtoul(a);
+ if (layer == ULONG_MAX)
+ return PARSE_ERR(a, "cmp: invalid " \
+ "layer");
+ }
+
+ if (layer > TCF_LAYER_MAX)
+ return PARSE_ERR(a, "cmp: illegal layer, " \
+ "must be in 0..%d", TCF_LAYER_MAX);
+ } else if (!bstrcmp(a, "mask")) {
+ if (a->next == NULL)
+ return PARSE_ERR(a, "cmp: missing argument");
+ a = bstr_next(a);
+
+ mask = bstrtoul(a);
+ if (mask == ULONG_MAX)
+ return PARSE_ERR(a, "cmp: invalid mask");
+ } else if (!bstrcmp(a, "trans")) {
+ cmp.flags |= TCF_EM_CMP_TRANS;
+ } else if (!bstrcmp(a, "eq") || !bstrcmp(a, "gt") ||
+ !bstrcmp(a, "lt")) {
+
+ if (!bstrcmp(a, "eq"))
+ opnd = TCF_EM_OPND_EQ;
+ else if (!bstrcmp(a, "gt"))
+ opnd = TCF_EM_OPND_GT;
+ else if (!bstrcmp(a, "lt"))
+ opnd = TCF_EM_OPND_LT;
+
+ if (a->next == NULL)
+ return PARSE_ERR(a, "cmp: missing argument");
+ a = bstr_next(a);
+
+ value = bstrtoul(a);
+ if (value == ULONG_MAX)
+ return PARSE_ERR(a, "cmp: invalid value");
+
+ value_present = 1;
+ } else
+ return PARSE_ERR(a, "nbyte: unknown parameter");
+ }
+
+ if (offset_present == 0 || value_present == 0)
+ return PARSE_ERR(a, "cmp: offset and value required");
+
+ cmp.val = (__u32) value;
+ cmp.mask = (__u32) mask;
+ cmp.off = (__u16) offset;
+ cmp.align = (__u8) align;
+ cmp.layer = (__u8) layer;
+ cmp.opnd = (__u8) opnd;
+
+ addraw_l(n, MAX_MSG, hdr, sizeof(*hdr));
+ addraw_l(n, MAX_MSG, &cmp, sizeof(cmp));
+
+#undef PARSE_ERR
+ return 0;
+}
+
+static int cmp_print_eopt(FILE *fd, struct tcf_ematch_hdr *hdr, void *data,
+ int data_len)
+{
+ struct tcf_em_cmp *cmp = data;
+
+ if (data_len < sizeof(*cmp)) {
+ fprintf(stderr, "CMP header size mismatch\n");
+ return -1;
+ }
+
+ if (cmp->align == TCF_EM_ALIGN_U8)
+ fprintf(fd, "u8 ");
+ else if (cmp->align == TCF_EM_ALIGN_U16)
+ fprintf(fd, "u16 ");
+ else if (cmp->align == TCF_EM_ALIGN_U32)
+ fprintf(fd, "u32 ");
+
+ fprintf(fd, "at %d layer %d ", cmp->off, cmp->layer);
+
+ if (cmp->mask)
+ fprintf(fd, "mask 0x%x ", cmp->mask);
+
+ if (cmp->flags & TCF_EM_CMP_TRANS)
+ fprintf(fd, "trans ");
+
+ if (cmp->opnd == TCF_EM_OPND_EQ)
+ fprintf(fd, "eq ");
+ else if (cmp->opnd == TCF_EM_OPND_LT)
+ fprintf(fd, "lt ");
+ else if (cmp->opnd == TCF_EM_OPND_GT)
+ fprintf(fd, "gt ");
+
+ fprintf(fd, "%d", cmp->val);
+
+ return 0;
+}
+
+struct ematch_util cmp_ematch_util = {
+ .kind = "cmp",
+ .kind_num = TCF_EM_CMP,
+ .parse_eopt = cmp_parse_eopt,
+ .print_eopt = cmp_print_eopt,
+ .print_usage = cmp_print_usage
+};
diff --git a/iproute2/tc/em_ipset.c b/iproute2/tc/em_ipset.c
new file mode 100644
index 0000000..a2d0d15
--- /dev/null
+++ b/iproute2/tc/em_ipset.c
@@ -0,0 +1,265 @@
+/*
+ * em_ipset.c IPset Ematch
+ *
+ * (C) 2012 Florian Westphal <fw@strlen.de>
+ *
+ * Parts taken from iptables libxt_set.h:
+ * Copyright (C) 2000-2002 Joakim Axelsson <gozem@linux.nu>
+ * Patrick Schaaf <bof@bof.de>
+ * Martin Josefsson <gandalf@wlug.westbo.se>
+ * Copyright (C) 2003-2010 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <stdbool.h>
+#include <stdio.h>
+#include <errno.h>
+#include <netdb.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdlib.h>
+#include <getopt.h>
+
+#include <xtables.h>
+#include <linux/netfilter/ipset/ip_set.h>
+
+#ifndef IPSET_INVALID_ID
+typedef __u16 ip_set_id_t;
+
+enum ip_set_dim {
+ IPSET_DIM_ZERO = 0,
+ IPSET_DIM_ONE,
+ IPSET_DIM_TWO,
+ IPSET_DIM_THREE,
+ IPSET_DIM_MAX = 6,
+};
+#endif /* IPSET_INVALID_ID */
+
+#include <linux/netfilter/xt_set.h>
+#include "m_ematch.h"
+
+#ifndef IPSET_INVALID_ID
+#define IPSET_INVALID_ID 65535
+#define SO_IP_SET 83
+
+union ip_set_name_index {
+ char name[IPSET_MAXNAMELEN];
+ __u16 index;
+};
+
+#define IP_SET_OP_GET_BYNAME 0x00000006 /* Get set index by name */
+struct ip_set_req_get_set {
+ unsigned op;
+ unsigned version;
+ union ip_set_name_index set;
+};
+
+#define IP_SET_OP_GET_BYINDEX 0x00000007 /* Get set name by index */
+/* Uses ip_set_req_get_set */
+
+#define IP_SET_OP_VERSION 0x00000100 /* Ask kernel version */
+struct ip_set_req_version {
+ unsigned op;
+ unsigned version;
+};
+#endif /* IPSET_INVALID_ID */
+
+extern struct ematch_util ipset_ematch_util;
+
+static int get_version(unsigned *version)
+{
+ int res, sockfd = socket(AF_INET, SOCK_RAW, IPPROTO_RAW);
+ struct ip_set_req_version req_version;
+ socklen_t size = sizeof(req_version);
+
+ if (sockfd < 0) {
+ fputs("Can't open socket to ipset.\n", stderr);
+ return -1;
+ }
+
+ req_version.op = IP_SET_OP_VERSION;
+ res = getsockopt(sockfd, SOL_IP, SO_IP_SET, &req_version, &size);
+ if (res != 0) {
+ perror("xt_set getsockopt");
+ return -1;
+ }
+
+ *version = req_version.version;
+ return sockfd;
+}
+
+static int do_getsockopt(struct ip_set_req_get_set *req)
+{
+ int sockfd, res;
+ socklen_t size = sizeof(struct ip_set_req_get_set);
+ sockfd = get_version(&req->version);
+ if (sockfd < 0)
+ return -1;
+ res = getsockopt(sockfd, SOL_IP, SO_IP_SET, req, &size);
+ if (res != 0)
+ perror("Problem when communicating with ipset");
+ close(sockfd);
+ if (res != 0)
+ return -1;
+
+ if (size != sizeof(struct ip_set_req_get_set)) {
+ fprintf(stderr,
+ "Incorrect return size from kernel during ipset lookup, "
+ "(want %zu, got %zu)\n",
+ sizeof(struct ip_set_req_get_set), (size_t)size);
+ return -1;
+ }
+
+ return res;
+}
+
+static int
+get_set_byid(char *setname, unsigned int idx)
+{
+ struct ip_set_req_get_set req;
+ int res;
+
+ req.op = IP_SET_OP_GET_BYINDEX;
+ req.set.index = idx;
+ res = do_getsockopt(&req);
+ if (res != 0)
+ return -1;
+ if (req.set.name[0] == '\0') {
+ fprintf(stderr,
+ "Set with index %i in kernel doesn't exist.\n", idx);
+ return -1;
+ }
+
+ strncpy(setname, req.set.name, IPSET_MAXNAMELEN);
+ return 0;
+}
+
+static int
+get_set_byname(const char *setname, struct xt_set_info *info)
+{
+ struct ip_set_req_get_set req;
+ int res;
+
+ req.op = IP_SET_OP_GET_BYNAME;
+ strncpy(req.set.name, setname, IPSET_MAXNAMELEN);
+ req.set.name[IPSET_MAXNAMELEN - 1] = '\0';
+ res = do_getsockopt(&req);
+ if (res != 0)
+ return -1;
+ if (req.set.index == IPSET_INVALID_ID)
+ return -1;
+ info->index = req.set.index;
+ return 0;
+}
+
+static int
+parse_dirs(const char *opt_arg, struct xt_set_info *info)
+{
+ char *saved = strdup(opt_arg);
+ char *ptr, *tmp = saved;
+
+ if (!tmp) {
+ perror("strdup");
+ return -1;
+ }
+
+ while (info->dim < IPSET_DIM_MAX && tmp != NULL) {
+ info->dim++;
+ ptr = strsep(&tmp, ",");
+ if (strncmp(ptr, "src", 3) == 0)
+ info->flags |= (1 << info->dim);
+ else if (strncmp(ptr, "dst", 3) != 0) {
+ fputs("You must specify (the comma separated list of) 'src' or 'dst'\n", stderr);
+ free(saved);
+ return -1;
+ }
+ }
+
+ if (tmp)
+ fprintf(stderr, "Can't be more src/dst options than %u", IPSET_DIM_MAX);
+ free(saved);
+ return tmp ? -1 : 0;
+}
+
+static void ipset_print_usage(FILE *fd)
+{
+ fprintf(fd,
+ "Usage: ipset(SETNAME FLAGS)\n" \
+ "where: SETNAME:= string\n" \
+ " FLAGS := { FLAG[,FLAGS] }\n" \
+ " FLAG := { src | dst }\n" \
+ "\n" \
+ "Example: 'ipset(bulk src,dst)'\n");
+}
+
+static int ipset_parse_eopt(struct nlmsghdr *n, struct tcf_ematch_hdr *hdr,
+ struct bstr *args)
+{
+ struct xt_set_info set_info;
+ int ret;
+
+ memset(&set_info, 0, sizeof(set_info));
+
+#define PARSE_ERR(CARG, FMT, ARGS...) \
+ em_parse_error(EINVAL, args, CARG, &ipset_ematch_util, FMT ,##ARGS)
+
+ if (args == NULL)
+ return PARSE_ERR(args, "ipset: missing set name");
+
+ if (args->len >= IPSET_MAXNAMELEN)
+ return PARSE_ERR(args, "ipset: set name too long (max %u)", IPSET_MAXNAMELEN - 1);
+ ret = get_set_byname(args->data, &set_info);
+ if (ret < 0)
+ return PARSE_ERR(args, "ipset: unknown set name '%s'", args->data);
+
+ if (args->next == NULL)
+ return PARSE_ERR(args, "ipset: missing set flags");
+
+ args = bstr_next(args);
+ if (parse_dirs(args->data, &set_info))
+ return PARSE_ERR(args, "ipset: error parsing set flags");
+
+ if (args->next) {
+ args = bstr_next(args);
+ return PARSE_ERR(args, "ipset: unknown parameter");
+ }
+
+ addraw_l(n, MAX_MSG, hdr, sizeof(*hdr));
+ addraw_l(n, MAX_MSG, &set_info, sizeof(set_info));
+
+#undef PARSE_ERR
+ return 0;
+}
+
+static int ipset_print_eopt(FILE *fd, struct tcf_ematch_hdr *hdr, void *data,
+ int data_len)
+{
+ int i;
+ char setname[IPSET_MAXNAMELEN];
+ const struct xt_set_info *set_info = data;
+
+ if (data_len != sizeof(*set_info)) {
+ fprintf(stderr, "xt_set_info struct size mismatch\n");
+ return -1;
+ }
+
+ if (get_set_byid(setname, set_info->index))
+ return -1;
+ fputs(setname, fd);
+ for (i = 1; i <= set_info->dim; i++) {
+ fprintf(fd, "%s%s", i == 1 ? " " : ",", set_info->flags & (1 << i) ? "src" : "dst");
+ }
+
+ return 0;
+}
+
+struct ematch_util ipset_ematch_util = {
+ .kind = "ipset",
+ .kind_num = TCF_EM_IPSET,
+ .parse_eopt = ipset_parse_eopt,
+ .print_eopt = ipset_print_eopt,
+ .print_usage = ipset_print_usage
+};
diff --git a/iproute2/tc/em_meta.c b/iproute2/tc/em_meta.c
new file mode 100644
index 0000000..b64f333
--- /dev/null
+++ b/iproute2/tc/em_meta.c
@@ -0,0 +1,546 @@
+/*
+ * em_meta.c Metadata Ematch
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Thomas Graf <tgraf@suug.ch>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <errno.h>
+
+#include "m_ematch.h"
+#include <linux/tc_ematch/tc_em_meta.h>
+
+extern struct ematch_util meta_ematch_util;
+
+static void meta_print_usage(FILE *fd)
+{
+ fprintf(fd,
+ "Usage: meta(OBJECT { eq | lt | gt } OBJECT)\n" \
+ "where: OBJECT := { META_ID | VALUE }\n" \
+ " META_ID := id [ shift SHIFT ] [ mask MASK ]\n" \
+ "\n" \
+ "Example: meta(nf_mark gt 24)\n" \
+ " meta(indev shift 1 eq \"ppp\")\n" \
+ " meta(tcindex mask 0xf0 eq 0xf0)\n" \
+ "\n" \
+ "For a list of meta identifiers, use meta(list).\n");
+}
+
+struct meta_entry {
+ int id;
+ char * kind;
+ char * mask;
+ char * desc;
+} meta_table[] = {
+#define TCF_META_ID_SECTION 0
+#define __A(id, name, mask, desc) { TCF_META_ID_##id, name, mask, desc }
+ __A(SECTION, "Generic", "", ""),
+ __A(RANDOM, "random", "i",
+ "Random value (32 bit)"),
+ __A(LOADAVG_0, "loadavg_1", "i",
+ "Load average in last minute"),
+ __A(LOADAVG_1, "loadavg_5", "i",
+ "Load average in last 5 minutes"),
+ __A(LOADAVG_2, "loadavg_15", "i",
+ "Load average in last 15 minutes"),
+
+ __A(SECTION, "Interfaces", "", ""),
+ __A(DEV, "dev", "iv",
+ "Device the packet is on"),
+ __A(SECTION, "Packet attributes", "", ""),
+ __A(PRIORITY, "priority", "i",
+ "Priority of packet"),
+ __A(PROTOCOL, "protocol", "i",
+ "Link layer protocol"),
+ __A(PKTTYPE, "pkt_type", "i",
+ "Packet type (uni|multi|broad|...)cast"),
+ __A(PKTLEN, "pkt_len", "i",
+ "Length of packet"),
+ __A(DATALEN, "data_len", "i",
+ "Length of data in packet"),
+ __A(MACLEN, "mac_len", "i",
+ "Length of link layer header"),
+
+ __A(SECTION, "Netfilter", "", ""),
+ __A(NFMARK, "nf_mark", "i",
+ "Netfilter mark"),
+ __A(NFMARK, "fwmark", "i",
+ "Alias for nf_mark"),
+
+ __A(SECTION, "Traffic Control", "", ""),
+ __A(TCINDEX, "tc_index", "i", "TC Index"),
+ __A(SECTION, "Routing", "", ""),
+ __A(RTCLASSID, "rt_classid", "i",
+ "Routing ClassID (cls_route)"),
+ __A(RTIIF, "rt_iif", "i",
+ "Incoming interface index"),
+ __A(VLAN_TAG, "vlan", "i", "Vlan tag"),
+
+ __A(SECTION, "Sockets", "", ""),
+ __A(SK_FAMILY, "sk_family", "i", "Address family"),
+ __A(SK_STATE, "sk_state", "i", "State"),
+ __A(SK_REUSE, "sk_reuse", "i", "Reuse Flag"),
+ __A(SK_BOUND_IF, "sk_bind_if", "iv", "Bound interface"),
+ __A(SK_REFCNT, "sk_refcnt", "i", "Reference counter"),
+ __A(SK_SHUTDOWN, "sk_shutdown", "i", "Shutdown mask"),
+ __A(SK_PROTO, "sk_proto", "i", "Protocol"),
+ __A(SK_TYPE, "sk_type", "i", "Type"),
+ __A(SK_RCVBUF, "sk_rcvbuf", "i", "Receive buffer size"),
+ __A(SK_RMEM_ALLOC, "sk_rmem", "i", "RMEM"),
+ __A(SK_WMEM_ALLOC, "sk_wmem", "i", "WMEM"),
+ __A(SK_OMEM_ALLOC, "sk_omem", "i", "OMEM"),
+ __A(SK_WMEM_QUEUED, "sk_wmem_queue","i", "WMEM queue"),
+ __A(SK_SND_QLEN, "sk_snd_queue", "i", "Send queue length"),
+ __A(SK_RCV_QLEN, "sk_rcv_queue", "i", "Receive queue length"),
+ __A(SK_ERR_QLEN, "sk_err_queue", "i", "Error queue length"),
+ __A(SK_FORWARD_ALLOCS, "sk_fwd_alloc", "i", "Forward allocations"),
+ __A(SK_SNDBUF, "sk_sndbuf", "i", "Send buffer size"),
+#undef __A
+};
+
+static inline int map_type(char k)
+{
+ switch (k) {
+ case 'i': return TCF_META_TYPE_INT;
+ case 'v': return TCF_META_TYPE_VAR;
+ }
+
+ fprintf(stderr, "BUG: Unknown map character '%c'\n", k);
+ return INT_MAX;
+}
+
+static struct meta_entry * lookup_meta_entry(struct bstr *kind)
+{
+ int i;
+
+ for (i = 0; i < (sizeof(meta_table)/sizeof(meta_table[0])); i++)
+ if (!bstrcmp(kind, meta_table[i].kind) &&
+ meta_table[i].id != 0)
+ return &meta_table[i];
+
+ return NULL;
+}
+
+static struct meta_entry * lookup_meta_entry_byid(int id)
+{
+ int i;
+
+ for (i = 0; i < (sizeof(meta_table)/sizeof(meta_table[0])); i++)
+ if (meta_table[i].id == id)
+ return &meta_table[i];
+
+ return NULL;
+}
+
+static inline void dump_value(struct nlmsghdr *n, int tlv, unsigned long val,
+ struct tcf_meta_val *hdr)
+{
+ __u32 t;
+
+ switch (TCF_META_TYPE(hdr->kind)) {
+ case TCF_META_TYPE_INT:
+ t = val;
+ addattr_l(n, MAX_MSG, tlv, &t, sizeof(t));
+ break;
+
+ case TCF_META_TYPE_VAR:
+ if (TCF_META_ID(hdr->kind) == TCF_META_ID_VALUE) {
+ struct bstr *a = (struct bstr *) val;
+ addattr_l(n, MAX_MSG, tlv, a->data, a->len);
+ }
+ break;
+ }
+}
+
+static inline int is_compatible(struct tcf_meta_val *what,
+ struct tcf_meta_val *needed)
+{
+ char *p;
+ struct meta_entry *entry;
+
+ entry = lookup_meta_entry_byid(TCF_META_ID(what->kind));
+
+ if (entry == NULL)
+ return 0;
+
+ for (p = entry->mask; p; p++)
+ if (map_type(*p) == TCF_META_TYPE(needed->kind))
+ return 1;
+
+ return 0;
+}
+
+static void list_meta_ids(FILE *fd)
+{
+ int i;
+
+ fprintf(fd,
+ "--------------------------------------------------------\n" \
+ " ID Type Description\n" \
+ "--------------------------------------------------------");
+
+ for (i = 0; i < (sizeof(meta_table)/sizeof(meta_table[0])); i++) {
+ if (meta_table[i].id == TCF_META_ID_SECTION) {
+ fprintf(fd, "\n%s:\n", meta_table[i].kind);
+ } else {
+ char *p = meta_table[i].mask;
+ char buf[64] = {0};
+
+ fprintf(fd, " %-16s ", meta_table[i].kind);
+
+ while (*p) {
+ int type = map_type(*p);
+
+ switch (type) {
+ case TCF_META_TYPE_INT:
+ strcat(buf, "INT");
+ break;
+
+ case TCF_META_TYPE_VAR:
+ strcat(buf, "VAR");
+ break;
+ }
+
+ if (*(++p))
+ strcat(buf, ",");
+ }
+
+ fprintf(fd, "%-10s %s\n", buf, meta_table[i].desc);
+ }
+ }
+
+ fprintf(fd,
+ "--------------------------------------------------------\n");
+}
+
+#undef TCF_META_ID_SECTION
+
+#define PARSE_FAILURE ((void *) (-1))
+
+#define PARSE_ERR(CARG, FMT, ARGS...) \
+ em_parse_error(EINVAL, args, CARG, &meta_ematch_util, FMT ,##ARGS)
+
+static inline int can_adopt(struct tcf_meta_val *val)
+{
+ return !!TCF_META_ID(val->kind);
+}
+
+static inline int overwrite_type(struct tcf_meta_val *src,
+ struct tcf_meta_val *dst)
+{
+ return (TCF_META_TYPE(dst->kind) << 12) | TCF_META_ID(src->kind);
+}
+
+
+static inline struct bstr *
+parse_object(struct bstr *args, struct bstr *arg, struct tcf_meta_val *obj,
+ unsigned long *dst, struct tcf_meta_val *left)
+{
+ struct meta_entry *entry;
+ unsigned long num;
+ struct bstr *a;
+
+ if (arg->quoted) {
+ obj->kind = TCF_META_TYPE_VAR << 12;
+ obj->kind |= TCF_META_ID_VALUE;
+ *dst = (unsigned long) arg;
+ return bstr_next(arg);
+ }
+
+ num = bstrtoul(arg);
+ if (num != ULONG_MAX) {
+ obj->kind = TCF_META_TYPE_INT << 12;
+ obj->kind |= TCF_META_ID_VALUE;
+ *dst = (unsigned long) num;
+ return bstr_next(arg);
+ }
+
+ entry = lookup_meta_entry(arg);
+
+ if (entry == NULL) {
+ PARSE_ERR(arg, "meta: unknown meta id\n");
+ return PARSE_FAILURE;
+ }
+
+ obj->kind = entry->id | (map_type(entry->mask[0]) << 12);
+
+ if (left) {
+ struct tcf_meta_val *right = obj;
+
+ if (TCF_META_TYPE(right->kind) == TCF_META_TYPE(left->kind))
+ goto compatible;
+
+ if (can_adopt(left) && !can_adopt(right)) {
+ if (is_compatible(left, right))
+ left->kind = overwrite_type(left, right);
+ else
+ goto not_compatible;
+ } else if (can_adopt(right) && !can_adopt(left)) {
+ if (is_compatible(right, left))
+ right->kind = overwrite_type(right, left);
+ else
+ goto not_compatible;
+ } else if (can_adopt(left) && can_adopt(right)) {
+ if (is_compatible(left, right))
+ left->kind = overwrite_type(left, right);
+ else if (is_compatible(right, left))
+ right->kind = overwrite_type(right, left);
+ else
+ goto not_compatible;
+ } else
+ goto not_compatible;
+ }
+
+compatible:
+
+ a = bstr_next(arg);
+
+ while(a) {
+ if (!bstrcmp(a, "shift")) {
+ unsigned long shift;
+
+ if (a->next == NULL) {
+ PARSE_ERR(a, "meta: missing argument");
+ return PARSE_FAILURE;
+ }
+ a = bstr_next(a);
+
+ shift = bstrtoul(a);
+ if (shift == ULONG_MAX) {
+ PARSE_ERR(a, "meta: invalid shift, must " \
+ "be numeric");
+ return PARSE_FAILURE;
+ }
+
+ obj->shift = (__u8) shift;
+ a = bstr_next(a);
+ } else if (!bstrcmp(a, "mask")) {
+ unsigned long mask;
+
+ if (a->next == NULL) {
+ PARSE_ERR(a, "meta: missing argument");
+ return PARSE_FAILURE;
+ }
+ a = bstr_next(a);
+
+ mask = bstrtoul(a);
+ if (mask == ULONG_MAX) {
+ PARSE_ERR(a, "meta: invalid mask, must be " \
+ "numeric");
+ return PARSE_FAILURE;
+ }
+ *dst = (unsigned long) mask;
+ a = bstr_next(a);
+ } else
+ break;
+ }
+
+ return a;
+
+not_compatible:
+ PARSE_ERR(arg, "lvalue and rvalue are not compatible.");
+ return PARSE_FAILURE;
+}
+
+static int meta_parse_eopt(struct nlmsghdr *n, struct tcf_ematch_hdr *hdr,
+ struct bstr *args)
+{
+ int opnd;
+ struct bstr *a;
+ struct tcf_meta_hdr meta_hdr;
+ unsigned long lvalue = 0, rvalue = 0;
+
+ memset(&meta_hdr, 0, sizeof(meta_hdr));
+
+ if (args == NULL)
+ return PARSE_ERR(args, "meta: missing arguments");
+
+ if (!bstrcmp(args, "list")) {
+ list_meta_ids(stderr);
+ return -1;
+ }
+
+ a = parse_object(args, args, &meta_hdr.left, &lvalue, NULL);
+ if (a == PARSE_FAILURE)
+ return -1;
+ else if (a == NULL)
+ return PARSE_ERR(args, "meta: missing operand");
+
+ if (!bstrcmp(a, "eq"))
+ opnd = TCF_EM_OPND_EQ;
+ else if (!bstrcmp(a, "gt"))
+ opnd = TCF_EM_OPND_GT;
+ else if (!bstrcmp(a, "lt"))
+ opnd = TCF_EM_OPND_LT;
+ else
+ return PARSE_ERR(a, "meta: invalid operand");
+
+ meta_hdr.left.op = (__u8) opnd;
+
+ if (a->next == NULL)
+ return PARSE_ERR(args, "meta: missing rvalue");
+ a = bstr_next(a);
+
+ a = parse_object(args, a, &meta_hdr.right, &rvalue, &meta_hdr.left);
+ if (a == PARSE_FAILURE)
+ return -1;
+ else if (a != NULL)
+ return PARSE_ERR(a, "meta: unexpected trailer");
+
+
+ addraw_l(n, MAX_MSG, hdr, sizeof(*hdr));
+
+ addattr_l(n, MAX_MSG, TCA_EM_META_HDR, &meta_hdr, sizeof(meta_hdr));
+
+ dump_value(n, TCA_EM_META_LVALUE, lvalue, &meta_hdr.left);
+ dump_value(n, TCA_EM_META_RVALUE, rvalue, &meta_hdr.right);
+
+ return 0;
+}
+#undef PARSE_ERR
+
+static inline void print_binary(FILE *fd, unsigned char *str, int len)
+{
+ int i;
+
+ for (i = 0; i < len; i++)
+ if (!isprint(str[i]))
+ goto binary;
+
+ for (i = 0; i < len; i++)
+ fprintf(fd, "%c", str[i]);
+ return;
+
+binary:
+ for (i = 0; i < len; i++)
+ fprintf(fd, "%02x ", str[i]);
+
+ fprintf(fd, "\"");
+ for (i = 0; i < len; i++)
+ fprintf(fd, "%c", isprint(str[i]) ? str[i] : '.');
+ fprintf(fd, "\"");
+}
+
+static inline int print_value(FILE *fd, int type, struct rtattr *rta)
+{
+ if (rta == NULL) {
+ fprintf(stderr, "Missing value TLV\n");
+ return -1;
+ }
+
+ switch(type) {
+ case TCF_META_TYPE_INT:
+ if (RTA_PAYLOAD(rta) < sizeof(__u32)) {
+ fprintf(stderr, "meta int type value TLV " \
+ "size mismatch.\n");
+ return -1;
+ }
+ fprintf(fd, "%d", rta_getattr_u32(rta));
+ break;
+
+ case TCF_META_TYPE_VAR:
+ print_binary(fd, RTA_DATA(rta), RTA_PAYLOAD(rta));
+ break;
+ }
+
+ return 0;
+}
+
+static int print_object(FILE *fd, struct tcf_meta_val *obj, struct rtattr *rta)
+{
+ int id = TCF_META_ID(obj->kind);
+ int type = TCF_META_TYPE(obj->kind);
+ struct meta_entry *entry;
+
+ if (id == TCF_META_ID_VALUE)
+ return print_value(fd, type, rta);
+
+ entry = lookup_meta_entry_byid(id);
+
+ if (entry == NULL)
+ fprintf(fd, "[unknown meta id %d]", id);
+ else
+ fprintf(fd, "%s", entry->kind);
+
+ if (obj->shift)
+ fprintf(fd, " shift %d", obj->shift);
+
+ switch (type) {
+ case TCF_META_TYPE_INT:
+ if (rta) {
+ if (RTA_PAYLOAD(rta) < sizeof(__u32))
+ goto size_mismatch;
+
+ fprintf(fd, " mask 0x%08x",
+ rta_getattr_u32(rta));
+ }
+ break;
+ }
+
+ return 0;
+
+size_mismatch:
+ fprintf(stderr, "meta int type mask TLV size mismatch\n");
+ return -1;
+}
+
+
+static int meta_print_eopt(FILE *fd, struct tcf_ematch_hdr *hdr, void *data,
+ int data_len)
+{
+ struct rtattr *tb[TCA_EM_META_MAX+1];
+ struct tcf_meta_hdr *meta_hdr;
+
+ if (parse_rtattr(tb, TCA_EM_META_MAX, data, data_len) < 0)
+ return -1;
+
+ if (tb[TCA_EM_META_HDR] == NULL) {
+ fprintf(stderr, "Missing meta header\n");
+ return -1;
+ }
+
+ if (RTA_PAYLOAD(tb[TCA_EM_META_HDR]) < sizeof(*meta_hdr)) {
+ fprintf(stderr, "Meta header size mismatch\n");
+ return -1;
+ }
+
+ meta_hdr = RTA_DATA(tb[TCA_EM_META_HDR]);
+
+ if (print_object(fd, &meta_hdr->left, tb[TCA_EM_META_LVALUE]) < 0)
+ return -1;
+
+ switch (meta_hdr->left.op) {
+ case TCF_EM_OPND_EQ:
+ fprintf(fd, " eq ");
+ break;
+ case TCF_EM_OPND_LT:
+ fprintf(fd, " lt ");
+ break;
+ case TCF_EM_OPND_GT:
+ fprintf(fd, " gt ");
+ break;
+ }
+
+ return print_object(fd, &meta_hdr->right, tb[TCA_EM_META_RVALUE]);
+}
+
+struct ematch_util meta_ematch_util = {
+ .kind = "meta",
+ .kind_num = TCF_EM_META,
+ .parse_eopt = meta_parse_eopt,
+ .print_eopt = meta_print_eopt,
+ .print_usage = meta_print_usage
+};
diff --git a/iproute2/tc/em_nbyte.c b/iproute2/tc/em_nbyte.c
new file mode 100644
index 0000000..87f3e9d
--- /dev/null
+++ b/iproute2/tc/em_nbyte.c
@@ -0,0 +1,143 @@
+/*
+ * em_nbyte.c N-Byte Ematch
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Thomas Graf <tgraf@suug.ch>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <errno.h>
+
+#include "m_ematch.h"
+#include <linux/tc_ematch/tc_em_nbyte.h>
+
+extern struct ematch_util nbyte_ematch_util;
+
+static void nbyte_print_usage(FILE *fd)
+{
+ fprintf(fd,
+ "Usage: nbyte(NEEDLE at OFFSET [layer LAYER])\n" \
+ "where: NEEDLE := { string | \"c-escape-sequence\" }\n" \
+ " OFFSET := int\n" \
+ " LAYER := { link | network | transport | 0..%d }\n" \
+ "\n" \
+ "Example: nbyte(\"ababa\" at 12 layer 1)\n",
+ TCF_LAYER_MAX);
+}
+
+static int nbyte_parse_eopt(struct nlmsghdr *n, struct tcf_ematch_hdr *hdr,
+ struct bstr *args)
+{
+ struct bstr *a;
+ struct bstr *needle = args;
+ unsigned long offset = 0, layer = TCF_LAYER_NETWORK;
+ int offset_present = 0;
+ struct tcf_em_nbyte nb;
+
+ memset(&nb, 0, sizeof(nb));
+
+#define PARSE_ERR(CARG, FMT, ARGS...) \
+ em_parse_error(EINVAL, args, CARG, &nbyte_ematch_util, FMT ,##ARGS)
+
+ if (args == NULL)
+ return PARSE_ERR(args, "nbyte: missing arguments");
+
+ if (needle->len <= 0)
+ return PARSE_ERR(args, "nbyte: needle length is 0");
+
+ for (a = bstr_next(args); a; a = bstr_next(a)) {
+ if (!bstrcmp(a, "at")) {
+ if (a->next == NULL)
+ return PARSE_ERR(a, "nbyte: missing argument");
+ a = bstr_next(a);
+
+ offset = bstrtoul(a);
+ if (offset == ULONG_MAX)
+ return PARSE_ERR(a, "nbyte: invalid offset, " \
+ "must be numeric");
+
+ offset_present = 1;
+ } else if (!bstrcmp(a, "layer")) {
+ if (a->next == NULL)
+ return PARSE_ERR(a, "nbyte: missing argument");
+ a = bstr_next(a);
+
+ layer = parse_layer(a);
+ if (layer == INT_MAX) {
+ layer = bstrtoul(a);
+ if (layer == ULONG_MAX)
+ return PARSE_ERR(a, "nbyte: invalid " \
+ "layer");
+ }
+
+ if (layer > TCF_LAYER_MAX)
+ return PARSE_ERR(a, "nbyte: illegal layer, " \
+ "must be in 0..%d", TCF_LAYER_MAX);
+ } else
+ return PARSE_ERR(a, "nbyte: unknown parameter");
+ }
+
+ if (offset_present == 0)
+ return PARSE_ERR(a, "nbyte: offset required");
+
+ nb.len = needle->len;
+ nb.layer = (__u8) layer;
+ nb.off = (__u16) offset;
+
+ addraw_l(n, MAX_MSG, hdr, sizeof(*hdr));
+ addraw_l(n, MAX_MSG, &nb, sizeof(nb));
+ addraw_l(n, MAX_MSG, needle->data, needle->len);
+
+#undef PARSE_ERR
+ return 0;
+}
+
+static int nbyte_print_eopt(FILE *fd, struct tcf_ematch_hdr *hdr, void *data,
+ int data_len)
+{
+ int i;
+ struct tcf_em_nbyte *nb = data;
+ __u8 *needle;
+
+ if (data_len < sizeof(*nb)) {
+ fprintf(stderr, "NByte header size mismatch\n");
+ return -1;
+ }
+
+ if (data_len < sizeof(*nb) + nb->len) {
+ fprintf(stderr, "NByte payload size mismatch\n");
+ return -1;
+ }
+
+ needle = data + sizeof(*nb);
+
+ for (i = 0; i < nb->len; i++)
+ fprintf(fd, "%02x ", needle[i]);
+
+ fprintf(fd, "\"");
+ for (i = 0; i < nb->len; i++)
+ fprintf(fd, "%c", isprint(needle[i]) ? needle[i] : '.');
+ fprintf(fd, "\" at %d layer %d", nb->off, nb->layer);
+
+ return 0;
+}
+
+struct ematch_util nbyte_ematch_util = {
+ .kind = "nbyte",
+ .kind_num = TCF_EM_NBYTE,
+ .parse_eopt = nbyte_parse_eopt,
+ .print_eopt = nbyte_print_eopt,
+ .print_usage = nbyte_print_usage
+};
diff --git a/iproute2/tc/em_u32.c b/iproute2/tc/em_u32.c
new file mode 100644
index 0000000..21ed70f
--- /dev/null
+++ b/iproute2/tc/em_u32.c
@@ -0,0 +1,177 @@
+/*
+ * em_u32.c U32 Ematch
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Thomas Graf <tgraf@suug.ch>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <errno.h>
+
+#include "m_ematch.h"
+
+extern struct ematch_util u32_ematch_util;
+
+static void u32_print_usage(FILE *fd)
+{
+ fprintf(fd,
+ "Usage: u32(ALIGN VALUE MASK at [ nexthdr+ ] OFFSET)\n" \
+ "where: ALIGN := { u8 | u16 | u32 }\n" \
+ "\n" \
+ "Example: u32(u16 0x1122 0xffff at nexthdr+4)\n");
+}
+
+static int u32_parse_eopt(struct nlmsghdr *n, struct tcf_ematch_hdr *hdr,
+ struct bstr *args)
+{
+ struct bstr *a;
+ int align, nh_len;
+ unsigned long key, mask, offmask = 0, offset;
+ struct tc_u32_key u_key;
+
+ memset(&u_key, 0, sizeof(u_key));
+
+#define PARSE_ERR(CARG, FMT, ARGS...) \
+ em_parse_error(EINVAL, args, CARG, &u32_ematch_util, FMT ,##ARGS)
+
+ if (args == NULL)
+ return PARSE_ERR(args, "u32: missing arguments");
+
+ if (!bstrcmp(args, "u8"))
+ align = 1;
+ else if (!bstrcmp(args, "u16"))
+ align = 2;
+ else if (!bstrcmp(args, "u32"))
+ align = 4;
+ else
+ return PARSE_ERR(args, "u32: invalid alignment");
+
+ a = bstr_next(args);
+ if (a == NULL)
+ return PARSE_ERR(a, "u32: missing key");
+
+ key = bstrtoul(a);
+ if (key == ULONG_MAX)
+ return PARSE_ERR(a, "u32: invalid key, must be numeric");
+
+ a = bstr_next(a);
+ if (a == NULL)
+ return PARSE_ERR(a, "u32: missing mask");
+
+ mask = bstrtoul(a);
+ if (mask == ULONG_MAX)
+ return PARSE_ERR(a, "u32: invalid mask, must be numeric");
+
+ a = bstr_next(a);
+ if (a == NULL || bstrcmp(a, "at") != 0)
+ return PARSE_ERR(a, "u32: missing \"at\"");
+
+ a = bstr_next(a);
+ if (a == NULL)
+ return PARSE_ERR(a, "u32: missing offset");
+
+ nh_len = strlen("nexthdr+");
+ if (a->len > nh_len && !memcmp(a->data, "nexthdr+", nh_len)) {
+ char buf[a->len - nh_len + 1];
+ offmask = -1;
+ memcpy(buf, a->data + nh_len, a->len - nh_len);
+ offset = strtoul(buf, NULL, 0);
+ } else if (!bstrcmp(a, "nexthdr+")) {
+ a = bstr_next(a);
+ if (a == NULL)
+ return PARSE_ERR(a, "u32: missing offset");
+ offset = bstrtoul(a);
+ } else
+ offset = bstrtoul(a);
+
+ if (offset == ULONG_MAX)
+ return PARSE_ERR(a, "u32: invalid offset");
+
+ if (a->next)
+ return PARSE_ERR(a->next, "u32: unexpected trailer");
+
+ switch (align) {
+ case 1:
+ if (key > 0xFF)
+ return PARSE_ERR(a, "Illegal key (>0xFF)");
+ if (mask > 0xFF)
+ return PARSE_ERR(a, "Illegal mask (>0xFF)");
+
+ key <<= 24 - ((offset & 3) * 8);
+ mask <<= 24 - ((offset & 3) * 8);
+ offset &= ~3;
+ break;
+
+ case 2:
+ if (key > 0xFFFF)
+ return PARSE_ERR(a, "Illegal key (>0xFFFF)");
+ if (mask > 0xFFFF)
+ return PARSE_ERR(a, "Illegal mask (>0xFFFF)");
+
+ if ((offset & 3) == 0) {
+ key <<= 16;
+ mask <<= 16;
+ }
+ offset &= ~3;
+ break;
+ }
+
+ key = htonl(key);
+ mask = htonl(mask);
+
+ if (offset % 4)
+ return PARSE_ERR(a, "u32: invalid offset alignment, " \
+ "must be aligned to 4.");
+
+ key &= mask;
+
+ u_key.mask = mask;
+ u_key.val = key;
+ u_key.off = offset;
+ u_key.offmask = offmask;
+
+ addraw_l(n, MAX_MSG, hdr, sizeof(*hdr));
+ addraw_l(n, MAX_MSG, &u_key, sizeof(u_key));
+
+#undef PARSE_ERR
+ return 0;
+}
+
+static int u32_print_eopt(FILE *fd, struct tcf_ematch_hdr *hdr, void *data,
+ int data_len)
+{
+ struct tc_u32_key *u_key = data;
+
+ if (data_len < sizeof(*u_key)) {
+ fprintf(stderr, "U32 header size mismatch\n");
+ return -1;
+ }
+
+ fprintf(fd, "%08x/%08x at %s%d",
+ (unsigned int) ntohl(u_key->val),
+ (unsigned int) ntohl(u_key->mask),
+ u_key->offmask ? "nexthdr+" : "",
+ u_key->off);
+
+ return 0;
+}
+
+struct ematch_util u32_ematch_util = {
+ .kind = "u32",
+ .kind_num = TCF_EM_U32,
+ .parse_eopt = u32_parse_eopt,
+ .print_eopt = u32_print_eopt,
+ .print_usage = u32_print_usage
+};
diff --git a/iproute2/tc/emp_ematch.l b/iproute2/tc/emp_ematch.l
new file mode 100644
index 0000000..d9b45be
--- /dev/null
+++ b/iproute2/tc/emp_ematch.l
@@ -0,0 +1,145 @@
+%{
+ #include "emp_ematch.yacc.h"
+ #include "m_ematch.h"
+
+ extern int ematch_argc;
+ extern char **ematch_argv;
+
+ #define yylval ematch_lval
+
+ #define NEXT_EM_ARG() do { ematch_argc--; ematch_argv++; } while(0);
+
+ #define YY_INPUT(buf, result, max_size) \
+ { \
+ next: \
+ if (ematch_argc <= 0) \
+ result = YY_NULL; \
+ else if (**ematch_argv == '\0') { \
+ NEXT_EM_ARG(); \
+ goto next; \
+ } else { \
+ if (max_size <= strlen(*ematch_argv) + 1) { \
+ fprintf(stderr, "match argument too long.\n"); \
+ result = YY_NULL; \
+ } else { \
+ strcpy(buf, *ematch_argv); \
+ result = strlen(*ematch_argv) + 1; \
+ buf[result-1] = ' '; \
+ buf[result] = '\0'; \
+ NEXT_EM_ARG(); \
+ } \
+ } \
+ }
+
+ static void __attribute__ ((unused)) yyunput (int c,char *buf_ptr );
+ static void __attribute__ ((unused)) yy_push_state (int new_state );
+ static void __attribute__ ((unused)) yy_pop_state (void);
+ static int __attribute__ ((unused)) yy_top_state (void );
+
+ static char *strbuf;
+ static unsigned int strbuf_size;
+ static unsigned int strbuf_index;
+
+ static void strbuf_enlarge(void)
+ {
+ strbuf_size += 512;
+ strbuf = realloc(strbuf, strbuf_size);
+ }
+
+ static void strbuf_append_char(char c)
+ {
+ while (strbuf_index >= strbuf_size)
+ strbuf_enlarge();
+ strbuf[strbuf_index++] = c;
+ }
+
+ static void strbuf_append_charp(char *s)
+ {
+ while (strbuf_index >= strbuf_size)
+ strbuf_enlarge();
+ memcpy(strbuf + strbuf_index, s, strlen(s));
+ strbuf_index += strlen(s);
+ }
+
+%}
+
+%x lexstr
+
+%option 8bit stack warn noyywrap prefix="ematch_"
+%%
+[ \t\r\n]+
+
+\" {
+ if (strbuf == NULL) {
+ strbuf_size = 512;
+ strbuf = calloc(1, strbuf_size);
+ if (strbuf == NULL)
+ return ERROR;
+ }
+ strbuf_index = 0;
+
+ BEGIN(lexstr);
+ }
+
+<lexstr>\" {
+ BEGIN(INITIAL);
+ yylval.b = bstr_new(strbuf, strbuf_index);
+ yylval.b->quoted = 1;
+ return ATTRIBUTE;
+ }
+
+<lexstr>\\[0-7]{1,3} { /* octal escape sequence */
+ int res;
+
+ sscanf(yytext + 1, "%o", &res);
+ if (res > 0xFF) {
+ fprintf(stderr, "error: octal escape sequence" \
+ " out of range\n");
+ return ERROR;
+ }
+ strbuf_append_char((unsigned char) res);
+ }
+
+<lexstr>\\[0-9]+ { /* catch wrong octal escape seq. */
+ fprintf(stderr, "error: invalid octale escape sequence\n");
+ return ERROR;
+ }
+
+<lexstr>\\x[0-9a-fA-F]{1,2} {
+ int res;
+
+ sscanf(yytext + 2, "%x", &res);
+
+ if (res > 0xFF) {
+ fprintf(stderr, "error: hexadecimal escape " \
+ "sequence out of range\n");
+ return ERROR;
+ }
+ strbuf_append_char((unsigned char) res);
+ }
+
+<lexstr>\\n strbuf_append_char('\n');
+<lexstr>\\r strbuf_append_char('\r');
+<lexstr>\\t strbuf_append_char('\t');
+<lexstr>\\v strbuf_append_char('\v');
+<lexstr>\\b strbuf_append_char('\b');
+<lexstr>\\f strbuf_append_char('\f');
+<lexstr>\\a strbuf_append_char('\a');
+
+<lexstr>\\(.|\n) strbuf_append_char(yytext[1]);
+<lexstr>[^\\\n\"]+ strbuf_append_charp(yytext);
+
+[aA][nN][dD] return AND;
+[oO][rR] return OR;
+[nN][oO][tT] return NOT;
+"(" |
+")" {
+ return yylval.i = *yytext;
+ }
+[^ \t\r\n()]+ {
+ yylval.b = bstr_alloc(yytext);
+ if (yylval.b == NULL)
+ return ERROR;
+ return ATTRIBUTE;
+ }
+%%
diff --git a/iproute2/tc/emp_ematch.y b/iproute2/tc/emp_ematch.y
new file mode 100644
index 0000000..2e6cf35
--- /dev/null
+++ b/iproute2/tc/emp_ematch.y
@@ -0,0 +1,100 @@
+%{
+ #include <stdio.h>
+ #include <stdlib.h>
+ #include <malloc.h>
+ #include <string.h>
+ #include "m_ematch.h"
+%}
+
+%locations
+%token-table
+%error-verbose
+%name-prefix "ematch_"
+
+%union {
+ unsigned int i;
+ struct bstr *b;
+ struct ematch *e;
+}
+
+%{
+ extern int ematch_lex(void);
+ extern void yyerror(const char *s);
+ extern struct ematch *ematch_root;
+ extern char *ematch_err;
+%}
+
+%token <i> ERROR
+%token <b> ATTRIBUTE
+%token <i> AND OR NOT
+%type <i> invert relation
+%type <e> match expr
+%type <b> args
+%right AND OR
+%start input
+%%
+input:
+ /* empty */
+ | expr
+ { ematch_root = $1; }
+ | expr error
+ {
+ ematch_root = $1;
+ YYACCEPT;
+ }
+ ;
+
+expr:
+ match
+ { $$ = $1; }
+ | match relation expr
+ {
+ $1->relation = $2;
+ $1->next = $3;
+ $$ = $1;
+ }
+ ;
+
+match:
+ invert ATTRIBUTE '(' args ')'
+ {
+ $2->next = $4;
+ $$ = new_ematch($2, $1);
+ if ($$ == NULL)
+ YYABORT;
+ }
+ | invert '(' expr ')'
+ {
+ $$ = new_ematch(NULL, $1);
+ if ($$ == NULL)
+ YYABORT;
+ $$->child = $3;
+ }
+ ;
+
+args:
+ ATTRIBUTE
+ { $$ = $1; }
+ | ATTRIBUTE args
+ { $1->next = $2; }
+ ;
+
+relation:
+ AND
+ { $$ = TCF_EM_REL_AND; }
+ | OR
+ { $$ = TCF_EM_REL_OR; }
+ ;
+
+invert:
+ /* empty */
+ { $$ = 0; }
+ | NOT
+ { $$ = 1; }
+ ;
+%%
+
+ void yyerror(const char *s)
+ {
+ ematch_err = strdup(s);
+ }
diff --git a/iproute2/tc/f_basic.c b/iproute2/tc/f_basic.c
new file mode 100644
index 0000000..4adf1d2
--- /dev/null
+++ b/iproute2/tc/f_basic.c
@@ -0,0 +1,147 @@
+/*
+ * f_basic.c Basic Classifier
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Thomas Graf <tgraf@suug.ch>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <linux/if.h>
+
+#include "utils.h"
+#include "tc_util.h"
+#include "m_ematch.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... basic [ match EMATCH_TREE ] \n");
+ fprintf(stderr, " [ action ACTION_SPEC ] [ classid CLASSID ]\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "Where: SELECTOR := SAMPLE SAMPLE ...\n");
+ fprintf(stderr, " FILTERID := X:Y:Z\n");
+ fprintf(stderr, " ACTION_SPEC := ... look at individual actions\n");
+ fprintf(stderr, "\nNOTE: CLASSID is parsed as hexadecimal input.\n");
+}
+
+static int basic_parse_opt(struct filter_util *qu, char *handle,
+ int argc, char **argv, struct nlmsghdr *n)
+{
+ struct tcmsg *t = NLMSG_DATA(n);
+ struct rtattr *tail;
+ long h = 0;
+
+ if (handle) {
+ h = strtol(handle, NULL, 0);
+ if (h == LONG_MIN || h == LONG_MAX) {
+ fprintf(stderr, "Illegal handle \"%s\", must be numeric.\n",
+ handle);
+ return -1;
+ }
+ }
+ t->tcm_handle = h;
+
+ if (argc == 0)
+ return 0;
+
+ tail = (struct rtattr*)(((void*)n)+NLMSG_ALIGN(n->nlmsg_len));
+ addattr_l(n, MAX_MSG, TCA_OPTIONS, NULL, 0);
+
+ while (argc > 0) {
+ if (matches(*argv, "match") == 0) {
+ NEXT_ARG();
+ if (parse_ematch(&argc, &argv, TCA_BASIC_EMATCHES, n)) {
+ fprintf(stderr, "Illegal \"ematch\"\n");
+ return -1;
+ }
+ continue;
+ } else if (matches(*argv, "classid") == 0 ||
+ strcmp(*argv, "flowid") == 0) {
+ unsigned handle;
+ NEXT_ARG();
+ if (get_tc_classid(&handle, *argv)) {
+ fprintf(stderr, "Illegal \"classid\"\n");
+ return -1;
+ }
+ addattr_l(n, MAX_MSG, TCA_BASIC_CLASSID, &handle, 4);
+ } else if (matches(*argv, "action") == 0) {
+ NEXT_ARG();
+ if (parse_action(&argc, &argv, TCA_BASIC_ACT, n)) {
+ fprintf(stderr, "Illegal \"action\"\n");
+ return -1;
+ }
+ continue;
+
+ } else if (matches(*argv, "police") == 0) {
+ NEXT_ARG();
+ if (parse_police(&argc, &argv, TCA_BASIC_POLICE, n)) {
+ fprintf(stderr, "Illegal \"police\"\n");
+ return -1;
+ }
+ continue;
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ tail->rta_len = (((void*)n)+n->nlmsg_len) - (void*)tail;
+ return 0;
+}
+
+static int basic_print_opt(struct filter_util *qu, FILE *f,
+ struct rtattr *opt, __u32 handle)
+{
+ struct rtattr *tb[TCA_BASIC_MAX+1];
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_BASIC_MAX, opt);
+
+ if (handle)
+ fprintf(f, "handle 0x%x ", handle);
+
+ if (tb[TCA_BASIC_CLASSID]) {
+ SPRINT_BUF(b1);
+ fprintf(f, "flowid %s ",
+ sprint_tc_classid(rta_getattr_u32(tb[TCA_BASIC_CLASSID]), b1));
+ }
+
+ if (tb[TCA_BASIC_EMATCHES])
+ print_ematch(f, tb[TCA_BASIC_EMATCHES]);
+
+ if (tb[TCA_BASIC_POLICE]) {
+ fprintf(f, "\n");
+ tc_print_police(f, tb[TCA_BASIC_POLICE]);
+ }
+
+ if (tb[TCA_BASIC_ACT]) {
+ tc_print_action(f, tb[TCA_BASIC_ACT]);
+ }
+
+ return 0;
+}
+
+struct filter_util basic_filter_util = {
+ .id = "basic",
+ .parse_fopt = basic_parse_opt,
+ .print_fopt = basic_print_opt,
+};
diff --git a/iproute2/tc/f_bpf.c b/iproute2/tc/f_bpf.c
new file mode 100644
index 0000000..afc2e58
--- /dev/null
+++ b/iproute2/tc/f_bpf.c
@@ -0,0 +1,203 @@
+/*
+ * f_bpf.c BPF-based Classifier
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Daniel Borkmann <dborkman@redhat.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+
+#include <linux/bpf.h>
+
+#include "utils.h"
+#include "tc_util.h"
+#include "tc_bpf.h"
+
+static const enum bpf_prog_type bpf_type = BPF_PROG_TYPE_SCHED_CLS;
+
+static const int nla_tbl[BPF_NLA_MAX] = {
+ [BPF_NLA_OPS_LEN] = TCA_BPF_OPS_LEN,
+ [BPF_NLA_OPS] = TCA_BPF_OPS,
+ [BPF_NLA_FD] = TCA_BPF_FD,
+ [BPF_NLA_NAME] = TCA_BPF_NAME,
+};
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... bpf ...\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "BPF use case:\n");
+ fprintf(stderr, " bytecode BPF_BYTECODE\n");
+ fprintf(stderr, " bytecode-file FILE\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "eBPF use case:\n");
+ fprintf(stderr, " object-file FILE [ section CLS_NAME ] [ export UDS_FILE ]");
+ fprintf(stderr, " [ verbose ] [ direct-action ]\n");
+ fprintf(stderr, " object-pinned FILE [ direct-action ]\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "Common remaining options:\n");
+ fprintf(stderr, " [ action ACTION_SPEC ]\n");
+ fprintf(stderr, " [ classid CLASSID ]\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "Where BPF_BYTECODE := \'s,c t f k,c t f k,c t f k,...\'\n");
+ fprintf(stderr, "c,t,f,k and s are decimals; s denotes number of 4-tuples\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "Where FILE points to a file containing the BPF_BYTECODE string,\n");
+ fprintf(stderr, "an ELF file containing eBPF map definitions and bytecode, or a\n");
+ fprintf(stderr, "pinned eBPF program.\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "Where CLS_NAME refers to the section name containing the\n");
+ fprintf(stderr, "classifier (default \'%s\').\n", bpf_default_section(bpf_type));
+ fprintf(stderr, "\n");
+ fprintf(stderr, "Where UDS_FILE points to a unix domain socket file in order\n");
+ fprintf(stderr, "to hand off control of all created eBPF maps to an agent.\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "ACTION_SPEC := ... look at individual actions\n");
+ fprintf(stderr, "NOTE: CLASSID is parsed as hexadecimal input.\n");
+}
+
+static int bpf_parse_opt(struct filter_util *qu, char *handle,
+ int argc, char **argv, struct nlmsghdr *n)
+{
+ const char *bpf_obj = NULL, *bpf_uds_name = NULL;
+ struct tcmsg *t = NLMSG_DATA(n);
+ unsigned int bpf_flags = 0;
+ bool seen_run = false;
+ struct rtattr *tail;
+ int ret = 0;
+
+ if (argc == 0)
+ return 0;
+
+ if (handle) {
+ if (get_u32(&t->tcm_handle, handle, 0)) {
+ fprintf(stderr, "Illegal \"handle\"\n");
+ return -1;
+ }
+ }
+
+ tail = (struct rtattr *)(((void *)n) + NLMSG_ALIGN(n->nlmsg_len));
+ addattr_l(n, MAX_MSG, TCA_OPTIONS, NULL, 0);
+
+ while (argc > 0) {
+ if (matches(*argv, "run") == 0) {
+ NEXT_ARG();
+opt_bpf:
+ seen_run = true;
+ if (bpf_parse_common(&argc, &argv, nla_tbl, bpf_type,
+ &bpf_obj, &bpf_uds_name, n)) {
+ fprintf(stderr, "Failed to retrieve (e)BPF data!\n");
+ return -1;
+ }
+ } else if (matches(*argv, "classid") == 0 ||
+ matches(*argv, "flowid") == 0) {
+ unsigned int handle;
+
+ NEXT_ARG();
+ if (get_tc_classid(&handle, *argv)) {
+ fprintf(stderr, "Illegal \"classid\"\n");
+ return -1;
+ }
+ addattr32(n, MAX_MSG, TCA_BPF_CLASSID, handle);
+ } else if (matches(*argv, "direct-action") == 0 ||
+ matches(*argv, "da") == 0) {
+ bpf_flags |= TCA_BPF_FLAG_ACT_DIRECT;
+ } else if (matches(*argv, "action") == 0) {
+ NEXT_ARG();
+ if (parse_action(&argc, &argv, TCA_BPF_ACT, n)) {
+ fprintf(stderr, "Illegal \"action\"\n");
+ return -1;
+ }
+ continue;
+ } else if (matches(*argv, "police") == 0) {
+ NEXT_ARG();
+ if (parse_police(&argc, &argv, TCA_BPF_POLICE, n)) {
+ fprintf(stderr, "Illegal \"police\"\n");
+ return -1;
+ }
+ continue;
+ } else if (matches(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ if (!seen_run)
+ goto opt_bpf;
+
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+
+ NEXT_ARG_FWD();
+ }
+
+ if (bpf_obj && bpf_flags)
+ addattr32(n, MAX_MSG, TCA_BPF_FLAGS, bpf_flags);
+
+ tail->rta_len = (((void *)n) + n->nlmsg_len) - (void *)tail;
+
+ if (bpf_uds_name)
+ ret = bpf_send_map_fds(bpf_uds_name, bpf_obj);
+
+ return ret;
+}
+
+static int bpf_print_opt(struct filter_util *qu, FILE *f,
+ struct rtattr *opt, __u32 handle)
+{
+ struct rtattr *tb[TCA_BPF_MAX + 1];
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_BPF_MAX, opt);
+
+ if (handle)
+ fprintf(f, "handle 0x%x ", handle);
+
+ if (tb[TCA_BPF_CLASSID]) {
+ SPRINT_BUF(b1);
+ fprintf(f, "flowid %s ",
+ sprint_tc_classid(rta_getattr_u32(tb[TCA_BPF_CLASSID]), b1));
+ }
+
+ if (tb[TCA_BPF_NAME])
+ fprintf(f, "%s ", rta_getattr_str(tb[TCA_BPF_NAME]));
+ else if (tb[TCA_BPF_FD])
+ fprintf(f, "pfd %u ", rta_getattr_u32(tb[TCA_BPF_FD]));
+
+ if (tb[TCA_BPF_FLAGS]) {
+ unsigned int flags = rta_getattr_u32(tb[TCA_BPF_FLAGS]);
+
+ if (flags & TCA_BPF_FLAG_ACT_DIRECT)
+ fprintf(f, "direct-action ");
+ }
+
+ if (tb[TCA_BPF_OPS] && tb[TCA_BPF_OPS_LEN]) {
+ bpf_print_ops(f, tb[TCA_BPF_OPS],
+ rta_getattr_u16(tb[TCA_BPF_OPS_LEN]));
+ fprintf(f, "\n");
+ }
+
+ if (tb[TCA_BPF_POLICE]) {
+ fprintf(f, "\n");
+ tc_print_police(f, tb[TCA_BPF_POLICE]);
+ }
+
+ if (tb[TCA_BPF_ACT]) {
+ tc_print_action(f, tb[TCA_BPF_ACT]);
+ }
+
+ return 0;
+}
+
+struct filter_util bpf_filter_util = {
+ .id = "bpf",
+ .parse_fopt = bpf_parse_opt,
+ .print_fopt = bpf_print_opt,
+};
diff --git a/iproute2/tc/f_cgroup.c b/iproute2/tc/f_cgroup.c
new file mode 100644
index 0000000..53f7406
--- /dev/null
+++ b/iproute2/tc/f_cgroup.c
@@ -0,0 +1,114 @@
+/*
+ * f_cgroup.c Control Group Classifier
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Thomas Graf <tgraf@infradead.org>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include "utils.h"
+#include "tc_util.h"
+#include "m_ematch.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... cgroup [ match EMATCH_TREE ]\n");
+ fprintf(stderr, " [ action ACTION_SPEC ]\n");
+}
+
+static int cgroup_parse_opt(struct filter_util *qu, char *handle,
+ int argc, char **argv, struct nlmsghdr *n)
+{
+ struct tcmsg *t = NLMSG_DATA(n);
+ struct rtattr *tail;
+ long h = 0;
+
+ if (handle) {
+ h = strtol(handle, NULL, 0);
+ if (h == LONG_MIN || h == LONG_MAX) {
+ fprintf(stderr, "Illegal handle \"%s\", must be numeric.\n",
+ handle);
+ return -1;
+ }
+ }
+
+ t->tcm_handle = h;
+
+ tail = (struct rtattr*)(((void*)n)+NLMSG_ALIGN(n->nlmsg_len));
+ addattr_l(n, MAX_MSG, TCA_OPTIONS, NULL, 0);
+
+ while (argc > 0) {
+ if (matches(*argv, "match") == 0) {
+ NEXT_ARG();
+ if (parse_ematch(&argc, &argv, TCA_CGROUP_EMATCHES, n)) {
+ fprintf(stderr, "Illegal \"ematch\"\n");
+ return -1;
+ }
+ continue;
+ } else if (matches(*argv, "action") == 0) {
+ NEXT_ARG();
+ if (parse_action(&argc, &argv, TCA_CGROUP_ACT, n)) {
+ fprintf(stderr, "Illegal \"action\"\n");
+ return -1;
+ }
+ continue;
+
+ } else if (matches(*argv, "police") == 0) {
+ NEXT_ARG();
+ if (parse_police(&argc, &argv, TCA_CGROUP_POLICE, n)) {
+ fprintf(stderr, "Illegal \"police\"\n");
+ return -1;
+ }
+ continue;
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ }
+
+ tail->rta_len = (((void*)n)+n->nlmsg_len) - (void*)tail;
+ return 0;
+}
+
+static int cgroup_print_opt(struct filter_util *qu, FILE *f,
+ struct rtattr *opt, __u32 handle)
+{
+ struct rtattr *tb[TCA_CGROUP_MAX+1];
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_CGROUP_MAX, opt);
+
+ if (handle)
+ fprintf(f, "handle 0x%x ", handle);
+
+ if (tb[TCA_CGROUP_EMATCHES])
+ print_ematch(f, tb[TCA_CGROUP_EMATCHES]);
+
+ if (tb[TCA_CGROUP_POLICE]) {
+ fprintf(f, "\n");
+ tc_print_police(f, tb[TCA_CGROUP_POLICE]);
+ }
+
+ if (tb[TCA_CGROUP_ACT])
+ tc_print_action(f, tb[TCA_CGROUP_ACT]);
+
+ return 0;
+}
+
+struct filter_util cgroup_filter_util = {
+ .id = "cgroup",
+ .parse_fopt = cgroup_parse_opt,
+ .print_fopt = cgroup_print_opt,
+};
diff --git a/iproute2/tc/f_flow.c b/iproute2/tc/f_flow.c
new file mode 100644
index 0000000..f398f55
--- /dev/null
+++ b/iproute2/tc/f_flow.c
@@ -0,0 +1,361 @@
+/*
+ * f_flow.c Flow filter
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Patrick McHardy <kaber@trash.net>
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <errno.h>
+
+#include "utils.h"
+#include "tc_util.h"
+#include "m_ematch.h"
+
+static void explain(void)
+{
+ fprintf(stderr,
+"Usage: ... flow ...\n"
+"\n"
+" [mapping mode]: map key KEY [ OPS ] ...\n"
+" [hashing mode]: hash keys KEY-LIST ... [ perturb SECS ]\n"
+"\n"
+" [ divisor NUM ] [ baseclass ID ] [ match EMATCH_TREE ]\n"
+" [ action ACTION_SPEC ]\n"
+"\n"
+"KEY-LIST := [ KEY-LIST , ] KEY\n"
+"KEY := [ src | dst | proto | proto-src | proto-dst | iif | priority | \n"
+" mark | nfct | nfct-src | nfct-dst | nfct-proto-src | \n"
+" nfct-proto-dst | rt-classid | sk-uid | sk-gid |\n"
+" vlan-tag | rxhash ]\n"
+"OPS := [ or NUM | and NUM | xor NUM | rshift NUM | addend NUM ]\n"
+"ID := X:Y\n"
+ );
+}
+
+static const char *flow_keys[FLOW_KEY_MAX+1] = {
+ [FLOW_KEY_SRC] = "src",
+ [FLOW_KEY_DST] = "dst",
+ [FLOW_KEY_PROTO] = "proto",
+ [FLOW_KEY_PROTO_SRC] = "proto-src",
+ [FLOW_KEY_PROTO_DST] = "proto-dst",
+ [FLOW_KEY_IIF] = "iif",
+ [FLOW_KEY_PRIORITY] = "priority",
+ [FLOW_KEY_MARK] = "mark",
+ [FLOW_KEY_NFCT] = "nfct",
+ [FLOW_KEY_NFCT_SRC] = "nfct-src",
+ [FLOW_KEY_NFCT_DST] = "nfct-dst",
+ [FLOW_KEY_NFCT_PROTO_SRC] = "nfct-proto-src",
+ [FLOW_KEY_NFCT_PROTO_DST] = "nfct-proto-dst",
+ [FLOW_KEY_RTCLASSID] = "rt-classid",
+ [FLOW_KEY_SKUID] = "sk-uid",
+ [FLOW_KEY_SKGID] = "sk-gid",
+ [FLOW_KEY_VLAN_TAG] = "vlan-tag",
+ [FLOW_KEY_RXHASH] = "rxhash",
+};
+
+static int flow_parse_keys(__u32 *keys, __u32 *nkeys, char *argv)
+{
+ char *s, *sep;
+ unsigned int i;
+
+ *keys = 0;
+ *nkeys = 0;
+ s = argv;
+ while (s != NULL) {
+ sep = strchr(s, ',');
+ if (sep)
+ *sep = '\0';
+
+ for (i = 0; i <= FLOW_KEY_MAX; i++) {
+ if (matches(s, flow_keys[i]) == 0) {
+ *keys |= 1 << i;
+ (*nkeys)++;
+ break;
+ }
+ }
+ if (i > FLOW_KEY_MAX) {
+ fprintf(stderr, "Unknown flow key \"%s\"\n", s);
+ return -1;
+ }
+ s = sep ? sep + 1 : NULL;
+ }
+ return 0;
+}
+
+static void transfer_bitop(__u32 *mask, __u32 *xor, __u32 m, __u32 x)
+{
+ *xor = x ^ (*xor & m);
+ *mask &= m;
+}
+
+static int get_addend(__u32 *addend, char *argv, __u32 keys)
+{
+ inet_prefix addr;
+ int sign = 0;
+ __u32 tmp;
+
+ if (*argv == '-') {
+ sign = 1;
+ argv++;
+ }
+
+ if (get_u32(&tmp, argv, 0) == 0)
+ goto out;
+
+ if (keys & (FLOW_KEY_SRC | FLOW_KEY_DST |
+ FLOW_KEY_NFCT_SRC | FLOW_KEY_NFCT_DST) &&
+ get_addr(&addr, argv, AF_UNSPEC) == 0) {
+ switch (addr.family) {
+ case AF_INET:
+ tmp = ntohl(addr.data[0]);
+ goto out;
+ case AF_INET6:
+ tmp = ntohl(addr.data[3]);
+ goto out;
+ }
+ }
+
+ return -1;
+out:
+ if (sign)
+ tmp = -tmp;
+ *addend = tmp;
+ return 0;
+}
+
+static int flow_parse_opt(struct filter_util *fu, char *handle,
+ int argc, char **argv, struct nlmsghdr *n)
+{
+ struct tc_police tp;
+ struct tcmsg *t = NLMSG_DATA(n);
+ struct rtattr *tail;
+ __u32 mask = ~0U, xor = 0;
+ __u32 keys = 0, nkeys = 0;
+ __u32 mode = FLOW_MODE_MAP;
+ __u32 tmp;
+
+ memset(&tp, 0, sizeof(tp));
+
+ if (handle) {
+ if (get_u32(&t->tcm_handle, handle, 0)) {
+ fprintf(stderr, "Illegal \"handle\"\n");
+ return -1;
+ }
+ }
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 4096, TCA_OPTIONS, NULL, 0);
+
+ while (argc > 0) {
+ if (matches(*argv, "map") == 0) {
+ mode = FLOW_MODE_MAP;
+ } else if (matches(*argv, "hash") == 0) {
+ mode = FLOW_MODE_HASH;
+ } else if (matches(*argv, "keys") == 0) {
+ NEXT_ARG();
+ if (flow_parse_keys(&keys, &nkeys, *argv))
+ return -1;
+ addattr32(n, 4096, TCA_FLOW_KEYS, keys);
+ } else if (matches(*argv, "and") == 0) {
+ NEXT_ARG();
+ if (get_u32(&tmp, *argv, 0)) {
+ fprintf(stderr, "Illegal \"mask\"\n");
+ return -1;
+ }
+ transfer_bitop(&mask, &xor, tmp, 0);
+ } else if (matches(*argv, "or") == 0) {
+ NEXT_ARG();
+ if (get_u32(&tmp, *argv, 0)) {
+ fprintf(stderr, "Illegal \"or\"\n");
+ return -1;
+ }
+ transfer_bitop(&mask, &xor, ~tmp, tmp);
+ } else if (matches(*argv, "xor") == 0) {
+ NEXT_ARG();
+ if (get_u32(&tmp, *argv, 0)) {
+ fprintf(stderr, "Illegal \"xor\"\n");
+ return -1;
+ }
+ transfer_bitop(&mask, &xor, ~0, tmp);
+ } else if (matches(*argv, "rshift") == 0) {
+ NEXT_ARG();
+ if (get_u32(&tmp, *argv, 0)) {
+ fprintf(stderr, "Illegal \"rshift\"\n");
+ return -1;
+ }
+ addattr32(n, 4096, TCA_FLOW_RSHIFT, tmp);
+ } else if (matches(*argv, "addend") == 0) {
+ NEXT_ARG();
+ if (get_addend(&tmp, *argv, keys)) {
+ fprintf(stderr, "Illegal \"addend\"\n");
+ return -1;
+ }
+ addattr32(n, 4096, TCA_FLOW_ADDEND, tmp);
+ } else if (matches(*argv, "divisor") == 0) {
+ NEXT_ARG();
+ if (get_u32(&tmp, *argv, 0)) {
+ fprintf(stderr, "Illegal \"divisor\"\n");
+ return -1;
+ }
+ addattr32(n, 4096, TCA_FLOW_DIVISOR, tmp);
+ } else if (matches(*argv, "baseclass") == 0) {
+ NEXT_ARG();
+ if (get_tc_classid(&tmp, *argv) || TC_H_MIN(tmp) == 0) {
+ fprintf(stderr, "Illegal \"baseclass\"\n");
+ return -1;
+ }
+ addattr32(n, 4096, TCA_FLOW_BASECLASS, tmp);
+ } else if (matches(*argv, "perturb") == 0) {
+ NEXT_ARG();
+ if (get_u32(&tmp, *argv, 0)) {
+ fprintf(stderr, "Illegal \"perturb\"\n");
+ return -1;
+ }
+ addattr32(n, 4096, TCA_FLOW_PERTURB, tmp);
+ } else if (matches(*argv, "police") == 0) {
+ NEXT_ARG();
+ if (parse_police(&argc, &argv, TCA_FLOW_POLICE, n)) {
+ fprintf(stderr, "Illegal \"police\"\n");
+ return -1;
+ }
+ continue;
+ } else if (matches(*argv, "action") == 0) {
+ NEXT_ARG();
+ if (parse_action(&argc, &argv, TCA_FLOW_ACT, n)) {
+ fprintf(stderr, "Illegal \"action\"\n");
+ return -1;
+ }
+ continue;
+ } else if (matches(*argv, "match") == 0) {
+ NEXT_ARG();
+ if (parse_ematch(&argc, &argv, TCA_FLOW_EMATCHES, n)) {
+ fprintf(stderr, "Illegal \"ematch\"\n");
+ return -1;
+ }
+ continue;
+ } else if (matches(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argv++, argc--;
+ }
+
+ if (nkeys > 1 && mode != FLOW_MODE_HASH) {
+ fprintf(stderr, "Invalid mode \"map\" for multiple keys\n");
+ return -1;
+ }
+ addattr32(n, 4096, TCA_FLOW_MODE, mode);
+
+ if (mask != ~0 || xor != 0) {
+ addattr32(n, 4096, TCA_FLOW_MASK, mask);
+ addattr32(n, 4096, TCA_FLOW_XOR, xor);
+ }
+
+ tail->rta_len = (void *)NLMSG_TAIL(n) - (void *)tail;
+ return 0;
+}
+
+static int flow_print_opt(struct filter_util *fu, FILE *f, struct rtattr *opt,
+ __u32 handle)
+{
+ struct rtattr *tb[TCA_FLOW_MAX+1];
+ SPRINT_BUF(b1);
+ unsigned int i;
+ __u32 mask = ~0, val = 0;
+
+ if (opt == NULL)
+ return -EINVAL;
+
+ parse_rtattr_nested(tb, TCA_FLOW_MAX, opt);
+
+ fprintf(f, "handle 0x%x ", handle);
+
+ if (tb[TCA_FLOW_MODE]) {
+ __u32 mode = rta_getattr_u32(tb[TCA_FLOW_MODE]);
+
+ switch (mode) {
+ case FLOW_MODE_MAP:
+ fprintf(f, "map ");
+ break;
+ case FLOW_MODE_HASH:
+ fprintf(f, "hash ");
+ break;
+ }
+ }
+
+ if (tb[TCA_FLOW_KEYS]) {
+ __u32 keymask = rta_getattr_u32(tb[TCA_FLOW_KEYS]);
+ char *sep = "";
+
+ fprintf(f, "keys ");
+ for (i = 0; i <= FLOW_KEY_MAX; i++) {
+ if (keymask & (1 << i)) {
+ fprintf(f, "%s%s", sep, flow_keys[i]);
+ sep = ",";
+ }
+ }
+ fprintf(f, " ");
+ }
+
+ if (tb[TCA_FLOW_MASK])
+ mask = rta_getattr_u32(tb[TCA_FLOW_MASK]);
+ if (tb[TCA_FLOW_XOR])
+ val = rta_getattr_u32(tb[TCA_FLOW_XOR]);
+
+ if (mask != ~0 || val != 0) {
+ __u32 or = (mask & val) ^ val;
+ __u32 xor = mask & val;
+
+ if (mask != ~0)
+ fprintf(f, "and 0x%.8x ", mask);
+ if (xor != 0)
+ fprintf(f, "xor 0x%.8x ", xor);
+ if (or != 0)
+ fprintf(f, "or 0x%.8x ", or);
+ }
+
+ if (tb[TCA_FLOW_RSHIFT])
+ fprintf(f, "rshift %u ",
+ rta_getattr_u32(tb[TCA_FLOW_RSHIFT]));
+ if (tb[TCA_FLOW_ADDEND])
+ fprintf(f, "addend 0x%x ",
+ rta_getattr_u32(tb[TCA_FLOW_ADDEND]));
+
+ if (tb[TCA_FLOW_DIVISOR])
+ fprintf(f, "divisor %u ",
+ rta_getattr_u32(tb[TCA_FLOW_DIVISOR]));
+ if (tb[TCA_FLOW_BASECLASS])
+ fprintf(f, "baseclass %s ",
+ sprint_tc_classid(rta_getattr_u32(tb[TCA_FLOW_BASECLASS]), b1));
+
+ if (tb[TCA_FLOW_PERTURB])
+ fprintf(f, "perturb %usec ",
+ rta_getattr_u32(tb[TCA_FLOW_PERTURB]));
+
+ if (tb[TCA_FLOW_EMATCHES])
+ print_ematch(f, tb[TCA_FLOW_EMATCHES]);
+ if (tb[TCA_FLOW_POLICE])
+ tc_print_police(f, tb[TCA_FLOW_POLICE]);
+ if (tb[TCA_FLOW_ACT]) {
+ fprintf(f, "\n");
+ tc_print_action(f, tb[TCA_FLOW_ACT]);
+ }
+ return 0;
+}
+
+struct filter_util flow_filter_util = {
+ .id = "flow",
+ .parse_fopt = flow_parse_opt,
+ .print_fopt = flow_print_opt,
+};
diff --git a/iproute2/tc/f_flower.c b/iproute2/tc/f_flower.c
new file mode 100644
index 0000000..db9cc29
--- /dev/null
+++ b/iproute2/tc/f_flower.c
@@ -0,0 +1,519 @@
+/*
+ * f_flower.c Flower Classifier
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Jiri Pirko <jiri@resnulli.us>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <string.h>
+#include <net/if.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+
+#include "utils.h"
+#include "tc_util.h"
+#include "rt_names.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... flower [ MATCH-LIST ]\n");
+ fprintf(stderr, " [ action ACTION-SPEC ] [ classid CLASSID ]\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "Where: MATCH-LIST := [ MATCH-LIST ] MATCH\n");
+ fprintf(stderr, " MATCH := { indev DEV-NAME | \n");
+ fprintf(stderr, " dst_mac MAC-ADDR | \n");
+ fprintf(stderr, " src_mac MAC-ADDR | \n");
+ fprintf(stderr, " [ipv4 | ipv6 ] | \n");
+ fprintf(stderr, " ip_proto [tcp | udp | IP-PROTO ] | \n");
+ fprintf(stderr, " dst_ip [ IPV4-ADDR | IPV6-ADDR ] | \n");
+ fprintf(stderr, " src_ip [ IPV4-ADDR | IPV6-ADDR ] | \n");
+ fprintf(stderr, " dst_port PORT-NUMBER | \n");
+ fprintf(stderr, " src_port PORT-NUMBER }\n");
+ fprintf(stderr, " FILTERID := X:Y:Z\n");
+ fprintf(stderr, " ACTION-SPEC := ... look at individual actions\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "NOTE: CLASSID, ETH-TYPE, IP-PROTO are parsed as hexadecimal input.\n");
+ fprintf(stderr, "NOTE: There can be only used one mask per one prio. If user needs\n");
+ fprintf(stderr, " to specify different mask, he has to use different prio.\n");
+}
+
+static int flower_parse_eth_addr(char *str, int addr_type, int mask_type,
+ struct nlmsghdr *n)
+{
+ int ret;
+ char addr[ETH_ALEN];
+
+ ret = ll_addr_a2n(addr, sizeof(addr), str);
+ if (ret < 0)
+ return -1;
+ addattr_l(n, MAX_MSG, addr_type, addr, sizeof(addr));
+ memset(addr, 0xff, ETH_ALEN);
+ addattr_l(n, MAX_MSG, mask_type, addr, sizeof(addr));
+ return 0;
+}
+
+static int flower_parse_ip_proto(char *str, __be16 eth_type, int type,
+ __u8 *p_ip_proto, struct nlmsghdr *n)
+{
+ int ret;
+ __u8 ip_proto;
+
+ if (eth_type != htons(ETH_P_IP) && eth_type != htons(ETH_P_IPV6)) {
+ fprintf(stderr, "Illegal \"eth_type\" for ip proto\n");
+ return -1;
+ }
+ if (matches(str, "tcp") == 0) {
+ ip_proto = IPPROTO_TCP;
+ } else if (matches(str, "udp") == 0) {
+ ip_proto = IPPROTO_UDP;
+ } else {
+ ret = get_u8(&ip_proto, str, 16);
+ if (ret)
+ return -1;
+ }
+ addattr8(n, MAX_MSG, type, ip_proto);
+ *p_ip_proto = ip_proto;
+ return 0;
+}
+
+static int flower_parse_ip_addr(char *str, __be16 eth_type,
+ int addr4_type, int mask4_type,
+ int addr6_type, int mask6_type,
+ struct nlmsghdr *n)
+{
+ int ret;
+ inet_prefix addr;
+ int family;
+ int bits;
+ int i;
+
+ if (eth_type == htons(ETH_P_IP)) {
+ family = AF_INET;
+ } else if (eth_type == htons(ETH_P_IPV6)) {
+ family = AF_INET6;
+ } else {
+ fprintf(stderr, "Illegal \"eth_type\" for ip address\n");
+ return -1;
+ }
+
+ ret = get_prefix(&addr, str, family);
+ if (ret)
+ return -1;
+
+ if (addr.family != family)
+ return -1;
+
+ addattr_l(n, MAX_MSG, addr.family == AF_INET ? addr4_type : addr6_type,
+ addr.data, addr.bytelen);
+
+ memset(addr.data, 0xff, addr.bytelen);
+ bits = addr.bitlen;
+ for (i = 0; i < addr.bytelen / 4; i++) {
+ if (!bits) {
+ addr.data[i] = 0;
+ } else if (bits / 32 >= 1) {
+ bits -= 32;
+ } else {
+ addr.data[i] <<= 32 - bits;
+ addr.data[i] = htonl(addr.data[i]);
+ bits = 0;
+ }
+ }
+
+ addattr_l(n, MAX_MSG, addr.family == AF_INET ? mask4_type : mask6_type,
+ addr.data, addr.bytelen);
+
+ return 0;
+}
+
+static int flower_parse_port(char *str, __u8 ip_port,
+ int tcp_type, int udp_type, struct nlmsghdr *n)
+{
+ int ret;
+ int type;
+ __be16 port;
+
+ if (ip_port == IPPROTO_TCP) {
+ type = tcp_type;
+ } else if (ip_port == IPPROTO_UDP) {
+ type = udp_type;
+ } else {
+ fprintf(stderr, "Illegal \"ip_proto\" for port\n");
+ return -1;
+ }
+
+ ret = get_u16(&port, str, 10);
+ if (ret)
+ return -1;
+
+ addattr16(n, MAX_MSG, type, htons(port));
+
+ return 0;
+}
+
+static int flower_parse_opt(struct filter_util *qu, char *handle,
+ int argc, char **argv, struct nlmsghdr *n)
+{
+ int ret;
+ struct tcmsg *t = NLMSG_DATA(n);
+ struct rtattr *tail;
+ __be16 eth_type = TC_H_MIN(t->tcm_info);
+ __u8 ip_proto = 0xff;
+
+ if (handle) {
+ ret = get_u32(&t->tcm_handle, handle, 0);
+ if (ret) {
+ fprintf(stderr, "Illegal \"handle\"\n");
+ return -1;
+ }
+ }
+
+ tail = (struct rtattr *) (((void *) n) + NLMSG_ALIGN(n->nlmsg_len));
+ addattr_l(n, MAX_MSG, TCA_OPTIONS, NULL, 0);
+
+ if (argc == 0) {
+ /*at minimal we will match all ethertype packets */
+ goto parse_done;
+ }
+
+ while (argc > 0) {
+ if (matches(*argv, "classid") == 0 ||
+ matches(*argv, "flowid") == 0) {
+ unsigned handle;
+
+ NEXT_ARG();
+ ret = get_tc_classid(&handle, *argv);
+ if (ret) {
+ fprintf(stderr, "Illegal \"classid\"\n");
+ return -1;
+ }
+ addattr_l(n, MAX_MSG, TCA_FLOWER_CLASSID, &handle, 4);
+ } else if (matches(*argv, "indev") == 0) {
+ char ifname[IFNAMSIZ];
+
+ NEXT_ARG();
+ memset(ifname, 0, sizeof(ifname));
+ strncpy(ifname, *argv, sizeof(ifname) - 1);
+ addattrstrz(n, MAX_MSG, TCA_FLOWER_INDEV, ifname);
+ } else if (matches(*argv, "dst_mac") == 0) {
+ NEXT_ARG();
+ ret = flower_parse_eth_addr(*argv,
+ TCA_FLOWER_KEY_ETH_DST,
+ TCA_FLOWER_KEY_ETH_DST_MASK,
+ n);
+ if (ret < 0) {
+ fprintf(stderr, "Illegal \"dst_mac\"\n");
+ return -1;
+ }
+ } else if (matches(*argv, "src_mac") == 0) {
+ NEXT_ARG();
+ ret = flower_parse_eth_addr(*argv,
+ TCA_FLOWER_KEY_ETH_SRC,
+ TCA_FLOWER_KEY_ETH_SRC_MASK,
+ n);
+ if (ret < 0) {
+ fprintf(stderr, "Illegal \"src_mac\"\n");
+ return -1;
+ }
+ } else if (matches(*argv, "ip_proto") == 0) {
+ NEXT_ARG();
+ ret = flower_parse_ip_proto(*argv, eth_type,
+ TCA_FLOWER_KEY_IP_PROTO,
+ &ip_proto, n);
+ if (ret < 0) {
+ fprintf(stderr, "Illegal \"ip_proto\"\n");
+ return -1;
+ }
+ } else if (matches(*argv, "dst_ip") == 0) {
+ NEXT_ARG();
+ ret = flower_parse_ip_addr(*argv, eth_type,
+ TCA_FLOWER_KEY_IPV4_DST,
+ TCA_FLOWER_KEY_IPV4_DST_MASK,
+ TCA_FLOWER_KEY_IPV6_DST,
+ TCA_FLOWER_KEY_IPV6_DST_MASK,
+ n);
+ if (ret < 0) {
+ fprintf(stderr, "Illegal \"dst_ip\"\n");
+ return -1;
+ }
+ } else if (matches(*argv, "src_ip") == 0) {
+ NEXT_ARG();
+ ret = flower_parse_ip_addr(*argv, eth_type,
+ TCA_FLOWER_KEY_IPV4_SRC,
+ TCA_FLOWER_KEY_IPV4_SRC_MASK,
+ TCA_FLOWER_KEY_IPV6_SRC,
+ TCA_FLOWER_KEY_IPV6_SRC_MASK,
+ n);
+ if (ret < 0) {
+ fprintf(stderr, "Illegal \"src_ip\"\n");
+ return -1;
+ }
+ } else if (matches(*argv, "dst_port") == 0) {
+ NEXT_ARG();
+ ret = flower_parse_port(*argv, ip_proto,
+ TCA_FLOWER_KEY_TCP_DST,
+ TCA_FLOWER_KEY_UDP_DST, n);
+ if (ret < 0) {
+ fprintf(stderr, "Illegal \"dst_port\"\n");
+ return -1;
+ }
+ } else if (matches(*argv, "src_port") == 0) {
+ NEXT_ARG();
+ ret = flower_parse_port(*argv, ip_proto,
+ TCA_FLOWER_KEY_TCP_SRC,
+ TCA_FLOWER_KEY_UDP_SRC, n);
+ if (ret < 0) {
+ fprintf(stderr, "Illegal \"src_port\"\n");
+ return -1;
+ }
+ } else if (matches(*argv, "action") == 0) {
+ NEXT_ARG();
+ ret = parse_action(&argc, &argv, TCA_FLOWER_ACT, n);
+ if (ret) {
+ fprintf(stderr, "Illegal \"action\"\n");
+ return -1;
+ }
+ continue;
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+parse_done:
+ ret = addattr16(n, MAX_MSG, TCA_FLOWER_KEY_ETH_TYPE, eth_type);
+ if (ret) {
+ fprintf(stderr, "Illegal \"eth_type\"(0x%x)\n",
+ ntohs(eth_type));
+ return -1;
+ }
+
+ tail->rta_len = (((void*)n)+n->nlmsg_len) - (void*)tail;
+
+ return 0;
+}
+
+static int __mask_bits(char *addr, size_t len)
+{
+ int bits = 0;
+ bool hole = false;
+ int i;
+ int j;
+
+ for (i = 0; i < len; i++, addr++) {
+ for (j = 7; j >= 0; j--) {
+ if (((*addr) >> j) & 0x1) {
+ if (hole)
+ return -1;
+ bits++;
+ } else if (bits) {
+ hole = true;
+ } else{
+ return -1;
+ }
+ }
+ }
+ return bits;
+}
+
+static void flower_print_eth_addr(FILE *f, char *name,
+ struct rtattr *addr_attr,
+ struct rtattr *mask_attr)
+{
+ SPRINT_BUF(b1);
+ int bits;
+
+ if (!addr_attr || RTA_PAYLOAD(addr_attr) != ETH_ALEN)
+ return;
+ fprintf(f, "\n %s %s", name, ll_addr_n2a(RTA_DATA(addr_attr), ETH_ALEN,
+ 0, b1, sizeof(b1)));
+ if (!mask_attr || RTA_PAYLOAD(mask_attr) != ETH_ALEN)
+ return;
+ bits = __mask_bits(RTA_DATA(mask_attr), ETH_ALEN);
+ if (bits < 0)
+ fprintf(f, "/%s", ll_addr_n2a(RTA_DATA(mask_attr), ETH_ALEN,
+ 0, b1, sizeof(b1)));
+ else if (bits < ETH_ALEN * 8)
+ fprintf(f, "/%d", bits);
+}
+
+static void flower_print_eth_type(FILE *f, __be16 *p_eth_type,
+ struct rtattr *eth_type_attr)
+{
+ __be16 eth_type;
+
+ if (!eth_type_attr)
+ return;
+
+ eth_type = rta_getattr_u16(eth_type_attr);
+ fprintf(f, "\n eth_type ");
+ if (eth_type == htons(ETH_P_IP))
+ fprintf(f, "ipv4");
+ else if (eth_type == htons(ETH_P_IPV6))
+ fprintf(f, "ipv6");
+ else
+ fprintf(f, "%04x", ntohs(eth_type));
+ *p_eth_type = eth_type;
+}
+
+static void flower_print_ip_proto(FILE *f, __u8 *p_ip_proto,
+ struct rtattr *ip_proto_attr)
+{
+ __u8 ip_proto;
+
+ if (!ip_proto_attr)
+ return;
+
+ ip_proto = rta_getattr_u8(ip_proto_attr);
+ fprintf(f, "\n ip_proto ");
+ if (ip_proto == IPPROTO_TCP)
+ fprintf(f, "tcp");
+ else if (ip_proto == IPPROTO_UDP)
+ fprintf(f, "udp");
+ else
+ fprintf(f, "%02x", ip_proto);
+ *p_ip_proto = ip_proto;
+}
+
+static void flower_print_ip_addr(FILE *f, char *name, __be16 eth_type,
+ struct rtattr *addr4_attr,
+ struct rtattr *mask4_attr,
+ struct rtattr *addr6_attr,
+ struct rtattr *mask6_attr)
+{
+ SPRINT_BUF(b1);
+ struct rtattr *addr_attr;
+ struct rtattr *mask_attr;
+ int family;
+ size_t len;
+ int bits;
+
+ if (eth_type == htons(ETH_P_IP)) {
+ family = AF_INET;
+ addr_attr = addr4_attr;
+ mask_attr = mask4_attr;
+ len = 4;
+ } else if (eth_type == htons(ETH_P_IPV6)) {
+ family = AF_INET6;
+ addr_attr = addr6_attr;
+ mask_attr = mask6_attr;
+ len = 16;
+ } else {
+ return;
+ }
+ if (!addr_attr || RTA_PAYLOAD(addr_attr) != len)
+ return;
+ fprintf(f, "\n %s %s", name, rt_addr_n2a(family,
+ RTA_PAYLOAD(addr_attr),
+ RTA_DATA(addr_attr),
+ b1, sizeof(b1)));
+ if (!mask_attr || RTA_PAYLOAD(mask_attr) != len)
+ return;
+ bits = __mask_bits(RTA_DATA(mask_attr), len);
+ if (bits < 0)
+ fprintf(f, "/%s", rt_addr_n2a(family,
+ RTA_PAYLOAD(mask_attr),
+ RTA_DATA(mask_attr),
+ b1, sizeof(b1)));
+ else if (bits < len * 8)
+ fprintf(f, "/%d", bits);
+}
+
+static void flower_print_port(FILE *f, char *name, __u8 ip_proto,
+ struct rtattr *tcp_attr,
+ struct rtattr *udp_attr)
+{
+ struct rtattr *attr;
+
+ if (ip_proto == IPPROTO_TCP)
+ attr = tcp_attr;
+ else if (ip_proto == IPPROTO_UDP)
+ attr = udp_attr;
+ else
+ return;
+ if (!attr)
+ return;
+ fprintf(f, "\n %s %d", name, ntohs(rta_getattr_u16(attr)));
+}
+
+static int flower_print_opt(struct filter_util *qu, FILE *f,
+ struct rtattr *opt, __u32 handle)
+{
+ struct rtattr *tb[TCA_FLOWER_MAX + 1];
+ __be16 eth_type = 0;
+ __u8 ip_proto = 0xff;
+
+ if (!opt)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_FLOWER_MAX, opt);
+
+ if (handle)
+ fprintf(f, "handle 0x%x ", handle);
+
+ if (tb[TCA_FLOWER_CLASSID]) {
+ SPRINT_BUF(b1);
+ fprintf(f, "classid %s ",
+ sprint_tc_classid(rta_getattr_u32(tb[TCA_FLOWER_CLASSID]),
+ b1));
+ }
+
+ if (tb[TCA_FLOWER_INDEV]) {
+ struct rtattr *attr = tb[TCA_FLOWER_INDEV];
+
+ fprintf(f, "\n indev %s", rta_getattr_str(attr));
+ }
+
+ flower_print_eth_addr(f, "dst_mac", tb[TCA_FLOWER_KEY_ETH_DST],
+ tb[TCA_FLOWER_KEY_ETH_DST_MASK]);
+ flower_print_eth_addr(f, "src_mac", tb[TCA_FLOWER_KEY_ETH_SRC],
+ tb[TCA_FLOWER_KEY_ETH_SRC_MASK]);
+
+ flower_print_eth_type(f, ð_type, tb[TCA_FLOWER_KEY_ETH_TYPE]);
+ flower_print_ip_proto(f, &ip_proto, tb[TCA_FLOWER_KEY_IP_PROTO]);
+
+ flower_print_ip_addr(f, "dst_ip", eth_type,
+ tb[TCA_FLOWER_KEY_IPV4_DST],
+ tb[TCA_FLOWER_KEY_IPV4_DST_MASK],
+ tb[TCA_FLOWER_KEY_IPV6_DST],
+ tb[TCA_FLOWER_KEY_IPV6_DST_MASK]);
+
+ flower_print_ip_addr(f, "src_ip", eth_type,
+ tb[TCA_FLOWER_KEY_IPV4_SRC],
+ tb[TCA_FLOWER_KEY_IPV4_SRC_MASK],
+ tb[TCA_FLOWER_KEY_IPV6_SRC],
+ tb[TCA_FLOWER_KEY_IPV6_SRC_MASK]);
+
+ flower_print_port(f, "dst_port", ip_proto,
+ tb[TCA_FLOWER_KEY_TCP_DST],
+ tb[TCA_FLOWER_KEY_UDP_DST]);
+
+ flower_print_port(f, "src_port", ip_proto,
+ tb[TCA_FLOWER_KEY_TCP_SRC],
+ tb[TCA_FLOWER_KEY_UDP_SRC]);
+
+ if (tb[TCA_FLOWER_ACT]) {
+ tc_print_action(f, tb[TCA_FLOWER_ACT]);
+ }
+
+ return 0;
+}
+
+struct filter_util flower_filter_util = {
+ .id = "flower",
+ .parse_fopt = flower_parse_opt,
+ .print_fopt = flower_print_opt,
+};
diff --git a/iproute2/tc/f_fw.c b/iproute2/tc/f_fw.c
new file mode 100644
index 0000000..165f489
--- /dev/null
+++ b/iproute2/tc/f_fw.c
@@ -0,0 +1,162 @@
+/*
+ * f_fw.c FW filter.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <linux/if.h> /* IFNAMSIZ */
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... fw [ classid CLASSID ] [ action ACTION_SPEC ]\n");
+ fprintf(stderr, " ACTION_SPEC := ... look at individual actions\n");
+ fprintf(stderr, " CLASSID := X:Y\n");
+ fprintf(stderr, "\nNOTE: CLASSID is parsed as hexadecimal input.\n");
+}
+
+static int fw_parse_opt(struct filter_util *qu, char *handle, int argc, char **argv, struct nlmsghdr *n)
+{
+ struct tc_police tp;
+ struct tcmsg *t = NLMSG_DATA(n);
+ struct rtattr *tail;
+ __u32 mask = 0;
+ int mask_set = 0;
+
+ memset(&tp, 0, sizeof(tp));
+
+ if (handle) {
+ char *slash;
+ if ((slash = strchr(handle, '/')) != NULL)
+ *slash = '\0';
+ if (get_u32(&t->tcm_handle, handle, 0)) {
+ fprintf(stderr, "Illegal \"handle\"\n");
+ return -1;
+ }
+ if (slash) {
+ if (get_u32(&mask, slash+1, 0)) {
+ fprintf(stderr, "Illegal \"handle\" mask\n");
+ return -1;
+ }
+ mask_set = 1;
+ }
+ }
+
+ if (argc == 0)
+ return 0;
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 4096, TCA_OPTIONS, NULL, 0);
+
+ if (mask_set)
+ addattr32(n, MAX_MSG, TCA_FW_MASK, mask);
+
+ while (argc > 0) {
+ if (matches(*argv, "classid") == 0 ||
+ matches(*argv, "flowid") == 0) {
+ unsigned handle;
+ NEXT_ARG();
+ if (get_tc_classid(&handle, *argv)) {
+ fprintf(stderr, "Illegal \"classid\"\n");
+ return -1;
+ }
+ addattr_l(n, 4096, TCA_FW_CLASSID, &handle, 4);
+ } else if (matches(*argv, "police") == 0) {
+ NEXT_ARG();
+ if (parse_police(&argc, &argv, TCA_FW_POLICE, n)) {
+ fprintf(stderr, "Illegal \"police\"\n");
+ return -1;
+ }
+ continue;
+ } else if (matches(*argv, "action") == 0) {
+ NEXT_ARG();
+ if (parse_action(&argc, &argv, TCA_FW_ACT, n)) {
+ fprintf(stderr, "Illegal fw \"action\"\n");
+ return -1;
+ }
+ continue;
+ } else if (strcmp(*argv, "indev") == 0) {
+ char d[IFNAMSIZ+1];
+ memset(d, 0, sizeof (d));
+ argc--;
+ argv++;
+ if (argc < 1) {
+ fprintf(stderr, "Illegal indev\n");
+ return -1;
+ }
+ strncpy(d, *argv, sizeof (d) - 1);
+ addattr_l(n, MAX_MSG, TCA_FW_INDEV, d, strlen(d) + 1);
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+static int fw_print_opt(struct filter_util *qu, FILE *f, struct rtattr *opt, __u32 handle)
+{
+ struct rtattr *tb[TCA_FW_MAX+1];
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_FW_MAX, opt);
+
+ if (handle || tb[TCA_FW_MASK]) {
+ __u32 mark = 0, mask = 0;
+ if(handle)
+ mark = handle;
+ if(tb[TCA_FW_MASK] &&
+ (mask = rta_getattr_u32(tb[TCA_FW_MASK])) != 0xFFFFFFFF)
+ fprintf(f, "handle 0x%x/0x%x ", mark, mask);
+ else
+ fprintf(f, "handle 0x%x ", handle);
+ }
+
+ if (tb[TCA_FW_CLASSID]) {
+ SPRINT_BUF(b1);
+ fprintf(f, "classid %s ", sprint_tc_classid(rta_getattr_u32(tb[TCA_FW_CLASSID]), b1));
+ }
+
+ if (tb[TCA_FW_POLICE])
+ tc_print_police(f, tb[TCA_FW_POLICE]);
+ if (tb[TCA_FW_INDEV]) {
+ struct rtattr *idev = tb[TCA_FW_INDEV];
+ fprintf(f, "input dev %s ",rta_getattr_str(idev));
+ }
+
+ if (tb[TCA_FW_ACT]) {
+ fprintf(f, "\n");
+ tc_print_action(f, tb[TCA_FW_ACT]);
+ }
+ return 0;
+}
+
+struct filter_util fw_filter_util = {
+ .id = "fw",
+ .parse_fopt = fw_parse_opt,
+ .print_fopt = fw_print_opt,
+};
diff --git a/iproute2/tc/f_route.c b/iproute2/tc/f_route.c
new file mode 100644
index 0000000..4e9032c
--- /dev/null
+++ b/iproute2/tc/f_route.c
@@ -0,0 +1,177 @@
+/*
+ * f_route.c ROUTE filter.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "rt_names.h"
+#include "tc_common.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... route [ from REALM | fromif TAG ] [ to REALM ]\n");
+ fprintf(stderr, " [ classid CLASSID ] [ action ACTION_SPEC ]\n");
+ fprintf(stderr, " ACTION_SPEC := ... look at individual actions\n");
+ fprintf(stderr, " CLASSID := X:Y\n");
+ fprintf(stderr, "\nNOTE: CLASSID is parsed as hexadecimal input.\n");
+}
+
+static int route_parse_opt(struct filter_util *qu, char *handle, int argc, char **argv, struct nlmsghdr *n)
+{
+ struct tc_police tp;
+ struct tcmsg *t = NLMSG_DATA(n);
+ struct rtattr *tail;
+ __u32 fh = 0xFFFF8000;
+ __u32 order = 0;
+
+ memset(&tp, 0, sizeof(tp));
+
+ if (handle) {
+ if (get_u32(&t->tcm_handle, handle, 0)) {
+ fprintf(stderr, "Illegal \"handle\"\n");
+ return -1;
+ }
+ }
+
+ if (argc == 0)
+ return 0;
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 4096, TCA_OPTIONS, NULL, 0);
+
+ while (argc > 0) {
+ if (matches(*argv, "to") == 0) {
+ __u32 id;
+ NEXT_ARG();
+ if (rtnl_rtrealm_a2n(&id, *argv)) {
+ fprintf(stderr, "Illegal \"to\"\n");
+ return -1;
+ }
+ addattr_l(n, 4096, TCA_ROUTE4_TO, &id, 4);
+ fh &= ~0x80FF;
+ fh |= id&0xFF;
+ } else if (matches(*argv, "from") == 0) {
+ __u32 id;
+ NEXT_ARG();
+ if (rtnl_rtrealm_a2n(&id, *argv)) {
+ fprintf(stderr, "Illegal \"from\"\n");
+ return -1;
+ }
+ addattr_l(n, 4096, TCA_ROUTE4_FROM, &id, 4);
+ fh &= 0xFFFF;
+ fh |= id<<16;
+ } else if (matches(*argv, "fromif") == 0) {
+ __u32 id;
+ NEXT_ARG();
+ ll_init_map(&rth);
+ if ((id=ll_name_to_index(*argv)) <= 0) {
+ fprintf(stderr, "Illegal \"fromif\"\n");
+ return -1;
+ }
+ addattr_l(n, 4096, TCA_ROUTE4_IIF, &id, 4);
+ fh &= 0xFFFF;
+ fh |= (0x8000|id)<<16;
+ } else if (matches(*argv, "classid") == 0 ||
+ strcmp(*argv, "flowid") == 0) {
+ unsigned handle;
+ NEXT_ARG();
+ if (get_tc_classid(&handle, *argv)) {
+ fprintf(stderr, "Illegal \"classid\"\n");
+ return -1;
+ }
+ addattr_l(n, 4096, TCA_ROUTE4_CLASSID, &handle, 4);
+ } else if (matches(*argv, "police") == 0) {
+ NEXT_ARG();
+ if (parse_police(&argc, &argv, TCA_ROUTE4_POLICE, n)) {
+ fprintf(stderr, "Illegal \"police\"\n");
+ return -1;
+ }
+ continue;
+ } else if (matches(*argv, "action") == 0) {
+ NEXT_ARG();
+ if (parse_action(&argc, &argv, TCA_ROUTE4_ACT, n)) {
+ fprintf(stderr, "Illegal \"action\"\n");
+ return -1;
+ }
+ continue;
+ } else if (matches(*argv, "order") == 0) {
+ NEXT_ARG();
+ if (get_u32(&order, *argv, 0)) {
+ fprintf(stderr, "Illegal \"order\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ if (order) {
+ fh &= ~0x7F00;
+ fh |= (order<<8)&0x7F00;
+ }
+ if (!t->tcm_handle)
+ t->tcm_handle = fh;
+ return 0;
+}
+
+static int route_print_opt(struct filter_util *qu, FILE *f, struct rtattr *opt, __u32 handle)
+{
+ struct rtattr *tb[TCA_ROUTE4_MAX+1];
+ SPRINT_BUF(b1);
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_ROUTE4_MAX, opt);
+
+ if (handle)
+ fprintf(f, "fh 0x%08x ", handle);
+ if (handle&0x7F00)
+ fprintf(f, "order %d ", (handle>>8)&0x7F);
+
+ if (tb[TCA_ROUTE4_CLASSID]) {
+ SPRINT_BUF(b1);
+ fprintf(f, "flowid %s ", sprint_tc_classid(rta_getattr_u32(tb[TCA_ROUTE4_CLASSID]), b1));
+ }
+ if (tb[TCA_ROUTE4_TO])
+ fprintf(f, "to %s ", rtnl_rtrealm_n2a(rta_getattr_u32(tb[TCA_ROUTE4_TO]), b1, sizeof(b1)));
+ if (tb[TCA_ROUTE4_FROM])
+ fprintf(f, "from %s ", rtnl_rtrealm_n2a(rta_getattr_u32(tb[TCA_ROUTE4_FROM]), b1, sizeof(b1)));
+ if (tb[TCA_ROUTE4_IIF])
+ fprintf(f, "fromif %s", ll_index_to_name(*(int*)RTA_DATA(tb[TCA_ROUTE4_IIF])));
+ if (tb[TCA_ROUTE4_POLICE])
+ tc_print_police(f, tb[TCA_ROUTE4_POLICE]);
+ if (tb[TCA_ROUTE4_ACT])
+ tc_print_action(f, tb[TCA_ROUTE4_ACT]);
+ return 0;
+}
+
+struct filter_util route_filter_util = {
+ .id = "route",
+ .parse_fopt = route_parse_opt,
+ .print_fopt = route_print_opt,
+};
diff --git a/iproute2/tc/f_rsvp.c b/iproute2/tc/f_rsvp.c
new file mode 100644
index 0000000..1fe9b15
--- /dev/null
+++ b/iproute2/tc/f_rsvp.c
@@ -0,0 +1,414 @@
+/*
+ * q_rsvp.c RSVP filter.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... rsvp ipproto PROTOCOL session DST[/PORT | GPI ]\n");
+ fprintf(stderr, " [ sender SRC[/PORT | GPI ] ]\n");
+ fprintf(stderr, " [ classid CLASSID ] [ action ACTION_SPEC ]\n");
+ fprintf(stderr, " [ tunnelid ID ] [ tunnel ID skip NUMBER ]\n");
+ fprintf(stderr, "Where: GPI := { flowlabel NUMBER | spi/ah SPI | spi/esp SPI |\n");
+ fprintf(stderr, " u{8|16|32} NUMBER mask MASK at OFFSET}\n");
+ fprintf(stderr, " ACTION_SPEC := ... look at individual actions\n");
+ fprintf(stderr, " FILTERID := X:Y\n");
+ fprintf(stderr, "\nNOTE: CLASSID is parsed as hexadecimal input.\n");
+}
+
+static int get_addr_and_pi(int *argc_p, char ***argv_p, inet_prefix * addr,
+ struct tc_rsvp_pinfo *pinfo, int dir, int family)
+{
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ char *p = strchr(*argv, '/');
+ struct tc_rsvp_gpi *pi = dir ? &pinfo->dpi : &pinfo->spi;
+
+ if (p) {
+ __u16 tmp;
+
+ if (get_u16(&tmp, p+1, 0))
+ return -1;
+
+ if (dir == 0) {
+ /* Source port: u16 at offset 0 */
+ pi->key = htonl(((__u32)tmp)<<16);
+ pi->mask = htonl(0xFFFF0000);
+ } else {
+ /* Destination port: u16 at offset 2 */
+ pi->key = htonl(((__u32)tmp));
+ pi->mask = htonl(0x0000FFFF);
+ }
+ pi->offset = 0;
+ *p = 0;
+ }
+ if (get_addr_1(addr, *argv, family))
+ return -1;
+ if (p)
+ *p = '/';
+
+ argc--; argv++;
+
+ if (pi->mask || argc <= 0)
+ goto done;
+
+ if (strcmp(*argv, "spi/ah") == 0 ||
+ strcmp(*argv, "gpi/ah") == 0) {
+ __u32 gpi;
+ NEXT_ARG();
+ if (get_u32(&gpi, *argv, 0))
+ return -1;
+ pi->mask = htonl(0xFFFFFFFF);
+ pi->key = htonl(gpi);
+ pi->offset = 4;
+ if (pinfo->protocol == 0)
+ pinfo->protocol = IPPROTO_AH;
+ argc--; argv++;
+ } else if (strcmp(*argv, "spi/esp") == 0 ||
+ strcmp(*argv, "gpi/esp") == 0) {
+ __u32 gpi;
+ NEXT_ARG();
+ if (get_u32(&gpi, *argv, 0))
+ return -1;
+ pi->mask = htonl(0xFFFFFFFF);
+ pi->key = htonl(gpi);
+ pi->offset = 0;
+ if (pinfo->protocol == 0)
+ pinfo->protocol = IPPROTO_ESP;
+ argc--; argv++;
+ } else if (strcmp(*argv, "flowlabel") == 0) {
+ __u32 flabel;
+ NEXT_ARG();
+ if (get_u32(&flabel, *argv, 0))
+ return -1;
+ if (family != AF_INET6)
+ return -1;
+ pi->mask = htonl(0x000FFFFF);
+ pi->key = htonl(flabel) & pi->mask;
+ pi->offset = -40;
+ argc--; argv++;
+ } else if (strcmp(*argv, "u32") == 0 ||
+ strcmp(*argv, "u16") == 0 ||
+ strcmp(*argv, "u8") == 0) {
+ int sz = 1;
+ __u32 tmp;
+ __u32 mask = 0xff;
+ if (strcmp(*argv, "u32") == 0) {
+ sz = 4;
+ mask = 0xffff;
+ } else if (strcmp(*argv, "u16") == 0) {
+ mask = 0xffffffff;
+ sz = 2;
+ }
+ NEXT_ARG();
+ if (get_u32(&tmp, *argv, 0))
+ return -1;
+ argc--; argv++;
+ if (strcmp(*argv, "mask") == 0) {
+ NEXT_ARG();
+ if (get_u32(&mask, *argv, 16))
+ return -1;
+ argc--; argv++;
+ }
+ if (strcmp(*argv, "at") == 0) {
+ NEXT_ARG();
+ if (get_integer(&pi->offset, *argv, 0))
+ return -1;
+ argc--; argv++;
+ }
+ if (sz == 1) {
+ if ((pi->offset & 3) == 0) {
+ mask <<= 24;
+ tmp <<= 24;
+ } else if ((pi->offset & 3) == 1) {
+ mask <<= 16;
+ tmp <<= 16;
+ } else if ((pi->offset & 3) == 3) {
+ mask <<= 8;
+ tmp <<= 8;
+ }
+ } else if (sz == 2) {
+ if ((pi->offset & 3) == 0) {
+ mask <<= 16;
+ tmp <<= 16;
+ }
+ }
+ pi->offset &= ~3;
+ pi->mask = htonl(mask);
+ pi->key = htonl(tmp) & pi->mask;
+ }
+
+done:
+ *argc_p = argc;
+ *argv_p = argv;
+ return 0;
+}
+
+
+static int rsvp_parse_opt(struct filter_util *qu, char *handle, int argc, char **argv, struct nlmsghdr *n)
+{
+ int family = strcmp(qu->id, "rsvp") == 0 ? AF_INET : AF_INET6;
+ struct tc_rsvp_pinfo pinfo;
+ struct tc_police tp;
+ struct tcmsg *t = NLMSG_DATA(n);
+ int pinfo_ok = 0;
+ struct rtattr *tail;
+
+ memset(&pinfo, 0, sizeof(pinfo));
+ memset(&tp, 0, sizeof(tp));
+
+ if (handle) {
+ if (get_u32(&t->tcm_handle, handle, 0)) {
+ fprintf(stderr, "Illegal \"handle\"\n");
+ return -1;
+ }
+ }
+
+ if (argc == 0)
+ return 0;
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 4096, TCA_OPTIONS, NULL, 0);
+
+ while (argc > 0) {
+ if (matches(*argv, "session") == 0) {
+ inet_prefix addr;
+ NEXT_ARG();
+ if (get_addr_and_pi(&argc, &argv, &addr, &pinfo, 1, family)) {
+ fprintf(stderr, "Illegal \"session\"\n");
+ return -1;
+ }
+ addattr_l(n, 4096, TCA_RSVP_DST, &addr.data, addr.bytelen);
+ if (pinfo.dpi.mask || pinfo.protocol)
+ pinfo_ok++;
+ continue;
+ } else if (matches(*argv, "sender") == 0 ||
+ matches(*argv, "flowspec") == 0) {
+ inet_prefix addr;
+ NEXT_ARG();
+ if (get_addr_and_pi(&argc, &argv, &addr, &pinfo, 0, family)) {
+ fprintf(stderr, "Illegal \"sender\"\n");
+ return -1;
+ }
+ addattr_l(n, 4096, TCA_RSVP_SRC, &addr.data, addr.bytelen);
+ if (pinfo.spi.mask || pinfo.protocol)
+ pinfo_ok++;
+ continue;
+ } else if (matches("ipproto", *argv) == 0) {
+ int num;
+ NEXT_ARG();
+ num = inet_proto_a2n(*argv);
+ if (num < 0) {
+ fprintf(stderr, "Illegal \"ipproto\"\n");
+ return -1;
+ }
+ pinfo.protocol = num;
+ pinfo_ok++;
+ } else if (matches(*argv, "classid") == 0 ||
+ strcmp(*argv, "flowid") == 0) {
+ unsigned handle;
+ NEXT_ARG();
+ if (get_tc_classid(&handle, *argv)) {
+ fprintf(stderr, "Illegal \"classid\"\n");
+ return -1;
+ }
+ addattr_l(n, 4096, TCA_RSVP_CLASSID, &handle, 4);
+ } else if (strcmp(*argv, "tunnelid") == 0) {
+ unsigned tid;
+ NEXT_ARG();
+ if (get_unsigned(&tid, *argv, 0)) {
+ fprintf(stderr, "Illegal \"tunnelid\"\n");
+ return -1;
+ }
+ pinfo.tunnelid = tid;
+ pinfo_ok++;
+ } else if (strcmp(*argv, "tunnel") == 0) {
+ unsigned tid;
+ NEXT_ARG();
+ if (get_unsigned(&tid, *argv, 0)) {
+ fprintf(stderr, "Illegal \"tunnel\"\n");
+ return -1;
+ }
+ addattr_l(n, 4096, TCA_RSVP_CLASSID, &tid, 4);
+ NEXT_ARG();
+ if (strcmp(*argv, "skip") == 0) {
+ NEXT_ARG();
+ }
+ if (get_unsigned(&tid, *argv, 0)) {
+ fprintf(stderr, "Illegal \"skip\"\n");
+ return -1;
+ }
+ pinfo.tunnelhdr = tid;
+ pinfo_ok++;
+ } else if (matches(*argv, "action") == 0) {
+ NEXT_ARG();
+ if (parse_action(&argc, &argv, TCA_RSVP_ACT, n)) {
+ fprintf(stderr, "Illegal \"action\"\n");
+ return -1;
+ }
+ continue;
+ } else if (matches(*argv, "police") == 0) {
+ NEXT_ARG();
+ if (parse_police(&argc, &argv, TCA_RSVP_POLICE, n)) {
+ fprintf(stderr, "Illegal \"police\"\n");
+ return -1;
+ }
+ continue;
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ if (pinfo_ok)
+ addattr_l(n, 4096, TCA_RSVP_PINFO, &pinfo, sizeof(pinfo));
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+static char * sprint_spi(struct tc_rsvp_gpi *pi, int dir, char *buf)
+{
+ if (pi->offset == 0) {
+ if (dir && pi->mask == htonl(0xFFFF)) {
+ snprintf(buf, SPRINT_BSIZE-1, "/%d", htonl(pi->key));
+ return buf;
+ }
+ if (!dir && pi->mask == htonl(0xFFFF0000)) {
+ snprintf(buf, SPRINT_BSIZE-1, "/%d", htonl(pi->key)>>16);
+ return buf;
+ }
+ if (pi->mask == htonl(0xFFFFFFFF)) {
+ snprintf(buf, SPRINT_BSIZE-1, " spi/esp 0x%08x", htonl(pi->key));
+ return buf;
+ }
+ } else if (pi->offset == 4 && pi->mask == htonl(0xFFFFFFFF)) {
+ snprintf(buf, SPRINT_BSIZE-1, " spi/ah 0x%08x", htonl(pi->key));
+ return buf;
+ } else if (pi->offset == -40 && pi->mask == htonl(0x000FFFFF)) {
+ snprintf(buf, SPRINT_BSIZE-1, " flowlabel 0x%05x", htonl(pi->key));
+ return buf;
+ }
+ snprintf(buf, SPRINT_BSIZE-1, " u32 0x%08x mask %08x at %d",
+ htonl(pi->key), htonl(pi->mask), pi->offset);
+ return buf;
+}
+
+static int rsvp_print_opt(struct filter_util *qu, FILE *f, struct rtattr *opt, __u32 handle)
+{
+ int family = strcmp(qu->id, "rsvp") == 0 ? AF_INET : AF_INET6;
+ struct rtattr *tb[TCA_RSVP_MAX+1];
+ struct tc_rsvp_pinfo *pinfo = NULL;
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_RSVP_MAX, opt);
+
+ if (handle)
+ fprintf(f, "fh 0x%08x ", handle);
+
+ if (tb[TCA_RSVP_PINFO]) {
+ if (RTA_PAYLOAD(tb[TCA_RSVP_PINFO]) < sizeof(*pinfo))
+ return -1;
+
+ pinfo = RTA_DATA(tb[TCA_RSVP_PINFO]);
+ }
+
+ if (tb[TCA_RSVP_CLASSID]) {
+ SPRINT_BUF(b1);
+ if (!pinfo || pinfo->tunnelhdr == 0)
+ fprintf(f, "flowid %s ", sprint_tc_classid(rta_getattr_u32(tb[TCA_RSVP_CLASSID]), b1));
+ else
+ fprintf(f, "tunnel %d skip %d ", rta_getattr_u32(tb[TCA_RSVP_CLASSID]), pinfo->tunnelhdr);
+ } else if (pinfo && pinfo->tunnelhdr)
+ fprintf(f, "tunnel [BAD] skip %d ", pinfo->tunnelhdr);
+
+ if (tb[TCA_RSVP_DST]) {
+ char buf[128];
+ fprintf(f, "session ");
+ if (inet_ntop(family, RTA_DATA(tb[TCA_RSVP_DST]), buf, sizeof(buf)) == 0)
+ fprintf(f, " [INVALID DADDR] ");
+ else
+ fprintf(f, "%s", buf);
+ if (pinfo && pinfo->dpi.mask) {
+ SPRINT_BUF(b2);
+ fprintf(f, "%s ", sprint_spi(&pinfo->dpi, 1, b2));
+ } else
+ fprintf(f, " ");
+ } else {
+ if (pinfo && pinfo->dpi.mask) {
+ SPRINT_BUF(b2);
+ fprintf(f, "session [NONE]%s ", sprint_spi(&pinfo->dpi, 1, b2));
+ } else
+ fprintf(f, "session NONE ");
+ }
+
+ if (pinfo && pinfo->protocol) {
+ SPRINT_BUF(b1);
+ fprintf(f, "ipproto %s ", inet_proto_n2a(pinfo->protocol, b1, sizeof(b1)));
+ }
+ if (pinfo && pinfo->tunnelid)
+ fprintf(f, "tunnelid %d ", pinfo->tunnelid);
+ if (tb[TCA_RSVP_SRC]) {
+ char buf[128];
+ fprintf(f, "sender ");
+ if (inet_ntop(family, RTA_DATA(tb[TCA_RSVP_SRC]), buf, sizeof(buf)) == 0) {
+ fprintf(f, "[BAD]");
+ } else {
+ fprintf(f, " %s", buf);
+ }
+ if (pinfo && pinfo->spi.mask) {
+ SPRINT_BUF(b2);
+ fprintf(f, "%s ", sprint_spi(&pinfo->spi, 0, b2));
+ } else
+ fprintf(f, " ");
+ } else if (pinfo && pinfo->spi.mask) {
+ SPRINT_BUF(b2);
+ fprintf(f, "sender [NONE]%s ", sprint_spi(&pinfo->spi, 0, b2));
+ }
+
+ if (tb[TCA_RSVP_ACT]) {
+ tc_print_action(f, tb[TCA_RSVP_ACT]);
+ }
+ if (tb[TCA_RSVP_POLICE])
+ tc_print_police(f, tb[TCA_RSVP_POLICE]);
+ return 0;
+}
+
+struct filter_util rsvp_filter_util = {
+ .id = "rsvp",
+ .parse_fopt = rsvp_parse_opt,
+ .print_fopt = rsvp_print_opt,
+};
+
+struct filter_util rsvp6_filter_util = {
+ .id = "rsvp6",
+ .parse_fopt = rsvp_parse_opt,
+ .print_fopt = rsvp_print_opt,
+};
diff --git a/iproute2/tc/f_tcindex.c b/iproute2/tc/f_tcindex.c
new file mode 100644
index 0000000..b1847c8
--- /dev/null
+++ b/iproute2/tc/f_tcindex.c
@@ -0,0 +1,193 @@
+/*
+ * f_tcindex.c Traffic control index filter
+ *
+ * Written 1998,1999 by Werner Almesberger
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <string.h>
+#include <netinet/in.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+ fprintf(stderr," Usage: ... tcindex [ hash SIZE ] [ mask MASK ]"
+ " [ shift SHIFT ]\n");
+ fprintf(stderr," [ pass_on | fall_through ]\n");
+ fprintf(stderr," [ classid CLASSID ] "
+ "[ action ACTION_SPEC ]\n");
+}
+
+static int tcindex_parse_opt(struct filter_util *qu, char *handle, int argc,
+ char **argv, struct nlmsghdr *n)
+{
+ struct tcmsg *t = NLMSG_DATA(n);
+ struct rtattr *tail;
+ char *end;
+
+ if (handle) {
+ t->tcm_handle = strtoul(handle,&end,0);
+ if (*end) {
+ fprintf(stderr, "Illegal filter ID\n");
+ return -1;
+ }
+ }
+ if (!argc) return 0;
+ tail = NLMSG_TAIL(n);
+ addattr_l(n,4096,TCA_OPTIONS,NULL,0);
+ while (argc) {
+ if (!strcmp(*argv,"hash")) {
+ int hash;
+
+ NEXT_ARG();
+ hash = strtoul(*argv,&end,0);
+ if (*end || !hash || hash > 0x10000) {
+ explain();
+ return -1;
+ }
+ addattr_l(n,4096,TCA_TCINDEX_HASH,&hash,sizeof(hash));
+ }
+ else if (!strcmp(*argv,"mask")) {
+ __u16 mask;
+
+ NEXT_ARG();
+ mask = strtoul(*argv,&end,0);
+ if (*end) {
+ explain();
+ return -1;
+ }
+ addattr_l(n,4096,TCA_TCINDEX_MASK,&mask,sizeof(mask));
+ }
+ else if (!strcmp(*argv,"shift")) {
+ int shift;
+
+ NEXT_ARG();
+ shift = strtoul(*argv,&end,0);
+ if (*end) {
+ explain();
+ return -1;
+ }
+ addattr_l(n,4096,TCA_TCINDEX_SHIFT,&shift,
+ sizeof(shift));
+ }
+ else if (!strcmp(*argv,"fall_through")) {
+ int value = 1;
+
+ addattr_l(n,4096,TCA_TCINDEX_FALL_THROUGH,&value,
+ sizeof(value));
+ }
+ else if (!strcmp(*argv,"pass_on")) {
+ int value = 0;
+
+ addattr_l(n,4096,TCA_TCINDEX_FALL_THROUGH,&value,
+ sizeof(value));
+ }
+ else if (!strcmp(*argv,"classid")) {
+ __u32 handle;
+
+ NEXT_ARG();
+ if (get_tc_classid(&handle,*argv)) {
+ fprintf(stderr, "Illegal \"classid\"\n");
+ return -1;
+ }
+ addattr_l(n, 4096, TCA_TCINDEX_CLASSID, &handle, 4);
+ }
+ else if (!strcmp(*argv,"police")) {
+ NEXT_ARG();
+ if (parse_police(&argc, &argv, TCA_TCINDEX_POLICE, n)) {
+ fprintf(stderr, "Illegal \"police\"\n");
+ return -1;
+ }
+ continue;
+ }
+ else if (!strcmp(*argv,"action")) {
+ NEXT_ARG();
+ if (parse_police(&argc, &argv, TCA_TCINDEX_ACT, n)) {
+ fprintf(stderr, "Illegal \"action\"\n");
+ return -1;
+ }
+ continue;
+ }
+ else {
+ explain();
+ return -1;
+ }
+ argc--;
+ argv++;
+ }
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+
+static int tcindex_print_opt(struct filter_util *qu, FILE *f,
+ struct rtattr *opt, __u32 handle)
+{
+ struct rtattr *tb[TCA_TCINDEX_MAX+1];
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_TCINDEX_MAX, opt);
+
+ if (handle != ~0) fprintf(f,"handle 0x%04x ",handle);
+ if (tb[TCA_TCINDEX_HASH]) {
+ __u16 hash;
+
+ if (RTA_PAYLOAD(tb[TCA_TCINDEX_HASH]) < sizeof(hash))
+ return -1;
+ hash = rta_getattr_u16(tb[TCA_TCINDEX_HASH]);
+ fprintf(f,"hash %d ",hash);
+ }
+ if (tb[TCA_TCINDEX_MASK]) {
+ __u16 mask;
+
+ if (RTA_PAYLOAD(tb[TCA_TCINDEX_MASK]) < sizeof(mask))
+ return -1;
+ mask = rta_getattr_u16(tb[TCA_TCINDEX_MASK]);
+ fprintf(f,"mask 0x%04x ",mask);
+ }
+ if (tb[TCA_TCINDEX_SHIFT]) {
+ int shift;
+
+ if (RTA_PAYLOAD(tb[TCA_TCINDEX_SHIFT]) < sizeof(shift))
+ return -1;
+ shift = *(int *) RTA_DATA(tb[TCA_TCINDEX_SHIFT]);
+ fprintf(f,"shift %d ",shift);
+ }
+ if (tb[TCA_TCINDEX_FALL_THROUGH]) {
+ int fall_through;
+
+ if (RTA_PAYLOAD(tb[TCA_TCINDEX_FALL_THROUGH]) <
+ sizeof(fall_through))
+ return -1;
+ fall_through = *(int *) RTA_DATA(tb[TCA_TCINDEX_FALL_THROUGH]);
+ fprintf(f,fall_through ? "fall_through " : "pass_on ");
+ }
+ if (tb[TCA_TCINDEX_CLASSID]) {
+ SPRINT_BUF(b1);
+ fprintf(f, "classid %s ",sprint_tc_classid(*(__u32 *)
+ RTA_DATA(tb[TCA_TCINDEX_CLASSID]), b1));
+ }
+ if (tb[TCA_TCINDEX_POLICE]) {
+ fprintf(f, "\n");
+ tc_print_police(f, tb[TCA_TCINDEX_POLICE]);
+ }
+ if (tb[TCA_TCINDEX_ACT]) {
+ fprintf(f, "\n");
+ tc_print_police(f, tb[TCA_TCINDEX_ACT]);
+ }
+ return 0;
+}
+
+struct filter_util tcindex_filter_util = {
+ .id = "tcindex",
+ .parse_fopt = tcindex_parse_opt,
+ .print_fopt = tcindex_print_opt,
+};
diff --git a/iproute2/tc/f_u32.c b/iproute2/tc/f_u32.c
new file mode 100644
index 0000000..0b97678
--- /dev/null
+++ b/iproute2/tc/f_u32.c
@@ -0,0 +1,1292 @@
+/*
+ * q_u32.c U32 filter.
+ *
+ * This program is free software; you can u32istribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ * Match mark added by Catalin(ux aka Dino) BOIE <catab at umbrella.ro> [5 nov 2004]
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <linux/if.h>
+#include <linux/if_ether.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+extern int show_pretty;
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... u32 [ match SELECTOR ... ] [ link HTID ]"
+ " [ classid CLASSID ]\n");
+ fprintf(stderr, " [ action ACTION_SPEC ]"
+ " [ offset OFFSET_SPEC ]\n");
+ fprintf(stderr, " [ ht HTID ] [ hashkey HASHKEY_SPEC ]\n");
+ fprintf(stderr, " [ sample SAMPLE ]\n");
+ fprintf(stderr, "or u32 divisor DIVISOR\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "Where: SELECTOR := SAMPLE SAMPLE ...\n");
+ fprintf(stderr, " SAMPLE := { ip | ip6 | udp | tcp | icmp |"
+ " u{32|16|8} | mark } SAMPLE_ARGS [divisor DIVISOR]\n");
+ fprintf(stderr, " FILTERID := X:Y:Z\n");
+ fprintf(stderr, "\nNOTE: CLASSID is parsed at hexadecimal input.\n");
+}
+
+static int get_u32_handle(__u32 *handle, const char *str)
+{
+ __u32 htid=0, hash=0, nodeid=0;
+ char *tmp = strchr(str, ':');
+
+ if (tmp == NULL) {
+ if (memcmp("0x", str, 2) == 0)
+ return get_u32(handle, str, 16);
+ return -1;
+ }
+ htid = strtoul(str, &tmp, 16);
+ if (tmp == str && *str != ':' && *str != 0)
+ return -1;
+ if (htid>=0x1000)
+ return -1;
+ if (*tmp) {
+ str = tmp + 1;
+ hash = strtoul(str, &tmp, 16);
+ if (tmp == str && *str != ':' && *str != 0)
+ return -1;
+ if (hash>=0x100)
+ return -1;
+ if (*tmp) {
+ str = tmp + 1;
+ nodeid = strtoul(str, &tmp, 16);
+ if (tmp == str && *str != 0)
+ return -1;
+ if (nodeid>=0x1000)
+ return -1;
+ }
+ }
+ *handle = (htid<<20)|(hash<<12)|nodeid;
+ return 0;
+}
+
+static char * sprint_u32_handle(__u32 handle, char *buf)
+{
+ int bsize = SPRINT_BSIZE-1;
+ __u32 htid = TC_U32_HTID(handle);
+ __u32 hash = TC_U32_HASH(handle);
+ __u32 nodeid = TC_U32_NODE(handle);
+ char *b = buf;
+
+ if (handle == 0) {
+ snprintf(b, bsize, "none");
+ return b;
+ }
+ if (htid) {
+ int l = snprintf(b, bsize, "%x:", htid>>20);
+ bsize -= l;
+ b += l;
+ }
+ if (nodeid|hash) {
+ if (hash) {
+ int l = snprintf(b, bsize, "%x", hash);
+ bsize -= l;
+ b += l;
+ }
+ if (nodeid) {
+ int l = snprintf(b, bsize, ":%x", nodeid);
+ bsize -= l;
+ b += l;
+ }
+ }
+ if (show_raw)
+ snprintf(b, bsize, "[%08x] ", handle);
+ return buf;
+}
+
+static int pack_key(struct tc_u32_sel *sel, __u32 key, __u32 mask,
+ int off, int offmask)
+{
+ int i;
+ int hwm = sel->nkeys;
+
+ key &= mask;
+
+ for (i=0; i<hwm; i++) {
+ if (sel->keys[i].off == off && sel->keys[i].offmask == offmask) {
+ __u32 intersect = mask & sel->keys[i].mask;
+
+ if ((key ^ sel->keys[i].val) & intersect)
+ return -1;
+ sel->keys[i].val |= key;
+ sel->keys[i].mask |= mask;
+ return 0;
+ }
+ }
+
+ if (hwm >= 128)
+ return -1;
+ if (off % 4)
+ return -1;
+ sel->keys[hwm].val = key;
+ sel->keys[hwm].mask = mask;
+ sel->keys[hwm].off = off;
+ sel->keys[hwm].offmask = offmask;
+ sel->nkeys++;
+ return 0;
+}
+
+static int pack_key32(struct tc_u32_sel *sel, __u32 key, __u32 mask,
+ int off, int offmask)
+{
+ key = htonl(key);
+ mask = htonl(mask);
+ return pack_key(sel, key, mask, off, offmask);
+}
+
+static int pack_key16(struct tc_u32_sel *sel, __u32 key, __u32 mask,
+ int off, int offmask)
+{
+ if (key > 0xFFFF || mask > 0xFFFF)
+ return -1;
+
+ if ((off & 3) == 0) {
+ key <<= 16;
+ mask <<= 16;
+ }
+ off &= ~3;
+ key = htonl(key);
+ mask = htonl(mask);
+
+ return pack_key(sel, key, mask, off, offmask);
+}
+
+static int pack_key8(struct tc_u32_sel *sel, __u32 key, __u32 mask, int off, int offmask)
+{
+ if (key > 0xFF || mask > 0xFF)
+ return -1;
+
+ if ((off & 3) == 0) {
+ key <<= 24;
+ mask <<= 24;
+ } else if ((off & 3) == 1) {
+ key <<= 16;
+ mask <<= 16;
+ } else if ((off & 3) == 2) {
+ key <<= 8;
+ mask <<= 8;
+ }
+ off &= ~3;
+ key = htonl(key);
+ mask = htonl(mask);
+
+ return pack_key(sel, key, mask, off, offmask);
+}
+
+
+static int parse_at(int *argc_p, char ***argv_p, int *off, int *offmask)
+{
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ char *p = *argv;
+
+ if (argc <= 0)
+ return -1;
+
+ if (strlen(p) > strlen("nexthdr+") &&
+ memcmp(p, "nexthdr+", strlen("nexthdr+")) == 0) {
+ *offmask = -1;
+ p += strlen("nexthdr+");
+ } else if (matches(*argv, "nexthdr+") == 0) {
+ NEXT_ARG();
+ *offmask = -1;
+ p = *argv;
+ }
+
+ if (get_integer(off, p, 0))
+ return -1;
+ argc--; argv++;
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return 0;
+}
+
+
+static int parse_u32(int *argc_p, char ***argv_p, struct tc_u32_sel *sel,
+ int off, int offmask)
+{
+ int res = -1;
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ __u32 key;
+ __u32 mask;
+
+ if (argc < 2)
+ return -1;
+
+ if (get_u32(&key, *argv, 0))
+ return -1;
+ argc--; argv++;
+
+ if (get_u32(&mask, *argv, 16))
+ return -1;
+ argc--; argv++;
+
+ if (argc > 0 && strcmp(argv[0], "at") == 0) {
+ NEXT_ARG();
+ if (parse_at(&argc, &argv, &off, &offmask))
+ return -1;
+ }
+
+ res = pack_key32(sel, key, mask, off, offmask);
+ *argc_p = argc;
+ *argv_p = argv;
+ return res;
+}
+
+static int parse_u16(int *argc_p, char ***argv_p, struct tc_u32_sel *sel,
+ int off, int offmask)
+{
+ int res = -1;
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ __u32 key;
+ __u32 mask;
+
+ if (argc < 2)
+ return -1;
+
+ if (get_u32(&key, *argv, 0))
+ return -1;
+ argc--; argv++;
+
+ if (get_u32(&mask, *argv, 16))
+ return -1;
+ argc--; argv++;
+
+ if (argc > 0 && strcmp(argv[0], "at") == 0) {
+ NEXT_ARG();
+ if (parse_at(&argc, &argv, &off, &offmask))
+ return -1;
+ }
+ res = pack_key16(sel, key, mask, off, offmask);
+ *argc_p = argc;
+ *argv_p = argv;
+ return res;
+}
+
+static int parse_u8(int *argc_p, char ***argv_p, struct tc_u32_sel *sel,
+ int off, int offmask)
+{
+ int res = -1;
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ __u32 key;
+ __u32 mask;
+
+ if (argc < 2)
+ return -1;
+
+ if (get_u32(&key, *argv, 0))
+ return -1;
+ argc--; argv++;
+
+ if (get_u32(&mask, *argv, 16))
+ return -1;
+ argc--; argv++;
+
+ if (key > 0xFF || mask > 0xFF)
+ return -1;
+
+ if (argc > 0 && strcmp(argv[0], "at") == 0) {
+ NEXT_ARG();
+ if (parse_at(&argc, &argv, &off, &offmask))
+ return -1;
+ }
+
+ res = pack_key8(sel, key, mask, off, offmask);
+ *argc_p = argc;
+ *argv_p = argv;
+ return res;
+}
+
+static int parse_ip_addr(int *argc_p, char ***argv_p, struct tc_u32_sel *sel,
+ int off)
+{
+ int res = -1;
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ inet_prefix addr;
+ __u32 mask;
+ int offmask = 0;
+
+ if (argc < 1)
+ return -1;
+
+ if (get_prefix_1(&addr, *argv, AF_INET))
+ return -1;
+ argc--; argv++;
+
+ if (argc > 0 && strcmp(argv[0], "at") == 0) {
+ NEXT_ARG();
+ if (parse_at(&argc, &argv, &off, &offmask))
+ return -1;
+ }
+
+ mask = 0;
+ if (addr.bitlen)
+ mask = htonl(0xFFFFFFFF << (32 - addr.bitlen));
+ if (pack_key(sel, addr.data[0], mask, off, offmask) < 0)
+ return -1;
+ res = 0;
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return res;
+}
+
+static int parse_ip6_addr(int *argc_p, char ***argv_p,
+ struct tc_u32_sel *sel, int off)
+{
+ int res = -1;
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ int plen = 128;
+ int i;
+ inet_prefix addr;
+ int offmask = 0;
+
+ if (argc < 1)
+ return -1;
+
+ if (get_prefix_1(&addr, *argv, AF_INET6))
+ return -1;
+ argc--; argv++;
+
+ if (argc > 0 && strcmp(argv[0], "at") == 0) {
+ NEXT_ARG();
+ if (parse_at(&argc, &argv, &off, &offmask))
+ return -1;
+ }
+
+ plen = addr.bitlen;
+ for (i = 0; i < plen; i += 32) {
+// if (((i + 31) & ~0x1F) <= plen) {
+ if (i + 31 <= plen) {
+ res = pack_key(sel, addr.data[i / 32],
+ 0xFFFFFFFF, off + 4 * (i / 32), offmask);
+ if (res < 0)
+ return -1;
+ } else if (i < plen) {
+ __u32 mask = htonl(0xFFFFFFFF << (32 - (plen - i)));
+ res = pack_key(sel, addr.data[i / 32],
+ mask, off + 4 * (i / 32), offmask);
+ if (res < 0)
+ return -1;
+ }
+ }
+ res = 0;
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return res;
+}
+
+static int parse_ip6_class(int *argc_p, char ***argv_p, struct tc_u32_sel *sel)
+{
+ int res = -1;
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ __u32 key;
+ __u32 mask;
+ int off = 0;
+ int offmask = 0;
+
+ if (argc < 2)
+ return -1;
+
+ if (get_u32(&key, *argv, 0))
+ return -1;
+ argc--; argv++;
+
+ if (get_u32(&mask, *argv, 16))
+ return -1;
+ argc--; argv++;
+
+ if (key > 0xFF || mask > 0xFF)
+ return -1;
+
+ key <<= 20;
+ mask <<= 20;
+ key = htonl(key);
+ mask = htonl(mask);
+
+ res = pack_key(sel, key, mask, off, offmask);
+ if (res < 0)
+ return -1;
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return 0;
+}
+
+static int parse_ether_addr(int *argc_p, char ***argv_p,
+ struct tc_u32_sel *sel, int off)
+{
+ int res = -1;
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ __u8 addr[6];
+ int offmask = 0;
+ int i;
+
+ if (argc < 1)
+ return -1;
+
+ if (sscanf(*argv, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx",
+ addr + 0, addr + 1, addr + 2,
+ addr + 3, addr + 4, addr + 5) != 6) {
+ fprintf(stderr, "parse_ether_addr: improperly formed address '%s'\n",
+ *argv);
+ return -1;
+ }
+
+ argc--; argv++;
+ if (argc > 0 && strcmp(argv[0], "at") == 0) {
+ NEXT_ARG();
+ if (parse_at(&argc, &argv, &off, &offmask))
+ return -1;
+ }
+
+ for (i = 0; i < 6; i++) {
+ res = pack_key8(sel, addr[i], 0xFF, off + i, offmask);
+ if (res < 0)
+ return -1;
+ }
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return res;
+}
+
+static int parse_ip(int *argc_p, char ***argv_p, struct tc_u32_sel *sel)
+{
+ int res = -1;
+ int argc = *argc_p;
+ char **argv = *argv_p;
+
+ if (argc < 2)
+ return -1;
+
+ if (strcmp(*argv, "src") == 0) {
+ NEXT_ARG();
+ res = parse_ip_addr(&argc, &argv, sel, 12);
+ } else if (strcmp(*argv, "dst") == 0) {
+ NEXT_ARG();
+ res = parse_ip_addr(&argc, &argv, sel, 16);
+ } else if (strcmp(*argv, "tos") == 0 ||
+ matches(*argv, "dsfield") == 0 ||
+ matches(*argv, "precedence") == 0) {
+ NEXT_ARG();
+ res = parse_u8(&argc, &argv, sel, 1, 0);
+ } else if (strcmp(*argv, "ihl") == 0) {
+ NEXT_ARG();
+ res = parse_u8(&argc, &argv, sel, 0, 0);
+ } else if (strcmp(*argv, "protocol") == 0) {
+ NEXT_ARG();
+ res = parse_u8(&argc, &argv, sel, 9, 0);
+ } else if (strcmp(*argv, "nofrag") == 0) {
+ argc--; argv++;
+ res = pack_key16(sel, 0, 0x3FFF, 6, 0);
+ } else if (strcmp(*argv, "firstfrag") == 0) {
+ argc--; argv++;
+ res = pack_key16(sel, 0x2000, 0x3FFF, 6, 0);
+ } else if (strcmp(*argv, "df") == 0) {
+ argc--; argv++;
+ res = pack_key16(sel, 0x4000, 0x4000, 6, 0);
+ } else if (strcmp(*argv, "mf") == 0) {
+ argc--; argv++;
+ res = pack_key16(sel, 0x2000, 0x2000, 6, 0);
+ } else if (strcmp(*argv, "dport") == 0) {
+ NEXT_ARG();
+ res = parse_u16(&argc, &argv, sel, 22, 0);
+ } else if (strcmp(*argv, "sport") == 0) {
+ NEXT_ARG();
+ res = parse_u16(&argc, &argv, sel, 20, 0);
+ } else if (strcmp(*argv, "icmp_type") == 0) {
+ NEXT_ARG();
+ res = parse_u8(&argc, &argv, sel, 20, 0);
+ } else if (strcmp(*argv, "icmp_code") == 0) {
+ NEXT_ARG();
+ res = parse_u8(&argc, &argv, sel, 21, 0);
+ } else
+ return -1;
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return res;
+}
+
+static int parse_ip6(int *argc_p, char ***argv_p, struct tc_u32_sel *sel)
+{
+ int res = -1;
+ int argc = *argc_p;
+ char **argv = *argv_p;
+
+ if (argc < 2)
+ return -1;
+
+ if (strcmp(*argv, "src") == 0) {
+ NEXT_ARG();
+ res = parse_ip6_addr(&argc, &argv, sel, 8);
+ } else if (strcmp(*argv, "dst") == 0) {
+ NEXT_ARG();
+ res = parse_ip6_addr(&argc, &argv, sel, 24);
+ } else if (strcmp(*argv, "priority") == 0) {
+ NEXT_ARG();
+ res = parse_ip6_class(&argc, &argv, sel);
+ } else if (strcmp(*argv, "protocol") == 0) {
+ NEXT_ARG();
+ res = parse_u8(&argc, &argv, sel, 6, 0);
+ } else if (strcmp(*argv, "flowlabel") == 0) {
+ NEXT_ARG();
+ res = parse_u32(&argc, &argv, sel, 0, 0);
+ } else if (strcmp(*argv, "dport") == 0) {
+ NEXT_ARG();
+ res = parse_u16(&argc, &argv, sel, 42, 0);
+ } else if (strcmp(*argv, "sport") == 0) {
+ NEXT_ARG();
+ res = parse_u16(&argc, &argv, sel, 40, 0);
+ } else if (strcmp(*argv, "icmp_type") == 0) {
+ NEXT_ARG();
+ res = parse_u8(&argc, &argv, sel, 40, 0);
+ } else if (strcmp(*argv, "icmp_code") == 0) {
+ NEXT_ARG();
+ res = parse_u8(&argc, &argv, sel, 41, 1);
+ } else
+ return -1;
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return res;
+}
+
+static int parse_ether(int *argc_p, char ***argv_p, struct tc_u32_sel *sel)
+{
+ int res = -1;
+ int argc = *argc_p;
+ char **argv = *argv_p;
+
+ if (argc < 2)
+ return -1;
+
+ if (strcmp(*argv, "src") == 0) {
+ NEXT_ARG();
+ res = parse_ether_addr(&argc, &argv, sel, -8);
+ } else if (strcmp(*argv, "dst") == 0) {
+ NEXT_ARG();
+ res = parse_ether_addr(&argc, &argv, sel, -14);
+ } else {
+ fprintf(stderr, "Unknown match: ether %s\n", *argv);
+ return -1;
+ }
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return res;
+}
+
+#define parse_tcp parse_udp
+static int parse_udp(int *argc_p, char ***argv_p, struct tc_u32_sel *sel)
+{
+ int res = -1;
+ int argc = *argc_p;
+ char **argv = *argv_p;
+
+ if (argc < 2)
+ return -1;
+
+ if (strcmp(*argv, "src") == 0) {
+ NEXT_ARG();
+ res = parse_u16(&argc, &argv, sel, 0, -1);
+ } else if (strcmp(*argv, "dst") == 0) {
+ NEXT_ARG();
+ res = parse_u16(&argc, &argv, sel, 2, -1);
+ } else
+ return -1;
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return res;
+}
+
+
+static int parse_icmp(int *argc_p, char ***argv_p, struct tc_u32_sel *sel)
+{
+ int res = -1;
+ int argc = *argc_p;
+ char **argv = *argv_p;
+
+ if (argc < 2)
+ return -1;
+
+ if (strcmp(*argv, "type") == 0) {
+ NEXT_ARG();
+ res = parse_u8(&argc, &argv, sel, 0, -1);
+ } else if (strcmp(*argv, "code") == 0) {
+ NEXT_ARG();
+ res = parse_u8(&argc, &argv, sel, 1, -1);
+ } else
+ return -1;
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return res;
+}
+
+static int parse_mark(int *argc_p, char ***argv_p, struct nlmsghdr *n)
+{
+ int res = -1;
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ struct tc_u32_mark mark;
+
+ if (argc <= 1)
+ return -1;
+
+ if (get_u32(&mark.val, *argv, 0)) {
+ fprintf(stderr, "Illegal \"mark\" value\n");
+ return -1;
+ }
+ NEXT_ARG();
+
+ if (get_u32(&mark.mask, *argv, 0)) {
+ fprintf(stderr, "Illegal \"mark\" mask\n");
+ return -1;
+ }
+ NEXT_ARG();
+
+ if ((mark.val & mark.mask) != mark.val) {
+ fprintf(stderr, "Illegal \"mark\" (impossible combination)\n");
+ return -1;
+ }
+
+ addattr_l(n, MAX_MSG, TCA_U32_MARK, &mark, sizeof(mark));
+ res = 0;
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return res;
+}
+
+static int parse_selector(int *argc_p, char ***argv_p,
+ struct tc_u32_sel *sel, struct nlmsghdr *n)
+{
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ int res = -1;
+
+ if (argc <= 0)
+ return -1;
+
+ if (matches(*argv, "u32") == 0) {
+ NEXT_ARG();
+ res = parse_u32(&argc, &argv, sel, 0, 0);
+ } else if (matches(*argv, "u16") == 0) {
+ NEXT_ARG();
+ res = parse_u16(&argc, &argv, sel, 0, 0);
+ } else if (matches(*argv, "u8") == 0) {
+ NEXT_ARG();
+ res = parse_u8(&argc, &argv, sel, 0, 0);
+ } else if (matches(*argv, "ip") == 0) {
+ NEXT_ARG();
+ res = parse_ip(&argc, &argv, sel);
+ } else if (matches(*argv, "ip6") == 0) {
+ NEXT_ARG();
+ res = parse_ip6(&argc, &argv, sel);
+ } else if (matches(*argv, "udp") == 0) {
+ NEXT_ARG();
+ res = parse_udp(&argc, &argv, sel);
+ } else if (matches(*argv, "tcp") == 0) {
+ NEXT_ARG();
+ res = parse_tcp(&argc, &argv, sel);
+ } else if (matches(*argv, "icmp") == 0) {
+ NEXT_ARG();
+ res = parse_icmp(&argc, &argv, sel);
+ } else if (matches(*argv, "mark") == 0) {
+ NEXT_ARG();
+ res = parse_mark(&argc, &argv, n);
+ } else if (matches(*argv, "ether") == 0) {
+ NEXT_ARG();
+ res = parse_ether(&argc, &argv, sel);
+ } else
+ return -1;
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return res;
+}
+
+static int parse_offset(int *argc_p, char ***argv_p, struct tc_u32_sel *sel)
+{
+ int argc = *argc_p;
+ char **argv = *argv_p;
+
+ while (argc > 0) {
+ if (matches(*argv, "plus") == 0) {
+ int off;
+ NEXT_ARG();
+ if (get_integer(&off, *argv, 0))
+ return -1;
+ sel->off = off;
+ sel->flags |= TC_U32_OFFSET;
+ } else if (matches(*argv, "at") == 0) {
+ int off;
+ NEXT_ARG();
+ if (get_integer(&off, *argv, 0))
+ return -1;
+ sel->offoff = off;
+ if (off%2) {
+ fprintf(stderr, "offset \"at\" must be even\n");
+ return -1;
+ }
+ sel->flags |= TC_U32_VAROFFSET;
+ } else if (matches(*argv, "mask") == 0) {
+ __u16 mask;
+ NEXT_ARG();
+ if (get_u16(&mask, *argv, 16))
+ return -1;
+ sel->offmask = htons(mask);
+ sel->flags |= TC_U32_VAROFFSET;
+ } else if (matches(*argv, "shift") == 0) {
+ int shift;
+ NEXT_ARG();
+ if (get_integer(&shift, *argv, 0))
+ return -1;
+ sel->offshift = shift;
+ sel->flags |= TC_U32_VAROFFSET;
+ } else if (matches(*argv, "eat") == 0) {
+ sel->flags |= TC_U32_EAT;
+ } else {
+ break;
+ }
+ argc--; argv++;
+ }
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return 0;
+}
+
+static int parse_hashkey(int *argc_p, char ***argv_p, struct tc_u32_sel *sel)
+{
+ int argc = *argc_p;
+ char **argv = *argv_p;
+
+ while (argc > 0) {
+ if (matches(*argv, "mask") == 0) {
+ __u32 mask;
+ NEXT_ARG();
+ if (get_u32(&mask, *argv, 16))
+ return -1;
+ sel->hmask = htonl(mask);
+ } else if (matches(*argv, "at") == 0) {
+ int num;
+ NEXT_ARG();
+ if (get_integer(&num, *argv, 0))
+ return -1;
+ if (num%4)
+ return -1;
+ sel->hoff = num;
+ } else {
+ break;
+ }
+ argc--; argv++;
+ }
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return 0;
+}
+
+static void print_ipv4(FILE *f, const struct tc_u32_key *key)
+{
+ char abuf[256];
+
+ switch (key->off) {
+ case 0:
+ switch (ntohl(key->mask)) {
+ case 0x0f000000:
+ fprintf(f, "\n match IP ihl %u", ntohl(key->val) >> 24);
+ return;
+ case 0x00ff0000:
+ fprintf(f, "\n match IP dsfield %#x", ntohl(key->val) >> 16);
+ return;
+ }
+ break;
+ case 8:
+ if (ntohl(key->mask) == 0x00ff0000) {
+ fprintf(f, "\n match IP protocol %d", ntohl(key->val) >> 16);
+ return;
+ }
+ break;
+ case 12:
+ case 16: {
+ int bits = mask2bits(key->mask);
+ if (bits >= 0) {
+ fprintf(f, "\n %s %s/%d",
+ key->off == 12 ? "match IP src" : "match IP dst",
+ inet_ntop(AF_INET, &key->val,
+ abuf, sizeof(abuf)),
+ bits);
+ return;
+ }
+ }
+ break;
+
+ case 20:
+ switch (ntohl(key->mask)) {
+ case 0x0000ffff:
+ fprintf(f, "\n match dport %u",
+ ntohl(key->val) & 0xffff);
+ return;
+ case 0xffff0000:
+ fprintf(f, "\n match sport %u",
+ ntohl(key->val) >> 16);
+ return;
+ case 0xffffffff:
+ fprintf(f, "\n match dport %u, match sport %u",
+ ntohl(key->val) & 0xffff,
+ ntohl(key->val) >> 16);
+
+ return;
+ }
+ /* XXX: Default print_raw */
+ }
+}
+
+static void print_ipv6(FILE *f, const struct tc_u32_key *key)
+{
+ char abuf[256];
+
+ switch (key->off) {
+ case 0:
+ switch (ntohl(key->mask)) {
+ case 0x0f000000:
+ fprintf(f, "\n match IP ihl %u", ntohl(key->val) >> 24);
+ return;
+ case 0x00ff0000:
+ fprintf(f, "\n match IP dsfield %#x", ntohl(key->val) >> 16);
+ return;
+ }
+ break;
+ case 8:
+ if (ntohl(key->mask) == 0x00ff0000) {
+ fprintf(f, "\n match IP protocol %d", ntohl(key->val) >> 16);
+ return;
+ }
+ break;
+ case 12:
+ case 16: {
+ int bits = mask2bits(key->mask);
+ if (bits >= 0) {
+ fprintf(f, "\n %s %s/%d",
+ key->off == 12 ? "match IP src" : "match IP dst",
+ inet_ntop(AF_INET, &key->val,
+ abuf, sizeof(abuf)),
+ bits);
+ return;
+ }
+ }
+ break;
+
+ case 20:
+ switch (ntohl(key->mask)) {
+ case 0x0000ffff:
+ fprintf(f, "\n match sport %u",
+ ntohl(key->val) & 0xffff);
+ return;
+ case 0xffff0000:
+ fprintf(f, "\n match dport %u",
+ ntohl(key->val) >> 16);
+ return;
+ case 0xffffffff:
+ fprintf(f, "\n match sport %u, match dport %u",
+ ntohl(key->val) & 0xffff,
+ ntohl(key->val) >> 16);
+
+ return;
+ }
+ /* XXX: Default print_raw */
+ }
+}
+
+static void print_raw(FILE *f, const struct tc_u32_key *key)
+{
+ fprintf(f, "\n match %08x/%08x at %s%d",
+ (unsigned int)ntohl(key->val),
+ (unsigned int)ntohl(key->mask),
+ key->offmask ? "nexthdr+" : "",
+ key->off);
+}
+
+static const struct {
+ __u16 proto;
+ __u16 pad;
+ void (*pprinter)(FILE *f, const struct tc_u32_key *key);
+} u32_pprinters[] = {
+ {0, 0, print_raw},
+ {ETH_P_IP, 0, print_ipv4},
+ {ETH_P_IPV6, 0, print_ipv6},
+};
+
+static void show_keys(FILE *f, const struct tc_u32_key *key)
+{
+ int i = 0;
+
+ if (!show_pretty)
+ goto show_k;
+
+ for (i = 0; i < sizeof(u32_pprinters) / sizeof(u32_pprinters[0]); i++) {
+ if (u32_pprinters[i].proto == ntohs(f_proto)) {
+show_k:
+ u32_pprinters[i].pprinter(f, key);
+ return;
+ }
+ }
+
+ i = 0;
+ goto show_k;
+}
+
+static int u32_parse_opt(struct filter_util *qu, char *handle,
+ int argc, char **argv, struct nlmsghdr *n)
+{
+ struct {
+ struct tc_u32_sel sel;
+ struct tc_u32_key keys[128];
+ } sel;
+ struct tcmsg *t = NLMSG_DATA(n);
+ struct rtattr *tail;
+ int sel_ok = 0, terminal_ok = 0;
+ int sample_ok = 0;
+ __u32 htid = 0;
+ __u32 order = 0;
+
+ memset(&sel, 0, sizeof(sel));
+
+ if (handle && get_u32_handle(&t->tcm_handle, handle)) {
+ fprintf(stderr, "Illegal filter ID\n");
+ return -1;
+ }
+
+ if (argc == 0)
+ return 0;
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, MAX_MSG, TCA_OPTIONS, NULL, 0);
+
+ while (argc > 0) {
+ if (matches(*argv, "match") == 0) {
+ NEXT_ARG();
+ if (parse_selector(&argc, &argv, &sel.sel, n)) {
+ fprintf(stderr, "Illegal \"match\"\n");
+ return -1;
+ }
+ sel_ok++;
+ continue;
+ } else if (matches(*argv, "offset") == 0) {
+ NEXT_ARG();
+ if (parse_offset(&argc, &argv, &sel.sel)) {
+ fprintf(stderr, "Illegal \"offset\"\n");
+ return -1;
+ }
+ continue;
+ } else if (matches(*argv, "hashkey") == 0) {
+ NEXT_ARG();
+ if (parse_hashkey(&argc, &argv, &sel.sel)) {
+ fprintf(stderr, "Illegal \"hashkey\"\n");
+ return -1;
+ }
+ continue;
+ } else if (matches(*argv, "classid") == 0 ||
+ strcmp(*argv, "flowid") == 0) {
+ unsigned handle;
+ NEXT_ARG();
+ if (get_tc_classid(&handle, *argv)) {
+ fprintf(stderr, "Illegal \"classid\"\n");
+ return -1;
+ }
+ addattr_l(n, MAX_MSG, TCA_U32_CLASSID, &handle, 4);
+ sel.sel.flags |= TC_U32_TERMINAL;
+ } else if (matches(*argv, "divisor") == 0) {
+ unsigned divisor;
+ NEXT_ARG();
+ if (get_unsigned(&divisor, *argv, 0) ||
+ divisor == 0 ||
+ divisor > 0x100 || ((divisor - 1) & divisor)) {
+ fprintf(stderr, "Illegal \"divisor\"\n");
+ return -1;
+ }
+ addattr_l(n, MAX_MSG, TCA_U32_DIVISOR, &divisor, 4);
+ } else if (matches(*argv, "order") == 0) {
+ NEXT_ARG();
+ if (get_u32(&order, *argv, 0)) {
+ fprintf(stderr, "Illegal \"order\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "link") == 0) {
+ unsigned handle;
+ NEXT_ARG();
+ if (get_u32_handle(&handle, *argv)) {
+ fprintf(stderr, "Illegal \"link\"\n");
+ return -1;
+ }
+ if (handle && TC_U32_NODE(handle)) {
+ fprintf(stderr, "\"link\" must be a hash table.\n");
+ return -1;
+ }
+ addattr_l(n, MAX_MSG, TCA_U32_LINK, &handle, 4);
+ } else if (strcmp(*argv, "ht") == 0) {
+ unsigned handle;
+ NEXT_ARG();
+ if (get_u32_handle(&handle, *argv)) {
+ fprintf(stderr, "Illegal \"ht\"\n");
+ return -1;
+ }
+ if (handle && TC_U32_NODE(handle)) {
+ fprintf(stderr, "\"ht\" must be a hash table.\n");
+ return -1;
+ }
+ if (sample_ok)
+ htid = (htid & 0xFF000) | (handle & 0xFFF00000);
+ else
+ htid = (handle & 0xFFFFF000);
+ } else if (strcmp(*argv, "sample") == 0) {
+ __u32 hash;
+ unsigned divisor = 0x100;
+
+ struct {
+ struct tc_u32_sel sel;
+ struct tc_u32_key keys[4];
+ } sel2;
+ memset(&sel2, 0, sizeof(sel2));
+ NEXT_ARG();
+ if (parse_selector(&argc, &argv, &sel2.sel, n)) {
+ fprintf(stderr, "Illegal \"sample\"\n");
+ return -1;
+ }
+ if (sel2.sel.nkeys != 1) {
+ fprintf(stderr, "\"sample\" must contain"
+ " exactly ONE key.\n");
+ return -1;
+ }
+ if (*argv != 0 && strcmp(*argv, "divisor") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&divisor, *argv, 0) || divisor == 0 ||
+ divisor > 0x100 || ((divisor - 1) & divisor)) {
+ fprintf(stderr, "Illegal sample \"divisor\"\n");
+ return -1;
+ }
+ NEXT_ARG();
+ }
+ hash = sel2.sel.keys[0].val & sel2.sel.keys[0].mask;
+ hash ^= hash >> 16;
+ hash ^= hash >> 8;
+ htid = ((hash % divisor) << 12) | (htid & 0xFFF00000);
+ sample_ok = 1;
+ continue;
+ } else if (strcmp(*argv, "indev") == 0) {
+ char ind[IFNAMSIZ + 1];
+ memset(ind, 0, sizeof (ind));
+ argc--;
+ argv++;
+ if (argc < 1) {
+ fprintf(stderr, "Illegal indev\n");
+ return -1;
+ }
+ strncpy(ind, *argv, sizeof (ind) - 1);
+ addattr_l(n, MAX_MSG, TCA_U32_INDEV, ind, strlen(ind) + 1);
+
+ } else if (matches(*argv, "action") == 0) {
+ NEXT_ARG();
+ if (parse_action(&argc, &argv, TCA_U32_ACT, n)) {
+ fprintf(stderr, "Illegal \"action\"\n");
+ return -1;
+ }
+ terminal_ok++;
+ continue;
+
+ } else if (matches(*argv, "police") == 0) {
+ NEXT_ARG();
+ if (parse_police(&argc, &argv, TCA_U32_POLICE, n)) {
+ fprintf(stderr, "Illegal \"police\"\n");
+ return -1;
+ }
+ terminal_ok++;
+ continue;
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ /* We dont necessarily need class/flowids */
+ if (terminal_ok)
+ sel.sel.flags |= TC_U32_TERMINAL;
+
+ if (order) {
+ if (TC_U32_NODE(t->tcm_handle) && order != TC_U32_NODE(t->tcm_handle)) {
+ fprintf(stderr, "\"order\" contradicts \"handle\"\n");
+ return -1;
+ }
+ t->tcm_handle |= order;
+ }
+
+ if (htid)
+ addattr_l(n, MAX_MSG, TCA_U32_HASH, &htid, 4);
+ if (sel_ok)
+ addattr_l(n, MAX_MSG, TCA_U32_SEL, &sel,
+ sizeof(sel.sel) + sel.sel.nkeys * sizeof(struct tc_u32_key));
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+static int u32_print_opt(struct filter_util *qu, FILE *f, struct rtattr *opt,
+ __u32 handle)
+{
+ struct rtattr *tb[TCA_U32_MAX + 1];
+ struct tc_u32_sel *sel = NULL;
+ struct tc_u32_pcnt *pf = NULL;
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_U32_MAX, opt);
+
+ if (handle) {
+ SPRINT_BUF(b1);
+ fprintf(f, "fh %s ", sprint_u32_handle(handle, b1));
+ }
+ if (TC_U32_NODE(handle)) {
+ fprintf(f, "order %d ", TC_U32_NODE(handle));
+ }
+
+ if (tb[TCA_U32_SEL]) {
+ if (RTA_PAYLOAD(tb[TCA_U32_SEL]) < sizeof(*sel))
+ return -1;
+
+ sel = RTA_DATA(tb[TCA_U32_SEL]);
+ }
+
+ if (tb[TCA_U32_DIVISOR]) {
+ fprintf(f, "ht divisor %d ", rta_getattr_u32(tb[TCA_U32_DIVISOR]));
+ } else if (tb[TCA_U32_HASH]) {
+ __u32 htid = rta_getattr_u32(tb[TCA_U32_HASH]);
+ fprintf(f, "key ht %x bkt %x ", TC_U32_USERHTID(htid),
+ TC_U32_HASH(htid));
+ } else {
+ fprintf(f, "??? ");
+ }
+ if (tb[TCA_U32_CLASSID]) {
+ SPRINT_BUF(b1);
+ fprintf(f, "%sflowid %s ",
+ !sel || !(sel->flags & TC_U32_TERMINAL) ? "*" : "",
+ sprint_tc_classid(rta_getattr_u32(tb[TCA_U32_CLASSID]), b1));
+ } else if (sel && sel->flags & TC_U32_TERMINAL) {
+ fprintf(f, "terminal flowid ??? ");
+ }
+ if (tb[TCA_U32_LINK]) {
+ SPRINT_BUF(b1);
+ fprintf(f, "link %s ",
+ sprint_u32_handle(rta_getattr_u32(tb[TCA_U32_LINK]), b1));
+ }
+
+ if (tb[TCA_U32_PCNT]) {
+ if (RTA_PAYLOAD(tb[TCA_U32_PCNT]) < sizeof(*pf)) {
+ fprintf(f, "Broken perf counters \n");
+ return -1;
+ }
+ pf = RTA_DATA(tb[TCA_U32_PCNT]);
+ }
+
+ if (sel && show_stats && NULL != pf)
+ fprintf(f, " (rule hit %llu success %llu)",
+ (unsigned long long) pf->rcnt,
+ (unsigned long long) pf->rhit);
+
+ if (tb[TCA_U32_MARK]) {
+ struct tc_u32_mark *mark = RTA_DATA(tb[TCA_U32_MARK]);
+ if (RTA_PAYLOAD(tb[TCA_U32_MARK]) < sizeof(*mark)) {
+ fprintf(f, "\n Invalid mark (kernel&iproute2 mismatch)\n");
+ } else {
+ fprintf(f, "\n mark 0x%04x 0x%04x (success %d)",
+ mark->val, mark->mask, mark->success);
+ }
+ }
+
+ if (sel) {
+ if (sel->nkeys) {
+ int i;
+ for (i=0; i<sel->nkeys; i++) {
+ show_keys(f, sel->keys + i);
+ if (show_stats && NULL != pf)
+ fprintf(f, " (success %llu ) ",
+ (unsigned long long) pf->kcnts[i]);
+ }
+ }
+
+ if (sel->flags & (TC_U32_VAROFFSET | TC_U32_OFFSET)) {
+ fprintf(f, "\n offset ");
+ if (sel->flags & TC_U32_VAROFFSET)
+ fprintf(f, "%04x>>%d at %d ",
+ ntohs(sel->offmask),
+ sel->offshift, sel->offoff);
+ if (sel->off)
+ fprintf(f, "plus %d ", sel->off);
+ }
+ if (sel->flags & TC_U32_EAT)
+ fprintf(f, " eat ");
+
+ if (sel->hmask) {
+ fprintf(f, "\n hash mask %08x at %d ",
+ (unsigned int)htonl(sel->hmask), sel->hoff);
+ }
+ }
+
+ if (tb[TCA_U32_POLICE]) {
+ fprintf(f, "\n");
+ tc_print_police(f, tb[TCA_U32_POLICE]);
+ }
+ if (tb[TCA_U32_INDEV]) {
+ struct rtattr *idev = tb[TCA_U32_INDEV];
+ fprintf(f, "\n input dev %s\n", rta_getattr_str(idev));
+ }
+ if (tb[TCA_U32_ACT]) {
+ tc_print_action(f, tb[TCA_U32_ACT]);
+ }
+
+ return 0;
+}
+
+struct filter_util u32_filter_util = {
+ .id = "u32",
+ .parse_fopt = u32_parse_opt,
+ .print_fopt = u32_print_opt,
+};
diff --git a/iproute2/tc/m_action.c b/iproute2/tc/m_action.c
new file mode 100644
index 0000000..8d3d51e
--- /dev/null
+++ b/iproute2/tc/m_action.c
@@ -0,0 +1,663 @@
+/*
+ * m_action.c Action Management
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: J Hadi Salim (hadi@cyberus.ca)
+ *
+ * TODO:
+ * - parse to be passed a filedescriptor for logging purposes
+ *
+*/
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <dlfcn.h>
+
+#include "utils.h"
+#include "tc_common.h"
+#include "tc_util.h"
+
+static struct action_util * action_list;
+
+#ifdef ANDROID
+extern struct action_util mirred_action_util;
+#endif
+
+#ifdef CONFIG_GACT
+int gact_ld = 0 ; //fuckin backward compatibility
+#endif
+int tab_flush = 0;
+
+static void act_usage(void)
+{
+ /*XXX: In the near future add a action->print_help to improve
+ * usability
+ * This would mean new tc will not be backward compatible
+ * with any action .so from the old days. But if someone really
+ * does that, they would know how to fix this ..
+ *
+ */
+ fprintf (stderr, "usage: tc actions <ACTSPECOP>*\n");
+ fprintf(stderr,
+ "Where: \tACTSPECOP := ACR | GD | FL\n"
+ "\tACR := add | change | replace <ACTSPEC>* \n"
+ "\tGD := get | delete | <ACTISPEC>*\n"
+ "\tFL := ls | list | flush | <ACTNAMESPEC>\n"
+ "\tACTNAMESPEC := action <ACTNAME>\n"
+ "\tACTISPEC := <ACTNAMESPEC> <INDEXSPEC>\n"
+ "\tACTSPEC := action <ACTDETAIL> [INDEXSPEC]\n"
+ "\tINDEXSPEC := index <32 bit indexvalue>\n"
+ "\tACTDETAIL := <ACTNAME> <ACTPARAMS>\n"
+ "\t\tExample ACTNAME is gact, mirred, bpf, etc\n"
+ "\t\tEach action has its own parameters (ACTPARAMS)\n"
+ "\n");
+
+ exit(-1);
+}
+
+static int print_noaopt(struct action_util *au, FILE *f, struct rtattr *opt)
+{
+ if (opt && RTA_PAYLOAD(opt))
+ fprintf(f, "[Unknown action, optlen=%u] ",
+ (unsigned) RTA_PAYLOAD(opt));
+ return 0;
+}
+
+static int parse_noaopt(struct action_util *au, int *argc_p, char ***argv_p, int code, struct nlmsghdr *n)
+{
+ int argc = *argc_p;
+ char **argv = *argv_p;
+
+ if (argc) {
+ fprintf(stderr, "Unknown action \"%s\", hence option \"%s\" is unparsable\n", au->id, *argv);
+ } else {
+ fprintf(stderr, "Unknown action \"%s\"\n", au->id);
+ }
+ return -1;
+}
+
+static struct action_util *get_action_kind(char *str)
+{
+#ifdef ANDROID
+ if (!strcmp(str, "mirred")) {
+ return &mirred_action_util;
+ } else {
+ fprintf(stderr, "Android does not support action '%s'", str);
+ return NULL;
+ }
+#endif
+ static void *aBODY;
+ void *dlh;
+ char buf[256];
+ struct action_util *a;
+#ifdef CONFIG_GACT
+ int looked4gact = 0;
+restart_s:
+#endif
+ for (a = action_list; a; a = a->next) {
+ if (strcmp(a->id, str) == 0)
+ return a;
+ }
+
+ snprintf(buf, sizeof(buf), "%s/m_%s.so", get_tc_lib(), str);
+ dlh = dlopen(buf, RTLD_LAZY | RTLD_GLOBAL);
+ if (dlh == NULL) {
+ dlh = aBODY;
+ if (dlh == NULL) {
+ dlh = aBODY = dlopen(NULL, RTLD_LAZY);
+ if (dlh == NULL)
+ goto noexist;
+ }
+ }
+
+ snprintf(buf, sizeof(buf), "%s_action_util", str);
+ a = dlsym(dlh, buf);
+ if (a == NULL)
+ goto noexist;
+
+reg:
+ a->next = action_list;
+ action_list = a;
+ return a;
+
+noexist:
+#ifdef CONFIG_GACT
+ if (!looked4gact) {
+ looked4gact = 1;
+ strcpy(str,"gact");
+ goto restart_s;
+ }
+#endif
+ a = malloc(sizeof(*a));
+ if (a) {
+ memset(a, 0, sizeof(*a));
+ strncpy(a->id, "noact", 15);
+ a->parse_aopt = parse_noaopt;
+ a->print_aopt = print_noaopt;
+ goto reg;
+ }
+ return a;
+}
+
+static int
+new_cmd(char **argv)
+{
+ if ((matches(*argv, "change") == 0) ||
+ (matches(*argv, "replace") == 0)||
+ (matches(*argv, "delete") == 0)||
+ (matches(*argv, "get") == 0)||
+ (matches(*argv, "add") == 0))
+ return 1;
+
+ return 0;
+
+}
+
+int
+parse_action(int *argc_p, char ***argv_p, int tca_id, struct nlmsghdr *n)
+{
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ struct rtattr *tail, *tail2;
+ char k[16];
+ int ok = 0;
+ int eap = 0; /* expect action parameters */
+
+ int ret = 0;
+ int prio = 0;
+
+ if (argc <= 0)
+ return -1;
+
+ tail = tail2 = NLMSG_TAIL(n);
+
+ addattr_l(n, MAX_MSG, tca_id, NULL, 0);
+
+ while (argc > 0) {
+
+ memset(k, 0, sizeof (k));
+
+ if (strcmp(*argv, "action") == 0 ) {
+ argc--;
+ argv++;
+ eap = 1;
+#ifdef CONFIG_GACT
+ if (!gact_ld) {
+ get_action_kind("gact");
+ }
+#endif
+ continue;
+ } else if (strcmp(*argv, "flowid") == 0) {
+ break;
+ } else if (strcmp(*argv, "classid") == 0) {
+ break;
+ } else if (strcmp(*argv, "help") == 0) {
+ return -1;
+ } else if (new_cmd(argv)) {
+ goto done0;
+ } else {
+ struct action_util *a = NULL;
+ strncpy(k, *argv, sizeof (k) - 1);
+ eap = 0;
+ if (argc > 0 ) {
+ a = get_action_kind(k);
+ } else {
+done0:
+ if (ok)
+ break;
+ else
+ goto done;
+ }
+
+ if (NULL == a) {
+ goto bad_val;
+ }
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, MAX_MSG, ++prio, NULL, 0);
+ addattr_l(n, MAX_MSG, TCA_ACT_KIND, k, strlen(k) + 1);
+
+ ret = a->parse_aopt(a,&argc, &argv, TCA_ACT_OPTIONS, n);
+
+ if (ret < 0) {
+ fprintf(stderr,"bad action parsing\n");
+ goto bad_val;
+ }
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ ok++;
+ }
+
+ }
+
+ if (eap > 0) {
+ fprintf(stderr,"bad action empty %d\n",eap);
+ goto bad_val;
+ }
+
+ tail2->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail2;
+
+done:
+ *argc_p = argc;
+ *argv_p = argv;
+ return 0;
+bad_val:
+ /* no need to undo things, returning from here should
+ * cause enough pain */
+ fprintf(stderr, "parse_action: bad value (%d:%s)!\n",argc,*argv);
+ return -1;
+}
+
+static int
+tc_print_one_action(FILE * f, struct rtattr *arg)
+{
+
+ struct rtattr *tb[TCA_ACT_MAX + 1];
+ int err = 0;
+ struct action_util *a = NULL;
+
+ if (arg == NULL)
+ return -1;
+
+ parse_rtattr_nested(tb, TCA_ACT_MAX, arg);
+
+ if (tb[TCA_ACT_KIND] == NULL) {
+ fprintf(stderr, "NULL Action!\n");
+ return -1;
+ }
+
+
+ a = get_action_kind(RTA_DATA(tb[TCA_ACT_KIND]));
+ if (NULL == a)
+ return err;
+
+ err = a->print_aopt(a, f, tb[TCA_ACT_OPTIONS]);
+
+ if (0 > err)
+ return err;
+
+ if (show_stats && tb[TCA_ACT_STATS]) {
+ fprintf(f, "\tAction statistics:\n");
+ print_tcstats2_attr(f, tb[TCA_ACT_STATS], "\t", NULL);
+ fprintf(f, "\n");
+ }
+
+ return 0;
+}
+
+static int
+tc_print_action_flush(FILE *f, const struct rtattr *arg)
+{
+
+ struct rtattr *tb[TCA_MAX + 1];
+ int err = 0;
+ struct action_util *a = NULL;
+ __u32 *delete_count = 0;
+
+ parse_rtattr_nested(tb, TCA_MAX, arg);
+
+ if (tb[TCA_KIND] == NULL) {
+ fprintf(stderr, "NULL Action!\n");
+ return -1;
+ }
+
+ a = get_action_kind(RTA_DATA(tb[TCA_KIND]));
+ if (NULL == a)
+ return err;
+
+ delete_count = RTA_DATA(tb[TCA_FCNT]);
+ fprintf(f," %s (%d entries)\n", a->id, *delete_count);
+ tab_flush = 0;
+ return 0;
+}
+
+int
+tc_print_action(FILE *f, const struct rtattr *arg)
+{
+
+ int i;
+ struct rtattr *tb[TCA_ACT_MAX_PRIO + 1];
+
+ if (arg == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_ACT_MAX_PRIO, arg);
+
+ if (tab_flush && NULL != tb[0] && NULL == tb[1])
+ return tc_print_action_flush(f, tb[0]);
+
+ for (i = 0; i < TCA_ACT_MAX_PRIO; i++) {
+ if (tb[i]) {
+ fprintf(f, "\n\taction order %d: ", i);
+ if (0 > tc_print_one_action(f, tb[i])) {
+ fprintf(f, "Error printing action\n");
+ }
+ }
+
+ }
+
+ return 0;
+}
+
+int print_action(const struct sockaddr_nl *who,
+ struct nlmsghdr *n,
+ void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ struct tcamsg *t = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr * tb[TCAA_MAX+1];
+
+ len -= NLMSG_LENGTH(sizeof(*t));
+
+ if (len < 0) {
+ fprintf(stderr, "Wrong len %d\n", len);
+ return -1;
+ }
+
+ parse_rtattr(tb, TCAA_MAX, TA_RTA(t), len);
+
+ if (NULL == tb[TCA_ACT_TAB]) {
+ if (n->nlmsg_type != RTM_GETACTION)
+ fprintf(stderr, "print_action: NULL kind\n");
+ return -1;
+ }
+
+ if (n->nlmsg_type == RTM_DELACTION) {
+ if (n->nlmsg_flags & NLM_F_ROOT) {
+ fprintf(fp, "Flushed table ");
+ tab_flush = 1;
+ } else {
+ fprintf(fp, "deleted action ");
+ }
+ }
+
+ if (n->nlmsg_type == RTM_NEWACTION)
+ fprintf(fp, "Added action ");
+ tc_print_action(fp, tb[TCA_ACT_TAB]);
+
+ return 0;
+}
+
+static int tc_action_gd(int cmd, unsigned flags, int *argc_p, char ***argv_p)
+{
+ char k[16];
+ struct action_util *a = NULL;
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ int prio = 0;
+ int ret = 0;
+ __u32 i;
+ struct sockaddr_nl nladdr;
+ struct rtattr *tail;
+ struct rtattr *tail2;
+ struct nlmsghdr *ans = NULL;
+
+ struct {
+ struct nlmsghdr n;
+ struct tcamsg t;
+ char buf[MAX_MSG];
+ } req;
+
+ req.t.tca_family = AF_UNSPEC;
+
+ memset(&req, 0, sizeof(req));
+
+ memset(&nladdr, 0, sizeof(nladdr));
+ nladdr.nl_family = AF_NETLINK;
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcamsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST|flags;
+ req.n.nlmsg_type = cmd;
+ argc -=1;
+ argv +=1;
+
+
+ tail = NLMSG_TAIL(&req.n);
+ addattr_l(&req.n, MAX_MSG, TCA_ACT_TAB, NULL, 0);
+
+ while (argc > 0) {
+ if (strcmp(*argv, "action") == 0 ) {
+ argc--;
+ argv++;
+ continue;
+ } else if (strcmp(*argv, "help") == 0) {
+ return -1;
+ }
+
+ strncpy(k, *argv, sizeof (k) - 1);
+ a = get_action_kind(k);
+ if (NULL == a) {
+ fprintf(stderr, "Error: non existent action: %s\n",k);
+ ret = -1;
+ goto bad_val;
+ }
+ if (strcmp(a->id, k) != 0) {
+ fprintf(stderr, "Error: non existent action: %s\n",k);
+ ret = -1;
+ goto bad_val;
+ }
+
+ argc -=1;
+ argv +=1;
+ if (argc <= 0) {
+ fprintf(stderr, "Error: no index specified action: %s\n",k);
+ ret = -1;
+ goto bad_val;
+ }
+
+ if (matches(*argv, "index") == 0) {
+ NEXT_ARG();
+ if (get_u32(&i, *argv, 10)) {
+ fprintf(stderr, "Illegal \"index\"\n");
+ ret = -1;
+ goto bad_val;
+ }
+ argc -=1;
+ argv +=1;
+ } else {
+ fprintf(stderr, "Error: no index specified action: %s\n",k);
+ ret = -1;
+ goto bad_val;
+ }
+
+ tail2 = NLMSG_TAIL(&req.n);
+ addattr_l(&req.n, MAX_MSG, ++prio, NULL, 0);
+ addattr_l(&req.n, MAX_MSG, TCA_ACT_KIND, k, strlen(k) + 1);
+ addattr32(&req.n, MAX_MSG, TCA_ACT_INDEX, i);
+ tail2->rta_len = (void *) NLMSG_TAIL(&req.n) - (void *) tail2;
+
+ }
+
+ tail->rta_len = (void *) NLMSG_TAIL(&req.n) - (void *) tail;
+
+ req.n.nlmsg_seq = rth.dump = ++rth.seq;
+ if (cmd == RTM_GETACTION)
+ ans = &req.n;
+
+ if (rtnl_talk(&rth, &req.n, ans, MAX_MSG) < 0) {
+ fprintf(stderr, "We have an error talking to the kernel\n");
+ return 1;
+ }
+
+ if (ans && print_action(NULL, &req.n, (void*)stdout) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ return 1;
+ }
+
+ *argc_p = argc;
+ *argv_p = argv;
+bad_val:
+ return ret;
+}
+
+static int tc_action_modify(int cmd, unsigned flags, int *argc_p, char ***argv_p)
+{
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ int ret = 0;
+
+ struct rtattr *tail;
+ struct {
+ struct nlmsghdr n;
+ struct tcamsg t;
+ char buf[MAX_MSG];
+ } req;
+
+ req.t.tca_family = AF_UNSPEC;
+
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcamsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST|flags;
+ req.n.nlmsg_type = cmd;
+ tail = NLMSG_TAIL(&req.n);
+ argc -=1;
+ argv +=1;
+ if (parse_action(&argc, &argv, TCA_ACT_TAB, &req.n)) {
+ fprintf(stderr, "Illegal \"action\"\n");
+ return -1;
+ }
+ tail->rta_len = (void *) NLMSG_TAIL(&req.n) - (void *) tail;
+
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0) {
+ fprintf(stderr, "We have an error talking to the kernel\n");
+ ret = -1;
+ }
+
+ *argc_p = argc;
+ *argv_p = argv;
+
+ return ret;
+}
+
+static int tc_act_list_or_flush(int argc, char **argv, int event)
+{
+ int ret = 0, prio = 0, msg_size = 0;
+ char k[16];
+ struct rtattr *tail,*tail2;
+ struct action_util *a = NULL;
+ struct {
+ struct nlmsghdr n;
+ struct tcamsg t;
+ char buf[MAX_MSG];
+ } req;
+
+ req.t.tca_family = AF_UNSPEC;
+
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcamsg));
+
+ tail = NLMSG_TAIL(&req.n);
+ addattr_l(&req.n, MAX_MSG, TCA_ACT_TAB, NULL, 0);
+ tail2 = NLMSG_TAIL(&req.n);
+
+ strncpy(k, *argv, sizeof (k) - 1);
+#ifdef CONFIG_GACT
+ if (!gact_ld) {
+ get_action_kind("gact");
+ }
+#endif
+ a = get_action_kind(k);
+ if (NULL == a) {
+ fprintf(stderr,"bad action %s\n",k);
+ goto bad_val;
+ }
+ if (strcmp(a->id, k) != 0) {
+ fprintf(stderr,"bad action %s\n",k);
+ goto bad_val;
+ }
+ strncpy(k, *argv, sizeof (k) - 1);
+
+ addattr_l(&req.n, MAX_MSG, ++prio, NULL, 0);
+ addattr_l(&req.n, MAX_MSG, TCA_ACT_KIND, k, strlen(k) + 1);
+ tail2->rta_len = (void *) NLMSG_TAIL(&req.n) - (void *) tail2;
+ tail->rta_len = (void *) NLMSG_TAIL(&req.n) - (void *) tail;
+
+ msg_size = NLMSG_ALIGN(req.n.nlmsg_len) - NLMSG_ALIGN(sizeof(struct nlmsghdr));
+
+ if (event == RTM_GETACTION) {
+ if (rtnl_dump_request(&rth, event, (void *)&req.t, msg_size) < 0) {
+ perror("Cannot send dump request");
+ return 1;
+ }
+ ret = rtnl_dump_filter(&rth, print_action, stdout);
+ }
+
+ if (event == RTM_DELACTION) {
+ req.n.nlmsg_len = NLMSG_ALIGN(req.n.nlmsg_len);
+ req.n.nlmsg_type = RTM_DELACTION;
+ req.n.nlmsg_flags |= NLM_F_ROOT;
+ req.n.nlmsg_flags |= NLM_F_REQUEST;
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0) {
+ fprintf(stderr, "We have an error flushing\n");
+ return 1;
+ }
+
+ }
+
+bad_val:
+
+ return ret;
+}
+
+int do_action(int argc, char **argv)
+{
+
+ int ret = 0;
+
+ while (argc > 0) {
+
+ if (matches(*argv, "add") == 0) {
+ ret = tc_action_modify(RTM_NEWACTION, NLM_F_EXCL|NLM_F_CREATE, &argc, &argv);
+ } else if (matches(*argv, "change") == 0 ||
+ matches(*argv, "replace") == 0) {
+ ret = tc_action_modify(RTM_NEWACTION, NLM_F_CREATE|NLM_F_REPLACE, &argc, &argv);
+ } else if (matches(*argv, "delete") == 0) {
+ argc -=1;
+ argv +=1;
+ ret = tc_action_gd(RTM_DELACTION, 0, &argc, &argv);
+ } else if (matches(*argv, "get") == 0) {
+ argc -=1;
+ argv +=1;
+ ret = tc_action_gd(RTM_GETACTION, 0, &argc, &argv);
+ } else if (matches(*argv, "list") == 0 || matches(*argv, "show") == 0
+ || matches(*argv, "lst") == 0) {
+ if (argc <= 2) {
+ act_usage();
+ return -1;
+ }
+ return tc_act_list_or_flush(argc-2, argv+2, RTM_GETACTION);
+ } else if (matches(*argv, "flush") == 0) {
+ if (argc <= 2) {
+ act_usage();
+ return -1;
+ }
+ return tc_act_list_or_flush(argc-2, argv+2, RTM_DELACTION);
+ } else if (matches(*argv, "help") == 0) {
+ act_usage();
+ return -1;
+ } else {
+
+ ret = -1;
+ }
+
+ if (ret < 0) {
+ fprintf(stderr, "Command \"%s\" is unknown, try \"tc actions help\".\n", *argv);
+ return -1;
+ }
+ }
+
+ return 0;
+}
diff --git a/iproute2/tc/m_bpf.c b/iproute2/tc/m_bpf.c
new file mode 100644
index 0000000..c5e2fa5
--- /dev/null
+++ b/iproute2/tc/m_bpf.c
@@ -0,0 +1,205 @@
+/*
+ * m_bpf.c BPF based action module
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Jiri Pirko <jiri@resnulli.us>
+ * Daniel Borkmann <daniel@iogearbox.net>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+
+#include <linux/bpf.h>
+#include <linux/tc_act/tc_bpf.h>
+
+#include "utils.h"
+#include "tc_util.h"
+#include "tc_bpf.h"
+
+static const enum bpf_prog_type bpf_type = BPF_PROG_TYPE_SCHED_ACT;
+
+static const int nla_tbl[BPF_NLA_MAX] = {
+ [BPF_NLA_OPS_LEN] = TCA_ACT_BPF_OPS_LEN,
+ [BPF_NLA_OPS] = TCA_ACT_BPF_OPS,
+ [BPF_NLA_FD] = TCA_ACT_BPF_FD,
+ [BPF_NLA_NAME] = TCA_ACT_BPF_NAME,
+};
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... bpf ... [ index INDEX ]\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "BPF use case:\n");
+ fprintf(stderr, " bytecode BPF_BYTECODE\n");
+ fprintf(stderr, " bytecode-file FILE\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "eBPF use case:\n");
+ fprintf(stderr, " object-file FILE [ section ACT_NAME ] [ export UDS_FILE ]");
+ fprintf(stderr, " [ verbose ]\n");
+ fprintf(stderr, " object-pinned FILE\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "Where BPF_BYTECODE := \'s,c t f k,c t f k,c t f k,...\'\n");
+ fprintf(stderr, "c,t,f,k and s are decimals; s denotes number of 4-tuples\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "Where FILE points to a file containing the BPF_BYTECODE string,\n");
+ fprintf(stderr, "an ELF file containing eBPF map definitions and bytecode, or a\n");
+ fprintf(stderr, "pinned eBPF program.\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "Where ACT_NAME refers to the section name containing the\n");
+ fprintf(stderr, "action (default \'%s\').\n", bpf_default_section(bpf_type));
+ fprintf(stderr, "\n");
+ fprintf(stderr, "Where UDS_FILE points to a unix domain socket file in order\n");
+ fprintf(stderr, "to hand off control of all created eBPF maps to an agent.\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, "Where optionally INDEX points to an existing action, or\n");
+ fprintf(stderr, "explicitly specifies an action index upon creation.\n");
+}
+
+static int bpf_parse_opt(struct action_util *a, int *ptr_argc, char ***ptr_argv,
+ int tca_id, struct nlmsghdr *n)
+{
+ const char *bpf_obj = NULL, *bpf_uds_name = NULL;
+ struct tc_act_bpf parm;
+ bool seen_run = false;
+ struct rtattr *tail;
+ int argc, ret = 0;
+ char **argv;
+
+ argv = *ptr_argv;
+ argc = *ptr_argc;
+
+ if (matches(*argv, "bpf") != 0)
+ return -1;
+
+ NEXT_ARG();
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, MAX_MSG, tca_id, NULL, 0);
+
+ while (argc > 0) {
+ if (matches(*argv, "run") == 0) {
+ NEXT_ARG();
+opt_bpf:
+ seen_run = true;
+ if (bpf_parse_common(&argc, &argv, nla_tbl, bpf_type,
+ &bpf_obj, &bpf_uds_name, n)) {
+ fprintf(stderr, "Failed to retrieve (e)BPF data!\n");
+ return -1;
+ }
+ } else if (matches(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else if (matches(*argv, "index") == 0) {
+ break;
+ } else {
+ if (!seen_run)
+ goto opt_bpf;
+ break;
+ }
+
+ NEXT_ARG_FWD();
+ }
+
+ memset(&parm, 0, sizeof(parm));
+ parm.action = TC_ACT_PIPE;
+
+ if (argc) {
+ if (matches(*argv, "reclassify") == 0) {
+ parm.action = TC_ACT_RECLASSIFY;
+ NEXT_ARG_FWD();
+ } else if (matches(*argv, "pipe") == 0) {
+ parm.action = TC_ACT_PIPE;
+ NEXT_ARG_FWD();
+ } else if (matches(*argv, "drop") == 0 ||
+ matches(*argv, "shot") == 0) {
+ parm.action = TC_ACT_SHOT;
+ NEXT_ARG_FWD();
+ } else if (matches(*argv, "continue") == 0) {
+ parm.action = TC_ACT_UNSPEC;
+ NEXT_ARG_FWD();
+ } else if (matches(*argv, "pass") == 0 ||
+ matches(*argv, "ok") == 0) {
+ parm.action = TC_ACT_OK;
+ NEXT_ARG_FWD();
+ }
+ }
+
+ if (argc) {
+ if (matches(*argv, "index") == 0) {
+ NEXT_ARG();
+ if (get_u32(&parm.index, *argv, 10)) {
+ fprintf(stderr, "bpf: Illegal \"index\"\n");
+ return -1;
+ }
+
+ NEXT_ARG_FWD();
+ }
+ }
+
+ addattr_l(n, MAX_MSG, TCA_ACT_BPF_PARMS, &parm, sizeof(parm));
+ tail->rta_len = (char *)NLMSG_TAIL(n) - (char *)tail;
+
+ if (bpf_uds_name)
+ ret = bpf_send_map_fds(bpf_uds_name, bpf_obj);
+
+ *ptr_argc = argc;
+ *ptr_argv = argv;
+
+ return ret;
+}
+
+static int bpf_print_opt(struct action_util *au, FILE *f, struct rtattr *arg)
+{
+ struct rtattr *tb[TCA_ACT_BPF_MAX + 1];
+ struct tc_act_bpf *parm;
+ SPRINT_BUF(action_buf);
+
+ if (arg == NULL)
+ return -1;
+
+ parse_rtattr_nested(tb, TCA_ACT_BPF_MAX, arg);
+
+ if (!tb[TCA_ACT_BPF_PARMS]) {
+ fprintf(f, "[NULL bpf parameters]");
+ return -1;
+ }
+
+ parm = RTA_DATA(tb[TCA_ACT_BPF_PARMS]);
+ fprintf(f, "bpf ");
+
+ if (tb[TCA_ACT_BPF_NAME])
+ fprintf(f, "%s ", rta_getattr_str(tb[TCA_ACT_BPF_NAME]));
+ else if (tb[TCA_ACT_BPF_FD])
+ fprintf(f, "pfd %u ", rta_getattr_u32(tb[TCA_ACT_BPF_FD]));
+
+ if (tb[TCA_ACT_BPF_OPS] && tb[TCA_ACT_BPF_OPS_LEN]) {
+ bpf_print_ops(f, tb[TCA_ACT_BPF_OPS],
+ rta_getattr_u16(tb[TCA_ACT_BPF_OPS_LEN]));
+ fprintf(f, " ");
+ }
+
+ fprintf(f, "default-action %s\n", action_n2a(parm->action, action_buf,
+ sizeof(action_buf)));
+ fprintf(f, "\tindex %d ref %d bind %d", parm->index, parm->refcnt,
+ parm->bindcnt);
+
+ if (show_stats) {
+ if (tb[TCA_ACT_BPF_TM]) {
+ struct tcf_t *tm = RTA_DATA(tb[TCA_ACT_BPF_TM]);
+ print_tm(f, tm);
+ }
+ }
+
+ fprintf(f, "\n ");
+ return 0;
+}
+
+struct action_util bpf_action_util = {
+ .id = "bpf",
+ .parse_aopt = bpf_parse_opt,
+ .print_aopt = bpf_print_opt,
+};
diff --git a/iproute2/tc/m_connmark.c b/iproute2/tc/m_connmark.c
new file mode 100644
index 0000000..6974c9b
--- /dev/null
+++ b/iproute2/tc/m_connmark.c
@@ -0,0 +1,166 @@
+/*
+ * m_connmark.c Connection tracking marking import
+ *
+ * Copyright (c) 2011 Felix Fietkau <nbd@openwrt.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, see <http://www.gnu.org/licenses>.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include "utils.h"
+#include "tc_util.h"
+#include <linux/tc_act/tc_connmark.h>
+
+static void
+explain(void)
+{
+ fprintf(stderr, "Usage: ... connmark [zone ZONE] [BRANCH] [index <INDEX>]\n");
+ fprintf(stderr, "where :\n"
+ "\tZONE is the conntrack zone\n"
+ "\tBRANCH := reclassify|pipe|drop|continue|ok\n");
+}
+
+static void
+usage(void)
+{
+ explain();
+ exit(-1);
+}
+
+static int
+parse_connmark(struct action_util *a, int *argc_p, char ***argv_p, int tca_id,
+ struct nlmsghdr *n)
+{
+ struct tc_connmark sel = {};
+ char **argv = *argv_p;
+ int argc = *argc_p;
+ int ok = 0;
+ struct rtattr *tail;
+
+ while (argc > 0) {
+ if (matches(*argv, "connmark") == 0) {
+ ok = 1;
+ argc--;
+ argv++;
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ } else {
+ break;
+ }
+
+ }
+
+ if (!ok) {
+ explain();
+ return -1;
+ }
+
+ if (argc) {
+ if (matches(*argv, "zone") == 0) {
+ NEXT_ARG();
+ if (get_u16(&sel.zone, *argv, 10)) {
+ fprintf(stderr, "simple: Illegal \"index\"\n");
+ return -1;
+ }
+ argc--;
+ argv++;
+ }
+ }
+
+ sel.action = TC_ACT_PIPE;
+ if (argc) {
+ if (matches(*argv, "reclassify") == 0) {
+ sel.action = TC_ACT_RECLASSIFY;
+ argc--;
+ argv++;
+ } else if (matches(*argv, "pipe") == 0) {
+ sel.action = TC_ACT_PIPE;
+ argc--;
+ argv++;
+ } else if (matches(*argv, "drop") == 0 ||
+ matches(*argv, "shot") == 0) {
+ sel.action = TC_ACT_SHOT;
+ argc--;
+ argv++;
+ } else if (matches(*argv, "continue") == 0) {
+ sel.action = TC_ACT_UNSPEC;
+ argc--;
+ argv++;
+ } else if (matches(*argv, "pass") == 0) {
+ sel.action = TC_ACT_OK;
+ argc--;
+ argv++;
+ }
+ }
+
+ if (argc) {
+ if (matches(*argv, "index") == 0) {
+ NEXT_ARG();
+ if (get_u32(&sel.index, *argv, 10)) {
+ fprintf(stderr, "simple: Illegal \"index\"\n");
+ return -1;
+ }
+ argc--;
+ argv++;
+ }
+ }
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, MAX_MSG, tca_id, NULL, 0);
+ addattr_l(n, MAX_MSG, TCA_CONNMARK_PARMS, &sel, sizeof(sel));
+ tail->rta_len = (char *)NLMSG_TAIL(n) - (char *)tail;
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return 0;
+}
+
+static int print_connmark(struct action_util *au, FILE *f, struct rtattr *arg)
+{
+ struct rtattr *tb[TCA_CONNMARK_MAX + 1];
+ struct tc_connmark *ci;
+
+ if (arg == NULL)
+ return -1;
+
+ parse_rtattr_nested(tb, TCA_CONNMARK_MAX, arg);
+ if (tb[TCA_CONNMARK_PARMS] == NULL) {
+ fprintf(f, "[NULL connmark parameters]");
+ return -1;
+ }
+
+ ci = RTA_DATA(tb[TCA_CONNMARK_PARMS]);
+
+ fprintf(f, " connmark zone %d\n", ci->zone);
+ fprintf(f, "\t index %d ref %d bind %d", ci->index,
+ ci->refcnt, ci->bindcnt);
+
+ if (show_stats) {
+ if (tb[TCA_CONNMARK_TM]) {
+ struct tcf_t *tm = RTA_DATA(tb[TCA_CONNMARK_TM]);
+ print_tm(f, tm);
+ }
+ }
+ fprintf(f, "\n");
+
+ return 0;
+}
+
+struct action_util connmark_action_util = {
+ .id = "connmark",
+ .parse_aopt = parse_connmark,
+ .print_aopt = print_connmark,
+};
diff --git a/iproute2/tc/m_csum.c b/iproute2/tc/m_csum.c
new file mode 100644
index 0000000..f7da6f0
--- /dev/null
+++ b/iproute2/tc/m_csum.c
@@ -0,0 +1,246 @@
+/*
+ * m_csum.c checksum updating action
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Gregoire Baron <baronchon@n7mm.org>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <linux/tc_act/tc_csum.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static void
+explain(void)
+{
+ fprintf(stderr, "Usage: ... csum <UPDATE>\n"
+ "Where: UPDATE := <TARGET> [<UPDATE>]\n"
+ " TARGET := { ip4h | icmp | igmp |"
+ " tcp | udp | udplite | <SWEETS> }\n"
+ " SWEETS := { and | or | \'+\' }\n");
+}
+
+static void
+usage(void)
+{
+ explain();
+ exit(-1);
+}
+
+static int
+parse_csum_args(int *argc_p, char ***argv_p, struct tc_csum *sel)
+{
+ int argc = *argc_p;
+ char **argv = *argv_p;
+
+ if (argc <= 0)
+ return -1;
+
+ while(argc > 0) {
+ if ((matches(*argv, "iph") == 0) ||
+ (matches(*argv, "ip4h") == 0) ||
+ (matches(*argv, "ipv4h") == 0))
+ sel->update_flags |= TCA_CSUM_UPDATE_FLAG_IPV4HDR;
+
+ else if (matches(*argv, "icmp") == 0)
+ sel->update_flags |= TCA_CSUM_UPDATE_FLAG_ICMP;
+
+ else if (matches(*argv, "igmp") == 0)
+ sel->update_flags |= TCA_CSUM_UPDATE_FLAG_IGMP;
+
+ else if (matches(*argv, "tcp") == 0)
+ sel->update_flags |= TCA_CSUM_UPDATE_FLAG_TCP;
+
+ else if (matches(*argv, "udp") == 0)
+ sel->update_flags |= TCA_CSUM_UPDATE_FLAG_UDP;
+
+ else if (matches(*argv, "udplite") == 0)
+ sel->update_flags |= TCA_CSUM_UPDATE_FLAG_UDPLITE;
+
+ else if ((matches(*argv, "and") == 0) ||
+ (matches(*argv, "or") == 0) ||
+ (matches(*argv, "+") == 0))
+ ; /* just ignore: ... csum iph and tcp or udp */
+ else
+ break;
+ argc--;
+ argv++;
+ }
+
+ *argc_p = argc;
+ *argv_p = argv;
+
+ return 0;
+}
+
+static int
+parse_csum(struct action_util *a, int *argc_p,
+ char ***argv_p, int tca_id, struct nlmsghdr *n)
+{
+ struct tc_csum sel;
+
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ int ok = 0;
+ struct rtattr *tail;
+
+ memset(&sel, 0, sizeof(sel));
+
+ while (argc > 0) {
+ if (matches(*argv, "csum") == 0) {
+ NEXT_ARG();
+ if (parse_csum_args(&argc, &argv, &sel)) {
+ fprintf(stderr, "Illegal csum construct (%s)\n",
+ *argv);
+ explain();
+ return -1;
+ }
+ ok++;
+ continue;
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ }
+ else {
+ break;
+ }
+ }
+
+ if (!ok) {
+ explain();
+ return -1;
+ }
+
+ if (sel.update_flags == 0) {
+ fprintf(stderr, "Illegal csum construct, empty <UPDATE> list\n");
+ return -1;
+ }
+
+ if (argc) {
+ if (matches(*argv, "reclassify") == 0) {
+ sel.action = TC_ACT_RECLASSIFY;
+ argc--;
+ argv++;
+ } else if (matches(*argv, "pipe") == 0) {
+ sel.action = TC_ACT_PIPE;
+ argc--;
+ argv++;
+ } else if (matches(*argv, "drop") == 0 ||
+ matches(*argv, "shot") == 0) {
+ sel.action = TC_ACT_SHOT;
+ argc--;
+ argv++;
+ } else if (matches(*argv, "continue") == 0) {
+ sel.action = TC_ACT_UNSPEC;
+ argc--;
+ argv++;
+ } else if (matches(*argv, "pass") == 0) {
+ sel.action = TC_ACT_OK;
+ argc--;
+ argv++;
+ }
+ }
+
+ if (argc) {
+ if (matches(*argv, "index") == 0) {
+ NEXT_ARG();
+ if (get_u32(&sel.index, *argv, 10)) {
+ fprintf(stderr, "Illegal \"index\" (%s) <csum>\n",
+ *argv);
+ return -1;
+ }
+ argc--;
+ argv++;
+ }
+ }
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, MAX_MSG, tca_id, NULL, 0);
+ addattr_l(n, MAX_MSG, TCA_CSUM_PARMS, &sel, sizeof(sel));
+ tail->rta_len = (char *)NLMSG_TAIL(n) - (char *)tail;
+
+ *argc_p = argc;
+ *argv_p = argv;
+
+ return 0;
+}
+
+static int
+print_csum(struct action_util *au, FILE * f, struct rtattr *arg)
+{
+ struct tc_csum *sel;
+
+ struct rtattr *tb[TCA_CSUM_MAX + 1];
+
+ char *uflag_1 = "";
+ char *uflag_2 = "";
+ char *uflag_3 = "";
+ char *uflag_4 = "";
+ char *uflag_5 = "";
+ char *uflag_6 = "";
+ SPRINT_BUF(action_buf);
+
+ int uflag_count = 0;
+
+ if (arg == NULL)
+ return -1;
+
+ parse_rtattr_nested(tb, TCA_CSUM_MAX, arg);
+
+ if (tb[TCA_CSUM_PARMS] == NULL) {
+ fprintf(f, "[NULL csum parameters]");
+ return -1;
+ }
+ sel = RTA_DATA(tb[TCA_CSUM_PARMS]);
+
+ if (sel->update_flags & TCA_CSUM_UPDATE_FLAG_IPV4HDR) {
+ uflag_1 = "iph";
+ uflag_count++;
+ }
+ #define CSUM_UFLAG_BUFFER(flag_buffer, flag_value, flag_string) \
+ do { \
+ if (sel->update_flags & flag_value) { \
+ flag_buffer = uflag_count > 0 ? \
+ ", " flag_string : flag_string; \
+ uflag_count++; \
+ } \
+ } while(0)
+ CSUM_UFLAG_BUFFER(uflag_2, TCA_CSUM_UPDATE_FLAG_ICMP, "icmp");
+ CSUM_UFLAG_BUFFER(uflag_3, TCA_CSUM_UPDATE_FLAG_IGMP, "igmp");
+ CSUM_UFLAG_BUFFER(uflag_4, TCA_CSUM_UPDATE_FLAG_TCP, "tcp");
+ CSUM_UFLAG_BUFFER(uflag_5, TCA_CSUM_UPDATE_FLAG_UDP, "udp");
+ CSUM_UFLAG_BUFFER(uflag_6, TCA_CSUM_UPDATE_FLAG_UDPLITE, "udplite");
+ if (!uflag_count) {
+ uflag_1 = "?empty";
+ }
+
+ fprintf(f, "csum (%s%s%s%s%s%s) action %s\n",
+ uflag_1, uflag_2, uflag_3,
+ uflag_4, uflag_5, uflag_6,
+ action_n2a(sel->action, action_buf, sizeof(action_buf)));
+ fprintf(f, "\tindex %d ref %d bind %d", sel->index, sel->refcnt, sel->bindcnt);
+
+ if (show_stats) {
+ if (tb[TCA_CSUM_TM]) {
+ struct tcf_t *tm = RTA_DATA(tb[TCA_CSUM_TM]);
+ print_tm(f,tm);
+ }
+ }
+ fprintf(f, "\n");
+
+ return 0;
+}
+
+struct action_util csum_action_util = {
+ .id = "csum",
+ .parse_aopt = parse_csum,
+ .print_aopt = print_csum,
+};
diff --git a/iproute2/tc/m_ematch.c b/iproute2/tc/m_ematch.c
new file mode 100644
index 0000000..4c3acf8
--- /dev/null
+++ b/iproute2/tc/m_ematch.c
@@ -0,0 +1,570 @@
+/*
+ * m_ematch.c Extended Matches
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Thomas Graf <tgraf@suug.ch>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <dlfcn.h>
+#include <stdarg.h>
+#include <errno.h>
+
+#include "utils.h"
+#include "tc_util.h"
+#include "m_ematch.h"
+
+#define EMATCH_MAP "/etc/iproute2/ematch_map"
+
+static struct ematch_util *ematch_list;
+
+/* export to bison parser */
+int ematch_argc;
+char **ematch_argv;
+char *ematch_err = NULL;
+struct ematch *ematch_root;
+
+static int begin_argc;
+static char **begin_argv;
+
+static inline void map_warning(int num, char *kind)
+{
+ fprintf(stderr,
+ "Error: Unable to find ematch \"%s\" in %s\n" \
+ "Please assign a unique ID to the ematch kind the suggested " \
+ "entry is:\n" \
+ "\t%d\t%s\n",
+ kind, EMATCH_MAP, num, kind);
+}
+
+static int lookup_map(__u16 num, char *dst, int len, const char *file)
+{
+ int err = -EINVAL;
+ char buf[512];
+ FILE *fd = fopen(file, "r");
+
+ if (fd == NULL)
+ return -errno;
+
+ while (fgets(buf, sizeof(buf), fd)) {
+ char namebuf[512], *p = buf;
+ int id;
+
+ while (*p == ' ' || *p == '\t')
+ p++;
+ if (*p == '#' || *p == '\n' || *p == 0)
+ continue;
+
+ if (sscanf(p, "%d %s", &id, namebuf) != 2) {
+ fprintf(stderr, "ematch map %s corrupted at %s\n",
+ file, p);
+ goto out;
+ }
+
+ if (id == num) {
+ if (dst)
+ strncpy(dst, namebuf, len - 1);
+ err = 0;
+ goto out;
+ }
+ }
+
+ err = -ENOENT;
+out:
+ fclose(fd);
+ return err;
+}
+
+static int lookup_map_id(char *kind, int *dst, const char *file)
+{
+ int err = -EINVAL;
+ char buf[512];
+ FILE *fd = fopen(file, "r");
+
+ if (fd == NULL)
+ return -errno;
+
+ while (fgets(buf, sizeof(buf), fd)) {
+ char namebuf[512], *p = buf;
+ int id;
+
+ while (*p == ' ' || *p == '\t')
+ p++;
+ if (*p == '#' || *p == '\n' || *p == 0)
+ continue;
+
+ if (sscanf(p, "%d %s", &id, namebuf) != 2) {
+ fprintf(stderr, "ematch map %s corrupted at %s\n",
+ file, p);
+ goto out;
+ }
+
+ if (!strcasecmp(namebuf, kind)) {
+ if (dst)
+ *dst = id;
+ err = 0;
+ goto out;
+ }
+ }
+
+ err = -ENOENT;
+ *dst = 0;
+out:
+ fclose(fd);
+ return err;
+}
+
+static struct ematch_util *get_ematch_kind(char *kind)
+{
+ static void *body;
+ void *dlh;
+ char buf[256];
+ struct ematch_util *e;
+
+ for (e = ematch_list; e; e = e->next) {
+ if (strcmp(e->kind, kind) == 0)
+ return e;
+ }
+
+ snprintf(buf, sizeof(buf), "em_%s.so", kind);
+ dlh = dlopen(buf, RTLD_LAZY);
+ if (dlh == NULL) {
+ dlh = body;
+ if (dlh == NULL) {
+ dlh = body = dlopen(NULL, RTLD_LAZY);
+ if (dlh == NULL)
+ return NULL;
+ }
+ }
+
+ snprintf(buf, sizeof(buf), "%s_ematch_util", kind);
+ e = dlsym(dlh, buf);
+ if (e == NULL)
+ return NULL;
+
+ e->next = ematch_list;
+ ematch_list = e;
+
+ return e;
+}
+
+static struct ematch_util *get_ematch_kind_num(__u16 kind)
+{
+ char name[32];
+
+ if (lookup_map(kind, name, sizeof(name), EMATCH_MAP) < 0)
+ return NULL;
+
+ return get_ematch_kind(name);
+}
+
+static int parse_tree(struct nlmsghdr *n, struct ematch *tree)
+{
+ int index = 1;
+ struct ematch *t;
+
+ for (t = tree; t; t = t->next) {
+ struct rtattr *tail = NLMSG_TAIL(n);
+ struct tcf_ematch_hdr hdr = {
+ .flags = t->relation
+ };
+
+ if (t->inverted)
+ hdr.flags |= TCF_EM_INVERT;
+
+ addattr_l(n, MAX_MSG, index++, NULL, 0);
+
+ if (t->child) {
+ __u32 r = t->child_ref;
+ addraw_l(n, MAX_MSG, &hdr, sizeof(hdr));
+ addraw_l(n, MAX_MSG, &r, sizeof(r));
+ } else {
+ int num = 0, err;
+ char buf[64];
+ struct ematch_util *e;
+
+ if (t->args == NULL)
+ return -1;
+
+ strncpy(buf, (char*) t->args->data, sizeof(buf)-1);
+ e = get_ematch_kind(buf);
+ if (e == NULL) {
+ fprintf(stderr, "Unknown ematch \"%s\"\n",
+ buf);
+ return -1;
+ }
+
+ err = lookup_map_id(buf, &num, EMATCH_MAP);
+ if (err < 0) {
+ if (err == -ENOENT)
+ map_warning(e->kind_num, buf);
+ return err;
+ }
+
+ hdr.kind = num;
+ if (e->parse_eopt(n, &hdr, t->args->next) < 0)
+ return -1;
+ }
+
+ tail->rta_len = (void*) NLMSG_TAIL(n) - (void*) tail;
+ }
+
+ return 0;
+}
+
+static int flatten_tree(struct ematch *head, struct ematch *tree)
+{
+ int i, count = 0;
+ struct ematch *t;
+
+ for (;;) {
+ count++;
+
+ if (tree->child) {
+ for (t = head; t->next; t = t->next);
+ t->next = tree->child;
+ count += flatten_tree(head, tree->child);
+ }
+
+ if (tree->relation == 0)
+ break;
+
+ tree = tree->next;
+ }
+
+ for (i = 0, t = head; t; t = t->next, i++)
+ t->index = i;
+
+ for (t = head; t; t = t->next)
+ if (t->child)
+ t->child_ref = t->child->index;
+
+ return count;
+}
+
+int em_parse_error(int err, struct bstr *args, struct bstr *carg,
+ struct ematch_util *e, char *fmt, ...)
+{
+ va_list a;
+
+ va_start(a, fmt);
+ vfprintf(stderr, fmt, a);
+ va_end(a);
+
+ if (ematch_err)
+ fprintf(stderr, ": %s\n... ", ematch_err);
+ else
+ fprintf(stderr, "\n... ");
+
+ while (ematch_argc < begin_argc) {
+ if (ematch_argc == (begin_argc - 1))
+ fprintf(stderr, ">>%s<< ", *begin_argv);
+ else
+ fprintf(stderr, "%s ", *begin_argv);
+ begin_argv++;
+ begin_argc--;
+ }
+
+ fprintf(stderr, "...\n");
+
+ if (args) {
+ fprintf(stderr, "... %s(", e->kind);
+ while (args) {
+ fprintf(stderr, "%s", args == carg ? ">>" : "");
+ bstr_print(stderr, args, 1);
+ fprintf(stderr, "%s%s", args == carg ? "<<" : "",
+ args->next ? " " : "");
+ args = args->next;
+ }
+ fprintf(stderr, ")...\n");
+
+ }
+
+ if (e == NULL) {
+ fprintf(stderr,
+ "Usage: EXPR\n" \
+ "where: EXPR := TERM [ { and | or } EXPR ]\n" \
+ " TERM := [ not ] { MATCH | '(' EXPR ')' }\n" \
+ " MATCH := module '(' ARGS ')'\n" \
+ " ARGS := ARG1 ARG2 ...\n" \
+ "\n" \
+ "Example: a(x y) and not (b(x) or c(x y z))\n");
+ } else
+ e->print_usage(stderr);
+
+ return -err;
+}
+
+static inline void free_ematch_err(void)
+{
+ if (ematch_err) {
+ free(ematch_err);
+ ematch_err = NULL;
+ }
+}
+
+extern int ematch_parse(void);
+
+int parse_ematch(int *argc_p, char ***argv_p, int tca_id, struct nlmsghdr *n)
+{
+ begin_argc = ematch_argc = *argc_p;
+ begin_argv = ematch_argv = *argv_p;
+
+ if (ematch_parse()) {
+ int err = em_parse_error(EINVAL, NULL, NULL, NULL,
+ "Parse error");
+ free_ematch_err();
+ return err;
+ }
+
+ free_ematch_err();
+
+ /* undo look ahead by parser */
+ ematch_argc++;
+ ematch_argv--;
+
+ if (ematch_root) {
+ struct rtattr *tail, *tail_list;
+
+ struct tcf_ematch_tree_hdr hdr = {
+ .nmatches = flatten_tree(ematch_root, ematch_root),
+ .progid = TCF_EM_PROG_TC
+ };
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, MAX_MSG, tca_id, NULL, 0);
+ addattr_l(n, MAX_MSG, TCA_EMATCH_TREE_HDR, &hdr, sizeof(hdr));
+
+ tail_list = NLMSG_TAIL(n);
+ addattr_l(n, MAX_MSG, TCA_EMATCH_TREE_LIST, NULL, 0);
+
+ if (parse_tree(n, ematch_root) < 0)
+ return -1;
+
+ tail_list->rta_len = (void*) NLMSG_TAIL(n) - (void*) tail_list;
+ tail->rta_len = (void*) NLMSG_TAIL(n) - (void*) tail;
+ }
+
+ *argc_p = ematch_argc;
+ *argv_p = ematch_argv;
+
+ return 0;
+}
+
+static int print_ematch_seq(FILE *fd, struct rtattr **tb, int start,
+ int prefix)
+{
+ int n, i = start;
+ struct tcf_ematch_hdr *hdr;
+ int dlen;
+ void *data;
+
+ for (;;) {
+ if (tb[i] == NULL)
+ return -1;
+
+ dlen = RTA_PAYLOAD(tb[i]) - sizeof(*hdr);
+ data = (void *) RTA_DATA(tb[i]) + sizeof(*hdr);
+
+ if (dlen < 0)
+ return -1;
+
+ hdr = RTA_DATA(tb[i]);
+
+ if (hdr->flags & TCF_EM_INVERT)
+ fprintf(fd, "NOT ");
+
+ if (hdr->kind == 0) {
+ __u32 ref;
+
+ if (dlen < sizeof(__u32))
+ return -1;
+
+ ref = *(__u32 *) data;
+ fprintf(fd, "(\n");
+ for (n = 0; n <= prefix; n++)
+ fprintf(fd, " ");
+ if (print_ematch_seq(fd, tb, ref + 1, prefix + 1) < 0)
+ return -1;
+ for (n = 0; n < prefix; n++)
+ fprintf(fd, " ");
+ fprintf(fd, ") ");
+
+ } else {
+ struct ematch_util *e;
+
+ e = get_ematch_kind_num(hdr->kind);
+ if (e == NULL)
+ fprintf(fd, "[unknown ematch %d]\n",
+ hdr->kind);
+ else {
+ fprintf(fd, "%s(", e->kind);
+ if (e->print_eopt(fd, hdr, data, dlen) < 0)
+ return -1;
+ fprintf(fd, ")\n");
+ }
+ if (hdr->flags & TCF_EM_REL_MASK)
+ for (n = 0; n < prefix; n++)
+ fprintf(fd, " ");
+ }
+
+ switch (hdr->flags & TCF_EM_REL_MASK) {
+ case TCF_EM_REL_AND:
+ fprintf(fd, "AND ");
+ break;
+
+ case TCF_EM_REL_OR:
+ fprintf(fd, "OR ");
+ break;
+
+ default:
+ return 0;
+ }
+
+ i++;
+ }
+
+ return 0;
+}
+
+static int print_ematch_list(FILE *fd, struct tcf_ematch_tree_hdr *hdr,
+ struct rtattr *rta)
+{
+ int err = -1;
+ struct rtattr **tb;
+
+ tb = malloc((hdr->nmatches + 1) * sizeof(struct rtattr *));
+ if (tb == NULL)
+ return -1;
+
+ if (hdr->nmatches > 0) {
+ if (parse_rtattr_nested(tb, hdr->nmatches, rta) < 0)
+ goto errout;
+
+ fprintf(fd, "\n ");
+ if (print_ematch_seq(fd, tb, 1, 1) < 0)
+ goto errout;
+ }
+
+ err = 0;
+errout:
+ free(tb);
+ return err;
+}
+
+int print_ematch(FILE *fd, const struct rtattr *rta)
+{
+ struct rtattr *tb[TCA_EMATCH_TREE_MAX+1];
+ struct tcf_ematch_tree_hdr *hdr;
+
+ if (parse_rtattr_nested(tb, TCA_EMATCH_TREE_MAX, rta) < 0)
+ return -1;
+
+ if (tb[TCA_EMATCH_TREE_HDR] == NULL) {
+ fprintf(stderr, "Missing ematch tree header\n");
+ return -1;
+ }
+
+ if (tb[TCA_EMATCH_TREE_LIST] == NULL) {
+ fprintf(stderr, "Missing ematch tree list\n");
+ return -1;
+ }
+
+ if (RTA_PAYLOAD(tb[TCA_EMATCH_TREE_HDR]) < sizeof(*hdr)) {
+ fprintf(stderr, "Ematch tree header size mismatch\n");
+ return -1;
+ }
+
+ hdr = RTA_DATA(tb[TCA_EMATCH_TREE_HDR]);
+
+ return print_ematch_list(fd, hdr, tb[TCA_EMATCH_TREE_LIST]);
+}
+
+struct bstr * bstr_alloc(const char *text)
+{
+ struct bstr *b = calloc(1, sizeof(*b));
+
+ if (b == NULL)
+ return NULL;
+
+ b->data = strdup(text);
+ if (b->data == NULL) {
+ free(b);
+ return NULL;
+ }
+
+ b->len = strlen(text);
+
+ return b;
+}
+
+unsigned long bstrtoul(const struct bstr *b)
+{
+ char *inv = NULL;
+ unsigned long l;
+ char buf[b->len+1];
+
+ memcpy(buf, b->data, b->len);
+ buf[b->len] = '\0';
+
+ l = strtoul(buf, &inv, 0);
+ if (l == ULONG_MAX || inv == buf)
+ return ULONG_MAX;
+
+ return l;
+}
+
+void bstr_print(FILE *fd, const struct bstr *b, int ascii)
+{
+ int i;
+ char *s = b->data;
+
+ if (ascii)
+ for (i = 0; i < b->len; i++)
+ fprintf(fd, "%c", isprint(s[i]) ? s[i] : '.');
+ else {
+ for (i = 0; i < b->len; i++)
+ fprintf(fd, "%02x", s[i]);
+ fprintf(fd, "\"");
+ for (i = 0; i < b->len; i++)
+ fprintf(fd, "%c", isprint(s[i]) ? s[i] : '.');
+ fprintf(fd, "\"");
+ }
+}
+
+void print_ematch_tree(const struct ematch *tree)
+{
+ const struct ematch *t;
+
+ for (t = tree; t; t = t->next) {
+ if (t->inverted)
+ printf("NOT ");
+
+ if (t->child) {
+ printf("(");
+ print_ematch_tree(t->child);
+ printf(")");
+ } else {
+ struct bstr *b;
+ for (b = t->args; b; b = b->next)
+ printf("%s%s", b->data, b->next ? " " : "");
+ }
+
+ if (t->relation == TCF_EM_REL_AND)
+ printf(" AND ");
+ else if (t->relation == TCF_EM_REL_OR)
+ printf(" OR ");
+ }
+}
diff --git a/iproute2/tc/m_ematch.h b/iproute2/tc/m_ematch.h
new file mode 100644
index 0000000..81456aa
--- /dev/null
+++ b/iproute2/tc/m_ematch.h
@@ -0,0 +1,112 @@
+#ifndef __TC_EMATCH_H_
+#define __TC_EMATCH_H_
+
+#include <ctype.h>
+#include <stdlib.h>
+#include <string.h>
+#include <limits.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+#define EMATCHKINDSIZ 16
+
+struct bstr
+{
+ char *data;
+ unsigned int len;
+ int quoted;
+ struct bstr *next;
+};
+
+extern struct bstr * bstr_alloc(const char *text);
+
+static inline struct bstr * bstr_new(char *data, unsigned int len)
+{
+ struct bstr *b = calloc(1, sizeof(*b));
+
+ if (b == NULL)
+ return NULL;
+
+ b->data = data;
+ b->len = len;
+
+ return b;
+}
+
+static inline int bstrcmp(struct bstr *b, const char *text)
+{
+ int len = strlen(text);
+ int d = b->len - len;
+
+ if (d == 0)
+ return strncmp(b->data, text, len);
+
+ return d;
+}
+
+static inline struct bstr *bstr_next(struct bstr *b)
+{
+ return b->next;
+}
+
+extern unsigned long bstrtoul(const struct bstr *b);
+extern void bstr_print(FILE *fd, const struct bstr *b, int ascii);
+
+
+struct ematch
+{
+ struct bstr *args;
+ int index;
+ int inverted;
+ int relation;
+ int child_ref;
+ struct ematch *child;
+ struct ematch *next;
+};
+
+static inline struct ematch * new_ematch(struct bstr *args, int inverted)
+{
+ struct ematch *e = calloc(1, sizeof(*e));
+
+ if (e == NULL)
+ return NULL;
+
+ e->args = args;
+ e->inverted = inverted;
+
+ return e;
+}
+
+extern void print_ematch_tree(const struct ematch *tree);
+
+
+struct ematch_util
+{
+ char kind[EMATCHKINDSIZ];
+ int kind_num;
+ int (*parse_eopt)(struct nlmsghdr *,struct tcf_ematch_hdr *,
+ struct bstr *);
+ int (*print_eopt)(FILE *, struct tcf_ematch_hdr *, void *, int);
+ void (*print_usage)(FILE *);
+ struct ematch_util *next;
+};
+
+static inline int parse_layer(struct bstr *b)
+{
+ if (*((char *) b->data) == 'l')
+ return TCF_LAYER_LINK;
+ else if (*((char *) b->data) == 'n')
+ return TCF_LAYER_NETWORK;
+ else if (*((char *) b->data) == 't')
+ return TCF_LAYER_TRANSPORT;
+ else
+ return INT_MAX;
+}
+
+extern int em_parse_error(int err, struct bstr *args, struct bstr *carg,
+ struct ematch_util *, char *fmt, ...);
+extern int print_ematch(FILE *, const struct rtattr *);
+extern int parse_ematch(int *, char ***, int, struct nlmsghdr *);
+
+#endif
diff --git a/iproute2/tc/m_estimator.c b/iproute2/tc/m_estimator.c
new file mode 100644
index 0000000..3dc8624
--- /dev/null
+++ b/iproute2/tc/m_estimator.c
@@ -0,0 +1,64 @@
+/*
+ * m_estimator.c Parse/print estimator module options.
+ *
+ * This program is free software; you can u32istribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+#include "tc_common.h"
+
+static void est_help(void);
+
+static void est_help(void)
+{
+ fprintf(stderr, "Usage: ... estimator INTERVAL TIME-CONST\n");
+ fprintf(stderr, " INTERVAL is interval between measurements\n");
+ fprintf(stderr, " TIME-CONST is averaging time constant\n");
+ fprintf(stderr, "Example: ... est 1sec 8sec\n");
+}
+
+int parse_estimator(int *p_argc, char ***p_argv, struct tc_estimator *est)
+{
+ int argc = *p_argc;
+ char **argv = *p_argv;
+ unsigned A, time_const;
+
+ NEXT_ARG();
+ if (est->ewma_log)
+ duparg("estimator", *argv);
+ if (matches(*argv, "help") == 0)
+ est_help();
+ if (get_time(&A, *argv))
+ invarg("estimator", "invalid estimator interval");
+ NEXT_ARG();
+ if (matches(*argv, "help") == 0)
+ est_help();
+ if (get_time(&time_const, *argv))
+ invarg("estimator", "invalid estimator time constant");
+ if (tc_setup_estimator(A, time_const, est) < 0) {
+ fprintf(stderr, "Error: estimator parameters are out of range.\n");
+ return -1;
+ }
+ if (show_raw)
+ fprintf(stderr, "[estimator i=%u e=%u]\n", est->interval, est->ewma_log);
+ *p_argc = argc;
+ *p_argv = argv;
+ return 0;
+}
diff --git a/iproute2/tc/m_gact.c b/iproute2/tc/m_gact.c
new file mode 100644
index 0000000..94bd5e7
--- /dev/null
+++ b/iproute2/tc/m_gact.c
@@ -0,0 +1,255 @@
+/*
+ * m_gact.c generic actions module
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: J Hadi Salim (hadi@cyberus.ca)
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+#include <linux/tc_act/tc_gact.h>
+
+/* define to turn on probablity stuff */
+
+#ifdef CONFIG_GACT_PROB
+static const char *prob_n2a(int p)
+{
+ if (p == PGACT_NONE)
+ return "none";
+ if (p == PGACT_NETRAND)
+ return "netrand";
+ if (p == PGACT_DETERM)
+ return "determ";
+ return "none";
+}
+#endif
+
+static void
+explain(void)
+{
+#ifdef CONFIG_GACT_PROB
+ fprintf(stderr, "Usage: ... gact <ACTION> [RAND] [INDEX]\n");
+ fprintf(stderr,
+ "Where: \tACTION := reclassify | drop | continue | pass \n"
+ "\tRAND := random <RANDTYPE> <ACTION> <VAL>\n"
+ "\tRANDTYPE := netrand | determ\n"
+ "\tVAL : = value not exceeding 10000\n"
+ "\tINDEX := index value used\n"
+ "\n");
+#else
+ fprintf(stderr, "Usage: ... gact <ACTION> [INDEX]\n");
+ fprintf(stderr,
+ "Where: \tACTION := reclassify | drop | continue | pass \n"
+ "\tINDEX := index value used\n"
+ "\n");
+#endif
+}
+
+
+static void
+usage(void)
+{
+ explain();
+ exit(-1);
+}
+
+static int
+get_act(char ***argv_p)
+{
+ char **argv = *argv_p;
+
+ if (matches(*argv, "reclassify") == 0) {
+ return TC_ACT_RECLASSIFY;
+ } else if (matches(*argv, "drop") == 0 || matches(*argv, "shot") == 0) {
+ return TC_ACT_SHOT;
+ } else if (matches(*argv, "continue") == 0) {
+ return TC_ACT_UNSPEC;
+ } else if (matches(*argv, "pipe") == 0) {
+ return TC_ACT_PIPE;
+ } else if (matches(*argv, "pass") == 0 || matches(*argv, "ok") == 0) {
+ return TC_ACT_OK;
+ } else {
+ fprintf(stderr,"bad action type %s\n",*argv);
+ return -10;
+ }
+}
+
+static int
+parse_gact(struct action_util *a, int *argc_p, char ***argv_p,
+ int tca_id, struct nlmsghdr *n)
+{
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ int ok = 0;
+ int action = TC_POLICE_RECLASSIFY;
+ struct tc_gact p;
+#ifdef CONFIG_GACT_PROB
+ int rd = 0;
+ struct tc_gact_p pp;
+#endif
+ struct rtattr *tail;
+
+ memset(&p, 0, sizeof (p));
+ p.action = TC_POLICE_RECLASSIFY;
+
+ if (argc < 0)
+ return -1;
+
+
+ if (matches(*argv, "gact") == 0) {
+ ok++;
+ } else {
+ action = get_act(&argv);
+ if (action != -10) {
+ p.action = action;
+ ok++;
+ } else {
+ explain();
+ return action;
+ }
+ }
+
+ if (ok) {
+ argc--;
+ argv++;
+ }
+
+#ifdef CONFIG_GACT_PROB
+ if (ok && argc > 0) {
+ if (matches(*argv, "random") == 0) {
+ rd = 1;
+ NEXT_ARG();
+ if (matches(*argv, "netrand") == 0) {
+ NEXT_ARG();
+ pp.ptype = PGACT_NETRAND;
+ } else if (matches(*argv, "determ") == 0) {
+ NEXT_ARG();
+ pp.ptype = PGACT_DETERM;
+ } else {
+ fprintf(stderr, "Illegal \"random type\"\n");
+ return -1;
+ }
+
+ action = get_act(&argv);
+ if (action != -10) { /* FIXME */
+ pp.paction = action;
+ } else {
+ explain();
+ return -1;
+ }
+ argc--;
+ argv++;
+ if (get_u16(&pp.pval, *argv, 10)) {
+ fprintf(stderr, "Illegal probability val 0x%x\n",pp.pval);
+ return -1;
+ }
+ if (pp.pval > 10000) {
+ fprintf(stderr, "Illegal probability val 0x%x\n",pp.pval);
+ return -1;
+ }
+ argc--;
+ argv++;
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ }
+ }
+#endif
+
+ if (argc > 0) {
+ if (matches(*argv, "index") == 0) {
+ NEXT_ARG();
+ if (get_u32(&p.index, *argv, 10)) {
+ fprintf(stderr, "Illegal \"index\"\n");
+ return -1;
+ }
+ argc--;
+ argv++;
+ ok++;
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ }
+ }
+
+ if (!ok)
+ return -1;
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, MAX_MSG, tca_id, NULL, 0);
+ addattr_l(n, MAX_MSG, TCA_GACT_PARMS, &p, sizeof (p));
+#ifdef CONFIG_GACT_PROB
+ if (rd) {
+ addattr_l(n, MAX_MSG, TCA_GACT_PROB, &pp, sizeof (pp));
+ }
+#endif
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return 0;
+}
+
+static int
+print_gact(struct action_util *au,FILE * f, struct rtattr *arg)
+{
+ SPRINT_BUF(b1);
+#ifdef CONFIG_GACT_PROB
+ SPRINT_BUF(b2);
+ struct tc_gact_p *pp = NULL;
+ struct tc_gact_p pp_dummy;
+#endif
+ struct tc_gact *p = NULL;
+ struct rtattr *tb[TCA_GACT_MAX + 1];
+
+ if (arg == NULL)
+ return -1;
+
+ parse_rtattr_nested(tb, TCA_GACT_MAX, arg);
+
+ if (tb[TCA_GACT_PARMS] == NULL) {
+ fprintf(f, "[NULL gact parameters]");
+ return -1;
+ }
+ p = RTA_DATA(tb[TCA_GACT_PARMS]);
+
+ fprintf(f, "gact action %s", action_n2a(p->action, b1, sizeof (b1)));
+#ifdef CONFIG_GACT_PROB
+ if (NULL != tb[TCA_GACT_PROB]) {
+ pp = RTA_DATA(tb[TCA_GACT_PROB]);
+ } else {
+ /* need to keep consistent output */
+ memset(&pp_dummy, 0, sizeof (pp_dummy));
+ pp = &pp_dummy;
+ }
+ fprintf(f, "\n\t random type %s %s val %d",prob_n2a(pp->ptype), action_n2a(pp->paction, b2, sizeof (b2)), pp->pval);
+#endif
+ fprintf(f, "\n\t index %d ref %d bind %d",p->index, p->refcnt, p->bindcnt);
+ if (show_stats) {
+ if (tb[TCA_GACT_TM]) {
+ struct tcf_t *tm = RTA_DATA(tb[TCA_GACT_TM]);
+ print_tm(f,tm);
+ }
+ }
+ fprintf(f, "\n ");
+ return 0;
+}
+
+struct action_util gact_action_util = {
+ .id = "gact",
+ .parse_aopt = parse_gact,
+ .print_aopt = print_gact,
+};
diff --git a/iproute2/tc/m_ipt.c b/iproute2/tc/m_ipt.c
new file mode 100644
index 0000000..948becb
--- /dev/null
+++ b/iproute2/tc/m_ipt.c
@@ -0,0 +1,620 @@
+/*
+ * m_ipt.c iptables based targets
+ * utilities mostly ripped from iptables <duh, its the linux way>
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: J Hadi Salim (hadi@cyberus.ca)
+ */
+
+#include <syslog.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <linux/if.h>
+#include <iptables.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv4/ip_tables.h>
+#include "utils.h"
+#include "tc_util.h"
+#include <linux/tc_act/tc_ipt.h>
+#include <stdio.h>
+#include <dlfcn.h>
+#include <getopt.h>
+#include <errno.h>
+#include <string.h>
+#include <netdb.h>
+#include <stdlib.h>
+#include <ctype.h>
+#include <stdarg.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/wait.h>
+
+static const char *pname = "tc-ipt";
+static const char *tname = "mangle";
+static const char *pversion = "0.1";
+
+static const char *ipthooks[] = {
+ "NF_IP_PRE_ROUTING",
+ "NF_IP_LOCAL_IN",
+ "NF_IP_FORWARD",
+ "NF_IP_LOCAL_OUT",
+ "NF_IP_POST_ROUTING",
+};
+
+static struct option original_opts[] = {
+ {"jump", 1, 0, 'j'},
+ {0, 0, 0, 0}
+};
+
+static struct iptables_target *t_list = NULL;
+static struct option *opts = original_opts;
+static unsigned int global_option_offset = 0;
+#define OPTION_OFFSET 256
+
+char *lib_dir;
+
+void
+register_target(struct iptables_target *me)
+{
+/* fprintf(stderr, "\nDummy register_target %s \n", me->name);
+*/
+ me->next = t_list;
+ t_list = me;
+
+}
+
+void
+xtables_register_target(struct iptables_target *me)
+{
+ me->next = t_list;
+ t_list = me;
+}
+
+void
+exit_tryhelp(int status)
+{
+ fprintf(stderr, "Try `%s -h' or '%s --help' for more information.\n",
+ pname, pname);
+ exit(status);
+}
+
+void
+exit_error(enum exittype status, char *msg, ...)
+{
+ va_list args;
+
+ va_start(args, msg);
+ fprintf(stderr, "%s v%s: ", pname, pversion);
+ vfprintf(stderr, msg, args);
+ va_end(args);
+ fprintf(stderr, "\n");
+ if (status == PARAMETER_PROBLEM)
+ exit_tryhelp(status);
+ if (status == VERSION_PROBLEM)
+ fprintf(stderr,
+ "Perhaps iptables or your kernel needs to be upgraded.\n");
+ exit(status);
+}
+
+/* stolen from iptables 1.2.11
+They should really have them as a library so i can link to them
+Email them next time i remember
+*/
+
+char *
+addr_to_dotted(const struct in_addr *addrp)
+{
+ static char buf[20];
+ const unsigned char *bytep;
+
+ bytep = (const unsigned char *) &(addrp->s_addr);
+ sprintf(buf, "%d.%d.%d.%d", bytep[0], bytep[1], bytep[2], bytep[3]);
+ return buf;
+}
+
+int string_to_number_ll(const char *s, unsigned long long min,
+ unsigned long long max,
+ unsigned long long *ret)
+{
+ unsigned long long number;
+ char *end;
+
+ /* Handle hex, octal, etc. */
+ errno = 0;
+ number = strtoull(s, &end, 0);
+ if (*end == '\0' && end != s) {
+ /* we parsed a number, let's see if we want this */
+ if (errno != ERANGE && min <= number && (!max || number <= max)) {
+ *ret = number;
+ return 0;
+ }
+ }
+ return -1;
+}
+
+int string_to_number_l(const char *s, unsigned long min, unsigned long max,
+ unsigned long *ret)
+{
+ int result;
+ unsigned long long number;
+
+ result = string_to_number_ll(s, min, max, &number);
+ *ret = (unsigned long)number;
+
+ return result;
+}
+
+int string_to_number(const char *s, unsigned int min, unsigned int max,
+ unsigned int *ret)
+{
+ int result;
+ unsigned long number;
+
+ result = string_to_number_l(s, min, max, &number);
+ *ret = (unsigned int)number;
+
+ return result;
+}
+
+static void free_opts(struct option *local_opts)
+{
+ if (local_opts != original_opts) {
+ free(local_opts);
+ opts = original_opts;
+ global_option_offset = 0;
+ }
+}
+
+static struct option *
+merge_options(struct option *oldopts, const struct option *newopts,
+ unsigned int *option_offset)
+{
+ struct option *merge;
+ unsigned int num_old, num_new, i;
+
+ for (num_old = 0; oldopts[num_old].name; num_old++) ;
+ for (num_new = 0; newopts[num_new].name; num_new++) ;
+
+ *option_offset = global_option_offset + OPTION_OFFSET;
+
+ merge = malloc(sizeof (struct option) * (num_new + num_old + 1));
+ memcpy(merge, oldopts, num_old * sizeof (struct option));
+ for (i = 0; i < num_new; i++) {
+ merge[num_old + i] = newopts[i];
+ merge[num_old + i].val += *option_offset;
+ }
+ memset(merge + num_old + num_new, 0, sizeof (struct option));
+
+ return merge;
+}
+
+static void *
+fw_calloc(size_t count, size_t size)
+{
+ void *p;
+
+ if ((p = (void *) calloc(count, size)) == NULL) {
+ perror("iptables: calloc failed");
+ exit(1);
+ }
+ return p;
+}
+
+static struct iptables_target *
+find_t(char *name)
+{
+ struct iptables_target *m;
+ for (m = t_list; m; m = m->next) {
+ if (strcmp(m->name, name) == 0)
+ return m;
+ }
+
+ return NULL;
+}
+
+static struct iptables_target *
+get_target_name(const char *name)
+{
+ void *handle;
+ char *error;
+ char *new_name, *lname;
+ struct iptables_target *m;
+ char path[strlen(lib_dir) + sizeof ("/libipt_.so") + strlen(name)];
+
+#ifdef NO_SHARED_LIBS
+ return NULL;
+#endif
+
+ new_name = malloc(strlen(name) + 1);
+ lname = malloc(strlen(name) + 1);
+ if (new_name)
+ memset(new_name, '\0', strlen(name) + 1);
+ else
+ exit_error(PARAMETER_PROBLEM, "get_target_name");
+
+ if (lname)
+ memset(lname, '\0', strlen(name) + 1);
+ else
+ exit_error(PARAMETER_PROBLEM, "get_target_name");
+
+ strcpy(new_name, name);
+ strcpy(lname, name);
+
+ if (isupper(lname[0])) {
+ int i;
+ for (i = 0; i < strlen(name); i++) {
+ lname[i] = tolower(lname[i]);
+ }
+ }
+
+ if (islower(new_name[0])) {
+ int i;
+ for (i = 0; i < strlen(new_name); i++) {
+ new_name[i] = toupper(new_name[i]);
+ }
+ }
+
+ /* try libxt_xx first */
+ sprintf(path, "%s/libxt_%s.so", lib_dir, new_name);
+ handle = dlopen(path, RTLD_LAZY);
+ if (!handle) {
+ /* try libipt_xx next */
+ sprintf(path, "%s/libipt_%s.so", lib_dir, new_name);
+ handle = dlopen(path, RTLD_LAZY);
+
+ if (!handle) {
+ sprintf(path, "%s/libxt_%s.so", lib_dir , lname);
+ handle = dlopen(path, RTLD_LAZY);
+ }
+
+ if (!handle) {
+ sprintf(path, "%s/libipt_%s.so", lib_dir , lname);
+ handle = dlopen(path, RTLD_LAZY);
+ }
+ /* ok, lets give up .. */
+ if (!handle) {
+ fputs(dlerror(), stderr);
+ printf("\n");
+ free(new_name);
+ free(lname);
+ return NULL;
+ }
+ }
+
+ m = dlsym(handle, new_name);
+ if ((error = dlerror()) != NULL) {
+ m = (struct iptables_target *) dlsym(handle, lname);
+ if ((error = dlerror()) != NULL) {
+ m = find_t(new_name);
+ if (NULL == m) {
+ m = find_t(lname);
+ if (NULL == m) {
+ fputs(error, stderr);
+ fprintf(stderr, "\n");
+ dlclose(handle);
+ free(new_name);
+ free(lname);
+ return NULL;
+ }
+ }
+ }
+ }
+
+ free(new_name);
+ free(lname);
+ return m;
+}
+
+
+struct in_addr *dotted_to_addr(const char *dotted)
+{
+ static struct in_addr addr;
+ unsigned char *addrp;
+ char *p, *q;
+ unsigned int onebyte;
+ int i;
+ char buf[20];
+
+ /* copy dotted string, because we need to modify it */
+ strncpy(buf, dotted, sizeof (buf) - 1);
+ addrp = (unsigned char *) &(addr.s_addr);
+
+ p = buf;
+ for (i = 0; i < 3; i++) {
+ if ((q = strchr(p, '.')) == NULL)
+ return (struct in_addr *) NULL;
+
+ *q = '\0';
+ if (string_to_number(p, 0, 255, &onebyte) == -1)
+ return (struct in_addr *) NULL;
+
+ addrp[i] = (unsigned char) onebyte;
+ p = q + 1;
+ }
+
+ /* we've checked 3 bytes, now we check the last one */
+ if (string_to_number(p, 0, 255, &onebyte) == -1)
+ return (struct in_addr *) NULL;
+
+ addrp[3] = (unsigned char) onebyte;
+
+ return &addr;
+}
+
+static void set_revision(char *name, u_int8_t revision)
+{
+ /* Old kernel sources don't have ".revision" field,
+ * but we stole a byte from name. */
+ name[IPT_FUNCTION_MAXNAMELEN - 2] = '\0';
+ name[IPT_FUNCTION_MAXNAMELEN - 1] = revision;
+}
+
+/*
+ * we may need to check for version mismatch
+*/
+int
+build_st(struct iptables_target *target, struct ipt_entry_target *t)
+{
+ unsigned int nfcache = 0;
+
+ if (target) {
+ size_t size;
+
+ size =
+ IPT_ALIGN(sizeof (struct ipt_entry_target)) + target->size;
+
+ if (NULL == t) {
+ target->t = fw_calloc(1, size);
+ target->t->u.target_size = size;
+
+ if (target->init != NULL)
+ target->init(target->t, &nfcache);
+ set_revision(target->t->u.user.name, target->revision);
+ } else {
+ target->t = t;
+ }
+ strcpy(target->t->u.user.name, target->name);
+ return 0;
+ }
+
+ return -1;
+}
+
+static int parse_ipt(struct action_util *a,int *argc_p,
+ char ***argv_p, int tca_id, struct nlmsghdr *n)
+{
+ struct iptables_target *m = NULL;
+ struct ipt_entry fw;
+ struct rtattr *tail;
+ int c;
+ int rargc = *argc_p;
+ char **argv = *argv_p;
+ int argc = 0, iargc = 0;
+ char k[16];
+ int size = 0;
+ int iok = 0, ok = 0;
+ __u32 hook = 0, index = 0;
+
+ lib_dir = getenv("IPTABLES_LIB_DIR");
+ if (!lib_dir)
+ lib_dir = IPT_LIB_DIR;
+
+ {
+ int i;
+ for (i = 0; i < rargc; i++) {
+ if (NULL == argv[i] || 0 == strcmp(argv[i], "action")) {
+ break;
+ }
+ }
+ iargc = argc = i;
+ }
+
+ if (argc <= 2) {
+ fprintf(stderr,"bad arguments to ipt %d vs %d \n", argc, rargc);
+ return -1;
+ }
+
+ while (1) {
+ c = getopt_long(argc, argv, "j:", opts, NULL);
+ if (c == -1)
+ break;
+ switch (c) {
+ case 'j':
+ m = get_target_name(optarg);
+ if (NULL != m) {
+
+ if (0 > build_st(m, NULL)) {
+ printf(" %s error \n", m->name);
+ return -1;
+ }
+ opts =
+ merge_options(opts, m->extra_opts,
+ &m->option_offset);
+ } else {
+ fprintf(stderr," failed to find target %s\n\n", optarg);
+ return -1;
+ }
+ ok++;
+ break;
+
+ default:
+ memset(&fw, 0, sizeof (fw));
+ if (m) {
+ m->parse(c - m->option_offset, argv, 0,
+ &m->tflags, NULL, &m->t);
+ } else {
+ fprintf(stderr," failed to find target %s\n\n", optarg);
+ return -1;
+
+ }
+ ok++;
+ break;
+
+ }
+ }
+
+ if (iargc > optind) {
+ if (matches(argv[optind], "index") == 0) {
+ if (get_u32(&index, argv[optind + 1], 10)) {
+ fprintf(stderr, "Illegal \"index\"\n");
+ free_opts(opts);
+ return -1;
+ }
+ iok++;
+
+ optind += 2;
+ }
+ }
+
+ if (!ok && !iok) {
+ fprintf(stderr," ipt Parser BAD!! (%s)\n", *argv);
+ return -1;
+ }
+
+ /* check that we passed the correct parameters to the target */
+ if (m)
+ m->final_check(m->tflags);
+
+ {
+ struct tcmsg *t = NLMSG_DATA(n);
+ if (t->tcm_parent != TC_H_ROOT
+ && t->tcm_parent == TC_H_MAJ(TC_H_INGRESS)) {
+ hook = NF_IP_PRE_ROUTING;
+ } else {
+ hook = NF_IP_POST_ROUTING;
+ }
+ }
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, MAX_MSG, tca_id, NULL, 0);
+ fprintf(stdout, "tablename: %s hook: %s\n ", tname, ipthooks[hook]);
+ fprintf(stdout, "\ttarget: ");
+
+ if (m)
+ m->print(NULL, m->t, 0);
+ fprintf(stdout, " index %d\n", index);
+
+ if (strlen(tname) > 16) {
+ size = 16;
+ k[15] = 0;
+ } else {
+ size = 1 + strlen(tname);
+ }
+ strncpy(k, tname, size);
+
+ addattr_l(n, MAX_MSG, TCA_IPT_TABLE, k, size);
+ addattr_l(n, MAX_MSG, TCA_IPT_HOOK, &hook, 4);
+ addattr_l(n, MAX_MSG, TCA_IPT_INDEX, &index, 4);
+ if (m)
+ addattr_l(n, MAX_MSG, TCA_IPT_TARG, m->t, m->t->u.target_size);
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+
+ argc -= optind;
+ argv += optind;
+ *argc_p = rargc - iargc;
+ *argv_p = argv;
+
+ optind = 0;
+ free_opts(opts);
+ /* Clear flags if target will be used again */
+ m->tflags=0;
+ m->used=0;
+ /* Free allocated memory */
+ if (m->t)
+ free(m->t);
+
+
+ return 0;
+
+}
+
+static int
+print_ipt(struct action_util *au,FILE * f, struct rtattr *arg)
+{
+ struct rtattr *tb[TCA_IPT_MAX + 1];
+ struct ipt_entry_target *t = NULL;
+
+ if (arg == NULL)
+ return -1;
+
+ lib_dir = getenv("IPTABLES_LIB_DIR");
+ if (!lib_dir)
+ lib_dir = IPT_LIB_DIR;
+
+ parse_rtattr_nested(tb, TCA_IPT_MAX, arg);
+
+ if (tb[TCA_IPT_TABLE] == NULL) {
+ fprintf(f, "[NULL ipt table name ] assuming mangle ");
+ } else {
+ fprintf(f, "tablename: %s ",
+ rta_getattr_str(tb[TCA_IPT_TABLE]));
+ }
+
+ if (tb[TCA_IPT_HOOK] == NULL) {
+ fprintf(f, "[NULL ipt hook name ]\n ");
+ return -1;
+ } else {
+ __u32 hook;
+ hook = rta_getattr_u32(tb[TCA_IPT_HOOK]);
+ fprintf(f, " hook: %s \n", ipthooks[hook]);
+ }
+
+ if (tb[TCA_IPT_TARG] == NULL) {
+ fprintf(f, "\t[NULL ipt target parameters ] \n");
+ return -1;
+ } else {
+ struct iptables_target *m = NULL;
+ t = RTA_DATA(tb[TCA_IPT_TARG]);
+ m = get_target_name(t->u.user.name);
+ if (NULL != m) {
+ if (0 > build_st(m, t)) {
+ fprintf(stderr, " %s error \n", m->name);
+ return -1;
+ }
+
+ opts =
+ merge_options(opts, m->extra_opts,
+ &m->option_offset);
+ } else {
+ fprintf(stderr, " failed to find target %s\n\n",
+ t->u.user.name);
+ return -1;
+ }
+ fprintf(f, "\ttarget ");
+ m->print(NULL, m->t, 0);
+ if (tb[TCA_IPT_INDEX] == NULL) {
+ fprintf(f, " [NULL ipt target index ]\n");
+ } else {
+ __u32 index;
+ index = rta_getattr_u32(tb[TCA_IPT_INDEX]);
+ fprintf(f, " \n\tindex %d", index);
+ }
+
+ if (tb[TCA_IPT_CNT]) {
+ struct tc_cnt *c = RTA_DATA(tb[TCA_IPT_CNT]);;
+ fprintf(f, " ref %d bind %d", c->refcnt, c->bindcnt);
+ }
+ if (show_stats) {
+ if (tb[TCA_IPT_TM]) {
+ struct tcf_t *tm = RTA_DATA(tb[TCA_IPT_TM]);
+ print_tm(f,tm);
+ }
+ }
+ fprintf(f, " \n");
+
+ }
+ free_opts(opts);
+
+ return 0;
+}
+
+struct action_util ipt_action_util = {
+ .id = "ipt",
+ .parse_aopt = parse_ipt,
+ .print_aopt = print_ipt,
+};
diff --git a/iproute2/tc/m_mirred.c b/iproute2/tc/m_mirred.c
new file mode 100644
index 0000000..dc231d7
--- /dev/null
+++ b/iproute2/tc/m_mirred.c
@@ -0,0 +1,298 @@
+/*
+ * m_egress.c ingress/egress packet mirror/redir actions module
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: J Hadi Salim (hadi@cyberus.ca)
+ *
+ * TODO: Add Ingress support
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include "utils.h"
+#include "tc_util.h"
+#include "tc_common.h"
+#include <linux/tc_act/tc_mirred.h>
+
+static void
+explain(void)
+{
+ fprintf(stderr, "Usage: mirred <DIRECTION> <ACTION> [index INDEX] <dev DEVICENAME> \n");
+ fprintf(stderr, "where: \n");
+ fprintf(stderr, "\tDIRECTION := <ingress | egress>\n");
+ fprintf(stderr, "\tACTION := <mirror | redirect>\n");
+ fprintf(stderr, "\tINDEX is the specific policy instance id\n");
+ fprintf(stderr, "\tDEVICENAME is the devicename \n");
+
+}
+
+static void
+usage(void)
+{
+ explain();
+ exit(-1);
+}
+
+static const char *mirred_n2a(int action)
+{
+ switch (action) {
+ case TCA_EGRESS_REDIR:
+ return "Egress Redirect";
+ case TCA_INGRESS_REDIR:
+ return "Ingress Redirect";
+ case TCA_EGRESS_MIRROR:
+ return "Egress Mirror";
+ case TCA_INGRESS_MIRROR:
+ return "Ingress Mirror";
+ default:
+ return "unknown";
+ }
+}
+
+static int
+parse_egress(struct action_util *a, int *argc_p, char ***argv_p,
+ int tca_id, struct nlmsghdr *n)
+{
+
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ int ok = 0, iok = 0, mirror=0,redir=0;
+ struct tc_mirred p;
+ struct rtattr *tail;
+ char d[16];
+
+ memset(d,0,sizeof(d)-1);
+ memset(&p,0,sizeof(struct tc_mirred));
+
+ while (argc > 0) {
+
+ if (matches(*argv, "action") == 0) {
+ break;
+ } else if (matches(*argv, "egress") == 0) {
+ NEXT_ARG();
+ ok++;
+ continue;
+ } else {
+
+ if (matches(*argv, "index") == 0) {
+ NEXT_ARG();
+ if (get_u32(&p.index, *argv, 10)) {
+ fprintf(stderr, "Illegal \"index\"\n");
+ return -1;
+ }
+ iok++;
+ if (!ok) {
+ argc--;
+ argv++;
+ break;
+ }
+ } else if(!ok) {
+ fprintf(stderr, "was expecting egress (%s)\n", *argv);
+ break;
+
+ } else if (!mirror && matches(*argv, "mirror") == 0) {
+ mirror=1;
+ if (redir) {
+ fprintf(stderr, "Can't have both mirror and redir\n");
+ return -1;
+ }
+ p.eaction = TCA_EGRESS_MIRROR;
+ p.action = TC_ACT_PIPE;
+ ok++;
+ } else if (!redir && matches(*argv, "redirect") == 0) {
+ redir=1;
+ if (mirror) {
+ fprintf(stderr, "Can't have both mirror and redir\n");
+ return -1;
+ }
+ p.eaction = TCA_EGRESS_REDIR;
+ p.action = TC_ACT_STOLEN;
+ ok++;
+ } else if ((redir || mirror) && matches(*argv, "dev") == 0) {
+ NEXT_ARG();
+ if (strlen(d))
+ duparg("dev", *argv);
+
+ strncpy(d, *argv, sizeof(d)-1);
+ argc--;
+ argv++;
+
+ break;
+
+ }
+ }
+
+ NEXT_ARG();
+ }
+
+ if (!ok && !iok) {
+ return -1;
+ }
+
+
+
+ if (d[0]) {
+ int idx;
+ ll_init_map(&rth);
+
+ if ((idx = ll_name_to_index(d)) == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", d);
+ return -1;
+ }
+
+ p.ifindex = idx;
+ }
+
+
+ if (argc && p.eaction == TCA_EGRESS_MIRROR) {
+
+ if (matches(*argv, "reclassify") == 0) {
+ p.action = TC_POLICE_RECLASSIFY;
+ NEXT_ARG();
+ } else if (matches(*argv, "pipe") == 0) {
+ p.action = TC_POLICE_PIPE;
+ NEXT_ARG();
+ } else if (matches(*argv, "drop") == 0 ||
+ matches(*argv, "shot") == 0) {
+ p.action = TC_POLICE_SHOT;
+ NEXT_ARG();
+ } else if (matches(*argv, "continue") == 0) {
+ p.action = TC_POLICE_UNSPEC;
+ NEXT_ARG();
+ } else if (matches(*argv, "pass") == 0) {
+ p.action = TC_POLICE_OK;
+ NEXT_ARG();
+ }
+
+ }
+
+ if (argc) {
+ if (iok && matches(*argv, "index") == 0) {
+ fprintf(stderr, "mirred: Illegal double index\n");
+ return -1;
+ } else {
+ if (matches(*argv, "index") == 0) {
+ NEXT_ARG();
+ if (get_u32(&p.index, *argv, 10)) {
+ fprintf(stderr, "mirred: Illegal \"index\"\n");
+ return -1;
+ }
+ argc--;
+ argv++;
+ }
+ }
+ }
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, MAX_MSG, tca_id, NULL, 0);
+ addattr_l(n, MAX_MSG, TCA_MIRRED_PARMS, &p, sizeof (p));
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return 0;
+}
+
+
+static int
+parse_mirred(struct action_util *a, int *argc_p, char ***argv_p,
+ int tca_id, struct nlmsghdr *n)
+{
+
+ int argc = *argc_p;
+ char **argv = *argv_p;
+
+ if (argc < 0) {
+ fprintf(stderr,"mirred bad argument count %d\n", argc);
+ return -1;
+ }
+
+ if (matches(*argv, "mirred") == 0) {
+ NEXT_ARG();
+ } else {
+ fprintf(stderr,"mirred bad argument %s\n", *argv);
+ return -1;
+ }
+
+
+ if (matches(*argv, "egress") == 0 || matches(*argv, "index") == 0) {
+ int ret = parse_egress(a, &argc, &argv, tca_id, n);
+ if (ret == 0) {
+ *argc_p = argc;
+ *argv_p = argv;
+ return 0;
+ }
+
+ } else if (matches(*argv, "ingress") == 0) {
+ fprintf(stderr,"mirred ingress not supported at the moment\n");
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ } else {
+ fprintf(stderr,"mirred option not supported %s\n", *argv);
+ }
+
+ return -1;
+
+}
+
+static int
+print_mirred(struct action_util *au,FILE * f, struct rtattr *arg)
+{
+ struct tc_mirred *p;
+ struct rtattr *tb[TCA_MIRRED_MAX + 1];
+ const char *dev;
+ SPRINT_BUF(b1);
+
+ if (arg == NULL)
+ return -1;
+
+ parse_rtattr_nested(tb, TCA_MIRRED_MAX, arg);
+
+ if (tb[TCA_MIRRED_PARMS] == NULL) {
+ fprintf(f, "[NULL mirred parameters]");
+ return -1;
+ }
+ p = RTA_DATA(tb[TCA_MIRRED_PARMS]);
+
+ /*
+ ll_init_map(&rth);
+ */
+
+
+ if ((dev = ll_index_to_name(p->ifindex)) == 0) {
+ fprintf(stderr, "Cannot find device %d\n", p->ifindex);
+ return -1;
+ }
+
+ fprintf(f, "mirred (%s to device %s) %s", mirred_n2a(p->eaction), dev,action_n2a(p->action, b1, sizeof (b1)));
+
+ fprintf(f, "\n ");
+ fprintf(f, "\tindex %d ref %d bind %d",p->index,p->refcnt,p->bindcnt);
+
+ if (show_stats) {
+ if (tb[TCA_MIRRED_TM]) {
+ struct tcf_t *tm = RTA_DATA(tb[TCA_MIRRED_TM]);
+ print_tm(f,tm);
+ }
+ }
+ fprintf(f, "\n ");
+ return 0;
+}
+
+struct action_util mirred_action_util = {
+ .id = "mirred",
+ .parse_aopt = parse_mirred,
+ .print_aopt = print_mirred,
+};
diff --git a/iproute2/tc/m_nat.c b/iproute2/tc/m_nat.c
new file mode 100644
index 0000000..d502a81
--- /dev/null
+++ b/iproute2/tc/m_nat.c
@@ -0,0 +1,212 @@
+/*
+ * m_nat.c NAT module
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Herbert Xu <herbert@gondor.apana.org.au>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include "utils.h"
+#include "tc_util.h"
+#include <linux/tc_act/tc_nat.h>
+
+static void
+explain(void)
+{
+ fprintf(stderr, "Usage: ... nat NAT\n"
+ "NAT := DIRECTION OLD NEW\n"
+ "DIRECTION := { ingress | egress }\n"
+ "OLD := PREFIX\n"
+ "NEW := ADDRESS\n");
+}
+
+static void
+usage(void)
+{
+ explain();
+ exit(-1);
+}
+
+static int
+parse_nat_args(int *argc_p, char ***argv_p,struct tc_nat *sel)
+{
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ inet_prefix addr;
+
+ if (argc <= 0)
+ return -1;
+
+ if (matches(*argv, "egress") == 0)
+ sel->flags |= TCA_NAT_FLAG_EGRESS;
+ else if (matches(*argv, "ingress") != 0)
+ goto bad_val;
+
+ NEXT_ARG();
+
+ if (get_prefix_1(&addr, *argv, AF_INET))
+ goto bad_val;
+
+ sel->old_addr = addr.data[0];
+ sel->mask = htonl(~0u << (32 - addr.bitlen));
+
+ NEXT_ARG();
+
+ if (get_prefix_1(&addr, *argv, AF_INET))
+ goto bad_val;
+
+ sel->new_addr = addr.data[0];
+
+ argc--;
+ argv++;
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return 0;
+
+bad_val:
+ return -1;
+}
+
+static int
+parse_nat(struct action_util *a, int *argc_p, char ***argv_p, int tca_id, struct nlmsghdr *n)
+{
+ struct tc_nat sel;
+
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ int ok = 0;
+ struct rtattr *tail;
+
+ memset(&sel, 0, sizeof(sel));
+
+ while (argc > 0) {
+ if (matches(*argv, "nat") == 0) {
+ NEXT_ARG();
+ if (parse_nat_args(&argc, &argv, &sel)) {
+ fprintf(stderr, "Illegal nat construct (%s) \n",
+ *argv);
+ explain();
+ return -1;
+ }
+ ok++;
+ continue;
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ } else {
+ break;
+ }
+
+ }
+
+ if (!ok) {
+ explain();
+ return -1;
+ }
+
+ if (argc) {
+ if (matches(*argv, "reclassify") == 0) {
+ sel.action = TC_ACT_RECLASSIFY;
+ argc--;
+ argv++;
+ } else if (matches(*argv, "pipe") == 0) {
+ sel.action = TC_ACT_PIPE;
+ argc--;
+ argv++;
+ } else if (matches(*argv, "drop") == 0 ||
+ matches(*argv, "shot") == 0) {
+ sel.action = TC_ACT_SHOT;
+ argc--;
+ argv++;
+ } else if (matches(*argv, "continue") == 0) {
+ sel.action = TC_ACT_UNSPEC;
+ argc--;
+ argv++;
+ } else if (matches(*argv, "pass") == 0) {
+ sel.action = TC_ACT_OK;
+ argc--;
+ argv++;
+ }
+ }
+
+ if (argc) {
+ if (matches(*argv, "index") == 0) {
+ NEXT_ARG();
+ if (get_u32(&sel.index, *argv, 10)) {
+ fprintf(stderr, "Nat: Illegal \"index\"\n");
+ return -1;
+ }
+ argc--;
+ argv++;
+ }
+ }
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, MAX_MSG, tca_id, NULL, 0);
+ addattr_l(n, MAX_MSG, TCA_NAT_PARMS, &sel, sizeof(sel));
+ tail->rta_len = (char *)NLMSG_TAIL(n) - (char *)tail;
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return 0;
+}
+
+static int
+print_nat(struct action_util *au,FILE * f, struct rtattr *arg)
+{
+ struct tc_nat *sel;
+ struct rtattr *tb[TCA_NAT_MAX + 1];
+ char buf1[256];
+ char buf2[256];
+ SPRINT_BUF(buf3);
+ int len;
+
+ if (arg == NULL)
+ return -1;
+
+ parse_rtattr_nested(tb, TCA_NAT_MAX, arg);
+
+ if (tb[TCA_NAT_PARMS] == NULL) {
+ fprintf(f, "[NULL nat parameters]");
+ return -1;
+ }
+ sel = RTA_DATA(tb[TCA_NAT_PARMS]);
+
+ len = ffs(sel->mask);
+ len = len ? 33 - len : 0;
+
+ fprintf(f, " nat %s %s/%d %s %s", sel->flags & TCA_NAT_FLAG_EGRESS ?
+ "egress" : "ingress",
+ format_host(AF_INET, 4, &sel->old_addr, buf1, sizeof(buf1)),
+ len,
+ format_host(AF_INET, 4, &sel->new_addr, buf2, sizeof(buf2)),
+ action_n2a(sel->action, buf3, sizeof (buf3)));
+
+ if (show_stats) {
+ if (tb[TCA_NAT_TM]) {
+ struct tcf_t *tm = RTA_DATA(tb[TCA_NAT_TM]);
+ print_tm(f,tm);
+ }
+ }
+
+ return 0;
+}
+
+struct action_util nat_action_util = {
+ .id = "nat",
+ .parse_aopt = parse_nat,
+ .print_aopt = print_nat,
+};
diff --git a/iproute2/tc/m_pedit.c b/iproute2/tc/m_pedit.c
new file mode 100644
index 0000000..4fdd189
--- /dev/null
+++ b/iproute2/tc/m_pedit.c
@@ -0,0 +1,591 @@
+/*
+ * m_pedit.c generic packet editor actions module
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: J Hadi Salim (hadi@cyberus.ca)
+ *
+ * TODO:
+ * 1) Big endian broken in some spots
+ * 2) A lot of this stuff was added on the fly; get a big double-double
+ * and clean it up at some point.
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <dlfcn.h>
+#include "utils.h"
+#include "tc_util.h"
+#include "m_pedit.h"
+
+static struct m_pedit_util *pedit_list;
+static int pedit_debug;
+
+static void
+explain(void)
+{
+ fprintf(stderr, "Usage: ... pedit munge <MUNGE>\n");
+ fprintf(stderr,
+ "Where: MUNGE := <RAW>|<LAYERED>\n"
+ "\t<RAW>:= <OFFSETC>[ATC]<CMD>\n "
+ "\t\tOFFSETC:= offset <offval> <u8|u16|u32>\n "
+ "\t\tATC:= at <atval> offmask <maskval> shift <shiftval>\n "
+ "\t\tNOTE: offval is byte offset, must be multiple of 4\n "
+ "\t\tNOTE: maskval is a 32 bit hex number\n "
+ "\t\tNOTE: shiftval is a is a shift value\n "
+ "\t\tCMD:= clear | invert | set <setval>| retain\n "
+ "\t<LAYERED>:= ip <ipdata> | ip6 <ip6data> \n "
+ " \t\t| udp <udpdata> | tcp <tcpdata> | icmp <icmpdata> \n"
+ "For Example usage look at the examples directory\n");
+
+}
+
+static void
+usage(void)
+{
+ explain();
+ exit(-1);
+}
+
+static int
+pedit_parse_nopopt (int *argc_p, char ***argv_p,struct tc_pedit_sel *sel,struct tc_pedit_key *tkey)
+{
+ int argc = *argc_p;
+ char **argv = *argv_p;
+
+ if (argc) {
+ fprintf(stderr, "Unknown action hence option \"%s\" is unparsable\n", *argv);
+ return -1;
+ }
+
+ return 0;
+
+}
+
+static struct m_pedit_util *get_pedit_kind(const char *str)
+{
+ static void *pBODY;
+ void *dlh;
+ char buf[256];
+ struct m_pedit_util *p;
+
+ for (p = pedit_list; p; p = p->next) {
+ if (strcmp(p->id, str) == 0)
+ return p;
+ }
+
+ snprintf(buf, sizeof(buf), "p_%s.so", str);
+ dlh = dlopen(buf, RTLD_LAZY);
+ if (dlh == NULL) {
+ dlh = pBODY;
+ if (dlh == NULL) {
+ dlh = pBODY = dlopen(NULL, RTLD_LAZY);
+ if (dlh == NULL)
+ goto noexist;
+ }
+ }
+
+ snprintf(buf, sizeof(buf), "p_pedit_%s", str);
+ p = dlsym(dlh, buf);
+ if (p == NULL)
+ goto noexist;
+
+reg:
+ p->next = pedit_list;
+ pedit_list = p;
+ return p;
+
+noexist:
+ p = malloc(sizeof(*p));
+ if (p) {
+ memset(p, 0, sizeof(*p));
+ strncpy(p->id, str, sizeof(p->id)-1);
+ p->parse_peopt = pedit_parse_nopopt;
+ goto reg;
+ }
+ return p;
+}
+
+int
+pack_key(struct tc_pedit_sel *sel,struct tc_pedit_key *tkey)
+{
+ int hwm = sel->nkeys;
+
+ if (hwm >= MAX_OFFS)
+ return -1;
+
+ if (tkey->off % 4) {
+ fprintf(stderr, "offsets MUST be in 32 bit boundaries\n");
+ return -1;
+ }
+
+ sel->keys[hwm].val = tkey->val;
+ sel->keys[hwm].mask = tkey->mask;
+ sel->keys[hwm].off = tkey->off;
+ sel->keys[hwm].at = tkey->at;
+ sel->keys[hwm].offmask = tkey->offmask;
+ sel->keys[hwm].shift = tkey->shift;
+ sel->nkeys++;
+ return 0;
+}
+
+
+int
+pack_key32(__u32 retain,struct tc_pedit_sel *sel,struct tc_pedit_key *tkey)
+{
+ if (tkey->off > (tkey->off & ~3)) {
+ fprintf(stderr,
+ "pack_key32: 32 bit offsets must begin in 32bit boundaries\n");
+ return -1;
+ }
+
+ tkey->val = htonl(tkey->val & retain);
+ tkey->mask = htonl(tkey->mask | ~retain);
+ /* jamal remove this - it is not necessary given the if check above */
+ tkey->off &= ~3;
+ return pack_key(sel,tkey);
+}
+
+int
+pack_key16(__u32 retain,struct tc_pedit_sel *sel,struct tc_pedit_key *tkey)
+{
+ int ind, stride;
+ __u32 m[4] = {0xFFFF0000,0xFF0000FF,0x0000FFFF};
+
+ if (tkey->val > 0xFFFF || tkey->mask > 0xFFFF) {
+ fprintf(stderr, "pack_key16 bad value\n");
+ return -1;
+ }
+
+ ind = tkey->off & 3;
+
+ if (ind == 3) {
+ fprintf(stderr, "pack_key16 bad index value %d\n",ind);
+ return -1;
+ }
+
+ stride = 8 * ind;
+ tkey->val = htons(tkey->val);
+ tkey->val <<= stride;
+ tkey->mask <<= stride;
+ retain <<= stride;
+ tkey->mask = retain|m[ind];
+
+ tkey->off &= ~3;
+
+ if (pedit_debug)
+ printf("pack_key16: Final val %08x mask %08x \n",tkey->val,tkey->mask);
+ return pack_key(sel,tkey);
+
+}
+
+int
+pack_key8(__u32 retain,struct tc_pedit_sel *sel,struct tc_pedit_key *tkey)
+{
+ int ind, stride;
+ __u32 m[4] = {0xFFFFFF00,0xFFFF00FF,0xFF00FFFF,0x00FFFFFF};
+
+ if (tkey->val > 0xFF || tkey->mask > 0xFF) {
+ fprintf(stderr, "pack_key8 bad value (val %x mask %x\n", tkey->val, tkey->mask);
+ return -1;
+ }
+
+ ind = tkey->off & 3;
+
+ stride = 8 * ind;
+ tkey->val <<= stride;
+ tkey->mask <<= stride;
+ retain <<= stride;
+ tkey->mask = retain|m[ind];
+
+ tkey->off &= ~3;
+
+ if (pedit_debug)
+ printf("pack_key8: Final word off %d val %08x mask %08x \n",tkey->off , tkey->val,tkey->mask);
+ return pack_key(sel,tkey);
+}
+
+int
+parse_val(int *argc_p, char ***argv_p, __u32 * val, int type)
+{
+ int argc = *argc_p;
+ char **argv = *argv_p;
+
+ if (argc <= 0)
+ return -1;
+
+ if (TINT == type)
+ return get_integer((int *) val, *argv, 0);
+
+ if (TU32 == type)
+ return get_u32(val, *argv, 0);
+
+ if (TIPV4 == type) {
+ inet_prefix addr;
+ if (get_prefix_1(&addr, *argv, AF_INET)) {
+ return -1;
+ }
+ *val=addr.data[0];
+ return 0;
+ }
+ if (TIPV6 == type) {
+ /* not implemented yet */
+ return -1;
+ }
+
+ return -1;
+}
+
+int
+parse_cmd(int *argc_p, char ***argv_p, __u32 len, int type,__u32 retain,struct tc_pedit_sel *sel,struct tc_pedit_key *tkey)
+{
+ __u32 mask = 0, val = 0;
+ __u32 o = 0xFF;
+ int res = -1;
+ int argc = *argc_p;
+ char **argv = *argv_p;
+
+ if (argc <= 0)
+ return -1;
+
+ if (pedit_debug)
+ printf("parse_cmd argc %d %s offset %d length %d\n",argc,*argv,tkey->off,len);
+
+ if (len == 2)
+ o = 0xFFFF;
+ if (len == 4)
+ o = 0xFFFFFFFF;
+
+ if (matches(*argv, "invert") == 0) {
+ retain = val = mask = o;
+ } else if (matches(*argv, "set") == 0) {
+ NEXT_ARG();
+ if (parse_val(&argc, &argv, &val, type))
+ return -1;
+ } else if (matches(*argv, "preserve") == 0) {
+ retain = mask = o;
+ } else {
+ if (matches(*argv, "clear") != 0)
+ return -1;
+ }
+
+ argc--; argv++;
+
+ if (argc && matches(*argv, "retain") == 0) {
+ NEXT_ARG();
+ if (parse_val(&argc, &argv, &retain, TU32))
+ return -1;
+ argc--; argv++;
+ }
+
+ tkey->val = val;
+
+ if (len == 1) {
+ tkey->mask = 0xFF;
+ res = pack_key8(retain,sel,tkey);
+ goto done;
+ }
+ if (len == 2) {
+ tkey->mask = mask;
+ res = pack_key16(retain,sel,tkey);
+ goto done;
+ }
+ if (len == 4) {
+ tkey->mask = mask;
+ res = pack_key32(retain,sel,tkey);
+ goto done;
+ }
+
+ return -1;
+done:
+ if (pedit_debug)
+ printf("parse_cmd done argc %d %s offset %d length %d\n",argc,*argv,tkey->off,len);
+ *argc_p = argc;
+ *argv_p = argv;
+ return res;
+
+}
+
+int
+parse_offset(int *argc_p, char ***argv_p,struct tc_pedit_sel *sel,struct tc_pedit_key *tkey)
+{
+ int off;
+ __u32 len, retain;
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ int res = -1;
+
+ if (argc <= 0)
+ return -1;
+
+ if (get_integer(&off, *argv, 0))
+ return -1;
+ tkey->off = off;
+
+ argc--;
+ argv++;
+
+ if (argc <= 0)
+ return -1;
+
+
+ if (matches(*argv, "u32") == 0) {
+ len = 4;
+ retain = 0xFFFFFFFF;
+ goto done;
+ }
+ if (matches(*argv, "u16") == 0) {
+ len = 2;
+ retain = 0x0;
+ goto done;
+ }
+ if (matches(*argv, "u8") == 0) {
+ len = 1;
+ retain = 0x0;
+ goto done;
+ }
+
+ return -1;
+
+done:
+
+ NEXT_ARG();
+
+ /* [at <someval> offmask <maskval> shift <shiftval>] */
+ if (matches(*argv, "at") == 0) {
+
+ __u32 atv=0,offmask=0x0,shift=0;
+
+ NEXT_ARG();
+ if (get_u32(&atv, *argv, 0))
+ return -1;
+ tkey->at = atv;
+
+ NEXT_ARG();
+
+ if (get_u32(&offmask, *argv, 16))
+ return -1;
+ tkey->offmask = offmask;
+
+ NEXT_ARG();
+
+ if (get_u32(&shift, *argv, 0))
+ return -1;
+ tkey->shift = shift;
+
+ NEXT_ARG();
+ }
+
+ res = parse_cmd(&argc, &argv, len, TU32,retain,sel,tkey);
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return res;
+}
+
+static int
+parse_munge(int *argc_p, char ***argv_p,struct tc_pedit_sel *sel)
+{
+ struct tc_pedit_key tkey;
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ int res = -1;
+
+ if (argc <= 0)
+ return -1;
+
+ memset(&tkey, 0, sizeof(tkey));
+
+ if (matches(*argv, "offset") == 0) {
+ NEXT_ARG();
+ res = parse_offset(&argc, &argv,sel,&tkey);
+ goto done;
+ } else {
+ char k[16];
+ struct m_pedit_util *p = NULL;
+
+ strncpy(k, *argv, sizeof (k) - 1);
+
+ if (argc > 0 ) {
+ p = get_pedit_kind(k);
+ if (NULL == p)
+ goto bad_val;
+ res = p->parse_peopt(&argc, &argv, sel,&tkey);
+ if (res < 0) {
+ fprintf(stderr,"bad pedit parsing\n");
+ goto bad_val;
+ }
+ goto done;
+ }
+ }
+
+bad_val:
+ return -1;
+
+done:
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return res;
+}
+
+int
+parse_pedit(struct action_util *a, int *argc_p, char ***argv_p, int tca_id, struct nlmsghdr *n)
+{
+ struct {
+ struct tc_pedit_sel sel;
+ struct tc_pedit_key keys[MAX_OFFS];
+ } sel;
+
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ int ok = 0, iok = 0;
+ struct rtattr *tail;
+
+ memset(&sel, 0, sizeof(sel));
+
+ while (argc > 0) {
+ if (pedit_debug > 1)
+ fprintf(stderr, "while pedit (%d:%s)\n",argc, *argv);
+ if (matches(*argv, "pedit") == 0) {
+ NEXT_ARG();
+ ok++;
+ continue;
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ } else if (matches(*argv, "munge") == 0) {
+ if (!ok) {
+ fprintf(stderr, "Illegal pedit construct (%s) \n", *argv);
+ explain();
+ return -1;
+ }
+ NEXT_ARG();
+ if (parse_munge(&argc, &argv,&sel.sel)) {
+ fprintf(stderr, "Illegal pedit construct (%s) \n", *argv);
+ explain();
+ return -1;
+ }
+ ok++;
+ } else {
+ break;
+ }
+
+ }
+
+ if (!ok) {
+ explain();
+ return -1;
+ }
+
+ if (argc) {
+ if (matches(*argv, "reclassify") == 0) {
+ sel.sel.action = TC_ACT_RECLASSIFY;
+ NEXT_ARG();
+ } else if (matches(*argv, "pipe") == 0) {
+ sel.sel.action = TC_ACT_PIPE;
+ NEXT_ARG();
+ } else if (matches(*argv, "drop") == 0 ||
+ matches(*argv, "shot") == 0) {
+ sel.sel.action = TC_ACT_SHOT;
+ NEXT_ARG();
+ } else if (matches(*argv, "continue") == 0) {
+ sel.sel.action = TC_ACT_UNSPEC;
+ NEXT_ARG();
+ } else if (matches(*argv, "pass") == 0) {
+ sel.sel.action = TC_ACT_OK;
+ NEXT_ARG();
+ }
+ }
+
+ if (argc) {
+ if (matches(*argv, "index") == 0) {
+ NEXT_ARG();
+ if (get_u32(&sel.sel.index, *argv, 10)) {
+ fprintf(stderr, "Pedit: Illegal \"index\"\n");
+ return -1;
+ }
+ argc--;
+ argv++;
+ iok++;
+ }
+ }
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, MAX_MSG, tca_id, NULL, 0);
+ addattr_l(n, MAX_MSG, TCA_PEDIT_PARMS,&sel, sizeof(sel.sel)+sel.sel.nkeys*sizeof(struct tc_pedit_key));
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return 0;
+}
+
+int
+print_pedit(struct action_util *au,FILE * f, struct rtattr *arg)
+{
+ struct tc_pedit_sel *sel;
+ struct rtattr *tb[TCA_PEDIT_MAX + 1];
+ SPRINT_BUF(b1);
+
+ if (arg == NULL)
+ return -1;
+
+ parse_rtattr_nested(tb, TCA_PEDIT_MAX, arg);
+
+ if (tb[TCA_PEDIT_PARMS] == NULL) {
+ fprintf(f, "[NULL pedit parameters]");
+ return -1;
+ }
+ sel = RTA_DATA(tb[TCA_PEDIT_PARMS]);
+
+ fprintf(f, " pedit action %s keys %d\n ", action_n2a(sel->action, b1, sizeof (b1)),sel->nkeys);
+ fprintf(f, "\t index %d ref %d bind %d", sel->index,sel->refcnt, sel->bindcnt);
+
+ if (show_stats) {
+ if (tb[TCA_PEDIT_TM]) {
+ struct tcf_t *tm = RTA_DATA(tb[TCA_PEDIT_TM]);
+ print_tm(f,tm);
+ }
+ }
+ if (sel->nkeys) {
+ int i;
+ struct tc_pedit_key *key = sel->keys;
+
+ for (i=0; i<sel->nkeys; i++, key++) {
+ fprintf(f, "\n\t key #%d",i);
+ fprintf(f, " at %d: val %08x mask %08x",
+ (unsigned int)key->off,
+ (unsigned int)ntohl(key->val),
+ (unsigned int)ntohl(key->mask));
+ }
+ } else {
+ fprintf(f, "\npedit %x keys %d is not LEGIT", sel->index,sel->nkeys);
+ }
+
+
+ fprintf(f, "\n ");
+ return 0;
+}
+
+int
+pedit_print_xstats(struct action_util *au, FILE *f, struct rtattr *xstats)
+{
+ return 0;
+}
+
+struct action_util pedit_action_util = {
+ .id = "pedit",
+ .parse_aopt = parse_pedit,
+ .print_aopt = print_pedit,
+};
diff --git a/iproute2/tc/m_pedit.h b/iproute2/tc/m_pedit.h
new file mode 100644
index 0000000..1698c95
--- /dev/null
+++ b/iproute2/tc/m_pedit.h
@@ -0,0 +1,62 @@
+/*
+ * m_pedit.h generic packet editor actions module
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: J Hadi Salim (hadi@cyberus.ca)
+ *
+ */
+
+#ifndef _ACT_PEDIT_H_
+#define _ACT_PEDIT_H_ 1
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include "utils.h"
+#include "tc_util.h"
+#include <linux/tc_act/tc_pedit.h>
+
+#define MAX_OFFS 128
+
+#define TIPV4 1
+#define TIPV6 2
+#define TINT 3
+#define TU32 4
+
+#define RU32 0xFFFFFFFF
+#define RU16 0xFFFF
+#define RU8 0xFF
+
+#define PEDITKINDSIZ 16
+
+struct m_pedit_util
+{
+ struct m_pedit_util *next;
+ char id[PEDITKINDSIZ];
+ int (*parse_peopt)(int *argc_p, char ***argv_p,struct tc_pedit_sel *sel,struct tc_pedit_key *tkey);
+};
+
+
+extern int parse_cmd(int *argc_p, char ***argv_p, __u32 len, int type,__u32 retain,struct tc_pedit_sel *sel,struct tc_pedit_key *tkey);
+extern int pack_key(struct tc_pedit_sel *sel,struct tc_pedit_key *tkey);
+extern int pack_key32(__u32 retain,struct tc_pedit_sel *sel,struct tc_pedit_key *tkey);
+extern int pack_key16(__u32 retain,struct tc_pedit_sel *sel,struct tc_pedit_key *tkey);
+extern int pack_key8(__u32 retain,struct tc_pedit_sel *sel,struct tc_pedit_key *tkey);
+extern int parse_val(int *argc_p, char ***argv_p, __u32 * val, int type);
+extern int parse_cmd(int *argc_p, char ***argv_p, __u32 len, int type,__u32 retain,struct tc_pedit_sel *sel,struct tc_pedit_key *tkey);
+extern int parse_offset(int *argc_p, char ***argv_p,struct tc_pedit_sel *sel,struct tc_pedit_key *tkey);
+int parse_pedit(struct action_util *a, int *argc_p, char ***argv_p, int tca_id, struct nlmsghdr *n);
+extern int print_pedit(struct action_util *au,FILE * f, struct rtattr *arg);
+extern int pedit_print_xstats(struct action_util *au, FILE *f, struct rtattr *xstats);
+
+#endif
diff --git a/iproute2/tc/m_police.c b/iproute2/tc/m_police.c
new file mode 100644
index 0000000..915f1a5
--- /dev/null
+++ b/iproute2/tc/m_police.c
@@ -0,0 +1,374 @@
+/*
+ * m_police.c Parse/print policing module options.
+ *
+ * This program is free software; you can u32istribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ * FIXES: 19990619 - J Hadi Salim (hadi@cyberus.ca)
+ * simple addattr packaging fix.
+ * 2002: J Hadi Salim - Add tc action extensions syntax
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+struct action_util police_action_util = {
+ .id = "police",
+ .parse_aopt = act_parse_police,
+ .print_aopt = print_police,
+};
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: ... police rate BPS burst BYTES[/BYTES] [ mtu BYTES[/BYTES] ]\n");
+ fprintf(stderr, " [ peakrate BPS ] [ avrate BPS ] [ overhead BYTES ]\n");
+ fprintf(stderr, " [ linklayer TYPE ] [ ACTIONTERM ]\n");
+
+ fprintf(stderr, "New Syntax ACTIONTERM := conform-exceed <EXCEEDACT>[/NOTEXCEEDACT] \n");
+ fprintf(stderr, "Where: *EXCEEDACT := pipe | ok | reclassify | drop | continue \n");
+ fprintf(stderr, "Where: pipe is only valid for new syntax \n");
+ exit(-1);
+}
+
+static void explain1(char *arg)
+{
+ fprintf(stderr, "Illegal \"%s\"\n", arg);
+}
+
+static const char *police_action_n2a(int action, char *buf, int len)
+{
+ switch (action) {
+ case -1:
+ return "continue";
+ break;
+ case TC_POLICE_OK:
+ return "pass";
+ break;
+ case TC_POLICE_SHOT:
+ return "drop";
+ break;
+ case TC_POLICE_RECLASSIFY:
+ return "reclassify";
+ case TC_POLICE_PIPE:
+ return "pipe";
+ default:
+ snprintf(buf, len, "%d", action);
+ return buf;
+ }
+}
+
+static int police_action_a2n(const char *arg, int *result)
+{
+ int res;
+
+ if (matches(arg, "continue") == 0)
+ res = -1;
+ else if (matches(arg, "drop") == 0)
+ res = TC_POLICE_SHOT;
+ else if (matches(arg, "shot") == 0)
+ res = TC_POLICE_SHOT;
+ else if (matches(arg, "pass") == 0)
+ res = TC_POLICE_OK;
+ else if (strcmp(arg, "ok") == 0)
+ res = TC_POLICE_OK;
+ else if (matches(arg, "reclassify") == 0)
+ res = TC_POLICE_RECLASSIFY;
+ else if (matches(arg, "pipe") == 0)
+ res = TC_POLICE_PIPE;
+ else {
+ char dummy;
+ if (sscanf(arg, "%d%c", &res, &dummy) != 1)
+ return -1;
+ }
+ *result = res;
+ return 0;
+}
+
+
+static int get_police_result(int *action, int *result, char *arg)
+{
+ char *p = strchr(arg, '/');
+
+ if (p)
+ *p = 0;
+
+ if (police_action_a2n(arg, action)) {
+ if (p)
+ *p = '/';
+ return -1;
+ }
+
+ if (p) {
+ *p = '/';
+ if (police_action_a2n(p+1, result))
+ return -1;
+ }
+ return 0;
+}
+
+
+int act_parse_police(struct action_util *a,int *argc_p, char ***argv_p, int tca_id, struct nlmsghdr *n)
+{
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ int res = -1;
+ int ok=0;
+ struct tc_police p;
+ __u32 rtab[256];
+ __u32 ptab[256];
+ __u32 avrate = 0;
+ int presult = 0;
+ unsigned buffer=0, mtu=0, mpu=0;
+ unsigned short overhead=0;
+ unsigned int linklayer = LINKLAYER_ETHERNET; /* Assume ethernet */
+ int Rcell_log=-1, Pcell_log = -1;
+ struct rtattr *tail;
+
+ memset(&p, 0, sizeof(p));
+ p.action = TC_POLICE_RECLASSIFY;
+
+ if (a) /* new way of doing things */
+ NEXT_ARG();
+
+ if (argc <= 0)
+ return -1;
+
+ while (argc > 0) {
+
+ if (matches(*argv, "index") == 0) {
+ NEXT_ARG();
+ if (get_u32(&p.index, *argv, 10)) {
+ fprintf(stderr, "Illegal \"index\"\n");
+ return -1;
+ }
+ } else if (matches(*argv, "burst") == 0 ||
+ strcmp(*argv, "buffer") == 0 ||
+ strcmp(*argv, "maxburst") == 0) {
+ NEXT_ARG();
+ if (buffer) {
+ fprintf(stderr, "Double \"buffer/burst\" spec\n");
+ return -1;
+ }
+ if (get_size_and_cell(&buffer, &Rcell_log, *argv) < 0) {
+ explain1("buffer");
+ return -1;
+ }
+ } else if (strcmp(*argv, "mtu") == 0 ||
+ strcmp(*argv, "minburst") == 0) {
+ NEXT_ARG();
+ if (mtu) {
+ fprintf(stderr, "Double \"mtu/minburst\" spec\n");
+ return -1;
+ }
+ if (get_size_and_cell(&mtu, &Pcell_log, *argv) < 0) {
+ explain1("mtu");
+ return -1;
+ }
+ } else if (strcmp(*argv, "mpu") == 0) {
+ NEXT_ARG();
+ if (mpu) {
+ fprintf(stderr, "Double \"mpu\" spec\n");
+ return -1;
+ }
+ if (get_size(&mpu, *argv)) {
+ explain1("mpu");
+ return -1;
+ }
+ } else if (strcmp(*argv, "rate") == 0) {
+ NEXT_ARG();
+ if (p.rate.rate) {
+ fprintf(stderr, "Double \"rate\" spec\n");
+ return -1;
+ }
+ if (get_rate(&p.rate.rate, *argv)) {
+ explain1("rate");
+ return -1;
+ }
+ } else if (strcmp(*argv, "avrate") == 0) {
+ NEXT_ARG();
+ if (avrate) {
+ fprintf(stderr, "Double \"avrate\" spec\n");
+ return -1;
+ }
+ if (get_rate(&avrate, *argv)) {
+ explain1("avrate");
+ return -1;
+ }
+ } else if (matches(*argv, "peakrate") == 0) {
+ NEXT_ARG();
+ if (p.peakrate.rate) {
+ fprintf(stderr, "Double \"peakrate\" spec\n");
+ return -1;
+ }
+ if (get_rate(&p.peakrate.rate, *argv)) {
+ explain1("peakrate");
+ return -1;
+ }
+ } else if (matches(*argv, "reclassify") == 0) {
+ p.action = TC_POLICE_RECLASSIFY;
+ } else if (matches(*argv, "drop") == 0 ||
+ matches(*argv, "shot") == 0) {
+ p.action = TC_POLICE_SHOT;
+ } else if (matches(*argv, "continue") == 0) {
+ p.action = TC_POLICE_UNSPEC;
+ } else if (matches(*argv, "pass") == 0) {
+ p.action = TC_POLICE_OK;
+ } else if (matches(*argv, "pipe") == 0) {
+ p.action = TC_POLICE_PIPE;
+ } else if (strcmp(*argv, "conform-exceed") == 0) {
+ NEXT_ARG();
+ if (get_police_result(&p.action, &presult, *argv)) {
+ fprintf(stderr, "Illegal \"action\"\n");
+ return -1;
+ }
+ } else if (matches(*argv, "overhead") == 0) {
+ NEXT_ARG();
+ if (get_u16(&overhead, *argv, 10)) {
+ explain1("overhead"); return -1;
+ }
+ } else if (matches(*argv, "linklayer") == 0) {
+ NEXT_ARG();
+ if (get_linklayer(&linklayer, *argv)) {
+ explain1("linklayer"); return -1;
+ }
+ } else if (strcmp(*argv, "help") == 0) {
+ usage();
+ } else {
+ break;
+ }
+ ok++;
+ argc--; argv++;
+ }
+
+ if (!ok)
+ return -1;
+
+ if (p.rate.rate && !buffer) {
+ fprintf(stderr, "\"burst\" requires \"rate\".\n");
+ return -1;
+ }
+ if (p.peakrate.rate) {
+ if (!p.rate.rate) {
+ fprintf(stderr, "\"peakrate\" requires \"rate\".\n");
+ return -1;
+ }
+ if (!mtu) {
+ fprintf(stderr, "\"mtu\" is required, if \"peakrate\" is requested.\n");
+ return -1;
+ }
+ }
+
+ if (p.rate.rate) {
+ p.rate.mpu = mpu;
+ p.rate.overhead = overhead;
+ if (tc_calc_rtable(&p.rate, rtab, Rcell_log, mtu, linklayer) < 0) {
+ fprintf(stderr, "TBF: failed to calculate rate table.\n");
+ return -1;
+ }
+ p.burst = tc_calc_xmittime(p.rate.rate, buffer);
+ }
+ p.mtu = mtu;
+ if (p.peakrate.rate) {
+ p.peakrate.mpu = mpu;
+ p.peakrate.overhead = overhead;
+ if (tc_calc_rtable(&p.peakrate, ptab, Pcell_log, mtu, linklayer) < 0) {
+ fprintf(stderr, "POLICE: failed to calculate peak rate table.\n");
+ return -1;
+ }
+ }
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, MAX_MSG, tca_id, NULL, 0);
+ addattr_l(n, MAX_MSG, TCA_POLICE_TBF, &p, sizeof(p));
+ if (p.rate.rate)
+ addattr_l(n, MAX_MSG, TCA_POLICE_RATE, rtab, 1024);
+ if (p.peakrate.rate)
+ addattr_l(n, MAX_MSG, TCA_POLICE_PEAKRATE, ptab, 1024);
+ if (avrate)
+ addattr32(n, MAX_MSG, TCA_POLICE_AVRATE, avrate);
+ if (presult)
+ addattr32(n, MAX_MSG, TCA_POLICE_RESULT, presult);
+
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ res = 0;
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return res;
+}
+
+int parse_police(int *argc_p, char ***argv_p, int tca_id, struct nlmsghdr *n)
+{
+ return act_parse_police(NULL,argc_p,argv_p,tca_id,n);
+}
+
+int
+print_police(struct action_util *a, FILE *f, struct rtattr *arg)
+{
+ SPRINT_BUF(b1);
+ SPRINT_BUF(b2);
+ struct tc_police *p;
+ struct rtattr *tb[TCA_POLICE_MAX+1];
+ unsigned buffer;
+ unsigned int linklayer;
+
+ if (arg == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_POLICE_MAX, arg);
+
+ if (tb[TCA_POLICE_TBF] == NULL) {
+ fprintf(f, "[NULL police tbf]");
+ return 0;
+ }
+#ifndef STOOPID_8BYTE
+ if (RTA_PAYLOAD(tb[TCA_POLICE_TBF]) < sizeof(*p)) {
+ fprintf(f, "[truncated police tbf]");
+ return -1;
+ }
+#endif
+ p = RTA_DATA(tb[TCA_POLICE_TBF]);
+
+ fprintf(f, " police 0x%x ", p->index);
+ fprintf(f, "rate %s ", sprint_rate(p->rate.rate, b1));
+ buffer = tc_calc_xmitsize(p->rate.rate, p->burst);
+ fprintf(f, "burst %s ", sprint_size(buffer, b1));
+ fprintf(f, "mtu %s ", sprint_size(p->mtu, b1));
+ if (show_raw)
+ fprintf(f, "[%08x] ", p->burst);
+ if (p->peakrate.rate)
+ fprintf(f, "peakrate %s ", sprint_rate(p->peakrate.rate, b1));
+ if (tb[TCA_POLICE_AVRATE])
+ fprintf(f, "avrate %s ", sprint_rate(rta_getattr_u32(tb[TCA_POLICE_AVRATE]), b1));
+ fprintf(f, "action %s", police_action_n2a(p->action, b1, sizeof(b1)));
+ if (tb[TCA_POLICE_RESULT]) {
+ fprintf(f, "/%s ", police_action_n2a(*(int*)RTA_DATA(tb[TCA_POLICE_RESULT]), b1, sizeof(b1)));
+ } else
+ fprintf(f, " ");
+ fprintf(f, "overhead %ub ", p->rate.overhead);
+ linklayer = (p->rate.linklayer & TC_LINKLAYER_MASK);
+ if (linklayer > TC_LINKLAYER_ETHERNET || show_details)
+ fprintf(f, "linklayer %s ", sprint_linklayer(linklayer, b2));
+ fprintf(f, "\nref %d bind %d\n",p->refcnt, p->bindcnt);
+
+ return 0;
+}
+
+int
+tc_print_police(FILE *f, struct rtattr *arg) {
+ return print_police(&police_action_util,f,arg);
+}
diff --git a/iproute2/tc/m_simple.c b/iproute2/tc/m_simple.c
new file mode 100644
index 0000000..1ad5526
--- /dev/null
+++ b/iproute2/tc/m_simple.c
@@ -0,0 +1,202 @@
+/*
+ * m_simple.c simple action
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: J Hadi Salim <jhs@mojatatu.com>
+ *
+ * Pedagogical example. Adds a string that will be printed every time
+ * the simple instance is hit.
+ * Use this as a skeleton action and keep modifying it to meet your needs.
+ * Look at linux/tc_act/tc_defact.h for the different components ids and
+ * definitions used in this actions
+ *
+ * example use, yell "Incoming ICMP!" every time you see an incoming ICMP on
+ * eth0. Steps are:
+ * 1) Add an ingress qdisc point to eth0
+ * 2) Start a chain on ingress of eth0 that first matches ICMP then invokes
+ * the simple action to shout.
+ * 3) display stats and show that no packet has been seen by the action
+ * 4) Send one ping packet to google (expect to receive a response back)
+ * 5) grep the logs to see the logged message
+ * 6) display stats again and observe increment by 1
+ *
+ hadi@noma1:$ tc qdisc add dev eth0 ingress
+ hadi@noma1:$tc filter add dev eth0 parent ffff: protocol ip prio 5 \
+ u32 match ip protocol 1 0xff flowid 1:1 action simple "Incoming ICMP"
+
+ hadi@noma1:$ sudo tc -s filter ls dev eth0 parent ffff:
+ filter protocol ip pref 5 u32
+ filter protocol ip pref 5 u32 fh 800: ht divisor 1
+ filter protocol ip pref 5 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:1
+ match 00010000/00ff0000 at 8
+ action order 1: Simple <Incoming ICMP>
+ index 4 ref 1 bind 1 installed 29 sec used 29 sec
+ Action statistics:
+ Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
+ backlog 0b 0p requeues 0
+
+
+ hadi@noma1$ ping -c 1 www.google.ca
+ PING www.google.ca (74.125.225.120) 56(84) bytes of data.
+ 64 bytes from ord08s08-in-f24.1e100.net (74.125.225.120): icmp_req=1 ttl=53 time=31.3 ms
+
+ --- www.google.ca ping statistics ---
+ 1 packets transmitted, 1 received, 0% packet loss, time 0ms
+ rtt min/avg/max/mdev = 31.316/31.316/31.316/0.000 ms
+
+ hadi@noma1$ dmesg | grep simple
+ [135354.473951] simple: Incoming ICMP_1
+
+ hadi@noma1$ sudo tc/tc -s filter ls dev eth0 parent ffff:
+ filter protocol ip pref 5 u32
+ filter protocol ip pref 5 u32 fh 800: ht divisor 1
+ filter protocol ip pref 5 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:1
+ match 00010000/00ff0000 at 8
+ action order 1: Simple <Incoming ICMP>
+ index 4 ref 1 bind 1 installed 206 sec used 67 sec
+ Action statistics:
+ Sent 84 bytes 1 pkt (dropped 0, overlimits 0 requeues 0)
+ backlog 0b 0p requeues 0
+*/
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include "utils.h"
+#include "tc_util.h"
+#include <linux/tc_act/tc_defact.h>
+
+#ifndef SIMP_MAX_DATA
+#define SIMP_MAX_DATA 32
+#endif
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... simple STRING\n"
+ "STRING being an arbitrary string\n"
+ "example: \"simple blah\"\n");
+}
+
+static void usage(void)
+{
+ explain();
+ exit(-1);
+}
+
+static int
+parse_simple(struct action_util *a, int *argc_p, char ***argv_p, int tca_id,
+ struct nlmsghdr *n)
+{
+ struct tc_defact sel = {};
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ int ok = 0;
+ struct rtattr *tail;
+ char *simpdata = NULL;
+
+
+ while (argc > 0) {
+ if (matches(*argv, "simple") == 0) {
+ NEXT_ARG();
+ simpdata = *argv;
+ ok = 1;
+ argc--;
+ argv++;
+ break;
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ } else {
+ break;
+ }
+
+ }
+
+ if (!ok) {
+ explain();
+ return -1;
+ }
+
+ if (argc) {
+ if (matches(*argv, "index") == 0) {
+ NEXT_ARG();
+ if (get_u32(&sel.index, *argv, 10)) {
+ fprintf(stderr, "simple: Illegal \"index\"\n");
+ return -1;
+ }
+ argc--;
+ argv++;
+ }
+ }
+
+ if (strlen(simpdata) > (SIMP_MAX_DATA - 1)) {
+ fprintf(stderr, "simple: Illegal string len %zu <%s> \n",
+ strlen(simpdata), simpdata);
+ return -1;
+ }
+
+ sel.action = TC_ACT_PIPE;
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, MAX_MSG, tca_id, NULL, 0);
+ addattr_l(n, MAX_MSG, TCA_DEF_PARMS, &sel, sizeof(sel));
+ addattr_l(n, MAX_MSG, TCA_DEF_DATA, simpdata, SIMP_MAX_DATA);
+ tail->rta_len = (char *)NLMSG_TAIL(n) - (char *)tail;
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return 0;
+}
+
+static int print_simple(struct action_util *au, FILE * f, struct rtattr *arg)
+{
+ struct tc_defact *sel;
+ struct rtattr *tb[TCA_DEF_MAX + 1];
+ char *simpdata;
+
+ if (arg == NULL)
+ return -1;
+
+ parse_rtattr_nested(tb, TCA_DEF_MAX, arg);
+
+ if (tb[TCA_DEF_PARMS] == NULL) {
+ fprintf(f, "[NULL simple parameters]");
+ return -1;
+ }
+ sel = RTA_DATA(tb[TCA_DEF_PARMS]);
+
+ if (tb[TCA_DEF_DATA] == NULL) {
+ fprintf(f, "[missing simple string]");
+ return -1;
+ }
+
+ simpdata = RTA_DATA(tb[TCA_DEF_DATA]);
+
+ fprintf(f, "Simple <%s>\n", simpdata);
+ fprintf(f, "\t index %d ref %d bind %d", sel->index,
+ sel->refcnt, sel->bindcnt);
+
+ if (show_stats) {
+ if (tb[TCA_DEF_TM]) {
+ struct tcf_t *tm = RTA_DATA(tb[TCA_DEF_TM]);
+ print_tm(f, tm);
+ }
+ }
+ fprintf(f, "\n");
+
+ return 0;
+}
+
+struct action_util simple_action_util = {
+ .id = "simple",
+ .parse_aopt = parse_simple,
+ .print_aopt = print_simple,
+};
diff --git a/iproute2/tc/m_skbedit.c b/iproute2/tc/m_skbedit.c
new file mode 100644
index 0000000..36323a9
--- /dev/null
+++ b/iproute2/tc/m_skbedit.c
@@ -0,0 +1,214 @@
+/*
+ * m_skbedit.c SKB Editing module
+ *
+ * Copyright (c) 2008, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses>.
+ *
+ * Authors: Alexander Duyck <alexander.h.duyck@intel.com>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include "utils.h"
+#include "tc_util.h"
+#include <linux/tc_act/tc_skbedit.h>
+
+static void
+explain(void)
+{
+ fprintf(stderr, "Usage: ... skbedit <[QM] [PM] [MM]>\n"
+ "QM = queue_mapping QUEUE_MAPPING\n"
+ "PM = priority PRIORITY \n"
+ "MM = mark MARK \n"
+ "QUEUE_MAPPING = device transmit queue to use\n"
+ "PRIORITY = classID to assign to priority field\n"
+ "MARK = firewall mark to set\n");
+}
+
+static void
+usage(void)
+{
+ explain();
+ exit(-1);
+}
+
+static int
+parse_skbedit(struct action_util *a, int *argc_p, char ***argv_p, int tca_id,
+ struct nlmsghdr *n)
+{
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ int ok = 0;
+ struct rtattr *tail;
+ unsigned int tmp;
+ __u16 queue_mapping;
+ __u32 flags = 0, priority, mark;
+ struct tc_skbedit sel = { 0 };
+
+ if (matches(*argv, "skbedit") != 0)
+ return -1;
+
+ NEXT_ARG();
+
+ while (argc > 0) {
+ if (matches(*argv, "queue_mapping") == 0) {
+ flags |= SKBEDIT_F_QUEUE_MAPPING;
+ NEXT_ARG();
+ if (get_unsigned(&tmp, *argv, 10) || tmp > 65535) {
+ fprintf(stderr, "Illegal queue_mapping\n");
+ return -1;
+ }
+ queue_mapping = tmp;
+ ok++;
+ } else if (matches(*argv, "priority") == 0) {
+ flags |= SKBEDIT_F_PRIORITY;
+ NEXT_ARG();
+ if (get_tc_classid(&priority, *argv)) {
+ fprintf(stderr, "Illegal priority\n");
+ return -1;
+ }
+ ok++;
+ } else if (matches(*argv, "mark") == 0) {
+ flags |= SKBEDIT_F_MARK;
+ NEXT_ARG();
+ if (get_u32(&mark, *argv, 0)) {
+ fprintf(stderr, "Illegal mark\n");
+ return -1;
+ }
+ ok++;
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ } else {
+ break;
+ }
+ argc--;
+ argv++;
+ }
+
+ sel.action = TC_ACT_PIPE;
+ if (argc) {
+ if (matches(*argv, "reclassify") == 0) {
+ sel.action = TC_ACT_RECLASSIFY;
+ NEXT_ARG();
+ } else if (matches(*argv, "pipe") == 0) {
+ sel.action = TC_ACT_PIPE;
+ NEXT_ARG();
+ } else if (matches(*argv, "drop") == 0 ||
+ matches(*argv, "shot") == 0) {
+ sel.action = TC_ACT_SHOT;
+ NEXT_ARG();
+ } else if (matches(*argv, "continue") == 0) {
+ sel.action = TC_ACT_UNSPEC;
+ NEXT_ARG();
+ } else if (matches(*argv, "pass") == 0) {
+ sel.action = TC_ACT_OK;
+ NEXT_ARG();
+ }
+ }
+
+ if (argc) {
+ if (matches(*argv, "index") == 0) {
+ NEXT_ARG();
+ if (get_u32(&sel.index, *argv, 10)) {
+ fprintf(stderr, "Pedit: Illegal \"index\"\n");
+ return -1;
+ }
+ argc--;
+ argv++;
+ ok++;
+ }
+ }
+
+ if (!ok) {
+ explain();
+ return -1;
+ }
+
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, MAX_MSG, tca_id, NULL, 0);
+ addattr_l(n, MAX_MSG, TCA_SKBEDIT_PARMS, &sel, sizeof(sel));
+ if (flags & SKBEDIT_F_QUEUE_MAPPING)
+ addattr_l(n, MAX_MSG, TCA_SKBEDIT_QUEUE_MAPPING,
+ &queue_mapping, sizeof(queue_mapping));
+ if (flags & SKBEDIT_F_PRIORITY)
+ addattr_l(n, MAX_MSG, TCA_SKBEDIT_PRIORITY,
+ &priority, sizeof(priority));
+ if (flags & SKBEDIT_F_MARK)
+ addattr_l(n, MAX_MSG, TCA_SKBEDIT_MARK,
+ &mark, sizeof(mark));
+ tail->rta_len = (char *)NLMSG_TAIL(n) - (char *)tail;
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return 0;
+}
+
+static int print_skbedit(struct action_util *au, FILE *f, struct rtattr *arg)
+{
+ struct rtattr *tb[TCA_SKBEDIT_MAX + 1];
+ SPRINT_BUF(b1);
+ __u32 *priority;
+ __u32 *mark;
+ __u16 *queue_mapping;
+ struct tc_skbedit *p = NULL;
+
+ if (arg == NULL)
+ return -1;
+
+ parse_rtattr_nested(tb, TCA_SKBEDIT_MAX, arg);
+
+ if (tb[TCA_SKBEDIT_PARMS] == NULL) {
+ fprintf(f, "[NULL skbedit parameters]");
+ return -1;
+ }
+ p = RTA_DATA(tb[TCA_SKBEDIT_PARMS]);
+
+ fprintf(f, " skbedit");
+
+ if (tb[TCA_SKBEDIT_QUEUE_MAPPING] != NULL) {
+ queue_mapping = RTA_DATA(tb[TCA_SKBEDIT_QUEUE_MAPPING]);
+ fprintf(f, " queue_mapping %u", *queue_mapping);
+ }
+ if (tb[TCA_SKBEDIT_PRIORITY] != NULL) {
+ priority = RTA_DATA(tb[TCA_SKBEDIT_PRIORITY]);
+ fprintf(f, " priority %s", sprint_tc_classid(*priority, b1));
+ }
+ if (tb[TCA_SKBEDIT_MARK] != NULL) {
+ mark = RTA_DATA(tb[TCA_SKBEDIT_MARK]);
+ fprintf(f, " mark %d", *mark);
+ }
+
+ fprintf(f, "\n\t index %d ref %d bind %d", p->index, p->refcnt, p->bindcnt);
+
+ if (show_stats) {
+ if (tb[TCA_SKBEDIT_TM]) {
+ struct tcf_t *tm = RTA_DATA(tb[TCA_SKBEDIT_TM]);
+ print_tm(f, tm);
+ }
+ }
+
+ fprintf(f, "\n ");
+
+ return 0;
+}
+
+struct action_util skbedit_action_util = {
+ .id = "skbedit",
+ .parse_aopt = parse_skbedit,
+ .print_aopt = print_skbedit,
+};
diff --git a/iproute2/tc/m_vlan.c b/iproute2/tc/m_vlan.c
new file mode 100644
index 0000000..32db5ed
--- /dev/null
+++ b/iproute2/tc/m_vlan.c
@@ -0,0 +1,227 @@
+/*
+ * m_vlan.c vlan manipulation module
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Jiri Pirko <jiri@resnulli.us>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <linux/if_ether.h>
+#include "utils.h"
+#include "rt_names.h"
+#include "tc_util.h"
+#include <linux/tc_act/tc_vlan.h>
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: vlan pop\n");
+ fprintf(stderr, " vlan push [ protocol VLANPROTO ] id VLANID\n");
+ fprintf(stderr, " VLANPROTO is one of 802.1Q or 802.1AD\n");
+ fprintf(stderr, " with default: 802.1Q\n");
+}
+
+static void usage(void)
+{
+ explain();
+ exit(-1);
+}
+
+static int parse_vlan(struct action_util *a, int *argc_p, char ***argv_p,
+ int tca_id, struct nlmsghdr *n)
+{
+ int argc = *argc_p;
+ char **argv = *argv_p;
+ struct rtattr *tail;
+ int action = 0;
+ __u16 id;
+ int id_set = 0;
+ __u16 proto;
+ int proto_set = 0;
+ struct tc_vlan parm = { 0 };
+
+ if (matches(*argv, "vlan") != 0)
+ return -1;
+
+ NEXT_ARG();
+
+ while (argc > 0) {
+ if (matches(*argv, "pop") == 0) {
+ if (action) {
+ fprintf(stderr, "unexpected \"%s\" - action already specified\n",
+ *argv);
+ explain();
+ return -1;
+ }
+ action = TCA_VLAN_ACT_POP;
+ } else if (matches(*argv, "push") == 0) {
+ if (action) {
+ fprintf(stderr, "unexpected \"%s\" - action already specified\n",
+ *argv);
+ explain();
+ return -1;
+ }
+ action = TCA_VLAN_ACT_PUSH;
+ } else if (matches(*argv, "id") == 0) {
+ if (action != TCA_VLAN_ACT_PUSH) {
+ fprintf(stderr, "\"%s\" is only valid for push\n",
+ *argv);
+ explain();
+ return -1;
+ }
+ NEXT_ARG();
+ if (get_u16(&id, *argv, 0))
+ invarg("id is invalid", *argv);
+ id_set = 1;
+ } else if (matches(*argv, "protocol") == 0) {
+ if (action != TCA_VLAN_ACT_PUSH) {
+ fprintf(stderr, "\"%s\" is only valid for push\n",
+ *argv);
+ explain();
+ return -1;
+ }
+ NEXT_ARG();
+ if (ll_proto_a2n(&proto, *argv))
+ invarg("protocol is invalid", *argv);
+ proto_set = 1;
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ } else {
+ break;
+ }
+ argc--;
+ argv++;
+ }
+
+ parm.action = TC_ACT_PIPE;
+ if (argc) {
+ if (matches(*argv, "reclassify") == 0) {
+ parm.action = TC_ACT_RECLASSIFY;
+ argc--;
+ argv++;
+ } else if (matches(*argv, "pipe") == 0) {
+ parm.action = TC_ACT_PIPE;
+ argc--;
+ argv++;
+ } else if (matches(*argv, "drop") == 0 ||
+ matches(*argv, "shot") == 0) {
+ parm.action = TC_ACT_SHOT;
+ argc--;
+ argv++;
+ } else if (matches(*argv, "continue") == 0) {
+ parm.action = TC_ACT_UNSPEC;
+ argc--;
+ argv++;
+ } else if (matches(*argv, "pass") == 0) {
+ parm.action = TC_ACT_OK;
+ argc--;
+ argv++;
+ }
+ }
+
+ if (argc) {
+ if (matches(*argv, "index") == 0) {
+ NEXT_ARG();
+ if (get_u32(&parm.index, *argv, 10)) {
+ fprintf(stderr, "vlan: Illegal \"index\"\n");
+ return -1;
+ }
+ argc--;
+ argv++;
+ }
+ }
+
+ if (action == TCA_VLAN_ACT_PUSH && !id_set) {
+ fprintf(stderr, "id needs to be set for push\n");
+ explain();
+ return -1;
+ }
+
+ parm.v_action = action;
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, MAX_MSG, tca_id, NULL, 0);
+ addattr_l(n, MAX_MSG, TCA_VLAN_PARMS, &parm, sizeof(parm));
+ if (id_set)
+ addattr_l(n, MAX_MSG, TCA_VLAN_PUSH_VLAN_ID, &id, 2);
+ if (proto_set) {
+ if (proto != htons(ETH_P_8021Q) &&
+ proto != htons(ETH_P_8021AD)) {
+ fprintf(stderr, "protocol not supported\n");
+ explain();
+ return -1;
+ }
+
+ addattr_l(n, MAX_MSG, TCA_VLAN_PUSH_VLAN_PROTOCOL, &proto, 2);
+ }
+ tail->rta_len = (char *)NLMSG_TAIL(n) - (char *)tail;
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return 0;
+}
+
+static int print_vlan(struct action_util *au, FILE *f, struct rtattr *arg)
+{
+ SPRINT_BUF(b1);
+ struct rtattr *tb[TCA_VLAN_MAX + 1];
+ __u16 val;
+ struct tc_vlan *parm;
+
+ if (arg == NULL)
+ return -1;
+
+ parse_rtattr_nested(tb, TCA_VLAN_MAX, arg);
+
+ if (!tb[TCA_VLAN_PARMS]) {
+ fprintf(f, "[NULL vlan parameters]");
+ return -1;
+ }
+ parm = RTA_DATA(tb[TCA_VLAN_PARMS]);
+
+ fprintf(f, " vlan");
+
+ switch(parm->v_action) {
+ case TCA_VLAN_ACT_POP:
+ fprintf(f, " pop");
+ break;
+ case TCA_VLAN_ACT_PUSH:
+ fprintf(f, " push");
+ if (tb[TCA_VLAN_PUSH_VLAN_ID]) {
+ val = rta_getattr_u16(tb[TCA_VLAN_PUSH_VLAN_ID]);
+ fprintf(f, " id %u", val);
+ }
+ if (tb[TCA_VLAN_PUSH_VLAN_PROTOCOL]) {
+ fprintf(f, " protocol %s",
+ ll_proto_n2a(rta_getattr_u16(tb[TCA_VLAN_PUSH_VLAN_PROTOCOL]),
+ b1, sizeof(b1)));
+ }
+ break;
+ }
+ fprintf(f, " %s", action_n2a(parm->action, b1, sizeof (b1)));
+
+ fprintf(f, "\n\t index %d ref %d bind %d", parm->index, parm->refcnt,
+ parm->bindcnt);
+
+ if (show_stats) {
+ if (tb[TCA_VLAN_TM]) {
+ struct tcf_t *tm = RTA_DATA(tb[TCA_VLAN_TM]);
+ print_tm(f, tm);
+ }
+ }
+
+ fprintf(f, "\n ");
+
+ return 0;
+}
+
+struct action_util vlan_action_util = {
+ .id = "vlan",
+ .parse_aopt = parse_vlan,
+ .print_aopt = print_vlan,
+};
diff --git a/iproute2/tc/m_xt.c b/iproute2/tc/m_xt.c
new file mode 100644
index 0000000..bf603fc
--- /dev/null
+++ b/iproute2/tc/m_xt.c
@@ -0,0 +1,390 @@
+/*
+ * m_xt.c xtables based targets
+ * utilities mostly ripped from iptables <duh, its the linux way>
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: J Hadi Salim (hadi@cyberus.ca)
+ */
+
+#include <syslog.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <net/if.h>
+#include <limits.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv4/ip_tables.h>
+#include <xtables.h>
+#include "utils.h"
+#include "tc_util.h"
+#include <linux/tc_act/tc_ipt.h>
+#include <stdio.h>
+#include <dlfcn.h>
+#include <getopt.h>
+#include <errno.h>
+#include <string.h>
+#include <netdb.h>
+#include <stdlib.h>
+#include <ctype.h>
+#include <stdarg.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/wait.h>
+#ifndef XT_LIB_DIR
+# define XT_LIB_DIR "/lib/xtables"
+#endif
+
+#ifndef __ALIGN_KERNEL
+#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
+#define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask))
+#endif
+
+#ifndef ALIGN
+#define ALIGN(x,a) __ALIGN_KERNEL((x), (a))
+#endif
+
+static const char *tname = "mangle";
+
+char *lib_dir;
+
+static const char *ipthooks[] = {
+ "NF_IP_PRE_ROUTING",
+ "NF_IP_LOCAL_IN",
+ "NF_IP_FORWARD",
+ "NF_IP_LOCAL_OUT",
+ "NF_IP_POST_ROUTING",
+};
+
+static struct option original_opts[] = {
+ {
+ .name = "jump",
+ .has_arg = 1,
+ .val = 'j'
+ },
+ {0, 0, 0, 0}
+};
+
+static struct xtables_globals tcipt_globals = {
+ .option_offset = 0,
+ .program_name = "tc-ipt",
+ .program_version = "0.2",
+ .orig_opts = original_opts,
+ .opts = original_opts,
+ .exit_err = NULL,
+};
+
+/*
+ * we may need to check for version mismatch
+*/
+static int
+build_st(struct xtables_target *target, struct xt_entry_target *t)
+{
+
+ size_t size =
+ XT_ALIGN(sizeof (struct xt_entry_target)) + target->size;
+
+ if (NULL == t) {
+ target->t = xtables_calloc(1, size);
+ target->t->u.target_size = size;
+ strcpy(target->t->u.user.name, target->name);
+ target->t->u.user.revision = target->revision;
+
+ if (target->init != NULL)
+ target->init(target->t);
+ } else {
+ target->t = t;
+ }
+ return 0;
+
+}
+
+static void set_lib_dir(void)
+{
+
+ lib_dir = getenv("XTABLES_LIBDIR");
+ if (!lib_dir) {
+ lib_dir = getenv("IPTABLES_LIB_DIR");
+ if (lib_dir)
+ fprintf(stderr, "using deprecated IPTABLES_LIB_DIR \n");
+ }
+ if (lib_dir == NULL)
+ lib_dir = XT_LIB_DIR;
+
+}
+
+static int parse_ipt(struct action_util *a,int *argc_p,
+ char ***argv_p, int tca_id, struct nlmsghdr *n)
+{
+ struct xtables_target *m = NULL;
+ struct ipt_entry fw;
+ struct rtattr *tail;
+
+ int c;
+ int rargc = *argc_p;
+ char **argv = *argv_p;
+ int argc = 0, iargc = 0;
+ char k[16];
+ int size = 0;
+ int iok = 0, ok = 0;
+ __u32 hook = 0, index = 0;
+ struct option *opts = NULL;
+
+ xtables_init_all(&tcipt_globals, NFPROTO_IPV4);
+ set_lib_dir();
+
+ {
+ int i;
+ for (i = 0; i < rargc; i++) {
+ if (NULL == argv[i] || 0 == strcmp(argv[i], "action")) {
+ break;
+ }
+ }
+ iargc = argc = i;
+ }
+
+ if (argc <= 2) {
+ fprintf(stderr,"bad arguments to ipt %d vs %d \n", argc, rargc);
+ return -1;
+ }
+
+ while (1) {
+ c = getopt_long(argc, argv, "j:", tcipt_globals.opts, NULL);
+ if (c == -1)
+ break;
+ switch (c) {
+ case 'j':
+ m = xtables_find_target(optarg, XTF_TRY_LOAD);
+ if (NULL != m) {
+
+ if (0 > build_st(m, NULL)) {
+ printf(" %s error \n", m->name);
+ return -1;
+ }
+#if (XTABLES_VERSION_CODE >= 6)
+ opts = xtables_options_xfrm(tcipt_globals.orig_opts,
+ tcipt_globals.opts,
+ m->x6_options,
+ &m->option_offset);
+#else
+ opts = xtables_merge_options(tcipt_globals.opts,
+ m->extra_opts,
+ &m->option_offset);
+#endif
+ if (opts == NULL) {
+ fprintf(stderr, " failed to find additional options for target %s\n\n", optarg);
+ return -1;
+ } else
+ tcipt_globals.opts = opts;
+ } else {
+ fprintf(stderr," failed to find target %s\n\n", optarg);
+ return -1;
+ }
+ ok++;
+ break;
+
+ default:
+ memset(&fw, 0, sizeof (fw));
+#if (XTABLES_VERSION_CODE >= 6)
+ if (m != NULL && m->x6_parse != NULL ) {
+ xtables_option_tpcall(c, argv, 0 , m, NULL);
+#else
+ if (m != NULL && m->parse != NULL ) {
+ m->parse(c - m->option_offset, argv, 0, &m->tflags,
+ NULL, &m->t);
+#endif
+ } else {
+ fprintf(stderr,"failed to find target %s\n\n", optarg);
+ return -1;
+
+ }
+ ok++;
+ break;
+ }
+ }
+
+ if (iargc > optind) {
+ if (matches(argv[optind], "index") == 0) {
+ if (get_u32(&index, argv[optind + 1], 10)) {
+ fprintf(stderr, "Illegal \"index\"\n");
+ xtables_free_opts(1);
+ return -1;
+ }
+ iok++;
+
+ optind += 2;
+ }
+ }
+
+ if (!ok && !iok) {
+ fprintf(stderr," ipt Parser BAD!! (%s)\n", *argv);
+ return -1;
+ }
+
+ /* check that we passed the correct parameters to the target */
+#if (XTABLES_VERSION_CODE >= 6)
+ if (m)
+ xtables_option_tfcall(m);
+#else
+ if (m && m->final_check)
+ m->final_check(m->tflags);
+#endif
+
+ {
+ struct tcmsg *t = NLMSG_DATA(n);
+ if (t->tcm_parent != TC_H_ROOT
+ && t->tcm_parent == TC_H_MAJ(TC_H_INGRESS)) {
+ hook = NF_IP_PRE_ROUTING;
+ } else {
+ hook = NF_IP_POST_ROUTING;
+ }
+ }
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, MAX_MSG, tca_id, NULL, 0);
+ fprintf(stdout, "tablename: %s hook: %s\n ", tname, ipthooks[hook]);
+ fprintf(stdout, "\ttarget: ");
+
+ if (m)
+ m->print(NULL, m->t, 0);
+ fprintf(stdout, " index %d\n", index);
+
+ if (strlen(tname) > 16) {
+ size = 16;
+ k[15] = 0;
+ } else {
+ size = 1 + strlen(tname);
+ }
+ strncpy(k, tname, size);
+
+ addattr_l(n, MAX_MSG, TCA_IPT_TABLE, k, size);
+ addattr_l(n, MAX_MSG, TCA_IPT_HOOK, &hook, 4);
+ addattr_l(n, MAX_MSG, TCA_IPT_INDEX, &index, 4);
+ if (m)
+ addattr_l(n, MAX_MSG, TCA_IPT_TARG, m->t, m->t->u.target_size);
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+
+ argc -= optind;
+ argv += optind;
+ *argc_p = rargc - iargc;
+ *argv_p = argv;
+
+ optind = 0;
+ xtables_free_opts(1);
+
+ if (m) {
+ /* Clear flags if target will be used again */
+ m->tflags = 0;
+ m->used = 0;
+ /* Free allocated memory */
+ if (m->t)
+ free(m->t);
+ }
+
+ return 0;
+
+}
+
+static int
+print_ipt(struct action_util *au,FILE * f, struct rtattr *arg)
+{
+ struct rtattr *tb[TCA_IPT_MAX + 1];
+ struct xt_entry_target *t = NULL;
+ struct option *opts = NULL;
+
+ if (arg == NULL)
+ return -1;
+
+ /* copy tcipt_globals because .opts will be modified by iptables */
+ struct xtables_globals tmp_tcipt_globals = tcipt_globals;
+
+ xtables_init_all(&tmp_tcipt_globals, NFPROTO_IPV4);
+ set_lib_dir();
+
+ parse_rtattr_nested(tb, TCA_IPT_MAX, arg);
+
+ if (tb[TCA_IPT_TABLE] == NULL) {
+ fprintf(f, "[NULL ipt table name ] assuming mangle ");
+ } else {
+ fprintf(f, "tablename: %s ",
+ rta_getattr_str(tb[TCA_IPT_TABLE]));
+ }
+
+ if (tb[TCA_IPT_HOOK] == NULL) {
+ fprintf(f, "[NULL ipt hook name ]\n ");
+ return -1;
+ } else {
+ __u32 hook;
+ hook = rta_getattr_u32(tb[TCA_IPT_HOOK]);
+ fprintf(f, " hook: %s \n", ipthooks[hook]);
+ }
+
+ if (tb[TCA_IPT_TARG] == NULL) {
+ fprintf(f, "\t[NULL ipt target parameters ] \n");
+ return -1;
+ } else {
+ struct xtables_target *m = NULL;
+ t = RTA_DATA(tb[TCA_IPT_TARG]);
+ m = xtables_find_target(t->u.user.name, XTF_TRY_LOAD);
+ if (NULL != m) {
+ if (0 > build_st(m, t)) {
+ fprintf(stderr, " %s error \n", m->name);
+ return -1;
+ }
+
+#if (XTABLES_VERSION_CODE >= 6)
+ opts = xtables_options_xfrm(tmp_tcipt_globals.orig_opts,
+ tmp_tcipt_globals.opts,
+ m->x6_options,
+ &m->option_offset);
+#else
+ opts = xtables_merge_options(tmp_tcipt_globals.opts,
+ m->extra_opts,
+ &m->option_offset);
+#endif
+ if (opts == NULL) {
+ fprintf(stderr, " failed to find additional options for target %s\n\n", optarg);
+ return -1;
+ } else
+ tmp_tcipt_globals.opts = opts;
+ } else {
+ fprintf(stderr, " failed to find target %s\n\n",
+ t->u.user.name);
+ return -1;
+ }
+ fprintf(f, "\ttarget ");
+ m->print(NULL, m->t, 0);
+ if (tb[TCA_IPT_INDEX] == NULL) {
+ fprintf(f, " [NULL ipt target index ]\n");
+ } else {
+ __u32 index;
+ index = rta_getattr_u32(tb[TCA_IPT_INDEX]);
+ fprintf(f, " \n\tindex %d", index);
+ }
+
+ if (tb[TCA_IPT_CNT]) {
+ struct tc_cnt *c = RTA_DATA(tb[TCA_IPT_CNT]);;
+ fprintf(f, " ref %d bind %d", c->refcnt, c->bindcnt);
+ }
+ if (show_stats) {
+ if (tb[TCA_IPT_TM]) {
+ struct tcf_t *tm = RTA_DATA(tb[TCA_IPT_TM]);
+ print_tm(f,tm);
+ }
+ }
+ fprintf(f, " \n");
+
+ }
+ xtables_free_opts(1);
+
+ return 0;
+}
+
+struct action_util xt_action_util = {
+ .id = "xt",
+ .parse_aopt = parse_ipt,
+ .print_aopt = print_ipt,
+};
diff --git a/iproute2/tc/m_xt_old.c b/iproute2/tc/m_xt_old.c
new file mode 100644
index 0000000..6e64308
--- /dev/null
+++ b/iproute2/tc/m_xt_old.c
@@ -0,0 +1,435 @@
+/*
+ * m_xt.c xtables based targets
+ * utilities mostly ripped from iptables <duh, its the linux way>
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: J Hadi Salim (hadi@cyberus.ca)
+ */
+
+/*XXX: in the future (xtables 1.4.3?) get rid of everything tagged
+ * as TC_CONFIG_XT_H */
+
+#include <syslog.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <net/if.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv4/ip_tables.h>
+#include <xtables.h>
+#include "utils.h"
+#include "tc_util.h"
+#include <linux/tc_act/tc_ipt.h>
+#include <stdio.h>
+#include <getopt.h>
+#include <errno.h>
+#include <string.h>
+#include <netdb.h>
+#include <stdlib.h>
+#include <ctype.h>
+#include <stdarg.h>
+#include <limits.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/wait.h>
+#ifdef TC_CONFIG_XT_H
+#include "xt-internal.h"
+#endif
+
+#ifndef ALIGN
+#define ALIGN(x,a) __ALIGN_MASK(x,(typeof(x))(a)-1)
+#define __ALIGN_MASK(x,mask) (((x)+(mask))&~(mask))
+#endif
+
+static const char *pname = "tc-ipt";
+static const char *tname = "mangle";
+static const char *pversion = "0.2";
+
+static const char *ipthooks[] = {
+ "NF_IP_PRE_ROUTING",
+ "NF_IP_LOCAL_IN",
+ "NF_IP_FORWARD",
+ "NF_IP_LOCAL_OUT",
+ "NF_IP_POST_ROUTING",
+};
+
+static struct option original_opts[] = {
+ {"jump", 1, 0, 'j'},
+ {0, 0, 0, 0}
+};
+
+static struct option *opts = original_opts;
+static unsigned int global_option_offset = 0;
+char *lib_dir;
+const char *program_version = XTABLES_VERSION;
+const char *program_name = "tc-ipt";
+struct afinfo afinfo = {
+ .family = AF_INET,
+ .libprefix = "libxt_",
+ .ipproto = IPPROTO_IP,
+ .kmod = "ip_tables",
+ .so_rev_target = IPT_SO_GET_REVISION_TARGET,
+};
+
+
+#define OPTION_OFFSET 256
+
+/*XXX: TC_CONFIG_XT_H */
+static void free_opts(struct option *local_opts)
+{
+ if (local_opts != original_opts) {
+ free(local_opts);
+ opts = original_opts;
+ global_option_offset = 0;
+ }
+}
+
+/*XXX: TC_CONFIG_XT_H */
+static struct option *
+merge_options(struct option *oldopts, const struct option *newopts,
+ unsigned int *option_offset)
+{
+ struct option *merge;
+ unsigned int num_old, num_new, i;
+
+ for (num_old = 0; oldopts[num_old].name; num_old++) ;
+ for (num_new = 0; newopts[num_new].name; num_new++) ;
+
+ *option_offset = global_option_offset + OPTION_OFFSET;
+
+ merge = malloc(sizeof (struct option) * (num_new + num_old + 1));
+ memcpy(merge, oldopts, num_old * sizeof (struct option));
+ for (i = 0; i < num_new; i++) {
+ merge[num_old + i] = newopts[i];
+ merge[num_old + i].val += *option_offset;
+ }
+ memset(merge + num_old + num_new, 0, sizeof (struct option));
+
+ return merge;
+}
+
+
+/*XXX: TC_CONFIG_XT_H */
+#ifndef TRUE
+#define TRUE 1
+#endif
+#ifndef FALSE
+#define FALSE 0
+#endif
+
+/*XXX: TC_CONFIG_XT_H */
+int
+check_inverse(const char option[], int *invert, int *my_optind, int argc)
+{
+ if (option && strcmp(option, "!") == 0) {
+ if (*invert)
+ exit_error(PARAMETER_PROBLEM,
+ "Multiple `!' flags not allowed");
+ *invert = TRUE;
+ if (my_optind != NULL) {
+ ++*my_optind;
+ if (argc && *my_optind > argc)
+ exit_error(PARAMETER_PROBLEM,
+ "no argument following `!'");
+ }
+
+ return TRUE;
+ }
+ return FALSE;
+}
+
+/*XXX: TC_CONFIG_XT_H */
+void exit_error(enum exittype status, const char *msg, ...)
+{
+ va_list args;
+
+ va_start(args, msg);
+ fprintf(stderr, "%s v%s: ", pname, pversion);
+ vfprintf(stderr, msg, args);
+ va_end(args);
+ fprintf(stderr, "\n");
+ /* On error paths, make sure that we don't leak memory */
+ exit(status);
+}
+
+/*XXX: TC_CONFIG_XT_H */
+static void set_revision(char *name, u_int8_t revision)
+{
+ /* Old kernel sources don't have ".revision" field,
+ * but we stole a byte from name. */
+ name[IPT_FUNCTION_MAXNAMELEN - 2] = '\0';
+ name[IPT_FUNCTION_MAXNAMELEN - 1] = revision;
+}
+
+/*
+ * we may need to check for version mismatch
+*/
+int
+build_st(struct xtables_target *target, struct xt_entry_target *t)
+{
+
+ size_t size =
+ XT_ALIGN(sizeof (struct xt_entry_target)) + target->size;
+
+ if (NULL == t) {
+ target->t = fw_calloc(1, size);
+ target->t->u.target_size = size;
+ strcpy(target->t->u.user.name, target->name);
+ set_revision(target->t->u.user.name, target->revision);
+
+ if (target->init != NULL)
+ target->init(target->t);
+ } else {
+ target->t = t;
+ }
+ return 0;
+
+}
+
+inline void set_lib_dir(void)
+{
+
+ lib_dir = getenv("XTABLES_LIBDIR");
+ if (!lib_dir) {
+ lib_dir = getenv("IPTABLES_LIB_DIR");
+ if (lib_dir)
+ fprintf(stderr, "using deprecated IPTABLES_LIB_DIR \n");
+ }
+ if (lib_dir == NULL)
+ lib_dir = XT_LIB_DIR;
+
+}
+
+static int parse_ipt(struct action_util *a,int *argc_p,
+ char ***argv_p, int tca_id, struct nlmsghdr *n)
+{
+ struct xtables_target *m = NULL;
+ struct ipt_entry fw;
+ struct rtattr *tail;
+ int c;
+ int rargc = *argc_p;
+ char **argv = *argv_p;
+ int argc = 0, iargc = 0;
+ char k[16];
+ int size = 0;
+ int iok = 0, ok = 0;
+ __u32 hook = 0, index = 0;
+
+ set_lib_dir();
+
+ {
+ int i;
+ for (i = 0; i < rargc; i++) {
+ if (NULL == argv[i] || 0 == strcmp(argv[i], "action")) {
+ break;
+ }
+ }
+ iargc = argc = i;
+ }
+
+ if (argc <= 2) {
+ fprintf(stderr,"bad arguments to ipt %d vs %d \n", argc, rargc);
+ return -1;
+ }
+
+ while (1) {
+ c = getopt_long(argc, argv, "j:", opts, NULL);
+ if (c == -1)
+ break;
+ switch (c) {
+ case 'j':
+ m = find_target(optarg, TRY_LOAD);
+ if (NULL != m) {
+
+ if (0 > build_st(m, NULL)) {
+ printf(" %s error \n", m->name);
+ return -1;
+ }
+ opts =
+ merge_options(opts, m->extra_opts,
+ &m->option_offset);
+ } else {
+ fprintf(stderr," failed to find target %s\n\n", optarg);
+ return -1;
+ }
+ ok++;
+ break;
+
+ default:
+ memset(&fw, 0, sizeof (fw));
+ if (m) {
+ m->parse(c - m->option_offset, argv, 0,
+ &m->tflags, NULL, &m->t);
+ } else {
+ fprintf(stderr," failed to find target %s\n\n", optarg);
+ return -1;
+
+ }
+ ok++;
+ break;
+
+ }
+ }
+
+ if (iargc > optind) {
+ if (matches(argv[optind], "index") == 0) {
+ if (get_u32(&index, argv[optind + 1], 10)) {
+ fprintf(stderr, "Illegal \"index\"\n");
+ free_opts(opts);
+ return -1;
+ }
+ iok++;
+
+ optind += 2;
+ }
+ }
+
+ if (!ok && !iok) {
+ fprintf(stderr," ipt Parser BAD!! (%s)\n", *argv);
+ return -1;
+ }
+
+ /* check that we passed the correct parameters to the target */
+ if (m)
+ m->final_check(m->tflags);
+
+ {
+ struct tcmsg *t = NLMSG_DATA(n);
+ if (t->tcm_parent != TC_H_ROOT
+ && t->tcm_parent == TC_H_MAJ(TC_H_INGRESS)) {
+ hook = NF_IP_PRE_ROUTING;
+ } else {
+ hook = NF_IP_POST_ROUTING;
+ }
+ }
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, MAX_MSG, tca_id, NULL, 0);
+ fprintf(stdout, "tablename: %s hook: %s\n ", tname, ipthooks[hook]);
+ fprintf(stdout, "\ttarget: ");
+
+ if (m)
+ m->print(NULL, m->t, 0);
+ fprintf(stdout, " index %d\n", index);
+
+ if (strlen(tname) > 16) {
+ size = 16;
+ k[15] = 0;
+ } else {
+ size = 1 + strlen(tname);
+ }
+ strncpy(k, tname, size);
+
+ addattr_l(n, MAX_MSG, TCA_IPT_TABLE, k, size);
+ addattr_l(n, MAX_MSG, TCA_IPT_HOOK, &hook, 4);
+ addattr_l(n, MAX_MSG, TCA_IPT_INDEX, &index, 4);
+ if (m)
+ addattr_l(n, MAX_MSG, TCA_IPT_TARG, m->t, m->t->u.target_size);
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+
+ argc -= optind;
+ argv += optind;
+ *argc_p = rargc - iargc;
+ *argv_p = argv;
+
+ optind = 0;
+ free_opts(opts);
+ /* Clear flags if target will be used again */
+ m->tflags=0;
+ m->used=0;
+ /* Free allocated memory */
+ if (m->t)
+ free(m->t);
+
+
+ return 0;
+
+}
+
+static int
+print_ipt(struct action_util *au,FILE * f, struct rtattr *arg)
+{
+ struct rtattr *tb[TCA_IPT_MAX + 1];
+ struct xt_entry_target *t = NULL;
+
+ if (arg == NULL)
+ return -1;
+
+ set_lib_dir();
+
+ parse_rtattr_nested(tb, TCA_IPT_MAX, arg);
+
+ if (tb[TCA_IPT_TABLE] == NULL) {
+ fprintf(f, "[NULL ipt table name ] assuming mangle ");
+ } else {
+ fprintf(f, "tablename: %s ",
+ rta_getattr_str(tb[TCA_IPT_TABLE]));
+ }
+
+ if (tb[TCA_IPT_HOOK] == NULL) {
+ fprintf(f, "[NULL ipt hook name ]\n ");
+ return -1;
+ } else {
+ __u32 hook;
+ hook = rta_getattr_u32(tb[TCA_IPT_HOOK]);
+ fprintf(f, " hook: %s \n", ipthooks[hook]);
+ }
+
+ if (tb[TCA_IPT_TARG] == NULL) {
+ fprintf(f, "\t[NULL ipt target parameters ] \n");
+ return -1;
+ } else {
+ struct xtables_target *m = NULL;
+ t = RTA_DATA(tb[TCA_IPT_TARG]);
+ m = find_target(t->u.user.name, TRY_LOAD);
+ if (NULL != m) {
+ if (0 > build_st(m, t)) {
+ fprintf(stderr, " %s error \n", m->name);
+ return -1;
+ }
+
+ opts =
+ merge_options(opts, m->extra_opts,
+ &m->option_offset);
+ } else {
+ fprintf(stderr, " failed to find target %s\n\n",
+ t->u.user.name);
+ return -1;
+ }
+ fprintf(f, "\ttarget ");
+ m->print(NULL, m->t, 0);
+ if (tb[TCA_IPT_INDEX] == NULL) {
+ fprintf(f, " [NULL ipt target index ]\n");
+ } else {
+ __u32 index;
+ index = rta_getattr_u32(tb[TCA_IPT_INDEX]);
+ fprintf(f, " \n\tindex %d", index);
+ }
+
+ if (tb[TCA_IPT_CNT]) {
+ struct tc_cnt *c = RTA_DATA(tb[TCA_IPT_CNT]);;
+ fprintf(f, " ref %d bind %d", c->refcnt, c->bindcnt);
+ }
+ if (show_stats) {
+ if (tb[TCA_IPT_TM]) {
+ struct tcf_t *tm = RTA_DATA(tb[TCA_IPT_TM]);
+ print_tm(f,tm);
+ }
+ }
+ fprintf(f, " \n");
+
+ }
+ free_opts(opts);
+
+ return 0;
+}
+
+struct action_util ipt_action_util = {
+ .id = "ipt",
+ .parse_aopt = parse_ipt,
+ .print_aopt = print_ipt,
+};
diff --git a/iproute2/tc/p_icmp.c b/iproute2/tc/p_icmp.c
new file mode 100644
index 0000000..a4b80c2
--- /dev/null
+++ b/iproute2/tc/p_icmp.c
@@ -0,0 +1,61 @@
+/*
+ * m_pedit_icmp.c packet editor: ICMP header
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: J Hadi Salim (hadi@cyberus.ca)
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include "utils.h"
+#include "tc_util.h"
+#include "m_pedit.h"
+
+
+static int
+parse_icmp(int *argc_p, char ***argv_p,struct tc_pedit_sel *sel,struct tc_pedit_key *tkey)
+{
+ int res = -1;
+#if 0
+ int argc = *argc_p;
+ char **argv = *argv_p;
+
+ if (argc < 2)
+ return -1;
+
+ if (strcmp(*argv, "type") == 0) {
+ NEXT_ARG();
+ res = parse_u8(&argc, &argv, 0);
+ goto done;
+ }
+ if (strcmp(*argv, "code") == 0) {
+ NEXT_ARG();
+ res = parse_u8(&argc, &argv, 1);
+ goto done;
+ }
+ return -1;
+
+ done:
+ *argc_p = argc;
+ *argv_p = argv;
+#endif
+ return res;
+}
+
+struct m_pedit_util p_pedit_icmp = {
+ NULL,
+ "icmp",
+ parse_icmp,
+};
diff --git a/iproute2/tc/p_ip.c b/iproute2/tc/p_ip.c
new file mode 100644
index 0000000..08fdbaa
--- /dev/null
+++ b/iproute2/tc/p_ip.c
@@ -0,0 +1,159 @@
+/*
+ * m_pedit.c packet editor: IPV4/6 header
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: J Hadi Salim (hadi@cyberus.ca)
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include "utils.h"
+#include "tc_util.h"
+#include "m_pedit.h"
+
+static int
+parse_ip(int *argc_p, char ***argv_p,struct tc_pedit_sel *sel,struct tc_pedit_key *tkey)
+{
+ int res = -1;
+ int argc = *argc_p;
+ char **argv = *argv_p;
+
+ if (argc < 2)
+ return -1;
+
+ if (strcmp(*argv, "src") == 0) {
+ NEXT_ARG();
+ tkey->off = 12;
+ res = parse_cmd(&argc, &argv, 4, TIPV4,RU32,sel,tkey);
+ goto done;
+ }
+ if (strcmp(*argv, "dst") == 0) {
+ NEXT_ARG();
+ tkey->off = 16;
+ res = parse_cmd(&argc, &argv, 4, TIPV4,RU32,sel,tkey);
+ goto done;
+ }
+ /* jamal - look at these and make them either old or new
+ ** scheme given diffserv
+ ** dont forget the CE bit
+ */
+ if (strcmp(*argv, "tos") == 0 || matches(*argv, "dsfield") == 0) {
+ NEXT_ARG();
+ tkey->off = 1;
+ res = parse_cmd(&argc, &argv, 1, TU32,RU8,sel,tkey);
+ goto done;
+ }
+ if (strcmp(*argv, "ihl") == 0) {
+ NEXT_ARG();
+ tkey->off = 0;
+ res = parse_cmd(&argc, &argv, 1, TU32,RU8,sel,tkey);
+ goto done;
+ }
+ if (strcmp(*argv, "protocol") == 0) {
+ NEXT_ARG();
+ tkey->off = 9;
+ res = parse_cmd(&argc, &argv, 1, TU32,RU8,sel,tkey);
+ goto done;
+ }
+ /* jamal - fix this */
+ if (matches(*argv, "precedence") == 0) {
+ NEXT_ARG();
+ tkey->off = 1;
+ res = parse_cmd(&argc, &argv, 1, TU32,RU8,sel,tkey);
+ goto done;
+ }
+ /* jamal - validate this at some point */
+ if (strcmp(*argv, "nofrag") == 0) {
+ NEXT_ARG();
+ tkey->off = 6;
+ res = parse_cmd(&argc, &argv, 1, TU32,0x3F,sel,tkey);
+ goto done;
+ }
+ /* jamal - validate this at some point */
+ if (strcmp(*argv, "firstfrag") == 0) {
+ NEXT_ARG();
+ tkey->off = 6;
+ res = parse_cmd(&argc, &argv, 1, TU32,0x1F,sel,tkey);
+ goto done;
+ }
+ if (strcmp(*argv, "ce") == 0) {
+ NEXT_ARG();
+ tkey->off = 6;
+ res = parse_cmd(&argc, &argv, 1, TU32,0x80,sel,tkey);
+ goto done;
+ }
+ if (strcmp(*argv, "df") == 0) {
+ NEXT_ARG();
+ tkey->off = 6;
+ res = parse_cmd(&argc, &argv, 1, TU32,0x40,sel,tkey);
+ goto done;
+ }
+ if (strcmp(*argv, "mf") == 0) {
+ NEXT_ARG();
+ tkey->off = 6;
+ res = parse_cmd(&argc, &argv, 1, TU32,0x20,sel,tkey);
+ goto done;
+ }
+ if (strcmp(*argv, "dport") == 0) {
+ NEXT_ARG();
+ tkey->off = 22;
+ res = parse_cmd(&argc, &argv, 2, TU32,RU16,sel,tkey);
+ goto done;
+ }
+ if (strcmp(*argv, "sport") == 0) {
+ NEXT_ARG();
+ tkey->off = 20;
+ res = parse_cmd(&argc, &argv, 2, TU32,RU16,sel,tkey);
+ goto done;
+ }
+ if (strcmp(*argv, "icmp_type") == 0) {
+ NEXT_ARG();
+ tkey->off = 20;
+ res = parse_cmd(&argc, &argv, 1, TU32,RU8,sel,tkey);
+ goto done;
+ }
+ if (strcmp(*argv, "icmp_code") == 0) {
+ NEXT_ARG();
+ tkey->off = 20;
+ res = parse_cmd(&argc, &argv, 1, TU32,RU8,sel,tkey);
+ goto done;
+ }
+ return -1;
+
+ done:
+ *argc_p = argc;
+ *argv_p = argv;
+ return res;
+}
+
+static int
+parse_ip6(int *argc_p, char ***argv_p,struct tc_pedit_sel *sel,struct tc_pedit_key *tkey)
+{
+ int res = -1;
+ return res;
+}
+
+struct m_pedit_util p_pedit_ip = {
+ NULL,
+ "ip",
+ parse_ip,
+};
+
+
+struct m_pedit_util p_pedit_ip6 = {
+ NULL,
+ "ip6",
+ parse_ip6,
+};
diff --git a/iproute2/tc/p_tcp.c b/iproute2/tc/p_tcp.c
new file mode 100644
index 0000000..32ffc02
--- /dev/null
+++ b/iproute2/tc/p_tcp.c
@@ -0,0 +1,36 @@
+/*
+ * m_pedit_tcp.c packet editor: TCP header
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: J Hadi Salim (hadi@cyberus.ca)
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include "utils.h"
+#include "tc_util.h"
+#include "m_pedit.h"
+
+static int
+parse_tcp(int *argc_p, char ***argv_p,struct tc_pedit_sel *sel,struct tc_pedit_key *tkey)
+{
+ int res = -1;
+ return res;
+}
+struct m_pedit_util p_pedit_tcp = {
+ NULL,
+ "tcp",
+ parse_tcp,
+};
diff --git a/iproute2/tc/p_udp.c b/iproute2/tc/p_udp.c
new file mode 100644
index 0000000..2b9b88f
--- /dev/null
+++ b/iproute2/tc/p_udp.c
@@ -0,0 +1,37 @@
+/*
+ * m_pedit_udp.c packet editor: UDP header
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: J Hadi Salim (hadi@cyberus.ca)
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include "utils.h"
+#include "tc_util.h"
+#include "m_pedit.h"
+
+static int
+parse_udp(int *argc_p, char ***argv_p,struct tc_pedit_sel *sel,struct tc_pedit_key *tkey)
+{
+ int res = -1;
+ return res;
+}
+
+struct m_pedit_util p_pedit_udp = {
+ NULL,
+ "udp",
+ parse_udp,
+};
diff --git a/iproute2/tc/q_atm.c b/iproute2/tc/q_atm.c
new file mode 100644
index 0000000..2598e29
--- /dev/null
+++ b/iproute2/tc/q_atm.c
@@ -0,0 +1,258 @@
+/*
+ * q_atm.c ATM.
+ *
+ * Hacked 1998-2000 by Werner Almesberger, EPFL ICA
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <ctype.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <atm.h>
+#include <linux/atmdev.h>
+#include <linux/atmarp.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+
+#define MAX_HDR_LEN 64
+
+
+static int atm_parse_opt(struct qdisc_util *qu, int argc, char **argv, struct nlmsghdr *n)
+{
+ if (argc) {
+ fprintf(stderr,"Usage: atm\n");
+ return -1;
+ }
+ return 0;
+}
+
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... atm ( pvc ADDR | svc ADDR [ sap SAP ] ) "
+ "[ qos QOS ] [ sndbuf BYTES ]\n");
+ fprintf(stderr, " [ hdr HEX... ] [ excess ( CLASSID | clp ) ] "
+ "[ clip ]\n");
+}
+
+
+static int atm_parse_class_opt(struct qdisc_util *qu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ struct sockaddr_atmsvc addr;
+ struct atm_qos qos;
+ struct atm_sap sap;
+ unsigned char hdr[MAX_HDR_LEN];
+ __u32 excess = 0;
+ struct rtattr *tail;
+ int sndbuf = 0;
+ int hdr_len = -1;
+ int set_clip = 0;
+ int s;
+
+ memset(&addr,0,sizeof(addr));
+ (void) text2qos("aal5,ubr:sdu=9180,rx:none",&qos,0);
+ (void) text2sap("blli:l2=iso8802",&sap,0);
+ while (argc > 0) {
+ if (!strcmp(*argv,"pvc")) {
+ NEXT_ARG();
+ if (text2atm(*argv,(struct sockaddr *) &addr,
+ sizeof(addr),T2A_PVC | T2A_NAME) < 0) {
+ explain();
+ return -1;
+ }
+ }
+ else if (!strcmp(*argv,"svc")) {
+ NEXT_ARG();
+ if (text2atm(*argv,(struct sockaddr *) &addr,
+ sizeof(addr),T2A_SVC | T2A_NAME) < 0) {
+ explain();
+ return -1;
+ }
+ }
+ else if (!strcmp(*argv,"qos")) {
+ NEXT_ARG();
+ if (text2qos(*argv,&qos,0) < 0) {
+ explain();
+ return -1;
+ }
+ }
+ else if (!strcmp(*argv,"sndbuf")) {
+ char *end;
+
+ NEXT_ARG();
+ sndbuf = strtol(*argv,&end,0);
+ if (*end) {
+ explain();
+ return -1;
+ }
+ }
+ else if (!strcmp(*argv,"sap")) {
+ NEXT_ARG();
+ if (addr.sas_family != AF_ATMSVC ||
+ text2sap(*argv,&sap,T2A_NAME) < 0) {
+ explain();
+ return -1;
+ }
+ }
+ else if (!strcmp(*argv,"hdr")) {
+ unsigned char *ptr;
+ char *walk;
+
+ NEXT_ARG();
+ ptr = hdr;
+ for (walk = *argv; *walk; walk++) {
+ int tmp;
+
+ if (ptr == hdr+MAX_HDR_LEN) {
+ fprintf(stderr,"header is too long\n");
+ return -1;
+ }
+ if (*walk == '.') continue;
+ if (!isxdigit(walk[0]) || !walk[1] ||
+ !isxdigit(walk[1])) {
+ explain();
+ return -1;
+ }
+ sscanf(walk,"%2x",&tmp);
+ *ptr++ = tmp;
+ walk++;
+ }
+ hdr_len = ptr-hdr;
+ }
+ else if (!strcmp(*argv,"excess")) {
+ NEXT_ARG();
+ if (!strcmp(*argv,"clp")) excess = 0;
+ else if (get_tc_classid(&excess,*argv)) {
+ explain();
+ return -1;
+ }
+ }
+ else if (!strcmp(*argv,"clip")) {
+ set_clip = 1;
+ }
+ else {
+ explain();
+ return 1;
+ }
+ argc--;
+ argv++;
+ }
+ s = socket(addr.sas_family,SOCK_DGRAM,0);
+ if (s < 0) {
+ perror("socket");
+ return -1;
+ }
+ if (setsockopt(s,SOL_ATM,SO_ATMQOS,&qos,sizeof(qos)) < 0) {
+ perror("SO_ATMQOS");
+ return -1;
+ }
+ if (sndbuf)
+ if (setsockopt(s,SOL_SOCKET,SO_SNDBUF,&sndbuf,sizeof(sndbuf)) < 0) {
+ perror("SO_SNDBUF");
+ return -1;
+ }
+ if (addr.sas_family == AF_ATMSVC && setsockopt(s,SOL_ATM,SO_ATMSAP,
+ &sap,sizeof(sap)) < 0) {
+ perror("SO_ATMSAP");
+ return -1;
+ }
+ if (connect(s,(struct sockaddr *) &addr,addr.sas_family == AF_ATMPVC ?
+ sizeof(struct sockaddr_atmpvc) : sizeof(addr)) < 0) {
+ perror("connect");
+ return -1;
+ }
+ if (set_clip)
+ if (ioctl(s,ATMARP_MKIP,0) < 0) {
+ perror("ioctl ATMARP_MKIP");
+ return -1;
+ }
+ tail = NLMSG_TAIL(n);
+ addattr_l(n,1024,TCA_OPTIONS,NULL,0);
+ addattr_l(n,1024,TCA_ATM_FD,&s,sizeof(s));
+ if (excess) addattr_l(n,1024,TCA_ATM_EXCESS,&excess,sizeof(excess));
+ if (hdr_len != -1) addattr_l(n,1024,TCA_ATM_HDR,hdr,hdr_len);
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+
+
+static int atm_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct rtattr *tb[TCA_ATM_MAX+1];
+ char buffer[MAX_ATM_ADDR_LEN+1];
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_ATM_MAX, opt);
+ if (tb[TCA_ATM_ADDR]) {
+ if (RTA_PAYLOAD(tb[TCA_ATM_ADDR]) <
+ sizeof(struct sockaddr_atmpvc))
+ fprintf(stderr,"ATM: address too short\n");
+ else {
+ if (atm2text(buffer,MAX_ATM_ADDR_LEN,
+ RTA_DATA(tb[TCA_ATM_ADDR]),A2T_PRETTY | A2T_NAME) <
+ 0) fprintf(stderr,"atm2text error\n");
+ fprintf(f,"pvc %s ",buffer);
+ }
+ }
+ if (tb[TCA_ATM_HDR]) {
+ int i;
+ const __u8 *hdr = RTA_DATA(tb[TCA_ATM_HDR]);
+
+ fprintf(f,"hdr");
+ for (i = 0; i < RTA_PAYLOAD(tb[TCA_ATM_HDR]); i++)
+ fprintf(f,"%c%02x", i ? '.' : ' ', hdr[i]);
+ if (!i) fprintf(f," .");
+ fprintf(f," ");
+ }
+ if (tb[TCA_ATM_EXCESS]) {
+ __u32 excess;
+
+ if (RTA_PAYLOAD(tb[TCA_ATM_EXCESS]) < sizeof(excess))
+ fprintf(stderr,"ATM: excess class ID too short\n");
+ else {
+ excess = rta_getattr_u32(tb[TCA_ATM_EXCESS]);
+ if (!excess) fprintf(f,"excess clp ");
+ else {
+ char buf[64];
+
+ print_tc_classid(buf,sizeof(buf),excess);
+ fprintf(f,"excess %s ",buf);
+ }
+ }
+ }
+ if (tb[TCA_ATM_STATE]) {
+ static const char *map[] = { ATM_VS2TXT_MAP };
+ int state;
+
+ if (RTA_PAYLOAD(tb[TCA_ATM_STATE]) < sizeof(state))
+ fprintf(stderr,"ATM: state field too short\n");
+ else {
+ state = *(int *) RTA_DATA(tb[TCA_ATM_STATE]);
+ fprintf(f,"%s ",map[state]);
+ }
+ }
+ return 0;
+}
+
+
+struct qdisc_util atm_qdisc_util = {
+ .id = "atm",
+ .parse_qopt = atm_parse_opt,
+ .print_qopt = atm_print_opt,
+ .parse_copt = atm_parse_class_opt,
+ .print_copt = atm_print_opt,
+};
diff --git a/iproute2/tc/q_cbq.c b/iproute2/tc/q_cbq.c
new file mode 100644
index 0000000..38a6163
--- /dev/null
+++ b/iproute2/tc/q_cbq.c
@@ -0,0 +1,584 @@
+/*
+ * q_cbq.c CBQ.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+#include "tc_cbq.h"
+
+static void explain_class(void)
+{
+ fprintf(stderr, "Usage: ... cbq bandwidth BPS rate BPS maxburst PKTS [ avpkt BYTES ]\n");
+ fprintf(stderr, " [ minburst PKTS ] [ bounded ] [ isolated ]\n");
+ fprintf(stderr, " [ allot BYTES ] [ mpu BYTES ] [ weight RATE ]\n");
+ fprintf(stderr, " [ prio NUMBER ] [ cell BYTES ] [ ewma LOG ]\n");
+ fprintf(stderr, " [ estimator INTERVAL TIME_CONSTANT ]\n");
+ fprintf(stderr, " [ split CLASSID ] [ defmap MASK/CHANGE ]\n");
+ fprintf(stderr, " [ overhead BYTES ] [ linklayer TYPE ]\n");
+}
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... cbq bandwidth BPS avpkt BYTES [ mpu BYTES ]\n");
+ fprintf(stderr, " [ cell BYTES ] [ ewma LOG ]\n");
+}
+
+static void explain1(char *arg)
+{
+ fprintf(stderr, "Illegal \"%s\"\n", arg);
+}
+
+
+static int cbq_parse_opt(struct qdisc_util *qu, int argc, char **argv, struct nlmsghdr *n)
+{
+ struct tc_ratespec r;
+ struct tc_cbq_lssopt lss;
+ __u32 rtab[256];
+ unsigned mpu=0, avpkt=0, allot=0;
+ unsigned short overhead=0;
+ unsigned int linklayer = LINKLAYER_ETHERNET; /* Assume ethernet */
+ int cell_log=-1;
+ int ewma_log=-1;
+ struct rtattr *tail;
+
+ memset(&lss, 0, sizeof(lss));
+ memset(&r, 0, sizeof(r));
+
+ while (argc > 0) {
+ if (matches(*argv, "bandwidth") == 0 ||
+ matches(*argv, "rate") == 0) {
+ NEXT_ARG();
+ if (get_rate(&r.rate, *argv)) {
+ explain1("bandwidth");
+ return -1;
+ }
+ } else if (matches(*argv, "ewma") == 0) {
+ NEXT_ARG();
+ if (get_integer(&ewma_log, *argv, 0)) {
+ explain1("ewma");
+ return -1;
+ }
+ if (ewma_log > 31) {
+ fprintf(stderr, "ewma_log must be < 32\n");
+ return -1;
+ }
+ } else if (matches(*argv, "cell") == 0) {
+ unsigned cell;
+ int i;
+ NEXT_ARG();
+ if (get_size(&cell, *argv)) {
+ explain1("cell");
+ return -1;
+ }
+ for (i=0; i<32; i++)
+ if ((1<<i) == cell)
+ break;
+ if (i>=32) {
+ fprintf(stderr, "cell must be 2^n\n");
+ return -1;
+ }
+ cell_log = i;
+ } else if (matches(*argv, "avpkt") == 0) {
+ NEXT_ARG();
+ if (get_size(&avpkt, *argv)) {
+ explain1("avpkt");
+ return -1;
+ }
+ } else if (matches(*argv, "mpu") == 0) {
+ NEXT_ARG();
+ if (get_size(&mpu, *argv)) {
+ explain1("mpu");
+ return -1;
+ }
+ } else if (matches(*argv, "allot") == 0) {
+ NEXT_ARG();
+ /* Accept and ignore "allot" for backward compatibility */
+ if (get_size(&allot, *argv)) {
+ explain1("allot");
+ return -1;
+ }
+ } else if (matches(*argv, "overhead") == 0) {
+ NEXT_ARG();
+ if (get_u16(&overhead, *argv, 10)) {
+ explain1("overhead"); return -1;
+ }
+ } else if (matches(*argv, "linklayer") == 0) {
+ NEXT_ARG();
+ if (get_linklayer(&linklayer, *argv)) {
+ explain1("linklayer"); return -1;
+ }
+ } else if (matches(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ /* OK. All options are parsed. */
+
+ if (r.rate == 0) {
+ fprintf(stderr, "CBQ: bandwidth is required parameter.\n");
+ return -1;
+ }
+ if (avpkt == 0) {
+ fprintf(stderr, "CBQ: \"avpkt\" is required.\n");
+ return -1;
+ }
+ if (allot < (avpkt*3)/2)
+ allot = (avpkt*3)/2;
+
+ r.mpu = mpu;
+ r.overhead = overhead;
+ if (tc_calc_rtable(&r, rtab, cell_log, allot, linklayer) < 0) {
+ fprintf(stderr, "CBQ: failed to calculate rate table.\n");
+ return -1;
+ }
+
+ if (ewma_log < 0)
+ ewma_log = TC_CBQ_DEF_EWMA;
+ lss.ewma_log = ewma_log;
+ lss.maxidle = tc_calc_xmittime(r.rate, avpkt);
+ lss.change = TCF_CBQ_LSS_MAXIDLE|TCF_CBQ_LSS_EWMA|TCF_CBQ_LSS_AVPKT;
+ lss.avpkt = avpkt;
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+ addattr_l(n, 1024, TCA_CBQ_RATE, &r, sizeof(r));
+ addattr_l(n, 1024, TCA_CBQ_LSSOPT, &lss, sizeof(lss));
+ addattr_l(n, 3024, TCA_CBQ_RTAB, rtab, 1024);
+ if (show_raw) {
+ int i;
+ for (i=0; i<256; i++)
+ printf("%u ", rtab[i]);
+ printf("\n");
+ }
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+static int cbq_parse_class_opt(struct qdisc_util *qu, int argc, char **argv, struct nlmsghdr *n)
+{
+ int wrr_ok=0, fopt_ok=0;
+ struct tc_ratespec r;
+ struct tc_cbq_lssopt lss;
+ struct tc_cbq_wrropt wrr;
+ struct tc_cbq_fopt fopt;
+ struct tc_cbq_ovl ovl;
+ __u32 rtab[256];
+ unsigned mpu=0;
+ int cell_log=-1;
+ int ewma_log=-1;
+ unsigned bndw = 0;
+ unsigned minburst=0, maxburst=0;
+ unsigned short overhead=0;
+ unsigned int linklayer = LINKLAYER_ETHERNET; /* Assume ethernet */
+ struct rtattr *tail;
+
+ memset(&r, 0, sizeof(r));
+ memset(&lss, 0, sizeof(lss));
+ memset(&wrr, 0, sizeof(wrr));
+ memset(&fopt, 0, sizeof(fopt));
+ memset(&ovl, 0, sizeof(ovl));
+
+ while (argc > 0) {
+ if (matches(*argv, "rate") == 0) {
+ NEXT_ARG();
+ if (get_rate(&r.rate, *argv)) {
+ explain1("rate");
+ return -1;
+ }
+ } else if (matches(*argv, "bandwidth") == 0) {
+ NEXT_ARG();
+ if (get_rate(&bndw, *argv)) {
+ explain1("bandwidth");
+ return -1;
+ }
+ } else if (matches(*argv, "minidle") == 0) {
+ NEXT_ARG();
+ if (get_u32(&lss.minidle, *argv, 0)) {
+ explain1("minidle");
+ return -1;
+ }
+ lss.change |= TCF_CBQ_LSS_MINIDLE;
+ } else if (matches(*argv, "minburst") == 0) {
+ NEXT_ARG();
+ if (get_u32(&minburst, *argv, 0)) {
+ explain1("minburst");
+ return -1;
+ }
+ lss.change |= TCF_CBQ_LSS_OFFTIME;
+ } else if (matches(*argv, "maxburst") == 0) {
+ NEXT_ARG();
+ if (get_u32(&maxburst, *argv, 0)) {
+ explain1("maxburst");
+ return -1;
+ }
+ lss.change |= TCF_CBQ_LSS_MAXIDLE;
+ } else if (matches(*argv, "bounded") == 0) {
+ lss.flags |= TCF_CBQ_LSS_BOUNDED;
+ lss.change |= TCF_CBQ_LSS_FLAGS;
+ } else if (matches(*argv, "borrow") == 0) {
+ lss.flags &= ~TCF_CBQ_LSS_BOUNDED;
+ lss.change |= TCF_CBQ_LSS_FLAGS;
+ } else if (matches(*argv, "isolated") == 0) {
+ lss.flags |= TCF_CBQ_LSS_ISOLATED;
+ lss.change |= TCF_CBQ_LSS_FLAGS;
+ } else if (matches(*argv, "sharing") == 0) {
+ lss.flags &= ~TCF_CBQ_LSS_ISOLATED;
+ lss.change |= TCF_CBQ_LSS_FLAGS;
+ } else if (matches(*argv, "ewma") == 0) {
+ NEXT_ARG();
+ if (get_integer(&ewma_log, *argv, 0)) {
+ explain1("ewma");
+ return -1;
+ }
+ if (ewma_log > 31) {
+ fprintf(stderr, "ewma_log must be < 32\n");
+ return -1;
+ }
+ lss.change |= TCF_CBQ_LSS_EWMA;
+ } else if (matches(*argv, "cell") == 0) {
+ unsigned cell;
+ int i;
+ NEXT_ARG();
+ if (get_size(&cell, *argv)) {
+ explain1("cell");
+ return -1;
+ }
+ for (i=0; i<32; i++)
+ if ((1<<i) == cell)
+ break;
+ if (i>=32) {
+ fprintf(stderr, "cell must be 2^n\n");
+ return -1;
+ }
+ cell_log = i;
+ } else if (matches(*argv, "prio") == 0) {
+ unsigned prio;
+ NEXT_ARG();
+ if (get_u32(&prio, *argv, 0)) {
+ explain1("prio");
+ return -1;
+ }
+ if (prio > TC_CBQ_MAXPRIO) {
+ fprintf(stderr, "\"prio\" must be number in the range 1...%d\n", TC_CBQ_MAXPRIO);
+ return -1;
+ }
+ wrr.priority = prio;
+ wrr_ok++;
+ } else if (matches(*argv, "allot") == 0) {
+ NEXT_ARG();
+ if (get_size(&wrr.allot, *argv)) {
+ explain1("allot");
+ return -1;
+ }
+ } else if (matches(*argv, "avpkt") == 0) {
+ NEXT_ARG();
+ if (get_size(&lss.avpkt, *argv)) {
+ explain1("avpkt");
+ return -1;
+ }
+ lss.change |= TCF_CBQ_LSS_AVPKT;
+ } else if (matches(*argv, "mpu") == 0) {
+ NEXT_ARG();
+ if (get_size(&mpu, *argv)) {
+ explain1("mpu");
+ return -1;
+ }
+ } else if (matches(*argv, "weight") == 0) {
+ NEXT_ARG();
+ if (get_size(&wrr.weight, *argv)) {
+ explain1("weight");
+ return -1;
+ }
+ wrr_ok++;
+ } else if (matches(*argv, "split") == 0) {
+ NEXT_ARG();
+ if (get_tc_classid(&fopt.split, *argv)) {
+ fprintf(stderr, "Invalid split node ID.\n");
+ return -1;
+ }
+ fopt_ok++;
+ } else if (matches(*argv, "defmap") == 0) {
+ int err;
+ NEXT_ARG();
+ err = sscanf(*argv, "%08x/%08x", &fopt.defmap, &fopt.defchange);
+ if (err < 1) {
+ fprintf(stderr, "Invalid defmap, should be MASK32[/MASK]\n");
+ return -1;
+ }
+ if (err == 1)
+ fopt.defchange = ~0;
+ fopt_ok++;
+ } else if (matches(*argv, "overhead") == 0) {
+ NEXT_ARG();
+ if (get_u16(&overhead, *argv, 10)) {
+ explain1("overhead"); return -1;
+ }
+ } else if (matches(*argv, "linklayer") == 0) {
+ NEXT_ARG();
+ if (get_linklayer(&linklayer, *argv)) {
+ explain1("linklayer"); return -1;
+ }
+ } else if (matches(*argv, "help") == 0) {
+ explain_class();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain_class();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ /* OK. All options are parsed. */
+
+ /* 1. Prepare link sharing scheduler parameters */
+ if (r.rate) {
+ unsigned pktsize = wrr.allot;
+ if (wrr.allot < (lss.avpkt*3)/2)
+ wrr.allot = (lss.avpkt*3)/2;
+ r.mpu = mpu;
+ r.overhead = overhead;
+ if (tc_calc_rtable(&r, rtab, cell_log, pktsize, linklayer) < 0) {
+ fprintf(stderr, "CBQ: failed to calculate rate table.\n");
+ return -1;
+ }
+ }
+ if (ewma_log < 0)
+ ewma_log = TC_CBQ_DEF_EWMA;
+ lss.ewma_log = ewma_log;
+ if (lss.change&(TCF_CBQ_LSS_OFFTIME|TCF_CBQ_LSS_MAXIDLE)) {
+ if (lss.avpkt == 0) {
+ fprintf(stderr, "CBQ: avpkt is required for max/minburst.\n");
+ return -1;
+ }
+ if (bndw==0 || r.rate == 0) {
+ fprintf(stderr, "CBQ: bandwidth&rate are required for max/minburst.\n");
+ return -1;
+ }
+ }
+ if (wrr.priority == 0 && (n->nlmsg_flags&NLM_F_EXCL)) {
+ wrr_ok = 1;
+ wrr.priority = TC_CBQ_MAXPRIO;
+ if (wrr.allot == 0)
+ wrr.allot = (lss.avpkt*3)/2;
+ }
+ if (wrr_ok) {
+ if (wrr.weight == 0)
+ wrr.weight = (wrr.priority == TC_CBQ_MAXPRIO) ? 1 : r.rate;
+ if (wrr.allot == 0) {
+ fprintf(stderr, "CBQ: \"allot\" is required to set WRR parameters.\n");
+ return -1;
+ }
+ }
+ if (lss.change&TCF_CBQ_LSS_MAXIDLE) {
+ lss.maxidle = tc_cbq_calc_maxidle(bndw, r.rate, lss.avpkt, ewma_log, maxburst);
+ lss.change |= TCF_CBQ_LSS_MAXIDLE;
+ lss.change |= TCF_CBQ_LSS_EWMA|TCF_CBQ_LSS_AVPKT;
+ }
+ if (lss.change&TCF_CBQ_LSS_OFFTIME) {
+ lss.offtime = tc_cbq_calc_offtime(bndw, r.rate, lss.avpkt, ewma_log, minburst);
+ lss.change |= TCF_CBQ_LSS_OFFTIME;
+ lss.change |= TCF_CBQ_LSS_EWMA|TCF_CBQ_LSS_AVPKT;
+ }
+ if (lss.change&TCF_CBQ_LSS_MINIDLE) {
+ lss.minidle <<= lss.ewma_log;
+ lss.change |= TCF_CBQ_LSS_EWMA;
+ }
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+ if (lss.change) {
+ lss.change |= TCF_CBQ_LSS_FLAGS;
+ addattr_l(n, 1024, TCA_CBQ_LSSOPT, &lss, sizeof(lss));
+ }
+ if (wrr_ok)
+ addattr_l(n, 1024, TCA_CBQ_WRROPT, &wrr, sizeof(wrr));
+ if (fopt_ok)
+ addattr_l(n, 1024, TCA_CBQ_FOPT, &fopt, sizeof(fopt));
+ if (r.rate) {
+ addattr_l(n, 1024, TCA_CBQ_RATE, &r, sizeof(r));
+ addattr_l(n, 3024, TCA_CBQ_RTAB, rtab, 1024);
+ if (show_raw) {
+ int i;
+ for (i=0; i<256; i++)
+ printf("%u ", rtab[i]);
+ printf("\n");
+ }
+ }
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+
+static int cbq_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct rtattr *tb[TCA_CBQ_MAX+1];
+ struct tc_ratespec *r = NULL;
+ struct tc_cbq_lssopt *lss = NULL;
+ struct tc_cbq_wrropt *wrr = NULL;
+ struct tc_cbq_fopt *fopt = NULL;
+ struct tc_cbq_ovl *ovl = NULL;
+ unsigned int linklayer;
+ SPRINT_BUF(b1);
+ SPRINT_BUF(b2);
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_CBQ_MAX, opt);
+
+ if (tb[TCA_CBQ_RATE]) {
+ if (RTA_PAYLOAD(tb[TCA_CBQ_RATE]) < sizeof(*r))
+ fprintf(stderr, "CBQ: too short rate opt\n");
+ else
+ r = RTA_DATA(tb[TCA_CBQ_RATE]);
+ }
+ if (tb[TCA_CBQ_LSSOPT]) {
+ if (RTA_PAYLOAD(tb[TCA_CBQ_LSSOPT]) < sizeof(*lss))
+ fprintf(stderr, "CBQ: too short lss opt\n");
+ else
+ lss = RTA_DATA(tb[TCA_CBQ_LSSOPT]);
+ }
+ if (tb[TCA_CBQ_WRROPT]) {
+ if (RTA_PAYLOAD(tb[TCA_CBQ_WRROPT]) < sizeof(*wrr))
+ fprintf(stderr, "CBQ: too short wrr opt\n");
+ else
+ wrr = RTA_DATA(tb[TCA_CBQ_WRROPT]);
+ }
+ if (tb[TCA_CBQ_FOPT]) {
+ if (RTA_PAYLOAD(tb[TCA_CBQ_FOPT]) < sizeof(*fopt))
+ fprintf(stderr, "CBQ: too short fopt\n");
+ else
+ fopt = RTA_DATA(tb[TCA_CBQ_FOPT]);
+ }
+ if (tb[TCA_CBQ_OVL_STRATEGY]) {
+ if (RTA_PAYLOAD(tb[TCA_CBQ_OVL_STRATEGY]) < sizeof(*ovl))
+ fprintf(stderr, "CBQ: too short overlimit strategy %u/%u\n",
+ (unsigned) RTA_PAYLOAD(tb[TCA_CBQ_OVL_STRATEGY]),
+ (unsigned) sizeof(*ovl));
+ else
+ ovl = RTA_DATA(tb[TCA_CBQ_OVL_STRATEGY]);
+ }
+
+ if (r) {
+ char buf[64];
+ print_rate(buf, sizeof(buf), r->rate);
+ fprintf(f, "rate %s ", buf);
+ linklayer = (r->linklayer & TC_LINKLAYER_MASK);
+ if (linklayer > TC_LINKLAYER_ETHERNET || show_details)
+ fprintf(f, "linklayer %s ", sprint_linklayer(linklayer, b2));
+ if (show_details) {
+ fprintf(f, "cell %ub ", 1<<r->cell_log);
+ if (r->mpu)
+ fprintf(f, "mpu %ub ", r->mpu);
+ if (r->overhead)
+ fprintf(f, "overhead %ub ", r->overhead);
+ }
+ }
+ if (lss && lss->flags) {
+ int comma=0;
+ fprintf(f, "(");
+ if (lss->flags&TCF_CBQ_LSS_BOUNDED) {
+ fprintf(f, "bounded");
+ comma=1;
+ }
+ if (lss->flags&TCF_CBQ_LSS_ISOLATED) {
+ if (comma)
+ fprintf(f, ",");
+ fprintf(f, "isolated");
+ }
+ fprintf(f, ") ");
+ }
+ if (wrr) {
+ if (wrr->priority != TC_CBQ_MAXPRIO)
+ fprintf(f, "prio %u", wrr->priority);
+ else
+ fprintf(f, "prio no-transmit");
+ if (show_details) {
+ char buf[64];
+ fprintf(f, "/%u ", wrr->cpriority);
+ if (wrr->weight != 1) {
+ print_rate(buf, sizeof(buf), wrr->weight);
+ fprintf(f, "weight %s ", buf);
+ }
+ if (wrr->allot)
+ fprintf(f, "allot %ub ", wrr->allot);
+ }
+ }
+ if (lss && show_details) {
+ fprintf(f, "\nlevel %u ewma %u avpkt %ub ", lss->level, lss->ewma_log, lss->avpkt);
+ if (lss->maxidle) {
+ fprintf(f, "maxidle %s ", sprint_ticks(lss->maxidle>>lss->ewma_log, b1));
+ if (show_raw)
+ fprintf(f, "[%08x] ", lss->maxidle);
+ }
+ if (lss->minidle!=0x7fffffff) {
+ fprintf(f, "minidle %s ", sprint_ticks(lss->minidle>>lss->ewma_log, b1));
+ if (show_raw)
+ fprintf(f, "[%08x] ", lss->minidle);
+ }
+ if (lss->offtime) {
+ fprintf(f, "offtime %s ", sprint_ticks(lss->offtime, b1));
+ if (show_raw)
+ fprintf(f, "[%08x] ", lss->offtime);
+ }
+ }
+ if (fopt && show_details) {
+ char buf[64];
+ print_tc_classid(buf, sizeof(buf), fopt->split);
+ fprintf(f, "\nsplit %s ", buf);
+ if (fopt->defmap) {
+ fprintf(f, "defmap %08x", fopt->defmap);
+ }
+ }
+ return 0;
+}
+
+static int cbq_print_xstats(struct qdisc_util *qu, FILE *f, struct rtattr *xstats)
+{
+ struct tc_cbq_xstats *st;
+
+ if (xstats == NULL)
+ return 0;
+
+ if (RTA_PAYLOAD(xstats) < sizeof(*st))
+ return -1;
+
+ st = RTA_DATA(xstats);
+ fprintf(f, " borrowed %u overactions %u avgidle %g undertime %g", st->borrows,
+ st->overactions, (double)st->avgidle, (double)st->undertime);
+ return 0;
+}
+
+struct qdisc_util cbq_qdisc_util = {
+ .id = "cbq",
+ .parse_qopt = cbq_parse_opt,
+ .print_qopt = cbq_print_opt,
+ .print_xstats = cbq_print_xstats,
+ .parse_copt = cbq_parse_class_opt,
+ .print_copt = cbq_print_opt,
+};
diff --git a/iproute2/tc/q_choke.c b/iproute2/tc/q_choke.c
new file mode 100644
index 0000000..bd9ceb8
--- /dev/null
+++ b/iproute2/tc/q_choke.c
@@ -0,0 +1,227 @@
+/*
+ * q_choke.c CHOKE.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Stephen Hemminger <shemminger@vyatta.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <math.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+#include "tc_red.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... choke limit PACKETS bandwidth KBPS [ecn]\n");
+ fprintf(stderr, " [ min PACKETS ] [ max PACKETS ] [ burst PACKETS ]\n");
+}
+
+static int choke_parse_opt(struct qdisc_util *qu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ struct tc_red_qopt opt;
+ unsigned burst = 0;
+ unsigned avpkt = 1000;
+ double probability = 0.02;
+ unsigned rate = 0;
+ int ecn_ok = 0;
+ int wlog;
+ __u8 sbuf[256];
+ __u32 max_P;
+ struct rtattr *tail;
+
+ memset(&opt, 0, sizeof(opt));
+
+ while (argc > 0) {
+ if (strcmp(*argv, "limit") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&opt.limit, *argv, 0)) {
+ fprintf(stderr, "Illegal \"limit\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "bandwidth") == 0) {
+ NEXT_ARG();
+ if (get_rate(&rate, *argv)) {
+ fprintf(stderr, "Illegal \"bandwidth\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "ecn") == 0) {
+ ecn_ok = 1;
+ } else if (strcmp(*argv, "min") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&opt.qth_min, *argv, 0)) {
+ fprintf(stderr, "Illegal \"min\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "max") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&opt.qth_max, *argv, 0)) {
+ fprintf(stderr, "Illegal \"max\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "burst") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&burst, *argv, 0)) {
+ fprintf(stderr, "Illegal \"burst\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "avpkt") == 0) {
+ NEXT_ARG();
+ if (get_size(&avpkt, *argv)) {
+ fprintf(stderr, "Illegal \"avpkt\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "probability") == 0) {
+ NEXT_ARG();
+ if (sscanf(*argv, "%lg", &probability) != 1) {
+ fprintf(stderr, "Illegal \"probability\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ if (!rate || !opt.limit) {
+ fprintf(stderr, "Required parameter (bandwidth, limit) is missing\n");
+ return -1;
+ }
+
+ /* Compute default min/max thresholds based on
+ Sally Floyd's recommendations:
+ http://www.icir.org/floyd/REDparameters.txt
+ */
+ if (!opt.qth_max)
+ opt.qth_max = opt.limit / 4;
+ if (!opt.qth_min)
+ opt.qth_min = opt.qth_max / 3;
+ if (!burst)
+ burst = (2 * opt.qth_min + opt.qth_max) / 3;
+
+ if (opt.qth_max > opt.limit) {
+ fprintf(stderr, "\"max\" is larger than \"limit\"\n");
+ return -1;
+ }
+
+ if (opt.qth_min >= opt.qth_max) {
+ fprintf(stderr, "\"min\" is not smaller than \"max\"\n");
+ return -1;
+ }
+
+ wlog = tc_red_eval_ewma(opt.qth_min*avpkt, burst, avpkt);
+ if (wlog < 0) {
+ fprintf(stderr, "CHOKE: failed to calculate EWMA constant.\n");
+ return -1;
+ }
+ if (wlog >= 10)
+ fprintf(stderr, "CHOKE: WARNING. Burst %d seems to be too large.\n", burst);
+ opt.Wlog = wlog;
+
+ wlog = tc_red_eval_P(opt.qth_min*avpkt, opt.qth_max*avpkt, probability);
+ if (wlog < 0) {
+ fprintf(stderr, "CHOKE: failed to calculate probability.\n");
+ return -1;
+ }
+ opt.Plog = wlog;
+
+ wlog = tc_red_eval_idle_damping(opt.Wlog, avpkt, rate, sbuf);
+ if (wlog < 0) {
+ fprintf(stderr, "CHOKE: failed to calculate idle damping table.\n");
+ return -1;
+ }
+ opt.Scell_log = wlog;
+ if (ecn_ok)
+ opt.flags |= TC_RED_ECN;
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+ addattr_l(n, 1024, TCA_CHOKE_PARMS, &opt, sizeof(opt));
+ addattr_l(n, 1024, TCA_CHOKE_STAB, sbuf, 256);
+ max_P = probability * pow(2, 32);
+ addattr_l(n, 1024, TCA_CHOKE_MAX_P, &max_P, sizeof(max_P));
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+static int choke_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct rtattr *tb[TCA_CHOKE_MAX+1];
+ const struct tc_red_qopt *qopt;
+ __u32 max_P = 0;
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_CHOKE_MAX, opt);
+
+ if (tb[TCA_CHOKE_PARMS] == NULL)
+ return -1;
+ qopt = RTA_DATA(tb[TCA_CHOKE_PARMS]);
+ if (RTA_PAYLOAD(tb[TCA_CHOKE_PARMS]) < sizeof(*qopt))
+ return -1;
+ if (tb[TCA_CHOKE_MAX_P] &&
+ RTA_PAYLOAD(tb[TCA_CHOKE_MAX_P]) >= sizeof(__u32))
+ max_P = rta_getattr_u32(tb[TCA_CHOKE_MAX_P]);
+
+ fprintf(f, "limit %up min %up max %up ",
+ qopt->limit, qopt->qth_min, qopt->qth_max);
+
+ if (qopt->flags & TC_RED_ECN)
+ fprintf(f, "ecn ");
+
+ if (show_details) {
+ fprintf(f, "ewma %u ", qopt->Wlog);
+ if (max_P)
+ fprintf(f, "probability %g ", max_P / pow(2, 32));
+ else
+ fprintf(f, "Plog %u ", qopt->Plog);
+ fprintf(f, "Scell_log %u", qopt->Scell_log);
+ }
+ return 0;
+}
+
+static int choke_print_xstats(struct qdisc_util *qu, FILE *f,
+ struct rtattr *xstats)
+{
+ struct tc_choke_xstats *st;
+
+ if (xstats == NULL)
+ return 0;
+
+ if (RTA_PAYLOAD(xstats) < sizeof(*st))
+ return -1;
+
+ st = RTA_DATA(xstats);
+ fprintf(f, " marked %u early %u pdrop %u other %u matched %u",
+ st->marked, st->early, st->pdrop, st->other, st->matched);
+ return 0;
+
+}
+
+struct qdisc_util choke_qdisc_util = {
+ .id = "choke",
+ .parse_qopt = choke_parse_opt,
+ .print_qopt = choke_print_opt,
+ .print_xstats = choke_print_xstats,
+};
diff --git a/iproute2/tc/q_clsact.c b/iproute2/tc/q_clsact.c
new file mode 100644
index 0000000..0c05dbd
--- /dev/null
+++ b/iproute2/tc/q_clsact.c
@@ -0,0 +1,34 @@
+#include <stdio.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... clsact\n");
+}
+
+static int clsact_parse_opt(struct qdisc_util *qu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ if (argc > 0) {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+
+ addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+ return 0;
+}
+
+static int clsact_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ return 0;
+}
+
+struct qdisc_util clsact_qdisc_util = {
+ .id = "clsact",
+ .parse_qopt = clsact_parse_opt,
+ .print_qopt = clsact_print_opt,
+};
diff --git a/iproute2/tc/q_codel.c b/iproute2/tc/q_codel.c
new file mode 100644
index 0000000..c24246c
--- /dev/null
+++ b/iproute2/tc/q_codel.c
@@ -0,0 +1,211 @@
+/*
+ * Codel - The Controlled-Delay Active Queue Management algorithm
+ *
+ * Copyright (C) 2011-2012 Kathleen Nichols <nichols@pollere.com>
+ * Copyright (C) 2011-2012 Van Jacobson <van@pollere.com>
+ * Copyright (C) 2012 Michael D. Taht <dave.taht@bufferbloat.net>
+ * Copyright (C) 2012,2015 Eric Dumazet <edumazet@google.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions, and the following disclaimer,
+ * without modification.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. The names of the authors may not be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * Alternatively, provided that this notice is retained in full, this
+ * software may be distributed under the terms of the GNU General
+ * Public License ("GPL") version 2, in which case the provisions of the
+ * GPL apply INSTEAD OF those given above.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... codel [ limit PACKETS ] [ target TIME]\n");
+ fprintf(stderr, " [ interval TIME ] [ ecn | noecn ]\n");
+ fprintf(stderr, " [ ce_threshold TIME ]\n");
+}
+
+static int codel_parse_opt(struct qdisc_util *qu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ unsigned limit = 0;
+ unsigned target = 0;
+ unsigned interval = 0;
+ unsigned ce_threshold = ~0U;
+ int ecn = -1;
+ struct rtattr *tail;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "limit") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&limit, *argv, 0)) {
+ fprintf(stderr, "Illegal \"limit\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "target") == 0) {
+ NEXT_ARG();
+ if (get_time(&target, *argv)) {
+ fprintf(stderr, "Illegal \"target\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "ce_threshold") == 0) {
+ NEXT_ARG();
+ if (get_time(&ce_threshold, *argv)) {
+ fprintf(stderr, "Illegal \"ce_threshold\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "interval") == 0) {
+ NEXT_ARG();
+ if (get_time(&interval, *argv)) {
+ fprintf(stderr, "Illegal \"interval\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "ecn") == 0) {
+ ecn = 1;
+ } else if (strcmp(*argv, "noecn") == 0) {
+ ecn = 0;
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+ if (limit)
+ addattr_l(n, 1024, TCA_CODEL_LIMIT, &limit, sizeof(limit));
+ if (interval)
+ addattr_l(n, 1024, TCA_CODEL_INTERVAL, &interval, sizeof(interval));
+ if (target)
+ addattr_l(n, 1024, TCA_CODEL_TARGET, &target, sizeof(target));
+ if (ecn != -1)
+ addattr_l(n, 1024, TCA_CODEL_ECN, &ecn, sizeof(ecn));
+ if (ce_threshold != ~0U)
+ addattr_l(n, 1024, TCA_CODEL_CE_THRESHOLD,
+ &ce_threshold, sizeof(ce_threshold));
+
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+static int codel_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct rtattr *tb[TCA_CODEL_MAX + 1];
+ unsigned limit;
+ unsigned interval;
+ unsigned target;
+ unsigned ecn;
+ unsigned ce_threshold;
+ SPRINT_BUF(b1);
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_CODEL_MAX, opt);
+
+ if (tb[TCA_CODEL_LIMIT] &&
+ RTA_PAYLOAD(tb[TCA_CODEL_LIMIT]) >= sizeof(__u32)) {
+ limit = rta_getattr_u32(tb[TCA_CODEL_LIMIT]);
+ fprintf(f, "limit %up ", limit);
+ }
+ if (tb[TCA_CODEL_TARGET] &&
+ RTA_PAYLOAD(tb[TCA_CODEL_TARGET]) >= sizeof(__u32)) {
+ target = rta_getattr_u32(tb[TCA_CODEL_TARGET]);
+ fprintf(f, "target %s ", sprint_time(target, b1));
+ }
+ if (tb[TCA_CODEL_CE_THRESHOLD] &&
+ RTA_PAYLOAD(tb[TCA_CODEL_CE_THRESHOLD]) >= sizeof(__u32)) {
+ ce_threshold = rta_getattr_u32(tb[TCA_CODEL_CE_THRESHOLD]);
+ fprintf(f, "ce_threshold %s ", sprint_time(ce_threshold, b1));
+ }
+ if (tb[TCA_CODEL_INTERVAL] &&
+ RTA_PAYLOAD(tb[TCA_CODEL_INTERVAL]) >= sizeof(__u32)) {
+ interval = rta_getattr_u32(tb[TCA_CODEL_INTERVAL]);
+ fprintf(f, "interval %s ", sprint_time(interval, b1));
+ }
+ if (tb[TCA_CODEL_ECN] &&
+ RTA_PAYLOAD(tb[TCA_CODEL_ECN]) >= sizeof(__u32)) {
+ ecn = rta_getattr_u32(tb[TCA_CODEL_ECN]);
+ if (ecn)
+ fprintf(f, "ecn ");
+ }
+
+ return 0;
+}
+
+static int codel_print_xstats(struct qdisc_util *qu, FILE *f,
+ struct rtattr *xstats)
+{
+ struct tc_codel_xstats _st, *st;
+ SPRINT_BUF(b1);
+
+ if (xstats == NULL)
+ return 0;
+
+ st = RTA_DATA(xstats);
+ if (RTA_PAYLOAD(xstats) < sizeof(*st)) {
+ memset(&_st, 0, sizeof(_st));
+ memcpy(&_st, st, RTA_PAYLOAD(xstats));
+ st = &_st;
+ }
+
+ fprintf(f, " count %u lastcount %u ldelay %s",
+ st->count, st->lastcount, sprint_time(st->ldelay, b1));
+ if (st->dropping)
+ fprintf(f, " dropping");
+ if (st->drop_next < 0)
+ fprintf(f, " drop_next -%s", sprint_time(-st->drop_next, b1));
+ else
+ fprintf(f, " drop_next %s", sprint_time(st->drop_next, b1));
+ fprintf(f, "\n maxpacket %u ecn_mark %u drop_overlimit %u",
+ st->maxpacket, st->ecn_mark, st->drop_overlimit);
+ if (st->ce_mark)
+ fprintf(f, " ce_mark %u", st->ce_mark);
+ return 0;
+
+}
+
+struct qdisc_util codel_qdisc_util = {
+ .id = "codel",
+ .parse_qopt = codel_parse_opt,
+ .print_qopt = codel_print_opt,
+ .print_xstats = codel_print_xstats,
+};
diff --git a/iproute2/tc/q_drr.c b/iproute2/tc/q_drr.c
new file mode 100644
index 0000000..746736d
--- /dev/null
+++ b/iproute2/tc/q_drr.c
@@ -0,0 +1,122 @@
+/*
+ * q_drr.c DRR.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Patrick McHardy <kaber@trash.net>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... drr\n");
+}
+
+static void explain2(void)
+{
+ fprintf(stderr, "Usage: ... drr quantum SIZE\n");
+}
+
+
+static int drr_parse_opt(struct qdisc_util *qu, int argc, char **argv, struct nlmsghdr *n)
+{
+ while (argc) {
+ if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ }
+ return 0;
+}
+
+static int drr_parse_class_opt(struct qdisc_util *qu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ struct rtattr *tail;
+ __u32 tmp;
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+
+ while (argc > 0) {
+ if (strcmp(*argv, "quantum") == 0) {
+ NEXT_ARG();
+ if (get_size(&tmp, *argv)) {
+ fprintf(stderr, "Illegal \"quantum\"\n");
+ return -1;
+ }
+ addattr_l(n, 1024, TCA_DRR_QUANTUM, &tmp, sizeof(tmp));
+ } else if (strcmp(*argv, "help") == 0) {
+ explain2();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain2();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *)tail;
+ return 0;
+}
+
+static int drr_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct rtattr *tb[TCA_DRR_MAX + 1];
+ SPRINT_BUF(b1);
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_DRR_MAX, opt);
+
+ if (tb[TCA_DRR_QUANTUM])
+ fprintf(f, "quantum %s ",
+ sprint_size(rta_getattr_u32(tb[TCA_DRR_QUANTUM]), b1));
+ return 0;
+}
+
+static int drr_print_xstats(struct qdisc_util *qu, FILE *f, struct rtattr *xstats)
+{
+ struct tc_drr_stats *x;
+ SPRINT_BUF(b1);
+
+ if (xstats == NULL)
+ return 0;
+ if (RTA_PAYLOAD(xstats) < sizeof(*x))
+ return -1;
+ x = RTA_DATA(xstats);
+
+ fprintf(f, " deficit %s ", sprint_size(x->deficit, b1));
+ return 0;
+}
+
+struct qdisc_util drr_qdisc_util = {
+ .id = "drr",
+ .parse_qopt = drr_parse_opt,
+ .print_qopt = drr_print_opt,
+ .print_xstats = drr_print_xstats,
+ .parse_copt = drr_parse_class_opt,
+ .print_copt = drr_print_opt,
+};
diff --git a/iproute2/tc/q_dsmark.c b/iproute2/tc/q_dsmark.c
new file mode 100644
index 0000000..05185c0
--- /dev/null
+++ b/iproute2/tc/q_dsmark.c
@@ -0,0 +1,174 @@
+/*
+ * q_dsmark.c Differentiated Services field marking.
+ *
+ * Hacked 1998,1999 by Werner Almesberger, EPFL ICA
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+
+static void explain(void)
+{
+ fprintf(stderr,"Usage: dsmark indices INDICES [ default_index "
+ "DEFAULT_INDEX ] [ set_tc_index ]\n");
+}
+
+
+static int dsmark_parse_opt(struct qdisc_util *qu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ struct rtattr *tail;
+ __u16 ind;
+ char *end;
+ int dflt,set_tc_index;
+
+ ind = set_tc_index = 0;
+ dflt = -1;
+ while (argc > 0) {
+ if (!strcmp(*argv,"indices")) {
+ NEXT_ARG();
+ ind = strtoul(*argv,&end,0);
+ if (*end) {
+ explain();
+ return -1;
+ }
+ }
+ else if (!strcmp(*argv,"default_index") || !strcmp(*argv,
+ "default")) {
+ NEXT_ARG();
+ dflt = strtoul(*argv,&end,0);
+ if (*end) {
+ explain();
+ return -1;
+ }
+ }
+ else if (!strcmp(*argv,"set_tc_index")) {
+ set_tc_index = 1;
+ }
+ else {
+ explain();
+ return -1;
+ }
+ argc--;
+ argv++;
+ }
+ if (!ind) {
+ explain();
+ return -1;
+ }
+ tail = NLMSG_TAIL(n);
+ addattr_l(n,1024,TCA_OPTIONS,NULL,0);
+ addattr_l(n,1024,TCA_DSMARK_INDICES,&ind,sizeof(ind));
+ if (dflt != -1) {
+ __u16 tmp = dflt;
+
+ addattr_l(n,1024,TCA_DSMARK_DEFAULT_INDEX,&tmp,sizeof(tmp));
+ }
+ if (set_tc_index) addattr_l(n,1024,TCA_DSMARK_SET_TC_INDEX,NULL,0);
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+
+static void explain_class(void)
+{
+ fprintf(stderr, "Usage: ... dsmark [ mask MASK ] [ value VALUE ]\n");
+}
+
+
+static int dsmark_parse_class_opt(struct qdisc_util *qu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ struct rtattr *tail;
+ __u8 tmp;
+ char *end;
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n,1024,TCA_OPTIONS,NULL,0);
+ while (argc > 0) {
+ if (!strcmp(*argv,"mask")) {
+ NEXT_ARG();
+ tmp = strtoul(*argv,&end,0);
+ if (*end) {
+ explain_class();
+ return -1;
+ }
+ addattr_l(n,1024,TCA_DSMARK_MASK,&tmp,1);
+ }
+ else if (!strcmp(*argv,"value")) {
+ NEXT_ARG();
+ tmp = strtoul(*argv,&end,0);
+ if (*end) {
+ explain_class();
+ return -1;
+ }
+ addattr_l(n,1024,TCA_DSMARK_VALUE,&tmp,1);
+ }
+ else {
+ explain_class();
+ return -1;
+ }
+ argc--;
+ argv++;
+ }
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+
+
+static int dsmark_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct rtattr *tb[TCA_DSMARK_MAX+1];
+
+ if (!opt) return 0;
+ memset(tb, 0, sizeof(tb));
+ parse_rtattr(tb, TCA_DSMARK_MAX, RTA_DATA(opt), RTA_PAYLOAD(opt));
+ if (tb[TCA_DSMARK_MASK]) {
+ if (!RTA_PAYLOAD(tb[TCA_DSMARK_MASK]))
+ fprintf(stderr,"dsmark: empty mask\n");
+ else fprintf(f,"mask 0x%02x ",
+ rta_getattr_u8(tb[TCA_DSMARK_MASK]));
+ }
+ if (tb[TCA_DSMARK_VALUE]) {
+ if (!RTA_PAYLOAD(tb[TCA_DSMARK_VALUE]))
+ fprintf(stderr,"dsmark: empty value\n");
+ else fprintf(f,"value 0x%02x ",
+ rta_getattr_u8(tb[TCA_DSMARK_VALUE]));
+ }
+ if (tb[TCA_DSMARK_INDICES]) {
+ if (RTA_PAYLOAD(tb[TCA_DSMARK_INDICES]) < sizeof(__u16))
+ fprintf(stderr,"dsmark: indices too short\n");
+ else fprintf(f,"indices 0x%04x ",
+ rta_getattr_u16(tb[TCA_DSMARK_INDICES]));
+ }
+ if (tb[TCA_DSMARK_DEFAULT_INDEX]) {
+ if (RTA_PAYLOAD(tb[TCA_DSMARK_DEFAULT_INDEX]) < sizeof(__u16))
+ fprintf(stderr,"dsmark: default_index too short\n");
+ else fprintf(f,"default_index 0x%04x ",
+ rta_getattr_u16(tb[TCA_DSMARK_DEFAULT_INDEX]));
+ }
+ if (tb[TCA_DSMARK_SET_TC_INDEX]) fprintf(f,"set_tc_index ");
+ return 0;
+}
+
+
+struct qdisc_util dsmark_qdisc_util = {
+ .id = "dsmark",
+ .parse_qopt = dsmark_parse_opt,
+ .print_qopt = dsmark_print_opt,
+ .parse_copt = dsmark_parse_class_opt,
+ .print_copt = dsmark_print_opt,
+};
diff --git a/iproute2/tc/q_fifo.c b/iproute2/tc/q_fifo.c
new file mode 100644
index 0000000..c9ab123
--- /dev/null
+++ b/iproute2/tc/q_fifo.c
@@ -0,0 +1,102 @@
+/*
+ * q_fifo.c FIFO.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... <[p|b]fifo | pfifo_head_drop> [ limit NUMBER ]\n");
+}
+
+static int fifo_parse_opt(struct qdisc_util *qu, int argc, char **argv, struct nlmsghdr *n)
+{
+ int ok=0;
+ struct tc_fifo_qopt opt;
+ memset(&opt, 0, sizeof(opt));
+
+ while (argc > 0) {
+ if (strcmp(*argv, "limit") == 0) {
+ NEXT_ARG();
+ if (get_size(&opt.limit, *argv)) {
+ fprintf(stderr, "%s: Illegal value for \"limit\": \"%s\"\n", qu->id, *argv);
+ return -1;
+ }
+ ok++;
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "%s: unknown parameter \"%s\"\n", qu->id, *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ if (ok)
+ addattr_l(n, 1024, TCA_OPTIONS, &opt, sizeof(opt));
+ return 0;
+}
+
+static int fifo_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct tc_fifo_qopt *qopt;
+
+ if (opt == NULL)
+ return 0;
+
+ if (RTA_PAYLOAD(opt) < sizeof(*qopt))
+ return -1;
+ qopt = RTA_DATA(opt);
+ if (strcmp(qu->id, "bfifo") == 0) {
+ SPRINT_BUF(b1);
+ fprintf(f, "limit %s", sprint_size(qopt->limit, b1));
+ } else
+ fprintf(f, "limit %up", qopt->limit);
+ return 0;
+}
+
+
+struct qdisc_util bfifo_qdisc_util = {
+ .id = "bfifo",
+ .parse_qopt = fifo_parse_opt,
+ .print_qopt = fifo_print_opt,
+};
+
+struct qdisc_util pfifo_qdisc_util = {
+ .id = "pfifo",
+ .parse_qopt = fifo_parse_opt,
+ .print_qopt = fifo_print_opt,
+};
+
+struct qdisc_util pfifo_head_drop_qdisc_util = {
+ .id = "pfifo_head_drop",
+ .parse_qopt = fifo_parse_opt,
+ .print_qopt = fifo_print_opt,
+};
+
+extern int prio_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt);
+struct qdisc_util pfifo_fast_qdisc_util = {
+ .id = "pfifo_fast",
+ .print_qopt = prio_print_opt,
+};
diff --git a/iproute2/tc/q_fq.c b/iproute2/tc/q_fq.c
new file mode 100644
index 0000000..2a370b3
--- /dev/null
+++ b/iproute2/tc/q_fq.c
@@ -0,0 +1,329 @@
+/*
+ * Fair Queue
+ *
+ * Copyright (C) 2013-2015 Eric Dumazet <edumazet@google.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions, and the following disclaimer,
+ * without modification.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. The names of the authors may not be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * Alternatively, provided that this notice is retained in full, this
+ * software may be distributed under the terms of the GNU General
+ * Public License ("GPL") version 2, in which case the provisions of the
+ * GPL apply INSTEAD OF those given above.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <stdbool.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... fq [ limit PACKETS ] [ flow_limit PACKETS ]\n");
+ fprintf(stderr, " [ quantum BYTES ] [ initial_quantum BYTES ]\n");
+ fprintf(stderr, " [ maxrate RATE ] [ buckets NUMBER ]\n");
+ fprintf(stderr, " [ [no]pacing ] [ refill_delay TIME ]\n");
+ fprintf(stderr, " [ orphan_mask MASK]\n");
+}
+
+static unsigned int ilog2(unsigned int val)
+{
+ unsigned int res = 0;
+
+ val--;
+ while (val) {
+ res++;
+ val >>= 1;
+ }
+ return res;
+}
+
+static int fq_parse_opt(struct qdisc_util *qu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ unsigned int plimit;
+ unsigned int flow_plimit;
+ unsigned int quantum;
+ unsigned int initial_quantum;
+ unsigned int buckets = 0;
+ unsigned int maxrate;
+ unsigned int defrate;
+ unsigned int refill_delay;
+ unsigned int orphan_mask;
+ bool set_plimit = false;
+ bool set_flow_plimit = false;
+ bool set_quantum = false;
+ bool set_initial_quantum = false;
+ bool set_maxrate = false;
+ bool set_defrate = false;
+ bool set_refill_delay = false;
+ bool set_orphan_mask = false;
+ int pacing = -1;
+ struct rtattr *tail;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "limit") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&plimit, *argv, 0)) {
+ fprintf(stderr, "Illegal \"limit\"\n");
+ return -1;
+ }
+ set_plimit = true;
+ } else if (strcmp(*argv, "flow_limit") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&flow_plimit, *argv, 0)) {
+ fprintf(stderr, "Illegal \"flow_limit\"\n");
+ return -1;
+ }
+ set_flow_plimit = true;
+ } else if (strcmp(*argv, "buckets") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&buckets, *argv, 0)) {
+ fprintf(stderr, "Illegal \"buckets\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "maxrate") == 0) {
+ NEXT_ARG();
+ if (get_rate(&maxrate, *argv)) {
+ fprintf(stderr, "Illegal \"maxrate\"\n");
+ return -1;
+ }
+ set_maxrate = true;
+ } else if (strcmp(*argv, "defrate") == 0) {
+ NEXT_ARG();
+ if (get_rate(&defrate, *argv)) {
+ fprintf(stderr, "Illegal \"defrate\"\n");
+ return -1;
+ }
+ set_defrate = true;
+ } else if (strcmp(*argv, "quantum") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&quantum, *argv, 0)) {
+ fprintf(stderr, "Illegal \"quantum\"\n");
+ return -1;
+ }
+ set_quantum = true;
+ } else if (strcmp(*argv, "initial_quantum") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&initial_quantum, *argv, 0)) {
+ fprintf(stderr, "Illegal \"initial_quantum\"\n");
+ return -1;
+ }
+ set_initial_quantum = true;
+ } else if (strcmp(*argv, "orphan_mask") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&orphan_mask, *argv, 0)) {
+ fprintf(stderr, "Illegal \"initial_quantum\"\n");
+ return -1;
+ }
+ set_orphan_mask = true;
+ } else if (strcmp(*argv, "refill_delay") == 0) {
+ NEXT_ARG();
+ if (get_time(&refill_delay, *argv)) {
+ fprintf(stderr, "Illegal \"refill_delay\"\n");
+ return -1;
+ }
+ set_refill_delay = true;
+ } else if (strcmp(*argv, "pacing") == 0) {
+ pacing = 1;
+ } else if (strcmp(*argv, "nopacing") == 0) {
+ pacing = 0;
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+ if (buckets) {
+ unsigned int log = ilog2(buckets);
+
+ addattr_l(n, 1024, TCA_FQ_BUCKETS_LOG,
+ &log, sizeof(log));
+ }
+ if (set_plimit)
+ addattr_l(n, 1024, TCA_FQ_PLIMIT,
+ &plimit, sizeof(plimit));
+ if (set_flow_plimit)
+ addattr_l(n, 1024, TCA_FQ_FLOW_PLIMIT,
+ &flow_plimit, sizeof(flow_plimit));
+ if (set_quantum)
+ addattr_l(n, 1024, TCA_FQ_QUANTUM, &quantum, sizeof(quantum));
+ if (set_initial_quantum)
+ addattr_l(n, 1024, TCA_FQ_INITIAL_QUANTUM,
+ &initial_quantum, sizeof(initial_quantum));
+ if (pacing != -1)
+ addattr_l(n, 1024, TCA_FQ_RATE_ENABLE,
+ &pacing, sizeof(pacing));
+ if (set_maxrate)
+ addattr_l(n, 1024, TCA_FQ_FLOW_MAX_RATE,
+ &maxrate, sizeof(maxrate));
+ if (set_defrate)
+ addattr_l(n, 1024, TCA_FQ_FLOW_DEFAULT_RATE,
+ &defrate, sizeof(defrate));
+ if (set_refill_delay)
+ addattr_l(n, 1024, TCA_FQ_FLOW_REFILL_DELAY,
+ &refill_delay, sizeof(refill_delay));
+ if (set_orphan_mask)
+ addattr_l(n, 1024, TCA_FQ_ORPHAN_MASK,
+ &orphan_mask, sizeof(refill_delay));
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+static int fq_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct rtattr *tb[TCA_FQ_MAX + 1];
+ unsigned int plimit, flow_plimit;
+ unsigned int buckets_log;
+ int pacing;
+ unsigned int rate, quantum;
+ unsigned int refill_delay;
+ unsigned int orphan_mask;
+ SPRINT_BUF(b1);
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_FQ_MAX, opt);
+
+ if (tb[TCA_FQ_PLIMIT] &&
+ RTA_PAYLOAD(tb[TCA_FQ_PLIMIT]) >= sizeof(__u32)) {
+ plimit = rta_getattr_u32(tb[TCA_FQ_PLIMIT]);
+ fprintf(f, "limit %up ", plimit);
+ }
+ if (tb[TCA_FQ_FLOW_PLIMIT] &&
+ RTA_PAYLOAD(tb[TCA_FQ_FLOW_PLIMIT]) >= sizeof(__u32)) {
+ flow_plimit = rta_getattr_u32(tb[TCA_FQ_FLOW_PLIMIT]);
+ fprintf(f, "flow_limit %up ", flow_plimit);
+ }
+ if (tb[TCA_FQ_BUCKETS_LOG] &&
+ RTA_PAYLOAD(tb[TCA_FQ_BUCKETS_LOG]) >= sizeof(__u32)) {
+ buckets_log = rta_getattr_u32(tb[TCA_FQ_BUCKETS_LOG]);
+ fprintf(f, "buckets %u ", 1U << buckets_log);
+ }
+ if (tb[TCA_FQ_ORPHAN_MASK] &&
+ RTA_PAYLOAD(tb[TCA_FQ_ORPHAN_MASK]) >= sizeof(__u32)) {
+ orphan_mask = rta_getattr_u32(tb[TCA_FQ_ORPHAN_MASK]);
+ fprintf(f, "orphan_mask %u ", orphan_mask);
+ }
+ if (tb[TCA_FQ_RATE_ENABLE] &&
+ RTA_PAYLOAD(tb[TCA_FQ_RATE_ENABLE]) >= sizeof(int)) {
+ pacing = rta_getattr_u32(tb[TCA_FQ_RATE_ENABLE]);
+ if (pacing == 0)
+ fprintf(f, "nopacing ");
+ }
+ if (tb[TCA_FQ_QUANTUM] &&
+ RTA_PAYLOAD(tb[TCA_FQ_QUANTUM]) >= sizeof(__u32)) {
+ quantum = rta_getattr_u32(tb[TCA_FQ_QUANTUM]);
+ fprintf(f, "quantum %u ", quantum);
+ }
+ if (tb[TCA_FQ_INITIAL_QUANTUM] &&
+ RTA_PAYLOAD(tb[TCA_FQ_INITIAL_QUANTUM]) >= sizeof(__u32)) {
+ quantum = rta_getattr_u32(tb[TCA_FQ_INITIAL_QUANTUM]);
+ fprintf(f, "initial_quantum %u ", quantum);
+ }
+ if (tb[TCA_FQ_FLOW_MAX_RATE] &&
+ RTA_PAYLOAD(tb[TCA_FQ_FLOW_MAX_RATE]) >= sizeof(__u32)) {
+ rate = rta_getattr_u32(tb[TCA_FQ_FLOW_MAX_RATE]);
+
+ if (rate != ~0U)
+ fprintf(f, "maxrate %s ", sprint_rate(rate, b1));
+ }
+ if (tb[TCA_FQ_FLOW_DEFAULT_RATE] &&
+ RTA_PAYLOAD(tb[TCA_FQ_FLOW_DEFAULT_RATE]) >= sizeof(__u32)) {
+ rate = rta_getattr_u32(tb[TCA_FQ_FLOW_DEFAULT_RATE]);
+
+ if (rate != 0)
+ fprintf(f, "defrate %s ", sprint_rate(rate, b1));
+ }
+ if (tb[TCA_FQ_FLOW_REFILL_DELAY] &&
+ RTA_PAYLOAD(tb[TCA_FQ_FLOW_REFILL_DELAY]) >= sizeof(__u32)) {
+ refill_delay = rta_getattr_u32(tb[TCA_FQ_FLOW_REFILL_DELAY]);
+ fprintf(f, "refill_delay %s ", sprint_time(refill_delay, b1));
+ }
+
+ return 0;
+}
+
+static int fq_print_xstats(struct qdisc_util *qu, FILE *f,
+ struct rtattr *xstats)
+{
+ struct tc_fq_qd_stats *st;
+
+ if (xstats == NULL)
+ return 0;
+
+ if (RTA_PAYLOAD(xstats) < sizeof(*st))
+ return -1;
+
+ st = RTA_DATA(xstats);
+
+ fprintf(f, " %u flows (%u inactive, %u throttled)",
+ st->flows, st->inactive_flows, st->throttled_flows);
+
+ if (st->time_next_delayed_flow > 0)
+ fprintf(f, ", next packet delay %llu ns", st->time_next_delayed_flow);
+
+ fprintf(f, "\n %llu gc, %llu highprio",
+ st->gc_flows, st->highprio_packets);
+
+ if (st->tcp_retrans)
+ fprintf(f, ", %llu retrans", st->tcp_retrans);
+
+ fprintf(f, ", %llu throttled", st->throttled);
+
+ if (st->flows_plimit)
+ fprintf(f, ", %llu flows_plimit", st->flows_plimit);
+
+ if (st->pkts_too_long || st->allocation_errors)
+ fprintf(f, "\n %llu too long pkts, %llu alloc errors\n",
+ st->pkts_too_long, st->allocation_errors);
+
+ return 0;
+}
+
+struct qdisc_util fq_qdisc_util = {
+ .id = "fq",
+ .parse_qopt = fq_parse_opt,
+ .print_qopt = fq_print_opt,
+ .print_xstats = fq_print_xstats,
+};
diff --git a/iproute2/tc/q_fq_codel.c b/iproute2/tc/q_fq_codel.c
new file mode 100644
index 0000000..4f747eb
--- /dev/null
+++ b/iproute2/tc/q_fq_codel.c
@@ -0,0 +1,253 @@
+/*
+ * Fair Queue Codel
+ *
+ * Copyright (C) 2012,2015 Eric Dumazet <edumazet@google.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions, and the following disclaimer,
+ * without modification.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. The names of the authors may not be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * Alternatively, provided that this notice is retained in full, this
+ * software may be distributed under the terms of the GNU General
+ * Public License ("GPL") version 2, in which case the provisions of the
+ * GPL apply INSTEAD OF those given above.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... fq_codel [ limit PACKETS ] [ flows NUMBER ]\n");
+ fprintf(stderr, " [ target TIME] [ interval TIME ]\n");
+ fprintf(stderr, " [ quantum BYTES ] [ [no]ecn ]\n");
+ fprintf(stderr, " [ ce_threshold TIME ]\n");
+}
+
+static int fq_codel_parse_opt(struct qdisc_util *qu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ unsigned limit = 0;
+ unsigned flows = 0;
+ unsigned target = 0;
+ unsigned interval = 0;
+ unsigned quantum = 0;
+ unsigned ce_threshold = ~0U;
+ int ecn = -1;
+ struct rtattr *tail;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "limit") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&limit, *argv, 0)) {
+ fprintf(stderr, "Illegal \"limit\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "flows") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&flows, *argv, 0)) {
+ fprintf(stderr, "Illegal \"flows\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "quantum") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&quantum, *argv, 0)) {
+ fprintf(stderr, "Illegal \"quantum\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "target") == 0) {
+ NEXT_ARG();
+ if (get_time(&target, *argv)) {
+ fprintf(stderr, "Illegal \"target\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "ce_threshold") == 0) {
+ NEXT_ARG();
+ if (get_time(&ce_threshold, *argv)) {
+ fprintf(stderr, "Illegal \"ce_threshold\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "interval") == 0) {
+ NEXT_ARG();
+ if (get_time(&interval, *argv)) {
+ fprintf(stderr, "Illegal \"interval\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "ecn") == 0) {
+ ecn = 1;
+ } else if (strcmp(*argv, "noecn") == 0) {
+ ecn = 0;
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+ if (limit)
+ addattr_l(n, 1024, TCA_FQ_CODEL_LIMIT, &limit, sizeof(limit));
+ if (flows)
+ addattr_l(n, 1024, TCA_FQ_CODEL_FLOWS, &flows, sizeof(flows));
+ if (quantum)
+ addattr_l(n, 1024, TCA_FQ_CODEL_QUANTUM, &quantum, sizeof(quantum));
+ if (interval)
+ addattr_l(n, 1024, TCA_FQ_CODEL_INTERVAL, &interval, sizeof(interval));
+ if (target)
+ addattr_l(n, 1024, TCA_FQ_CODEL_TARGET, &target, sizeof(target));
+ if (ecn != -1)
+ addattr_l(n, 1024, TCA_FQ_CODEL_ECN, &ecn, sizeof(ecn));
+ if (ce_threshold != ~0U)
+ addattr_l(n, 1024, TCA_FQ_CODEL_CE_THRESHOLD,
+ &ce_threshold, sizeof(ce_threshold));
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+static int fq_codel_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct rtattr *tb[TCA_FQ_CODEL_MAX + 1];
+ unsigned limit;
+ unsigned flows;
+ unsigned interval;
+ unsigned target;
+ unsigned ecn;
+ unsigned quantum;
+ unsigned ce_threshold;
+ SPRINT_BUF(b1);
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_FQ_CODEL_MAX, opt);
+
+ if (tb[TCA_FQ_CODEL_LIMIT] &&
+ RTA_PAYLOAD(tb[TCA_FQ_CODEL_LIMIT]) >= sizeof(__u32)) {
+ limit = rta_getattr_u32(tb[TCA_FQ_CODEL_LIMIT]);
+ fprintf(f, "limit %up ", limit);
+ }
+ if (tb[TCA_FQ_CODEL_FLOWS] &&
+ RTA_PAYLOAD(tb[TCA_FQ_CODEL_FLOWS]) >= sizeof(__u32)) {
+ flows = rta_getattr_u32(tb[TCA_FQ_CODEL_FLOWS]);
+ fprintf(f, "flows %u ", flows);
+ }
+ if (tb[TCA_FQ_CODEL_QUANTUM] &&
+ RTA_PAYLOAD(tb[TCA_FQ_CODEL_QUANTUM]) >= sizeof(__u32)) {
+ quantum = rta_getattr_u32(tb[TCA_FQ_CODEL_QUANTUM]);
+ fprintf(f, "quantum %u ", quantum);
+ }
+ if (tb[TCA_FQ_CODEL_TARGET] &&
+ RTA_PAYLOAD(tb[TCA_FQ_CODEL_TARGET]) >= sizeof(__u32)) {
+ target = rta_getattr_u32(tb[TCA_FQ_CODEL_TARGET]);
+ fprintf(f, "target %s ", sprint_time(target, b1));
+ }
+ if (tb[TCA_FQ_CODEL_CE_THRESHOLD] &&
+ RTA_PAYLOAD(tb[TCA_FQ_CODEL_CE_THRESHOLD]) >= sizeof(__u32)) {
+ ce_threshold = rta_getattr_u32(tb[TCA_FQ_CODEL_CE_THRESHOLD]);
+ fprintf(f, "ce_threshold %s ", sprint_time(ce_threshold, b1));
+ }
+ if (tb[TCA_FQ_CODEL_INTERVAL] &&
+ RTA_PAYLOAD(tb[TCA_FQ_CODEL_INTERVAL]) >= sizeof(__u32)) {
+ interval = rta_getattr_u32(tb[TCA_FQ_CODEL_INTERVAL]);
+ fprintf(f, "interval %s ", sprint_time(interval, b1));
+ }
+ if (tb[TCA_FQ_CODEL_ECN] &&
+ RTA_PAYLOAD(tb[TCA_FQ_CODEL_ECN]) >= sizeof(__u32)) {
+ ecn = rta_getattr_u32(tb[TCA_FQ_CODEL_ECN]);
+ if (ecn)
+ fprintf(f, "ecn ");
+ }
+
+ return 0;
+}
+
+static int fq_codel_print_xstats(struct qdisc_util *qu, FILE *f,
+ struct rtattr *xstats)
+{
+ struct tc_fq_codel_xstats _st, *st;
+ SPRINT_BUF(b1);
+
+ if (xstats == NULL)
+ return 0;
+
+ st = RTA_DATA(xstats);
+ if (RTA_PAYLOAD(xstats) < sizeof(*st)) {
+ memset(&_st, 0, sizeof(_st));
+ memcpy(&_st, st, RTA_PAYLOAD(xstats));
+ st = &_st;
+ }
+ if (st->type == TCA_FQ_CODEL_XSTATS_QDISC) {
+ fprintf(f, " maxpacket %u drop_overlimit %u new_flow_count %u ecn_mark %u",
+ st->qdisc_stats.maxpacket,
+ st->qdisc_stats.drop_overlimit,
+ st->qdisc_stats.new_flow_count,
+ st->qdisc_stats.ecn_mark);
+ if (st->qdisc_stats.ce_mark)
+ fprintf(f, " ce_mark %u", st->qdisc_stats.ce_mark);
+ fprintf(f, "\n new_flows_len %u old_flows_len %u",
+ st->qdisc_stats.new_flows_len,
+ st->qdisc_stats.old_flows_len);
+ }
+ if (st->type == TCA_FQ_CODEL_XSTATS_CLASS) {
+ fprintf(f, " deficit %d count %u lastcount %u ldelay %s",
+ st->class_stats.deficit,
+ st->class_stats.count,
+ st->class_stats.lastcount,
+ sprint_time(st->class_stats.ldelay, b1));
+ if (st->class_stats.dropping) {
+ fprintf(f, " dropping");
+ if (st->class_stats.drop_next < 0)
+ fprintf(f, " drop_next -%s",
+ sprint_time(-st->class_stats.drop_next, b1));
+ else
+ fprintf(f, " drop_next %s",
+ sprint_time(st->class_stats.drop_next, b1));
+ }
+ }
+ return 0;
+
+}
+
+struct qdisc_util fq_codel_qdisc_util = {
+ .id = "fq_codel",
+ .parse_qopt = fq_codel_parse_opt,
+ .print_qopt = fq_codel_print_opt,
+ .print_xstats = fq_codel_print_xstats,
+};
diff --git a/iproute2/tc/q_gred.c b/iproute2/tc/q_gred.c
new file mode 100644
index 0000000..f31daa3
--- /dev/null
+++ b/iproute2/tc/q_gred.c
@@ -0,0 +1,354 @@
+/*
+ * q_gred.c GRED.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: J Hadi Salim(hadi@nortelnetworks.com)
+ * code ruthlessly ripped from
+ * Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <math.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+#include "tc_red.h"
+
+
+#if 0
+#define DPRINTF(format,args...) fprintf(stderr,format,##args)
+#else
+#define DPRINTF(format,args...)
+#endif
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: tc qdisc { add | replace | change } ... gred setup vqs NUMBER\n");
+ fprintf(stderr, " default DEFAULT_VQ [ grio ] [ limit BYTES ]\n");
+ fprintf(stderr, " tc qdisc change ... gred vq VQ [ prio VALUE ] limit BYTES\n");
+ fprintf(stderr, " min BYTES max BYTES avpkt BYTES [ burst PACKETS ]\n");
+ fprintf(stderr, " [ probability PROBABILITY ] [ bandwidth KBPS ]\n");
+}
+
+static int init_gred(struct qdisc_util *qu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+
+ struct rtattr *tail;
+ struct tc_gred_sopt opt = { 0 };
+ __u32 limit = 0;
+
+ opt.def_DP = MAX_DPs;
+
+ while (argc > 0) {
+ DPRINTF(stderr,"init_gred: invoked with %s\n",*argv);
+ if (strcmp(*argv, "vqs") == 0 ||
+ strcmp(*argv, "DPs") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&opt.DPs, *argv, 10)) {
+ fprintf(stderr, "Illegal \"vqs\"\n");
+ return -1;
+ } else if (opt.DPs > MAX_DPs) {
+ fprintf(stderr, "GRED: only %u VQs are "
+ "currently supported\n", MAX_DPs);
+ return -1;
+ }
+ } else if (strcmp(*argv, "default") == 0) {
+ if (opt.DPs == 0) {
+ fprintf(stderr, "\"default\" must be defined "
+ "after \"vqs\"\n");
+ return -1;
+ }
+ NEXT_ARG();
+ if (get_unsigned(&opt.def_DP, *argv, 10)) {
+ fprintf(stderr, "Illegal \"default\"\n");
+ return -1;
+ } else if (opt.def_DP >= opt.DPs) {
+ fprintf(stderr, "\"default\" must be less than "
+ "\"vqs\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "grio") == 0) {
+ opt.grio = 1;
+ } else if (strcmp(*argv, "limit") == 0) {
+ NEXT_ARG();
+ if (get_size(&limit, *argv)) {
+ fprintf(stderr, "Illegal \"limit\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ if (!opt.DPs || opt.def_DP == MAX_DPs) {
+ fprintf(stderr, "Illegal gred setup parameters \n");
+ return -1;
+ }
+
+ DPRINTF("TC_GRED: sending DPs=%u def_DP=%u\n",opt.DPs,opt.def_DP);
+ n->nlmsg_flags|=NLM_F_CREATE;
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+ addattr_l(n, 1024, TCA_GRED_DPS, &opt, sizeof(struct tc_gred_sopt));
+ if (limit)
+ addattr32(n, 1024, TCA_GRED_LIMIT, limit);
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+/*
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+*/
+static int gred_parse_opt(struct qdisc_util *qu, int argc, char **argv, struct nlmsghdr *n)
+{
+ int ok=0;
+ struct tc_gred_qopt opt = { 0 };
+ unsigned burst = 0;
+ unsigned avpkt = 0;
+ double probability = 0.02;
+ unsigned rate = 0;
+ int parm;
+ __u8 sbuf[256];
+ struct rtattr *tail;
+ __u32 max_P;
+
+ opt.DP = MAX_DPs;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "limit") == 0) {
+ NEXT_ARG();
+ if (get_size(&opt.limit, *argv)) {
+ fprintf(stderr, "Illegal \"limit\"\n");
+ return -1;
+ }
+ ok++;
+ } else if (strcmp(*argv, "setup") == 0) {
+ if (ok) {
+ fprintf(stderr, "Illegal \"setup\"\n");
+ return -1;
+ }
+ return init_gred(qu, argc-1, argv+1, n);
+ } else if (strcmp(*argv, "min") == 0) {
+ NEXT_ARG();
+ if (get_size(&opt.qth_min, *argv)) {
+ fprintf(stderr, "Illegal \"min\"\n");
+ return -1;
+ }
+ ok++;
+ } else if (strcmp(*argv, "max") == 0) {
+ NEXT_ARG();
+ if (get_size(&opt.qth_max, *argv)) {
+ fprintf(stderr, "Illegal \"max\"\n");
+ return -1;
+ }
+ ok++;
+ } else if (strcmp(*argv, "vq") == 0 ||
+ strcmp(*argv, "DP") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&opt.DP, *argv, 10)) {
+ fprintf(stderr, "Illegal \"vq\"\n");
+ return -1;
+ } else if (opt.DP >= MAX_DPs) {
+ fprintf(stderr, "GRED: only %u VQs are "
+ "currently supported\n", MAX_DPs);
+ return -1;
+ } /* need a better error check */
+ ok++;
+ } else if (strcmp(*argv, "burst") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&burst, *argv, 0)) {
+ fprintf(stderr, "Illegal \"burst\"\n");
+ return -1;
+ }
+ ok++;
+ } else if (strcmp(*argv, "avpkt") == 0) {
+ NEXT_ARG();
+ if (get_size(&avpkt, *argv)) {
+ fprintf(stderr, "Illegal \"avpkt\"\n");
+ return -1;
+ }
+ ok++;
+ } else if (strcmp(*argv, "probability") == 0) {
+ NEXT_ARG();
+ if (sscanf(*argv, "%lg", &probability) != 1) {
+ fprintf(stderr, "Illegal \"probability\"\n");
+ return -1;
+ }
+ ok++;
+ } else if (strcmp(*argv, "prio") == 0) {
+ NEXT_ARG();
+ opt.prio=strtol(*argv, (char **)NULL, 10);
+ /* some error check here */
+ ok++;
+ } else if (strcmp(*argv, "bandwidth") == 0) {
+ NEXT_ARG();
+ if (get_rate(&rate, *argv)) {
+ fprintf(stderr, "Illegal \"bandwidth\"\n");
+ return -1;
+ }
+ ok++;
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ if (!ok) {
+ explain();
+ return -1;
+ }
+ if (opt.DP == MAX_DPs || !opt.limit || !opt.qth_min || !opt.qth_max ||
+ !avpkt) {
+ fprintf(stderr, "Required parameter (vq, limit, min, max, "
+ "avpkt) is missing\n");
+ return -1;
+ }
+ if (!burst) {
+ burst = (2 * opt.qth_min + opt.qth_max) / (3 * avpkt);
+ fprintf(stderr, "GRED: set burst to %u\n", burst);
+ }
+ if (!rate) {
+ get_rate(&rate, "10Mbit");
+ fprintf(stderr, "GRED: set bandwidth to 10Mbit\n");
+ }
+ if ((parm = tc_red_eval_ewma(opt.qth_min, burst, avpkt)) < 0) {
+ fprintf(stderr, "GRED: failed to calculate EWMA constant.\n");
+ return -1;
+ }
+ if (parm >= 10)
+ fprintf(stderr, "GRED: WARNING. Burst %u seems to be too "
+ "large.\n", burst);
+ opt.Wlog = parm;
+ if ((parm = tc_red_eval_P(opt.qth_min, opt.qth_max, probability)) < 0) {
+ fprintf(stderr, "GRED: failed to calculate probability.\n");
+ return -1;
+ }
+ opt.Plog = parm;
+ if ((parm = tc_red_eval_idle_damping(opt.Wlog, avpkt, rate, sbuf)) < 0)
+ {
+ fprintf(stderr, "GRED: failed to calculate idle damping "
+ "table.\n");
+ return -1;
+ }
+ opt.Scell_log = parm;
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+ addattr_l(n, 1024, TCA_GRED_PARMS, &opt, sizeof(opt));
+ addattr_l(n, 1024, TCA_GRED_STAB, sbuf, 256);
+ max_P = probability * pow(2, 32);
+ addattr32(n, 1024, TCA_GRED_MAX_P, max_P);
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+static int gred_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct rtattr *tb[TCA_GRED_MAX + 1];
+ struct tc_gred_sopt *sopt;
+ struct tc_gred_qopt *qopt;
+ __u32 *max_p = NULL;
+ __u32 *limit = NULL;
+ unsigned i;
+ SPRINT_BUF(b1);
+ SPRINT_BUF(b2);
+ SPRINT_BUF(b3);
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_GRED_MAX, opt);
+
+ if (tb[TCA_GRED_PARMS] == NULL)
+ return -1;
+
+ if (tb[TCA_GRED_MAX_P] &&
+ RTA_PAYLOAD(tb[TCA_GRED_MAX_P]) >= sizeof(__u32) * MAX_DPs)
+ max_p = RTA_DATA(tb[TCA_GRED_MAX_P]);
+
+ if (tb[TCA_GRED_LIMIT] &&
+ RTA_PAYLOAD(tb[TCA_GRED_LIMIT]) == sizeof(__u32))
+ limit = RTA_DATA(tb[TCA_GRED_LIMIT]);
+
+ sopt = RTA_DATA(tb[TCA_GRED_DPS]);
+ qopt = RTA_DATA(tb[TCA_GRED_PARMS]);
+ if (RTA_PAYLOAD(tb[TCA_GRED_DPS]) < sizeof(*sopt) ||
+ RTA_PAYLOAD(tb[TCA_GRED_PARMS]) < sizeof(*qopt)*MAX_DPs) {
+ fprintf(f,"\n GRED received message smaller than expected\n");
+ return -1;
+ }
+
+/* Bad hack! should really return a proper message as shown above*/
+
+ fprintf(f, "vqs %u default %u %s",
+ sopt->DPs,
+ sopt->def_DP,
+ sopt->grio ? "grio " : "");
+
+ if (limit)
+ fprintf(f, "limit %s ",
+ sprint_size(*limit, b1));
+
+ for (i=0;i<MAX_DPs;i++, qopt++) {
+ if (qopt->DP >= MAX_DPs) continue;
+ fprintf(f, "\n vq %u prio %hhu limit %s min %s max %s ",
+ qopt->DP,
+ qopt->prio,
+ sprint_size(qopt->limit, b1),
+ sprint_size(qopt->qth_min, b2),
+ sprint_size(qopt->qth_max, b3));
+ if (show_details) {
+ fprintf(f, "ewma %u ", qopt->Wlog);
+ if (max_p)
+ fprintf(f, "probability %lg ", max_p[i] / pow(2, 32));
+ else
+ fprintf(f, "Plog %u ", qopt->Plog);
+ fprintf(f, "Scell_log %u ", qopt->Scell_log);
+ }
+ if (show_stats) {
+ fprintf(f, "\n Queue size: average %s current %s ",
+ sprint_size(qopt->qave, b1),
+ sprint_size(qopt->backlog, b2));
+ fprintf(f, "\n Dropped packets: forced %u early %u pdrop %u other %u ",
+ qopt->forced,
+ qopt->early,
+ qopt->pdrop,
+ qopt->other);
+ fprintf(f, "\n Total packets: %u (%s) ",
+ qopt->packets,
+ sprint_size(qopt->bytesin, b1));
+ }
+ }
+ return 0;
+}
+
+struct qdisc_util gred_qdisc_util = {
+ .id = "gred",
+ .parse_qopt = gred_parse_opt,
+ .print_qopt = gred_print_opt,
+};
diff --git a/iproute2/tc/q_hfsc.c b/iproute2/tc/q_hfsc.c
new file mode 100644
index 0000000..03539ec
--- /dev/null
+++ b/iproute2/tc/q_hfsc.c
@@ -0,0 +1,410 @@
+/*
+ * q_hfsc.c HFSC.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Patrick McHardy, <kaber@trash.net>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <math.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static int hfsc_get_sc(int *, char ***, struct tc_service_curve *);
+
+
+static void
+explain_qdisc(void)
+{
+ fprintf(stderr,
+ "Usage: ... hfsc [ default CLASSID ]\n"
+ "\n"
+ " default: default class for unclassified packets\n"
+ );
+}
+
+static void
+explain_class(void)
+{
+ fprintf(stderr,
+ "Usage: ... hfsc [ [ rt SC ] [ ls SC ] | [ sc SC ] ] [ ul SC ]\n"
+ "\n"
+ "SC := [ [ m1 BPS ] d SEC ] m2 BPS\n"
+ "\n"
+ " m1 : slope of first segment\n"
+ " d : x-coordinate of intersection\n"
+ " m2 : slope of second segment\n"
+ "\n"
+ "Alternative format:\n"
+ "\n"
+ "SC := [ [ umax BYTE ] dmax SEC ] rate BPS\n"
+ "\n"
+ " umax : maximum unit of work\n"
+ " dmax : maximum delay\n"
+ " rate : rate\n"
+ "\n"
+ "Remarks:\n"
+ " - at least one of 'rt', 'ls' or 'sc' must be specified\n"
+ " - 'ul' can only be specified with 'ls' or 'sc'\n"
+ "\n"
+ );
+}
+
+static void
+explain1(char *arg)
+{
+ fprintf(stderr, "HFSC: Illegal \"%s\"\n", arg);
+}
+
+static int
+hfsc_parse_opt(struct qdisc_util *qu, int argc, char **argv, struct nlmsghdr *n)
+{
+ struct tc_hfsc_qopt qopt;
+
+ memset(&qopt, 0, sizeof(qopt));
+
+ while (argc > 0) {
+ if (matches(*argv, "default") == 0) {
+ NEXT_ARG();
+ if (qopt.defcls != 0) {
+ fprintf(stderr, "HFSC: Double \"default\"\n");
+ return -1;
+ }
+ if (get_u16(&qopt.defcls, *argv, 16) < 0) {
+ explain1("default");
+ return -1;
+ }
+ } else if (matches(*argv, "help") == 0) {
+ explain_qdisc();
+ return -1;
+ } else {
+ fprintf(stderr, "HFSC: What is \"%s\" ?\n", *argv);
+ explain_qdisc();
+ return -1;
+ }
+ argc--, argv++;
+ }
+
+ addattr_l(n, 1024, TCA_OPTIONS, &qopt, sizeof(qopt));
+ return 0;
+}
+
+static int
+hfsc_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct tc_hfsc_qopt *qopt;
+
+ if (opt == NULL)
+ return 0;
+ if (RTA_PAYLOAD(opt) < sizeof(*qopt))
+ return -1;
+ qopt = RTA_DATA(opt);
+
+ if (qopt->defcls != 0)
+ fprintf(f, "default %x ", qopt->defcls);
+
+ return 0;
+}
+
+static int
+hfsc_print_xstats(struct qdisc_util *qu, FILE *f, struct rtattr *xstats)
+{
+ struct tc_hfsc_stats *st;
+
+ if (xstats == NULL)
+ return 0;
+ if (RTA_PAYLOAD(xstats) < sizeof(*st))
+ return -1;
+ st = RTA_DATA(xstats);
+
+ fprintf(f, " period %u ", st->period);
+ if (st->work != 0)
+ fprintf(f, "work %llu bytes ", (unsigned long long) st->work);
+ if (st->rtwork != 0)
+ fprintf(f, "rtwork %llu bytes ", (unsigned long long) st->rtwork);
+ fprintf(f, "level %u ", st->level);
+ fprintf(f, "\n");
+
+ return 0;
+}
+
+static int
+hfsc_parse_class_opt(struct qdisc_util *qu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ struct tc_service_curve rsc, fsc, usc;
+ int rsc_ok, fsc_ok, usc_ok;
+ struct rtattr *tail;
+
+ memset(&rsc, 0, sizeof(rsc));
+ memset(&fsc, 0, sizeof(fsc));
+ memset(&usc, 0, sizeof(usc));
+ rsc_ok = fsc_ok = usc_ok = 0;
+
+ while (argc > 0) {
+ if (matches(*argv, "rt") == 0) {
+ NEXT_ARG();
+ if (hfsc_get_sc(&argc, &argv, &rsc) < 0) {
+ explain1("rt");
+ return -1;
+ }
+ rsc_ok = 1;
+ } else if (matches(*argv, "ls") == 0) {
+ NEXT_ARG();
+ if (hfsc_get_sc(&argc, &argv, &fsc) < 0) {
+ explain1("ls");
+ return -1;
+ }
+ fsc_ok = 1;
+ } else if (matches(*argv, "sc") == 0) {
+ NEXT_ARG();
+ if (hfsc_get_sc(&argc, &argv, &rsc) < 0) {
+ explain1("sc");
+ return -1;
+ }
+ memcpy(&fsc, &rsc, sizeof(fsc));
+ rsc_ok = 1;
+ fsc_ok = 1;
+ } else if (matches(*argv, "ul") == 0) {
+ NEXT_ARG();
+ if (hfsc_get_sc(&argc, &argv, &usc) < 0) {
+ explain1("ul");
+ return -1;
+ }
+ usc_ok = 1;
+ } else if (matches(*argv, "help") == 0) {
+ explain_class();
+ return -1;
+ } else {
+ fprintf(stderr, "HFSC: What is \"%s\" ?\n", *argv);
+ explain_class();
+ return -1;
+ }
+ argc--, argv++;
+ }
+
+ if (!(rsc_ok || fsc_ok || usc_ok)) {
+ fprintf(stderr, "HFSC: no parameters given\n");
+ explain_class();
+ return -1;
+ }
+ if (usc_ok && !fsc_ok) {
+ fprintf(stderr, "HFSC: Upper-limit Service Curve without "
+ "Link-Share Service Curve\n");
+ explain_class();
+ return -1;
+ }
+
+ tail = NLMSG_TAIL(n);
+
+ addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+ if (rsc_ok)
+ addattr_l(n, 1024, TCA_HFSC_RSC, &rsc, sizeof(rsc));
+ if (fsc_ok)
+ addattr_l(n, 1024, TCA_HFSC_FSC, &fsc, sizeof(fsc));
+ if (usc_ok)
+ addattr_l(n, 1024, TCA_HFSC_USC, &usc, sizeof(usc));
+
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+static void
+hfsc_print_sc(FILE *f, char *name, struct tc_service_curve *sc)
+{
+ SPRINT_BUF(b1);
+
+ fprintf(f, "%s ", name);
+ fprintf(f, "m1 %s ", sprint_rate(sc->m1, b1));
+ fprintf(f, "d %s ", sprint_time(tc_core_ktime2time(sc->d), b1));
+ fprintf(f, "m2 %s ", sprint_rate(sc->m2, b1));
+}
+
+static int
+hfsc_print_class_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct rtattr *tb[TCA_HFSC_MAX+1];
+ struct tc_service_curve *rsc = NULL, *fsc = NULL, *usc = NULL;
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_HFSC_MAX, opt);
+
+ if (tb[TCA_HFSC_RSC]) {
+ if (RTA_PAYLOAD(tb[TCA_HFSC_RSC]) < sizeof(*rsc))
+ fprintf(stderr, "HFSC: truncated realtime option\n");
+ else
+ rsc = RTA_DATA(tb[TCA_HFSC_RSC]);
+ }
+ if (tb[TCA_HFSC_FSC]) {
+ if (RTA_PAYLOAD(tb[TCA_HFSC_FSC]) < sizeof(*fsc))
+ fprintf(stderr, "HFSC: truncated linkshare option\n");
+ else
+ fsc = RTA_DATA(tb[TCA_HFSC_FSC]);
+ }
+ if (tb[TCA_HFSC_USC]) {
+ if (RTA_PAYLOAD(tb[TCA_HFSC_USC]) < sizeof(*usc))
+ fprintf(stderr, "HFSC: truncated upperlimit option\n");
+ else
+ usc = RTA_DATA(tb[TCA_HFSC_USC]);
+ }
+
+
+ if (rsc != NULL && fsc != NULL &&
+ memcmp(rsc, fsc, sizeof(*rsc)) == 0)
+ hfsc_print_sc(f, "sc", rsc);
+ else {
+ if (rsc != NULL)
+ hfsc_print_sc(f, "rt", rsc);
+ if (fsc != NULL)
+ hfsc_print_sc(f, "ls", fsc);
+ }
+ if (usc != NULL)
+ hfsc_print_sc(f, "ul", usc);
+
+ return 0;
+}
+
+struct qdisc_util hfsc_qdisc_util = {
+ .id = "hfsc",
+ .parse_qopt = hfsc_parse_opt,
+ .print_qopt = hfsc_print_opt,
+ .print_xstats = hfsc_print_xstats,
+ .parse_copt = hfsc_parse_class_opt,
+ .print_copt = hfsc_print_class_opt,
+};
+
+static int
+hfsc_get_sc1(int *argcp, char ***argvp, struct tc_service_curve *sc)
+{
+ char **argv = *argvp;
+ int argc = *argcp;
+ unsigned int m1 = 0, d = 0, m2 = 0;
+
+ if (matches(*argv, "m1") == 0) {
+ NEXT_ARG();
+ if (get_rate(&m1, *argv) < 0) {
+ explain1("m1");
+ return -1;
+ }
+ NEXT_ARG();
+ }
+
+ if (matches(*argv, "d") == 0) {
+ NEXT_ARG();
+ if (get_time(&d, *argv) < 0) {
+ explain1("d");
+ return -1;
+ }
+ NEXT_ARG();
+ }
+
+ if (matches(*argv, "m2") == 0) {
+ NEXT_ARG();
+ if (get_rate(&m2, *argv) < 0) {
+ explain1("m2");
+ return -1;
+ }
+ } else
+ return -1;
+
+ sc->m1 = m1;
+ sc->d = tc_core_time2ktime(d);
+ sc->m2 = m2;
+
+ *argvp = argv;
+ *argcp = argc;
+ return 0;
+}
+
+static int
+hfsc_get_sc2(int *argcp, char ***argvp, struct tc_service_curve *sc)
+{
+ char **argv = *argvp;
+ int argc = *argcp;
+ unsigned int umax = 0, dmax = 0, rate = 0;
+
+ if (matches(*argv, "umax") == 0) {
+ NEXT_ARG();
+ if (get_size(&umax, *argv) < 0) {
+ explain1("umax");
+ return -1;
+ }
+ NEXT_ARG();
+ }
+
+ if (matches(*argv, "dmax") == 0) {
+ NEXT_ARG();
+ if (get_time(&dmax, *argv) < 0) {
+ explain1("dmax");
+ return -1;
+ }
+ NEXT_ARG();
+ }
+
+ if (matches(*argv, "rate") == 0) {
+ NEXT_ARG();
+ if (get_rate(&rate, *argv) < 0) {
+ explain1("rate");
+ return -1;
+ }
+ } else
+ return -1;
+
+ if (umax != 0 && dmax == 0) {
+ fprintf(stderr, "HFSC: umax given but dmax is zero.\n");
+ return -1;
+ }
+
+ if (dmax != 0 && ceil(1.0 * umax * TIME_UNITS_PER_SEC / dmax) > rate) {
+ /*
+ * concave curve, slope of first segment is umax/dmax,
+ * intersection is at dmax
+ */
+ sc->m1 = ceil(1.0 * umax * TIME_UNITS_PER_SEC / dmax); /* in bps */
+ sc->d = tc_core_time2ktime(dmax);
+ sc->m2 = rate;
+ } else {
+ /*
+ * convex curve, slope of first segment is 0, intersection
+ * is at dmax - umax / rate
+ */
+ sc->m1 = 0;
+ sc->d = tc_core_time2ktime(ceil(dmax - umax * TIME_UNITS_PER_SEC / rate));
+ sc->m2 = rate;
+ }
+
+ *argvp = argv;
+ *argcp = argc;
+ return 0;
+}
+
+static int
+hfsc_get_sc(int *argcp, char ***argvp, struct tc_service_curve *sc)
+{
+ if (hfsc_get_sc1(argcp, argvp, sc) < 0 &&
+ hfsc_get_sc2(argcp, argvp, sc) < 0)
+ return -1;
+
+ if (sc->m1 == 0 && sc->m2 == 0) {
+ fprintf(stderr, "HFSC: Service Curve has two zero slopes\n");
+ return -1;
+ }
+
+ return 0;
+}
diff --git a/iproute2/tc/q_hhf.c b/iproute2/tc/q_hhf.c
new file mode 100644
index 0000000..06ec8a2
--- /dev/null
+++ b/iproute2/tc/q_hhf.c
@@ -0,0 +1,199 @@
+/* q_hhf.c Heavy-Hitter Filter (HHF)
+ *
+ * Copyright (C) 2013 Terry Lam <vtlam@google.com>
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... hhf [ limit PACKETS ] [ quantum BYTES]\n");
+ fprintf(stderr, " [ hh_limit NUMBER ]\n");
+ fprintf(stderr, " [ reset_timeout TIME ]\n");
+ fprintf(stderr, " [ admit_bytes BYTES ]\n");
+ fprintf(stderr, " [ evict_timeout TIME ]\n");
+ fprintf(stderr, " [ non_hh_weight NUMBER ]\n");
+}
+
+static int hhf_parse_opt(struct qdisc_util *qu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ unsigned limit = 0;
+ unsigned quantum = 0;
+ unsigned hh_limit = 0;
+ unsigned reset_timeout = 0;
+ unsigned admit_bytes = 0;
+ unsigned evict_timeout = 0;
+ unsigned non_hh_weight = 0;
+ struct rtattr *tail;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "limit") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&limit, *argv, 0)) {
+ fprintf(stderr, "Illegal \"limit\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "quantum") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&quantum, *argv, 0)) {
+ fprintf(stderr, "Illegal \"quantum\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "hh_limit") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&hh_limit, *argv, 0)) {
+ fprintf(stderr, "Illegal \"hh_limit\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "reset_timeout") == 0) {
+ NEXT_ARG();
+ if (get_time(&reset_timeout, *argv)) {
+ fprintf(stderr, "Illegal \"reset_timeout\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "admit_bytes") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&admit_bytes, *argv, 0)) {
+ fprintf(stderr, "Illegal \"admit_bytes\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "evict_timeout") == 0) {
+ NEXT_ARG();
+ if (get_time(&evict_timeout, *argv)) {
+ fprintf(stderr, "Illegal \"evict_timeout\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "non_hh_weight") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&non_hh_weight, *argv, 0)) {
+ fprintf(stderr, "Illegal \"non_hh_weight\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+ if (limit)
+ addattr_l(n, 1024, TCA_HHF_BACKLOG_LIMIT, &limit,
+ sizeof(limit));
+ if (quantum)
+ addattr_l(n, 1024, TCA_HHF_QUANTUM, &quantum, sizeof(quantum));
+ if (hh_limit)
+ addattr_l(n, 1024, TCA_HHF_HH_FLOWS_LIMIT, &hh_limit,
+ sizeof(hh_limit));
+ if (reset_timeout)
+ addattr_l(n, 1024, TCA_HHF_RESET_TIMEOUT, &reset_timeout,
+ sizeof(reset_timeout));
+ if (admit_bytes)
+ addattr_l(n, 1024, TCA_HHF_ADMIT_BYTES, &admit_bytes,
+ sizeof(admit_bytes));
+ if (evict_timeout)
+ addattr_l(n, 1024, TCA_HHF_EVICT_TIMEOUT, &evict_timeout,
+ sizeof(evict_timeout));
+ if (non_hh_weight)
+ addattr_l(n, 1024, TCA_HHF_NON_HH_WEIGHT, &non_hh_weight,
+ sizeof(non_hh_weight));
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+static int hhf_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct rtattr *tb[TCA_HHF_MAX + 1];
+ unsigned limit;
+ unsigned quantum;
+ unsigned hh_limit;
+ unsigned reset_timeout;
+ unsigned admit_bytes;
+ unsigned evict_timeout;
+ unsigned non_hh_weight;
+ SPRINT_BUF(b1);
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_HHF_MAX, opt);
+
+ if (tb[TCA_HHF_BACKLOG_LIMIT] &&
+ RTA_PAYLOAD(tb[TCA_HHF_BACKLOG_LIMIT]) >= sizeof(__u32)) {
+ limit = rta_getattr_u32(tb[TCA_HHF_BACKLOG_LIMIT]);
+ fprintf(f, "limit %up ", limit);
+ }
+ if (tb[TCA_HHF_QUANTUM] &&
+ RTA_PAYLOAD(tb[TCA_HHF_QUANTUM]) >= sizeof(__u32)) {
+ quantum = rta_getattr_u32(tb[TCA_HHF_QUANTUM]);
+ fprintf(f, "quantum %u ", quantum);
+ }
+ if (tb[TCA_HHF_HH_FLOWS_LIMIT] &&
+ RTA_PAYLOAD(tb[TCA_HHF_HH_FLOWS_LIMIT]) >= sizeof(__u32)) {
+ hh_limit = rta_getattr_u32(tb[TCA_HHF_HH_FLOWS_LIMIT]);
+ fprintf(f, "hh_limit %u ", hh_limit);
+ }
+ if (tb[TCA_HHF_RESET_TIMEOUT] &&
+ RTA_PAYLOAD(tb[TCA_HHF_RESET_TIMEOUT]) >= sizeof(__u32)) {
+ reset_timeout = rta_getattr_u32(tb[TCA_HHF_RESET_TIMEOUT]);
+ fprintf(f, "reset_timeout %s ", sprint_time(reset_timeout, b1));
+ }
+ if (tb[TCA_HHF_ADMIT_BYTES] &&
+ RTA_PAYLOAD(tb[TCA_HHF_ADMIT_BYTES]) >= sizeof(__u32)) {
+ admit_bytes = rta_getattr_u32(tb[TCA_HHF_ADMIT_BYTES]);
+ fprintf(f, "admit_bytes %u ", admit_bytes);
+ }
+ if (tb[TCA_HHF_EVICT_TIMEOUT] &&
+ RTA_PAYLOAD(tb[TCA_HHF_EVICT_TIMEOUT]) >= sizeof(__u32)) {
+ evict_timeout = rta_getattr_u32(tb[TCA_HHF_EVICT_TIMEOUT]);
+ fprintf(f, "evict_timeout %s ", sprint_time(evict_timeout, b1));
+ }
+ if (tb[TCA_HHF_NON_HH_WEIGHT] &&
+ RTA_PAYLOAD(tb[TCA_HHF_NON_HH_WEIGHT]) >= sizeof(__u32)) {
+ non_hh_weight = rta_getattr_u32(tb[TCA_HHF_NON_HH_WEIGHT]);
+ fprintf(f, "non_hh_weight %u ", non_hh_weight);
+ }
+ return 0;
+}
+
+static int hhf_print_xstats(struct qdisc_util *qu, FILE *f,
+ struct rtattr *xstats)
+{
+ struct tc_hhf_xstats *st;
+
+ if (xstats == NULL)
+ return 0;
+
+ if (RTA_PAYLOAD(xstats) < sizeof(*st))
+ return -1;
+
+ st = RTA_DATA(xstats);
+
+ fprintf(f, " drop_overlimit %u hh_overlimit %u tot_hh %u cur_hh %u",
+ st->drop_overlimit, st->hh_overlimit,
+ st->hh_tot_count, st->hh_cur_count);
+ return 0;
+}
+
+struct qdisc_util hhf_qdisc_util = {
+ .id = "hhf",
+ .parse_qopt = hhf_parse_opt,
+ .print_qopt = hhf_print_opt,
+ .print_xstats = hhf_print_xstats,
+};
diff --git a/iproute2/tc/q_htb.c b/iproute2/tc/q_htb.c
new file mode 100644
index 0000000..7075a4c
--- /dev/null
+++ b/iproute2/tc/q_htb.c
@@ -0,0 +1,376 @@
+/*
+ * q_htb.c HTB.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Martin Devera, devik@cdi.cz
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+#define HTB_TC_VER 0x30003
+#if HTB_TC_VER >> 16 != TC_HTB_PROTOVER
+#error "Different kernel and TC HTB versions"
+#endif
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... qdisc add ... htb [default N] [r2q N]\n"
+ " [direct_qlen P]\n"
+ " default minor id of class to which unclassified packets are sent {0}\n"
+ " r2q DRR quantums are computed as rate in Bps/r2q {10}\n"
+ " debug string of 16 numbers each 0-3 {0}\n\n"
+ " direct_qlen Limit of the direct queue {in packets}\n"
+ "... class add ... htb rate R1 [burst B1] [mpu B] [overhead O]\n"
+ " [prio P] [slot S] [pslot PS]\n"
+ " [ceil R2] [cburst B2] [mtu MTU] [quantum Q]\n"
+ " rate rate allocated to this class (class can still borrow)\n"
+ " burst max bytes burst which can be accumulated during idle period {computed}\n"
+ " mpu minimum packet size used in rate computations\n"
+ " overhead per-packet size overhead used in rate computations\n"
+ " linklay adapting to a linklayer e.g. atm\n"
+ " ceil definite upper class rate (no borrows) {rate}\n"
+ " cburst burst but for ceil {computed}\n"
+ " mtu max packet size we create rate map for {1600}\n"
+ " prio priority of leaf; lower are served first {0}\n"
+ " quantum how much bytes to serve from leaf at once {use r2q}\n"
+ "\nTC HTB version %d.%d\n",HTB_TC_VER>>16,HTB_TC_VER&0xffff
+ );
+}
+
+static void explain1(char *arg)
+{
+ fprintf(stderr, "Illegal \"%s\"\n", arg);
+ explain();
+}
+
+
+static int htb_parse_opt(struct qdisc_util *qu, int argc, char **argv, struct nlmsghdr *n)
+{
+ unsigned int direct_qlen = ~0U;
+ struct tc_htb_glob opt;
+ struct rtattr *tail;
+ unsigned i; char *p;
+ memset(&opt,0,sizeof(opt));
+ opt.rate2quantum = 10;
+ opt.version = 3;
+
+ while (argc > 0) {
+ if (matches(*argv, "r2q") == 0) {
+ NEXT_ARG();
+ if (get_u32(&opt.rate2quantum, *argv, 10)) {
+ explain1("r2q"); return -1;
+ }
+ } else if (matches(*argv, "default") == 0) {
+ NEXT_ARG();
+ if (get_u32(&opt.defcls, *argv, 16)) {
+ explain1("default"); return -1;
+ }
+ } else if (matches(*argv, "debug") == 0) {
+ NEXT_ARG(); p = *argv;
+ for (i=0; i<16; i++,p++) {
+ if (*p<'0' || *p>'3') break;
+ opt.debug |= (*p-'0')<<(2*i);
+ }
+ } else if (matches(*argv, "direct_qlen") == 0) {
+ NEXT_ARG();
+ if (get_u32(&direct_qlen, *argv, 10)) {
+ explain1("direct_qlen"); return -1;
+ }
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+ addattr_l(n, 2024, TCA_HTB_INIT, &opt, NLMSG_ALIGN(sizeof(opt)));
+ if (direct_qlen != ~0U)
+ addattr_l(n, 2024, TCA_HTB_DIRECT_QLEN,
+ &direct_qlen, sizeof(direct_qlen));
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+static int htb_parse_class_opt(struct qdisc_util *qu, int argc, char **argv, struct nlmsghdr *n)
+{
+ int ok=0;
+ struct tc_htb_opt opt;
+ __u32 rtab[256],ctab[256];
+ unsigned buffer=0,cbuffer=0;
+ int cell_log=-1,ccell_log = -1;
+ unsigned mtu;
+ unsigned short mpu = 0;
+ unsigned short overhead = 0;
+ unsigned int linklayer = LINKLAYER_ETHERNET; /* Assume ethernet */
+ struct rtattr *tail;
+ __u64 ceil64 = 0, rate64 = 0;
+
+ memset(&opt, 0, sizeof(opt)); mtu = 1600; /* eth packet len */
+
+ while (argc > 0) {
+ if (matches(*argv, "prio") == 0) {
+ NEXT_ARG();
+ if (get_u32(&opt.prio, *argv, 10)) {
+ explain1("prio"); return -1;
+ }
+ ok++;
+ } else if (matches(*argv, "mtu") == 0) {
+ NEXT_ARG();
+ if (get_u32(&mtu, *argv, 10)) {
+ explain1("mtu"); return -1;
+ }
+ } else if (matches(*argv, "mpu") == 0) {
+ NEXT_ARG();
+ if (get_u16(&mpu, *argv, 10)) {
+ explain1("mpu"); return -1;
+ }
+ } else if (matches(*argv, "overhead") == 0) {
+ NEXT_ARG();
+ if (get_u16(&overhead, *argv, 10)) {
+ explain1("overhead"); return -1;
+ }
+ } else if (matches(*argv, "linklayer") == 0) {
+ NEXT_ARG();
+ if (get_linklayer(&linklayer, *argv)) {
+ explain1("linklayer"); return -1;
+ }
+ } else if (matches(*argv, "quantum") == 0) {
+ NEXT_ARG();
+ if (get_u32(&opt.quantum, *argv, 10)) {
+ explain1("quantum"); return -1;
+ }
+ } else if (matches(*argv, "burst") == 0 ||
+ strcmp(*argv, "buffer") == 0 ||
+ strcmp(*argv, "maxburst") == 0) {
+ NEXT_ARG();
+ if (get_size_and_cell(&buffer, &cell_log, *argv) < 0) {
+ explain1("buffer");
+ return -1;
+ }
+ ok++;
+ } else if (matches(*argv, "cburst") == 0 ||
+ strcmp(*argv, "cbuffer") == 0 ||
+ strcmp(*argv, "cmaxburst") == 0) {
+ NEXT_ARG();
+ if (get_size_and_cell(&cbuffer, &ccell_log, *argv) < 0) {
+ explain1("cbuffer");
+ return -1;
+ }
+ ok++;
+ } else if (strcmp(*argv, "ceil") == 0) {
+ NEXT_ARG();
+ if (ceil64) {
+ fprintf(stderr, "Double \"ceil\" spec\n");
+ return -1;
+ }
+ if (get_rate64(&ceil64, *argv)) {
+ explain1("ceil");
+ return -1;
+ }
+ ok++;
+ } else if (strcmp(*argv, "rate") == 0) {
+ NEXT_ARG();
+ if (rate64) {
+ fprintf(stderr, "Double \"rate\" spec\n");
+ return -1;
+ }
+ if (get_rate64(&rate64, *argv)) {
+ explain1("rate");
+ return -1;
+ }
+ ok++;
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ /* if (!ok)
+ return 0;*/
+
+ if (!rate64) {
+ fprintf(stderr, "\"rate\" is required.\n");
+ return -1;
+ }
+ /* if ceil params are missing, use the same as rate */
+ if (!ceil64)
+ ceil64 = rate64;
+
+ opt.rate.rate = (rate64 >= (1ULL << 32)) ? ~0U : rate64;
+ opt.ceil.rate = (ceil64 >= (1ULL << 32)) ? ~0U : ceil64;
+
+ /* compute minimal allowed burst from rate; mtu is added here to make
+ sute that buffer is larger than mtu and to have some safeguard space */
+ if (!buffer)
+ buffer = rate64 / get_hz() + mtu;
+ if (!cbuffer)
+ cbuffer = ceil64 / get_hz() + mtu;
+
+ opt.ceil.overhead = overhead;
+ opt.rate.overhead = overhead;
+
+ opt.ceil.mpu = mpu;
+ opt.rate.mpu = mpu;
+
+ if (tc_calc_rtable(&opt.rate, rtab, cell_log, mtu, linklayer) < 0) {
+ fprintf(stderr, "htb: failed to calculate rate table.\n");
+ return -1;
+ }
+ opt.buffer = tc_calc_xmittime(rate64, buffer);
+
+ if (tc_calc_rtable(&opt.ceil, ctab, ccell_log, mtu, linklayer) < 0) {
+ fprintf(stderr, "htb: failed to calculate ceil rate table.\n");
+ return -1;
+ }
+ opt.cbuffer = tc_calc_xmittime(ceil64, cbuffer);
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+
+ if (rate64 >= (1ULL << 32))
+ addattr_l(n, 1124, TCA_HTB_RATE64, &rate64, sizeof(rate64));
+
+ if (ceil64 >= (1ULL << 32))
+ addattr_l(n, 1224, TCA_HTB_CEIL64, &ceil64, sizeof(ceil64));
+
+ addattr_l(n, 2024, TCA_HTB_PARMS, &opt, sizeof(opt));
+ addattr_l(n, 3024, TCA_HTB_RTAB, rtab, 1024);
+ addattr_l(n, 4024, TCA_HTB_CTAB, ctab, 1024);
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+static int htb_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct rtattr *tb[TCA_HTB_MAX + 1];
+ struct tc_htb_opt *hopt;
+ struct tc_htb_glob *gopt;
+ double buffer,cbuffer;
+ unsigned int linklayer;
+ __u64 rate64, ceil64;
+ SPRINT_BUF(b1);
+ SPRINT_BUF(b2);
+ SPRINT_BUF(b3);
+ SPRINT_BUF(b4);
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_HTB_MAX, opt);
+
+ if (tb[TCA_HTB_PARMS]) {
+ hopt = RTA_DATA(tb[TCA_HTB_PARMS]);
+ if (RTA_PAYLOAD(tb[TCA_HTB_PARMS]) < sizeof(*hopt)) return -1;
+
+ if (!hopt->level) {
+ fprintf(f, "prio %d ", (int)hopt->prio);
+ if (show_details)
+ fprintf(f, "quantum %d ", (int)hopt->quantum);
+ }
+
+ rate64 = hopt->rate.rate;
+ if (tb[TCA_HTB_RATE64] &&
+ RTA_PAYLOAD(tb[TCA_HTB_RATE64]) >= sizeof(rate64)) {
+ rate64 = rta_getattr_u64(tb[TCA_HTB_RATE64]);
+ }
+
+ ceil64 = hopt->ceil.rate;
+ if (tb[TCA_HTB_CEIL64] &&
+ RTA_PAYLOAD(tb[TCA_HTB_CEIL64]) >= sizeof(ceil64))
+ ceil64 = rta_getattr_u64(tb[TCA_HTB_CEIL64]);
+
+ fprintf(f, "rate %s ", sprint_rate(rate64, b1));
+ if (hopt->rate.overhead)
+ fprintf(f, "overhead %u ", hopt->rate.overhead);
+ buffer = tc_calc_xmitsize(rate64, hopt->buffer);
+
+ fprintf(f, "ceil %s ", sprint_rate(ceil64, b1));
+ cbuffer = tc_calc_xmitsize(ceil64, hopt->cbuffer);
+ linklayer = (hopt->rate.linklayer & TC_LINKLAYER_MASK);
+ if (linklayer > TC_LINKLAYER_ETHERNET || show_details)
+ fprintf(f, "linklayer %s ", sprint_linklayer(linklayer, b4));
+ if (show_details) {
+ fprintf(f, "burst %s/%u mpu %s overhead %s ",
+ sprint_size(buffer, b1),
+ 1<<hopt->rate.cell_log,
+ sprint_size(hopt->rate.mpu&0xFF, b2),
+ sprint_size((hopt->rate.mpu>>8)&0xFF, b3));
+ fprintf(f, "cburst %s/%u mpu %s overhead %s ",
+ sprint_size(cbuffer, b1),
+ 1<<hopt->ceil.cell_log,
+ sprint_size(hopt->ceil.mpu&0xFF, b2),
+ sprint_size((hopt->ceil.mpu>>8)&0xFF, b3));
+ fprintf(f, "level %d ", (int)hopt->level);
+ } else {
+ fprintf(f, "burst %s ", sprint_size(buffer, b1));
+ fprintf(f, "cburst %s ", sprint_size(cbuffer, b1));
+ }
+ if (show_raw)
+ fprintf(f, "buffer [%08x] cbuffer [%08x] ",
+ hopt->buffer,hopt->cbuffer);
+ }
+ if (tb[TCA_HTB_INIT]) {
+ gopt = RTA_DATA(tb[TCA_HTB_INIT]);
+ if (RTA_PAYLOAD(tb[TCA_HTB_INIT]) < sizeof(*gopt)) return -1;
+
+ fprintf(f, "r2q %d default %x direct_packets_stat %u",
+ gopt->rate2quantum,gopt->defcls,gopt->direct_pkts);
+ if (show_details)
+ fprintf(f," ver %d.%d",gopt->version >> 16,gopt->version & 0xffff);
+ }
+ if (tb[TCA_HTB_DIRECT_QLEN] &&
+ RTA_PAYLOAD(tb[TCA_HTB_DIRECT_QLEN]) >= sizeof(__u32)) {
+ __u32 direct_qlen = rta_getattr_u32(tb[TCA_HTB_DIRECT_QLEN]);
+
+ fprintf(f, " direct_qlen %u", direct_qlen);
+ }
+ return 0;
+}
+
+static int htb_print_xstats(struct qdisc_util *qu, FILE *f, struct rtattr *xstats)
+{
+ struct tc_htb_xstats *st;
+ if (xstats == NULL)
+ return 0;
+
+ if (RTA_PAYLOAD(xstats) < sizeof(*st))
+ return -1;
+
+ st = RTA_DATA(xstats);
+ fprintf(f, " lended: %u borrowed: %u giants: %u\n",
+ st->lends,st->borrows,st->giants);
+ fprintf(f, " tokens: %d ctokens: %d\n", st->tokens,st->ctokens);
+ return 0;
+}
+
+struct qdisc_util htb_qdisc_util = {
+ .id = "htb",
+ .parse_qopt = htb_parse_opt,
+ .print_qopt = htb_print_opt,
+ .print_xstats = htb_print_xstats,
+ .parse_copt = htb_parse_class_opt,
+ .print_copt = htb_print_opt,
+};
diff --git a/iproute2/tc/q_ingress.c b/iproute2/tc/q_ingress.c
new file mode 100644
index 0000000..c3c9b40
--- /dev/null
+++ b/iproute2/tc/q_ingress.c
@@ -0,0 +1,52 @@
+/*
+ * q_ingress.c INGRESS.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: J Hadi Salim
+ */
+
+#include <stdio.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... ingress\n");
+}
+
+static int ingress_parse_opt(struct qdisc_util *qu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ while (argc > 0) {
+ if (strcmp(*argv, "handle") == 0) {
+ NEXT_ARG();
+ argc--; argv++;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ }
+
+ addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+ return 0;
+}
+
+static int ingress_print_opt(struct qdisc_util *qu, FILE *f,
+ struct rtattr *opt)
+{
+ fprintf(f, "---------------- ");
+ return 0;
+}
+
+struct qdisc_util ingress_qdisc_util = {
+ .id = "ingress",
+ .parse_qopt = ingress_parse_opt,
+ .print_qopt = ingress_print_opt,
+};
diff --git a/iproute2/tc/q_mqprio.c b/iproute2/tc/q_mqprio.c
new file mode 100644
index 0000000..fa1022b
--- /dev/null
+++ b/iproute2/tc/q_mqprio.c
@@ -0,0 +1,131 @@
+/*
+ * q_mqprio.c MQ prio qdisc
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Author: John Fastabend, <john.r.fastabend@intel.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... mqprio [num_tc NUMBER] [map P0 P1 ...]\n");
+ fprintf(stderr, " [queues count1@offset1 count2@offset2 ...] ");
+ fprintf(stderr, "[hw 1|0]\n");
+}
+
+static int mqprio_parse_opt(struct qdisc_util *qu, int argc,
+ char **argv, struct nlmsghdr *n)
+{
+ int idx;
+ struct tc_mqprio_qopt opt = {
+ 8,
+ {0, 1, 2, 3, 4, 5, 6, 7, 0, 1, 1, 1, 3, 3, 3, 3},
+ 1,
+ };
+
+ while (argc > 0) {
+ idx = 0;
+ if (strcmp(*argv, "num_tc") == 0) {
+ NEXT_ARG();
+ if (get_u8(&opt.num_tc, *argv, 10)) {
+ fprintf(stderr, "Illegal \"num_tc\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "map") == 0) {
+ while (idx < TC_QOPT_MAX_QUEUE && NEXT_ARG_OK()) {
+ NEXT_ARG();
+ if (get_u8(&opt.prio_tc_map[idx], *argv, 10)) {
+ PREV_ARG();
+ break;
+ }
+ idx++;
+ }
+ for ( ; idx < TC_QOPT_MAX_QUEUE; idx++)
+ opt.prio_tc_map[idx] = 0;
+ } else if (strcmp(*argv, "queues") == 0) {
+ char *tmp, *tok;
+
+ while (idx < TC_QOPT_MAX_QUEUE && NEXT_ARG_OK()) {
+ NEXT_ARG();
+
+ tmp = strdup(*argv);
+ if (!tmp)
+ break;
+
+ tok = strtok(tmp, "@");
+ if (get_u16(&opt.count[idx], tok, 10)) {
+ free(tmp);
+ PREV_ARG();
+ break;
+ }
+ tok = strtok(NULL, "@");
+ if (get_u16(&opt.offset[idx], tok, 10)) {
+ free(tmp);
+ PREV_ARG();
+ break;
+ }
+ free(tmp);
+ idx++;
+ }
+ } else if (strcmp(*argv, "hw") == 0) {
+ NEXT_ARG();
+ if (get_u8(&opt.hw, *argv, 10)) {
+ fprintf(stderr, "Illegal \"hw\"\n");
+ return -1;
+ }
+ idx++;
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "Unknown argument\n");
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ addattr_l(n, 1024, TCA_OPTIONS, &opt, sizeof(opt));
+ return 0;
+}
+
+static int mqprio_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ int i;
+ struct tc_mqprio_qopt *qopt;
+
+ if (opt == NULL)
+ return 0;
+
+ qopt = RTA_DATA(opt);
+
+ fprintf(f, " tc %u map ", qopt->num_tc);
+ for (i = 0; i <= TC_PRIO_MAX; i++)
+ fprintf(f, "%u ", qopt->prio_tc_map[i]);
+ fprintf(f, "\n queues:");
+ for (i = 0; i < qopt->num_tc; i++)
+ fprintf(f, "(%u:%u) ", qopt->offset[i],
+ qopt->offset[i] + qopt->count[i] - 1);
+ return 0;
+}
+
+struct qdisc_util mqprio_qdisc_util = {
+ .id = "mqprio",
+ .parse_qopt = mqprio_parse_opt,
+ .print_qopt = mqprio_print_opt,
+};
diff --git a/iproute2/tc/q_multiq.c b/iproute2/tc/q_multiq.c
new file mode 100644
index 0000000..f4f41f7
--- /dev/null
+++ b/iproute2/tc/q_multiq.c
@@ -0,0 +1,83 @@
+/*
+ * q_multiq.c Multiqueue aware qdisc
+ *
+ * Copyright (c) 2008, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses>.
+ *
+ * Author: Alexander Duyck <alexander.h.duyck@intel.com>
+ *
+ * Original Authors: PJ Waskiewicz, <peter.p.waskiewicz.jr@intel.com> (RR)
+ * Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> (from PRIO)
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... multiq [help]\n");
+}
+
+static int multiq_parse_opt(struct qdisc_util *qu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ struct tc_multiq_qopt opt;
+
+ if (argc) {
+ if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ }
+
+ addattr_l(n, 1024, TCA_OPTIONS, &opt, sizeof(opt));
+ return 0;
+}
+
+static int multiq_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct tc_multiq_qopt *qopt;
+
+ if (opt == NULL)
+ return 0;
+ if (RTA_PAYLOAD(opt) < sizeof(*qopt))
+ return 0;
+
+ qopt = RTA_DATA(opt);
+
+ fprintf(f, "bands %u/%u ", qopt->bands, qopt->max_bands);
+
+ return 0;
+}
+
+struct qdisc_util multiq_qdisc_util = {
+ .id = "multiq",
+ .parse_qopt = multiq_parse_opt,
+ .print_qopt = multiq_print_opt,
+};
diff --git a/iproute2/tc/q_netem.c b/iproute2/tc/q_netem.c
new file mode 100644
index 0000000..7bc8c6a
--- /dev/null
+++ b/iproute2/tc/q_netem.c
@@ -0,0 +1,690 @@
+/*
+ * q_netem.c NETEM.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Stephen Hemminger <shemminger@linux-foundation.org>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <math.h>
+#include <ctype.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <errno.h>
+
+#include "utils.h"
+#include "tc_util.h"
+#include "tc_common.h"
+
+static void explain(void)
+{
+ fprintf(stderr,
+"Usage: ... netem [ limit PACKETS ] \n" \
+" [ delay TIME [ JITTER [CORRELATION]]]\n" \
+" [ distribution {uniform|normal|pareto|paretonormal} ]\n" \
+" [ corrupt PERCENT [CORRELATION]] \n" \
+" [ duplicate PERCENT [CORRELATION]]\n" \
+" [ loss random PERCENT [CORRELATION]]\n" \
+" [ loss state P13 [P31 [P32 [P23 P14]]]\n" \
+" [ loss gemodel PERCENT [R [1-H [1-K]]]\n" \
+" [ ecn ]\n" \
+" [ reorder PRECENT [CORRELATION] [ gap DISTANCE ]]\n" \
+" [ rate RATE [PACKETOVERHEAD] [CELLSIZE] [CELLOVERHEAD]]\n");
+}
+
+static void explain1(const char *arg)
+{
+ fprintf(stderr, "Illegal \"%s\"\n", arg);
+}
+
+/* Upper bound on size of distribution
+ * really (TCA_BUF_MAX - other headers) / sizeof (__s16)
+ */
+#define MAX_DIST (16*1024)
+
+static const double max_percent_value = 0xffffffff;
+
+/* scaled value used to percent of maximum. */
+static void set_percent(__u32 *percent, double per)
+{
+ *percent = (unsigned) rint(per * max_percent_value);
+}
+
+
+/* Parse either a fraction '.3' or percent '30%
+ * return: 0 = ok, -1 = error, 1 = out of range
+ */
+static int parse_percent(double *val, const char *str)
+{
+ char *p;
+
+ *val = strtod(str, &p) / 100.;
+ if (*p && strcmp(p, "%") )
+ return -1;
+
+ return 0;
+}
+
+static int get_percent(__u32 *percent, const char *str)
+{
+ double per;
+
+ if (parse_percent(&per, str))
+ return -1;
+
+ set_percent(percent, per);
+ return 0;
+}
+
+static void print_percent(char *buf, int len, __u32 per)
+{
+ snprintf(buf, len, "%g%%", 100. * (double) per / max_percent_value);
+}
+
+static char * sprint_percent(__u32 per, char *buf)
+{
+ print_percent(buf, SPRINT_BSIZE-1, per);
+ return buf;
+}
+
+/*
+ * Simplistic file parser for distrbution data.
+ * Format is:
+ * # comment line(s)
+ * data0 data1 ...
+ */
+static int get_distribution(const char *type, __s16 *data, int maxdata)
+{
+ FILE *f;
+ int n;
+ long x;
+ size_t len;
+ char *line = NULL;
+ char name[128];
+
+ snprintf(name, sizeof(name), "%s/%s.dist", get_tc_lib(), type);
+ if ((f = fopen(name, "r")) == NULL) {
+ fprintf(stderr, "No distribution data for %s (%s: %s)\n",
+ type, name, strerror(errno));
+ return -1;
+ }
+
+ n = 0;
+ while (getline(&line, &len, f) != -1) {
+ char *p, *endp;
+ if (*line == '\n' || *line == '#')
+ continue;
+
+ for (p = line; ; p = endp) {
+ x = strtol(p, &endp, 0);
+ if (endp == p)
+ break;
+
+ if (n >= maxdata) {
+ fprintf(stderr, "%s: too much data\n",
+ name);
+ n = -1;
+ goto error;
+ }
+ data[n++] = x;
+ }
+ }
+ error:
+ free(line);
+ fclose(f);
+ return n;
+}
+
+#define NEXT_IS_NUMBER() (NEXT_ARG_OK() && isdigit(argv[1][0]))
+#define NEXT_IS_SIGNED_NUMBER() \
+ (NEXT_ARG_OK() && (isdigit(argv[1][0]) || argv[1][0] == '-'))
+
+/* Adjust for the fact that psched_ticks aren't always usecs
+ (based on kernel PSCHED_CLOCK configuration */
+static int get_ticks(__u32 *ticks, const char *str)
+{
+ unsigned t;
+
+ if(get_time(&t, str))
+ return -1;
+
+ if (tc_core_time2big(t)) {
+ fprintf(stderr, "Illegal %u time (too large)\n", t);
+ return -1;
+ }
+
+ *ticks = tc_core_time2tick(t);
+ return 0;
+}
+
+static int netem_parse_opt(struct qdisc_util *qu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ int dist_size = 0;
+ struct rtattr *tail;
+ struct tc_netem_qopt opt = { .limit = 1000 };
+ struct tc_netem_corr cor;
+ struct tc_netem_reorder reorder;
+ struct tc_netem_corrupt corrupt;
+ struct tc_netem_gimodel gimodel;
+ struct tc_netem_gemodel gemodel;
+ struct tc_netem_rate rate;
+ __s16 *dist_data = NULL;
+ __u16 loss_type = NETEM_LOSS_UNSPEC;
+ int present[__TCA_NETEM_MAX];
+ __u64 rate64 = 0;
+
+ memset(&cor, 0, sizeof(cor));
+ memset(&reorder, 0, sizeof(reorder));
+ memset(&corrupt, 0, sizeof(corrupt));
+ memset(&rate, 0, sizeof(rate));
+ memset(present, 0, sizeof(present));
+
+ for( ; argc > 0; --argc, ++argv) {
+ if (matches(*argv, "limit") == 0) {
+ NEXT_ARG();
+ if (get_size(&opt.limit, *argv)) {
+ explain1("limit");
+ return -1;
+ }
+ } else if (matches(*argv, "latency") == 0 ||
+ matches(*argv, "delay") == 0) {
+ NEXT_ARG();
+ if (get_ticks(&opt.latency, *argv)) {
+ explain1("latency");
+ return -1;
+ }
+
+ if (NEXT_IS_NUMBER()) {
+ NEXT_ARG();
+ if (get_ticks(&opt.jitter, *argv)) {
+ explain1("latency");
+ return -1;
+ }
+
+ if (NEXT_IS_NUMBER()) {
+ NEXT_ARG();
+ ++present[TCA_NETEM_CORR];
+ if (get_percent(&cor.delay_corr, *argv)) {
+ explain1("latency");
+ return -1;
+ }
+ }
+ }
+ } else if (matches(*argv, "loss") == 0 ||
+ matches(*argv, "drop") == 0) {
+ if (opt.loss > 0 || loss_type != NETEM_LOSS_UNSPEC) {
+ explain1("duplicate loss argument\n");
+ return -1;
+ }
+
+ NEXT_ARG();
+ /* Old (deprecated) random loss model syntax */
+ if (isdigit(argv[0][0]))
+ goto random_loss_model;
+
+ if (!strcmp(*argv, "random")) {
+ NEXT_ARG();
+ random_loss_model:
+ if (get_percent(&opt.loss, *argv)) {
+ explain1("loss percent");
+ return -1;
+ }
+ if (NEXT_IS_NUMBER()) {
+ NEXT_ARG();
+ ++present[TCA_NETEM_CORR];
+ if (get_percent(&cor.loss_corr, *argv)) {
+ explain1("loss correllation");
+ return -1;
+ }
+ }
+ } else if (!strcmp(*argv, "state")) {
+ double p13;
+
+ NEXT_ARG();
+ if (parse_percent(&p13, *argv)) {
+ explain1("loss p13");
+ return -1;
+ }
+
+ /* set defaults */
+ set_percent(&gimodel.p13, p13);
+ set_percent(&gimodel.p31, 1. - p13);
+ set_percent(&gimodel.p32, 0);
+ set_percent(&gimodel.p23, 1.);
+ set_percent(&gimodel.p14, 0);
+ loss_type = NETEM_LOSS_GI;
+
+ if (!NEXT_IS_NUMBER())
+ continue;
+ NEXT_ARG();
+ if (get_percent(&gimodel.p31, *argv)) {
+ explain1("loss p31");
+ return -1;
+ }
+
+ if (!NEXT_IS_NUMBER())
+ continue;
+ NEXT_ARG();
+ if (get_percent(&gimodel.p32, *argv)) {
+ explain1("loss p32");
+ return -1;
+ }
+
+ if (!NEXT_IS_NUMBER())
+ continue;
+ NEXT_ARG();
+ if (get_percent(&gimodel.p23, *argv)) {
+ explain1("loss p23");
+ return -1;
+ }
+ if (!NEXT_IS_NUMBER())
+ continue;
+ NEXT_ARG();
+ if (get_percent(&gimodel.p14, *argv)) {
+ explain1("loss p14");
+ return -1;
+ }
+
+ } else if (!strcmp(*argv, "gemodel")) {
+ NEXT_ARG();
+ if (get_percent(&gemodel.p, *argv)) {
+ explain1("loss gemodel p");
+ return -1;
+ }
+
+ /* set defaults */
+ set_percent(&gemodel.r, 1.);
+ set_percent(&gemodel.h, 0);
+ set_percent(&gemodel.k1, 0);
+ loss_type = NETEM_LOSS_GE;
+
+ if (!NEXT_IS_NUMBER())
+ continue;
+ NEXT_ARG();
+ if (get_percent(&gemodel.r, *argv)) {
+ explain1("loss gemodel r");
+ return -1;
+ }
+
+ if (!NEXT_IS_NUMBER())
+ continue;
+ NEXT_ARG();
+ if (get_percent(&gemodel.h, *argv)) {
+ explain1("loss gemodel h");
+ return -1;
+ }
+ /* netem option is "1-h" but kernel
+ * expects "h".
+ */
+ gemodel.h = max_percent_value - gemodel.h;
+
+ if (!NEXT_IS_NUMBER())
+ continue;
+ NEXT_ARG();
+ if (get_percent(&gemodel.k1, *argv)) {
+ explain1("loss gemodel k");
+ return -1;
+ }
+ } else {
+ fprintf(stderr, "Unknown loss parameter: %s\n",
+ *argv);
+ return -1;
+ }
+ } else if (matches(*argv, "ecn") == 0) {
+ present[TCA_NETEM_ECN] = 1;
+ } else if (matches(*argv, "reorder") == 0) {
+ NEXT_ARG();
+ present[TCA_NETEM_REORDER] = 1;
+ if (get_percent(&reorder.probability, *argv)) {
+ explain1("reorder");
+ return -1;
+ }
+ if (NEXT_IS_NUMBER()) {
+ NEXT_ARG();
+ ++present[TCA_NETEM_CORR];
+ if (get_percent(&reorder.correlation, *argv)) {
+ explain1("reorder");
+ return -1;
+ }
+ }
+ } else if (matches(*argv, "corrupt") == 0) {
+ NEXT_ARG();
+ present[TCA_NETEM_CORRUPT] = 1;
+ if (get_percent(&corrupt.probability, *argv)) {
+ explain1("corrupt");
+ return -1;
+ }
+ if (NEXT_IS_NUMBER()) {
+ NEXT_ARG();
+ ++present[TCA_NETEM_CORR];
+ if (get_percent(&corrupt.correlation, *argv)) {
+ explain1("corrupt");
+ return -1;
+ }
+ }
+ } else if (matches(*argv, "gap") == 0) {
+ NEXT_ARG();
+ if (get_u32(&opt.gap, *argv, 0)) {
+ explain1("gap");
+ return -1;
+ }
+ } else if (matches(*argv, "duplicate") == 0) {
+ NEXT_ARG();
+ if (get_percent(&opt.duplicate, *argv)) {
+ explain1("duplicate");
+ return -1;
+ }
+ if (NEXT_IS_NUMBER()) {
+ NEXT_ARG();
+ if (get_percent(&cor.dup_corr, *argv)) {
+ explain1("duplicate");
+ return -1;
+ }
+ }
+ } else if (matches(*argv, "distribution") == 0) {
+ NEXT_ARG();
+ dist_data = calloc(sizeof(dist_data[0]), MAX_DIST);
+ dist_size = get_distribution(*argv, dist_data, MAX_DIST);
+ if (dist_size <= 0) {
+ free(dist_data);
+ return -1;
+ }
+ } else if (matches(*argv, "rate") == 0) {
+ ++present[TCA_NETEM_RATE];
+ NEXT_ARG();
+ if (get_rate64(&rate64, *argv)) {
+ explain1("rate");
+ return -1;
+ }
+ if (NEXT_IS_SIGNED_NUMBER()) {
+ NEXT_ARG();
+ if (get_s32(&rate.packet_overhead, *argv, 0)) {
+ explain1("rate");
+ return -1;
+ }
+ }
+ if (NEXT_IS_NUMBER()) {
+ NEXT_ARG();
+ if (get_u32(&rate.cell_size, *argv, 0)) {
+ explain1("rate");
+ return -1;
+ }
+ }
+ if (NEXT_IS_SIGNED_NUMBER()) {
+ NEXT_ARG();
+ if (get_s32(&rate.cell_overhead, *argv, 0)) {
+ explain1("rate");
+ return -1;
+ }
+ }
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ }
+
+ tail = NLMSG_TAIL(n);
+
+ if (reorder.probability) {
+ if (opt.latency == 0) {
+ fprintf(stderr, "reordering not possible without specifying some delay\n");
+ explain();
+ return -1;
+ }
+ if (opt.gap == 0)
+ opt.gap = 1;
+ } else if (opt.gap > 0) {
+ fprintf(stderr, "gap specified without reorder probability\n");
+ explain();
+ return -1;
+ }
+
+ if (present[TCA_NETEM_ECN]) {
+ if (opt.loss <= 0 && loss_type == NETEM_LOSS_UNSPEC) {
+ fprintf(stderr, "ecn requested without loss model\n");
+ explain();
+ return -1;
+ }
+ }
+
+ if (dist_data && (opt.latency == 0 || opt.jitter == 0)) {
+ fprintf(stderr, "distribution specified but no latency and jitter values\n");
+ explain();
+ return -1;
+ }
+
+ if (addattr_l(n, 1024, TCA_OPTIONS, &opt, sizeof(opt)) < 0)
+ return -1;
+
+ if (present[TCA_NETEM_CORR] &&
+ addattr_l(n, 1024, TCA_NETEM_CORR, &cor, sizeof(cor)) < 0)
+ return -1;
+
+ if (present[TCA_NETEM_REORDER] &&
+ addattr_l(n, 1024, TCA_NETEM_REORDER, &reorder, sizeof(reorder)) < 0)
+ return -1;
+
+ if (present[TCA_NETEM_ECN] &&
+ addattr_l(n, 1024, TCA_NETEM_ECN, &present[TCA_NETEM_ECN],
+ sizeof(present[TCA_NETEM_ECN])) < 0)
+ return -1;
+
+ if (present[TCA_NETEM_CORRUPT] &&
+ addattr_l(n, 1024, TCA_NETEM_CORRUPT, &corrupt, sizeof(corrupt)) < 0)
+ return -1;
+
+ if (loss_type != NETEM_LOSS_UNSPEC) {
+ struct rtattr *start;
+
+ start = addattr_nest(n, 1024, TCA_NETEM_LOSS | NLA_F_NESTED);
+ if (loss_type == NETEM_LOSS_GI) {
+ if (addattr_l(n, 1024, NETEM_LOSS_GI,
+ &gimodel, sizeof(gimodel)) < 0)
+ return -1;
+ } else if (loss_type == NETEM_LOSS_GE) {
+ if (addattr_l(n, 1024, NETEM_LOSS_GE,
+ &gemodel, sizeof(gemodel)) < 0)
+ return -1;
+ } else {
+ fprintf(stderr, "loss in the weeds!\n");
+ return -1;
+ }
+
+ addattr_nest_end(n, start);
+ }
+
+ if (present[TCA_NETEM_RATE]) {
+ if (rate64 >= (1ULL << 32)) {
+ if (addattr_l(n, 1024,
+ TCA_NETEM_RATE64, &rate64, sizeof(rate64)) < 0)
+ return -1;
+ rate.rate = ~0U;
+ } else {
+ rate.rate = rate64;
+ }
+ if (addattr_l(n, 1024, TCA_NETEM_RATE, &rate, sizeof(rate)) < 0)
+ return -1;
+ }
+
+ if (dist_data) {
+ if (addattr_l(n, MAX_DIST * sizeof(dist_data[0]),
+ TCA_NETEM_DELAY_DIST,
+ dist_data, dist_size * sizeof(dist_data[0])) < 0)
+ return -1;
+ free(dist_data);
+ }
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+static int netem_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ const struct tc_netem_corr *cor = NULL;
+ const struct tc_netem_reorder *reorder = NULL;
+ const struct tc_netem_corrupt *corrupt = NULL;
+ const struct tc_netem_gimodel *gimodel = NULL;
+ const struct tc_netem_gemodel *gemodel = NULL;
+ int *ecn = NULL;
+ struct tc_netem_qopt qopt;
+ const struct tc_netem_rate *rate = NULL;
+ int len = RTA_PAYLOAD(opt) - sizeof(qopt);
+ __u64 rate64 = 0;
+ SPRINT_BUF(b1);
+
+ if (opt == NULL)
+ return 0;
+
+ if (len < 0) {
+ fprintf(stderr, "options size error\n");
+ return -1;
+ }
+ memcpy(&qopt, RTA_DATA(opt), sizeof(qopt));
+
+ if (len > 0) {
+ struct rtattr *tb[TCA_NETEM_MAX+1];
+ parse_rtattr(tb, TCA_NETEM_MAX, RTA_DATA(opt) + sizeof(qopt),
+ len);
+
+ if (tb[TCA_NETEM_CORR]) {
+ if (RTA_PAYLOAD(tb[TCA_NETEM_CORR]) < sizeof(*cor))
+ return -1;
+ cor = RTA_DATA(tb[TCA_NETEM_CORR]);
+ }
+ if (tb[TCA_NETEM_REORDER]) {
+ if (RTA_PAYLOAD(tb[TCA_NETEM_REORDER]) < sizeof(*reorder))
+ return -1;
+ reorder = RTA_DATA(tb[TCA_NETEM_REORDER]);
+ }
+ if (tb[TCA_NETEM_CORRUPT]) {
+ if (RTA_PAYLOAD(tb[TCA_NETEM_CORRUPT]) < sizeof(*corrupt))
+ return -1;
+ corrupt = RTA_DATA(tb[TCA_NETEM_CORRUPT]);
+ }
+ if (tb[TCA_NETEM_LOSS]) {
+ struct rtattr *lb[NETEM_LOSS_MAX + 1];
+
+ parse_rtattr_nested(lb, NETEM_LOSS_MAX, tb[TCA_NETEM_LOSS]);
+ if (lb[NETEM_LOSS_GI])
+ gimodel = RTA_DATA(lb[NETEM_LOSS_GI]);
+ if (lb[NETEM_LOSS_GE])
+ gemodel = RTA_DATA(lb[NETEM_LOSS_GE]);
+ }
+ if (tb[TCA_NETEM_RATE]) {
+ if (RTA_PAYLOAD(tb[TCA_NETEM_RATE]) < sizeof(*rate))
+ return -1;
+ rate = RTA_DATA(tb[TCA_NETEM_RATE]);
+ }
+ if (tb[TCA_NETEM_ECN]) {
+ if (RTA_PAYLOAD(tb[TCA_NETEM_ECN]) < sizeof(*ecn))
+ return -1;
+ ecn = RTA_DATA(tb[TCA_NETEM_ECN]);
+ }
+ if (tb[TCA_NETEM_RATE64]) {
+ if (RTA_PAYLOAD(tb[TCA_NETEM_RATE64]) < sizeof(rate64))
+ return -1;
+ rate64 = rta_getattr_u64(tb[TCA_NETEM_RATE64]);
+ }
+ }
+
+ fprintf(f, "limit %d", qopt.limit);
+
+ if (qopt.latency) {
+ fprintf(f, " delay %s", sprint_ticks(qopt.latency, b1));
+
+ if (qopt.jitter) {
+ fprintf(f, " %s", sprint_ticks(qopt.jitter, b1));
+ if (cor && cor->delay_corr)
+ fprintf(f, " %s", sprint_percent(cor->delay_corr, b1));
+ }
+ }
+
+ if (qopt.loss) {
+ fprintf(f, " loss %s", sprint_percent(qopt.loss, b1));
+ if (cor && cor->loss_corr)
+ fprintf(f, " %s", sprint_percent(cor->loss_corr, b1));
+ }
+
+ if (gimodel) {
+ fprintf(f, " loss state p13 %s", sprint_percent(gimodel->p13, b1));
+ fprintf(f, " p31 %s", sprint_percent(gimodel->p31, b1));
+ fprintf(f, " p32 %s", sprint_percent(gimodel->p32, b1));
+ fprintf(f, " p23 %s", sprint_percent(gimodel->p23, b1));
+ fprintf(f, " p14 %s", sprint_percent(gimodel->p14, b1));
+ }
+
+ if (gemodel) {
+ fprintf(f, " loss gemodel p %s",
+ sprint_percent(gemodel->p, b1));
+ fprintf(f, " r %s", sprint_percent(gemodel->r, b1));
+ fprintf(f, " 1-h %s", sprint_percent(max_percent_value -
+ gemodel->h, b1));
+ fprintf(f, " 1-k %s", sprint_percent(gemodel->k1, b1));
+ }
+
+ if (qopt.duplicate) {
+ fprintf(f, " duplicate %s",
+ sprint_percent(qopt.duplicate, b1));
+ if (cor && cor->dup_corr)
+ fprintf(f, " %s", sprint_percent(cor->dup_corr, b1));
+ }
+
+ if (reorder && reorder->probability) {
+ fprintf(f, " reorder %s",
+ sprint_percent(reorder->probability, b1));
+ if (reorder->correlation)
+ fprintf(f, " %s",
+ sprint_percent(reorder->correlation, b1));
+ }
+
+ if (corrupt && corrupt->probability) {
+ fprintf(f, " corrupt %s",
+ sprint_percent(corrupt->probability, b1));
+ if (corrupt->correlation)
+ fprintf(f, " %s",
+ sprint_percent(corrupt->correlation, b1));
+ }
+
+ if (rate && rate->rate) {
+ if (rate64)
+ fprintf(f, " rate %s", sprint_rate(rate64, b1));
+ else
+ fprintf(f, " rate %s", sprint_rate(rate->rate, b1));
+ if (rate->packet_overhead)
+ fprintf(f, " packetoverhead %d", rate->packet_overhead);
+ if (rate->cell_size)
+ fprintf(f, " cellsize %u", rate->cell_size);
+ if (rate->cell_overhead)
+ fprintf(f, " celloverhead %d", rate->cell_overhead);
+ }
+
+ if (ecn)
+ fprintf(f, " ecn ");
+
+ if (qopt.gap)
+ fprintf(f, " gap %lu", (unsigned long)qopt.gap);
+
+
+ return 0;
+}
+
+struct qdisc_util netem_qdisc_util = {
+ .id = "netem",
+ .parse_qopt = netem_parse_opt,
+ .print_qopt = netem_print_opt,
+};
diff --git a/iproute2/tc/q_pie.c b/iproute2/tc/q_pie.c
new file mode 100644
index 0000000..193b05d
--- /dev/null
+++ b/iproute2/tc/q_pie.c
@@ -0,0 +1,218 @@
+/* Copyright (C) 2013 Cisco Systems, Inc, 2013.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * Author: Vijay Subramanian <vijaynsu@cisco.com>
+ * Author: Mythili Prabhu <mysuryan@cisco.com>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <math.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... pie [ limit PACKETS ][ target TIME us]\n");
+ fprintf(stderr, " [ tupdate TIME us][ alpha ALPHA ]");
+ fprintf(stderr, "[beta BETA ][bytemode | nobytemode][ecn | noecn ]\n");
+}
+
+#define ALPHA_MAX 32
+#define ALPHA_MIN 0
+#define BETA_MAX 32
+#define BETA_MIN 0
+
+static int pie_parse_opt(struct qdisc_util *qu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ unsigned int limit = 0;
+ unsigned int target = 0;
+ unsigned int tupdate = 0;
+ unsigned int alpha = 0;
+ unsigned int beta = 0;
+ int ecn = -1;
+ int bytemode = -1;
+ struct rtattr *tail;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "limit") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&limit, *argv, 0)) {
+ fprintf(stderr, "Illegal \"limit\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "target") == 0) {
+ NEXT_ARG();
+ if (get_time(&target, *argv)) {
+ fprintf(stderr, "Illegal \"target\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "tupdate") == 0) {
+ NEXT_ARG();
+ if (get_time(&tupdate, *argv)) {
+ fprintf(stderr, "Illegal \"tupdate\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "alpha") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&alpha, *argv, 0) ||
+ (alpha > ALPHA_MAX) || (alpha < ALPHA_MIN)) {
+ fprintf(stderr, "Illegal \"alpha\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "beta") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&beta, *argv, 0) ||
+ (beta > BETA_MAX) || (beta < BETA_MIN)) {
+ fprintf(stderr, "Illegal \"beta\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "ecn") == 0) {
+ ecn = 1;
+ } else if (strcmp(*argv, "noecn") == 0) {
+ ecn = 0;
+ } else if (strcmp(*argv, "bytemode") == 0) {
+ bytemode = 1;
+ } else if (strcmp(*argv, "nobytemode") == 0) {
+ bytemode = 0;
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--;
+ argv++;
+ }
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+ if (limit)
+ addattr_l(n, 1024, TCA_PIE_LIMIT, &limit, sizeof(limit));
+ if (tupdate)
+ addattr_l(n, 1024, TCA_PIE_TUPDATE, &tupdate, sizeof(tupdate));
+ if (target)
+ addattr_l(n, 1024, TCA_PIE_TARGET, &target, sizeof(target));
+ if (alpha)
+ addattr_l(n, 1024, TCA_PIE_ALPHA, &alpha, sizeof(alpha));
+ if (beta)
+ addattr_l(n, 1024, TCA_PIE_BETA, &beta, sizeof(beta));
+ if (ecn != -1)
+ addattr_l(n, 1024, TCA_PIE_ECN, &ecn, sizeof(ecn));
+ if (bytemode != -1)
+ addattr_l(n, 1024, TCA_PIE_BYTEMODE, &bytemode,
+ sizeof(bytemode));
+
+ tail->rta_len = (void *)NLMSG_TAIL(n) - (void *)tail;
+ return 0;
+}
+
+static int pie_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct rtattr *tb[TCA_PIE_MAX + 1];
+ unsigned int limit;
+ unsigned int tupdate;
+ unsigned int target;
+ unsigned int alpha;
+ unsigned int beta;
+ unsigned ecn;
+ unsigned bytemode;
+ SPRINT_BUF(b1);
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_PIE_MAX, opt);
+
+ if (tb[TCA_PIE_LIMIT] &&
+ RTA_PAYLOAD(tb[TCA_PIE_LIMIT]) >= sizeof(__u32)) {
+ limit = rta_getattr_u32(tb[TCA_PIE_LIMIT]);
+ fprintf(f, "limit %up ", limit);
+ }
+ if (tb[TCA_PIE_TARGET] &&
+ RTA_PAYLOAD(tb[TCA_PIE_TARGET]) >= sizeof(__u32)) {
+ target = rta_getattr_u32(tb[TCA_PIE_TARGET]);
+ fprintf(f, "target %s ", sprint_time(target, b1));
+ }
+ if (tb[TCA_PIE_TUPDATE] &&
+ RTA_PAYLOAD(tb[TCA_PIE_TUPDATE]) >= sizeof(__u32)) {
+ tupdate = rta_getattr_u32(tb[TCA_PIE_TUPDATE]);
+ fprintf(f, "tupdate %s ", sprint_time(tupdate, b1));
+ }
+ if (tb[TCA_PIE_ALPHA] &&
+ RTA_PAYLOAD(tb[TCA_PIE_ALPHA]) >= sizeof(__u32)) {
+ alpha = rta_getattr_u32(tb[TCA_PIE_ALPHA]);
+ fprintf(f, "alpha %u ", alpha);
+ }
+ if (tb[TCA_PIE_BETA] &&
+ RTA_PAYLOAD(tb[TCA_PIE_BETA]) >= sizeof(__u32)) {
+ beta = rta_getattr_u32(tb[TCA_PIE_BETA]);
+ fprintf(f, "beta %u ", beta);
+ }
+
+ if (tb[TCA_PIE_ECN] && RTA_PAYLOAD(tb[TCA_PIE_ECN]) >= sizeof(__u32)) {
+ ecn = rta_getattr_u32(tb[TCA_PIE_ECN]);
+ if (ecn)
+ fprintf(f, "ecn ");
+ }
+
+ if (tb[TCA_PIE_BYTEMODE] &&
+ RTA_PAYLOAD(tb[TCA_PIE_BYTEMODE]) >= sizeof(__u32)) {
+ bytemode = rta_getattr_u32(tb[TCA_PIE_BYTEMODE]);
+ if (bytemode)
+ fprintf(f, "bytemode ");
+ }
+
+ return 0;
+}
+
+static int pie_print_xstats(struct qdisc_util *qu, FILE *f,
+ struct rtattr *xstats)
+{
+ struct tc_pie_xstats *st;
+
+ if (xstats == NULL)
+ return 0;
+
+ if (RTA_PAYLOAD(xstats) < sizeof(*st))
+ return -1;
+
+ st = RTA_DATA(xstats);
+ /*prob is returned as a fracion of maximum integer value */
+ fprintf(f, "prob %f delay %uus avg_dq_rate %u\n",
+ (double)st->prob / (double)0xffffffff, st->delay,
+ st->avg_dq_rate);
+ fprintf(f, "pkts_in %u overlimit %u dropped %u maxq %u ecn_mark %u\n",
+ st->packets_in, st->overlimit, st->dropped, st->maxq,
+ st->ecn_mark);
+ return 0;
+
+}
+
+struct qdisc_util pie_qdisc_util = {
+ .id = "pie",
+ .parse_qopt = pie_parse_opt,
+ .print_qopt = pie_print_opt,
+ .print_xstats = pie_print_xstats,
+};
diff --git a/iproute2/tc/q_prio.c b/iproute2/tc/q_prio.c
new file mode 100644
index 0000000..3236bec
--- /dev/null
+++ b/iproute2/tc/q_prio.c
@@ -0,0 +1,124 @@
+/*
+ * q_prio.c PRIO.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... prio bands NUMBER priomap P1 P2...[multiqueue]\n");
+}
+
+static int prio_parse_opt(struct qdisc_util *qu, int argc, char **argv, struct nlmsghdr *n)
+{
+ int pmap_mode = 0;
+ int idx = 0;
+ struct tc_prio_qopt opt={3,{ 1, 2, 2, 2, 1, 2, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1 }};
+ struct rtattr *nest;
+ unsigned char mq = 0;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "bands") == 0) {
+ if (pmap_mode)
+ explain();
+ NEXT_ARG();
+ if (get_integer(&opt.bands, *argv, 10)) {
+ fprintf(stderr, "Illegal \"bands\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "priomap") == 0) {
+ if (pmap_mode) {
+ fprintf(stderr, "Error: duplicate priomap\n");
+ return -1;
+ }
+ pmap_mode = 1;
+ } else if (strcmp(*argv, "multiqueue") == 0) {
+ mq = 1;
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ unsigned band;
+ if (!pmap_mode) {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ if (get_unsigned(&band, *argv, 10)) {
+ fprintf(stderr, "Illegal \"priomap\" element\n");
+ return -1;
+ }
+ if (band >= opt.bands) {
+ fprintf(stderr, "\"priomap\" element is out of bands\n");
+ return -1;
+ }
+ if (idx > TC_PRIO_MAX) {
+ fprintf(stderr, "\"priomap\" index > TC_PRIO_MAX=%u\n", TC_PRIO_MAX);
+ return -1;
+ }
+ opt.priomap[idx++] = band;
+ }
+ argc--; argv++;
+ }
+
+/*
+ if (pmap_mode) {
+ for (; idx < TC_PRIO_MAX; idx++)
+ opt.priomap[idx] = opt.priomap[TC_PRIO_BESTEFFORT];
+ }
+*/
+ nest = addattr_nest_compat(n, 1024, TCA_OPTIONS, &opt, sizeof(opt));
+ if (mq)
+ addattr_l(n, 1024, TCA_PRIO_MQ, NULL, 0);
+ addattr_nest_compat_end(n, nest);
+ return 0;
+}
+
+int prio_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ int i;
+ struct tc_prio_qopt *qopt;
+ struct rtattr *tb[TCA_PRIO_MAX+1];
+
+ if (opt == NULL)
+ return 0;
+
+ if (parse_rtattr_nested_compat(tb, TCA_PRIO_MAX, opt, qopt,
+ sizeof(*qopt)))
+ return -1;
+
+ fprintf(f, "bands %u priomap ", qopt->bands);
+ for (i=0; i<=TC_PRIO_MAX; i++)
+ fprintf(f, " %d", qopt->priomap[i]);
+
+ if (tb[TCA_PRIO_MQ])
+ fprintf(f, " multiqueue: %s ",
+ rta_getattr_u8(tb[TCA_PRIO_MQ]) ? "on" : "off");
+
+ return 0;
+}
+
+struct qdisc_util prio_qdisc_util = {
+ .id = "prio",
+ .parse_qopt = prio_parse_opt,
+ .print_qopt = prio_print_opt,
+};
diff --git a/iproute2/tc/q_qfq.c b/iproute2/tc/q_qfq.c
new file mode 100644
index 0000000..05b4d84
--- /dev/null
+++ b/iproute2/tc/q_qfq.c
@@ -0,0 +1,122 @@
+/*
+ * q_qfq.c QFQ.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Stephen Hemminger <shemminger@vyatta.com>
+ * Fabio Checconi <fabio@gandalf.sssup.it>
+ *
+ */
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... qfq\n");
+}
+
+static void explain1(const char *arg)
+{
+ fprintf(stderr, "Illegal \"%s\"\n", arg);
+}
+
+static void explain_class(void)
+{
+ fprintf(stderr, "Usage: ... qfq weight NUMBER maxpkt BYTES\n");
+}
+
+static int qfq_parse_opt(struct qdisc_util *qu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ while (argc > 0) {
+ if (matches(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ return 0;
+}
+
+static int qfq_parse_class_opt(struct qdisc_util *qu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ struct rtattr *tail;
+ __u32 tmp;
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 4096, TCA_OPTIONS, NULL, 0);
+
+ while (argc > 0) {
+ if (matches(*argv, "weight") == 0) {
+ NEXT_ARG();
+ if (get_u32(&tmp, *argv, 10)) {
+ explain1("weight"); return -1;
+ }
+ addattr32(n, 4096, TCA_QFQ_WEIGHT, tmp);
+ } else if (matches(*argv, "maxpkt") == 0) {
+ NEXT_ARG();
+ if (get_u32(&tmp, *argv, 10)) {
+ explain1("maxpkt"); return -1;
+ }
+ addattr32(n, 4096, TCA_QFQ_LMAX, tmp);
+ } else if (strcmp(*argv, "help") == 0) {
+ explain_class();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain_class();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ tail->rta_len = (void *)NLMSG_TAIL(n) - (void *)tail;
+
+ return 0;
+}
+
+static int qfq_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct rtattr *tb[TCA_QFQ_MAX + 1];
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_QFQ_MAX, opt);
+
+ if (tb[TCA_QFQ_WEIGHT]) {
+ fprintf(f, "weight %u ",
+ rta_getattr_u32(tb[TCA_QFQ_WEIGHT]));
+ }
+
+ if (tb[TCA_QFQ_LMAX]) {
+ fprintf(f, "maxpkt %u ",
+ rta_getattr_u32(tb[TCA_QFQ_LMAX]));
+ }
+
+ return 0;
+}
+
+struct qdisc_util qfq_qdisc_util = {
+ .id = "qfq",
+ .parse_qopt = qfq_parse_opt,
+ .print_qopt = qfq_print_opt,
+ .parse_copt = qfq_parse_class_opt,
+ .print_copt = qfq_print_opt,
+};
diff --git a/iproute2/tc/q_red.c b/iproute2/tc/q_red.c
new file mode 100644
index 0000000..abd86c7
--- /dev/null
+++ b/iproute2/tc/q_red.c
@@ -0,0 +1,229 @@
+/*
+ * q_red.c RED.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <math.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+#include "tc_red.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... red limit BYTES [min BYTES] [max BYTES] avpkt BYTES [burst PACKETS]\n");
+ fprintf(stderr, " [adaptive] [probability PROBABILITY] [bandwidth KBPS]\n");
+ fprintf(stderr, " [ecn] [harddrop]\n");
+}
+
+static int red_parse_opt(struct qdisc_util *qu, int argc, char **argv, struct nlmsghdr *n)
+{
+ struct tc_red_qopt opt;
+ unsigned burst = 0;
+ unsigned avpkt = 0;
+ double probability = 0.02;
+ unsigned rate = 0;
+ int parm;
+ __u8 sbuf[256];
+ __u32 max_P;
+ struct rtattr *tail;
+
+ memset(&opt, 0, sizeof(opt));
+
+ while (argc > 0) {
+ if (strcmp(*argv, "limit") == 0) {
+ NEXT_ARG();
+ if (get_size(&opt.limit, *argv)) {
+ fprintf(stderr, "Illegal \"limit\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "min") == 0) {
+ NEXT_ARG();
+ if (get_size(&opt.qth_min, *argv)) {
+ fprintf(stderr, "Illegal \"min\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "max") == 0) {
+ NEXT_ARG();
+ if (get_size(&opt.qth_max, *argv)) {
+ fprintf(stderr, "Illegal \"max\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "burst") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&burst, *argv, 0)) {
+ fprintf(stderr, "Illegal \"burst\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "avpkt") == 0) {
+ NEXT_ARG();
+ if (get_size(&avpkt, *argv)) {
+ fprintf(stderr, "Illegal \"avpkt\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "probability") == 0) {
+ NEXT_ARG();
+ if (sscanf(*argv, "%lg", &probability) != 1) {
+ fprintf(stderr, "Illegal \"probability\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "bandwidth") == 0) {
+ NEXT_ARG();
+ if (get_rate(&rate, *argv)) {
+ fprintf(stderr, "Illegal \"bandwidth\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "ecn") == 0) {
+ opt.flags |= TC_RED_ECN;
+ } else if (strcmp(*argv, "harddrop") == 0) {
+ opt.flags |= TC_RED_HARDDROP;
+ } else if (strcmp(*argv, "adaptative") == 0) {
+ opt.flags |= TC_RED_ADAPTATIVE;
+ } else if (strcmp(*argv, "adaptive") == 0) {
+ opt.flags |= TC_RED_ADAPTATIVE;
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ if (!opt.limit || !avpkt) {
+ fprintf(stderr, "RED: Required parameter (limit, avpkt) is missing\n");
+ return -1;
+ }
+ /* Compute default min/max thresholds based on
+ * Sally Floyd's recommendations:
+ * http://www.icir.org/floyd/REDparameters.txt
+ */
+ if (!opt.qth_max)
+ opt.qth_max = opt.qth_min ? opt.qth_min * 3 : opt.limit / 4;
+ if (!opt.qth_min)
+ opt.qth_min = opt.qth_max / 3;
+ if (!burst)
+ burst = (2 * opt.qth_min + opt.qth_max) / (3 * avpkt);
+ if (!rate) {
+ get_rate(&rate, "10Mbit");
+ fprintf(stderr, "RED: set bandwidth to 10Mbit\n");
+ }
+ if ((parm = tc_red_eval_ewma(opt.qth_min, burst, avpkt)) < 0) {
+ fprintf(stderr, "RED: failed to calculate EWMA constant.\n");
+ return -1;
+ }
+ if (parm >= 10)
+ fprintf(stderr, "RED: WARNING. Burst %u seems to be too large.\n", burst);
+ opt.Wlog = parm;
+ if ((parm = tc_red_eval_P(opt.qth_min, opt.qth_max, probability)) < 0) {
+ fprintf(stderr, "RED: failed to calculate probability.\n");
+ return -1;
+ }
+ opt.Plog = parm;
+ if ((parm = tc_red_eval_idle_damping(opt.Wlog, avpkt, rate, sbuf)) < 0) {
+ fprintf(stderr, "RED: failed to calculate idle damping table.\n");
+ return -1;
+ }
+ opt.Scell_log = parm;
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+ addattr_l(n, 1024, TCA_RED_PARMS, &opt, sizeof(opt));
+ addattr_l(n, 1024, TCA_RED_STAB, sbuf, 256);
+ max_P = probability * pow(2, 32);
+ addattr_l(n, 1024, TCA_RED_MAX_P, &max_P, sizeof(max_P));
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+static int red_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct rtattr *tb[TCA_RED_MAX + 1];
+ struct tc_red_qopt *qopt;
+ __u32 max_P = 0;
+ SPRINT_BUF(b1);
+ SPRINT_BUF(b2);
+ SPRINT_BUF(b3);
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_RED_MAX, opt);
+
+ if (tb[TCA_RED_PARMS] == NULL)
+ return -1;
+ qopt = RTA_DATA(tb[TCA_RED_PARMS]);
+ if (RTA_PAYLOAD(tb[TCA_RED_PARMS]) < sizeof(*qopt))
+ return -1;
+
+ if (tb[TCA_RED_MAX_P] &&
+ RTA_PAYLOAD(tb[TCA_RED_MAX_P]) >= sizeof(__u32))
+ max_P = rta_getattr_u32(tb[TCA_RED_MAX_P]);
+
+ fprintf(f, "limit %s min %s max %s ",
+ sprint_size(qopt->limit, b1),
+ sprint_size(qopt->qth_min, b2),
+ sprint_size(qopt->qth_max, b3));
+ if (qopt->flags & TC_RED_ECN)
+ fprintf(f, "ecn ");
+ if (qopt->flags & TC_RED_HARDDROP)
+ fprintf(f, "harddrop ");
+ if (qopt->flags & TC_RED_ADAPTATIVE)
+ fprintf(f, "adaptive ");
+ if (show_details) {
+ fprintf(f, "ewma %u ", qopt->Wlog);
+ if (max_P)
+ fprintf(f, "probability %lg ", max_P / pow(2, 32));
+ else
+ fprintf(f, "Plog %u ", qopt->Plog);
+ fprintf(f, "Scell_log %u", qopt->Scell_log);
+ }
+ return 0;
+}
+
+static int red_print_xstats(struct qdisc_util *qu, FILE *f, struct rtattr *xstats)
+{
+#ifdef TC_RED_ECN
+ struct tc_red_xstats *st;
+
+ if (xstats == NULL)
+ return 0;
+
+ if (RTA_PAYLOAD(xstats) < sizeof(*st))
+ return -1;
+
+ st = RTA_DATA(xstats);
+ fprintf(f, " marked %u early %u pdrop %u other %u",
+ st->marked, st->early, st->pdrop, st->other);
+ return 0;
+
+#endif
+ return 0;
+}
+
+
+struct qdisc_util red_qdisc_util = {
+ .id = "red",
+ .parse_qopt = red_parse_opt,
+ .print_qopt = red_print_opt,
+ .print_xstats = red_print_xstats,
+};
diff --git a/iproute2/tc/q_rr.c b/iproute2/tc/q_rr.c
new file mode 100644
index 0000000..e8a9165
--- /dev/null
+++ b/iproute2/tc/q_rr.c
@@ -0,0 +1,119 @@
+/*
+ * q_rr.c RR.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: PJ Waskiewicz, <peter.p.waskiewicz.jr@intel.com>
+ * Original Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> (from PRIO)
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... rr bands NUMBER priomap P1 P2... [multiqueue]\n");
+}
+
+
+static int rr_parse_opt(struct qdisc_util *qu, int argc, char **argv, struct nlmsghdr *n)
+{
+ int pmap_mode = 0;
+ int idx = 0;
+ struct tc_prio_qopt opt={3,{ 1, 2, 2, 2, 1, 2, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1 }};
+ struct rtattr *nest;
+ unsigned char mq = 0;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "bands") == 0) {
+ if (pmap_mode)
+ explain();
+ NEXT_ARG();
+ if (get_integer(&opt.bands, *argv, 10)) {
+ fprintf(stderr, "Illegal \"bands\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "priomap") == 0) {
+ if (pmap_mode) {
+ fprintf(stderr, "Error: duplicate priomap\n");
+ return -1;
+ }
+ pmap_mode = 1;
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else if (strcmp(*argv, "multiqueue") == 0) {
+ mq = 1;
+ } else {
+ unsigned band;
+ if (!pmap_mode) {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ if (get_unsigned(&band, *argv, 10)) {
+ fprintf(stderr, "Illegal \"priomap\" element\n");
+ return -1;
+ }
+ if (band > opt.bands) {
+ fprintf(stderr, "\"priomap\" element is out of bands\n");
+ return -1;
+ }
+ if (idx > TC_PRIO_MAX) {
+ fprintf(stderr, "\"priomap\" index > TC_RR_MAX=%u\n", TC_PRIO_MAX);
+ return -1;
+ }
+ opt.priomap[idx++] = band;
+ }
+ argc--; argv++;
+ }
+
+ nest = addattr_nest_compat(n, 1024, TCA_OPTIONS, &opt, sizeof(opt));
+ if (mq)
+ addattr_l(n, 1024, TCA_PRIO_MQ, NULL, 0);
+ addattr_nest_compat_end(n, nest);
+ return 0;
+}
+
+static int rr_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ int i;
+ struct tc_prio_qopt *qopt;
+ struct rtattr *tb[TCA_PRIO_MAX + 1];
+
+ if (opt == NULL)
+ return 0;
+
+ if (parse_rtattr_nested_compat(tb, TCA_PRIO_MAX, opt, qopt,
+ sizeof(*qopt)))
+ return -1;
+
+ fprintf(f, "bands %u priomap ", qopt->bands);
+ for (i=0; i <= TC_PRIO_MAX; i++)
+ fprintf(f, " %d", qopt->priomap[i]);
+
+ if (tb[TCA_PRIO_MQ])
+ fprintf(f, " multiqueue: %s ",
+ rta_getattr_u8(tb[TCA_PRIO_MQ]) ? "on" : "off");
+
+ return 0;
+}
+
+struct qdisc_util rr_qdisc_util = {
+ .id = "rr",
+ .parse_qopt = rr_parse_opt,
+ .print_qopt = rr_print_opt,
+};
diff --git a/iproute2/tc/q_sfb.c b/iproute2/tc/q_sfb.c
new file mode 100644
index 0000000..f11c33a
--- /dev/null
+++ b/iproute2/tc/q_sfb.c
@@ -0,0 +1,200 @@
+/*
+ * q_sfb.c Stochastic Fair Blue.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Juliusz Chroboczek <jch@pps.jussieu.fr>
+ *
+ */
+
+
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+ fprintf(stderr,
+ "Usage: ... sfb [ rehash SECS ] [ db SECS ]\n"
+ " [ limit PACKETS ] [ max PACKETS ] [ target PACKETS ]\n"
+ " [ increment FLOAT ] [ decrement FLOAT ]\n"
+ " [ penalty_rate PPS ] [ penalty_burst PACKETS ]\n");
+}
+
+static int get_prob(__u32 *val, const char *arg)
+{
+ double d;
+ char *ptr;
+
+ if (!arg || !*arg)
+ return -1;
+ d = strtod(arg, &ptr);
+ if (!ptr || ptr == arg || d < 0.0 || d > 1.0)
+ return -1;
+ *val = (__u32)(d * SFB_MAX_PROB + 0.5);
+ return 0;
+}
+
+static int sfb_parse_opt(struct qdisc_util *qu, int argc, char **argv,
+ struct nlmsghdr *n)
+{
+ struct tc_sfb_qopt opt;
+ struct rtattr *tail;
+
+ memset(&opt, 0, sizeof(opt));
+ opt.rehash_interval = 600*1000;
+ opt.warmup_time = 60*1000;
+ opt.penalty_rate = 10;
+ opt.penalty_burst = 20;
+ opt.increment = (SFB_MAX_PROB + 1000) / 2000;
+ opt.decrement = (SFB_MAX_PROB + 10000) / 20000;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "rehash") == 0) {
+ NEXT_ARG();
+ if (get_u32(&opt.rehash_interval, *argv, 0)) {
+ fprintf(stderr, "Illegal \"rehash\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "db") == 0) {
+ NEXT_ARG();
+ if (get_u32(&opt.warmup_time, *argv, 0)) {
+ fprintf(stderr, "Illegal \"db\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "limit") == 0) {
+ NEXT_ARG();
+ if (get_u32(&opt.limit, *argv, 0)) {
+ fprintf(stderr, "Illegal \"limit\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "max") == 0) {
+ NEXT_ARG();
+ if (get_u32(&opt.max, *argv, 0)) {
+ fprintf(stderr, "Illegal \"max\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "target") == 0) {
+ NEXT_ARG();
+ if (get_u32(&opt.bin_size, *argv, 0)) {
+ fprintf(stderr, "Illegal \"target\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "increment") == 0) {
+ NEXT_ARG();
+ if (get_prob(&opt.increment, *argv)) {
+ fprintf(stderr, "Illegal \"increment\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "decrement") == 0) {
+ NEXT_ARG();
+ if (get_prob(&opt.decrement, *argv)) {
+ fprintf(stderr, "Illegal \"decrement\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "penalty_rate") == 0) {
+ NEXT_ARG();
+ if (get_u32(&opt.penalty_rate, *argv, 0)) {
+ fprintf(stderr, "Illegal \"penalty_rate\"\n");
+ return -1;
+ }
+ } else if (strcmp(*argv, "penalty_burst") == 0) {
+ NEXT_ARG();
+ if (get_u32(&opt.penalty_burst, *argv, 0)) {
+ fprintf(stderr, "Illegal \"penalty_burst\"\n");
+ return -1;
+ }
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ if (opt.max == 0) {
+ if (opt.bin_size >= 1)
+ opt.max = (opt.bin_size * 5 + 1) / 4;
+ else
+ opt.max = 25;
+ }
+ if (opt.bin_size == 0)
+ opt.bin_size = (opt.max * 4 + 3) / 5;
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+ addattr_l(n, 1024, TCA_SFB_PARMS, &opt, sizeof(opt));
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+static int sfb_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct rtattr *tb[__TCA_SFB_MAX];
+ struct tc_sfb_qopt *qopt;
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_SFB_MAX, opt);
+ if (tb[TCA_SFB_PARMS] == NULL)
+ return -1;
+ qopt = RTA_DATA(tb[TCA_SFB_PARMS]);
+ if (RTA_PAYLOAD(tb[TCA_SFB_PARMS]) < sizeof(*qopt))
+ return -1;
+
+ fprintf(f,
+ "limit %d max %d target %d\n"
+ " increment %.5f decrement %.5f penalty rate %d burst %d "
+ "(%ums %ums)",
+ qopt->limit, qopt->max, qopt->bin_size,
+ (double)qopt->increment / SFB_MAX_PROB,
+ (double)qopt->decrement / SFB_MAX_PROB,
+ qopt->penalty_rate, qopt->penalty_burst,
+ qopt->rehash_interval, qopt->warmup_time);
+
+ return 0;
+}
+
+static int sfb_print_xstats(struct qdisc_util *qu, FILE *f,
+ struct rtattr *xstats)
+{
+ struct tc_sfb_xstats *st;
+
+ if (xstats == NULL)
+ return 0;
+
+ if (RTA_PAYLOAD(xstats) < sizeof(*st))
+ return -1;
+
+ st = RTA_DATA(xstats);
+ fprintf(f,
+ " earlydrop %u penaltydrop %u bucketdrop %u queuedrop %u childdrop %u marked %u\n"
+ " maxqlen %u maxprob %.5f avgprob %.5f ",
+ st->earlydrop, st->penaltydrop, st->bucketdrop, st->queuedrop, st->childdrop,
+ st->marked,
+ st->maxqlen, (double)st->maxprob / SFB_MAX_PROB,
+ (double)st->avgprob / SFB_MAX_PROB);
+
+ return 0;
+}
+
+struct qdisc_util sfb_qdisc_util = {
+ .id = "sfb",
+ .parse_qopt = sfb_parse_opt,
+ .print_qopt = sfb_print_opt,
+ .print_xstats = sfb_print_xstats,
+};
diff --git a/iproute2/tc/q_sfq.c b/iproute2/tc/q_sfq.c
new file mode 100644
index 0000000..50846a9
--- /dev/null
+++ b/iproute2/tc/q_sfq.c
@@ -0,0 +1,277 @@
+/*
+ * q_sfq.c SFQ.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <math.h>
+
+#include "utils.h"
+#include "tc_util.h"
+#include "tc_red.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... sfq [ limit NUMBER ] [ perturb SECS ] [ quantum BYTES ]\n");
+ fprintf(stderr, " [ divisor NUMBER ] [ flows NUMBER] [ depth NUMBER ]\n");
+ fprintf(stderr, " [ headdrop ]\n");
+ fprintf(stderr, " [ redflowlimit BYTES ] [ min BYTES ] [ max BYTES ]\n");
+ fprintf(stderr, " [ avpkt BYTES ] [ burst PACKETS ] [ probability P ]\n");
+ fprintf(stderr, " [ ecn ] [ harddrop ]\n");
+}
+
+static int sfq_parse_opt(struct qdisc_util *qu, int argc, char **argv, struct nlmsghdr *n)
+{
+ int ok = 0, red = 0;
+ struct tc_sfq_qopt_v1 opt;
+ unsigned int burst = 0;
+ int wlog;
+ unsigned int avpkt = 1000;
+ double probability = 0.02;
+
+ memset(&opt, 0, sizeof(opt));
+
+ while (argc > 0) {
+ if (strcmp(*argv, "quantum") == 0) {
+ NEXT_ARG();
+ if (get_size(&opt.v0.quantum, *argv)) {
+ fprintf(stderr, "Illegal \"limit\"\n");
+ return -1;
+ }
+ ok++;
+ } else if (strcmp(*argv, "perturb") == 0) {
+ NEXT_ARG();
+ if (get_integer(&opt.v0.perturb_period, *argv, 0)) {
+ fprintf(stderr, "Illegal \"perturb\"\n");
+ return -1;
+ }
+ ok++;
+ } else if (strcmp(*argv, "limit") == 0) {
+ NEXT_ARG();
+ if (get_u32(&opt.v0.limit, *argv, 0)) {
+ fprintf(stderr, "Illegal \"limit\"\n");
+ return -1;
+ }
+ if (opt.v0.limit < 2) {
+ fprintf(stderr, "Illegal \"limit\", must be > 1\n");
+ return -1;
+ }
+ ok++;
+ } else if (strcmp(*argv, "divisor") == 0) {
+ NEXT_ARG();
+ if (get_u32(&opt.v0.divisor, *argv, 0)) {
+ fprintf(stderr, "Illegal \"divisor\"\n");
+ return -1;
+ }
+ ok++;
+ } else if (strcmp(*argv, "flows") == 0) {
+ NEXT_ARG();
+ if (get_u32(&opt.v0.flows, *argv, 0)) {
+ fprintf(stderr, "Illegal \"flows\"\n");
+ return -1;
+ }
+ ok++;
+ } else if (strcmp(*argv, "depth") == 0) {
+ NEXT_ARG();
+ if (get_u32(&opt.depth, *argv, 0)) {
+ fprintf(stderr, "Illegal \"flows\"\n");
+ return -1;
+ }
+ ok++;
+ } else if (strcmp(*argv, "headdrop") == 0) {
+ opt.headdrop = 1;
+ ok++;
+ } else if (strcmp(*argv, "redflowlimit") == 0) {
+ NEXT_ARG();
+ if (get_u32(&opt.limit, *argv, 0)) {
+ fprintf(stderr, "Illegal \"redflowlimit\"\n");
+ return -1;
+ }
+ red++;
+ } else if (strcmp(*argv, "min") == 0) {
+ NEXT_ARG();
+ if (get_u32(&opt.qth_min, *argv, 0)) {
+ fprintf(stderr, "Illegal \"min\"\n");
+ return -1;
+ }
+ red++;
+ } else if (strcmp(*argv, "max") == 0) {
+ NEXT_ARG();
+ if (get_u32(&opt.qth_max, *argv, 0)) {
+ fprintf(stderr, "Illegal \"max\"\n");
+ return -1;
+ }
+ red++;
+ } else if (strcmp(*argv, "burst") == 0) {
+ NEXT_ARG();
+ if (get_unsigned(&burst, *argv, 0)) {
+ fprintf(stderr, "Illegal \"burst\"\n");
+ return -1;
+ }
+ red++;
+ } else if (strcmp(*argv, "avpkt") == 0) {
+ NEXT_ARG();
+ if (get_size(&avpkt, *argv)) {
+ fprintf(stderr, "Illegal \"avpkt\"\n");
+ return -1;
+ }
+ red++;
+ } else if (strcmp(*argv, "probability") == 0) {
+ NEXT_ARG();
+ if (sscanf(*argv, "%lg", &probability) != 1) {
+ fprintf(stderr, "Illegal \"probability\"\n");
+ return -1;
+ }
+ red++;
+ } else if (strcmp(*argv, "ecn") == 0) {
+ opt.flags |= TC_RED_ECN;
+ red++;
+ } else if (strcmp(*argv, "harddrop") == 0) {
+ opt.flags |= TC_RED_HARDDROP;
+ red++;
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+ if (red) {
+ if (!opt.limit) {
+ fprintf(stderr, "Required parameter (redflowlimit) is missing\n");
+ return -1;
+ }
+ /* Compute default min/max thresholds based on
+ Sally Floyd's recommendations:
+ http://www.icir.org/floyd/REDparameters.txt
+ */
+ if (!opt.qth_max)
+ opt.qth_max = opt.limit / 4;
+ if (!opt.qth_min)
+ opt.qth_min = opt.qth_max / 3;
+ if (!burst)
+ burst = (2 * opt.qth_min + opt.qth_max) / (3 * avpkt);
+
+ if (opt.qth_max > opt.limit) {
+ fprintf(stderr, "\"max\" is larger than \"limit\"\n");
+ return -1;
+ }
+
+ if (opt.qth_min >= opt.qth_max) {
+ fprintf(stderr, "\"min\" is not smaller than \"max\"\n");
+ return -1;
+ }
+
+ wlog = tc_red_eval_ewma(opt.qth_min, burst, avpkt);
+ if (wlog < 0) {
+ fprintf(stderr, "SFQ: failed to calculate EWMA constant.\n");
+ return -1;
+ }
+ if (wlog >= 10)
+ fprintf(stderr, "SFQ: WARNING. Burst %u seems to be too large.\n", burst);
+ opt.Wlog = wlog;
+
+ wlog = tc_red_eval_P(opt.qth_min, opt.qth_max, probability);
+ if (wlog < 0) {
+ fprintf(stderr, "SFQ: failed to calculate probability.\n");
+ return -1;
+ }
+ opt.Plog = wlog;
+ opt.max_P = probability * pow(2, 32);
+ }
+
+ if (ok || red)
+ addattr_l(n, 1024, TCA_OPTIONS, &opt, sizeof(opt));
+ return 0;
+}
+
+static int sfq_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct tc_sfq_qopt *qopt;
+ struct tc_sfq_qopt_v1 *qopt_ext = NULL;
+ SPRINT_BUF(b1);
+ SPRINT_BUF(b2);
+ SPRINT_BUF(b3);
+ if (opt == NULL)
+ return 0;
+
+ if (RTA_PAYLOAD(opt) < sizeof(*qopt))
+ return -1;
+ if (RTA_PAYLOAD(opt) >= sizeof(*qopt_ext))
+ qopt_ext = RTA_DATA(opt);
+ qopt = RTA_DATA(opt);
+ fprintf(f, "limit %up ", qopt->limit);
+ fprintf(f, "quantum %s ", sprint_size(qopt->quantum, b1));
+ if (qopt_ext && qopt_ext->depth)
+ fprintf(f, "depth %u ", qopt_ext->depth);
+ if (qopt_ext && qopt_ext->headdrop)
+ fprintf(f, "headdrop ");
+
+ if (show_details) {
+ fprintf(f, "flows %u/%u ", qopt->flows, qopt->divisor);
+ }
+ fprintf(f, "divisor %u ", qopt->divisor);
+ if (qopt->perturb_period)
+ fprintf(f, "perturb %dsec ", qopt->perturb_period);
+ if (qopt_ext && qopt_ext->qth_min) {
+ fprintf(f, "\n ewma %u ", qopt_ext->Wlog);
+ fprintf(f, "min %s max %s probability %g ",
+ sprint_size(qopt_ext->qth_min, b2),
+ sprint_size(qopt_ext->qth_max, b3),
+ qopt_ext->max_P / pow(2, 32));
+ if (qopt_ext->flags & TC_RED_ECN)
+ fprintf(f, "ecn ");
+ if (show_stats) {
+ fprintf(f, "\n prob_mark %u prob_mark_head %u prob_drop %u",
+ qopt_ext->stats.prob_mark,
+ qopt_ext->stats.prob_mark_head,
+ qopt_ext->stats.prob_drop);
+ fprintf(f, "\n forced_mark %u forced_mark_head %u forced_drop %u",
+ qopt_ext->stats.forced_mark,
+ qopt_ext->stats.forced_mark_head,
+ qopt_ext->stats.forced_drop);
+ }
+ }
+ return 0;
+}
+
+static int sfq_print_xstats(struct qdisc_util *qu, FILE *f,
+ struct rtattr *xstats)
+{
+ struct tc_sfq_xstats *st;
+
+ if (xstats == NULL)
+ return 0;
+ if (RTA_PAYLOAD(xstats) < sizeof(*st))
+ return -1;
+ st = RTA_DATA(xstats);
+
+ fprintf(f, " allot %d ", st->allot);
+ fprintf(f, "\n");
+ return 0;
+}
+
+struct qdisc_util sfq_qdisc_util = {
+ .id = "sfq",
+ .parse_qopt = sfq_parse_opt,
+ .print_qopt = sfq_print_opt,
+ .print_xstats = sfq_print_xstats,
+};
diff --git a/iproute2/tc/q_tbf.c b/iproute2/tc/q_tbf.c
new file mode 100644
index 0000000..0981e6f
--- /dev/null
+++ b/iproute2/tc/q_tbf.c
@@ -0,0 +1,330 @@
+/*
+ * q_tbf.c TBF.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+ fprintf(stderr, "Usage: ... tbf limit BYTES burst BYTES[/BYTES] rate KBPS [ mtu BYTES[/BYTES] ]\n");
+ fprintf(stderr, " [ peakrate KBPS ] [ latency TIME ] ");
+ fprintf(stderr, "[ overhead BYTES ] [ linklayer TYPE ]\n");
+}
+
+static void explain1(const char *arg, const char *val)
+{
+ fprintf(stderr, "tbf: illegal value for \"%s\": \"%s\"\n", arg, val);
+}
+
+
+static int tbf_parse_opt(struct qdisc_util *qu, int argc, char **argv, struct nlmsghdr *n)
+{
+ int ok=0;
+ struct tc_tbf_qopt opt;
+ __u32 rtab[256];
+ __u32 ptab[256];
+ unsigned buffer=0, mtu=0, mpu=0, latency=0;
+ int Rcell_log=-1, Pcell_log = -1;
+ unsigned short overhead=0;
+ unsigned int linklayer = LINKLAYER_ETHERNET; /* Assume ethernet */
+ struct rtattr *tail;
+ __u64 rate64 = 0, prate64 = 0;
+
+ memset(&opt, 0, sizeof(opt));
+
+ while (argc > 0) {
+ if (matches(*argv, "limit") == 0) {
+ NEXT_ARG();
+ if (opt.limit) {
+ fprintf(stderr, "tbf: duplicate \"limit\" specification\n");
+ return -1;
+ }
+ if (latency) {
+ fprintf(stderr, "tbf: specifying both \"latency\" and \"limit\" is not allowed\n");
+ return -1;
+ }
+ if (get_size(&opt.limit, *argv)) {
+ explain1("limit", *argv);
+ return -1;
+ }
+ ok++;
+ } else if (matches(*argv, "latency") == 0) {
+ NEXT_ARG();
+ if (latency) {
+ fprintf(stderr, "tbf: duplicate \"latency\" specification\n");
+ return -1;
+ }
+ if (opt.limit) {
+ fprintf(stderr, "tbf: specifying both \"limit\" and \"/latency\" is not allowed\n");
+ return -1;
+ }
+ if (get_time(&latency, *argv)) {
+ explain1("latency", *argv);
+ return -1;
+ }
+ ok++;
+ } else if (matches(*argv, "burst") == 0 ||
+ strcmp(*argv, "buffer") == 0 ||
+ strcmp(*argv, "maxburst") == 0) {
+ const char *parm_name = *argv;
+ NEXT_ARG();
+ if (buffer) {
+ fprintf(stderr, "tbf: duplicate \"buffer/burst/maxburst\" specification\n");
+ return -1;
+ }
+ if (get_size_and_cell(&buffer, &Rcell_log, *argv) < 0) {
+ explain1(parm_name, *argv);
+ return -1;
+ }
+ ok++;
+ } else if (strcmp(*argv, "mtu") == 0 ||
+ strcmp(*argv, "minburst") == 0) {
+ const char *parm_name = *argv;
+ NEXT_ARG();
+ if (mtu) {
+ fprintf(stderr, "tbf: duplicate \"mtu/minburst\" specification\n");
+ return -1;
+ }
+ if (get_size_and_cell(&mtu, &Pcell_log, *argv) < 0) {
+ explain1(parm_name, *argv);
+ return -1;
+ }
+ ok++;
+ } else if (strcmp(*argv, "mpu") == 0) {
+ NEXT_ARG();
+ if (mpu) {
+ fprintf(stderr, "tbf: duplicate \"mpu\" specification\n");
+ return -1;
+ }
+ if (get_size(&mpu, *argv)) {
+ explain1("mpu", *argv);
+ return -1;
+ }
+ ok++;
+ } else if (strcmp(*argv, "rate") == 0) {
+ NEXT_ARG();
+ if (rate64) {
+ fprintf(stderr, "tbf: duplicate \"rate\" specification\n");
+ return -1;
+ }
+ if (get_rate64(&rate64, *argv)) {
+ explain1("rate", *argv);
+ return -1;
+ }
+ ok++;
+ } else if (matches(*argv, "peakrate") == 0) {
+ NEXT_ARG();
+ if (prate64) {
+ fprintf(stderr, "tbf: duplicate \"peakrate\" specification\n");
+ return -1;
+ }
+ if (get_rate64(&prate64, *argv)) {
+ explain1("peakrate", *argv);
+ return -1;
+ }
+ ok++;
+ } else if (matches(*argv, "overhead") == 0) {
+ NEXT_ARG();
+ if (overhead) {
+ fprintf(stderr, "tbf: duplicate \"overhead\" specification\n");
+ return -1;
+ }
+ if (get_u16(&overhead, *argv, 10)) {
+ explain1("overhead", *argv); return -1;
+ }
+ } else if (matches(*argv, "linklayer") == 0) {
+ NEXT_ARG();
+ if (get_linklayer(&linklayer, *argv)) {
+ explain1("linklayer", *argv); return -1;
+ }
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "tbf: unknown parameter \"%s\"\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ int verdict = 0;
+
+ /* Be nice to the user: try to emit all error messages in
+ * one go rather than reveal one more problem when a
+ * previous one has been fixed.
+ */
+ if (rate64 == 0) {
+ fprintf(stderr, "tbf: the \"rate\" parameter is mandatory.\n");
+ verdict = -1;
+ }
+ if (!buffer) {
+ fprintf(stderr, "tbf: the \"burst\" parameter is mandatory.\n");
+ verdict = -1;
+ }
+ if (prate64) {
+ if (!mtu) {
+ fprintf(stderr, "tbf: when \"peakrate\" is specified, \"mtu\" must also be specified.\n");
+ verdict = -1;
+ }
+ }
+
+ if (opt.limit == 0 && latency == 0) {
+ fprintf(stderr, "tbf: either \"limit\" or \"latency\" is required.\n");
+ verdict = -1;
+ }
+
+ if (verdict != 0) {
+ explain();
+ return verdict;
+ }
+
+ opt.rate.rate = (rate64 >= (1ULL << 32)) ? ~0U : rate64;
+ opt.peakrate.rate = (prate64 >= (1ULL << 32)) ? ~0U : prate64;
+
+ if (opt.limit == 0) {
+ double lim = rate64*(double)latency/TIME_UNITS_PER_SEC + buffer;
+ if (prate64) {
+ double lim2 = prate64*(double)latency/TIME_UNITS_PER_SEC + mtu;
+ if (lim2 < lim)
+ lim = lim2;
+ }
+ opt.limit = lim;
+ }
+
+ opt.rate.mpu = mpu;
+ opt.rate.overhead = overhead;
+ if (tc_calc_rtable(&opt.rate, rtab, Rcell_log, mtu, linklayer) < 0) {
+ fprintf(stderr, "tbf: failed to calculate rate table.\n");
+ return -1;
+ }
+ opt.buffer = tc_calc_xmittime(opt.rate.rate, buffer);
+
+ if (opt.peakrate.rate) {
+ opt.peakrate.mpu = mpu;
+ opt.peakrate.overhead = overhead;
+ if (tc_calc_rtable(&opt.peakrate, ptab, Pcell_log, mtu, linklayer) < 0) {
+ fprintf(stderr, "tbf: failed to calculate peak rate table.\n");
+ return -1;
+ }
+ opt.mtu = tc_calc_xmittime(opt.peakrate.rate, mtu);
+ }
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+ addattr_l(n, 2024, TCA_TBF_PARMS, &opt, sizeof(opt));
+ addattr_l(n, 2124, TCA_TBF_BURST, &buffer, sizeof(buffer));
+ if (rate64 >= (1ULL << 32))
+ addattr_l(n, 2124, TCA_TBF_RATE64, &rate64, sizeof(rate64));
+ addattr_l(n, 3024, TCA_TBF_RTAB, rtab, 1024);
+ if (opt.peakrate.rate) {
+ if (prate64 >= (1ULL << 32))
+ addattr_l(n, 3124, TCA_TBF_PRATE64, &prate64, sizeof(prate64));
+ addattr_l(n, 3224, TCA_TBF_PBURST, &mtu, sizeof(mtu));
+ addattr_l(n, 4096, TCA_TBF_PTAB, ptab, 1024);
+ }
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+static int tbf_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct rtattr *tb[TCA_TBF_MAX+1];
+ struct tc_tbf_qopt *qopt;
+ unsigned int linklayer;
+ double buffer, mtu;
+ double latency;
+ __u64 rate64 = 0, prate64 = 0;
+ SPRINT_BUF(b1);
+ SPRINT_BUF(b2);
+ SPRINT_BUF(b3);
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_TBF_MAX, opt);
+
+ if (tb[TCA_TBF_PARMS] == NULL)
+ return -1;
+
+ qopt = RTA_DATA(tb[TCA_TBF_PARMS]);
+ if (RTA_PAYLOAD(tb[TCA_TBF_PARMS]) < sizeof(*qopt))
+ return -1;
+ rate64 = qopt->rate.rate;
+ if (tb[TCA_TBF_RATE64] &&
+ RTA_PAYLOAD(tb[TCA_TBF_RATE64]) >= sizeof(rate64))
+ rate64 = rta_getattr_u64(tb[TCA_TBF_RATE64]);
+ fprintf(f, "rate %s ", sprint_rate(rate64, b1));
+ buffer = tc_calc_xmitsize(rate64, qopt->buffer);
+ if (show_details) {
+ fprintf(f, "burst %s/%u mpu %s ", sprint_size(buffer, b1),
+ 1<<qopt->rate.cell_log, sprint_size(qopt->rate.mpu, b2));
+ } else {
+ fprintf(f, "burst %s ", sprint_size(buffer, b1));
+ }
+ if (show_raw)
+ fprintf(f, "[%08x] ", qopt->buffer);
+ prate64 = qopt->peakrate.rate;
+ if (tb[TCA_TBF_PRATE64] &&
+ RTA_PAYLOAD(tb[TCA_TBF_PRATE64]) >= sizeof(prate64))
+ prate64 = rta_getattr_u64(tb[TCA_TBF_PRATE64]);
+ if (prate64) {
+ fprintf(f, "peakrate %s ", sprint_rate(prate64, b1));
+ if (qopt->mtu || qopt->peakrate.mpu) {
+ mtu = tc_calc_xmitsize(prate64, qopt->mtu);
+ if (show_details) {
+ fprintf(f, "mtu %s/%u mpu %s ", sprint_size(mtu, b1),
+ 1<<qopt->peakrate.cell_log, sprint_size(qopt->peakrate.mpu, b2));
+ } else {
+ fprintf(f, "minburst %s ", sprint_size(mtu, b1));
+ }
+ if (show_raw)
+ fprintf(f, "[%08x] ", qopt->mtu);
+ }
+ }
+
+ latency = TIME_UNITS_PER_SEC*(qopt->limit/(double)rate64) - tc_core_tick2time(qopt->buffer);
+ if (prate64) {
+ double lat2 = TIME_UNITS_PER_SEC*(qopt->limit/(double)prate64) - tc_core_tick2time(qopt->mtu);
+ if (lat2 > latency)
+ latency = lat2;
+ }
+ if (latency >= 0.0)
+ fprintf(f, "lat %s ", sprint_time(latency, b1));
+ if (show_raw || latency < 0.0)
+ fprintf(f, "limit %s ", sprint_size(qopt->limit, b1));
+
+ if (qopt->rate.overhead) {
+ fprintf(f, "overhead %d", qopt->rate.overhead);
+ }
+ linklayer = (qopt->rate.linklayer & TC_LINKLAYER_MASK);
+ if (linklayer > TC_LINKLAYER_ETHERNET || show_details)
+ fprintf(f, "linklayer %s ", sprint_linklayer(linklayer, b3));
+
+ return 0;
+}
+
+struct qdisc_util tbf_qdisc_util = {
+ .id = "tbf",
+ .parse_qopt = tbf_parse_opt,
+ .print_qopt = tbf_print_opt,
+};
diff --git a/iproute2/tc/static-syms.c b/iproute2/tc/static-syms.c
new file mode 100644
index 0000000..0bc8074
--- /dev/null
+++ b/iproute2/tc/static-syms.c
@@ -0,0 +1,14 @@
+/*
+ * This file creates a dummy version of dynamic loading
+ * for environments where dynamic linking
+ * is not used or available.
+ */
+
+#include <string.h>
+#include "dlfcn.h"
+
+void *_dlsym(const char *sym)
+{
+#include "static-syms.h"
+ return NULL;
+}
diff --git a/iproute2/tc/tc.c b/iproute2/tc/tc.c
new file mode 100644
index 0000000..e1d4bc3
--- /dev/null
+++ b/iproute2/tc/tc.c
@@ -0,0 +1,393 @@
+/*
+ * tc.c "tc" utility frontend.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ * Fixes:
+ *
+ * Petri Mattila <petri@prihateam.fi> 990308: wrong memset's resulted in faults
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <dlfcn.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <errno.h>
+
+#include "SNAPSHOT.h"
+#include "utils.h"
+#include "tc_util.h"
+#include "tc_common.h"
+#include "namespace.h"
+
+int show_stats = 0;
+int show_details = 0;
+int show_raw = 0;
+int show_pretty = 0;
+int show_graph = 0;
+int timestamp;
+
+int batch_mode = 0;
+int resolve_hosts = 0;
+int use_iec = 0;
+int force = 0;
+bool use_names = false;
+
+static char *conf_file;
+
+struct rtnl_handle rth;
+
+static void *BODY = NULL; /* cached handle dlopen(NULL) */
+static struct qdisc_util * qdisc_list;
+static struct filter_util * filter_list;
+
+#ifdef ANDROID
+extern struct qdisc_util cbq_qdisc_util;
+extern struct qdisc_util htb_qdisc_util;
+extern struct qdisc_util ingress_qdisc_util;
+extern struct filter_util u32_filter_util;
+#endif
+
+static int print_noqopt(struct qdisc_util *qu, FILE *f,
+ struct rtattr *opt)
+{
+ if (opt && RTA_PAYLOAD(opt))
+ fprintf(f, "[Unknown qdisc, optlen=%u] ",
+ (unsigned) RTA_PAYLOAD(opt));
+ return 0;
+}
+
+static int parse_noqopt(struct qdisc_util *qu, int argc, char **argv, struct nlmsghdr *n)
+{
+ if (argc) {
+ fprintf(stderr, "Unknown qdisc \"%s\", hence option \"%s\" is unparsable\n", qu->id, *argv);
+ return -1;
+ }
+ return 0;
+}
+
+static int print_nofopt(struct filter_util *qu, FILE *f, struct rtattr *opt, __u32 fhandle)
+{
+ if (opt && RTA_PAYLOAD(opt))
+ fprintf(f, "fh %08x [Unknown filter, optlen=%u] ",
+ fhandle, (unsigned) RTA_PAYLOAD(opt));
+ else if (fhandle)
+ fprintf(f, "fh %08x ", fhandle);
+ return 0;
+}
+
+static int parse_nofopt(struct filter_util *qu, char *fhandle, int argc, char **argv, struct nlmsghdr *n)
+{
+ __u32 handle;
+
+ if (argc) {
+ fprintf(stderr, "Unknown filter \"%s\", hence option \"%s\" is unparsable\n", qu->id, *argv);
+ return -1;
+ }
+ if (fhandle) {
+ struct tcmsg *t = NLMSG_DATA(n);
+ if (get_u32(&handle, fhandle, 16)) {
+ fprintf(stderr, "Unparsable filter ID \"%s\"\n", fhandle);
+ return -1;
+ }
+ t->tcm_handle = handle;
+ }
+ return 0;
+}
+
+struct qdisc_util *get_qdisc_kind(const char *str)
+{
+ void *dlh;
+ char buf[256];
+ struct qdisc_util *q;
+
+#ifdef ANDROID
+ if (!strcmp(str, "cbq"))
+ return &cbq_qdisc_util;
+ else if (!strcmp(str, "htb"))
+ return &htb_qdisc_util;
+ else if (!strcmp(str, "ingress"))
+ return &ingress_qdisc_util;
+ else {
+ fprintf(stderr, "Android does not support qdisc '%s'\n", str);
+ return NULL;
+ }
+#endif
+ for (q = qdisc_list; q; q = q->next)
+ if (strcmp(q->id, str) == 0)
+ return q;
+
+ snprintf(buf, sizeof(buf), "%s/q_%s.so", get_tc_lib(), str);
+ dlh = dlopen(buf, RTLD_LAZY);
+ if (!dlh) {
+ /* look in current binary, only open once */
+ dlh = BODY;
+ if (dlh == NULL) {
+ dlh = BODY = dlopen(NULL, RTLD_LAZY);
+ if (dlh == NULL)
+ goto noexist;
+ }
+ }
+
+ snprintf(buf, sizeof(buf), "%s_qdisc_util", str);
+ q = dlsym(dlh, buf);
+ if (q == NULL)
+ goto noexist;
+
+reg:
+ q->next = qdisc_list;
+ qdisc_list = q;
+ return q;
+
+noexist:
+ q = malloc(sizeof(*q));
+ if (q) {
+
+ memset(q, 0, sizeof(*q));
+ q->id = strcpy(malloc(strlen(str)+1), str);
+ q->parse_qopt = parse_noqopt;
+ q->print_qopt = print_noqopt;
+ goto reg;
+ }
+ return q;
+}
+
+
+struct filter_util *get_filter_kind(const char *str)
+{
+ void *dlh;
+ char buf[256];
+ struct filter_util *q;
+#ifdef ANDROID
+ if (!strcmp(str, "u32"))
+ return &u32_filter_util;
+ else {
+ fprintf(stderr, "Android does not support filter '%s'\n", str);
+ return NULL;
+ }
+#endif
+
+ for (q = filter_list; q; q = q->next)
+ if (strcmp(q->id, str) == 0)
+ return q;
+
+ snprintf(buf, sizeof(buf), "%s/f_%s.so", get_tc_lib(), str);
+ dlh = dlopen(buf, RTLD_LAZY);
+ if (dlh == NULL) {
+ dlh = BODY;
+ if (dlh == NULL) {
+ dlh = BODY = dlopen(NULL, RTLD_LAZY);
+ if (dlh == NULL)
+ goto noexist;
+ }
+ }
+
+ snprintf(buf, sizeof(buf), "%s_filter_util", str);
+ q = dlsym(dlh, buf);
+ if (q == NULL)
+ goto noexist;
+
+reg:
+ q->next = filter_list;
+ filter_list = q;
+ return q;
+noexist:
+ q = malloc(sizeof(*q));
+ if (q) {
+ memset(q, 0, sizeof(*q));
+ strncpy(q->id, str, 15);
+ q->parse_fopt = parse_nofopt;
+ q->print_fopt = print_nofopt;
+ goto reg;
+ }
+ return q;
+}
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: tc [ OPTIONS ] OBJECT { COMMAND | help }\n"
+#ifdef ANDROID
+ " tc [-force]\n"
+#else
+ " tc [-force] -batch filename\n"
+#endif
+ "where OBJECT := { qdisc | class | filter | action | monitor | exec }\n"
+ " OPTIONS := { -s[tatistics] | -d[etails] | -r[aw] | -p[retty] | -b[atch] [filename] | "
+ "-n[etns] name |\n"
+ " -nm | -nam[es] | { -cf | -conf } path }\n");
+}
+
+static int do_cmd(int argc, char **argv)
+{
+ if (matches(*argv, "qdisc") == 0)
+ return do_qdisc(argc-1, argv+1);
+ if (matches(*argv, "class") == 0)
+ return do_class(argc-1, argv+1);
+ if (matches(*argv, "filter") == 0)
+ return do_filter(argc-1, argv+1);
+ if (matches(*argv, "actions") == 0)
+ return do_action(argc-1, argv+1);
+ if (matches(*argv, "monitor") == 0)
+ return do_tcmonitor(argc-1, argv+1);
+ if (matches(*argv, "exec") == 0)
+ return do_exec(argc-1, argv+1);
+ if (matches(*argv, "help") == 0) {
+ usage();
+ return 0;
+ }
+
+ fprintf(stderr, "Object \"%s\" is unknown, try \"tc help\".\n",
+ *argv);
+ return -1;
+}
+
+#ifndef ANDROID
+static int batch(const char *name)
+{
+ char *line = NULL;
+ size_t len = 0;
+ int ret = 0;
+
+ batch_mode = 1;
+ if (name && strcmp(name, "-") != 0) {
+ if (freopen(name, "r", stdin) == NULL) {
+ fprintf(stderr, "Cannot open file \"%s\" for reading: %s\n",
+ name, strerror(errno));
+ return -1;
+ }
+ }
+
+ tc_core_init();
+
+ if (rtnl_open(&rth, 0) < 0) {
+ fprintf(stderr, "Cannot open rtnetlink\n");
+ return -1;
+ }
+
+ cmdlineno = 0;
+ while (getcmdline(&line, &len, stdin) != -1) {
+ char *largv[100];
+ int largc;
+
+ largc = makeargs(line, largv, 100);
+ if (largc == 0)
+ continue; /* blank line */
+
+ if (do_cmd(largc, largv)) {
+ fprintf(stderr, "Command failed %s:%d\n", name, cmdlineno);
+ ret = 1;
+ if (!force)
+ break;
+ }
+ }
+ if (line)
+ free(line);
+
+ rtnl_close(&rth);
+ return ret;
+}
+#endif
+
+
+int main(int argc, char **argv)
+{
+ int ret;
+#ifndef ANDROID
+ char *batch_file = NULL;
+#endif
+
+ while (argc > 1) {
+ if (argv[1][0] != '-')
+ break;
+ if (matches(argv[1], "-stats") == 0 ||
+ matches(argv[1], "-statistics") == 0) {
+ ++show_stats;
+ } else if (matches(argv[1], "-details") == 0) {
+ ++show_details;
+ } else if (matches(argv[1], "-raw") == 0) {
+ ++show_raw;
+ } else if (matches(argv[1], "-pretty") == 0) {
+ ++show_pretty;
+ } else if (matches(argv[1], "-graph") == 0) {
+ show_graph = 1;
+ } else if (matches(argv[1], "-Version") == 0) {
+ printf("tc utility, iproute2-ss%s\n", SNAPSHOT);
+ return 0;
+ } else if (matches(argv[1], "-iec") == 0) {
+ ++use_iec;
+ } else if (matches(argv[1], "-help") == 0) {
+ usage();
+ return 0;
+ } else if (matches(argv[1], "-force") == 0) {
+ ++force;
+#ifndef ANDROID
+ } else if (matches(argv[1], "-batch") == 0) {
+ argc--; argv++;
+ if (argc <= 1)
+ usage();
+ batch_file = argv[1];
+#endif
+ } else if (matches(argv[1], "-netns") == 0) {
+ NEXT_ARG();
+ if (netns_switch(argv[1]))
+ return -1;
+ } else if (matches(argv[1], "-names") == 0 ||
+ matches(argv[1], "-nm") == 0) {
+ use_names = true;
+ } else if (matches(argv[1], "-cf") == 0 ||
+ matches(argv[1], "-conf") == 0) {
+ NEXT_ARG();
+ conf_file = argv[1];
+ } else if (matches(argv[1], "-timestamp") == 0) {
+ timestamp++;
+ } else if (matches(argv[1], "-tshort") == 0) {
+ ++timestamp;
+ ++timestamp_short;
+ } else {
+ fprintf(stderr, "Option \"%s\" is unknown, try \"tc -help\".\n", argv[1]);
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+#ifndef ANDROID
+ if (batch_file)
+ return batch(batch_file);
+#endif
+
+ if (argc <= 1) {
+ usage();
+ return 0;
+ }
+
+ tc_core_init();
+ if (rtnl_open(&rth, 0) < 0) {
+ fprintf(stderr, "Cannot open rtnetlink\n");
+ exit(1);
+ }
+
+ if (use_names && cls_names_init(conf_file)) {
+ ret = -1;
+ goto Exit;
+ }
+
+ ret = do_cmd(argc-1, argv+1);
+Exit:
+ rtnl_close(&rth);
+
+ if (use_names)
+ cls_names_uninit();
+
+ return ret;
+}
diff --git a/iproute2/tc/tc_bpf.c b/iproute2/tc/tc_bpf.c
new file mode 100644
index 0000000..42c8841
--- /dev/null
+++ b/iproute2/tc/tc_bpf.c
@@ -0,0 +1,1892 @@
+/*
+ * tc_bpf.c BPF common code
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Daniel Borkmann <dborkman@redhat.com>
+ * Jiri Pirko <jiri@resnulli.us>
+ * Alexei Starovoitov <ast@plumgrid.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <stdarg.h>
+
+#ifdef HAVE_ELF
+#include <libelf.h>
+#include <gelf.h>
+#endif
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/un.h>
+#include <sys/vfs.h>
+#include <sys/mount.h>
+#include <sys/syscall.h>
+#include <sys/sendfile.h>
+#include <sys/resource.h>
+
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/if_alg.h>
+
+#include <arpa/inet.h>
+
+#include "utils.h"
+
+#include "bpf_elf.h"
+#include "bpf_scm.h"
+
+#include "tc_util.h"
+#include "tc_bpf.h"
+
+#ifdef HAVE_ELF
+static int bpf_obj_open(const char *path, enum bpf_prog_type type,
+ const char *sec, bool verbose);
+#else
+static int bpf_obj_open(const char *path, enum bpf_prog_type type,
+ const char *sec, bool verbose)
+{
+ fprintf(stderr, "No ELF library support compiled in.\n");
+ errno = ENOSYS;
+ return -1;
+}
+#endif
+
+static inline __u64 bpf_ptr_to_u64(const void *ptr)
+{
+ return (__u64)(unsigned long)ptr;
+}
+
+static int bpf(int cmd, union bpf_attr *attr, unsigned int size)
+{
+#ifdef __NR_bpf
+ return syscall(__NR_bpf, cmd, attr, size);
+#else
+ fprintf(stderr, "No bpf syscall, kernel headers too old?\n");
+ errno = ENOSYS;
+ return -1;
+#endif
+}
+
+static int bpf_map_update(int fd, const void *key, const void *value,
+ uint64_t flags)
+{
+ union bpf_attr attr = {
+ .map_fd = fd,
+ .key = bpf_ptr_to_u64(key),
+ .value = bpf_ptr_to_u64(value),
+ .flags = flags,
+ };
+
+ return bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
+}
+
+static int bpf_parse_string(char *arg, bool from_file, __u16 *bpf_len,
+ char **bpf_string, bool *need_release,
+ const char separator)
+{
+ char sp;
+
+ if (from_file) {
+ size_t tmp_len, op_len = sizeof("65535 255 255 4294967295,");
+ char *tmp_string;
+ FILE *fp;
+
+ tmp_len = sizeof("4096,") + BPF_MAXINSNS * op_len;
+ tmp_string = malloc(tmp_len);
+ if (tmp_string == NULL)
+ return -ENOMEM;
+
+ memset(tmp_string, 0, tmp_len);
+
+ fp = fopen(arg, "r");
+ if (fp == NULL) {
+ perror("Cannot fopen");
+ free(tmp_string);
+ return -ENOENT;
+ }
+
+ if (!fgets(tmp_string, tmp_len, fp)) {
+ free(tmp_string);
+ fclose(fp);
+ return -EIO;
+ }
+
+ fclose(fp);
+
+ *need_release = true;
+ *bpf_string = tmp_string;
+ } else {
+ *need_release = false;
+ *bpf_string = arg;
+ }
+
+ if (sscanf(*bpf_string, "%hu%c", bpf_len, &sp) != 2 ||
+ sp != separator) {
+ if (*need_release)
+ free(*bpf_string);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int bpf_ops_parse(int argc, char **argv, struct sock_filter *bpf_ops,
+ bool from_file)
+{
+ char *bpf_string, *token, separator = ',';
+ int ret = 0, i = 0;
+ bool need_release;
+ __u16 bpf_len = 0;
+
+ if (argc < 1)
+ return -EINVAL;
+ if (bpf_parse_string(argv[0], from_file, &bpf_len, &bpf_string,
+ &need_release, separator))
+ return -EINVAL;
+ if (bpf_len == 0 || bpf_len > BPF_MAXINSNS) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ token = bpf_string;
+ while ((token = strchr(token, separator)) && (++token)[0]) {
+ if (i >= bpf_len) {
+ fprintf(stderr, "Real program length exceeds encoded "
+ "length parameter!\n");
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (sscanf(token, "%hu %hhu %hhu %u,",
+ &bpf_ops[i].code, &bpf_ops[i].jt,
+ &bpf_ops[i].jf, &bpf_ops[i].k) != 4) {
+ fprintf(stderr, "Error at instruction %d!\n", i);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ i++;
+ }
+
+ if (i != bpf_len) {
+ fprintf(stderr, "Parsed program length is less than encoded"
+ "length parameter!\n");
+ ret = -EINVAL;
+ goto out;
+ }
+ ret = bpf_len;
+out:
+ if (need_release)
+ free(bpf_string);
+
+ return ret;
+}
+
+void bpf_print_ops(FILE *f, struct rtattr *bpf_ops, __u16 len)
+{
+ struct sock_filter *ops = (struct sock_filter *) RTA_DATA(bpf_ops);
+ int i;
+
+ if (len == 0)
+ return;
+
+ fprintf(f, "bytecode \'%u,", len);
+
+ for (i = 0; i < len - 1; i++)
+ fprintf(f, "%hu %hhu %hhu %u,", ops[i].code, ops[i].jt,
+ ops[i].jf, ops[i].k);
+
+ fprintf(f, "%hu %hhu %hhu %u\'", ops[i].code, ops[i].jt,
+ ops[i].jf, ops[i].k);
+}
+
+static int bpf_map_selfcheck_pinned(int fd, const struct bpf_elf_map *map,
+ int length)
+{
+ char file[PATH_MAX], buff[4096];
+ struct bpf_elf_map tmp, zero;
+ unsigned int val;
+ FILE *fp;
+
+ snprintf(file, sizeof(file), "/proc/%d/fdinfo/%d", getpid(), fd);
+
+ fp = fopen(file, "r");
+ if (!fp) {
+ fprintf(stderr, "No procfs support?!\n");
+ return -EIO;
+ }
+
+ memset(&tmp, 0, sizeof(tmp));
+ while (fgets(buff, sizeof(buff), fp)) {
+ if (sscanf(buff, "map_type:\t%u", &val) == 1)
+ tmp.type = val;
+ else if (sscanf(buff, "key_size:\t%u", &val) == 1)
+ tmp.size_key = val;
+ else if (sscanf(buff, "value_size:\t%u", &val) == 1)
+ tmp.size_value = val;
+ else if (sscanf(buff, "max_entries:\t%u", &val) == 1)
+ tmp.max_elem = val;
+ }
+
+ fclose(fp);
+
+ if (!memcmp(&tmp, map, length)) {
+ return 0;
+ } else {
+ memset(&zero, 0, sizeof(zero));
+ /* If kernel doesn't have eBPF-related fdinfo, we cannot do much,
+ * so just accept it. We know we do have an eBPF fd and in this
+ * case, everything is 0. It is guaranteed that no such map exists
+ * since map type of 0 is unloadable BPF_MAP_TYPE_UNSPEC.
+ */
+ if (!memcmp(&tmp, &zero, length))
+ return 0;
+
+ fprintf(stderr, "Map specs from pinned file differ!\n");
+ return -EINVAL;
+ }
+}
+
+static int bpf_mnt_fs(const char *target)
+{
+ bool bind_done = false;
+
+ while (mount("", target, "none", MS_PRIVATE | MS_REC, NULL)) {
+ if (errno != EINVAL || bind_done) {
+ fprintf(stderr, "mount --make-private %s failed: %s\n",
+ target, strerror(errno));
+ return -1;
+ }
+
+ if (mount(target, target, "none", MS_BIND, NULL)) {
+ fprintf(stderr, "mount --bind %s %s failed: %s\n",
+ target, target, strerror(errno));
+ return -1;
+ }
+
+ bind_done = true;
+ }
+
+ if (mount("bpf", target, "bpf", 0, NULL)) {
+ fprintf(stderr, "mount -t bpf bpf %s failed: %s\n",
+ target, strerror(errno));
+ return -1;
+ }
+
+ return 0;
+}
+
+static int bpf_valid_mntpt(const char *mnt, unsigned long magic)
+{
+ struct statfs st_fs;
+
+ if (statfs(mnt, &st_fs) < 0)
+ return -ENOENT;
+ if ((unsigned long)st_fs.f_type != magic)
+ return -ENOENT;
+
+ return 0;
+}
+
+static const char *bpf_find_mntpt(const char *fstype, unsigned long magic,
+ char *mnt, int len,
+ const char * const *known_mnts)
+{
+ const char * const *ptr;
+ char type[100];
+ FILE *fp;
+
+ if (known_mnts) {
+ ptr = known_mnts;
+ while (*ptr) {
+ if (bpf_valid_mntpt(*ptr, magic) == 0) {
+ strncpy(mnt, *ptr, len - 1);
+ mnt[len - 1] = 0;
+ return mnt;
+ }
+ ptr++;
+ }
+ }
+
+ fp = fopen("/proc/mounts", "r");
+ if (fp == NULL || len != PATH_MAX)
+ return NULL;
+
+ while (fscanf(fp, "%*s %" textify(PATH_MAX) "s %99s %*s %*d %*d\n",
+ mnt, type) == 2) {
+ if (strcmp(type, fstype) == 0)
+ break;
+ }
+
+ fclose(fp);
+ if (strcmp(type, fstype) != 0)
+ return NULL;
+
+ return mnt;
+}
+
+int bpf_trace_pipe(void)
+{
+ char tracefs_mnt[PATH_MAX] = TRACE_DIR_MNT;
+ static const char * const tracefs_known_mnts[] = {
+ TRACE_DIR_MNT,
+ "/sys/kernel/debug/tracing",
+ "/tracing",
+ "/trace",
+ 0,
+ };
+ char tpipe[PATH_MAX];
+ const char *mnt;
+ int fd;
+
+ mnt = bpf_find_mntpt("tracefs", TRACEFS_MAGIC, tracefs_mnt,
+ sizeof(tracefs_mnt), tracefs_known_mnts);
+ if (!mnt) {
+ fprintf(stderr, "tracefs not mounted?\n");
+ return -1;
+ }
+
+ snprintf(tpipe, sizeof(tpipe), "%s/trace_pipe", mnt);
+
+ fd = open(tpipe, O_RDONLY);
+ if (fd < 0)
+ return -1;
+
+ fprintf(stderr, "Running! Hang up with ^C!\n\n");
+ while (1) {
+ static char buff[4096];
+ ssize_t ret;
+
+ ret = read(fd, buff, sizeof(buff) - 1);
+ if (ret > 0) {
+ write(2, buff, ret);
+ fflush(stderr);
+ }
+ }
+
+ return 0;
+}
+
+static const char *bpf_get_tc_dir(void)
+{
+ static bool bpf_mnt_cached = false;
+ static char bpf_tc_dir[PATH_MAX];
+ static const char *mnt;
+ static const char * const bpf_known_mnts[] = {
+ BPF_DIR_MNT,
+ 0,
+ };
+ char bpf_mnt[PATH_MAX] = BPF_DIR_MNT;
+ char bpf_glo_dir[PATH_MAX];
+ int ret;
+
+ if (bpf_mnt_cached)
+ goto done;
+
+ mnt = bpf_find_mntpt("bpf", BPF_FS_MAGIC, bpf_mnt, sizeof(bpf_mnt),
+ bpf_known_mnts);
+ if (!mnt) {
+ mnt = getenv(BPF_ENV_MNT);
+ if (!mnt)
+ mnt = BPF_DIR_MNT;
+ ret = bpf_mnt_fs(mnt);
+ if (ret) {
+ mnt = NULL;
+ goto out;
+ }
+ }
+
+ snprintf(bpf_tc_dir, sizeof(bpf_tc_dir), "%s/%s", mnt, BPF_DIR_TC);
+ ret = mkdir(bpf_tc_dir, S_IRWXU);
+ if (ret && errno != EEXIST) {
+ fprintf(stderr, "mkdir %s failed: %s\n", bpf_tc_dir,
+ strerror(errno));
+ mnt = NULL;
+ goto out;
+ }
+
+ snprintf(bpf_glo_dir, sizeof(bpf_glo_dir), "%s/%s",
+ bpf_tc_dir, BPF_DIR_GLOBALS);
+ ret = mkdir(bpf_glo_dir, S_IRWXU);
+ if (ret && errno != EEXIST) {
+ fprintf(stderr, "mkdir %s failed: %s\n", bpf_glo_dir,
+ strerror(errno));
+ mnt = NULL;
+ goto out;
+ }
+
+ mnt = bpf_tc_dir;
+out:
+ bpf_mnt_cached = true;
+done:
+ return mnt;
+}
+
+static int bpf_obj_get(const char *pathname)
+{
+ union bpf_attr attr;
+ char tmp[PATH_MAX];
+
+ if (strlen(pathname) > 2 && pathname[0] == 'm' &&
+ pathname[1] == ':' && bpf_get_tc_dir()) {
+ snprintf(tmp, sizeof(tmp), "%s/%s",
+ bpf_get_tc_dir(), pathname + 2);
+ pathname = tmp;
+ }
+
+ memset(&attr, 0, sizeof(attr));
+ attr.pathname = bpf_ptr_to_u64(pathname);
+
+ return bpf(BPF_OBJ_GET, &attr, sizeof(attr));
+}
+
+const char *bpf_default_section(const enum bpf_prog_type type)
+{
+ switch (type) {
+ case BPF_PROG_TYPE_SCHED_CLS:
+ return ELF_SECTION_CLASSIFIER;
+ case BPF_PROG_TYPE_SCHED_ACT:
+ return ELF_SECTION_ACTION;
+ default:
+ return NULL;
+ }
+}
+
+enum bpf_mode {
+ CBPF_BYTECODE = 0,
+ CBPF_FILE,
+ EBPF_OBJECT,
+ EBPF_PINNED,
+ __BPF_MODE_MAX,
+#define BPF_MODE_MAX __BPF_MODE_MAX
+};
+
+static int bpf_parse(int *ptr_argc, char ***ptr_argv, const bool *opt_tbl,
+ enum bpf_prog_type *type, enum bpf_mode *mode,
+ const char **ptr_object, const char **ptr_section,
+ const char **ptr_uds_name, struct sock_filter *opcodes)
+{
+ const char *file, *section, *uds_name;
+ bool verbose = false;
+ int ret, argc;
+ char **argv;
+
+ argv = *ptr_argv;
+ argc = *ptr_argc;
+
+ if (opt_tbl[CBPF_BYTECODE] &&
+ (matches(*argv, "bytecode") == 0 ||
+ strcmp(*argv, "bc") == 0)) {
+ *mode = CBPF_BYTECODE;
+ } else if (opt_tbl[CBPF_FILE] &&
+ (matches(*argv, "bytecode-file") == 0 ||
+ strcmp(*argv, "bcf") == 0)) {
+ *mode = CBPF_FILE;
+ } else if (opt_tbl[EBPF_OBJECT] &&
+ (matches(*argv, "object-file") == 0 ||
+ strcmp(*argv, "obj") == 0)) {
+ *mode = EBPF_OBJECT;
+ } else if (opt_tbl[EBPF_PINNED] &&
+ (matches(*argv, "object-pinned") == 0 ||
+ matches(*argv, "pinned") == 0 ||
+ matches(*argv, "fd") == 0)) {
+ *mode = EBPF_PINNED;
+ } else {
+ fprintf(stderr, "What mode is \"%s\"?\n", *argv);
+ return -1;
+ }
+
+ NEXT_ARG();
+ file = section = uds_name = NULL;
+ if (*mode == EBPF_OBJECT || *mode == EBPF_PINNED) {
+ file = *argv;
+ NEXT_ARG_FWD();
+
+ if (*type == BPF_PROG_TYPE_UNSPEC) {
+ if (argc > 0 && matches(*argv, "type") == 0) {
+ NEXT_ARG();
+ if (matches(*argv, "cls") == 0) {
+ *type = BPF_PROG_TYPE_SCHED_CLS;
+ } else if (matches(*argv, "act") == 0) {
+ *type = BPF_PROG_TYPE_SCHED_ACT;
+ } else {
+ fprintf(stderr, "What type is \"%s\"?\n",
+ *argv);
+ return -1;
+ }
+ NEXT_ARG_FWD();
+ } else {
+ *type = BPF_PROG_TYPE_SCHED_CLS;
+ }
+ }
+
+ section = bpf_default_section(*type);
+ if (argc > 0 && matches(*argv, "section") == 0) {
+ NEXT_ARG();
+ section = *argv;
+ NEXT_ARG_FWD();
+ }
+
+ uds_name = getenv(BPF_ENV_UDS);
+ if (argc > 0 && !uds_name &&
+ matches(*argv, "export") == 0) {
+ NEXT_ARG();
+ uds_name = *argv;
+ NEXT_ARG_FWD();
+ }
+
+ if (argc > 0 && matches(*argv, "verbose") == 0) {
+ verbose = true;
+ NEXT_ARG_FWD();
+ }
+
+ PREV_ARG();
+ }
+
+ if (*mode == CBPF_BYTECODE || *mode == CBPF_FILE)
+ ret = bpf_ops_parse(argc, argv, opcodes, *mode == CBPF_FILE);
+ else if (*mode == EBPF_OBJECT)
+ ret = bpf_obj_open(file, *type, section, verbose);
+ else if (*mode == EBPF_PINNED)
+ ret = bpf_obj_get(file);
+ else
+ return -1;
+
+ if (ptr_object)
+ *ptr_object = file;
+ if (ptr_section)
+ *ptr_section = section;
+ if (ptr_uds_name)
+ *ptr_uds_name = uds_name;
+
+ *ptr_argc = argc;
+ *ptr_argv = argv;
+
+ return ret;
+}
+
+int bpf_parse_common(int *ptr_argc, char ***ptr_argv, const int *nla_tbl,
+ enum bpf_prog_type type, const char **ptr_object,
+ const char **ptr_uds_name, struct nlmsghdr *n)
+{
+ struct sock_filter opcodes[BPF_MAXINSNS];
+ const bool opt_tbl[BPF_MODE_MAX] = {
+ [CBPF_BYTECODE] = true,
+ [CBPF_FILE] = true,
+ [EBPF_OBJECT] = true,
+ [EBPF_PINNED] = true,
+ };
+ char annotation[256];
+ const char *section;
+ enum bpf_mode mode;
+ int ret;
+
+ ret = bpf_parse(ptr_argc, ptr_argv, opt_tbl, &type, &mode,
+ ptr_object, §ion, ptr_uds_name, opcodes);
+ if (ret < 0)
+ return ret;
+
+ if (mode == CBPF_BYTECODE || mode == CBPF_FILE) {
+ addattr16(n, MAX_MSG, nla_tbl[BPF_NLA_OPS_LEN], ret);
+ addattr_l(n, MAX_MSG, nla_tbl[BPF_NLA_OPS], opcodes,
+ ret * sizeof(struct sock_filter));
+ }
+
+ if (mode == EBPF_OBJECT || mode == EBPF_PINNED) {
+ snprintf(annotation, sizeof(annotation), "%s:[%s]",
+ basename(*ptr_object), mode == EBPF_PINNED ?
+ "*fsobj" : section);
+
+ addattr32(n, MAX_MSG, nla_tbl[BPF_NLA_FD], ret);
+ addattrstrz(n, MAX_MSG, nla_tbl[BPF_NLA_NAME], annotation);
+ }
+
+ return 0;
+}
+
+int bpf_graft_map(const char *map_path, uint32_t *key, int argc, char **argv)
+{
+ enum bpf_prog_type type = BPF_PROG_TYPE_UNSPEC;
+ const bool opt_tbl[BPF_MODE_MAX] = {
+ [CBPF_BYTECODE] = false,
+ [CBPF_FILE] = false,
+ [EBPF_OBJECT] = true,
+ [EBPF_PINNED] = true,
+ };
+ const struct bpf_elf_map test = {
+ .type = BPF_MAP_TYPE_PROG_ARRAY,
+ .size_key = sizeof(int),
+ .size_value = sizeof(int),
+ };
+ int ret, prog_fd, map_fd;
+ const char *section;
+ enum bpf_mode mode;
+ uint32_t map_key;
+
+ prog_fd = bpf_parse(&argc, &argv, opt_tbl, &type, &mode,
+ NULL, §ion, NULL, NULL);
+ if (prog_fd < 0)
+ return prog_fd;
+ if (key) {
+ map_key = *key;
+ } else {
+ ret = sscanf(section, "%*i/%i", &map_key);
+ if (ret != 1) {
+ fprintf(stderr, "Couldn\'t infer map key from section "
+ "name! Please provide \'key\' argument!\n");
+ ret = -EINVAL;
+ goto out_prog;
+ }
+ }
+
+ map_fd = bpf_obj_get(map_path);
+ if (map_fd < 0) {
+ fprintf(stderr, "Couldn\'t retrieve pinned map \'%s\': %s\n",
+ map_path, strerror(errno));
+ ret = map_fd;
+ goto out_prog;
+ }
+
+ ret = bpf_map_selfcheck_pinned(map_fd, &test,
+ offsetof(struct bpf_elf_map, max_elem));
+ if (ret < 0) {
+ fprintf(stderr, "Map \'%s\' self-check failed!\n", map_path);
+ goto out_map;
+ }
+
+ ret = bpf_map_update(map_fd, &map_key, &prog_fd, BPF_ANY);
+ if (ret < 0)
+ fprintf(stderr, "Map update failed: %s\n", strerror(errno));
+out_map:
+ close(map_fd);
+out_prog:
+ close(prog_fd);
+ return ret;
+}
+
+#ifdef HAVE_ELF
+struct bpf_elf_prog {
+ enum bpf_prog_type type;
+ const struct bpf_insn *insns;
+ size_t size;
+ const char *license;
+};
+
+struct bpf_hash_entry {
+ unsigned int pinning;
+ const char *subpath;
+ struct bpf_hash_entry *next;
+};
+
+struct bpf_elf_ctx {
+ Elf *elf_fd;
+ GElf_Ehdr elf_hdr;
+ Elf_Data *sym_tab;
+ Elf_Data *str_tab;
+ int obj_fd;
+ int map_fds[ELF_MAX_MAPS];
+ struct bpf_elf_map maps[ELF_MAX_MAPS];
+ int sym_num;
+ int map_num;
+ bool *sec_done;
+ int sec_maps;
+ char license[ELF_MAX_LICENSE_LEN];
+ enum bpf_prog_type type;
+ bool verbose;
+ struct bpf_elf_st stat;
+ struct bpf_hash_entry *ht[256];
+};
+
+struct bpf_elf_sec_data {
+ GElf_Shdr sec_hdr;
+ Elf_Data *sec_data;
+ const char *sec_name;
+};
+
+struct bpf_map_data {
+ int *fds;
+ const char *obj;
+ struct bpf_elf_st *st;
+ struct bpf_elf_map *ent;
+};
+
+/* If we provide a small buffer with log level enabled, the kernel
+ * could fail program load as no buffer space is available for the
+ * log and thus verifier fails. In case something doesn't pass the
+ * verifier we still want to hand something descriptive to the user.
+ */
+static char bpf_log_buf[65536];
+
+static __check_format_string(1, 2) void bpf_dump_error(const char *format, ...)
+{
+ va_list vl;
+
+ va_start(vl, format);
+ vfprintf(stderr, format, vl);
+ va_end(vl);
+
+ if (bpf_log_buf[0]) {
+ fprintf(stderr, "%s\n", bpf_log_buf);
+ memset(bpf_log_buf, 0, sizeof(bpf_log_buf));
+ }
+}
+
+static int bpf_map_create(enum bpf_map_type type, unsigned int size_key,
+ unsigned int size_value, unsigned int max_elem)
+{
+ union bpf_attr attr = {
+ .map_type = type,
+ .key_size = size_key,
+ .value_size = size_value,
+ .max_entries = max_elem,
+ };
+
+ return bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+}
+
+static int bpf_prog_load(enum bpf_prog_type type, const struct bpf_insn *insns,
+ size_t size, const char *license)
+{
+ union bpf_attr attr = {
+ .prog_type = type,
+ .insns = bpf_ptr_to_u64(insns),
+ .insn_cnt = size / sizeof(struct bpf_insn),
+ .license = bpf_ptr_to_u64(license),
+ .log_buf = bpf_ptr_to_u64(bpf_log_buf),
+ .log_size = sizeof(bpf_log_buf),
+ .log_level = 1,
+ };
+
+ if (getenv(BPF_ENV_NOLOG)) {
+ attr.log_buf = 0;
+ attr.log_size = 0;
+ attr.log_level = 0;
+ }
+
+ return bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+}
+
+static int bpf_obj_pin(int fd, const char *pathname)
+{
+ union bpf_attr attr = {
+ .pathname = bpf_ptr_to_u64(pathname),
+ .bpf_fd = fd,
+ };
+
+ return bpf(BPF_OBJ_PIN, &attr, sizeof(attr));
+}
+
+static int bpf_obj_hash(const char *object, uint8_t *out, size_t len)
+{
+ struct sockaddr_alg alg = {
+ .salg_family = AF_ALG,
+ .salg_type = "hash",
+ .salg_name = "sha1",
+ };
+ int ret, cfd, ofd, ffd;
+ struct stat stbuff;
+ ssize_t size;
+
+ if (!object || len != 20)
+ return -EINVAL;
+
+ cfd = socket(AF_ALG, SOCK_SEQPACKET, 0);
+ if (cfd < 0) {
+ fprintf(stderr, "Cannot get AF_ALG socket: %s\n",
+ strerror(errno));
+ return cfd;
+ }
+
+ ret = bind(cfd, (struct sockaddr *)&alg, sizeof(alg));
+ if (ret < 0) {
+ fprintf(stderr, "Error binding socket: %s\n", strerror(errno));
+ goto out_cfd;
+ }
+
+ ofd = accept(cfd, NULL, 0);
+ if (ofd < 0) {
+ fprintf(stderr, "Error accepting socket: %s\n",
+ strerror(errno));
+ ret = ofd;
+ goto out_cfd;
+ }
+
+ ffd = open(object, O_RDONLY);
+ if (ffd < 0) {
+ fprintf(stderr, "Error opening object %s: %s\n",
+ object, strerror(errno));
+ ret = ffd;
+ goto out_ofd;
+ }
+
+ ret = fstat(ffd, &stbuff);
+ if (ret < 0) {
+ fprintf(stderr, "Error doing fstat: %s\n",
+ strerror(errno));
+ goto out_ffd;
+ }
+
+ size = sendfile(ofd, ffd, NULL, stbuff.st_size);
+ if (size != stbuff.st_size) {
+ fprintf(stderr, "Error from sendfile (%zd vs %zu bytes): %s\n",
+ size, stbuff.st_size, strerror(errno));
+ ret = -1;
+ goto out_ffd;
+ }
+
+ size = read(ofd, out, len);
+ if (size != len) {
+ fprintf(stderr, "Error from read (%zd vs %zu bytes): %s\n",
+ size, len, strerror(errno));
+ ret = -1;
+ } else {
+ ret = 0;
+ }
+out_ffd:
+ close(ffd);
+out_ofd:
+ close(ofd);
+out_cfd:
+ close(cfd);
+ return ret;
+}
+
+static const char *bpf_get_obj_uid(const char *pathname)
+{
+ static bool bpf_uid_cached = false;
+ static char bpf_uid[64];
+ uint8_t tmp[20];
+ int ret;
+
+ if (bpf_uid_cached)
+ goto done;
+
+ ret = bpf_obj_hash(pathname, tmp, sizeof(tmp));
+ if (ret) {
+ fprintf(stderr, "Object hashing failed!\n");
+ return NULL;
+ }
+
+ hexstring_n2a(tmp, sizeof(tmp), bpf_uid, sizeof(bpf_uid));
+ bpf_uid_cached = true;
+done:
+ return bpf_uid;
+}
+
+static int bpf_init_env(const char *pathname)
+{
+ struct rlimit limit = {
+ .rlim_cur = RLIM_INFINITY,
+ .rlim_max = RLIM_INFINITY,
+ };
+
+ /* Don't bother in case we fail! */
+ setrlimit(RLIMIT_MEMLOCK, &limit);
+
+ if (!bpf_get_tc_dir()) {
+ fprintf(stderr, "Continuing without mounted eBPF fs. "
+ "Too old kernel?\n");
+ return 0;
+ }
+
+ if (!bpf_get_obj_uid(pathname))
+ return -1;
+
+ return 0;
+}
+
+static const char *bpf_custom_pinning(const struct bpf_elf_ctx *ctx,
+ uint32_t pinning)
+{
+ struct bpf_hash_entry *entry;
+
+ entry = ctx->ht[pinning & (ARRAY_SIZE(ctx->ht) - 1)];
+ while (entry && entry->pinning != pinning)
+ entry = entry->next;
+
+ return entry ? entry->subpath : NULL;
+}
+
+static bool bpf_no_pinning(const struct bpf_elf_ctx *ctx,
+ uint32_t pinning)
+{
+ switch (pinning) {
+ case PIN_OBJECT_NS:
+ case PIN_GLOBAL_NS:
+ return false;
+ case PIN_NONE:
+ return true;
+ default:
+ return !bpf_custom_pinning(ctx, pinning);
+ }
+}
+
+static void bpf_make_pathname(char *pathname, size_t len, const char *name,
+ const struct bpf_elf_ctx *ctx, uint32_t pinning)
+{
+ switch (pinning) {
+ case PIN_OBJECT_NS:
+ snprintf(pathname, len, "%s/%s/%s", bpf_get_tc_dir(),
+ bpf_get_obj_uid(NULL), name);
+ break;
+ case PIN_GLOBAL_NS:
+ snprintf(pathname, len, "%s/%s/%s", bpf_get_tc_dir(),
+ BPF_DIR_GLOBALS, name);
+ break;
+ default:
+ snprintf(pathname, len, "%s/../%s/%s", bpf_get_tc_dir(),
+ bpf_custom_pinning(ctx, pinning), name);
+ break;
+ }
+}
+
+static int bpf_probe_pinned(const char *name, const struct bpf_elf_ctx *ctx,
+ uint32_t pinning)
+{
+ char pathname[PATH_MAX];
+
+ if (bpf_no_pinning(ctx, pinning) || !bpf_get_tc_dir())
+ return 0;
+
+ bpf_make_pathname(pathname, sizeof(pathname), name, ctx, pinning);
+ return bpf_obj_get(pathname);
+}
+
+static int bpf_make_obj_path(void)
+{
+ char tmp[PATH_MAX];
+ int ret;
+
+ snprintf(tmp, sizeof(tmp), "%s/%s", bpf_get_tc_dir(),
+ bpf_get_obj_uid(NULL));
+
+ ret = mkdir(tmp, S_IRWXU);
+ if (ret && errno != EEXIST) {
+ fprintf(stderr, "mkdir %s failed: %s\n", tmp, strerror(errno));
+ return ret;
+ }
+
+ return 0;
+}
+
+static int bpf_make_custom_path(const char *todo)
+{
+ char tmp[PATH_MAX], rem[PATH_MAX], *sub;
+ int ret;
+
+ snprintf(tmp, sizeof(tmp), "%s/../", bpf_get_tc_dir());
+ snprintf(rem, sizeof(rem), "%s/", todo);
+ sub = strtok(rem, "/");
+
+ while (sub) {
+ if (strlen(tmp) + strlen(sub) + 2 > PATH_MAX)
+ return -EINVAL;
+
+ strcat(tmp, sub);
+ strcat(tmp, "/");
+
+ ret = mkdir(tmp, S_IRWXU);
+ if (ret && errno != EEXIST) {
+ fprintf(stderr, "mkdir %s failed: %s\n", tmp,
+ strerror(errno));
+ return ret;
+ }
+
+ sub = strtok(NULL, "/");
+ }
+
+ return 0;
+}
+
+static int bpf_place_pinned(int fd, const char *name,
+ const struct bpf_elf_ctx *ctx, uint32_t pinning)
+{
+ char pathname[PATH_MAX];
+ const char *tmp;
+ int ret = 0;
+
+ if (bpf_no_pinning(ctx, pinning) || !bpf_get_tc_dir())
+ return 0;
+
+ if (pinning == PIN_OBJECT_NS)
+ ret = bpf_make_obj_path();
+ else if ((tmp = bpf_custom_pinning(ctx, pinning)))
+ ret = bpf_make_custom_path(tmp);
+ if (ret < 0)
+ return ret;
+
+ bpf_make_pathname(pathname, sizeof(pathname), name, ctx, pinning);
+ return bpf_obj_pin(fd, pathname);
+}
+
+static int bpf_prog_attach(const char *section,
+ const struct bpf_elf_prog *prog, bool verbose)
+{
+ int fd;
+
+ /* We can add pinning here later as well, same as bpf_map_attach(). */
+ errno = 0;
+ fd = bpf_prog_load(prog->type, prog->insns, prog->size,
+ prog->license);
+ if (fd < 0 || verbose) {
+ bpf_dump_error("Prog section \'%s\' (type:%u insns:%zu "
+ "license:\'%s\') %s%s (%d)!\n\n",
+ section, prog->type,
+ prog->size / sizeof(struct bpf_insn),
+ prog->license, fd < 0 ? "rejected: " :
+ "loaded", fd < 0 ? strerror(errno) : "",
+ fd < 0 ? errno : fd);
+ }
+
+ return fd;
+}
+
+static int bpf_map_attach(const char *name, const struct bpf_elf_map *map,
+ const struct bpf_elf_ctx *ctx, bool verbose)
+{
+ int fd, ret;
+
+ fd = bpf_probe_pinned(name, ctx, map->pinning);
+ if (fd > 0) {
+ ret = bpf_map_selfcheck_pinned(fd, map,
+ offsetof(struct bpf_elf_map,
+ id));
+ if (ret < 0) {
+ close(fd);
+ fprintf(stderr, "Map \'%s\' self-check failed!\n",
+ name);
+ return ret;
+ }
+ if (verbose)
+ fprintf(stderr, "Map \'%s\' loaded as pinned!\n",
+ name);
+ return fd;
+ }
+
+ errno = 0;
+ fd = bpf_map_create(map->type, map->size_key, map->size_value,
+ map->max_elem);
+ if (fd < 0 || verbose) {
+ bpf_dump_error("Map \'%s\' (type:%u id:%u pinning:%u "
+ "ksize:%u vsize:%u max-elems:%u) %s%s (%d)!\n",
+ name, map->type, map->id, map->pinning,
+ map->size_key, map->size_value, map->max_elem,
+ fd < 0 ? "rejected: " : "loaded", fd < 0 ?
+ strerror(errno) : "", fd < 0 ? errno : fd);
+ if (fd < 0)
+ return fd;
+ }
+
+ ret = bpf_place_pinned(fd, name, ctx, map->pinning);
+ if (ret < 0 && errno != EEXIST) {
+ fprintf(stderr, "Could not pin %s map: %s\n", name,
+ strerror(errno));
+ close(fd);
+ return ret;
+ }
+
+ return fd;
+}
+
+#define __ELF_ST_BIND(x) ((x) >> 4)
+#define __ELF_ST_TYPE(x) (((unsigned int) x) & 0xf)
+
+static const char *bpf_str_tab_name(const struct bpf_elf_ctx *ctx,
+ const GElf_Sym *sym)
+{
+ return ctx->str_tab->d_buf + sym->st_name;
+}
+
+static const char *bpf_map_fetch_name(struct bpf_elf_ctx *ctx, int which)
+{
+ GElf_Sym sym;
+ int i;
+
+ for (i = 0; i < ctx->sym_num; i++) {
+ if (gelf_getsym(ctx->sym_tab, i, &sym) != &sym)
+ continue;
+
+ if (__ELF_ST_BIND(sym.st_info) != STB_GLOBAL ||
+ __ELF_ST_TYPE(sym.st_info) != STT_NOTYPE ||
+ sym.st_shndx != ctx->sec_maps ||
+ sym.st_value / sizeof(struct bpf_elf_map) != which)
+ continue;
+
+ return bpf_str_tab_name(ctx, &sym);
+ }
+
+ return NULL;
+}
+
+static int bpf_maps_attach_all(struct bpf_elf_ctx *ctx)
+{
+ const char *map_name;
+ int i, fd;
+
+ for (i = 0; i < ctx->map_num; i++) {
+ map_name = bpf_map_fetch_name(ctx, i);
+ if (!map_name)
+ return -EIO;
+
+ fd = bpf_map_attach(map_name, &ctx->maps[i], ctx,
+ ctx->verbose);
+ if (fd < 0)
+ return fd;
+
+ ctx->map_fds[i] = fd;
+ }
+
+ return 0;
+}
+
+static int bpf_fill_section_data(struct bpf_elf_ctx *ctx, int section,
+ struct bpf_elf_sec_data *data)
+{
+ Elf_Data *sec_edata;
+ GElf_Shdr sec_hdr;
+ Elf_Scn *sec_fd;
+ char *sec_name;
+
+ memset(data, 0, sizeof(*data));
+
+ sec_fd = elf_getscn(ctx->elf_fd, section);
+ if (!sec_fd)
+ return -EINVAL;
+ if (gelf_getshdr(sec_fd, &sec_hdr) != &sec_hdr)
+ return -EIO;
+
+ sec_name = elf_strptr(ctx->elf_fd, ctx->elf_hdr.e_shstrndx,
+ sec_hdr.sh_name);
+ if (!sec_name || !sec_hdr.sh_size)
+ return -ENOENT;
+
+ sec_edata = elf_getdata(sec_fd, NULL);
+ if (!sec_edata || elf_getdata(sec_fd, sec_edata))
+ return -EIO;
+
+ memcpy(&data->sec_hdr, &sec_hdr, sizeof(sec_hdr));
+
+ data->sec_name = sec_name;
+ data->sec_data = sec_edata;
+ return 0;
+}
+
+static int bpf_fetch_maps(struct bpf_elf_ctx *ctx, int section,
+ struct bpf_elf_sec_data *data)
+{
+ if (data->sec_data->d_size % sizeof(struct bpf_elf_map) != 0)
+ return -EINVAL;
+
+ ctx->map_num = data->sec_data->d_size / sizeof(struct bpf_elf_map);
+ ctx->sec_maps = section;
+ ctx->sec_done[section] = true;
+
+ if (ctx->map_num > ARRAY_SIZE(ctx->map_fds)) {
+ fprintf(stderr, "Too many BPF maps in ELF section!\n");
+ return -ENOMEM;
+ }
+
+ memcpy(ctx->maps, data->sec_data->d_buf, data->sec_data->d_size);
+ return 0;
+}
+
+static int bpf_fetch_license(struct bpf_elf_ctx *ctx, int section,
+ struct bpf_elf_sec_data *data)
+{
+ if (data->sec_data->d_size > sizeof(ctx->license))
+ return -ENOMEM;
+
+ memcpy(ctx->license, data->sec_data->d_buf, data->sec_data->d_size);
+ ctx->sec_done[section] = true;
+ return 0;
+}
+
+static int bpf_fetch_symtab(struct bpf_elf_ctx *ctx, int section,
+ struct bpf_elf_sec_data *data)
+{
+ ctx->sym_tab = data->sec_data;
+ ctx->sym_num = data->sec_hdr.sh_size / data->sec_hdr.sh_entsize;
+ ctx->sec_done[section] = true;
+ return 0;
+}
+
+static int bpf_fetch_strtab(struct bpf_elf_ctx *ctx, int section,
+ struct bpf_elf_sec_data *data)
+{
+ ctx->str_tab = data->sec_data;
+ ctx->sec_done[section] = true;
+ return 0;
+}
+
+static int bpf_fetch_ancillary(struct bpf_elf_ctx *ctx)
+{
+ struct bpf_elf_sec_data data;
+ int i, ret = -1;
+
+ for (i = 1; i < ctx->elf_hdr.e_shnum; i++) {
+ ret = bpf_fill_section_data(ctx, i, &data);
+ if (ret < 0)
+ continue;
+
+ if (data.sec_hdr.sh_type == SHT_PROGBITS &&
+ !strcmp(data.sec_name, ELF_SECTION_MAPS))
+ ret = bpf_fetch_maps(ctx, i, &data);
+ else if (data.sec_hdr.sh_type == SHT_PROGBITS &&
+ !strcmp(data.sec_name, ELF_SECTION_LICENSE))
+ ret = bpf_fetch_license(ctx, i, &data);
+ else if (data.sec_hdr.sh_type == SHT_SYMTAB &&
+ !strcmp(data.sec_name, ".symtab"))
+ ret = bpf_fetch_symtab(ctx, i, &data);
+ else if (data.sec_hdr.sh_type == SHT_STRTAB &&
+ !strcmp(data.sec_name, ".strtab"))
+ ret = bpf_fetch_strtab(ctx, i, &data);
+ if (ret < 0) {
+ fprintf(stderr, "Error parsing section %d! Perhaps"
+ "check with readelf -a?\n", i);
+ break;
+ }
+ }
+
+ if (ctx->sym_tab && ctx->str_tab && ctx->sec_maps) {
+ ret = bpf_maps_attach_all(ctx);
+ if (ret < 0) {
+ fprintf(stderr, "Error loading maps into kernel!\n");
+ return ret;
+ }
+ }
+
+ return ret;
+}
+
+static int bpf_fetch_prog(struct bpf_elf_ctx *ctx, const char *section)
+{
+ struct bpf_elf_sec_data data;
+ struct bpf_elf_prog prog;
+ int ret, i, fd = -1;
+
+ for (i = 1; i < ctx->elf_hdr.e_shnum; i++) {
+ if (ctx->sec_done[i])
+ continue;
+
+ ret = bpf_fill_section_data(ctx, i, &data);
+ if (ret < 0 ||
+ !(data.sec_hdr.sh_type == SHT_PROGBITS &&
+ data.sec_hdr.sh_flags & SHF_EXECINSTR &&
+ !strcmp(data.sec_name, section)))
+ continue;
+
+ memset(&prog, 0, sizeof(prog));
+ prog.type = ctx->type;
+ prog.insns = data.sec_data->d_buf;
+ prog.size = data.sec_data->d_size;
+ prog.license = ctx->license;
+
+ fd = bpf_prog_attach(section, &prog, ctx->verbose);
+ if (fd < 0)
+ continue;
+
+ ctx->sec_done[i] = true;
+ break;
+ }
+
+ return fd;
+}
+
+static int bpf_apply_relo_data(struct bpf_elf_ctx *ctx,
+ struct bpf_elf_sec_data *data_relo,
+ struct bpf_elf_sec_data *data_insn)
+{
+ Elf_Data *idata = data_insn->sec_data;
+ GElf_Shdr *rhdr = &data_relo->sec_hdr;
+ int relo_ent, relo_num = rhdr->sh_size / rhdr->sh_entsize;
+ struct bpf_insn *insns = idata->d_buf;
+ unsigned int num_insns = idata->d_size / sizeof(*insns);
+
+ for (relo_ent = 0; relo_ent < relo_num; relo_ent++) {
+ unsigned int ioff, rmap;
+ GElf_Rel relo;
+ GElf_Sym sym;
+
+ if (gelf_getrel(data_relo->sec_data, relo_ent, &relo) != &relo)
+ return -EIO;
+
+ ioff = relo.r_offset / sizeof(struct bpf_insn);
+ if (ioff >= num_insns ||
+ insns[ioff].code != (BPF_LD | BPF_IMM | BPF_DW))
+ return -EINVAL;
+
+ if (gelf_getsym(ctx->sym_tab, GELF_R_SYM(relo.r_info), &sym) != &sym)
+ return -EIO;
+
+ rmap = sym.st_value / sizeof(struct bpf_elf_map);
+ if (rmap >= ARRAY_SIZE(ctx->map_fds))
+ return -EINVAL;
+ if (!ctx->map_fds[rmap])
+ return -EINVAL;
+
+ if (ctx->verbose)
+ fprintf(stderr, "Map \'%s\' (%d) injected into prog "
+ "section \'%s\' at offset %u!\n",
+ bpf_str_tab_name(ctx, &sym), ctx->map_fds[rmap],
+ data_insn->sec_name, ioff);
+
+ insns[ioff].src_reg = BPF_PSEUDO_MAP_FD;
+ insns[ioff].imm = ctx->map_fds[rmap];
+ }
+
+ return 0;
+}
+
+static int bpf_fetch_prog_relo(struct bpf_elf_ctx *ctx, const char *section)
+{
+ struct bpf_elf_sec_data data_relo, data_insn;
+ struct bpf_elf_prog prog;
+ int ret, idx, i, fd = -1;
+
+ for (i = 1; i < ctx->elf_hdr.e_shnum; i++) {
+ ret = bpf_fill_section_data(ctx, i, &data_relo);
+ if (ret < 0 || data_relo.sec_hdr.sh_type != SHT_REL)
+ continue;
+
+ idx = data_relo.sec_hdr.sh_info;
+ ret = bpf_fill_section_data(ctx, idx, &data_insn);
+ if (ret < 0 ||
+ !(data_insn.sec_hdr.sh_type == SHT_PROGBITS &&
+ data_insn.sec_hdr.sh_flags & SHF_EXECINSTR &&
+ !strcmp(data_insn.sec_name, section)))
+ continue;
+
+ ret = bpf_apply_relo_data(ctx, &data_relo, &data_insn);
+ if (ret < 0)
+ continue;
+
+ memset(&prog, 0, sizeof(prog));
+ prog.type = ctx->type;
+ prog.insns = data_insn.sec_data->d_buf;
+ prog.size = data_insn.sec_data->d_size;
+ prog.license = ctx->license;
+
+ fd = bpf_prog_attach(section, &prog, ctx->verbose);
+ if (fd < 0)
+ continue;
+
+ ctx->sec_done[i] = true;
+ ctx->sec_done[idx] = true;
+ break;
+ }
+
+ return fd;
+}
+
+static int bpf_fetch_prog_sec(struct bpf_elf_ctx *ctx, const char *section)
+{
+ int ret = -1;
+
+ if (ctx->sym_tab)
+ ret = bpf_fetch_prog_relo(ctx, section);
+ if (ret < 0)
+ ret = bpf_fetch_prog(ctx, section);
+
+ return ret;
+}
+
+static int bpf_find_map_by_id(struct bpf_elf_ctx *ctx, uint32_t id)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(ctx->map_fds); i++)
+ if (ctx->map_fds[i] && ctx->maps[i].id == id &&
+ ctx->maps[i].type == BPF_MAP_TYPE_PROG_ARRAY)
+ return i;
+ return -1;
+}
+
+static int bpf_fill_prog_arrays(struct bpf_elf_ctx *ctx)
+{
+ struct bpf_elf_sec_data data;
+ uint32_t map_id, key_id;
+ int fd, i, ret, idx;
+
+ for (i = 1; i < ctx->elf_hdr.e_shnum; i++) {
+ if (ctx->sec_done[i])
+ continue;
+
+ ret = bpf_fill_section_data(ctx, i, &data);
+ if (ret < 0)
+ continue;
+
+ ret = sscanf(data.sec_name, "%i/%i", &map_id, &key_id);
+ if (ret != 2)
+ continue;
+
+ idx = bpf_find_map_by_id(ctx, map_id);
+ if (idx < 0)
+ continue;
+
+ fd = bpf_fetch_prog_sec(ctx, data.sec_name);
+ if (fd < 0)
+ return -EIO;
+
+ ret = bpf_map_update(ctx->map_fds[idx], &key_id,
+ &fd, BPF_ANY);
+ if (ret < 0)
+ return -ENOENT;
+
+ ctx->sec_done[i] = true;
+ }
+
+ return 0;
+}
+
+static void bpf_save_finfo(struct bpf_elf_ctx *ctx)
+{
+ struct stat st;
+ int ret;
+
+ memset(&ctx->stat, 0, sizeof(ctx->stat));
+
+ ret = fstat(ctx->obj_fd, &st);
+ if (ret < 0) {
+ fprintf(stderr, "Stat of elf file failed: %s\n",
+ strerror(errno));
+ return;
+ }
+
+ ctx->stat.st_dev = st.st_dev;
+ ctx->stat.st_ino = st.st_ino;
+}
+
+static int bpf_read_pin_mapping(FILE *fp, uint32_t *id, char *path)
+{
+ char buff[PATH_MAX];
+
+ while (fgets(buff, sizeof(buff), fp)) {
+ char *ptr = buff;
+
+ while (*ptr == ' ' || *ptr == '\t')
+ ptr++;
+
+ if (*ptr == '#' || *ptr == '\n' || *ptr == 0)
+ continue;
+
+ if (sscanf(ptr, "%i %s\n", id, path) != 2 &&
+ sscanf(ptr, "%i %s #", id, path) != 2) {
+ strcpy(path, ptr);
+ return -1;
+ }
+
+ return 1;
+ }
+
+ return 0;
+}
+
+static bool bpf_pinning_reserved(uint32_t pinning)
+{
+ switch (pinning) {
+ case PIN_NONE:
+ case PIN_OBJECT_NS:
+ case PIN_GLOBAL_NS:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static void bpf_hash_init(struct bpf_elf_ctx *ctx, const char *db_file)
+{
+ struct bpf_hash_entry *entry;
+ char subpath[PATH_MAX];
+ uint32_t pinning;
+ FILE *fp;
+ int ret;
+
+ fp = fopen(db_file, "r");
+ if (!fp)
+ return;
+
+ memset(subpath, 0, sizeof(subpath));
+ while ((ret = bpf_read_pin_mapping(fp, &pinning, subpath))) {
+ if (ret == -1) {
+ fprintf(stderr, "Database %s is corrupted at: %s\n",
+ db_file, subpath);
+ fclose(fp);
+ return;
+ }
+
+ if (bpf_pinning_reserved(pinning)) {
+ fprintf(stderr, "Database %s, id %u is reserved - "
+ "ignoring!\n", db_file, pinning);
+ continue;
+ }
+
+ entry = malloc(sizeof(*entry));
+ if (!entry) {
+ fprintf(stderr, "No memory left for db entry!\n");
+ continue;
+ }
+
+ entry->pinning = pinning;
+ entry->subpath = strdup(subpath);
+ if (!entry->subpath) {
+ fprintf(stderr, "No memory left for db entry!\n");
+ free(entry);
+ continue;
+ }
+
+ entry->next = ctx->ht[pinning & (ARRAY_SIZE(ctx->ht) - 1)];
+ ctx->ht[pinning & (ARRAY_SIZE(ctx->ht) - 1)] = entry;
+ }
+
+ fclose(fp);
+}
+
+static void bpf_hash_destroy(struct bpf_elf_ctx *ctx)
+{
+ struct bpf_hash_entry *entry;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(ctx->ht); i++) {
+ while ((entry = ctx->ht[i]) != NULL) {
+ ctx->ht[i] = entry->next;
+ free((char *)entry->subpath);
+ free(entry);
+ }
+ }
+}
+
+static int bpf_elf_check_ehdr(const struct bpf_elf_ctx *ctx)
+{
+ if (ctx->elf_hdr.e_type != ET_REL ||
+ ctx->elf_hdr.e_machine != 0 ||
+ ctx->elf_hdr.e_version != EV_CURRENT) {
+ fprintf(stderr, "ELF format error, ELF file not for eBPF?\n");
+ return -EINVAL;
+ }
+
+ switch (ctx->elf_hdr.e_ident[EI_DATA]) {
+ default:
+ fprintf(stderr, "ELF format error, wrong endianness info?\n");
+ return -EINVAL;
+ case ELFDATA2LSB:
+ if (htons(1) == 1) {
+ fprintf(stderr,
+ "We are big endian, eBPF object is little endian!\n");
+ return -EIO;
+ }
+ break;
+ case ELFDATA2MSB:
+ if (htons(1) != 1) {
+ fprintf(stderr,
+ "We are little endian, eBPF object is big endian!\n");
+ return -EIO;
+ }
+ break;
+ }
+
+ return 0;
+}
+
+static int bpf_elf_ctx_init(struct bpf_elf_ctx *ctx, const char *pathname,
+ enum bpf_prog_type type, bool verbose)
+{
+ int ret = -EINVAL;
+
+ if (elf_version(EV_CURRENT) == EV_NONE ||
+ bpf_init_env(pathname))
+ return ret;
+
+ memset(ctx, 0, sizeof(*ctx));
+ ctx->verbose = verbose;
+ ctx->type = type;
+
+ ctx->obj_fd = open(pathname, O_RDONLY);
+ if (ctx->obj_fd < 0)
+ return ctx->obj_fd;
+
+ ctx->elf_fd = elf_begin(ctx->obj_fd, ELF_C_READ, NULL);
+ if (!ctx->elf_fd) {
+ ret = -EINVAL;
+ goto out_fd;
+ }
+
+ if (elf_kind(ctx->elf_fd) != ELF_K_ELF) {
+ ret = -EINVAL;
+ goto out_fd;
+ }
+
+ if (gelf_getehdr(ctx->elf_fd, &ctx->elf_hdr) !=
+ &ctx->elf_hdr) {
+ ret = -EIO;
+ goto out_elf;
+ }
+
+ ret = bpf_elf_check_ehdr(ctx);
+ if (ret < 0)
+ goto out_elf;
+
+ ctx->sec_done = calloc(ctx->elf_hdr.e_shnum,
+ sizeof(*(ctx->sec_done)));
+ if (!ctx->sec_done) {
+ ret = -ENOMEM;
+ goto out_elf;
+ }
+
+ bpf_save_finfo(ctx);
+ bpf_hash_init(ctx, CONFDIR "/bpf_pinning");
+
+ return 0;
+out_elf:
+ elf_end(ctx->elf_fd);
+out_fd:
+ close(ctx->obj_fd);
+ return ret;
+}
+
+static int bpf_maps_count(struct bpf_elf_ctx *ctx)
+{
+ int i, count = 0;
+
+ for (i = 0; i < ARRAY_SIZE(ctx->map_fds); i++) {
+ if (!ctx->map_fds[i])
+ break;
+ count++;
+ }
+
+ return count;
+}
+
+static void bpf_maps_teardown(struct bpf_elf_ctx *ctx)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(ctx->map_fds); i++) {
+ if (ctx->map_fds[i])
+ close(ctx->map_fds[i]);
+ }
+}
+
+static void bpf_elf_ctx_destroy(struct bpf_elf_ctx *ctx, bool failure)
+{
+ if (failure)
+ bpf_maps_teardown(ctx);
+
+ bpf_hash_destroy(ctx);
+ free(ctx->sec_done);
+ elf_end(ctx->elf_fd);
+ close(ctx->obj_fd);
+}
+
+static struct bpf_elf_ctx __ctx;
+
+static int bpf_obj_open(const char *pathname, enum bpf_prog_type type,
+ const char *section, bool verbose)
+{
+ struct bpf_elf_ctx *ctx = &__ctx;
+ int fd = 0, ret;
+
+ ret = bpf_elf_ctx_init(ctx, pathname, type, verbose);
+ if (ret < 0) {
+ fprintf(stderr, "Cannot initialize ELF context!\n");
+ return ret;
+ }
+
+ ret = bpf_fetch_ancillary(ctx);
+ if (ret < 0) {
+ fprintf(stderr, "Error fetching ELF ancillary data!\n");
+ goto out;
+ }
+
+ fd = bpf_fetch_prog_sec(ctx, section);
+ if (fd < 0) {
+ fprintf(stderr, "Error fetching program/map!\n");
+ ret = fd;
+ goto out;
+ }
+
+ ret = bpf_fill_prog_arrays(ctx);
+ if (ret < 0)
+ fprintf(stderr, "Error filling program arrays!\n");
+out:
+ bpf_elf_ctx_destroy(ctx, ret < 0);
+ if (ret < 0) {
+ if (fd)
+ close(fd);
+ return ret;
+ }
+
+ return fd;
+}
+
+static int
+bpf_map_set_send(int fd, struct sockaddr_un *addr, unsigned int addr_len,
+ const struct bpf_map_data *aux, unsigned int entries)
+{
+ struct bpf_map_set_msg msg;
+ int *cmsg_buf, min_fd;
+ char *amsg_buf;
+ int i;
+
+ memset(&msg, 0, sizeof(msg));
+
+ msg.aux.uds_ver = BPF_SCM_AUX_VER;
+ msg.aux.num_ent = entries;
+
+ strncpy(msg.aux.obj_name, aux->obj, sizeof(msg.aux.obj_name));
+ memcpy(&msg.aux.obj_st, aux->st, sizeof(msg.aux.obj_st));
+
+ cmsg_buf = bpf_map_set_init(&msg, addr, addr_len);
+ amsg_buf = (char *)msg.aux.ent;
+
+ for (i = 0; i < entries; i += min_fd) {
+ int ret;
+
+ min_fd = min(BPF_SCM_MAX_FDS * 1U, entries - i);
+ bpf_map_set_init_single(&msg, min_fd);
+
+ memcpy(cmsg_buf, &aux->fds[i], sizeof(aux->fds[0]) * min_fd);
+ memcpy(amsg_buf, &aux->ent[i], sizeof(aux->ent[0]) * min_fd);
+
+ ret = sendmsg(fd, &msg.hdr, 0);
+ if (ret <= 0)
+ return ret ? : -1;
+ }
+
+ return 0;
+}
+
+static int
+bpf_map_set_recv(int fd, int *fds, struct bpf_map_aux *aux,
+ unsigned int entries)
+{
+ struct bpf_map_set_msg msg;
+ int *cmsg_buf, min_fd;
+ char *amsg_buf, *mmsg_buf;
+ unsigned int needed = 1;
+ int i;
+
+ cmsg_buf = bpf_map_set_init(&msg, NULL, 0);
+ amsg_buf = (char *)msg.aux.ent;
+ mmsg_buf = (char *)&msg.aux;
+
+ for (i = 0; i < min(entries, needed); i += min_fd) {
+ struct cmsghdr *cmsg;
+ int ret;
+
+ min_fd = min(entries, entries - i);
+ bpf_map_set_init_single(&msg, min_fd);
+
+ ret = recvmsg(fd, &msg.hdr, 0);
+ if (ret <= 0)
+ return ret ? : -1;
+
+ cmsg = CMSG_FIRSTHDR(&msg.hdr);
+ if (!cmsg || cmsg->cmsg_type != SCM_RIGHTS)
+ return -EINVAL;
+ if (msg.hdr.msg_flags & MSG_CTRUNC)
+ return -EIO;
+ if (msg.aux.uds_ver != BPF_SCM_AUX_VER)
+ return -ENOSYS;
+
+ min_fd = (cmsg->cmsg_len - sizeof(*cmsg)) / sizeof(fd);
+ if (min_fd > entries || min_fd <= 0)
+ return -EINVAL;
+
+ memcpy(&fds[i], cmsg_buf, sizeof(fds[0]) * min_fd);
+ memcpy(&aux->ent[i], amsg_buf, sizeof(aux->ent[0]) * min_fd);
+ memcpy(aux, mmsg_buf, offsetof(struct bpf_map_aux, ent));
+
+ needed = aux->num_ent;
+ }
+
+ return 0;
+}
+
+int bpf_send_map_fds(const char *path, const char *obj)
+{
+ struct bpf_elf_ctx *ctx = &__ctx;
+ struct sockaddr_un addr;
+ struct bpf_map_data bpf_aux;
+ int fd, ret;
+
+ fd = socket(AF_UNIX, SOCK_DGRAM, 0);
+ if (fd < 0) {
+ fprintf(stderr, "Cannot open socket: %s\n",
+ strerror(errno));
+ return -1;
+ }
+
+ memset(&addr, 0, sizeof(addr));
+ addr.sun_family = AF_UNIX;
+ strncpy(addr.sun_path, path, sizeof(addr.sun_path));
+
+ ret = connect(fd, (struct sockaddr *)&addr, sizeof(addr));
+ if (ret < 0) {
+ fprintf(stderr, "Cannot connect to %s: %s\n",
+ path, strerror(errno));
+ return -1;
+ }
+
+ memset(&bpf_aux, 0, sizeof(bpf_aux));
+
+ bpf_aux.fds = ctx->map_fds;
+ bpf_aux.ent = ctx->maps;
+ bpf_aux.st = &ctx->stat;
+ bpf_aux.obj = obj;
+
+ ret = bpf_map_set_send(fd, &addr, sizeof(addr), &bpf_aux,
+ bpf_maps_count(ctx));
+ if (ret < 0)
+ fprintf(stderr, "Cannot send fds to %s: %s\n",
+ path, strerror(errno));
+
+ bpf_maps_teardown(ctx);
+ close(fd);
+ return ret;
+}
+
+int bpf_recv_map_fds(const char *path, int *fds, struct bpf_map_aux *aux,
+ unsigned int entries)
+{
+ struct sockaddr_un addr;
+ int fd, ret;
+
+ fd = socket(AF_UNIX, SOCK_DGRAM, 0);
+ if (fd < 0) {
+ fprintf(stderr, "Cannot open socket: %s\n",
+ strerror(errno));
+ return -1;
+ }
+
+ memset(&addr, 0, sizeof(addr));
+ addr.sun_family = AF_UNIX;
+ strncpy(addr.sun_path, path, sizeof(addr.sun_path));
+
+ ret = bind(fd, (struct sockaddr *)&addr, sizeof(addr));
+ if (ret < 0) {
+ fprintf(stderr, "Cannot bind to socket: %s\n",
+ strerror(errno));
+ return -1;
+ }
+
+ ret = bpf_map_set_recv(fd, fds, aux, entries);
+ if (ret < 0)
+ fprintf(stderr, "Cannot recv fds from %s: %s\n",
+ path, strerror(errno));
+
+ unlink(addr.sun_path);
+ close(fd);
+ return ret;
+}
+#endif /* HAVE_ELF */
diff --git a/iproute2/tc/tc_bpf.h b/iproute2/tc/tc_bpf.h
new file mode 100644
index 0000000..526d0b1
--- /dev/null
+++ b/iproute2/tc/tc_bpf.h
@@ -0,0 +1,79 @@
+/*
+ * tc_bpf.h BPF common code
+ *
+ * This program is free software; you can distribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Daniel Borkmann <dborkman@redhat.com>
+ * Jiri Pirko <jiri@resnulli.us>
+ */
+
+#ifndef _TC_BPF_H_
+#define _TC_BPF_H_ 1
+
+#include <linux/netlink.h>
+#include <linux/bpf.h>
+#include <linux/magic.h>
+
+#include "utils.h"
+#include "bpf_scm.h"
+
+enum {
+ BPF_NLA_OPS_LEN = 0,
+ BPF_NLA_OPS,
+ BPF_NLA_FD,
+ BPF_NLA_NAME,
+ __BPF_NLA_MAX,
+};
+
+#define BPF_NLA_MAX __BPF_NLA_MAX
+
+#define BPF_ENV_UDS "TC_BPF_UDS"
+#define BPF_ENV_MNT "TC_BPF_MNT"
+#define BPF_ENV_NOLOG "TC_BPF_NOLOG"
+
+#ifndef BPF_FS_MAGIC
+# define BPF_FS_MAGIC 0xcafe4a11
+#endif
+
+#define BPF_DIR_MNT "/sys/fs/bpf"
+
+#define BPF_DIR_TC "tc"
+#define BPF_DIR_GLOBALS "globals"
+
+#ifndef TRACEFS_MAGIC
+# define TRACEFS_MAGIC 0x74726163
+#endif
+
+#define TRACE_DIR_MNT "/sys/kernel/tracing"
+
+int bpf_trace_pipe(void);
+const char *bpf_default_section(const enum bpf_prog_type type);
+
+int bpf_parse_common(int *ptr_argc, char ***ptr_argv, const int *nla_tbl,
+ enum bpf_prog_type type, const char **ptr_object,
+ const char **ptr_uds_name, struct nlmsghdr *n);
+int bpf_graft_map(const char *map_path, uint32_t *key, int argc, char **argv);
+
+void bpf_print_ops(FILE *f, struct rtattr *bpf_ops, __u16 len);
+
+#ifdef HAVE_ELF
+int bpf_send_map_fds(const char *path, const char *obj);
+int bpf_recv_map_fds(const char *path, int *fds, struct bpf_map_aux *aux,
+ unsigned int entries);
+#else
+static inline int bpf_send_map_fds(const char *path, const char *obj)
+{
+ return 0;
+}
+
+static inline int bpf_recv_map_fds(const char *path, int *fds,
+ struct bpf_map_aux *aux,
+ unsigned int entries)
+{
+ return -1;
+}
+#endif /* HAVE_ELF */
+#endif /* _TC_BPF_H_ */
diff --git a/iproute2/tc/tc_cbq.c b/iproute2/tc/tc_cbq.c
new file mode 100644
index 0000000..0bb262e
--- /dev/null
+++ b/iproute2/tc/tc_cbq.c
@@ -0,0 +1,57 @@
+/*
+ * tc_cbq.c CBQ maintanance routines.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <math.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "tc_core.h"
+#include "tc_cbq.h"
+
+unsigned tc_cbq_calc_maxidle(unsigned bndw, unsigned rate, unsigned avpkt,
+ int ewma_log, unsigned maxburst)
+{
+ double maxidle;
+ double g = 1.0 - 1.0/(1<<ewma_log);
+ double xmt = (double)avpkt/bndw;
+
+ maxidle = xmt*(1-g);
+ if (bndw != rate && maxburst) {
+ double vxmt = (double)avpkt/rate - xmt;
+ vxmt *= (pow(g, -(double)maxburst) - 1);
+ if (vxmt > maxidle)
+ maxidle = vxmt;
+ }
+ return tc_core_time2tick(maxidle*(1<<ewma_log)*TIME_UNITS_PER_SEC);
+}
+
+unsigned tc_cbq_calc_offtime(unsigned bndw, unsigned rate, unsigned avpkt,
+ int ewma_log, unsigned minburst)
+{
+ double g = 1.0 - 1.0/(1<<ewma_log);
+ double offtime = (double)avpkt/rate - (double)avpkt/bndw;
+
+ if (minburst == 0)
+ return 0;
+ if (minburst == 1)
+ offtime *= pow(g, -(double)minburst) - 1;
+ else
+ offtime *= 1 + (pow(g, -(double)(minburst-1)) - 1)/(1-g);
+ return tc_core_time2tick(offtime*TIME_UNITS_PER_SEC);
+}
diff --git a/iproute2/tc/tc_cbq.h b/iproute2/tc/tc_cbq.h
new file mode 100644
index 0000000..8f95649
--- /dev/null
+++ b/iproute2/tc/tc_cbq.h
@@ -0,0 +1,9 @@
+#ifndef _TC_CBQ_H_
+#define _TC_CBQ_H_ 1
+
+unsigned tc_cbq_calc_maxidle(unsigned bndw, unsigned rate, unsigned avpkt,
+ int ewma_log, unsigned maxburst);
+unsigned tc_cbq_calc_offtime(unsigned bndw, unsigned rate, unsigned avpkt,
+ int ewma_log, unsigned minburst);
+
+#endif
diff --git a/iproute2/tc/tc_class.c b/iproute2/tc/tc_class.c
new file mode 100644
index 0000000..3acd030
--- /dev/null
+++ b/iproute2/tc/tc_class.c
@@ -0,0 +1,500 @@
+/*
+ * tc_class.c "tc class".
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <math.h>
+
+#include "utils.h"
+#include "tc_util.h"
+#include "tc_common.h"
+#include "hlist.h"
+
+struct graph_node {
+ struct hlist_node hlist;
+ __u32 id;
+ __u32 parent_id;
+ struct graph_node *parent_node;
+ struct graph_node *right_node;
+ void *data;
+ int data_len;
+ int nodes_count;
+};
+
+static struct hlist_head cls_list = {};
+static struct hlist_head root_cls_list = {};
+
+static void usage(void);
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: tc class [ add | del | change | replace | show ] dev STRING\n");
+ fprintf(stderr, " [ classid CLASSID ] [ root | parent CLASSID ]\n");
+ fprintf(stderr, " [ [ QDISC_KIND ] [ help | OPTIONS ] ]\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, " tc class show [ dev STRING ] [ root | parent CLASSID ]\n");
+ fprintf(stderr, "Where:\n");
+ fprintf(stderr, "QDISC_KIND := { prio | cbq | etc. }\n");
+ fprintf(stderr, "OPTIONS := ... try tc class add <desired QDISC_KIND> help\n");
+ return;
+}
+
+static int tc_class_modify(int cmd, unsigned flags, int argc, char **argv)
+{
+ struct {
+ struct nlmsghdr n;
+ struct tcmsg t;
+ char buf[4096];
+ } req;
+ struct qdisc_util *q = NULL;
+ struct tc_estimator est;
+ char d[16];
+ char k[16];
+
+ memset(&req, 0, sizeof(req));
+ memset(&est, 0, sizeof(est));
+ memset(d, 0, sizeof(d));
+ memset(k, 0, sizeof(k));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST|flags;
+ req.n.nlmsg_type = cmd;
+ req.t.tcm_family = AF_UNSPEC;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ if (d[0])
+ duparg("dev", *argv);
+ strncpy(d, *argv, sizeof(d)-1);
+ } else if (strcmp(*argv, "classid") == 0) {
+ __u32 handle;
+ NEXT_ARG();
+ if (req.t.tcm_handle)
+ duparg("classid", *argv);
+ if (get_tc_classid(&handle, *argv))
+ invarg("invalid class ID", *argv);
+ req.t.tcm_handle = handle;
+ } else if (strcmp(*argv, "handle") == 0) {
+ fprintf(stderr, "Error: try \"classid\" instead of \"handle\"\n");
+ return -1;
+ } else if (strcmp(*argv, "root") == 0) {
+ if (req.t.tcm_parent) {
+ fprintf(stderr, "Error: \"root\" is duplicate parent ID.\n");
+ return -1;
+ }
+ req.t.tcm_parent = TC_H_ROOT;
+ } else if (strcmp(*argv, "parent") == 0) {
+ __u32 handle;
+ NEXT_ARG();
+ if (req.t.tcm_parent)
+ duparg("parent", *argv);
+ if (get_tc_classid(&handle, *argv))
+ invarg("invalid parent ID", *argv);
+ req.t.tcm_parent = handle;
+ } else if (matches(*argv, "estimator") == 0) {
+ if (parse_estimator(&argc, &argv, &est))
+ return -1;
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ } else {
+ strncpy(k, *argv, sizeof(k)-1);
+
+ q = get_qdisc_kind(k);
+ argc--; argv++;
+ break;
+ }
+ argc--; argv++;
+ }
+
+ if (k[0])
+ addattr_l(&req.n, sizeof(req), TCA_KIND, k, strlen(k)+1);
+ if (est.ewma_log)
+ addattr_l(&req.n, sizeof(req), TCA_RATE, &est, sizeof(est));
+
+ if (q) {
+ if (q->parse_copt == NULL) {
+ fprintf(stderr, "Error: Qdisc \"%s\" is classless.\n", k);
+ return 1;
+ }
+ if (q->parse_copt(q, argc, argv, &req.n))
+ return 1;
+ } else {
+ if (argc) {
+ if (matches(*argv, "help") == 0)
+ usage();
+ fprintf(stderr, "Garbage instead of arguments \"%s ...\". Try \"tc class help\".", *argv);
+ return -1;
+ }
+ }
+
+ if (d[0]) {
+ ll_init_map(&rth);
+
+ if ((req.t.tcm_ifindex = ll_name_to_index(d)) == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", d);
+ return 1;
+ }
+ }
+
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ return 2;
+
+ return 0;
+}
+
+int filter_ifindex;
+__u32 filter_qdisc;
+__u32 filter_classid;
+
+static void graph_node_add(__u32 parent_id, __u32 id, void *data,
+ int len)
+{
+ struct graph_node *node = malloc(sizeof(struct graph_node));
+
+ memset(node, 0, sizeof(*node));
+ node->id = id;
+ node->parent_id = parent_id;
+
+ if (data && len) {
+ node->data = malloc(len);
+ node->data_len = len;
+ memcpy(node->data, data, len);
+ }
+
+ if (parent_id == TC_H_ROOT)
+ hlist_add_head(&node->hlist, &root_cls_list);
+ else
+ hlist_add_head(&node->hlist, &cls_list);
+}
+
+static void graph_indent(char *buf, struct graph_node *node, int is_newline,
+ int add_spaces)
+{
+ char spaces[100] = {0};
+
+ while (node && node->parent_node) {
+ node->parent_node->right_node = node;
+ node = node->parent_node;
+ }
+ while (node && node->right_node) {
+ if (node->hlist.next)
+ strcat(buf, "| ");
+ else
+ strcat(buf, " ");
+
+ node = node->right_node;
+ }
+
+ if (is_newline) {
+ if (node->hlist.next && node->nodes_count)
+ strcat(buf, "| |");
+ else if (node->hlist.next)
+ strcat(buf, "| ");
+ else if (node->nodes_count)
+ strcat(buf, " |");
+ else if (!node->hlist.next)
+ strcat(buf, " ");
+ }
+ if (add_spaces > 0) {
+ sprintf(spaces, "%-*s", add_spaces, "");
+ strcat(buf, spaces);
+ }
+}
+
+static void graph_cls_show(FILE *fp, char *buf, struct hlist_head *root_list,
+ int level)
+{
+ struct hlist_node *n, *tmp_cls;
+ char cls_id_str[256] = {};
+ struct rtattr *tb[TCA_MAX + 1] = {};
+ struct qdisc_util *q;
+ char str[100] = {};
+
+ hlist_for_each_safe(n, tmp_cls, root_list) {
+ struct hlist_node *c, *tmp_chld;
+ struct hlist_head children = {};
+ struct graph_node *cls = container_of(n, struct graph_node,
+ hlist);
+
+ hlist_for_each_safe(c, tmp_chld, &cls_list) {
+ struct graph_node *child = container_of(c,
+ struct graph_node, hlist);
+
+ if (cls->id == child->parent_id) {
+ hlist_del(c);
+ hlist_add_head(c, &children);
+ cls->nodes_count++;
+ child->parent_node = cls;
+ }
+ }
+
+ graph_indent(buf, cls, 0, 0);
+
+ print_tc_classid(cls_id_str, sizeof(cls_id_str), cls->id);
+ sprintf(str, "+---(%s)", cls_id_str);
+ strcat(buf, str);
+
+ parse_rtattr(tb, TCA_MAX, (struct rtattr *)cls->data,
+ cls->data_len);
+
+ if (tb[TCA_KIND] == NULL) {
+ strcat(buf, " [unknown qdisc kind] ");
+ } else {
+ const char *kind = rta_getattr_str(tb[TCA_KIND]);
+
+ sprintf(str, " %s ", kind);
+ strcat(buf, str);
+ fprintf(fp, "%s", buf);
+ buf[0] = '\0';
+
+ q = get_qdisc_kind(kind);
+ if (q && q->print_copt) {
+ q->print_copt(q, fp, tb[TCA_OPTIONS]);
+ }
+ if (q && show_stats) {
+ int cls_indent = strlen(q->id) - 2 +
+ strlen(cls_id_str);
+ struct rtattr *stats = NULL;
+
+ graph_indent(buf, cls, 1, cls_indent);
+
+ if (tb[TCA_STATS] || tb[TCA_STATS2]) {
+ fprintf(fp, "\n");
+ print_tcstats_attr(fp, tb, buf, &stats);
+ buf[0] = '\0';
+ }
+ if (cls->hlist.next || cls->nodes_count) {
+ strcat(buf, "\n");
+ graph_indent(buf, cls, 1, 0);
+ }
+ }
+ }
+ free(cls->data);
+ fprintf(fp, "%s\n", buf);
+ buf[0] = '\0';
+
+ graph_cls_show(fp, buf, &children, level + 1);
+ if (!cls->hlist.next) {
+ graph_indent(buf, cls, 0, 0);
+ strcat(buf, "\n");
+ }
+
+ fprintf(fp, "%s", buf);
+ buf[0] = '\0';
+ free(cls);
+ }
+}
+
+int print_class(const struct sockaddr_nl *who,
+ struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ struct tcmsg *t = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr *tb[TCA_MAX + 1] = {};
+ struct qdisc_util *q;
+ char abuf[256];
+
+ if (n->nlmsg_type != RTM_NEWTCLASS && n->nlmsg_type != RTM_DELTCLASS) {
+ fprintf(stderr, "Not a class\n");
+ return 0;
+ }
+ len -= NLMSG_LENGTH(sizeof(*t));
+ if (len < 0) {
+ fprintf(stderr, "Wrong len %d\n", len);
+ return -1;
+ }
+
+ if (show_graph) {
+ graph_node_add(t->tcm_parent, t->tcm_handle, TCA_RTA(t), len);
+ return 0;
+ }
+
+ if (filter_qdisc && TC_H_MAJ(t->tcm_handle^filter_qdisc))
+ return 0;
+
+ if (filter_classid && t->tcm_handle != filter_classid)
+ return 0;
+
+ parse_rtattr(tb, TCA_MAX, TCA_RTA(t), len);
+
+ if (tb[TCA_KIND] == NULL) {
+ fprintf(stderr, "print_class: NULL kind\n");
+ return -1;
+ }
+
+ if (n->nlmsg_type == RTM_DELTCLASS)
+ fprintf(fp, "deleted ");
+
+ abuf[0] = 0;
+ if (t->tcm_handle) {
+ if (filter_qdisc)
+ print_tc_classid(abuf, sizeof(abuf), TC_H_MIN(t->tcm_handle));
+ else
+ print_tc_classid(abuf, sizeof(abuf), t->tcm_handle);
+ }
+ fprintf(fp, "class %s %s ", rta_getattr_str(tb[TCA_KIND]), abuf);
+
+ if (filter_ifindex == 0)
+ fprintf(fp, "dev %s ", ll_index_to_name(t->tcm_ifindex));
+
+ if (t->tcm_parent == TC_H_ROOT)
+ fprintf(fp, "root ");
+ else {
+ if (filter_qdisc)
+ print_tc_classid(abuf, sizeof(abuf), TC_H_MIN(t->tcm_parent));
+ else
+ print_tc_classid(abuf, sizeof(abuf), t->tcm_parent);
+ fprintf(fp, "parent %s ", abuf);
+ }
+ if (t->tcm_info)
+ fprintf(fp, "leaf %x: ", t->tcm_info>>16);
+ q = get_qdisc_kind(RTA_DATA(tb[TCA_KIND]));
+ if (tb[TCA_OPTIONS]) {
+ if (q && q->print_copt)
+ q->print_copt(q, fp, tb[TCA_OPTIONS]);
+ else
+ fprintf(fp, "[cannot parse class parameters]");
+ }
+ fprintf(fp, "\n");
+ if (show_stats) {
+ struct rtattr *xstats = NULL;
+
+ if (tb[TCA_STATS] || tb[TCA_STATS2]) {
+ print_tcstats_attr(fp, tb, " ", &xstats);
+ fprintf(fp, "\n");
+ }
+ if (q && (xstats || tb[TCA_XSTATS]) && q->print_xstats) {
+ q->print_xstats(q, fp, xstats ? : tb[TCA_XSTATS]);
+ fprintf(fp, "\n");
+ }
+ }
+ fflush(fp);
+ return 0;
+}
+
+
+static int tc_class_list(int argc, char **argv)
+{
+ struct tcmsg t;
+ char d[16];
+ char buf[1024] = {0};
+
+ memset(&t, 0, sizeof(t));
+ t.tcm_family = AF_UNSPEC;
+ memset(d, 0, sizeof(d));
+
+ filter_qdisc = 0;
+ filter_classid = 0;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ if (d[0])
+ duparg("dev", *argv);
+ strncpy(d, *argv, sizeof(d)-1);
+ } else if (strcmp(*argv, "qdisc") == 0) {
+ NEXT_ARG();
+ if (filter_qdisc)
+ duparg("qdisc", *argv);
+ if (get_qdisc_handle(&filter_qdisc, *argv))
+ invarg("invalid qdisc ID", *argv);
+ } else if (strcmp(*argv, "classid") == 0) {
+ NEXT_ARG();
+ if (filter_classid)
+ duparg("classid", *argv);
+ if (get_tc_classid(&filter_classid, *argv))
+ invarg("invalid class ID", *argv);
+ } else if (strcmp(*argv, "root") == 0) {
+ if (t.tcm_parent) {
+ fprintf(stderr, "Error: \"root\" is duplicate parent ID\n");
+ return -1;
+ }
+ t.tcm_parent = TC_H_ROOT;
+ } else if (strcmp(*argv, "parent") == 0) {
+ __u32 handle;
+ if (t.tcm_parent)
+ duparg("parent", *argv);
+ NEXT_ARG();
+ if (get_tc_classid(&handle, *argv))
+ invarg("invalid parent ID", *argv);
+ t.tcm_parent = handle;
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ } else {
+ fprintf(stderr, "What is \"%s\"? Try \"tc class help\".\n", *argv);
+ return -1;
+ }
+
+ argc--; argv++;
+ }
+
+ ll_init_map(&rth);
+
+ if (d[0]) {
+ if ((t.tcm_ifindex = ll_name_to_index(d)) == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", d);
+ return 1;
+ }
+ filter_ifindex = t.tcm_ifindex;
+ }
+
+ if (rtnl_dump_request(&rth, RTM_GETTCLASS, &t, sizeof(t)) < 0) {
+ perror("Cannot send dump request");
+ return 1;
+ }
+
+ if (rtnl_dump_filter(&rth, print_class, stdout) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ return 1;
+ }
+
+ if (show_graph)
+ graph_cls_show(stdout, &buf[0], &root_cls_list, 0);
+
+ return 0;
+}
+
+int do_class(int argc, char **argv)
+{
+ if (argc < 1)
+ return tc_class_list(0, NULL);
+ if (matches(*argv, "add") == 0)
+ return tc_class_modify(RTM_NEWTCLASS, NLM_F_EXCL|NLM_F_CREATE, argc-1, argv+1);
+ if (matches(*argv, "change") == 0)
+ return tc_class_modify(RTM_NEWTCLASS, 0, argc-1, argv+1);
+ if (matches(*argv, "replace") == 0)
+ return tc_class_modify(RTM_NEWTCLASS, NLM_F_CREATE, argc-1, argv+1);
+ if (matches(*argv, "delete") == 0)
+ return tc_class_modify(RTM_DELTCLASS, 0, argc-1, argv+1);
+#if 0
+ if (matches(*argv, "get") == 0)
+ return tc_class_get(RTM_GETTCLASS, 0, argc-1, argv+1);
+#endif
+ if (matches(*argv, "list") == 0 || matches(*argv, "show") == 0
+ || matches(*argv, "lst") == 0)
+ return tc_class_list(argc-1, argv+1);
+ if (matches(*argv, "help") == 0) {
+ usage();
+ return 0;
+ }
+ fprintf(stderr, "Command \"%s\" is unknown, try \"tc class help\".\n", *argv);
+ return -1;
+}
diff --git a/iproute2/tc/tc_common.h b/iproute2/tc/tc_common.h
new file mode 100644
index 0000000..a2f3898
--- /dev/null
+++ b/iproute2/tc/tc_common.h
@@ -0,0 +1,27 @@
+
+#define TCA_BUF_MAX (64*1024)
+
+extern struct rtnl_handle rth;
+
+extern int do_qdisc(int argc, char **argv);
+extern int do_class(int argc, char **argv);
+extern int do_filter(int argc, char **argv);
+extern int do_action(int argc, char **argv);
+extern int do_tcmonitor(int argc, char **argv);
+extern int do_exec(int argc, char **argv);
+
+extern int print_action(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg);
+extern int print_filter(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg);
+extern int print_qdisc(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg);
+extern int print_class(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg);
+extern void print_size_table(FILE *fp, const char *prefix, struct rtattr *rta);
+
+struct tc_estimator;
+extern int parse_estimator(int *p_argc, char ***p_argv, struct tc_estimator *est);
+
+struct tc_sizespec;
+extern int parse_size_table(int *p_argc, char ***p_argv, struct tc_sizespec *s);
+extern int check_size_table_opts(struct tc_sizespec *s);
+
+extern int show_graph;
+extern bool use_names;
diff --git a/iproute2/tc/tc_core.c b/iproute2/tc/tc_core.c
new file mode 100644
index 0000000..46eaefb
--- /dev/null
+++ b/iproute2/tc/tc_core.c
@@ -0,0 +1,227 @@
+/*
+ * tc_core.c TC core library.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <math.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "tc_core.h"
+#include <linux/atm.h>
+
+static double tick_in_usec = 1;
+static double clock_factor = 1;
+
+int tc_core_time2big(unsigned time)
+{
+ __u64 t = time;
+
+ t *= tick_in_usec;
+ return (t >> 32) != 0;
+}
+
+
+unsigned tc_core_time2tick(unsigned time)
+{
+ return time*tick_in_usec;
+}
+
+unsigned tc_core_tick2time(unsigned tick)
+{
+ return tick/tick_in_usec;
+}
+
+unsigned tc_core_time2ktime(unsigned time)
+{
+ return time * clock_factor;
+}
+
+unsigned tc_core_ktime2time(unsigned ktime)
+{
+ return ktime / clock_factor;
+}
+
+unsigned tc_calc_xmittime(__u64 rate, unsigned size)
+{
+ return tc_core_time2tick(TIME_UNITS_PER_SEC*((double)size/(double)rate));
+}
+
+unsigned tc_calc_xmitsize(__u64 rate, unsigned ticks)
+{
+ return ((double)rate*tc_core_tick2time(ticks))/TIME_UNITS_PER_SEC;
+}
+
+/*
+ * The align to ATM cells is used for determining the (ATM) SAR
+ * alignment overhead at the ATM layer. (SAR = Segmentation And
+ * Reassembly). This is for example needed when scheduling packet on
+ * an ADSL connection. Note that the extra ATM-AAL overhead is _not_
+ * included in this calculation. This overhead is added in the kernel
+ * before doing the rate table lookup, as this gives better precision
+ * (as the table will always be aligned for 48 bytes).
+ * --Hawk, d.7/11-2004. <hawk@diku.dk>
+ */
+static unsigned tc_align_to_atm(unsigned size)
+{
+ int linksize, cells;
+ cells = size / ATM_CELL_PAYLOAD;
+ if ((size % ATM_CELL_PAYLOAD) > 0)
+ cells++;
+
+ linksize = cells * ATM_CELL_SIZE; /* Use full cell size to add ATM tax */
+ return linksize;
+}
+
+static unsigned tc_adjust_size(unsigned sz, unsigned mpu, enum link_layer linklayer)
+{
+ if (sz < mpu)
+ sz = mpu;
+
+ switch (linklayer) {
+ case LINKLAYER_ATM:
+ return tc_align_to_atm(sz);
+ case LINKLAYER_ETHERNET:
+ default:
+ // No size adjustments on Ethernet
+ return sz;
+ }
+}
+
+/* Notice, the rate table calculated here, have gotten replaced in the
+ * kernel and is no-longer used for lookups.
+ *
+ * This happened in kernel release v3.8 caused by kernel
+ * - commit 56b765b79 ("htb: improved accuracy at high rates").
+ * This change unfortunately caused breakage of tc overhead and
+ * linklayer parameters.
+ *
+ * Kernel overhead handling got fixed in kernel v3.10 by
+ * - commit 01cb71d2d47 (net_sched: restore "overhead xxx" handling)
+ *
+ * Kernel linklayer handling got fixed in kernel v3.11 by
+ * - commit 8a8e3d84b17 (net_sched: restore "linklayer atm" handling)
+ */
+
+/*
+ rtab[pkt_len>>cell_log] = pkt_xmit_time
+ */
+
+int tc_calc_rtable(struct tc_ratespec *r, __u32 *rtab,
+ int cell_log, unsigned mtu,
+ enum link_layer linklayer)
+{
+ int i;
+ unsigned sz;
+ unsigned bps = r->rate;
+ unsigned mpu = r->mpu;
+
+ if (mtu == 0)
+ mtu = 2047;
+
+ if (cell_log < 0) {
+ cell_log = 0;
+ while ((mtu >> cell_log) > 255)
+ cell_log++;
+ }
+
+ for (i=0; i<256; i++) {
+ sz = tc_adjust_size((i + 1) << cell_log, mpu, linklayer);
+ rtab[i] = tc_calc_xmittime(bps, sz);
+ }
+
+ r->cell_align=-1; // Due to the sz calc
+ r->cell_log=cell_log;
+ r->linklayer = (linklayer & TC_LINKLAYER_MASK);
+ return cell_log;
+}
+
+/*
+ stab[pkt_len>>cell_log] = pkt_xmit_size>>size_log
+ */
+
+int tc_calc_size_table(struct tc_sizespec *s, __u16 **stab)
+{
+ int i;
+ enum link_layer linklayer = s->linklayer;
+ unsigned int sz;
+
+ if (linklayer <= LINKLAYER_ETHERNET && s->mpu == 0) {
+ /* don't need data table in this case (only overhead set) */
+ s->mtu = 0;
+ s->tsize = 0;
+ s->cell_log = 0;
+ s->cell_align = 0;
+ *stab = NULL;
+ return 0;
+ }
+
+ if (s->mtu == 0)
+ s->mtu = 2047;
+ if (s->tsize == 0)
+ s->tsize = 512;
+
+ s->cell_log = 0;
+ while ((s->mtu >> s->cell_log) > s->tsize - 1)
+ s->cell_log++;
+
+ *stab = malloc(s->tsize * sizeof(__u16));
+ if (!*stab)
+ return -1;
+
+again:
+ for (i = s->tsize - 1; i >= 0; i--) {
+ sz = tc_adjust_size((i + 1) << s->cell_log, s->mpu, linklayer);
+ if ((sz >> s->size_log) > UINT16_MAX) {
+ s->size_log++;
+ goto again;
+ }
+ (*stab)[i] = sz >> s->size_log;
+ }
+
+ s->cell_align = -1; // Due to the sz calc
+ return 0;
+}
+
+int tc_core_init(void)
+{
+ FILE *fp;
+ __u32 clock_res;
+ __u32 t2us;
+ __u32 us2t;
+
+ fp = fopen("/proc/net/psched", "r");
+ if (fp == NULL)
+ return -1;
+
+ if (fscanf(fp, "%08x%08x%08x", &t2us, &us2t, &clock_res) != 3) {
+ fclose(fp);
+ return -1;
+ }
+ fclose(fp);
+
+ /* compatibility hack: for old iproute binaries (ignoring
+ * the kernel clock resolution) the kernel advertises a
+ * tick multiplier of 1000 in case of nano-second resolution,
+ * which really is 1. */
+ if (clock_res == 1000000000)
+ t2us = us2t;
+
+ clock_factor = (double)clock_res / TIME_UNITS_PER_SEC;
+ tick_in_usec = (double)t2us / us2t * clock_factor;
+ return 0;
+}
diff --git a/iproute2/tc/tc_core.h b/iproute2/tc/tc_core.h
new file mode 100644
index 0000000..8a63b79
--- /dev/null
+++ b/iproute2/tc/tc_core.h
@@ -0,0 +1,34 @@
+#ifndef _TC_CORE_H_
+#define _TC_CORE_H_ 1
+
+#include <asm/types.h>
+#include <linux/pkt_sched.h>
+
+#define TIME_UNITS_PER_SEC 1000000
+
+enum link_layer {
+ LINKLAYER_UNSPEC,
+ LINKLAYER_ETHERNET,
+ LINKLAYER_ATM,
+};
+
+
+int tc_core_time2big(unsigned time);
+unsigned tc_core_time2tick(unsigned time);
+unsigned tc_core_tick2time(unsigned tick);
+unsigned tc_core_time2ktime(unsigned time);
+unsigned tc_core_ktime2time(unsigned ktime);
+unsigned tc_calc_xmittime(__u64 rate, unsigned size);
+unsigned tc_calc_xmitsize(__u64 rate, unsigned ticks);
+int tc_calc_rtable(struct tc_ratespec *r, __u32 *rtab,
+ int cell_log, unsigned mtu, enum link_layer link_layer);
+int tc_calc_size_table(struct tc_sizespec *s, __u16 **stab);
+
+int tc_setup_estimator(unsigned A, unsigned time_const, struct tc_estimator *est);
+
+int tc_core_init(void);
+
+extern struct rtnl_handle g_rth;
+extern int is_batch_mode;
+
+#endif
diff --git a/iproute2/tc/tc_estimator.c b/iproute2/tc/tc_estimator.c
new file mode 100644
index 0000000..e559add
--- /dev/null
+++ b/iproute2/tc/tc_estimator.c
@@ -0,0 +1,44 @@
+/*
+ * tc_core.c TC core library.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <math.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "tc_core.h"
+
+int tc_setup_estimator(unsigned A, unsigned time_const, struct tc_estimator *est)
+{
+ for (est->interval=0; est->interval<=5; est->interval++) {
+ if (A <= (1<<est->interval)*(TIME_UNITS_PER_SEC/4))
+ break;
+ }
+ if (est->interval > 5)
+ return -1;
+ est->interval -= 2;
+ for (est->ewma_log=1; est->ewma_log<32; est->ewma_log++) {
+ double w = 1.0 - 1.0/(1<<est->ewma_log);
+ if (A/(-log(w)) > time_const)
+ break;
+ }
+ est->ewma_log--;
+ if (est->ewma_log==0 || est->ewma_log >= 31)
+ return -1;
+ return 0;
+}
diff --git a/iproute2/tc/tc_exec.c b/iproute2/tc/tc_exec.c
new file mode 100644
index 0000000..61be672
--- /dev/null
+++ b/iproute2/tc/tc_exec.c
@@ -0,0 +1,109 @@
+/*
+ * tc_exec.c "tc exec".
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Daniel Borkmann <daniel@iogearbox.net>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <dlfcn.h>
+
+#include "utils.h"
+
+#include "tc_util.h"
+#include "tc_common.h"
+
+static struct exec_util *exec_list;
+static void *BODY = NULL;
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: tc exec [ EXEC_TYPE ] [ help | OPTIONS ]\n");
+ fprintf(stderr, "Where:\n");
+ fprintf(stderr, "EXEC_TYPE := { bpf | etc. }\n");
+ fprintf(stderr, "OPTIONS := ... try tc exec <desired EXEC_KIND> help\n");
+}
+
+static int parse_noeopt(struct exec_util *eu, int argc, char **argv)
+{
+ if (argc) {
+ fprintf(stderr, "Unknown exec \"%s\", hence option \"%s\" "
+ "is unparsable\n", eu->id, *argv);
+ return -1;
+ }
+
+ return 0;
+}
+
+static struct exec_util *get_exec_kind(const char *name)
+{
+ struct exec_util *eu;
+ char buf[256];
+ void *dlh;
+
+ for (eu = exec_list; eu; eu = eu->next)
+ if (strcmp(eu->id, name) == 0)
+ return eu;
+
+ snprintf(buf, sizeof(buf), "%s/e_%s.so", get_tc_lib(), name);
+ dlh = dlopen(buf, RTLD_LAZY);
+ if (dlh == NULL) {
+ dlh = BODY;
+ if (dlh == NULL) {
+ dlh = BODY = dlopen(NULL, RTLD_LAZY);
+ if (dlh == NULL)
+ goto noexist;
+ }
+ }
+
+ snprintf(buf, sizeof(buf), "%s_exec_util", name);
+ eu = dlsym(dlh, buf);
+ if (eu == NULL)
+ goto noexist;
+reg:
+ eu->next = exec_list;
+ exec_list = eu;
+
+ return eu;
+noexist:
+ eu = malloc(sizeof(*eu));
+ if (eu) {
+ memset(eu, 0, sizeof(*eu));
+ strncpy(eu->id, name, sizeof(eu->id) - 1);
+ eu->parse_eopt = parse_noeopt;
+ goto reg;
+ }
+
+ return eu;
+}
+
+int do_exec(int argc, char **argv)
+{
+ struct exec_util *eu;
+ char kind[16];
+
+ if (argc < 1) {
+ fprintf(stderr, "No command given, try \"tc exec help\".\n");
+ return -1;
+ }
+
+ if (matches(*argv, "help") == 0) {
+ usage();
+ return 0;
+ }
+
+ memset(kind, 0, sizeof(kind));
+ strncpy(kind, *argv, sizeof(kind) - 1);
+
+ eu = get_exec_kind(kind);
+
+ argc--;
+ argv++;
+
+ return eu->parse_eopt(eu, argc, argv);
+}
diff --git a/iproute2/tc/tc_filter.c b/iproute2/tc/tc_filter.c
new file mode 100644
index 0000000..1a1082b
--- /dev/null
+++ b/iproute2/tc/tc_filter.c
@@ -0,0 +1,407 @@
+/*
+ * tc_filter.c "tc filter".
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <linux/if_ether.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "tc_util.h"
+#include "tc_common.h"
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: tc filter [ add | del | change | replace | show ] dev STRING\n");
+ fprintf(stderr, " [ pref PRIO ] protocol PROTO\n");
+ fprintf(stderr, " [ estimator INTERVAL TIME_CONSTANT ]\n");
+ fprintf(stderr, " [ root | ingress | egress | parent CLASSID ]\n");
+ fprintf(stderr, " [ handle FILTERID ] [ [ FILTER_TYPE ] [ help | OPTIONS ] ]\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, " tc filter show [ dev STRING ] [ root | ingress | egress | parent CLASSID ]\n");
+ fprintf(stderr, "Where:\n");
+ fprintf(stderr, "FILTER_TYPE := { rsvp | u32 | bpf | fw | route | etc. }\n");
+ fprintf(stderr, "FILTERID := ... format depends on classifier, see there\n");
+ fprintf(stderr, "OPTIONS := ... try tc filter add <desired FILTER_KIND> help\n");
+}
+
+static int tc_filter_modify(int cmd, unsigned flags, int argc, char **argv)
+{
+ struct {
+ struct nlmsghdr n;
+ struct tcmsg t;
+ char buf[MAX_MSG];
+ } req;
+ struct filter_util *q = NULL;
+ __u32 prio = 0;
+ __u32 protocol = 0;
+ int protocol_set = 0;
+ char *fhandle = NULL;
+ char d[16];
+ char k[16];
+ struct tc_estimator est;
+
+ memset(&req, 0, sizeof(req));
+ memset(&est, 0, sizeof(est));
+ memset(d, 0, sizeof(d));
+ memset(k, 0, sizeof(k));
+ memset(&req, 0, sizeof(req));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST|flags;
+ req.n.nlmsg_type = cmd;
+ req.t.tcm_family = AF_UNSPEC;
+
+ if (cmd == RTM_NEWTFILTER && flags & NLM_F_CREATE)
+ protocol = htons(ETH_P_ALL);
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ if (d[0])
+ duparg("dev", *argv);
+ strncpy(d, *argv, sizeof(d)-1);
+ } else if (strcmp(*argv, "root") == 0) {
+ if (req.t.tcm_parent) {
+ fprintf(stderr, "Error: \"root\" is duplicate parent ID\n");
+ return -1;
+ }
+ req.t.tcm_parent = TC_H_ROOT;
+ } else if (strcmp(*argv, "ingress") == 0) {
+ if (req.t.tcm_parent) {
+ fprintf(stderr, "Error: \"ingress\" is duplicate parent ID\n");
+ return -1;
+ }
+ req.t.tcm_parent = TC_H_MAKE(TC_H_CLSACT,
+ TC_H_MIN_INGRESS);
+ } else if (strcmp(*argv, "egress") == 0) {
+ if (req.t.tcm_parent) {
+ fprintf(stderr, "Error: \"egress\" is duplicate parent ID\n");
+ return -1;
+ }
+ req.t.tcm_parent = TC_H_MAKE(TC_H_CLSACT,
+ TC_H_MIN_EGRESS);
+ } else if (strcmp(*argv, "parent") == 0) {
+ __u32 handle;
+ NEXT_ARG();
+ if (req.t.tcm_parent)
+ duparg("parent", *argv);
+ if (get_tc_classid(&handle, *argv))
+ invarg("Invalid parent ID", *argv);
+ req.t.tcm_parent = handle;
+ } else if (strcmp(*argv, "handle") == 0) {
+ NEXT_ARG();
+ if (fhandle)
+ duparg("handle", *argv);
+ fhandle = *argv;
+ } else if (matches(*argv, "preference") == 0 ||
+ matches(*argv, "priority") == 0) {
+ NEXT_ARG();
+ if (prio)
+ duparg("priority", *argv);
+ if (get_u32(&prio, *argv, 0) || prio > 0xFFFF)
+ invarg("invalid priority value", *argv);
+ } else if (matches(*argv, "protocol") == 0) {
+ __u16 id;
+ NEXT_ARG();
+ if (protocol_set)
+ duparg("protocol", *argv);
+ if (ll_proto_a2n(&id, *argv))
+ invarg("invalid protocol", *argv);
+ protocol = id;
+ protocol_set = 1;
+ } else if (matches(*argv, "estimator") == 0) {
+ if (parse_estimator(&argc, &argv, &est) < 0)
+ return -1;
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ return 0;
+ } else {
+ strncpy(k, *argv, sizeof(k)-1);
+
+ q = get_filter_kind(k);
+ argc--; argv++;
+ break;
+ }
+
+ argc--; argv++;
+ }
+
+ req.t.tcm_info = TC_H_MAKE(prio<<16, protocol);
+
+ if (k[0])
+ addattr_l(&req.n, sizeof(req), TCA_KIND, k, strlen(k)+1);
+
+ if (q) {
+ if (q->parse_fopt(q, fhandle, argc, argv, &req.n))
+ return 1;
+ } else {
+ if (fhandle) {
+ fprintf(stderr, "Must specify filter type when using "
+ "\"handle\"\n");
+ return -1;
+ }
+ if (argc) {
+ if (matches(*argv, "help") == 0)
+ usage();
+ fprintf(stderr, "Garbage instead of arguments \"%s ...\". Try \"tc filter help\".\n", *argv);
+ return -1;
+ }
+ }
+ if (est.ewma_log)
+ addattr_l(&req.n, sizeof(req), TCA_RATE, &est, sizeof(est));
+
+
+ if (d[0]) {
+ ll_init_map(&rth);
+
+ if ((req.t.tcm_ifindex = ll_name_to_index(d)) == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", d);
+ return 1;
+ }
+ }
+
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0) {
+ fprintf(stderr, "We have an error talking to the kernel\n");
+ return 2;
+ }
+
+ return 0;
+}
+
+static __u32 filter_parent;
+static int filter_ifindex;
+static __u32 filter_prio;
+static __u32 filter_protocol;
+__u16 f_proto = 0;
+
+int print_filter(const struct sockaddr_nl *who,
+ struct nlmsghdr *n,
+ void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ struct tcmsg *t = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr * tb[TCA_MAX+1];
+ struct filter_util *q;
+ char abuf[256];
+
+ if (n->nlmsg_type != RTM_NEWTFILTER && n->nlmsg_type != RTM_DELTFILTER) {
+ fprintf(stderr, "Not a filter\n");
+ return 0;
+ }
+ len -= NLMSG_LENGTH(sizeof(*t));
+ if (len < 0) {
+ fprintf(stderr, "Wrong len %d\n", len);
+ return -1;
+ }
+
+ memset(tb, 0, sizeof(tb));
+ parse_rtattr(tb, TCA_MAX, TCA_RTA(t), len);
+
+ if (tb[TCA_KIND] == NULL) {
+ fprintf(stderr, "print_filter: NULL kind\n");
+ return -1;
+ }
+
+ if (n->nlmsg_type == RTM_DELTFILTER)
+ fprintf(fp, "deleted ");
+
+ fprintf(fp, "filter ");
+ if (!filter_ifindex || filter_ifindex != t->tcm_ifindex)
+ fprintf(fp, "dev %s ", ll_index_to_name(t->tcm_ifindex));
+
+ if (!filter_parent || filter_parent != t->tcm_parent) {
+ if (t->tcm_parent == TC_H_ROOT)
+ fprintf(fp, "root ");
+ else if (t->tcm_parent == TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS))
+ fprintf(fp, "ingress ");
+ else if (t->tcm_parent == TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_EGRESS))
+ fprintf(fp, "egress ");
+ else {
+ print_tc_classid(abuf, sizeof(abuf), t->tcm_parent);
+ fprintf(fp, "parent %s ", abuf);
+ }
+ }
+
+ if (t->tcm_info) {
+ f_proto = TC_H_MIN(t->tcm_info);
+ __u32 prio = TC_H_MAJ(t->tcm_info)>>16;
+ if (!filter_protocol || filter_protocol != f_proto) {
+ if (f_proto) {
+ SPRINT_BUF(b1);
+ fprintf(fp, "protocol %s ",
+ ll_proto_n2a(f_proto, b1, sizeof(b1)));
+ }
+ }
+ if (!filter_prio || filter_prio != prio) {
+ if (prio)
+ fprintf(fp, "pref %u ", prio);
+ }
+ }
+ fprintf(fp, "%s ", rta_getattr_str(tb[TCA_KIND]));
+ q = get_filter_kind(RTA_DATA(tb[TCA_KIND]));
+ if (tb[TCA_OPTIONS]) {
+ if (q)
+ q->print_fopt(q, fp, tb[TCA_OPTIONS], t->tcm_handle);
+ else
+ fprintf(fp, "[cannot parse parameters]");
+ }
+ fprintf(fp, "\n");
+
+ if (show_stats && (tb[TCA_STATS] || tb[TCA_STATS2])) {
+ print_tcstats_attr(fp, tb, " ", NULL);
+ fprintf(fp, "\n");
+ }
+
+ fflush(fp);
+ return 0;
+}
+
+static int tc_filter_list(int argc, char **argv)
+{
+ struct tcmsg t;
+ char d[16];
+ __u32 prio = 0;
+ __u32 protocol = 0;
+ char *fhandle = NULL;
+
+ memset(&t, 0, sizeof(t));
+ t.tcm_family = AF_UNSPEC;
+ memset(d, 0, sizeof(d));
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ if (d[0])
+ duparg("dev", *argv);
+ strncpy(d, *argv, sizeof(d)-1);
+ } else if (strcmp(*argv, "root") == 0) {
+ if (t.tcm_parent) {
+ fprintf(stderr, "Error: \"root\" is duplicate parent ID\n");
+ return -1;
+ }
+ filter_parent = t.tcm_parent = TC_H_ROOT;
+ } else if (strcmp(*argv, "ingress") == 0) {
+ if (t.tcm_parent) {
+ fprintf(stderr, "Error: \"ingress\" is duplicate parent ID\n");
+ return -1;
+ }
+ filter_parent = TC_H_MAKE(TC_H_CLSACT,
+ TC_H_MIN_INGRESS);
+ t.tcm_parent = filter_parent;
+ } else if (strcmp(*argv, "egress") == 0) {
+ if (t.tcm_parent) {
+ fprintf(stderr, "Error: \"egress\" is duplicate parent ID\n");
+ return -1;
+ }
+ filter_parent = TC_H_MAKE(TC_H_CLSACT,
+ TC_H_MIN_EGRESS);
+ t.tcm_parent = filter_parent;
+ } else if (strcmp(*argv, "parent") == 0) {
+ __u32 handle;
+ NEXT_ARG();
+ if (t.tcm_parent)
+ duparg("parent", *argv);
+ if (get_tc_classid(&handle, *argv))
+ invarg("invalid parent ID", *argv);
+ filter_parent = t.tcm_parent = handle;
+ } else if (strcmp(*argv, "handle") == 0) {
+ NEXT_ARG();
+ if (fhandle)
+ duparg("handle", *argv);
+ fhandle = *argv;
+ } else if (matches(*argv, "preference") == 0 ||
+ matches(*argv, "priority") == 0) {
+ NEXT_ARG();
+ if (prio)
+ duparg("priority", *argv);
+ if (get_u32(&prio, *argv, 0))
+ invarg("invalid preference", *argv);
+ filter_prio = prio;
+ } else if (matches(*argv, "protocol") == 0) {
+ __u16 res;
+ NEXT_ARG();
+ if (protocol)
+ duparg("protocol", *argv);
+ if (ll_proto_a2n(&res, *argv))
+ invarg("invalid protocol", *argv);
+ protocol = res;
+ filter_protocol = protocol;
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ } else {
+ fprintf(stderr, " What is \"%s\"? Try \"tc filter help\"\n", *argv);
+ return -1;
+ }
+
+ argc--; argv++;
+ }
+
+ t.tcm_info = TC_H_MAKE(prio<<16, protocol);
+
+ ll_init_map(&rth);
+
+ if (d[0]) {
+ if ((t.tcm_ifindex = ll_name_to_index(d)) == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", d);
+ return 1;
+ }
+ filter_ifindex = t.tcm_ifindex;
+ }
+
+ if (rtnl_dump_request(&rth, RTM_GETTFILTER, &t, sizeof(t)) < 0) {
+ perror("Cannot send dump request");
+ return 1;
+ }
+
+ if (rtnl_dump_filter(&rth, print_filter, stdout) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ return 1;
+ }
+
+ return 0;
+}
+
+int do_filter(int argc, char **argv)
+{
+ if (argc < 1)
+ return tc_filter_list(0, NULL);
+ if (matches(*argv, "add") == 0)
+ return tc_filter_modify(RTM_NEWTFILTER, NLM_F_EXCL|NLM_F_CREATE, argc-1, argv+1);
+ if (matches(*argv, "change") == 0)
+ return tc_filter_modify(RTM_NEWTFILTER, 0, argc-1, argv+1);
+ if (matches(*argv, "replace") == 0)
+ return tc_filter_modify(RTM_NEWTFILTER, NLM_F_CREATE, argc-1, argv+1);
+ if (matches(*argv, "delete") == 0)
+ return tc_filter_modify(RTM_DELTFILTER, 0, argc-1, argv+1);
+#if 0
+ if (matches(*argv, "get") == 0)
+ return tc_filter_get(RTM_GETTFILTER, 0, argc-1, argv+1);
+#endif
+ if (matches(*argv, "list") == 0 || matches(*argv, "show") == 0
+ || matches(*argv, "lst") == 0)
+ return tc_filter_list(argc-1, argv+1);
+ if (matches(*argv, "help") == 0) {
+ usage();
+ return 0;
+ }
+ fprintf(stderr, "Command \"%s\" is unknown, try \"tc filter help\".\n", *argv);
+ return -1;
+}
diff --git a/iproute2/tc/tc_monitor.c b/iproute2/tc/tc_monitor.c
new file mode 100644
index 0000000..ebb9432
--- /dev/null
+++ b/iproute2/tc/tc_monitor.c
@@ -0,0 +1,119 @@
+/*
+ * tc_monitor.c "tc monitor".
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Jamal Hadi Salim
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <time.h>
+#include "rt_names.h"
+#include "utils.h"
+#include "tc_util.h"
+#include "tc_common.h"
+
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: tc [-timestamp [-tshort] monitor\n");
+ exit(-1);
+}
+
+
+static int accept_tcmsg(const struct sockaddr_nl *who,
+ struct rtnl_ctrl_data *ctrl,
+ struct nlmsghdr *n, void *arg)
+{
+ FILE *fp = (FILE*)arg;
+
+ if (timestamp)
+ print_timestamp(fp);
+
+ if (n->nlmsg_type == RTM_NEWTFILTER || n->nlmsg_type == RTM_DELTFILTER) {
+ print_filter(who, n, arg);
+ return 0;
+ }
+ if (n->nlmsg_type == RTM_NEWTCLASS || n->nlmsg_type == RTM_DELTCLASS) {
+ print_class(who, n, arg);
+ return 0;
+ }
+ if (n->nlmsg_type == RTM_NEWQDISC || n->nlmsg_type == RTM_DELQDISC) {
+ print_qdisc(who, n, arg);
+ return 0;
+ }
+ if (n->nlmsg_type == RTM_GETACTION || n->nlmsg_type == RTM_NEWACTION ||
+ n->nlmsg_type == RTM_DELACTION) {
+ print_action(who, n, arg);
+ return 0;
+ }
+ if (n->nlmsg_type != NLMSG_ERROR && n->nlmsg_type != NLMSG_NOOP &&
+ n->nlmsg_type != NLMSG_DONE) {
+ fprintf(fp, "Unknown message: length %08d type %08x flags %08x\n",
+ n->nlmsg_len, n->nlmsg_type, n->nlmsg_flags);
+ }
+ return 0;
+}
+
+int do_tcmonitor(int argc, char **argv)
+{
+ struct rtnl_handle rth;
+ char *file = NULL;
+ unsigned groups = nl_mgrp(RTNLGRP_TC);
+
+ while (argc > 0) {
+ if (matches(*argv, "file") == 0) {
+ NEXT_ARG();
+ file = *argv;
+ } else {
+ if (matches(*argv, "help") == 0) {
+ usage();
+ } else {
+ fprintf(stderr, "Argument \"%s\" is unknown, try \"tc monitor help\".\n", *argv);
+ exit(-1);
+ }
+ }
+ argc--; argv++;
+ }
+
+ if (file) {
+ FILE *fp = fopen(file, "r");
+ int ret;
+
+ if (fp == NULL) {
+ perror("Cannot fopen");
+ exit(-1);
+ }
+
+ ret = rtnl_from_file(fp, accept_tcmsg, stdout);
+ fclose(fp);
+ return ret;
+ }
+
+ if (rtnl_open(&rth, groups) < 0)
+ exit(1);
+
+ ll_init_map(&rth);
+
+ if (rtnl_listen(&rth, accept_tcmsg, (void*)stdout) < 0) {
+ rtnl_close(&rth);
+ exit(2);
+ }
+
+ rtnl_close(&rth);
+ exit(0);
+}
diff --git a/iproute2/tc/tc_qdisc.c b/iproute2/tc/tc_qdisc.c
new file mode 100644
index 0000000..cb861e0
--- /dev/null
+++ b/iproute2/tc/tc_qdisc.c
@@ -0,0 +1,366 @@
+/*
+ * tc_qdisc.c "tc qdisc".
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ * J Hadi Salim: Extension to ingress
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <math.h>
+#include <malloc.h>
+
+#include "utils.h"
+#include "tc_util.h"
+#include "tc_common.h"
+
+static int usage(void)
+{
+ fprintf(stderr, "Usage: tc qdisc [ add | del | replace | change | show ] dev STRING\n");
+ fprintf(stderr, " [ handle QHANDLE ] [ root | ingress | clsact | parent CLASSID ]\n");
+ fprintf(stderr, " [ estimator INTERVAL TIME_CONSTANT ]\n");
+ fprintf(stderr, " [ stab [ help | STAB_OPTIONS] ]\n");
+ fprintf(stderr, " [ [ QDISC_KIND ] [ help | OPTIONS ] ]\n");
+ fprintf(stderr, "\n");
+ fprintf(stderr, " tc qdisc show [ dev STRING ] [ ingress | clsact ]\n");
+ fprintf(stderr, "Where:\n");
+ fprintf(stderr, "QDISC_KIND := { [p|b]fifo | tbf | prio | cbq | red | etc. }\n");
+ fprintf(stderr, "OPTIONS := ... try tc qdisc add <desired QDISC_KIND> help\n");
+ fprintf(stderr, "STAB_OPTIONS := ... try tc qdisc add stab help\n");
+ return -1;
+}
+
+static int tc_qdisc_modify(int cmd, unsigned flags, int argc, char **argv)
+{
+ struct qdisc_util *q = NULL;
+ struct tc_estimator est;
+ struct {
+ struct tc_sizespec szopts;
+ __u16 *data;
+ } stab;
+ char d[16];
+ char k[16];
+ struct {
+ struct nlmsghdr n;
+ struct tcmsg t;
+ char buf[TCA_BUF_MAX];
+ } req;
+
+ memset(&req, 0, sizeof(req));
+ memset(&stab, 0, sizeof(stab));
+ memset(&est, 0, sizeof(est));
+ memset(&d, 0, sizeof(d));
+ memset(&k, 0, sizeof(k));
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg));
+ req.n.nlmsg_flags = NLM_F_REQUEST|flags;
+ req.n.nlmsg_type = cmd;
+ req.t.tcm_family = AF_UNSPEC;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ if (d[0])
+ duparg("dev", *argv);
+ strncpy(d, *argv, sizeof(d)-1);
+ } else if (strcmp(*argv, "handle") == 0) {
+ __u32 handle;
+ if (req.t.tcm_handle)
+ duparg("handle", *argv);
+ NEXT_ARG();
+ if (get_qdisc_handle(&handle, *argv))
+ invarg("invalid qdisc ID", *argv);
+ req.t.tcm_handle = handle;
+ } else if (strcmp(*argv, "root") == 0) {
+ if (req.t.tcm_parent) {
+ fprintf(stderr, "Error: \"root\" is duplicate parent ID\n");
+ return -1;
+ }
+ req.t.tcm_parent = TC_H_ROOT;
+ } else if (strcmp(*argv, "clsact") == 0) {
+ if (req.t.tcm_parent) {
+ fprintf(stderr, "Error: \"clsact\" is a duplicate parent ID\n");
+ return -1;
+ }
+ req.t.tcm_parent = TC_H_CLSACT;
+ strncpy(k, "clsact", sizeof(k) - 1);
+ q = get_qdisc_kind(k);
+ req.t.tcm_handle = TC_H_MAKE(TC_H_CLSACT, 0);
+ NEXT_ARG_FWD();
+ break;
+ } else if (strcmp(*argv, "ingress") == 0) {
+ if (req.t.tcm_parent) {
+ fprintf(stderr, "Error: \"ingress\" is a duplicate parent ID\n");
+ return -1;
+ }
+ req.t.tcm_parent = TC_H_INGRESS;
+ strncpy(k, "ingress", sizeof(k) - 1);
+ q = get_qdisc_kind(k);
+ req.t.tcm_handle = TC_H_MAKE(TC_H_INGRESS, 0);
+ NEXT_ARG_FWD();
+ break;
+ } else if (strcmp(*argv, "parent") == 0) {
+ __u32 handle;
+ NEXT_ARG();
+ if (req.t.tcm_parent)
+ duparg("parent", *argv);
+ if (get_tc_classid(&handle, *argv))
+ invarg("invalid parent ID", *argv);
+ req.t.tcm_parent = handle;
+ } else if (matches(*argv, "estimator") == 0) {
+ if (parse_estimator(&argc, &argv, &est))
+ return -1;
+ } else if (matches(*argv, "stab") == 0) {
+ if (parse_size_table(&argc, &argv, &stab.szopts) < 0)
+ return -1;
+ continue;
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ } else {
+ strncpy(k, *argv, sizeof(k)-1);
+
+ q = get_qdisc_kind(k);
+ argc--; argv++;
+ break;
+ }
+ argc--; argv++;
+ }
+
+ if (k[0])
+ addattr_l(&req.n, sizeof(req), TCA_KIND, k, strlen(k)+1);
+ if (est.ewma_log)
+ addattr_l(&req.n, sizeof(req), TCA_RATE, &est, sizeof(est));
+
+ if (q) {
+ if (q->parse_qopt) {
+ if (q->parse_qopt(q, argc, argv, &req.n))
+ return 1;
+ } else if (argc) {
+ fprintf(stderr, "qdisc '%s' does not support option parsing\n", k);
+ return -1;
+ }
+ } else {
+ if (argc) {
+ if (matches(*argv, "help") == 0)
+ usage();
+
+ fprintf(stderr, "Garbage instead of arguments \"%s ...\". Try \"tc qdisc help\".\n", *argv);
+ return -1;
+ }
+ }
+
+ if (check_size_table_opts(&stab.szopts)) {
+ struct rtattr *tail;
+
+ if (tc_calc_size_table(&stab.szopts, &stab.data) < 0) {
+ fprintf(stderr, "failed to calculate size table.\n");
+ return -1;
+ }
+
+ tail = NLMSG_TAIL(&req.n);
+ addattr_l(&req.n, sizeof(req), TCA_STAB, NULL, 0);
+ addattr_l(&req.n, sizeof(req), TCA_STAB_BASE, &stab.szopts,
+ sizeof(stab.szopts));
+ if (stab.data)
+ addattr_l(&req.n, sizeof(req), TCA_STAB_DATA, stab.data,
+ stab.szopts.tsize * sizeof(__u16));
+ tail->rta_len = (void *)NLMSG_TAIL(&req.n) - (void *)tail;
+ if (stab.data)
+ free(stab.data);
+ }
+
+ if (d[0]) {
+ int idx;
+
+ ll_init_map(&rth);
+
+ if ((idx = ll_name_to_index(d)) == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", d);
+ return 1;
+ }
+ req.t.tcm_ifindex = idx;
+ }
+
+ if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ return 2;
+
+ return 0;
+}
+
+static int filter_ifindex;
+
+int print_qdisc(const struct sockaddr_nl *who,
+ struct nlmsghdr *n,
+ void *arg)
+{
+ FILE *fp = (FILE*)arg;
+ struct tcmsg *t = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr * tb[TCA_MAX+1];
+ struct qdisc_util *q;
+ char abuf[256];
+
+ if (n->nlmsg_type != RTM_NEWQDISC && n->nlmsg_type != RTM_DELQDISC) {
+ fprintf(stderr, "Not a qdisc\n");
+ return 0;
+ }
+ len -= NLMSG_LENGTH(sizeof(*t));
+ if (len < 0) {
+ fprintf(stderr, "Wrong len %d\n", len);
+ return -1;
+ }
+
+ if (filter_ifindex && filter_ifindex != t->tcm_ifindex)
+ return 0;
+
+ memset(tb, 0, sizeof(tb));
+ parse_rtattr(tb, TCA_MAX, TCA_RTA(t), len);
+
+ if (tb[TCA_KIND] == NULL) {
+ fprintf(stderr, "print_qdisc: NULL kind\n");
+ return -1;
+ }
+
+ if (n->nlmsg_type == RTM_DELQDISC)
+ fprintf(fp, "deleted ");
+
+ fprintf(fp, "qdisc %s %x: ", rta_getattr_str(tb[TCA_KIND]), t->tcm_handle>>16);
+ if (filter_ifindex == 0)
+ fprintf(fp, "dev %s ", ll_index_to_name(t->tcm_ifindex));
+ if (t->tcm_parent == TC_H_ROOT)
+ fprintf(fp, "root ");
+ else if (t->tcm_parent) {
+ print_tc_classid(abuf, sizeof(abuf), t->tcm_parent);
+ fprintf(fp, "parent %s ", abuf);
+ }
+ if (t->tcm_info != 1) {
+ fprintf(fp, "refcnt %d ", t->tcm_info);
+ }
+ /* pfifo_fast is generic enough to warrant the hardcoding --JHS */
+
+ if (0 == strcmp("pfifo_fast", RTA_DATA(tb[TCA_KIND])))
+ q = get_qdisc_kind("prio");
+ else
+ q = get_qdisc_kind(RTA_DATA(tb[TCA_KIND]));
+
+ if (tb[TCA_OPTIONS]) {
+ if (q)
+ q->print_qopt(q, fp, tb[TCA_OPTIONS]);
+ else
+ fprintf(fp, "[cannot parse qdisc parameters]");
+ }
+ fprintf(fp, "\n");
+ if (show_details && tb[TCA_STAB]) {
+ print_size_table(fp, " ", tb[TCA_STAB]);
+ fprintf(fp, "\n");
+ }
+ if (show_stats) {
+ struct rtattr *xstats = NULL;
+
+ if (tb[TCA_STATS] || tb[TCA_STATS2] || tb[TCA_XSTATS]) {
+ print_tcstats_attr(fp, tb, " ", &xstats);
+ fprintf(fp, "\n");
+ }
+
+ if (q && xstats && q->print_xstats) {
+ q->print_xstats(q, fp, xstats);
+ fprintf(fp, "\n");
+ }
+ }
+ fflush(fp);
+ return 0;
+}
+
+static int tc_qdisc_list(int argc, char **argv)
+{
+ struct tcmsg t;
+ char d[16];
+
+ memset(&t, 0, sizeof(t));
+ t.tcm_family = AF_UNSPEC;
+ memset(&d, 0, sizeof(d));
+
+ while (argc > 0) {
+ if (strcmp(*argv, "dev") == 0) {
+ NEXT_ARG();
+ strncpy(d, *argv, sizeof(d)-1);
+ } else if (strcmp(*argv, "ingress") == 0 ||
+ strcmp(*argv, "clsact") == 0) {
+ if (t.tcm_parent) {
+ fprintf(stderr, "Duplicate parent ID\n");
+ usage();
+ }
+ t.tcm_parent = TC_H_INGRESS;
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ } else {
+ fprintf(stderr, "What is \"%s\"? Try \"tc qdisc help\".\n", *argv);
+ return -1;
+ }
+
+ argc--; argv++;
+ }
+
+ ll_init_map(&rth);
+
+ if (d[0]) {
+ if ((t.tcm_ifindex = ll_name_to_index(d)) == 0) {
+ fprintf(stderr, "Cannot find device \"%s\"\n", d);
+ return 1;
+ }
+ filter_ifindex = t.tcm_ifindex;
+ }
+
+ if (rtnl_dump_request(&rth, RTM_GETQDISC, &t, sizeof(t)) < 0) {
+ perror("Cannot send dump request");
+ return 1;
+ }
+
+ if (rtnl_dump_filter(&rth, print_qdisc, stdout) < 0) {
+ fprintf(stderr, "Dump terminated\n");
+ return 1;
+ }
+
+ return 0;
+}
+
+int do_qdisc(int argc, char **argv)
+{
+ if (argc < 1)
+ return tc_qdisc_list(0, NULL);
+ if (matches(*argv, "add") == 0)
+ return tc_qdisc_modify(RTM_NEWQDISC, NLM_F_EXCL|NLM_F_CREATE, argc-1, argv+1);
+ if (matches(*argv, "change") == 0)
+ return tc_qdisc_modify(RTM_NEWQDISC, 0, argc-1, argv+1);
+ if (matches(*argv, "replace") == 0)
+ return tc_qdisc_modify(RTM_NEWQDISC, NLM_F_CREATE|NLM_F_REPLACE, argc-1, argv+1);
+ if (matches(*argv, "link") == 0)
+ return tc_qdisc_modify(RTM_NEWQDISC, NLM_F_REPLACE, argc-1, argv+1);
+ if (matches(*argv, "delete") == 0)
+ return tc_qdisc_modify(RTM_DELQDISC, 0, argc-1, argv+1);
+#if 0
+ if (matches(*argv, "get") == 0)
+ return tc_qdisc_get(RTM_GETQDISC, 0, argc-1, argv+1);
+#endif
+ if (matches(*argv, "list") == 0 || matches(*argv, "show") == 0
+ || matches(*argv, "lst") == 0)
+ return tc_qdisc_list(argc-1, argv+1);
+ if (matches(*argv, "help") == 0) {
+ usage();
+ return 0;
+ }
+ fprintf(stderr, "Command \"%s\" is unknown, try \"tc qdisc help\".\n", *argv);
+ return -1;
+}
diff --git a/iproute2/tc/tc_red.c b/iproute2/tc/tc_red.c
new file mode 100644
index 0000000..81a83bd
--- /dev/null
+++ b/iproute2/tc/tc_red.c
@@ -0,0 +1,98 @@
+/*
+ * tc_red.c RED maintanance routines.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <math.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "tc_core.h"
+#include "tc_red.h"
+
+/*
+ Plog = log(prob/(qmax - qmin))
+ */
+int tc_red_eval_P(unsigned qmin, unsigned qmax, double prob)
+{
+ int i = qmax - qmin;
+
+ if (i <= 0)
+ return -1;
+
+ prob /= i;
+
+ for (i=0; i<32; i++) {
+ if (prob > 1.0)
+ break;
+ prob *= 2;
+ }
+ if (i>=32)
+ return -1;
+ return i;
+}
+
+/*
+ burst + 1 - qmin/avpkt < (1-(1-W)^burst)/W
+ */
+
+int tc_red_eval_ewma(unsigned qmin, unsigned burst, unsigned avpkt)
+{
+ int wlog = 1;
+ double W = 0.5;
+ double a = (double)burst + 1 - (double)qmin/avpkt;
+
+ if (a < 1.0) {
+ fprintf(stderr, "tc_red_eval_ewma() burst %u is too small ?"
+ " Try burst %u\n", burst, 1 + qmin/avpkt);
+ return -1;
+ }
+ for (wlog=1; wlog<32; wlog++, W /= 2) {
+ if (a <= (1 - pow(1-W, burst))/W)
+ return wlog;
+ }
+ return -1;
+}
+
+/*
+ Stab[t>>Scell_log] = -log(1-W) * t/xmit_time
+ */
+
+int tc_red_eval_idle_damping(int Wlog, unsigned avpkt, unsigned bps, __u8 *sbuf)
+{
+ double xmit_time = tc_calc_xmittime(bps, avpkt);
+ double lW = -log(1.0 - 1.0/(1<<Wlog))/xmit_time;
+ double maxtime = 31/lW;
+ int clog;
+ int i;
+
+ for (clog=0; clog<32; clog++) {
+ if (maxtime/(1<<clog) < 512)
+ break;
+ }
+ if (clog >= 32)
+ return -1;
+
+ sbuf[0] = 0;
+ for (i=1; i<255; i++) {
+ sbuf[i] = (i<<clog)*lW;
+ if (sbuf[i] > 31)
+ sbuf[i] = 31;
+ }
+ sbuf[255] = 31;
+ return clog;
+}
diff --git a/iproute2/tc/tc_red.h b/iproute2/tc/tc_red.h
new file mode 100644
index 0000000..6f6b09e
--- /dev/null
+++ b/iproute2/tc/tc_red.h
@@ -0,0 +1,8 @@
+#ifndef _TC_RED_H_
+#define _TC_RED_H_ 1
+
+extern int tc_red_eval_P(unsigned qmin, unsigned qmax, double prob);
+extern int tc_red_eval_ewma(unsigned qmin, unsigned burst, unsigned avpkt);
+extern int tc_red_eval_idle_damping(int wlog, unsigned avpkt, unsigned bandwidth, __u8 *sbuf);
+
+#endif
diff --git a/iproute2/tc/tc_stab.c b/iproute2/tc/tc_stab.c
new file mode 100644
index 0000000..aba8ae8
--- /dev/null
+++ b/iproute2/tc/tc_stab.c
@@ -0,0 +1,150 @@
+/*
+ * tc_stab.c "tc qdisc ... stab *".
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Jussi Kivilinna, <jussi.kivilinna@mbnet.fi>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <math.h>
+#include <sys/socket.h>
+#include <sys/param.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <malloc.h>
+
+#include "utils.h"
+#include "tc_util.h"
+#include "tc_core.h"
+#include "tc_common.h"
+
+static void stab_help(void)
+{
+ fprintf(stderr,
+ "Usage: ... stab [ mtu BYTES ] [ tsize SLOTS ] [ mpu BYTES ] \n"
+ " [ overhead BYTES ] [ linklayer TYPE ] ...\n"
+ " mtu : max packet size we create rate map for {2047}\n"
+ " tsize : how many slots should size table have {512}\n"
+ " mpu : minimum packet size used in rate computations\n"
+ " overhead : per-packet size overhead used in rate computations\n"
+ " linklayer : adapting to a linklayer e.g. atm\n"
+ "Example: ... stab overhead 20 linklayer atm\n");
+
+ return;
+}
+
+int check_size_table_opts(struct tc_sizespec *s)
+{
+ return s->linklayer >= LINKLAYER_ETHERNET || s->mpu != 0 ||
+ s->overhead != 0;
+}
+
+int parse_size_table(int *argcp, char ***argvp, struct tc_sizespec *sp)
+{
+ char **argv = *argvp;
+ int argc = *argcp;
+ struct tc_sizespec s;
+
+ memset(&s, 0, sizeof(s));
+
+ NEXT_ARG();
+ if (matches(*argv, "help") == 0) {
+ stab_help();
+ return -1;
+ }
+ while (argc > 0) {
+ if (matches(*argv, "mtu") == 0) {
+ NEXT_ARG();
+ if (s.mtu)
+ duparg("mtu", *argv);
+ if (get_u32(&s.mtu, *argv, 10))
+ invarg("mtu", "invalid mtu");
+ } else if (matches(*argv, "mpu") == 0) {
+ NEXT_ARG();
+ if (s.mpu)
+ duparg("mpu", *argv);
+ if (get_u32(&s.mpu, *argv, 10))
+ invarg("mpu", "invalid mpu");
+ } else if (matches(*argv, "overhead") == 0) {
+ NEXT_ARG();
+ if (s.overhead)
+ duparg("overhead", *argv);
+ if (get_integer(&s.overhead, *argv, 10))
+ invarg("overhead", "invalid overhead");
+ } else if (matches(*argv, "tsize") == 0) {
+ NEXT_ARG();
+ if (s.tsize)
+ duparg("tsize", *argv);
+ if (get_u32(&s.tsize, *argv, 10))
+ invarg("tsize", "invalid table size");
+ } else if (matches(*argv, "linklayer") == 0) {
+ NEXT_ARG();
+ if (s.linklayer != LINKLAYER_UNSPEC)
+ duparg("linklayer", *argv);
+ if (get_linklayer(&s.linklayer, *argv))
+ invarg("linklayer", "invalid linklayer");
+ } else
+ break;
+ argc--; argv++;
+ }
+
+ if (!check_size_table_opts(&s))
+ return -1;
+
+ *sp = s;
+ *argvp = argv;
+ *argcp = argc;
+ return 0;
+}
+
+void print_size_table(FILE *fp, const char *prefix, struct rtattr *rta)
+{
+ struct rtattr *tb[TCA_STAB_MAX + 1];
+ SPRINT_BUF(b1);
+
+ parse_rtattr_nested(tb, TCA_STAB_MAX, rta);
+
+ if (tb[TCA_STAB_BASE]) {
+ struct tc_sizespec s = {0};
+ memcpy(&s, RTA_DATA(tb[TCA_STAB_BASE]),
+ MIN(RTA_PAYLOAD(tb[TCA_STAB_BASE]), sizeof(s)));
+
+ fprintf(fp, "%s", prefix);
+ if (s.linklayer)
+ fprintf(fp, "linklayer %s ",
+ sprint_linklayer(s.linklayer, b1));
+ if (s.overhead)
+ fprintf(fp, "overhead %d ", s.overhead);
+ if (s.mpu)
+ fprintf(fp, "mpu %u ", s.mpu);
+ if (s.mtu)
+ fprintf(fp, "mtu %u ", s.mtu);
+ if (s.tsize)
+ fprintf(fp, "tsize %u ", s.tsize);
+ }
+
+#if 0
+ if (tb[TCA_STAB_DATA]) {
+ unsigned i, j, dlen;
+ __u16 *data = RTA_DATA(tb[TCA_STAB_DATA]);
+ dlen = RTA_PAYLOAD(tb[TCA_STAB_DATA]) / sizeof(__u16);
+
+ fprintf(fp, "\n%sstab data:", prefix);
+ for (i = 0; i < dlen/12; i++) {
+ fprintf(fp, "\n%s %3u:", prefix, i * 12);
+ for (j = 0; i * 12 + j < dlen; j++)
+ fprintf(fp, " %05x", data[i * 12 + j]);
+ }
+ }
+#endif
+}
diff --git a/iproute2/tc/tc_util.c b/iproute2/tc/tc_util.c
new file mode 100644
index 0000000..4764ecc
--- /dev/null
+++ b/iproute2/tc/tc_util.c
@@ -0,0 +1,610 @@
+/*
+ * tc_util.c Misc TC utility functions.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <sys/param.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <math.h>
+#include <errno.h>
+
+#include "utils.h"
+#include "names.h"
+#include "tc_util.h"
+#include "tc_common.h"
+
+#ifndef LIBDIR
+#define LIBDIR "/usr/lib"
+#endif
+
+static struct db_names *cls_names = NULL;
+
+#define NAMES_DB "/etc/iproute2/tc_cls"
+
+int cls_names_init(char *path)
+{
+ int ret;
+
+ cls_names = db_names_alloc();
+ if (!cls_names)
+ return -1;
+
+ ret = db_names_load(cls_names, path ?: NAMES_DB);
+ if (ret == -ENOENT && path) {
+ fprintf(stderr, "Can't open class names file: %s\n", path);
+ return -1;
+ }
+ if (ret) {
+ db_names_free(cls_names);
+ cls_names = NULL;
+ }
+
+ return 0;
+}
+
+void cls_names_uninit(void)
+{
+ db_names_free(cls_names);
+}
+
+const char *get_tc_lib(void)
+{
+ const char *lib_dir;
+
+ lib_dir = getenv("TC_LIB_DIR");
+ if (!lib_dir)
+ lib_dir = LIBDIR "/tc/";
+
+ return lib_dir;
+}
+
+int get_qdisc_handle(__u32 *h, const char *str)
+{
+ __u32 maj;
+ char *p;
+
+ maj = TC_H_UNSPEC;
+ if (strcmp(str, "none") == 0)
+ goto ok;
+ maj = strtoul(str, &p, 16);
+ if (p == str)
+ return -1;
+ maj <<= 16;
+ if (*p != ':' && *p!=0)
+ return -1;
+ok:
+ *h = maj;
+ return 0;
+}
+
+int get_tc_classid(__u32 *h, const char *str)
+{
+ __u32 maj, min;
+ char *p;
+
+ maj = TC_H_ROOT;
+ if (strcmp(str, "root") == 0)
+ goto ok;
+ maj = TC_H_UNSPEC;
+ if (strcmp(str, "none") == 0)
+ goto ok;
+ maj = strtoul(str, &p, 16);
+ if (p == str) {
+ maj = 0;
+ if (*p != ':')
+ return -1;
+ }
+ if (*p == ':') {
+ if (maj >= (1<<16))
+ return -1;
+ maj <<= 16;
+ str = p+1;
+ min = strtoul(str, &p, 16);
+ if (*p != 0)
+ return -1;
+ if (min >= (1<<16))
+ return -1;
+ maj |= min;
+ } else if (*p != 0)
+ return -1;
+
+ok:
+ *h = maj;
+ return 0;
+}
+
+int print_tc_classid(char *buf, int blen, __u32 h)
+{
+ SPRINT_BUF(handle) = {};
+ int hlen = SPRINT_BSIZE - 1;
+
+ if (h == TC_H_ROOT)
+ sprintf(handle, "root");
+ else if (h == TC_H_UNSPEC)
+ snprintf(handle, hlen, "none");
+ else if (TC_H_MAJ(h) == 0)
+ snprintf(handle, hlen, ":%x", TC_H_MIN(h));
+ else if (TC_H_MIN(h) == 0)
+ snprintf(handle, hlen, "%x:", TC_H_MAJ(h) >> 16);
+ else
+ snprintf(handle, hlen, "%x:%x", TC_H_MAJ(h) >> 16, TC_H_MIN(h));
+
+ if (use_names) {
+ char clname[IDNAME_MAX] = {};
+
+ if (id_to_name(cls_names, h, clname))
+ snprintf(buf, blen, "%s#%s", clname, handle);
+ else
+ snprintf(buf, blen, "%s", handle);
+ } else {
+ snprintf(buf, blen, "%s", handle);
+ }
+
+ return 0;
+}
+
+char *sprint_tc_classid(__u32 h, char *buf)
+{
+ if (print_tc_classid(buf, SPRINT_BSIZE-1, h))
+ strcpy(buf, "???");
+ return buf;
+}
+
+/* See http://physics.nist.gov/cuu/Units/binary.html */
+static const struct rate_suffix {
+ const char *name;
+ double scale;
+} suffixes[] = {
+ { "bit", 1. },
+ { "Kibit", 1024. },
+ { "kbit", 1000. },
+ { "mibit", 1024.*1024. },
+ { "mbit", 1000000. },
+ { "gibit", 1024.*1024.*1024. },
+ { "gbit", 1000000000. },
+ { "tibit", 1024.*1024.*1024.*1024. },
+ { "tbit", 1000000000000. },
+ { "Bps", 8. },
+ { "KiBps", 8.*1024. },
+ { "KBps", 8000. },
+ { "MiBps", 8.*1024*1024. },
+ { "MBps", 8000000. },
+ { "GiBps", 8.*1024.*1024.*1024. },
+ { "GBps", 8000000000. },
+ { "TiBps", 8.*1024.*1024.*1024.*1024. },
+ { "TBps", 8000000000000. },
+ { NULL }
+};
+
+
+int get_rate(unsigned *rate, const char *str)
+{
+ char *p;
+ double bps = strtod(str, &p);
+ const struct rate_suffix *s;
+
+ if (p == str)
+ return -1;
+
+ for (s = suffixes; s->name; ++s) {
+ if (strcasecmp(s->name, p) == 0) {
+ bps *= s->scale;
+ p += strlen(p);
+ break;
+ }
+ }
+
+ if (*p)
+ return -1; /* unknown suffix */
+
+ bps /= 8; /* -> bytes per second */
+ *rate = bps;
+ /* detect if an overflow happened */
+ if (*rate != floor(bps))
+ return -1;
+ return 0;
+}
+
+int get_rate64(__u64 *rate, const char *str)
+{
+ char *p;
+ double bps = strtod(str, &p);
+ const struct rate_suffix *s;
+
+ if (p == str)
+ return -1;
+
+ for (s = suffixes; s->name; ++s) {
+ if (strcasecmp(s->name, p) == 0) {
+ bps *= s->scale;
+ p += strlen(p);
+ break;
+ }
+ }
+
+ if (*p)
+ return -1; /* unknown suffix */
+
+ bps /= 8; /* -> bytes per second */
+ *rate = bps;
+ return 0;
+}
+
+void print_rate(char *buf, int len, __u64 rate)
+{
+ extern int use_iec;
+ unsigned long kilo = use_iec ? 1024 : 1000;
+ const char *str = use_iec ? "i" : "";
+ static char *units[5] = {"", "K", "M", "G", "T"};
+ int i;
+
+ rate <<= 3; /* bytes/sec -> bits/sec */
+
+ for (i = 0; i < ARRAY_SIZE(units) - 1; i++) {
+ if (rate < kilo)
+ break;
+ if (((rate % kilo) != 0) && rate < 1000*kilo)
+ break;
+ rate /= kilo;
+ }
+
+ snprintf(buf, len, "%.0f%s%sbit", (double)rate, units[i], str);
+}
+
+char * sprint_rate(__u64 rate, char *buf)
+{
+ print_rate(buf, SPRINT_BSIZE-1, rate);
+ return buf;
+}
+
+int get_time(unsigned *time, const char *str)
+{
+ double t;
+ char *p;
+
+ t = strtod(str, &p);
+ if (p == str)
+ return -1;
+
+ if (*p) {
+ if (strcasecmp(p, "s") == 0 || strcasecmp(p, "sec")==0 ||
+ strcasecmp(p, "secs")==0)
+ t *= TIME_UNITS_PER_SEC;
+ else if (strcasecmp(p, "ms") == 0 || strcasecmp(p, "msec")==0 ||
+ strcasecmp(p, "msecs") == 0)
+ t *= TIME_UNITS_PER_SEC/1000;
+ else if (strcasecmp(p, "us") == 0 || strcasecmp(p, "usec")==0 ||
+ strcasecmp(p, "usecs") == 0)
+ t *= TIME_UNITS_PER_SEC/1000000;
+ else
+ return -1;
+ }
+
+ *time = t;
+ return 0;
+}
+
+
+void print_time(char *buf, int len, __u32 time)
+{
+ double tmp = time;
+
+ if (tmp >= TIME_UNITS_PER_SEC)
+ snprintf(buf, len, "%.1fs", tmp/TIME_UNITS_PER_SEC);
+ else if (tmp >= TIME_UNITS_PER_SEC/1000)
+ snprintf(buf, len, "%.1fms", tmp/(TIME_UNITS_PER_SEC/1000));
+ else
+ snprintf(buf, len, "%uus", time);
+}
+
+char * sprint_time(__u32 time, char *buf)
+{
+ print_time(buf, SPRINT_BSIZE-1, time);
+ return buf;
+}
+
+char * sprint_ticks(__u32 ticks, char *buf)
+{
+ return sprint_time(tc_core_tick2time(ticks), buf);
+}
+
+int get_size(unsigned *size, const char *str)
+{
+ double sz;
+ char *p;
+
+ sz = strtod(str, &p);
+ if (p == str)
+ return -1;
+
+ if (*p) {
+ if (strcasecmp(p, "kb") == 0 || strcasecmp(p, "k")==0)
+ sz *= 1024;
+ else if (strcasecmp(p, "gb") == 0 || strcasecmp(p, "g")==0)
+ sz *= 1024*1024*1024;
+ else if (strcasecmp(p, "gbit") == 0)
+ sz *= 1024*1024*1024/8;
+ else if (strcasecmp(p, "mb") == 0 || strcasecmp(p, "m")==0)
+ sz *= 1024*1024;
+ else if (strcasecmp(p, "mbit") == 0)
+ sz *= 1024*1024/8;
+ else if (strcasecmp(p, "kbit") == 0)
+ sz *= 1024/8;
+ else if (strcasecmp(p, "b") != 0)
+ return -1;
+ }
+
+ *size = sz;
+ return 0;
+}
+
+int get_size_and_cell(unsigned *size, int *cell_log, char *str)
+{
+ char * slash = strchr(str, '/');
+
+ if (slash)
+ *slash = 0;
+
+ if (get_size(size, str))
+ return -1;
+
+ if (slash) {
+ int cell;
+ int i;
+
+ if (get_integer(&cell, slash+1, 0))
+ return -1;
+ *slash = '/';
+
+ for (i=0; i<32; i++) {
+ if ((1<<i) == cell) {
+ *cell_log = i;
+ return 0;
+ }
+ }
+ return -1;
+ }
+ return 0;
+}
+
+void print_size(char *buf, int len, __u32 sz)
+{
+ double tmp = sz;
+
+ if (sz >= 1024*1024 && fabs(1024*1024*rint(tmp/(1024*1024)) - sz) < 1024)
+ snprintf(buf, len, "%gMb", rint(tmp/(1024*1024)));
+ else if (sz >= 1024 && fabs(1024*rint(tmp/1024) - sz) < 16)
+ snprintf(buf, len, "%gKb", rint(tmp/1024));
+ else
+ snprintf(buf, len, "%ub", sz);
+}
+
+char * sprint_size(__u32 size, char *buf)
+{
+ print_size(buf, SPRINT_BSIZE-1, size);
+ return buf;
+}
+
+void print_qdisc_handle(char *buf, int len, __u32 h)
+{
+ snprintf(buf, len, "%x:", TC_H_MAJ(h)>>16);
+}
+
+char * sprint_qdisc_handle(__u32 h, char *buf)
+{
+ print_qdisc_handle(buf, SPRINT_BSIZE-1, h);
+ return buf;
+}
+
+char * action_n2a(int action, char *buf, int len)
+{
+ switch (action) {
+ case -1:
+ return "continue";
+ break;
+ case TC_ACT_OK:
+ return "pass";
+ break;
+ case TC_ACT_SHOT:
+ return "drop";
+ break;
+ case TC_ACT_RECLASSIFY:
+ return "reclassify";
+ case TC_ACT_PIPE:
+ return "pipe";
+ case TC_ACT_STOLEN:
+ return "stolen";
+ default:
+ snprintf(buf, len, "%d", action);
+ return buf;
+ }
+}
+
+int action_a2n(char *arg, int *result)
+{
+ int res;
+
+ if (matches(arg, "continue") == 0)
+ res = -1;
+ else if (matches(arg, "drop") == 0)
+ res = TC_ACT_SHOT;
+ else if (matches(arg, "shot") == 0)
+ res = TC_ACT_SHOT;
+ else if (matches(arg, "pass") == 0)
+ res = TC_ACT_OK;
+ else if (strcmp(arg, "ok") == 0)
+ res = TC_ACT_OK;
+ else if (matches(arg, "reclassify") == 0)
+ res = TC_ACT_RECLASSIFY;
+ else {
+ char dummy;
+ if (sscanf(arg, "%d%c", &res, &dummy) != 1)
+ return -1;
+ }
+ *result = res;
+ return 0;
+}
+
+int get_linklayer(unsigned *val, const char *arg)
+{
+ int res;
+
+ if (matches(arg, "ethernet") == 0)
+ res = LINKLAYER_ETHERNET;
+ else if (matches(arg, "atm") == 0)
+ res = LINKLAYER_ATM;
+ else if (matches(arg, "adsl") == 0)
+ res = LINKLAYER_ATM;
+ else
+ return -1; /* Indicate error */
+
+ *val = res;
+ return 0;
+}
+
+void print_linklayer(char *buf, int len, unsigned linklayer)
+{
+ switch (linklayer) {
+ case LINKLAYER_UNSPEC:
+ snprintf(buf, len, "%s", "unspec");
+ return;
+ case LINKLAYER_ETHERNET:
+ snprintf(buf, len, "%s", "ethernet");
+ return;
+ case LINKLAYER_ATM:
+ snprintf(buf, len, "%s", "atm");
+ return;
+ default:
+ snprintf(buf, len, "%s", "unknown");
+ return;
+ }
+}
+
+char *sprint_linklayer(unsigned linklayer, char *buf)
+{
+ print_linklayer(buf, SPRINT_BSIZE-1, linklayer);
+ return buf;
+}
+
+void print_tm(FILE * f, const struct tcf_t *tm)
+{
+ int hz = get_user_hz();
+ if (tm->install != 0)
+ fprintf(f, " installed %u sec", (unsigned)(tm->install/hz));
+ if (tm->lastuse != 0)
+ fprintf(f, " used %u sec", (unsigned)(tm->lastuse/hz));
+ if (tm->expires != 0)
+ fprintf(f, " expires %u sec", (unsigned)(tm->expires/hz));
+}
+
+void print_tcstats2_attr(FILE *fp, struct rtattr *rta, char *prefix, struct rtattr **xstats)
+{
+ SPRINT_BUF(b1);
+ struct rtattr *tbs[TCA_STATS_MAX + 1];
+
+ parse_rtattr_nested(tbs, TCA_STATS_MAX, rta);
+
+ if (tbs[TCA_STATS_BASIC]) {
+ struct gnet_stats_basic bs = {0};
+ memcpy(&bs, RTA_DATA(tbs[TCA_STATS_BASIC]), MIN(RTA_PAYLOAD(tbs[TCA_STATS_BASIC]), sizeof(bs)));
+ fprintf(fp, "%sSent %llu bytes %u pkt",
+ prefix, (unsigned long long) bs.bytes, bs.packets);
+ }
+
+ if (tbs[TCA_STATS_QUEUE]) {
+ struct gnet_stats_queue q = {0};
+ memcpy(&q, RTA_DATA(tbs[TCA_STATS_QUEUE]), MIN(RTA_PAYLOAD(tbs[TCA_STATS_QUEUE]), sizeof(q)));
+ fprintf(fp, " (dropped %u, overlimits %u requeues %u) ",
+ q.drops, q.overlimits, q.requeues);
+ }
+
+ if (tbs[TCA_STATS_RATE_EST64]) {
+ struct gnet_stats_rate_est64 re = {0};
+
+ memcpy(&re, RTA_DATA(tbs[TCA_STATS_RATE_EST64]),
+ MIN(RTA_PAYLOAD(tbs[TCA_STATS_RATE_EST64]),
+ sizeof(re)));
+ fprintf(fp, "\n%srate %s %llupps ",
+ prefix, sprint_rate(re.bps, b1), re.pps);
+ } else if (tbs[TCA_STATS_RATE_EST]) {
+ struct gnet_stats_rate_est re = {0};
+
+ memcpy(&re, RTA_DATA(tbs[TCA_STATS_RATE_EST]),
+ MIN(RTA_PAYLOAD(tbs[TCA_STATS_RATE_EST]), sizeof(re)));
+ fprintf(fp, "\n%srate %s %upps ",
+ prefix, sprint_rate(re.bps, b1), re.pps);
+ }
+
+ if (tbs[TCA_STATS_QUEUE]) {
+ struct gnet_stats_queue q = {0};
+ memcpy(&q, RTA_DATA(tbs[TCA_STATS_QUEUE]), MIN(RTA_PAYLOAD(tbs[TCA_STATS_QUEUE]), sizeof(q)));
+ if (!tbs[TCA_STATS_RATE_EST])
+ fprintf(fp, "\n%s", prefix);
+ fprintf(fp, "backlog %s %up requeues %u ",
+ sprint_size(q.backlog, b1), q.qlen, q.requeues);
+ }
+
+ if (xstats)
+ *xstats = tbs[TCA_STATS_APP] ? : NULL;
+}
+
+void print_tcstats_attr(FILE *fp, struct rtattr *tb[], char *prefix, struct rtattr **xstats)
+{
+ SPRINT_BUF(b1);
+
+ if (tb[TCA_STATS2]) {
+ print_tcstats2_attr(fp, tb[TCA_STATS2], prefix, xstats);
+ if (xstats && NULL == *xstats)
+ goto compat_xstats;
+ return;
+ }
+ /* backward compatibility */
+ if (tb[TCA_STATS]) {
+ struct tc_stats st;
+
+ /* handle case where kernel returns more/less than we know about */
+ memset(&st, 0, sizeof(st));
+ memcpy(&st, RTA_DATA(tb[TCA_STATS]), MIN(RTA_PAYLOAD(tb[TCA_STATS]), sizeof(st)));
+
+ fprintf(fp, "%sSent %llu bytes %u pkts (dropped %u, overlimits %u) ",
+ prefix, (unsigned long long)st.bytes, st.packets, st.drops,
+ st.overlimits);
+
+ if (st.bps || st.pps || st.qlen || st.backlog) {
+ fprintf(fp, "\n%s", prefix);
+ if (st.bps || st.pps) {
+ fprintf(fp, "rate ");
+ if (st.bps)
+ fprintf(fp, "%s ", sprint_rate(st.bps, b1));
+ if (st.pps)
+ fprintf(fp, "%upps ", st.pps);
+ }
+ if (st.qlen || st.backlog) {
+ fprintf(fp, "backlog ");
+ if (st.backlog)
+ fprintf(fp, "%s ", sprint_size(st.backlog, b1));
+ if (st.qlen)
+ fprintf(fp, "%up ", st.qlen);
+ }
+ }
+ }
+
+compat_xstats:
+ if (tb[TCA_XSTATS] && xstats)
+ *xstats = tb[TCA_XSTATS];
+}
diff --git a/iproute2/tc/tc_util.h b/iproute2/tc/tc_util.h
new file mode 100644
index 0000000..61e60b1
--- /dev/null
+++ b/iproute2/tc/tc_util.h
@@ -0,0 +1,110 @@
+#ifndef _TC_UTIL_H_
+#define _TC_UTIL_H_ 1
+
+#define MAX_MSG 16384
+#include <linux/pkt_sched.h>
+#include <linux/pkt_cls.h>
+#include <linux/gen_stats.h>
+#include "tc_core.h"
+
+/* This is the deprecated multiqueue interface */
+#ifndef TCA_PRIO_MAX
+enum
+{
+ TCA_PRIO_UNSPEC,
+ TCA_PRIO_MQ,
+ __TCA_PRIO_MAX
+};
+
+#define TCA_PRIO_MAX (__TCA_PRIO_MAX - 1)
+#endif
+
+struct qdisc_util {
+ struct qdisc_util *next;
+ const char *id;
+ int (*parse_qopt)(struct qdisc_util *qu, int argc, char **argv, struct nlmsghdr *n);
+ int (*print_qopt)(struct qdisc_util *qu, FILE *f, struct rtattr *opt);
+ int (*print_xstats)(struct qdisc_util *qu, FILE *f, struct rtattr *xstats);
+
+ int (*parse_copt)(struct qdisc_util *qu, int argc, char **argv, struct nlmsghdr *n);
+ int (*print_copt)(struct qdisc_util *qu, FILE *f, struct rtattr *opt);
+};
+
+extern __u16 f_proto;
+struct filter_util {
+ struct filter_util *next;
+ char id[16];
+ int (*parse_fopt)(struct filter_util *qu, char *fhandle, int argc,
+ char **argv, struct nlmsghdr *n);
+ int (*print_fopt)(struct filter_util *qu, FILE *f, struct rtattr *opt, __u32 fhandle);
+};
+
+struct action_util {
+ struct action_util *next;
+ char id[16];
+ int (*parse_aopt)(struct action_util *a, int *argc, char ***argv,
+ int code, struct nlmsghdr *n);
+ int (*print_aopt)(struct action_util *au, FILE *f, struct rtattr *opt);
+ int (*print_xstats)(struct action_util *au, FILE *f, struct rtattr *xstats);
+};
+
+struct exec_util {
+ struct exec_util *next;
+ char id[16];
+ int (*parse_eopt)(struct exec_util *eu, int argc, char **argv);
+};
+
+extern const char *get_tc_lib(void);
+
+extern struct qdisc_util *get_qdisc_kind(const char *str);
+extern struct filter_util *get_filter_kind(const char *str);
+
+extern int get_qdisc_handle(__u32 *h, const char *str);
+extern int get_rate(unsigned *rate, const char *str);
+extern int get_rate64(__u64 *rate, const char *str);
+extern int get_size(unsigned *size, const char *str);
+extern int get_size_and_cell(unsigned *size, int *cell_log, char *str);
+extern int get_time(unsigned *time, const char *str);
+extern int get_linklayer(unsigned *val, const char *arg);
+
+extern void print_rate(char *buf, int len, __u64 rate);
+extern void print_size(char *buf, int len, __u32 size);
+extern void print_qdisc_handle(char *buf, int len, __u32 h);
+extern void print_time(char *buf, int len, __u32 time);
+extern void print_linklayer(char *buf, int len, unsigned linklayer);
+
+extern char * sprint_rate(__u64 rate, char *buf);
+extern char * sprint_size(__u32 size, char *buf);
+extern char * sprint_qdisc_handle(__u32 h, char *buf);
+extern char * sprint_tc_classid(__u32 h, char *buf);
+extern char * sprint_time(__u32 time, char *buf);
+extern char * sprint_ticks(__u32 ticks, char *buf);
+extern char * sprint_linklayer(unsigned linklayer, char *buf);
+
+extern void print_tcstats_attr(FILE *fp, struct rtattr *tb[], char *prefix, struct rtattr **xstats);
+extern void print_tcstats2_attr(FILE *fp, struct rtattr *rta, char *prefix, struct rtattr **xstats);
+
+extern int get_tc_classid(__u32 *h, const char *str);
+extern int print_tc_classid(char *buf, int len, __u32 h);
+extern char * sprint_tc_classid(__u32 h, char *buf);
+
+extern int tc_print_police(FILE *f, struct rtattr *tb);
+extern int parse_police(int *, char ***, int, struct nlmsghdr *);
+
+extern char *action_n2a(int action, char *buf, int len);
+extern int action_a2n(char *arg, int *result);
+extern int act_parse_police(struct action_util *a,int *, char ***, int, struct nlmsghdr *);
+extern int print_police(struct action_util *a, FILE *f,
+ struct rtattr *tb);
+extern int police_print_xstats(struct action_util *a,FILE *f,
+ struct rtattr *tb);
+extern int tc_print_action(FILE *f, const struct rtattr *tb);
+extern int tc_print_ipt(FILE *f, const struct rtattr *tb);
+extern int parse_action(int *, char ***, int, struct nlmsghdr *);
+extern void print_tm(FILE *f, const struct tcf_t *tm);
+extern int prio_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt);
+
+extern int cls_names_init(char *path);
+extern void cls_names_uninit(void);
+
+#endif
diff --git a/iproute2/testsuite/Makefile b/iproute2/testsuite/Makefile
new file mode 100644
index 0000000..2027650
--- /dev/null
+++ b/iproute2/testsuite/Makefile
@@ -0,0 +1,69 @@
+## -- Config --
+DEV := lo
+PREFIX := sudo -E unshare -n
+RESULTS_DIR := results
+## -- End Config --
+
+HAVE_UNSHARED_UTIL := $(shell unshare --version 2> /dev/null)
+
+rwildcard=$(wildcard $1$2) $(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2))
+
+TESTS := $(patsubst tests/%,%,$(call rwildcard,tests/,*.t))
+TESTS_DIR := $(dir $(TESTS))
+
+IPVERS := $(filter-out iproute2/Makefile,$(wildcard iproute2/*))
+
+ifneq (,$(wildcard /proc/config.gz))
+ KENV := $(shell cat /proc/config.gz | gunzip | grep ^CONFIG)
+endif
+
+.PHONY: compile listtests alltests configure $(TESTS)
+
+configure:
+ echo "Entering iproute2" && cd iproute2 && $(MAKE) configure && cd ..;
+
+compile: configure
+ echo "Entering iproute2" && cd iproute2 && $(MAKE) && cd ..;
+
+listtests:
+ @for t in $(TESTS); do \
+ echo "$$t"; \
+ done
+
+alltests: $(TESTS)
+
+clean:
+ @echo "Removing $(RESULTS_DIR) dir ..."
+ @rm -rf $(RESULTS_DIR)
+
+distclean: clean
+ echo "Entering iproute2" && cd iproute2 && $(MAKE) distclean && cd ..;
+
+$(TESTS): clean
+ifeq (,$(HAVE_UNSHARED_UTIL))
+ $(error Please install util-linux tools to run tests in separated network namespace)
+endif
+ @mkdir -p $(RESULTS_DIR)
+
+ @for d in $(TESTS_DIR); do \
+ mkdir -p $(RESULTS_DIR)/$$d; \
+ done
+
+ @for i in $(IPVERS); do \
+ o=`echo $$i | sed -e 's/iproute2\///'`; \
+ echo -n "Running $@ [$$o/`uname -r`]: "; \
+ TMP_ERR=`mktemp /tmp/tc_testsuite.XXXXXX`; \
+ TMP_OUT=`mktemp /tmp/tc_testsuite.XXXXXX`; \
+ STD_ERR="$$TMP_ERR" STD_OUT="$$TMP_OUT" \
+ TC="$$i/tc/tc" IP="$$i/ip/ip" DEV="$(DEV)" IPVER="$@" SNAME="$$i" \
+ ERRF="$(RESULTS_DIR)/$@.$$o.err" $(KENV) $(PREFIX) tests/$@ > $(RESULTS_DIR)/$@.$$o.out; \
+ if [ "$$?" = "127" ]; then \
+ echo "SKIPPED"; \
+ elif [ -e "$(RESULTS_DIR)/$@.$$o.err" ]; then \
+ echo "FAILED"; \
+ else \
+ echo "PASS"; \
+ fi; \
+ rm "$$TMP_ERR" "$$TMP_OUT"; \
+ dmesg > $(RESULTS_DIR)/$@.$$o.dmesg; \
+ done
diff --git a/iproute2/testsuite/configs/all-2.4 b/iproute2/testsuite/configs/all-2.4
new file mode 100644
index 0000000..cc4131c
--- /dev/null
+++ b/iproute2/testsuite/configs/all-2.4
@@ -0,0 +1,848 @@
+#
+# Automatically generated by make menuconfig: don't edit
+#
+CONFIG_X86=y
+# CONFIG_SBUS is not set
+CONFIG_UID16=y
+
+#
+# Code maturity level options
+#
+CONFIG_EXPERIMENTAL=y
+
+#
+# Loadable module support
+#
+CONFIG_MODULES=y
+CONFIG_MODVERSIONS=y
+CONFIG_KMOD=y
+
+#
+# Processor type and features
+#
+# CONFIG_M386 is not set
+# CONFIG_M486 is not set
+# CONFIG_M586 is not set
+# CONFIG_M586TSC is not set
+# CONFIG_M586MMX is not set
+# CONFIG_M686 is not set
+# CONFIG_MPENTIUMIII is not set
+CONFIG_MPENTIUM4=y
+# CONFIG_MK6 is not set
+# CONFIG_MK7 is not set
+# CONFIG_MK8 is not set
+# CONFIG_MELAN is not set
+# CONFIG_MCRUSOE is not set
+# CONFIG_MWINCHIPC6 is not set
+# CONFIG_MWINCHIP2 is not set
+# CONFIG_MWINCHIP3D is not set
+# CONFIG_MCYRIXIII is not set
+# CONFIG_MVIAC3_2 is not set
+CONFIG_X86_WP_WORKS_OK=y
+CONFIG_X86_INVLPG=y
+CONFIG_X86_CMPXCHG=y
+CONFIG_X86_XADD=y
+CONFIG_X86_BSWAP=y
+CONFIG_X86_POPAD_OK=y
+# CONFIG_RWSEM_GENERIC_SPINLOCK is not set
+CONFIG_RWSEM_XCHGADD_ALGORITHM=y
+CONFIG_X86_L1_CACHE_SHIFT=7
+CONFIG_X86_HAS_TSC=y
+CONFIG_X86_GOOD_APIC=y
+CONFIG_X86_PGE=y
+CONFIG_X86_USE_PPRO_CHECKSUM=y
+CONFIG_X86_F00F_WORKS_OK=y
+CONFIG_X86_MCE=y
+# CONFIG_TOSHIBA is not set
+# CONFIG_I8K is not set
+# CONFIG_MICROCODE is not set
+# CONFIG_X86_MSR is not set
+# CONFIG_X86_CPUID is not set
+# CONFIG_EDD is not set
+CONFIG_NOHIGHMEM=y
+# CONFIG_HIGHMEM4G is not set
+# CONFIG_HIGHMEM64G is not set
+# CONFIG_HIGHMEM is not set
+# CONFIG_MATH_EMULATION is not set
+# CONFIG_MTRR is not set
+CONFIG_SMP=y
+CONFIG_NR_CPUS=32
+# CONFIG_X86_NUMA is not set
+# CONFIG_X86_TSC_DISABLE is not set
+CONFIG_X86_TSC=y
+CONFIG_HAVE_DEC_LOCK=y
+
+#
+# General setup
+#
+CONFIG_NET=y
+CONFIG_X86_IO_APIC=y
+CONFIG_X86_LOCAL_APIC=y
+CONFIG_PCI=y
+# CONFIG_PCI_GOBIOS is not set
+# CONFIG_PCI_GODIRECT is not set
+CONFIG_PCI_GOANY=y
+CONFIG_PCI_BIOS=y
+CONFIG_PCI_DIRECT=y
+CONFIG_ISA=y
+CONFIG_PCI_NAMES=y
+# CONFIG_EISA is not set
+# CONFIG_MCA is not set
+CONFIG_HOTPLUG=y
+
+#
+# PCMCIA/CardBus support
+#
+CONFIG_PCMCIA=y
+CONFIG_CARDBUS=y
+# CONFIG_TCIC is not set
+# CONFIG_I82092 is not set
+# CONFIG_I82365 is not set
+
+#
+# PCI Hotplug Support
+#
+# CONFIG_HOTPLUG_PCI is not set
+# CONFIG_HOTPLUG_PCI_COMPAQ is not set
+# CONFIG_HOTPLUG_PCI_COMPAQ_NVRAM is not set
+# CONFIG_HOTPLUG_PCI_IBM is not set
+# CONFIG_HOTPLUG_PCI_SHPC is not set
+# CONFIG_HOTPLUG_PCI_SHPC_POLL_EVENT_MODE is not set
+# CONFIG_HOTPLUG_PCI_SHPC_PHPRM_LEGACY is not set
+# CONFIG_HOTPLUG_PCI_PCIE is not set
+# CONFIG_HOTPLUG_PCI_PCIE_POLL_EVENT_MODE is not set
+CONFIG_SYSVIPC=y
+# CONFIG_BSD_PROCESS_ACCT is not set
+CONFIG_SYSCTL=y
+CONFIG_KCORE_ELF=y
+# CONFIG_KCORE_AOUT is not set
+CONFIG_BINFMT_AOUT=y
+CONFIG_BINFMT_ELF=y
+CONFIG_BINFMT_MISC=y
+# CONFIG_OOM_KILLER is not set
+CONFIG_PM=y
+# CONFIG_APM is not set
+
+#
+# ACPI Support
+#
+# CONFIG_ACPI is not set
+CONFIG_ACPI_BOOT=y
+
+#
+# Memory Technology Devices (MTD)
+#
+# CONFIG_MTD is not set
+
+#
+# Parallel port support
+#
+# CONFIG_PARPORT is not set
+
+#
+# Plug and Play configuration
+#
+CONFIG_PNP=y
+CONFIG_ISAPNP=y
+
+#
+# Block devices
+#
+CONFIG_BLK_DEV_FD=y
+# CONFIG_BLK_DEV_XD is not set
+# CONFIG_PARIDE is not set
+# CONFIG_BLK_CPQ_DA is not set
+# CONFIG_BLK_CPQ_CISS_DA is not set
+# CONFIG_CISS_SCSI_TAPE is not set
+# CONFIG_CISS_MONITOR_THREAD is not set
+# CONFIG_BLK_DEV_DAC960 is not set
+# CONFIG_BLK_DEV_UMEM is not set
+# CONFIG_BLK_DEV_SX8 is not set
+# CONFIG_BLK_DEV_LOOP is not set
+# CONFIG_BLK_DEV_NBD is not set
+# CONFIG_BLK_DEV_RAM is not set
+# CONFIG_BLK_DEV_INITRD is not set
+# CONFIG_BLK_STATS is not set
+
+#
+# Multi-device support (RAID and LVM)
+#
+# CONFIG_MD is not set
+# CONFIG_BLK_DEV_MD is not set
+# CONFIG_MD_LINEAR is not set
+# CONFIG_MD_RAID0 is not set
+# CONFIG_MD_RAID1 is not set
+# CONFIG_MD_RAID5 is not set
+# CONFIG_MD_MULTIPATH is not set
+# CONFIG_BLK_DEV_LVM is not set
+
+#
+# Networking options
+#
+CONFIG_PACKET=y
+# CONFIG_PACKET_MMAP is not set
+# CONFIG_NETLINK_DEV is not set
+# CONFIG_NETFILTER is not set
+# CONFIG_FILTER is not set
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_ROUTE_NAT=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_TOS=y
+# CONFIG_IP_ROUTE_VERBOSE is not set
+# CONFIG_IP_PNP is not set
+# CONFIG_NET_IPIP is not set
+# CONFIG_NET_IPGRE is not set
+# CONFIG_IP_MROUTE is not set
+# CONFIG_ARPD is not set
+# CONFIG_INET_ECN is not set
+# CONFIG_SYN_COOKIES is not set
+# CONFIG_IPV6 is not set
+# CONFIG_KHTTPD is not set
+
+#
+# SCTP Configuration (EXPERIMENTAL)
+#
+# CONFIG_IP_SCTP is not set
+CONFIG_ATM=y
+CONFIG_ATM_CLIP=y
+# CONFIG_ATM_CLIP_NO_ICMP is not set
+# CONFIG_ATM_LANE is not set
+# CONFIG_ATM_BR2684 is not set
+# CONFIG_VLAN_8021Q is not set
+# CONFIG_IPX is not set
+# CONFIG_ATALK is not set
+
+#
+# Appletalk devices
+#
+# CONFIG_DEV_APPLETALK is not set
+# CONFIG_DECNET is not set
+# CONFIG_BRIDGE is not set
+# CONFIG_X25 is not set
+# CONFIG_LAPB is not set
+# CONFIG_LLC is not set
+# CONFIG_NET_DIVERT is not set
+# CONFIG_ECONET is not set
+# CONFIG_WAN_ROUTER is not set
+# CONFIG_NET_FASTROUTE is not set
+# CONFIG_NET_HW_FLOWCONTROL is not set
+
+#
+# QoS and/or fair queueing
+#
+CONFIG_NET_SCHED=y
+CONFIG_NET_SCH_CBQ=y
+CONFIG_NET_SCH_HTB=y
+CONFIG_NET_SCH_CSZ=y
+CONFIG_NET_SCH_HFSC=y
+CONFIG_NET_SCH_ATM=y
+CONFIG_NET_SCH_PRIO=y
+CONFIG_NET_SCH_RED=y
+CONFIG_NET_SCH_SFQ=y
+CONFIG_NET_SCH_TEQL=y
+CONFIG_NET_SCH_TBF=y
+CONFIG_NET_SCH_GRED=y
+CONFIG_NET_SCH_NETEM=y
+CONFIG_NET_SCH_DSMARK=y
+CONFIG_NET_QOS=y
+CONFIG_NET_ESTIMATOR=y
+CONFIG_NET_CLS=y
+CONFIG_NET_CLS_TCINDEX=y
+CONFIG_NET_CLS_ROUTE4=y
+CONFIG_NET_CLS_ROUTE=y
+CONFIG_NET_CLS_FW=y
+CONFIG_NET_CLS_U32=y
+CONFIG_NET_CLS_RSVP=y
+CONFIG_NET_CLS_RSVP6=y
+CONFIG_NET_CLS_POLICE=y
+
+#
+# Network testing
+#
+# CONFIG_NET_PKTGEN is not set
+
+#
+# Telephony Support
+#
+# CONFIG_PHONE is not set
+# CONFIG_PHONE_IXJ is not set
+# CONFIG_PHONE_IXJ_PCMCIA is not set
+
+#
+# ATA/IDE/MFM/RLL support
+#
+CONFIG_IDE=y
+
+#
+# IDE, ATA and ATAPI Block devices
+#
+CONFIG_BLK_DEV_IDE=y
+# CONFIG_BLK_DEV_HD_IDE is not set
+# CONFIG_BLK_DEV_HD is not set
+# CONFIG_BLK_DEV_IDE_SATA is not set
+CONFIG_BLK_DEV_IDEDISK=y
+CONFIG_IDEDISK_MULTI_MODE=y
+# CONFIG_IDEDISK_STROKE is not set
+# CONFIG_BLK_DEV_IDECS is not set
+# CONFIG_BLK_DEV_DELKIN is not set
+CONFIG_BLK_DEV_IDECD=y
+# CONFIG_BLK_DEV_IDETAPE is not set
+# CONFIG_BLK_DEV_IDEFLOPPY is not set
+# CONFIG_BLK_DEV_IDESCSI is not set
+# CONFIG_IDE_TASK_IOCTL is not set
+CONFIG_BLK_DEV_CMD640=y
+# CONFIG_BLK_DEV_CMD640_ENHANCED is not set
+# CONFIG_BLK_DEV_ISAPNP is not set
+CONFIG_BLK_DEV_IDEPCI=y
+# CONFIG_BLK_DEV_GENERIC is not set
+CONFIG_IDEPCI_SHARE_IRQ=y
+CONFIG_BLK_DEV_IDEDMA_PCI=y
+# CONFIG_BLK_DEV_OFFBOARD is not set
+# CONFIG_BLK_DEV_IDEDMA_FORCED is not set
+CONFIG_IDEDMA_PCI_AUTO=y
+# CONFIG_IDEDMA_ONLYDISK is not set
+CONFIG_BLK_DEV_IDEDMA=y
+# CONFIG_IDEDMA_PCI_WIP is not set
+# CONFIG_BLK_DEV_ADMA100 is not set
+# CONFIG_BLK_DEV_AEC62XX is not set
+# CONFIG_BLK_DEV_ALI15X3 is not set
+# CONFIG_WDC_ALI15X3 is not set
+# CONFIG_BLK_DEV_AMD74XX is not set
+# CONFIG_AMD74XX_OVERRIDE is not set
+# CONFIG_BLK_DEV_ATIIXP is not set
+# CONFIG_BLK_DEV_CMD64X is not set
+# CONFIG_BLK_DEV_TRIFLEX is not set
+# CONFIG_BLK_DEV_CY82C693 is not set
+# CONFIG_BLK_DEV_CS5530 is not set
+# CONFIG_BLK_DEV_HPT34X is not set
+# CONFIG_HPT34X_AUTODMA is not set
+# CONFIG_BLK_DEV_HPT366 is not set
+CONFIG_BLK_DEV_PIIX=y
+# CONFIG_BLK_DEV_NS87415 is not set
+# CONFIG_BLK_DEV_OPTI621 is not set
+# CONFIG_BLK_DEV_PDC202XX_OLD is not set
+# CONFIG_PDC202XX_BURST is not set
+# CONFIG_BLK_DEV_PDC202XX_NEW is not set
+CONFIG_BLK_DEV_RZ1000=y
+# CONFIG_BLK_DEV_SC1200 is not set
+# CONFIG_BLK_DEV_SVWKS is not set
+# CONFIG_BLK_DEV_SIIMAGE is not set
+# CONFIG_BLK_DEV_SIS5513 is not set
+# CONFIG_BLK_DEV_SLC90E66 is not set
+# CONFIG_BLK_DEV_TRM290 is not set
+# CONFIG_BLK_DEV_VIA82CXXX is not set
+# CONFIG_IDE_CHIPSETS is not set
+CONFIG_IDEDMA_AUTO=y
+# CONFIG_IDEDMA_IVB is not set
+# CONFIG_DMA_NONPCI is not set
+# CONFIG_BLK_DEV_ATARAID is not set
+# CONFIG_BLK_DEV_ATARAID_PDC is not set
+# CONFIG_BLK_DEV_ATARAID_HPT is not set
+# CONFIG_BLK_DEV_ATARAID_MEDLEY is not set
+# CONFIG_BLK_DEV_ATARAID_SII is not set
+
+#
+# SCSI support
+#
+# CONFIG_SCSI is not set
+
+#
+# Fusion MPT device support
+#
+# CONFIG_FUSION is not set
+# CONFIG_FUSION_BOOT is not set
+# CONFIG_FUSION_ISENSE is not set
+# CONFIG_FUSION_CTL is not set
+# CONFIG_FUSION_LAN is not set
+
+#
+# IEEE 1394 (FireWire) support (EXPERIMENTAL)
+#
+# CONFIG_IEEE1394 is not set
+
+#
+# I2O device support
+#
+# CONFIG_I2O is not set
+# CONFIG_I2O_PCI is not set
+# CONFIG_I2O_BLOCK is not set
+# CONFIG_I2O_LAN is not set
+# CONFIG_I2O_SCSI is not set
+# CONFIG_I2O_PROC is not set
+
+#
+# Network device support
+#
+CONFIG_NETDEVICES=y
+
+#
+# ARCnet devices
+#
+# CONFIG_ARCNET is not set
+CONFIG_DUMMY=m
+# CONFIG_BONDING is not set
+# CONFIG_EQUALIZER is not set
+# CONFIG_TUN is not set
+# CONFIG_ETHERTAP is not set
+# CONFIG_NET_SB1000 is not set
+
+#
+# Ethernet (10 or 100Mbit)
+#
+CONFIG_NET_ETHERNET=y
+# CONFIG_SUNLANCE is not set
+# CONFIG_HAPPYMEAL is not set
+# CONFIG_SUNBMAC is not set
+# CONFIG_SUNQE is not set
+# CONFIG_SUNGEM is not set
+# CONFIG_NET_VENDOR_3COM is not set
+# CONFIG_LANCE is not set
+# CONFIG_NET_VENDOR_SMC is not set
+# CONFIG_NET_VENDOR_RACAL is not set
+# CONFIG_AT1700 is not set
+# CONFIG_DEPCA is not set
+# CONFIG_HP100 is not set
+# CONFIG_NET_ISA is not set
+CONFIG_NET_PCI=y
+# CONFIG_PCNET32 is not set
+# CONFIG_AMD8111_ETH is not set
+# CONFIG_ADAPTEC_STARFIRE is not set
+# CONFIG_AC3200 is not set
+# CONFIG_APRICOT is not set
+# CONFIG_B44 is not set
+# CONFIG_CS89x0 is not set
+# CONFIG_TULIP is not set
+# CONFIG_DE4X5 is not set
+# CONFIG_DGRS is not set
+# CONFIG_DM9102 is not set
+# CONFIG_EEPRO100 is not set
+# CONFIG_EEPRO100_PIO is not set
+# CONFIG_E100 is not set
+# CONFIG_LNE390 is not set
+# CONFIG_FEALNX is not set
+# CONFIG_NATSEMI is not set
+# CONFIG_NE2K_PCI is not set
+# CONFIG_FORCEDETH is not set
+# CONFIG_NE3210 is not set
+# CONFIG_ES3210 is not set
+# CONFIG_8139CP is not set
+CONFIG_8139TOO=y
+CONFIG_8139TOO_PIO=y
+# CONFIG_8139TOO_TUNE_TWISTER is not set
+# CONFIG_8139TOO_8129 is not set
+# CONFIG_8139_OLD_RX_RESET is not set
+# CONFIG_SIS900 is not set
+# CONFIG_EPIC100 is not set
+# CONFIG_SUNDANCE is not set
+# CONFIG_SUNDANCE_MMIO is not set
+# CONFIG_TLAN is not set
+# CONFIG_VIA_RHINE is not set
+# CONFIG_VIA_RHINE_MMIO is not set
+# CONFIG_WINBOND_840 is not set
+# CONFIG_NET_POCKET is not set
+
+#
+# Ethernet (1000 Mbit)
+#
+# CONFIG_ACENIC is not set
+# CONFIG_DL2K is not set
+# CONFIG_E1000 is not set
+# CONFIG_MYRI_SBUS is not set
+# CONFIG_NS83820 is not set
+# CONFIG_HAMACHI is not set
+# CONFIG_YELLOWFIN is not set
+# CONFIG_R8169 is not set
+# CONFIG_SK98LIN is not set
+# CONFIG_TIGON3 is not set
+# CONFIG_FDDI is not set
+# CONFIG_HIPPI is not set
+# CONFIG_PLIP is not set
+# CONFIG_PPP is not set
+# CONFIG_SLIP is not set
+
+#
+# Wireless LAN (non-hamradio)
+#
+# CONFIG_NET_RADIO is not set
+
+#
+# Token Ring devices
+#
+# CONFIG_TR is not set
+# CONFIG_NET_FC is not set
+# CONFIG_RCPCI is not set
+# CONFIG_SHAPER is not set
+
+#
+# Wan interfaces
+#
+# CONFIG_WAN is not set
+
+#
+# PCMCIA network device support
+#
+# CONFIG_NET_PCMCIA is not set
+
+#
+# ATM drivers
+#
+# CONFIG_ATM_TCP is not set
+# CONFIG_ATM_LANAI is not set
+# CONFIG_ATM_ENI is not set
+# CONFIG_ATM_FIRESTREAM is not set
+# CONFIG_ATM_ZATM is not set
+# CONFIG_ATM_NICSTAR is not set
+# CONFIG_ATM_IDT77252 is not set
+# CONFIG_ATM_AMBASSADOR is not set
+# CONFIG_ATM_HORIZON is not set
+# CONFIG_ATM_IA is not set
+# CONFIG_ATM_FORE200E_MAYBE is not set
+# CONFIG_ATM_HE is not set
+
+#
+# Amateur Radio support
+#
+# CONFIG_HAMRADIO is not set
+
+#
+# IrDA (infrared) support
+#
+# CONFIG_IRDA is not set
+
+#
+# ISDN subsystem
+#
+# CONFIG_ISDN is not set
+
+#
+# Old CD-ROM drivers (not SCSI, not IDE)
+#
+# CONFIG_CD_NO_IDESCSI is not set
+
+#
+# Input core support
+#
+# CONFIG_INPUT is not set
+# CONFIG_INPUT_KEYBDEV is not set
+# CONFIG_INPUT_MOUSEDEV is not set
+# CONFIG_INPUT_JOYDEV is not set
+# CONFIG_INPUT_EVDEV is not set
+# CONFIG_INPUT_UINPUT is not set
+
+#
+# Character devices
+#
+CONFIG_VT=y
+CONFIG_VT_CONSOLE=y
+CONFIG_SERIAL=y
+# CONFIG_SERIAL_CONSOLE is not set
+# CONFIG_SERIAL_EXTENDED is not set
+# CONFIG_SERIAL_NONSTANDARD is not set
+CONFIG_UNIX98_PTYS=y
+CONFIG_UNIX98_PTY_COUNT=256
+
+#
+# I2C support
+#
+# CONFIG_I2C is not set
+
+#
+# Mice
+#
+# CONFIG_BUSMOUSE is not set
+CONFIG_MOUSE=y
+CONFIG_PSMOUSE=y
+# CONFIG_82C710_MOUSE is not set
+# CONFIG_PC110_PAD is not set
+# CONFIG_MK712_MOUSE is not set
+
+#
+# Joysticks
+#
+# CONFIG_INPUT_GAMEPORT is not set
+# CONFIG_QIC02_TAPE is not set
+# CONFIG_IPMI_HANDLER is not set
+# CONFIG_IPMI_PANIC_EVENT is not set
+# CONFIG_IPMI_DEVICE_INTERFACE is not set
+# CONFIG_IPMI_KCS is not set
+# CONFIG_IPMI_WATCHDOG is not set
+
+#
+# Watchdog Cards
+#
+# CONFIG_WATCHDOG is not set
+# CONFIG_SCx200 is not set
+# CONFIG_SCx200_GPIO is not set
+# CONFIG_AMD_RNG is not set
+# CONFIG_INTEL_RNG is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_AMD_PM768 is not set
+# CONFIG_NVRAM is not set
+# CONFIG_RTC is not set
+# CONFIG_DTLK is not set
+# CONFIG_R3964 is not set
+# CONFIG_APPLICOM is not set
+# CONFIG_SONYPI is not set
+
+#
+# Ftape, the floppy tape device driver
+#
+# CONFIG_FTAPE is not set
+# CONFIG_AGP is not set
+
+#
+# Direct Rendering Manager (XFree86 DRI support)
+#
+# CONFIG_DRM is not set
+
+#
+# PCMCIA character devices
+#
+# CONFIG_PCMCIA_SERIAL_CS is not set
+# CONFIG_SYNCLINK_CS is not set
+# CONFIG_MWAVE is not set
+# CONFIG_OBMOUSE is not set
+
+#
+# Multimedia devices
+#
+# CONFIG_VIDEO_DEV is not set
+
+#
+# File systems
+#
+# CONFIG_QUOTA is not set
+# CONFIG_QFMT_V2 is not set
+# CONFIG_AUTOFS_FS is not set
+CONFIG_AUTOFS4_FS=y
+# CONFIG_REISERFS_FS is not set
+# CONFIG_REISERFS_CHECK is not set
+# CONFIG_REISERFS_PROC_INFO is not set
+# CONFIG_ADFS_FS is not set
+# CONFIG_ADFS_FS_RW is not set
+# CONFIG_AFFS_FS is not set
+# CONFIG_HFS_FS is not set
+# CONFIG_HFSPLUS_FS is not set
+# CONFIG_BEFS_FS is not set
+# CONFIG_BEFS_DEBUG is not set
+# CONFIG_BFS_FS is not set
+# CONFIG_EXT3_FS is not set
+# CONFIG_JBD is not set
+# CONFIG_JBD_DEBUG is not set
+# CONFIG_FAT_FS is not set
+# CONFIG_MSDOS_FS is not set
+# CONFIG_UMSDOS_FS is not set
+# CONFIG_VFAT_FS is not set
+# CONFIG_EFS_FS is not set
+# CONFIG_JFFS_FS is not set
+# CONFIG_JFFS2_FS is not set
+# CONFIG_CRAMFS is not set
+CONFIG_TMPFS=y
+CONFIG_RAMFS=y
+CONFIG_ISO9660_FS=y
+# CONFIG_JOLIET is not set
+# CONFIG_ZISOFS is not set
+# CONFIG_JFS_FS is not set
+# CONFIG_JFS_DEBUG is not set
+# CONFIG_JFS_STATISTICS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_VXFS_FS is not set
+# CONFIG_NTFS_FS is not set
+# CONFIG_NTFS_RW is not set
+# CONFIG_HPFS_FS is not set
+CONFIG_PROC_FS=y
+# CONFIG_DEVFS_FS is not set
+# CONFIG_DEVFS_MOUNT is not set
+# CONFIG_DEVFS_DEBUG is not set
+CONFIG_DEVPTS_FS=y
+# CONFIG_QNX4FS_FS is not set
+# CONFIG_QNX4FS_RW is not set
+# CONFIG_ROMFS_FS is not set
+CONFIG_EXT2_FS=y
+# CONFIG_SYSV_FS is not set
+# CONFIG_UDF_FS is not set
+# CONFIG_UDF_RW is not set
+# CONFIG_UFS_FS is not set
+# CONFIG_UFS_FS_WRITE is not set
+# CONFIG_XFS_FS is not set
+# CONFIG_XFS_QUOTA is not set
+# CONFIG_XFS_RT is not set
+# CONFIG_XFS_TRACE is not set
+# CONFIG_XFS_DEBUG is not set
+
+#
+# Network File Systems
+#
+# CONFIG_CODA_FS is not set
+# CONFIG_INTERMEZZO_FS is not set
+CONFIG_NFS_FS=y
+# CONFIG_NFS_V3 is not set
+# CONFIG_NFS_DIRECTIO is not set
+# CONFIG_ROOT_NFS is not set
+CONFIG_NFSD=y
+# CONFIG_NFSD_V3 is not set
+CONFIG_NFSD_TCP=y
+CONFIG_SUNRPC=y
+CONFIG_LOCKD=y
+# CONFIG_SMB_FS is not set
+# CONFIG_NCP_FS is not set
+# CONFIG_NCPFS_PACKET_SIGNING is not set
+# CONFIG_NCPFS_IOCTL_LOCKING is not set
+# CONFIG_NCPFS_STRONG is not set
+# CONFIG_NCPFS_NFS_NS is not set
+# CONFIG_NCPFS_OS2_NS is not set
+# CONFIG_NCPFS_SMALLDOS is not set
+# CONFIG_NCPFS_NLS is not set
+# CONFIG_NCPFS_EXTRAS is not set
+# CONFIG_ZISOFS_FS is not set
+
+#
+# Partition Types
+#
+# CONFIG_PARTITION_ADVANCED is not set
+CONFIG_MSDOS_PARTITION=y
+# CONFIG_SMB_NLS is not set
+# CONFIG_NLS is not set
+
+#
+# Console drivers
+#
+CONFIG_VGA_CONSOLE=y
+# CONFIG_VIDEO_SELECT is not set
+# CONFIG_MDA_CONSOLE is not set
+
+#
+# Frame-buffer support
+#
+# CONFIG_FB is not set
+
+#
+# Sound
+#
+CONFIG_SOUND=y
+# CONFIG_SOUND_ALI5455 is not set
+# CONFIG_SOUND_BT878 is not set
+# CONFIG_SOUND_CMPCI is not set
+CONFIG_SOUND_EMU10K1=y
+CONFIG_MIDI_EMU10K1=y
+# CONFIG_SOUND_FUSION is not set
+# CONFIG_SOUND_CS4281 is not set
+# CONFIG_SOUND_ES1370 is not set
+# CONFIG_SOUND_ES1371 is not set
+# CONFIG_SOUND_ESSSOLO1 is not set
+# CONFIG_SOUND_MAESTRO is not set
+# CONFIG_SOUND_MAESTRO3 is not set
+# CONFIG_SOUND_FORTE is not set
+# CONFIG_SOUND_ICH is not set
+# CONFIG_SOUND_RME96XX is not set
+# CONFIG_SOUND_SONICVIBES is not set
+# CONFIG_SOUND_TRIDENT is not set
+# CONFIG_SOUND_MSNDCLAS is not set
+# CONFIG_SOUND_MSNDPIN is not set
+# CONFIG_SOUND_VIA82CXXX is not set
+# CONFIG_MIDI_VIA82CXXX is not set
+# CONFIG_SOUND_OSS is not set
+# CONFIG_SOUND_TVMIXER is not set
+# CONFIG_SOUND_AD1980 is not set
+# CONFIG_SOUND_WM97XX is not set
+
+#
+# USB support
+#
+CONFIG_USB=y
+# CONFIG_USB_DEBUG is not set
+# CONFIG_USB_DEVICEFS is not set
+# CONFIG_USB_BANDWIDTH is not set
+# CONFIG_USB_EHCI_HCD is not set
+CONFIG_USB_UHCI_ALT=y
+# CONFIG_USB_OHCI is not set
+# CONFIG_USB_SL811HS_ALT is not set
+# CONFIG_USB_SL811HS is not set
+# CONFIG_USB_AUDIO is not set
+# CONFIG_USB_EMI26 is not set
+# CONFIG_USB_BLUETOOTH is not set
+# CONFIG_USB_MIDI is not set
+# CONFIG_USB_STORAGE is not set
+# CONFIG_USB_STORAGE_DEBUG is not set
+# CONFIG_USB_STORAGE_DATAFAB is not set
+# CONFIG_USB_STORAGE_FREECOM is not set
+# CONFIG_USB_STORAGE_ISD200 is not set
+# CONFIG_USB_STORAGE_DPCM is not set
+# CONFIG_USB_STORAGE_HP8200e is not set
+# CONFIG_USB_STORAGE_SDDR09 is not set
+# CONFIG_USB_STORAGE_SDDR55 is not set
+# CONFIG_USB_STORAGE_JUMPSHOT is not set
+# CONFIG_USB_ACM is not set
+# CONFIG_USB_PRINTER is not set
+# CONFIG_USB_HID is not set
+# CONFIG_USB_HIDINPUT is not set
+# CONFIG_USB_HIDDEV is not set
+# CONFIG_USB_KBD is not set
+# CONFIG_USB_MOUSE is not set
+# CONFIG_USB_AIPTEK is not set
+# CONFIG_USB_WACOM is not set
+# CONFIG_USB_KBTAB is not set
+# CONFIG_USB_POWERMATE is not set
+# CONFIG_USB_DC2XX is not set
+# CONFIG_USB_MDC800 is not set
+# CONFIG_USB_SCANNER is not set
+# CONFIG_USB_MICROTEK is not set
+# CONFIG_USB_HPUSBSCSI is not set
+# CONFIG_USB_PEGASUS is not set
+# CONFIG_USB_RTL8150 is not set
+# CONFIG_USB_KAWETH is not set
+# CONFIG_USB_CATC is not set
+# CONFIG_USB_CDCETHER is not set
+# CONFIG_USB_USBNET is not set
+# CONFIG_USB_USS720 is not set
+
+#
+# USB Serial Converter support
+#
+# CONFIG_USB_SERIAL is not set
+# CONFIG_USB_RIO500 is not set
+# CONFIG_USB_AUERSWALD is not set
+# CONFIG_USB_TIGL is not set
+# CONFIG_USB_BRLVGER is not set
+# CONFIG_USB_LCD is not set
+# CONFIG_USB_SPEEDTOUCH is not set
+
+#
+# Support for USB gadgets
+#
+# CONFIG_USB_GADGET is not set
+
+#
+# Bluetooth support
+#
+# CONFIG_BLUEZ is not set
+
+#
+# Kernel hacking
+#
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DEBUG_STACKOVERFLOW=y
+CONFIG_DEBUG_HIGHMEM=y
+CONFIG_DEBUG_SLAB=y
+CONFIG_DEBUG_IOVIRT=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_SPINLOCK=y
+CONFIG_FRAME_POINTER=y
+CONFIG_LOG_BUF_SHIFT=0
+
+#
+# Cryptographic options
+#
+# CONFIG_CRYPTO is not set
+
+#
+# Library routines
+#
+CONFIG_CRC32=y
+# CONFIG_ZLIB_INFLATE is not set
+# CONFIG_ZLIB_DEFLATE is not set
+# CONFIG_FW_LOADER is not set
diff --git a/iproute2/testsuite/configs/all-no-act b/iproute2/testsuite/configs/all-no-act
new file mode 100644
index 0000000..baeed43
--- /dev/null
+++ b/iproute2/testsuite/configs/all-no-act
@@ -0,0 +1,1499 @@
+#
+# Automatically generated make config: don't edit
+# Linux kernel version: 2.6.10-rc2-bk13
+# Wed Dec 8 14:43:07 2004
+#
+CONFIG_X86=y
+CONFIG_MMU=y
+CONFIG_UID16=y
+CONFIG_GENERIC_ISA_DMA=y
+CONFIG_GENERIC_IOMAP=y
+
+#
+# Code maturity level options
+#
+CONFIG_EXPERIMENTAL=y
+CONFIG_CLEAN_COMPILE=y
+CONFIG_LOCK_KERNEL=y
+
+#
+# General setup
+#
+CONFIG_LOCALVERSION="no-act"
+CONFIG_SWAP=y
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+# CONFIG_BSD_PROCESS_ACCT is not set
+CONFIG_SYSCTL=y
+CONFIG_AUDIT=y
+CONFIG_AUDITSYSCALL=y
+CONFIG_LOG_BUF_SHIFT=14
+CONFIG_HOTPLUG=y
+CONFIG_KOBJECT_UEVENT=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+# CONFIG_EMBEDDED is not set
+CONFIG_KALLSYMS=y
+# CONFIG_KALLSYMS_ALL is not set
+# CONFIG_KALLSYMS_EXTRA_PASS is not set
+CONFIG_FUTEX=y
+CONFIG_EPOLL=y
+# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
+CONFIG_SHMEM=y
+CONFIG_CC_ALIGN_FUNCTIONS=0
+CONFIG_CC_ALIGN_LABELS=0
+CONFIG_CC_ALIGN_LOOPS=0
+CONFIG_CC_ALIGN_JUMPS=0
+# CONFIG_TINY_SHMEM is not set
+
+#
+# Loadable module support
+#
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_OBSOLETE_MODPARM=y
+# CONFIG_MODVERSIONS is not set
+# CONFIG_MODULE_SRCVERSION_ALL is not set
+CONFIG_KMOD=y
+CONFIG_STOP_MACHINE=y
+
+#
+# Processor type and features
+#
+CONFIG_X86_PC=y
+# CONFIG_X86_ELAN is not set
+# CONFIG_X86_VOYAGER is not set
+# CONFIG_X86_NUMAQ is not set
+# CONFIG_X86_SUMMIT is not set
+# CONFIG_X86_BIGSMP is not set
+# CONFIG_X86_VISWS is not set
+# CONFIG_X86_GENERICARCH is not set
+# CONFIG_X86_ES7000 is not set
+# CONFIG_M386 is not set
+# CONFIG_M486 is not set
+# CONFIG_M586 is not set
+# CONFIG_M586TSC is not set
+# CONFIG_M586MMX is not set
+# CONFIG_M686 is not set
+# CONFIG_MPENTIUMII is not set
+# CONFIG_MPENTIUMIII is not set
+# CONFIG_MPENTIUMM is not set
+CONFIG_MPENTIUM4=y
+# CONFIG_MK6 is not set
+# CONFIG_MK7 is not set
+# CONFIG_MK8 is not set
+# CONFIG_MCRUSOE is not set
+# CONFIG_MEFFICEON is not set
+# CONFIG_MWINCHIPC6 is not set
+# CONFIG_MWINCHIP2 is not set
+# CONFIG_MWINCHIP3D is not set
+# CONFIG_MCYRIXIII is not set
+# CONFIG_MVIAC3_2 is not set
+# CONFIG_X86_GENERIC is not set
+CONFIG_X86_CMPXCHG=y
+CONFIG_X86_XADD=y
+CONFIG_X86_L1_CACHE_SHIFT=7
+CONFIG_RWSEM_XCHGADD_ALGORITHM=y
+CONFIG_X86_WP_WORKS_OK=y
+CONFIG_X86_INVLPG=y
+CONFIG_X86_BSWAP=y
+CONFIG_X86_POPAD_OK=y
+CONFIG_X86_GOOD_APIC=y
+CONFIG_X86_INTEL_USERCOPY=y
+CONFIG_X86_USE_PPRO_CHECKSUM=y
+# CONFIG_HPET_TIMER is not set
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+# CONFIG_SCHED_SMT is not set
+CONFIG_PREEMPT=y
+CONFIG_X86_LOCAL_APIC=y
+CONFIG_X86_IO_APIC=y
+CONFIG_X86_TSC=y
+CONFIG_X86_MCE=y
+CONFIG_X86_MCE_NONFATAL=y
+# CONFIG_X86_MCE_P4THERMAL is not set
+# CONFIG_TOSHIBA is not set
+# CONFIG_I8K is not set
+# CONFIG_MICROCODE is not set
+# CONFIG_X86_MSR is not set
+# CONFIG_X86_CPUID is not set
+
+#
+# Firmware Drivers
+#
+# CONFIG_EDD is not set
+CONFIG_NOHIGHMEM=y
+# CONFIG_HIGHMEM4G is not set
+# CONFIG_HIGHMEM64G is not set
+# CONFIG_MATH_EMULATION is not set
+CONFIG_MTRR=y
+# CONFIG_EFI is not set
+CONFIG_IRQBALANCE=y
+CONFIG_HAVE_DEC_LOCK=y
+# CONFIG_REGPARM is not set
+
+#
+# Power management options (ACPI, APM)
+#
+CONFIG_PM=y
+# CONFIG_PM_DEBUG is not set
+CONFIG_SOFTWARE_SUSPEND=y
+CONFIG_PM_STD_PARTITION=""
+
+#
+# ACPI (Advanced Configuration and Power Interface) Support
+#
+CONFIG_ACPI=y
+CONFIG_ACPI_BOOT=y
+CONFIG_ACPI_INTERPRETER=y
+CONFIG_ACPI_SLEEP=y
+CONFIG_ACPI_SLEEP_PROC_FS=y
+CONFIG_ACPI_AC=y
+CONFIG_ACPI_BATTERY=y
+CONFIG_ACPI_BUTTON=y
+CONFIG_ACPI_VIDEO=y
+CONFIG_ACPI_FAN=y
+CONFIG_ACPI_PROCESSOR=y
+CONFIG_ACPI_THERMAL=y
+# CONFIG_ACPI_ASUS is not set
+# CONFIG_ACPI_IBM is not set
+# CONFIG_ACPI_TOSHIBA is not set
+# CONFIG_ACPI_CUSTOM_DSDT is not set
+CONFIG_ACPI_BLACKLIST_YEAR=0
+# CONFIG_ACPI_DEBUG is not set
+CONFIG_ACPI_BUS=y
+CONFIG_ACPI_EC=y
+CONFIG_ACPI_POWER=y
+CONFIG_ACPI_PCI=y
+CONFIG_ACPI_SYSTEM=y
+# CONFIG_X86_PM_TIMER is not set
+
+#
+# APM (Advanced Power Management) BIOS Support
+#
+# CONFIG_APM is not set
+
+#
+# CPU Frequency scaling
+#
+# CONFIG_CPU_FREQ is not set
+
+#
+# Bus options (PCI, PCMCIA, EISA, MCA, ISA)
+#
+CONFIG_PCI=y
+# CONFIG_PCI_GOBIOS is not set
+# CONFIG_PCI_GOMMCONFIG is not set
+# CONFIG_PCI_GODIRECT is not set
+CONFIG_PCI_GOANY=y
+CONFIG_PCI_BIOS=y
+CONFIG_PCI_DIRECT=y
+CONFIG_PCI_MMCONFIG=y
+# CONFIG_PCI_MSI is not set
+CONFIG_PCI_LEGACY_PROC=y
+CONFIG_PCI_NAMES=y
+CONFIG_ISA=y
+# CONFIG_EISA is not set
+# CONFIG_MCA is not set
+# CONFIG_SCx200 is not set
+
+#
+# PCCARD (PCMCIA/CardBus) support
+#
+# CONFIG_PCCARD is not set
+
+#
+# PC-card bridges
+#
+CONFIG_PCMCIA_PROBE=y
+
+#
+# PCI Hotplug Support
+#
+# CONFIG_HOTPLUG_PCI is not set
+
+#
+# Executable file formats
+#
+CONFIG_BINFMT_ELF=y
+CONFIG_BINFMT_AOUT=y
+CONFIG_BINFMT_MISC=y
+
+#
+# Device Drivers
+#
+
+#
+# Generic Driver Options
+#
+# CONFIG_STANDALONE is not set
+CONFIG_PREVENT_FIRMWARE_BUILD=y
+CONFIG_FW_LOADER=m
+# CONFIG_DEBUG_DRIVER is not set
+
+#
+# Memory Technology Devices (MTD)
+#
+# CONFIG_MTD is not set
+
+#
+# Parallel port support
+#
+# CONFIG_PARPORT is not set
+
+#
+# Plug and Play support
+#
+CONFIG_PNP=y
+# CONFIG_PNP_DEBUG is not set
+
+#
+# Protocols
+#
+# CONFIG_ISAPNP is not set
+# CONFIG_PNPBIOS is not set
+CONFIG_PNPACPI=y
+
+#
+# Block devices
+#
+CONFIG_BLK_DEV_FD=y
+# CONFIG_BLK_DEV_XD is not set
+# CONFIG_BLK_CPQ_DA is not set
+# CONFIG_BLK_CPQ_CISS_DA is not set
+# CONFIG_BLK_DEV_DAC960 is not set
+# CONFIG_BLK_DEV_UMEM is not set
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_CRYPTOLOOP=y
+CONFIG_BLK_DEV_NBD=y
+# CONFIG_BLK_DEV_SX8 is not set
+# CONFIG_BLK_DEV_UB is not set
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=4096
+# CONFIG_BLK_DEV_INITRD is not set
+CONFIG_INITRAMFS_SOURCE=""
+CONFIG_LBD=y
+CONFIG_CDROM_PKTCDVD=y
+CONFIG_CDROM_PKTCDVD_BUFFERS=8
+# CONFIG_CDROM_PKTCDVD_WCACHE is not set
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+CONFIG_IOSCHED_AS=y
+CONFIG_IOSCHED_DEADLINE=y
+CONFIG_IOSCHED_CFQ=y
+
+#
+# ATA/ATAPI/MFM/RLL support
+#
+CONFIG_IDE=y
+CONFIG_BLK_DEV_IDE=y
+
+#
+# Please see Documentation/ide.txt for help/info on IDE drives
+#
+# CONFIG_BLK_DEV_IDE_SATA is not set
+# CONFIG_BLK_DEV_HD_IDE is not set
+CONFIG_BLK_DEV_IDEDISK=y
+CONFIG_IDEDISK_MULTI_MODE=y
+CONFIG_BLK_DEV_IDECD=y
+# CONFIG_BLK_DEV_IDETAPE is not set
+# CONFIG_BLK_DEV_IDEFLOPPY is not set
+# CONFIG_BLK_DEV_IDESCSI is not set
+# CONFIG_IDE_TASK_IOCTL is not set
+
+#
+# IDE chipset support/bugfixes
+#
+CONFIG_IDE_GENERIC=y
+CONFIG_BLK_DEV_CMD640=y
+# CONFIG_BLK_DEV_CMD640_ENHANCED is not set
+# CONFIG_BLK_DEV_IDEPNP is not set
+CONFIG_BLK_DEV_IDEPCI=y
+CONFIG_IDEPCI_SHARE_IRQ=y
+# CONFIG_BLK_DEV_OFFBOARD is not set
+CONFIG_BLK_DEV_GENERIC=y
+# CONFIG_BLK_DEV_OPTI621 is not set
+# CONFIG_BLK_DEV_RZ1000 is not set
+CONFIG_BLK_DEV_IDEDMA_PCI=y
+# CONFIG_BLK_DEV_IDEDMA_FORCED is not set
+CONFIG_IDEDMA_PCI_AUTO=y
+# CONFIG_IDEDMA_ONLYDISK is not set
+# CONFIG_BLK_DEV_AEC62XX is not set
+# CONFIG_BLK_DEV_ALI15X3 is not set
+# CONFIG_BLK_DEV_AMD74XX is not set
+# CONFIG_BLK_DEV_ATIIXP is not set
+# CONFIG_BLK_DEV_CMD64X is not set
+# CONFIG_BLK_DEV_TRIFLEX is not set
+# CONFIG_BLK_DEV_CY82C693 is not set
+# CONFIG_BLK_DEV_CS5520 is not set
+# CONFIG_BLK_DEV_CS5530 is not set
+# CONFIG_BLK_DEV_HPT34X is not set
+# CONFIG_BLK_DEV_HPT366 is not set
+# CONFIG_BLK_DEV_SC1200 is not set
+# CONFIG_BLK_DEV_PIIX is not set
+# CONFIG_BLK_DEV_NS87415 is not set
+# CONFIG_BLK_DEV_PDC202XX_OLD is not set
+# CONFIG_BLK_DEV_PDC202XX_NEW is not set
+# CONFIG_BLK_DEV_SVWKS is not set
+# CONFIG_BLK_DEV_SIIMAGE is not set
+CONFIG_BLK_DEV_SIS5513=y
+# CONFIG_BLK_DEV_SLC90E66 is not set
+# CONFIG_BLK_DEV_TRM290 is not set
+# CONFIG_BLK_DEV_VIA82CXXX is not set
+# CONFIG_IDE_ARM is not set
+# CONFIG_IDE_CHIPSETS is not set
+CONFIG_BLK_DEV_IDEDMA=y
+# CONFIG_IDEDMA_IVB is not set
+CONFIG_IDEDMA_AUTO=y
+# CONFIG_BLK_DEV_HD is not set
+
+#
+# SCSI device support
+#
+CONFIG_SCSI=y
+# CONFIG_SCSI_PROC_FS is not set
+
+#
+# SCSI support type (disk, tape, CD-ROM)
+#
+# CONFIG_BLK_DEV_SD is not set
+# CONFIG_CHR_DEV_ST is not set
+# CONFIG_CHR_DEV_OSST is not set
+# CONFIG_BLK_DEV_SR is not set
+# CONFIG_CHR_DEV_SG is not set
+
+#
+# Some SCSI devices (e.g. CD jukebox) support multiple LUNs
+#
+# CONFIG_SCSI_MULTI_LUN is not set
+# CONFIG_SCSI_CONSTANTS is not set
+# CONFIG_SCSI_LOGGING is not set
+
+#
+# SCSI Transport Attributes
+#
+# CONFIG_SCSI_SPI_ATTRS is not set
+# CONFIG_SCSI_FC_ATTRS is not set
+
+#
+# SCSI low-level drivers
+#
+# CONFIG_BLK_DEV_3W_XXXX_RAID is not set
+# CONFIG_SCSI_3W_9XXX is not set
+# CONFIG_SCSI_7000FASST is not set
+# CONFIG_SCSI_ACARD is not set
+# CONFIG_SCSI_AHA152X is not set
+# CONFIG_SCSI_AHA1542 is not set
+# CONFIG_SCSI_AACRAID is not set
+# CONFIG_SCSI_AIC7XXX is not set
+# CONFIG_SCSI_AIC7XXX_OLD is not set
+# CONFIG_SCSI_AIC79XX is not set
+# CONFIG_SCSI_DPT_I2O is not set
+# CONFIG_SCSI_IN2000 is not set
+# CONFIG_MEGARAID_NEWGEN is not set
+# CONFIG_MEGARAID_LEGACY is not set
+# CONFIG_SCSI_SATA is not set
+# CONFIG_SCSI_BUSLOGIC is not set
+# CONFIG_SCSI_DMX3191D is not set
+# CONFIG_SCSI_DTC3280 is not set
+# CONFIG_SCSI_EATA is not set
+# CONFIG_SCSI_EATA_PIO is not set
+# CONFIG_SCSI_FUTURE_DOMAIN is not set
+# CONFIG_SCSI_GDTH is not set
+# CONFIG_SCSI_GENERIC_NCR5380 is not set
+# CONFIG_SCSI_GENERIC_NCR5380_MMIO is not set
+# CONFIG_SCSI_IPS is not set
+# CONFIG_SCSI_INITIO is not set
+# CONFIG_SCSI_INIA100 is not set
+# CONFIG_SCSI_NCR53C406A is not set
+# CONFIG_SCSI_SYM53C8XX_2 is not set
+# CONFIG_SCSI_IPR is not set
+# CONFIG_SCSI_PAS16 is not set
+# CONFIG_SCSI_PSI240I is not set
+# CONFIG_SCSI_QLOGIC_FAS is not set
+# CONFIG_SCSI_QLOGIC_ISP is not set
+# CONFIG_SCSI_QLOGIC_FC is not set
+# CONFIG_SCSI_QLOGIC_1280 is not set
+CONFIG_SCSI_QLA2XXX=y
+# CONFIG_SCSI_QLA21XX is not set
+# CONFIG_SCSI_QLA22XX is not set
+# CONFIG_SCSI_QLA2300 is not set
+# CONFIG_SCSI_QLA2322 is not set
+# CONFIG_SCSI_QLA6312 is not set
+# CONFIG_SCSI_QLA6322 is not set
+# CONFIG_SCSI_SYM53C416 is not set
+# CONFIG_SCSI_DC395x is not set
+# CONFIG_SCSI_DC390T is not set
+# CONFIG_SCSI_T128 is not set
+# CONFIG_SCSI_U14_34F is not set
+# CONFIG_SCSI_ULTRASTOR is not set
+# CONFIG_SCSI_NSP32 is not set
+# CONFIG_SCSI_DEBUG is not set
+
+#
+# Old CD-ROM drivers (not SCSI, not IDE)
+#
+# CONFIG_CD_NO_IDESCSI is not set
+
+#
+# Multi-device support (RAID and LVM)
+#
+# CONFIG_MD is not set
+
+#
+# Fusion MPT device support
+#
+# CONFIG_FUSION is not set
+
+#
+# IEEE 1394 (FireWire) support
+#
+# CONFIG_IEEE1394 is not set
+
+#
+# I2O device support
+#
+CONFIG_I2O=y
+CONFIG_I2O_CONFIG=y
+CONFIG_I2O_BLOCK=y
+# CONFIG_I2O_SCSI is not set
+CONFIG_I2O_PROC=y
+
+#
+# Networking support
+#
+CONFIG_NET=y
+
+#
+# Networking options
+#
+CONFIG_PACKET=y
+CONFIG_PACKET_MMAP=y
+# CONFIG_NETLINK_DEV is not set
+CONFIG_UNIX=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_ROUTE_FWMARK=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_VERBOSE=y
+# CONFIG_IP_PNP is not set
+CONFIG_NET_IPIP=y
+CONFIG_NET_IPGRE=y
+CONFIG_NET_IPGRE_BROADCAST=y
+CONFIG_IP_MROUTE=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
+CONFIG_ARPD=y
+CONFIG_SYN_COOKIES=y
+CONFIG_INET_AH=y
+CONFIG_INET_ESP=y
+CONFIG_INET_IPCOMP=y
+CONFIG_INET_TUNNEL=y
+CONFIG_IP_TCPDIAG=y
+CONFIG_IP_TCPDIAG_IPV6=y
+
+#
+# IP: Virtual Server Configuration
+#
+# CONFIG_IP_VS is not set
+CONFIG_IPV6=y
+CONFIG_IPV6_PRIVACY=y
+CONFIG_INET6_AH=y
+CONFIG_INET6_ESP=y
+CONFIG_INET6_IPCOMP=y
+CONFIG_INET6_TUNNEL=y
+CONFIG_IPV6_TUNNEL=y
+CONFIG_NETFILTER=y
+# CONFIG_NETFILTER_DEBUG is not set
+CONFIG_BRIDGE_NETFILTER=y
+
+#
+# IP: Netfilter Configuration
+#
+CONFIG_IP_NF_CONNTRACK=y
+CONFIG_IP_NF_CT_ACCT=y
+CONFIG_IP_NF_CONNTRACK_MARK=y
+# CONFIG_IP_NF_CT_PROTO_SCTP is not set
+CONFIG_IP_NF_FTP=y
+CONFIG_IP_NF_IRC=y
+CONFIG_IP_NF_TFTP=y
+# CONFIG_IP_NF_AMANDA is not set
+CONFIG_IP_NF_QUEUE=y
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP_NF_MATCH_LIMIT=y
+CONFIG_IP_NF_MATCH_IPRANGE=y
+CONFIG_IP_NF_MATCH_MAC=y
+CONFIG_IP_NF_MATCH_PKTTYPE=y
+CONFIG_IP_NF_MATCH_MARK=y
+CONFIG_IP_NF_MATCH_MULTIPORT=y
+CONFIG_IP_NF_MATCH_TOS=y
+CONFIG_IP_NF_MATCH_RECENT=y
+CONFIG_IP_NF_MATCH_ECN=y
+CONFIG_IP_NF_MATCH_DSCP=y
+CONFIG_IP_NF_MATCH_AH_ESP=y
+CONFIG_IP_NF_MATCH_LENGTH=y
+CONFIG_IP_NF_MATCH_TTL=y
+CONFIG_IP_NF_MATCH_TCPMSS=y
+CONFIG_IP_NF_MATCH_HELPER=y
+CONFIG_IP_NF_MATCH_STATE=y
+CONFIG_IP_NF_MATCH_CONNTRACK=y
+CONFIG_IP_NF_MATCH_OWNER=y
+CONFIG_IP_NF_MATCH_PHYSDEV=y
+CONFIG_IP_NF_MATCH_ADDRTYPE=y
+CONFIG_IP_NF_MATCH_REALM=y
+# CONFIG_IP_NF_MATCH_SCTP is not set
+CONFIG_IP_NF_MATCH_COMMENT=y
+CONFIG_IP_NF_MATCH_CONNMARK=y
+CONFIG_IP_NF_MATCH_HASHLIMIT=y
+CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_TARGET_REJECT=y
+CONFIG_IP_NF_TARGET_LOG=y
+CONFIG_IP_NF_TARGET_ULOG=y
+CONFIG_IP_NF_TARGET_TCPMSS=y
+CONFIG_IP_NF_NAT=y
+CONFIG_IP_NF_NAT_NEEDED=y
+CONFIG_IP_NF_TARGET_MASQUERADE=y
+CONFIG_IP_NF_TARGET_REDIRECT=y
+CONFIG_IP_NF_TARGET_NETMAP=y
+CONFIG_IP_NF_TARGET_SAME=y
+# CONFIG_IP_NF_NAT_LOCAL is not set
+# CONFIG_IP_NF_NAT_SNMP_BASIC is not set
+CONFIG_IP_NF_NAT_IRC=y
+CONFIG_IP_NF_NAT_FTP=y
+CONFIG_IP_NF_NAT_TFTP=y
+CONFIG_IP_NF_MANGLE=y
+CONFIG_IP_NF_TARGET_TOS=y
+CONFIG_IP_NF_TARGET_ECN=y
+CONFIG_IP_NF_TARGET_DSCP=y
+CONFIG_IP_NF_TARGET_MARK=y
+CONFIG_IP_NF_TARGET_CLASSIFY=y
+CONFIG_IP_NF_TARGET_CONNMARK=y
+CONFIG_IP_NF_TARGET_CLUSTERIP=y
+CONFIG_IP_NF_RAW=y
+CONFIG_IP_NF_TARGET_NOTRACK=y
+CONFIG_IP_NF_ARPTABLES=y
+CONFIG_IP_NF_ARPFILTER=y
+CONFIG_IP_NF_ARP_MANGLE=y
+
+#
+# IPv6: Netfilter Configuration
+#
+CONFIG_IP6_NF_QUEUE=y
+CONFIG_IP6_NF_IPTABLES=y
+CONFIG_IP6_NF_MATCH_LIMIT=y
+CONFIG_IP6_NF_MATCH_MAC=y
+CONFIG_IP6_NF_MATCH_RT=y
+CONFIG_IP6_NF_MATCH_OPTS=y
+CONFIG_IP6_NF_MATCH_FRAG=y
+CONFIG_IP6_NF_MATCH_HL=y
+CONFIG_IP6_NF_MATCH_MULTIPORT=y
+CONFIG_IP6_NF_MATCH_OWNER=y
+CONFIG_IP6_NF_MATCH_MARK=y
+CONFIG_IP6_NF_MATCH_IPV6HEADER=y
+CONFIG_IP6_NF_MATCH_AHESP=y
+CONFIG_IP6_NF_MATCH_LENGTH=y
+CONFIG_IP6_NF_MATCH_EUI64=y
+CONFIG_IP6_NF_MATCH_PHYSDEV=y
+CONFIG_IP6_NF_FILTER=y
+CONFIG_IP6_NF_TARGET_LOG=y
+CONFIG_IP6_NF_MANGLE=y
+CONFIG_IP6_NF_TARGET_MARK=y
+CONFIG_IP6_NF_RAW=y
+
+#
+# Bridge: Netfilter Configuration
+#
+# CONFIG_BRIDGE_NF_EBTABLES is not set
+CONFIG_XFRM=y
+CONFIG_XFRM_USER=y
+
+#
+# SCTP Configuration (EXPERIMENTAL)
+#
+# CONFIG_IP_SCTP is not set
+CONFIG_ATM=y
+# CONFIG_ATM_CLIP is not set
+# CONFIG_ATM_LANE is not set
+# CONFIG_ATM_BR2684 is not set
+CONFIG_BRIDGE=y
+CONFIG_VLAN_8021Q=y
+# CONFIG_DECNET is not set
+CONFIG_LLC=y
+CONFIG_LLC2=y
+# CONFIG_IPX is not set
+# CONFIG_ATALK is not set
+# CONFIG_X25 is not set
+# CONFIG_LAPB is not set
+# CONFIG_NET_DIVERT is not set
+# CONFIG_ECONET is not set
+# CONFIG_WAN_ROUTER is not set
+
+#
+# QoS and/or fair queueing
+#
+CONFIG_NET_SCHED=y
+CONFIG_NET_SCH_CLK_JIFFIES=y
+# CONFIG_NET_SCH_CLK_GETTIMEOFDAY is not set
+# CONFIG_NET_SCH_CLK_CPU is not set
+CONFIG_NET_SCH_CBQ=y
+CONFIG_NET_SCH_HTB=y
+CONFIG_NET_SCH_HFSC=y
+CONFIG_NET_SCH_ATM=y
+CONFIG_NET_SCH_PRIO=y
+CONFIG_NET_SCH_RED=y
+CONFIG_NET_SCH_SFQ=y
+CONFIG_NET_SCH_TEQL=y
+CONFIG_NET_SCH_TBF=y
+CONFIG_NET_SCH_GRED=y
+CONFIG_NET_SCH_DSMARK=y
+CONFIG_NET_SCH_NETEM=y
+CONFIG_NET_SCH_INGRESS=y
+CONFIG_NET_QOS=y
+CONFIG_NET_ESTIMATOR=y
+CONFIG_NET_CLS=y
+CONFIG_NET_CLS_TCINDEX=y
+CONFIG_NET_CLS_ROUTE4=y
+CONFIG_NET_CLS_ROUTE=y
+CONFIG_NET_CLS_FW=y
+CONFIG_NET_CLS_U32=y
+CONFIG_NET_CLS_EGP=y
+CONFIG_EGP_DEBUG=y
+CONFIG_NET_CLS_EGP_SIMPLE_CMP=y
+CONFIG_NET_CLS_EGP_NBYTE=y
+CONFIG_NET_CLS_EGP_KMP=y
+CONFIG_NET_CLS_EGP_REGEXP=y
+CONFIG_NET_CLS_EGP_CMD=y
+CONFIG_EGP_CMD_BACK_TTL=4096
+CONFIG_CLS_U32_PERF=y
+CONFIG_NET_CLS_IND=y
+CONFIG_NET_CLS_RSVP=y
+CONFIG_NET_CLS_RSVP6=y
+# CONFIG_NET_CLS_ACT is not set
+CONFIG_NET_CLS_POLICE=y
+
+#
+# Network testing
+#
+CONFIG_NET_PKTGEN=y
+# CONFIG_NETPOLL is not set
+# CONFIG_NET_POLL_CONTROLLER is not set
+# CONFIG_HAMRADIO is not set
+# CONFIG_IRDA is not set
+# CONFIG_BT is not set
+CONFIG_NETDEVICES=y
+CONFIG_DUMMY=y
+# CONFIG_BONDING is not set
+# CONFIG_EQUALIZER is not set
+CONFIG_TUN=y
+# CONFIG_NET_SB1000 is not set
+
+#
+# ARCnet devices
+#
+# CONFIG_ARCNET is not set
+
+#
+# Ethernet (10 or 100Mbit)
+#
+CONFIG_NET_ETHERNET=y
+CONFIG_MII=y
+# CONFIG_HAPPYMEAL is not set
+# CONFIG_SUNGEM is not set
+# CONFIG_NET_VENDOR_3COM is not set
+# CONFIG_LANCE is not set
+# CONFIG_NET_VENDOR_SMC is not set
+# CONFIG_NET_VENDOR_RACAL is not set
+
+#
+# Tulip family network device support
+#
+# CONFIG_NET_TULIP is not set
+# CONFIG_AT1700 is not set
+# CONFIG_DEPCA is not set
+# CONFIG_HP100 is not set
+# CONFIG_NET_ISA is not set
+CONFIG_NET_PCI=y
+# CONFIG_PCNET32 is not set
+# CONFIG_AMD8111_ETH is not set
+# CONFIG_ADAPTEC_STARFIRE is not set
+# CONFIG_AC3200 is not set
+# CONFIG_APRICOT is not set
+# CONFIG_B44 is not set
+# CONFIG_FORCEDETH is not set
+# CONFIG_CS89x0 is not set
+# CONFIG_DGRS is not set
+# CONFIG_EEPRO100 is not set
+# CONFIG_E100 is not set
+# CONFIG_FEALNX is not set
+# CONFIG_NATSEMI is not set
+# CONFIG_NE2K_PCI is not set
+# CONFIG_8139CP is not set
+CONFIG_8139TOO=y
+CONFIG_8139TOO_PIO=y
+# CONFIG_8139TOO_TUNE_TWISTER is not set
+# CONFIG_8139TOO_8129 is not set
+# CONFIG_8139_OLD_RX_RESET is not set
+# CONFIG_SIS900 is not set
+# CONFIG_EPIC100 is not set
+# CONFIG_SUNDANCE is not set
+# CONFIG_TLAN is not set
+# CONFIG_VIA_RHINE is not set
+# CONFIG_NET_POCKET is not set
+
+#
+# Ethernet (1000 Mbit)
+#
+# CONFIG_ACENIC is not set
+# CONFIG_DL2K is not set
+# CONFIG_E1000 is not set
+# CONFIG_NS83820 is not set
+# CONFIG_HAMACHI is not set
+# CONFIG_YELLOWFIN is not set
+# CONFIG_R8169 is not set
+# CONFIG_SK98LIN is not set
+# CONFIG_VIA_VELOCITY is not set
+# CONFIG_TIGON3 is not set
+
+#
+# Ethernet (10000 Mbit)
+#
+# CONFIG_IXGB is not set
+# CONFIG_S2IO is not set
+
+#
+# Token Ring devices
+#
+# CONFIG_TR is not set
+
+#
+# Wireless LAN (non-hamradio)
+#
+# CONFIG_NET_RADIO is not set
+
+#
+# Wan interfaces
+#
+# CONFIG_WAN is not set
+
+#
+# ATM drivers
+#
+# CONFIG_ATM_TCP is not set
+# CONFIG_ATM_LANAI is not set
+# CONFIG_ATM_ENI is not set
+# CONFIG_ATM_FIRESTREAM is not set
+# CONFIG_ATM_ZATM is not set
+# CONFIG_ATM_NICSTAR is not set
+# CONFIG_ATM_IDT77252 is not set
+# CONFIG_ATM_AMBASSADOR is not set
+# CONFIG_ATM_HORIZON is not set
+# CONFIG_ATM_IA is not set
+# CONFIG_ATM_FORE200E_MAYBE is not set
+# CONFIG_ATM_HE is not set
+# CONFIG_FDDI is not set
+# CONFIG_HIPPI is not set
+CONFIG_PPP=y
+CONFIG_PPP_MULTILINK=y
+CONFIG_PPP_FILTER=y
+# CONFIG_PPP_ASYNC is not set
+# CONFIG_PPP_SYNC_TTY is not set
+# CONFIG_PPP_DEFLATE is not set
+CONFIG_PPP_BSDCOMP=y
+# CONFIG_PPPOE is not set
+# CONFIG_PPPOATM is not set
+# CONFIG_SLIP is not set
+# CONFIG_NET_FC is not set
+CONFIG_SHAPER=y
+# CONFIG_NETCONSOLE is not set
+
+#
+# ISDN subsystem
+#
+# CONFIG_ISDN is not set
+
+#
+# Telephony Support
+#
+# CONFIG_PHONE is not set
+
+#
+# Input device support
+#
+CONFIG_INPUT=y
+
+#
+# Userland interfaces
+#
+CONFIG_INPUT_MOUSEDEV=y
+CONFIG_INPUT_MOUSEDEV_PSAUX=y
+CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
+CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
+# CONFIG_INPUT_JOYDEV is not set
+# CONFIG_INPUT_TSDEV is not set
+# CONFIG_INPUT_EVDEV is not set
+# CONFIG_INPUT_EVBUG is not set
+
+#
+# Input I/O drivers
+#
+# CONFIG_GAMEPORT is not set
+CONFIG_SOUND_GAMEPORT=y
+CONFIG_SERIO=y
+CONFIG_SERIO_I8042=y
+# CONFIG_SERIO_SERPORT is not set
+# CONFIG_SERIO_CT82C710 is not set
+# CONFIG_SERIO_PCIPS2 is not set
+# CONFIG_SERIO_RAW is not set
+
+#
+# Input Device Drivers
+#
+CONFIG_INPUT_KEYBOARD=y
+CONFIG_KEYBOARD_ATKBD=y
+# CONFIG_KEYBOARD_SUNKBD is not set
+# CONFIG_KEYBOARD_LKKBD is not set
+# CONFIG_KEYBOARD_XTKBD is not set
+# CONFIG_KEYBOARD_NEWTON is not set
+CONFIG_INPUT_MOUSE=y
+CONFIG_MOUSE_PS2=y
+# CONFIG_MOUSE_SERIAL is not set
+# CONFIG_MOUSE_INPORT is not set
+# CONFIG_MOUSE_LOGIBM is not set
+# CONFIG_MOUSE_PC110PAD is not set
+# CONFIG_MOUSE_VSXXXAA is not set
+# CONFIG_INPUT_JOYSTICK is not set
+# CONFIG_INPUT_TOUCHSCREEN is not set
+# CONFIG_INPUT_MISC is not set
+
+#
+# Character devices
+#
+CONFIG_VT=y
+CONFIG_VT_CONSOLE=y
+CONFIG_HW_CONSOLE=y
+# CONFIG_SERIAL_NONSTANDARD is not set
+
+#
+# Serial drivers
+#
+CONFIG_SERIAL_8250=y
+# CONFIG_SERIAL_8250_CONSOLE is not set
+# CONFIG_SERIAL_8250_ACPI is not set
+CONFIG_SERIAL_8250_NR_UARTS=4
+# CONFIG_SERIAL_8250_EXTENDED is not set
+
+#
+# Non-8250 serial port support
+#
+CONFIG_SERIAL_CORE=y
+CONFIG_UNIX98_PTYS=y
+CONFIG_LEGACY_PTYS=y
+CONFIG_LEGACY_PTY_COUNT=256
+
+#
+# IPMI
+#
+# CONFIG_IPMI_HANDLER is not set
+
+#
+# Watchdog Cards
+#
+# CONFIG_WATCHDOG is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_NVRAM is not set
+# CONFIG_RTC is not set
+# CONFIG_GEN_RTC is not set
+# CONFIG_DTLK is not set
+# CONFIG_R3964 is not set
+# CONFIG_APPLICOM is not set
+# CONFIG_SONYPI is not set
+
+#
+# Ftape, the floppy tape device driver
+#
+# CONFIG_AGP is not set
+# CONFIG_DRM is not set
+# CONFIG_MWAVE is not set
+# CONFIG_RAW_DRIVER is not set
+# CONFIG_HPET is not set
+# CONFIG_HANGCHECK_TIMER is not set
+
+#
+# I2C support
+#
+CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
+
+#
+# I2C Algorithms
+#
+CONFIG_I2C_ALGOBIT=y
+# CONFIG_I2C_ALGOPCF is not set
+# CONFIG_I2C_ALGOPCA is not set
+
+#
+# I2C Hardware Bus support
+#
+# CONFIG_I2C_ALI1535 is not set
+# CONFIG_I2C_ALI1563 is not set
+# CONFIG_I2C_ALI15X3 is not set
+# CONFIG_I2C_AMD756 is not set
+# CONFIG_I2C_AMD8111 is not set
+# CONFIG_I2C_I801 is not set
+# CONFIG_I2C_I810 is not set
+# CONFIG_I2C_ISA is not set
+# CONFIG_I2C_NFORCE2 is not set
+# CONFIG_I2C_PARPORT_LIGHT is not set
+# CONFIG_I2C_PIIX4 is not set
+# CONFIG_I2C_PROSAVAGE is not set
+# CONFIG_I2C_SAVAGE4 is not set
+# CONFIG_SCx200_ACB is not set
+# CONFIG_I2C_SIS5595 is not set
+# CONFIG_I2C_SIS630 is not set
+CONFIG_I2C_SIS96X=y
+# CONFIG_I2C_STUB is not set
+# CONFIG_I2C_VIA is not set
+# CONFIG_I2C_VIAPRO is not set
+# CONFIG_I2C_VOODOO3 is not set
+# CONFIG_I2C_PCA_ISA is not set
+
+#
+# Hardware Sensors Chip support
+#
+CONFIG_I2C_SENSOR=y
+# CONFIG_SENSORS_ADM1021 is not set
+# CONFIG_SENSORS_ADM1025 is not set
+# CONFIG_SENSORS_ADM1031 is not set
+# CONFIG_SENSORS_ASB100 is not set
+# CONFIG_SENSORS_DS1621 is not set
+# CONFIG_SENSORS_FSCHER is not set
+# CONFIG_SENSORS_GL518SM is not set
+# CONFIG_SENSORS_IT87 is not set
+# CONFIG_SENSORS_LM63 is not set
+# CONFIG_SENSORS_LM75 is not set
+# CONFIG_SENSORS_LM77 is not set
+# CONFIG_SENSORS_LM78 is not set
+# CONFIG_SENSORS_LM80 is not set
+# CONFIG_SENSORS_LM83 is not set
+# CONFIG_SENSORS_LM85 is not set
+# CONFIG_SENSORS_LM87 is not set
+# CONFIG_SENSORS_LM90 is not set
+# CONFIG_SENSORS_MAX1619 is not set
+# CONFIG_SENSORS_PC87360 is not set
+# CONFIG_SENSORS_SMSC47M1 is not set
+# CONFIG_SENSORS_VIA686A is not set
+# CONFIG_SENSORS_W83781D is not set
+# CONFIG_SENSORS_W83L785TS is not set
+# CONFIG_SENSORS_W83627HF is not set
+
+#
+# Other I2C Chip support
+#
+CONFIG_SENSORS_EEPROM=y
+# CONFIG_SENSORS_PCF8574 is not set
+# CONFIG_SENSORS_PCF8591 is not set
+# CONFIG_SENSORS_RTC8564 is not set
+# CONFIG_I2C_DEBUG_CORE is not set
+# CONFIG_I2C_DEBUG_ALGO is not set
+# CONFIG_I2C_DEBUG_BUS is not set
+# CONFIG_I2C_DEBUG_CHIP is not set
+
+#
+# Dallas's 1-wire bus
+#
+# CONFIG_W1 is not set
+
+#
+# Misc devices
+#
+# CONFIG_IBM_ASM is not set
+
+#
+# Multimedia devices
+#
+# CONFIG_VIDEO_DEV is not set
+
+#
+# Digital Video Broadcasting Devices
+#
+# CONFIG_DVB is not set
+
+#
+# Graphics support
+#
+# CONFIG_FB is not set
+# CONFIG_VIDEO_SELECT is not set
+
+#
+# Console display driver support
+#
+CONFIG_VGA_CONSOLE=y
+# CONFIG_MDA_CONSOLE is not set
+CONFIG_DUMMY_CONSOLE=y
+
+#
+# Sound
+#
+CONFIG_SOUND=y
+
+#
+# Advanced Linux Sound Architecture
+#
+CONFIG_SND=y
+CONFIG_SND_TIMER=y
+CONFIG_SND_PCM=y
+CONFIG_SND_HWDEP=y
+CONFIG_SND_RAWMIDI=y
+CONFIG_SND_SEQUENCER=y
+# CONFIG_SND_SEQ_DUMMY is not set
+CONFIG_SND_OSSEMUL=y
+CONFIG_SND_MIXER_OSS=y
+CONFIG_SND_PCM_OSS=y
+CONFIG_SND_SEQUENCER_OSS=y
+# CONFIG_SND_VERBOSE_PRINTK is not set
+# CONFIG_SND_DEBUG is not set
+
+#
+# Generic devices
+#
+# CONFIG_SND_DUMMY is not set
+# CONFIG_SND_VIRMIDI is not set
+# CONFIG_SND_MTPAV is not set
+# CONFIG_SND_SERIAL_U16550 is not set
+# CONFIG_SND_MPU401 is not set
+
+#
+# ISA devices
+#
+# CONFIG_SND_AD1848 is not set
+# CONFIG_SND_CS4231 is not set
+# CONFIG_SND_CS4232 is not set
+# CONFIG_SND_CS4236 is not set
+# CONFIG_SND_ES1688 is not set
+# CONFIG_SND_ES18XX is not set
+# CONFIG_SND_GUSCLASSIC is not set
+# CONFIG_SND_GUSEXTREME is not set
+# CONFIG_SND_GUSMAX is not set
+# CONFIG_SND_INTERWAVE is not set
+# CONFIG_SND_INTERWAVE_STB is not set
+# CONFIG_SND_OPTI92X_AD1848 is not set
+# CONFIG_SND_OPTI92X_CS4231 is not set
+# CONFIG_SND_OPTI93X is not set
+# CONFIG_SND_SB8 is not set
+# CONFIG_SND_SB16 is not set
+# CONFIG_SND_SBAWE is not set
+# CONFIG_SND_WAVEFRONT is not set
+# CONFIG_SND_CMI8330 is not set
+# CONFIG_SND_OPL3SA2 is not set
+# CONFIG_SND_SGALAXY is not set
+# CONFIG_SND_SSCAPE is not set
+
+#
+# PCI devices
+#
+CONFIG_SND_AC97_CODEC=y
+# CONFIG_SND_ALI5451 is not set
+# CONFIG_SND_ATIIXP is not set
+# CONFIG_SND_ATIIXP_MODEM is not set
+# CONFIG_SND_AU8810 is not set
+# CONFIG_SND_AU8820 is not set
+# CONFIG_SND_AU8830 is not set
+# CONFIG_SND_AZT3328 is not set
+# CONFIG_SND_BT87X is not set
+# CONFIG_SND_CS46XX is not set
+# CONFIG_SND_CS4281 is not set
+CONFIG_SND_EMU10K1=y
+# CONFIG_SND_KORG1212 is not set
+# CONFIG_SND_MIXART is not set
+# CONFIG_SND_NM256 is not set
+# CONFIG_SND_RME32 is not set
+# CONFIG_SND_RME96 is not set
+# CONFIG_SND_RME9652 is not set
+# CONFIG_SND_HDSP is not set
+# CONFIG_SND_TRIDENT is not set
+# CONFIG_SND_YMFPCI is not set
+# CONFIG_SND_ALS4000 is not set
+# CONFIG_SND_CMIPCI is not set
+# CONFIG_SND_ENS1370 is not set
+# CONFIG_SND_ENS1371 is not set
+# CONFIG_SND_ES1938 is not set
+# CONFIG_SND_ES1968 is not set
+# CONFIG_SND_MAESTRO3 is not set
+# CONFIG_SND_FM801 is not set
+# CONFIG_SND_ICE1712 is not set
+# CONFIG_SND_ICE1724 is not set
+# CONFIG_SND_INTEL8X0 is not set
+# CONFIG_SND_INTEL8X0M is not set
+# CONFIG_SND_SONICVIBES is not set
+# CONFIG_SND_VIA82XX is not set
+# CONFIG_SND_VX222 is not set
+
+#
+# USB devices
+#
+# CONFIG_SND_USB_AUDIO is not set
+# CONFIG_SND_USB_USX2Y is not set
+
+#
+# Open Sound System
+#
+# CONFIG_SOUND_PRIME is not set
+
+#
+# USB support
+#
+CONFIG_USB=y
+# CONFIG_USB_DEBUG is not set
+
+#
+# Miscellaneous USB options
+#
+CONFIG_USB_DEVICEFS=y
+# CONFIG_USB_BANDWIDTH is not set
+# CONFIG_USB_DYNAMIC_MINORS is not set
+# CONFIG_USB_SUSPEND is not set
+# CONFIG_USB_OTG is not set
+CONFIG_USB_ARCH_HAS_HCD=y
+CONFIG_USB_ARCH_HAS_OHCI=y
+
+#
+# USB Host Controller Drivers
+#
+CONFIG_USB_EHCI_HCD=y
+# CONFIG_USB_EHCI_SPLIT_ISO is not set
+# CONFIG_USB_EHCI_ROOT_HUB_TT is not set
+# CONFIG_USB_OHCI_HCD is not set
+CONFIG_USB_UHCI_HCD=y
+
+#
+# USB Device Class drivers
+#
+# CONFIG_USB_AUDIO is not set
+# CONFIG_USB_BLUETOOTH_TTY is not set
+# CONFIG_USB_MIDI is not set
+# CONFIG_USB_ACM is not set
+CONFIG_USB_PRINTER=y
+CONFIG_USB_STORAGE=y
+# CONFIG_USB_STORAGE_DEBUG is not set
+# CONFIG_USB_STORAGE_RW_DETECT is not set
+# CONFIG_USB_STORAGE_DATAFAB is not set
+# CONFIG_USB_STORAGE_FREECOM is not set
+# CONFIG_USB_STORAGE_ISD200 is not set
+# CONFIG_USB_STORAGE_DPCM is not set
+# CONFIG_USB_STORAGE_HP8200e is not set
+# CONFIG_USB_STORAGE_SDDR09 is not set
+# CONFIG_USB_STORAGE_SDDR55 is not set
+# CONFIG_USB_STORAGE_JUMPSHOT is not set
+
+#
+# USB Input Devices
+#
+CONFIG_USB_HID=y
+CONFIG_USB_HIDINPUT=y
+# CONFIG_HID_FF is not set
+# CONFIG_USB_HIDDEV is not set
+# CONFIG_USB_AIPTEK is not set
+# CONFIG_USB_WACOM is not set
+# CONFIG_USB_KBTAB is not set
+# CONFIG_USB_POWERMATE is not set
+# CONFIG_USB_MTOUCH is not set
+CONFIG_USB_EGALAX=m
+# CONFIG_USB_XPAD is not set
+# CONFIG_USB_ATI_REMOTE is not set
+
+#
+# USB Imaging devices
+#
+# CONFIG_USB_MDC800 is not set
+# CONFIG_USB_MICROTEK is not set
+# CONFIG_USB_HPUSBSCSI is not set
+
+#
+# USB Multimedia devices
+#
+# CONFIG_USB_DABUSB is not set
+
+#
+# Video4Linux support is needed for USB Multimedia device support
+#
+
+#
+# USB Network Adapters
+#
+# CONFIG_USB_CATC is not set
+# CONFIG_USB_KAWETH is not set
+# CONFIG_USB_PEGASUS is not set
+# CONFIG_USB_RTL8150 is not set
+# CONFIG_USB_USBNET is not set
+
+#
+# USB port drivers
+#
+
+#
+# USB Serial Converter support
+#
+# CONFIG_USB_SERIAL is not set
+
+#
+# USB Miscellaneous drivers
+#
+# CONFIG_USB_EMI62 is not set
+# CONFIG_USB_EMI26 is not set
+# CONFIG_USB_TIGL is not set
+# CONFIG_USB_AUERSWALD is not set
+# CONFIG_USB_RIO500 is not set
+# CONFIG_USB_LEGOTOWER is not set
+# CONFIG_USB_LCD is not set
+# CONFIG_USB_LED is not set
+CONFIG_USB_CYTHERM=m
+# CONFIG_USB_PHIDGETKIT is not set
+CONFIG_USB_PHIDGETSERVO=m
+# CONFIG_USB_TEST is not set
+
+#
+# USB ATM/DSL drivers
+#
+# CONFIG_USB_ATM is not set
+# CONFIG_USB_SPEEDTOUCH is not set
+
+#
+# USB Gadget Support
+#
+# CONFIG_USB_GADGET is not set
+
+#
+# File systems
+#
+CONFIG_EXT2_FS=y
+# CONFIG_EXT2_FS_XATTR is not set
+CONFIG_EXT3_FS=y
+CONFIG_EXT3_FS_XATTR=y
+# CONFIG_EXT3_FS_POSIX_ACL is not set
+# CONFIG_EXT3_FS_SECURITY is not set
+CONFIG_JBD=y
+# CONFIG_JBD_DEBUG is not set
+CONFIG_FS_MBCACHE=y
+# CONFIG_REISERFS_FS is not set
+# CONFIG_JFS_FS is not set
+# CONFIG_XFS_FS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_ROMFS_FS is not set
+# CONFIG_QUOTA is not set
+CONFIG_DNOTIFY=y
+# CONFIG_AUTOFS_FS is not set
+CONFIG_AUTOFS4_FS=y
+
+#
+# CD-ROM/DVD Filesystems
+#
+CONFIG_ISO9660_FS=y
+CONFIG_JOLIET=y
+# CONFIG_ZISOFS is not set
+CONFIG_UDF_FS=y
+CONFIG_UDF_NLS=y
+
+#
+# DOS/FAT/NT Filesystems
+#
+CONFIG_FAT_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_FAT_DEFAULT_CODEPAGE=437
+CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
+# CONFIG_NTFS_FS is not set
+
+#
+# Pseudo filesystems
+#
+CONFIG_PROC_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_SYSFS=y
+# CONFIG_DEVFS_FS is not set
+# CONFIG_DEVPTS_FS_XATTR is not set
+CONFIG_TMPFS=y
+# CONFIG_TMPFS_XATTR is not set
+# CONFIG_HUGETLBFS is not set
+# CONFIG_HUGETLB_PAGE is not set
+CONFIG_RAMFS=y
+
+#
+# Miscellaneous filesystems
+#
+# CONFIG_ADFS_FS is not set
+# CONFIG_AFFS_FS is not set
+# CONFIG_HFS_FS is not set
+# CONFIG_HFSPLUS_FS is not set
+# CONFIG_BEFS_FS is not set
+# CONFIG_BFS_FS is not set
+# CONFIG_EFS_FS is not set
+# CONFIG_CRAMFS is not set
+# CONFIG_VXFS_FS is not set
+# CONFIG_HPFS_FS is not set
+# CONFIG_QNX4FS_FS is not set
+# CONFIG_SYSV_FS is not set
+# CONFIG_UFS_FS is not set
+
+#
+# Network File Systems
+#
+CONFIG_NFS_FS=y
+# CONFIG_NFS_V3 is not set
+# CONFIG_NFS_V4 is not set
+# CONFIG_NFS_DIRECTIO is not set
+CONFIG_NFSD=y
+# CONFIG_NFSD_V3 is not set
+CONFIG_NFSD_TCP=y
+CONFIG_LOCKD=y
+CONFIG_EXPORTFS=y
+CONFIG_SUNRPC=y
+# CONFIG_RPCSEC_GSS_KRB5 is not set
+# CONFIG_RPCSEC_GSS_SPKM3 is not set
+# CONFIG_SMB_FS is not set
+# CONFIG_CIFS is not set
+# CONFIG_NCP_FS is not set
+# CONFIG_CODA_FS is not set
+# CONFIG_AFS_FS is not set
+
+#
+# Partition Types
+#
+# CONFIG_PARTITION_ADVANCED is not set
+CONFIG_MSDOS_PARTITION=y
+
+#
+# Native Language Support
+#
+CONFIG_NLS=y
+CONFIG_NLS_DEFAULT="iso8859-1"
+CONFIG_NLS_CODEPAGE_437=y
+# CONFIG_NLS_CODEPAGE_737 is not set
+# CONFIG_NLS_CODEPAGE_775 is not set
+# CONFIG_NLS_CODEPAGE_850 is not set
+# CONFIG_NLS_CODEPAGE_852 is not set
+# CONFIG_NLS_CODEPAGE_855 is not set
+# CONFIG_NLS_CODEPAGE_857 is not set
+# CONFIG_NLS_CODEPAGE_860 is not set
+# CONFIG_NLS_CODEPAGE_861 is not set
+# CONFIG_NLS_CODEPAGE_862 is not set
+# CONFIG_NLS_CODEPAGE_863 is not set
+# CONFIG_NLS_CODEPAGE_864 is not set
+# CONFIG_NLS_CODEPAGE_865 is not set
+# CONFIG_NLS_CODEPAGE_866 is not set
+# CONFIG_NLS_CODEPAGE_869 is not set
+# CONFIG_NLS_CODEPAGE_936 is not set
+# CONFIG_NLS_CODEPAGE_950 is not set
+# CONFIG_NLS_CODEPAGE_932 is not set
+# CONFIG_NLS_CODEPAGE_949 is not set
+# CONFIG_NLS_CODEPAGE_874 is not set
+# CONFIG_NLS_ISO8859_8 is not set
+# CONFIG_NLS_CODEPAGE_1250 is not set
+# CONFIG_NLS_CODEPAGE_1251 is not set
+# CONFIG_NLS_ASCII is not set
+CONFIG_NLS_ISO8859_1=y
+# CONFIG_NLS_ISO8859_2 is not set
+# CONFIG_NLS_ISO8859_3 is not set
+# CONFIG_NLS_ISO8859_4 is not set
+# CONFIG_NLS_ISO8859_5 is not set
+# CONFIG_NLS_ISO8859_6 is not set
+# CONFIG_NLS_ISO8859_7 is not set
+# CONFIG_NLS_ISO8859_9 is not set
+# CONFIG_NLS_ISO8859_13 is not set
+# CONFIG_NLS_ISO8859_14 is not set
+# CONFIG_NLS_ISO8859_15 is not set
+# CONFIG_NLS_KOI8_R is not set
+# CONFIG_NLS_KOI8_U is not set
+# CONFIG_NLS_UTF8 is not set
+
+#
+# Profiling support
+#
+CONFIG_PROFILING=y
+CONFIG_OPROFILE=y
+
+#
+# Kernel hacking
+#
+CONFIG_DEBUG_KERNEL=y
+CONFIG_MAGIC_SYSRQ=y
+# CONFIG_SCHEDSTATS is not set
+CONFIG_DEBUG_SLAB=y
+# CONFIG_DEBUG_SPINLOCK is not set
+# CONFIG_DEBUG_SPINLOCK_SLEEP is not set
+# CONFIG_DEBUG_KOBJECT is not set
+# CONFIG_DEBUG_INFO is not set
+CONFIG_FRAME_POINTER=y
+CONFIG_EARLY_PRINTK=y
+# CONFIG_DEBUG_STACKOVERFLOW is not set
+# CONFIG_KPROBES is not set
+# CONFIG_DEBUG_STACK_USAGE is not set
+# CONFIG_DEBUG_PAGEALLOC is not set
+# CONFIG_4KSTACKS is not set
+CONFIG_X86_FIND_SMP_CONFIG=y
+CONFIG_X86_MPPARSE=y
+
+#
+# Security options
+#
+# CONFIG_KEYS is not set
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_SECURITY_CAPABILITIES=m
+CONFIG_SECURITY_ROOTPLUG=m
+# CONFIG_SECURITY_SECLVL is not set
+CONFIG_SECURITY_SELINUX=y
+# CONFIG_SECURITY_SELINUX_BOOTPARAM is not set
+CONFIG_SECURITY_SELINUX_DISABLE=y
+CONFIG_SECURITY_SELINUX_DEVELOP=y
+# CONFIG_SECURITY_SELINUX_MLS is not set
+
+#
+# Cryptographic options
+#
+CONFIG_CRYPTO=y
+CONFIG_CRYPTO_HMAC=y
+CONFIG_CRYPTO_NULL=y
+CONFIG_CRYPTO_MD4=y
+CONFIG_CRYPTO_MD5=y
+CONFIG_CRYPTO_SHA1=y
+CONFIG_CRYPTO_SHA256=y
+CONFIG_CRYPTO_SHA512=y
+CONFIG_CRYPTO_WP512=y
+CONFIG_CRYPTO_DES=y
+CONFIG_CRYPTO_BLOWFISH=y
+CONFIG_CRYPTO_TWOFISH=y
+CONFIG_CRYPTO_SERPENT=y
+CONFIG_CRYPTO_AES_586=y
+CONFIG_CRYPTO_CAST5=y
+CONFIG_CRYPTO_CAST6=y
+CONFIG_CRYPTO_TEA=y
+CONFIG_CRYPTO_ARC4=y
+CONFIG_CRYPTO_KHAZAD=y
+# CONFIG_CRYPTO_ANUBIS is not set
+CONFIG_CRYPTO_DEFLATE=y
+CONFIG_CRYPTO_MICHAEL_MIC=y
+CONFIG_CRYPTO_CRC32C=y
+CONFIG_CRYPTO_TEST=y
+
+#
+# Library routines
+#
+# CONFIG_CRC_CCITT is not set
+CONFIG_CRC32=y
+CONFIG_LIBCRC32C=y
+CONFIG_ZLIB_INFLATE=y
+CONFIG_ZLIB_DEFLATE=y
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_GENERIC_IRQ_PROBE=y
+CONFIG_X86_SMP=y
+CONFIG_X86_HT=y
+CONFIG_X86_BIOS_REBOOT=y
+CONFIG_X86_TRAMPOLINE=y
+CONFIG_PC=y
diff --git a/iproute2/testsuite/configs/all-police-act b/iproute2/testsuite/configs/all-police-act
new file mode 100644
index 0000000..1c84282
--- /dev/null
+++ b/iproute2/testsuite/configs/all-police-act
@@ -0,0 +1,1504 @@
+#
+# Automatically generated make config: don't edit
+# Linux kernel version: 2.6.10-rc2-bk13
+# Wed Dec 8 14:19:17 2004
+#
+CONFIG_X86=y
+CONFIG_MMU=y
+CONFIG_UID16=y
+CONFIG_GENERIC_ISA_DMA=y
+CONFIG_GENERIC_IOMAP=y
+
+#
+# Code maturity level options
+#
+CONFIG_EXPERIMENTAL=y
+CONFIG_CLEAN_COMPILE=y
+CONFIG_LOCK_KERNEL=y
+
+#
+# General setup
+#
+CONFIG_LOCALVERSION=""
+CONFIG_SWAP=y
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+# CONFIG_BSD_PROCESS_ACCT is not set
+CONFIG_SYSCTL=y
+CONFIG_AUDIT=y
+CONFIG_AUDITSYSCALL=y
+CONFIG_LOG_BUF_SHIFT=14
+CONFIG_HOTPLUG=y
+CONFIG_KOBJECT_UEVENT=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+# CONFIG_EMBEDDED is not set
+CONFIG_KALLSYMS=y
+# CONFIG_KALLSYMS_ALL is not set
+# CONFIG_KALLSYMS_EXTRA_PASS is not set
+CONFIG_FUTEX=y
+CONFIG_EPOLL=y
+# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
+CONFIG_SHMEM=y
+CONFIG_CC_ALIGN_FUNCTIONS=0
+CONFIG_CC_ALIGN_LABELS=0
+CONFIG_CC_ALIGN_LOOPS=0
+CONFIG_CC_ALIGN_JUMPS=0
+# CONFIG_TINY_SHMEM is not set
+
+#
+# Loadable module support
+#
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_OBSOLETE_MODPARM=y
+# CONFIG_MODVERSIONS is not set
+# CONFIG_MODULE_SRCVERSION_ALL is not set
+CONFIG_KMOD=y
+CONFIG_STOP_MACHINE=y
+
+#
+# Processor type and features
+#
+CONFIG_X86_PC=y
+# CONFIG_X86_ELAN is not set
+# CONFIG_X86_VOYAGER is not set
+# CONFIG_X86_NUMAQ is not set
+# CONFIG_X86_SUMMIT is not set
+# CONFIG_X86_BIGSMP is not set
+# CONFIG_X86_VISWS is not set
+# CONFIG_X86_GENERICARCH is not set
+# CONFIG_X86_ES7000 is not set
+# CONFIG_M386 is not set
+# CONFIG_M486 is not set
+# CONFIG_M586 is not set
+# CONFIG_M586TSC is not set
+# CONFIG_M586MMX is not set
+# CONFIG_M686 is not set
+# CONFIG_MPENTIUMII is not set
+# CONFIG_MPENTIUMIII is not set
+# CONFIG_MPENTIUMM is not set
+CONFIG_MPENTIUM4=y
+# CONFIG_MK6 is not set
+# CONFIG_MK7 is not set
+# CONFIG_MK8 is not set
+# CONFIG_MCRUSOE is not set
+# CONFIG_MEFFICEON is not set
+# CONFIG_MWINCHIPC6 is not set
+# CONFIG_MWINCHIP2 is not set
+# CONFIG_MWINCHIP3D is not set
+# CONFIG_MCYRIXIII is not set
+# CONFIG_MVIAC3_2 is not set
+# CONFIG_X86_GENERIC is not set
+CONFIG_X86_CMPXCHG=y
+CONFIG_X86_XADD=y
+CONFIG_X86_L1_CACHE_SHIFT=7
+CONFIG_RWSEM_XCHGADD_ALGORITHM=y
+CONFIG_X86_WP_WORKS_OK=y
+CONFIG_X86_INVLPG=y
+CONFIG_X86_BSWAP=y
+CONFIG_X86_POPAD_OK=y
+CONFIG_X86_GOOD_APIC=y
+CONFIG_X86_INTEL_USERCOPY=y
+CONFIG_X86_USE_PPRO_CHECKSUM=y
+# CONFIG_HPET_TIMER is not set
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+# CONFIG_SCHED_SMT is not set
+CONFIG_PREEMPT=y
+CONFIG_X86_LOCAL_APIC=y
+CONFIG_X86_IO_APIC=y
+CONFIG_X86_TSC=y
+CONFIG_X86_MCE=y
+CONFIG_X86_MCE_NONFATAL=y
+# CONFIG_X86_MCE_P4THERMAL is not set
+# CONFIG_TOSHIBA is not set
+# CONFIG_I8K is not set
+# CONFIG_MICROCODE is not set
+# CONFIG_X86_MSR is not set
+# CONFIG_X86_CPUID is not set
+
+#
+# Firmware Drivers
+#
+# CONFIG_EDD is not set
+CONFIG_NOHIGHMEM=y
+# CONFIG_HIGHMEM4G is not set
+# CONFIG_HIGHMEM64G is not set
+# CONFIG_MATH_EMULATION is not set
+CONFIG_MTRR=y
+# CONFIG_EFI is not set
+CONFIG_IRQBALANCE=y
+CONFIG_HAVE_DEC_LOCK=y
+# CONFIG_REGPARM is not set
+
+#
+# Power management options (ACPI, APM)
+#
+CONFIG_PM=y
+# CONFIG_PM_DEBUG is not set
+CONFIG_SOFTWARE_SUSPEND=y
+CONFIG_PM_STD_PARTITION=""
+
+#
+# ACPI (Advanced Configuration and Power Interface) Support
+#
+CONFIG_ACPI=y
+CONFIG_ACPI_BOOT=y
+CONFIG_ACPI_INTERPRETER=y
+CONFIG_ACPI_SLEEP=y
+CONFIG_ACPI_SLEEP_PROC_FS=y
+CONFIG_ACPI_AC=y
+CONFIG_ACPI_BATTERY=y
+CONFIG_ACPI_BUTTON=y
+CONFIG_ACPI_VIDEO=y
+CONFIG_ACPI_FAN=y
+CONFIG_ACPI_PROCESSOR=y
+CONFIG_ACPI_THERMAL=y
+# CONFIG_ACPI_ASUS is not set
+# CONFIG_ACPI_IBM is not set
+# CONFIG_ACPI_TOSHIBA is not set
+# CONFIG_ACPI_CUSTOM_DSDT is not set
+CONFIG_ACPI_BLACKLIST_YEAR=0
+# CONFIG_ACPI_DEBUG is not set
+CONFIG_ACPI_BUS=y
+CONFIG_ACPI_EC=y
+CONFIG_ACPI_POWER=y
+CONFIG_ACPI_PCI=y
+CONFIG_ACPI_SYSTEM=y
+# CONFIG_X86_PM_TIMER is not set
+
+#
+# APM (Advanced Power Management) BIOS Support
+#
+# CONFIG_APM is not set
+
+#
+# CPU Frequency scaling
+#
+# CONFIG_CPU_FREQ is not set
+
+#
+# Bus options (PCI, PCMCIA, EISA, MCA, ISA)
+#
+CONFIG_PCI=y
+# CONFIG_PCI_GOBIOS is not set
+# CONFIG_PCI_GOMMCONFIG is not set
+# CONFIG_PCI_GODIRECT is not set
+CONFIG_PCI_GOANY=y
+CONFIG_PCI_BIOS=y
+CONFIG_PCI_DIRECT=y
+CONFIG_PCI_MMCONFIG=y
+# CONFIG_PCI_MSI is not set
+CONFIG_PCI_LEGACY_PROC=y
+CONFIG_PCI_NAMES=y
+CONFIG_ISA=y
+# CONFIG_EISA is not set
+# CONFIG_MCA is not set
+# CONFIG_SCx200 is not set
+
+#
+# PCCARD (PCMCIA/CardBus) support
+#
+# CONFIG_PCCARD is not set
+
+#
+# PC-card bridges
+#
+CONFIG_PCMCIA_PROBE=y
+
+#
+# PCI Hotplug Support
+#
+# CONFIG_HOTPLUG_PCI is not set
+
+#
+# Executable file formats
+#
+CONFIG_BINFMT_ELF=y
+CONFIG_BINFMT_AOUT=y
+CONFIG_BINFMT_MISC=y
+
+#
+# Device Drivers
+#
+
+#
+# Generic Driver Options
+#
+# CONFIG_STANDALONE is not set
+CONFIG_PREVENT_FIRMWARE_BUILD=y
+CONFIG_FW_LOADER=m
+# CONFIG_DEBUG_DRIVER is not set
+
+#
+# Memory Technology Devices (MTD)
+#
+# CONFIG_MTD is not set
+
+#
+# Parallel port support
+#
+# CONFIG_PARPORT is not set
+
+#
+# Plug and Play support
+#
+CONFIG_PNP=y
+# CONFIG_PNP_DEBUG is not set
+
+#
+# Protocols
+#
+# CONFIG_ISAPNP is not set
+# CONFIG_PNPBIOS is not set
+CONFIG_PNPACPI=y
+
+#
+# Block devices
+#
+CONFIG_BLK_DEV_FD=y
+# CONFIG_BLK_DEV_XD is not set
+# CONFIG_BLK_CPQ_DA is not set
+# CONFIG_BLK_CPQ_CISS_DA is not set
+# CONFIG_BLK_DEV_DAC960 is not set
+# CONFIG_BLK_DEV_UMEM is not set
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_CRYPTOLOOP=y
+CONFIG_BLK_DEV_NBD=y
+# CONFIG_BLK_DEV_SX8 is not set
+# CONFIG_BLK_DEV_UB is not set
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=4096
+# CONFIG_BLK_DEV_INITRD is not set
+CONFIG_INITRAMFS_SOURCE=""
+CONFIG_LBD=y
+CONFIG_CDROM_PKTCDVD=y
+CONFIG_CDROM_PKTCDVD_BUFFERS=8
+# CONFIG_CDROM_PKTCDVD_WCACHE is not set
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+CONFIG_IOSCHED_AS=y
+CONFIG_IOSCHED_DEADLINE=y
+CONFIG_IOSCHED_CFQ=y
+
+#
+# ATA/ATAPI/MFM/RLL support
+#
+CONFIG_IDE=y
+CONFIG_BLK_DEV_IDE=y
+
+#
+# Please see Documentation/ide.txt for help/info on IDE drives
+#
+# CONFIG_BLK_DEV_IDE_SATA is not set
+# CONFIG_BLK_DEV_HD_IDE is not set
+CONFIG_BLK_DEV_IDEDISK=y
+CONFIG_IDEDISK_MULTI_MODE=y
+CONFIG_BLK_DEV_IDECD=y
+# CONFIG_BLK_DEV_IDETAPE is not set
+# CONFIG_BLK_DEV_IDEFLOPPY is not set
+# CONFIG_BLK_DEV_IDESCSI is not set
+# CONFIG_IDE_TASK_IOCTL is not set
+
+#
+# IDE chipset support/bugfixes
+#
+CONFIG_IDE_GENERIC=y
+CONFIG_BLK_DEV_CMD640=y
+# CONFIG_BLK_DEV_CMD640_ENHANCED is not set
+# CONFIG_BLK_DEV_IDEPNP is not set
+CONFIG_BLK_DEV_IDEPCI=y
+CONFIG_IDEPCI_SHARE_IRQ=y
+# CONFIG_BLK_DEV_OFFBOARD is not set
+CONFIG_BLK_DEV_GENERIC=y
+# CONFIG_BLK_DEV_OPTI621 is not set
+# CONFIG_BLK_DEV_RZ1000 is not set
+CONFIG_BLK_DEV_IDEDMA_PCI=y
+# CONFIG_BLK_DEV_IDEDMA_FORCED is not set
+CONFIG_IDEDMA_PCI_AUTO=y
+# CONFIG_IDEDMA_ONLYDISK is not set
+# CONFIG_BLK_DEV_AEC62XX is not set
+# CONFIG_BLK_DEV_ALI15X3 is not set
+# CONFIG_BLK_DEV_AMD74XX is not set
+# CONFIG_BLK_DEV_ATIIXP is not set
+# CONFIG_BLK_DEV_CMD64X is not set
+# CONFIG_BLK_DEV_TRIFLEX is not set
+# CONFIG_BLK_DEV_CY82C693 is not set
+# CONFIG_BLK_DEV_CS5520 is not set
+# CONFIG_BLK_DEV_CS5530 is not set
+# CONFIG_BLK_DEV_HPT34X is not set
+# CONFIG_BLK_DEV_HPT366 is not set
+# CONFIG_BLK_DEV_SC1200 is not set
+# CONFIG_BLK_DEV_PIIX is not set
+# CONFIG_BLK_DEV_NS87415 is not set
+# CONFIG_BLK_DEV_PDC202XX_OLD is not set
+# CONFIG_BLK_DEV_PDC202XX_NEW is not set
+# CONFIG_BLK_DEV_SVWKS is not set
+# CONFIG_BLK_DEV_SIIMAGE is not set
+CONFIG_BLK_DEV_SIS5513=y
+# CONFIG_BLK_DEV_SLC90E66 is not set
+# CONFIG_BLK_DEV_TRM290 is not set
+# CONFIG_BLK_DEV_VIA82CXXX is not set
+# CONFIG_IDE_ARM is not set
+# CONFIG_IDE_CHIPSETS is not set
+CONFIG_BLK_DEV_IDEDMA=y
+# CONFIG_IDEDMA_IVB is not set
+CONFIG_IDEDMA_AUTO=y
+# CONFIG_BLK_DEV_HD is not set
+
+#
+# SCSI device support
+#
+CONFIG_SCSI=y
+# CONFIG_SCSI_PROC_FS is not set
+
+#
+# SCSI support type (disk, tape, CD-ROM)
+#
+# CONFIG_BLK_DEV_SD is not set
+# CONFIG_CHR_DEV_ST is not set
+# CONFIG_CHR_DEV_OSST is not set
+# CONFIG_BLK_DEV_SR is not set
+# CONFIG_CHR_DEV_SG is not set
+
+#
+# Some SCSI devices (e.g. CD jukebox) support multiple LUNs
+#
+# CONFIG_SCSI_MULTI_LUN is not set
+# CONFIG_SCSI_CONSTANTS is not set
+# CONFIG_SCSI_LOGGING is not set
+
+#
+# SCSI Transport Attributes
+#
+# CONFIG_SCSI_SPI_ATTRS is not set
+# CONFIG_SCSI_FC_ATTRS is not set
+
+#
+# SCSI low-level drivers
+#
+# CONFIG_BLK_DEV_3W_XXXX_RAID is not set
+# CONFIG_SCSI_3W_9XXX is not set
+# CONFIG_SCSI_7000FASST is not set
+# CONFIG_SCSI_ACARD is not set
+# CONFIG_SCSI_AHA152X is not set
+# CONFIG_SCSI_AHA1542 is not set
+# CONFIG_SCSI_AACRAID is not set
+# CONFIG_SCSI_AIC7XXX is not set
+# CONFIG_SCSI_AIC7XXX_OLD is not set
+# CONFIG_SCSI_AIC79XX is not set
+# CONFIG_SCSI_DPT_I2O is not set
+# CONFIG_SCSI_IN2000 is not set
+# CONFIG_MEGARAID_NEWGEN is not set
+# CONFIG_MEGARAID_LEGACY is not set
+# CONFIG_SCSI_SATA is not set
+# CONFIG_SCSI_BUSLOGIC is not set
+# CONFIG_SCSI_DMX3191D is not set
+# CONFIG_SCSI_DTC3280 is not set
+# CONFIG_SCSI_EATA is not set
+# CONFIG_SCSI_EATA_PIO is not set
+# CONFIG_SCSI_FUTURE_DOMAIN is not set
+# CONFIG_SCSI_GDTH is not set
+# CONFIG_SCSI_GENERIC_NCR5380 is not set
+# CONFIG_SCSI_GENERIC_NCR5380_MMIO is not set
+# CONFIG_SCSI_IPS is not set
+# CONFIG_SCSI_INITIO is not set
+# CONFIG_SCSI_INIA100 is not set
+# CONFIG_SCSI_NCR53C406A is not set
+# CONFIG_SCSI_SYM53C8XX_2 is not set
+# CONFIG_SCSI_IPR is not set
+# CONFIG_SCSI_PAS16 is not set
+# CONFIG_SCSI_PSI240I is not set
+# CONFIG_SCSI_QLOGIC_FAS is not set
+# CONFIG_SCSI_QLOGIC_ISP is not set
+# CONFIG_SCSI_QLOGIC_FC is not set
+# CONFIG_SCSI_QLOGIC_1280 is not set
+CONFIG_SCSI_QLA2XXX=y
+# CONFIG_SCSI_QLA21XX is not set
+# CONFIG_SCSI_QLA22XX is not set
+# CONFIG_SCSI_QLA2300 is not set
+# CONFIG_SCSI_QLA2322 is not set
+# CONFIG_SCSI_QLA6312 is not set
+# CONFIG_SCSI_QLA6322 is not set
+# CONFIG_SCSI_SYM53C416 is not set
+# CONFIG_SCSI_DC395x is not set
+# CONFIG_SCSI_DC390T is not set
+# CONFIG_SCSI_T128 is not set
+# CONFIG_SCSI_U14_34F is not set
+# CONFIG_SCSI_ULTRASTOR is not set
+# CONFIG_SCSI_NSP32 is not set
+# CONFIG_SCSI_DEBUG is not set
+
+#
+# Old CD-ROM drivers (not SCSI, not IDE)
+#
+# CONFIG_CD_NO_IDESCSI is not set
+
+#
+# Multi-device support (RAID and LVM)
+#
+# CONFIG_MD is not set
+
+#
+# Fusion MPT device support
+#
+# CONFIG_FUSION is not set
+
+#
+# IEEE 1394 (FireWire) support
+#
+# CONFIG_IEEE1394 is not set
+
+#
+# I2O device support
+#
+CONFIG_I2O=y
+CONFIG_I2O_CONFIG=y
+CONFIG_I2O_BLOCK=y
+# CONFIG_I2O_SCSI is not set
+CONFIG_I2O_PROC=y
+
+#
+# Networking support
+#
+CONFIG_NET=y
+
+#
+# Networking options
+#
+CONFIG_PACKET=y
+CONFIG_PACKET_MMAP=y
+# CONFIG_NETLINK_DEV is not set
+CONFIG_UNIX=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_ROUTE_FWMARK=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_VERBOSE=y
+# CONFIG_IP_PNP is not set
+CONFIG_NET_IPIP=y
+CONFIG_NET_IPGRE=y
+CONFIG_NET_IPGRE_BROADCAST=y
+CONFIG_IP_MROUTE=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
+CONFIG_ARPD=y
+CONFIG_SYN_COOKIES=y
+CONFIG_INET_AH=y
+CONFIG_INET_ESP=y
+CONFIG_INET_IPCOMP=y
+CONFIG_INET_TUNNEL=y
+CONFIG_IP_TCPDIAG=y
+CONFIG_IP_TCPDIAG_IPV6=y
+
+#
+# IP: Virtual Server Configuration
+#
+# CONFIG_IP_VS is not set
+CONFIG_IPV6=y
+CONFIG_IPV6_PRIVACY=y
+CONFIG_INET6_AH=y
+CONFIG_INET6_ESP=y
+CONFIG_INET6_IPCOMP=y
+CONFIG_INET6_TUNNEL=y
+CONFIG_IPV6_TUNNEL=y
+CONFIG_NETFILTER=y
+# CONFIG_NETFILTER_DEBUG is not set
+CONFIG_BRIDGE_NETFILTER=y
+
+#
+# IP: Netfilter Configuration
+#
+CONFIG_IP_NF_CONNTRACK=y
+CONFIG_IP_NF_CT_ACCT=y
+CONFIG_IP_NF_CONNTRACK_MARK=y
+# CONFIG_IP_NF_CT_PROTO_SCTP is not set
+CONFIG_IP_NF_FTP=y
+CONFIG_IP_NF_IRC=y
+CONFIG_IP_NF_TFTP=y
+# CONFIG_IP_NF_AMANDA is not set
+CONFIG_IP_NF_QUEUE=y
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP_NF_MATCH_LIMIT=y
+CONFIG_IP_NF_MATCH_IPRANGE=y
+CONFIG_IP_NF_MATCH_MAC=y
+CONFIG_IP_NF_MATCH_PKTTYPE=y
+CONFIG_IP_NF_MATCH_MARK=y
+CONFIG_IP_NF_MATCH_MULTIPORT=y
+CONFIG_IP_NF_MATCH_TOS=y
+CONFIG_IP_NF_MATCH_RECENT=y
+CONFIG_IP_NF_MATCH_ECN=y
+CONFIG_IP_NF_MATCH_DSCP=y
+CONFIG_IP_NF_MATCH_AH_ESP=y
+CONFIG_IP_NF_MATCH_LENGTH=y
+CONFIG_IP_NF_MATCH_TTL=y
+CONFIG_IP_NF_MATCH_TCPMSS=y
+CONFIG_IP_NF_MATCH_HELPER=y
+CONFIG_IP_NF_MATCH_STATE=y
+CONFIG_IP_NF_MATCH_CONNTRACK=y
+CONFIG_IP_NF_MATCH_OWNER=y
+CONFIG_IP_NF_MATCH_PHYSDEV=y
+CONFIG_IP_NF_MATCH_ADDRTYPE=y
+CONFIG_IP_NF_MATCH_REALM=y
+# CONFIG_IP_NF_MATCH_SCTP is not set
+CONFIG_IP_NF_MATCH_COMMENT=y
+CONFIG_IP_NF_MATCH_CONNMARK=y
+CONFIG_IP_NF_MATCH_HASHLIMIT=y
+CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_TARGET_REJECT=y
+CONFIG_IP_NF_TARGET_LOG=y
+CONFIG_IP_NF_TARGET_ULOG=y
+CONFIG_IP_NF_TARGET_TCPMSS=y
+CONFIG_IP_NF_NAT=y
+CONFIG_IP_NF_NAT_NEEDED=y
+CONFIG_IP_NF_TARGET_MASQUERADE=y
+CONFIG_IP_NF_TARGET_REDIRECT=y
+CONFIG_IP_NF_TARGET_NETMAP=y
+CONFIG_IP_NF_TARGET_SAME=y
+# CONFIG_IP_NF_NAT_LOCAL is not set
+# CONFIG_IP_NF_NAT_SNMP_BASIC is not set
+CONFIG_IP_NF_NAT_IRC=y
+CONFIG_IP_NF_NAT_FTP=y
+CONFIG_IP_NF_NAT_TFTP=y
+CONFIG_IP_NF_MANGLE=y
+CONFIG_IP_NF_TARGET_TOS=y
+CONFIG_IP_NF_TARGET_ECN=y
+CONFIG_IP_NF_TARGET_DSCP=y
+CONFIG_IP_NF_TARGET_MARK=y
+CONFIG_IP_NF_TARGET_CLASSIFY=y
+CONFIG_IP_NF_TARGET_CONNMARK=y
+CONFIG_IP_NF_TARGET_CLUSTERIP=y
+CONFIG_IP_NF_RAW=y
+CONFIG_IP_NF_TARGET_NOTRACK=y
+CONFIG_IP_NF_ARPTABLES=y
+CONFIG_IP_NF_ARPFILTER=y
+CONFIG_IP_NF_ARP_MANGLE=y
+
+#
+# IPv6: Netfilter Configuration
+#
+CONFIG_IP6_NF_QUEUE=y
+CONFIG_IP6_NF_IPTABLES=y
+CONFIG_IP6_NF_MATCH_LIMIT=y
+CONFIG_IP6_NF_MATCH_MAC=y
+CONFIG_IP6_NF_MATCH_RT=y
+CONFIG_IP6_NF_MATCH_OPTS=y
+CONFIG_IP6_NF_MATCH_FRAG=y
+CONFIG_IP6_NF_MATCH_HL=y
+CONFIG_IP6_NF_MATCH_MULTIPORT=y
+CONFIG_IP6_NF_MATCH_OWNER=y
+CONFIG_IP6_NF_MATCH_MARK=y
+CONFIG_IP6_NF_MATCH_IPV6HEADER=y
+CONFIG_IP6_NF_MATCH_AHESP=y
+CONFIG_IP6_NF_MATCH_LENGTH=y
+CONFIG_IP6_NF_MATCH_EUI64=y
+CONFIG_IP6_NF_MATCH_PHYSDEV=y
+CONFIG_IP6_NF_FILTER=y
+CONFIG_IP6_NF_TARGET_LOG=y
+CONFIG_IP6_NF_MANGLE=y
+CONFIG_IP6_NF_TARGET_MARK=y
+CONFIG_IP6_NF_RAW=y
+
+#
+# Bridge: Netfilter Configuration
+#
+# CONFIG_BRIDGE_NF_EBTABLES is not set
+CONFIG_XFRM=y
+CONFIG_XFRM_USER=y
+
+#
+# SCTP Configuration (EXPERIMENTAL)
+#
+# CONFIG_IP_SCTP is not set
+CONFIG_ATM=y
+# CONFIG_ATM_CLIP is not set
+# CONFIG_ATM_LANE is not set
+# CONFIG_ATM_BR2684 is not set
+CONFIG_BRIDGE=y
+CONFIG_VLAN_8021Q=y
+# CONFIG_DECNET is not set
+CONFIG_LLC=y
+CONFIG_LLC2=y
+# CONFIG_IPX is not set
+# CONFIG_ATALK is not set
+# CONFIG_X25 is not set
+# CONFIG_LAPB is not set
+# CONFIG_NET_DIVERT is not set
+# CONFIG_ECONET is not set
+# CONFIG_WAN_ROUTER is not set
+
+#
+# QoS and/or fair queueing
+#
+CONFIG_NET_SCHED=y
+CONFIG_NET_SCH_CLK_JIFFIES=y
+# CONFIG_NET_SCH_CLK_GETTIMEOFDAY is not set
+# CONFIG_NET_SCH_CLK_CPU is not set
+CONFIG_NET_SCH_CBQ=y
+CONFIG_NET_SCH_HTB=y
+CONFIG_NET_SCH_HFSC=y
+CONFIG_NET_SCH_ATM=y
+CONFIG_NET_SCH_PRIO=y
+CONFIG_NET_SCH_RED=y
+CONFIG_NET_SCH_SFQ=y
+CONFIG_NET_SCH_TEQL=y
+CONFIG_NET_SCH_TBF=y
+CONFIG_NET_SCH_GRED=y
+CONFIG_NET_SCH_DSMARK=y
+CONFIG_NET_SCH_NETEM=y
+CONFIG_NET_SCH_INGRESS=y
+CONFIG_NET_QOS=y
+CONFIG_NET_ESTIMATOR=y
+CONFIG_NET_CLS=y
+CONFIG_NET_CLS_TCINDEX=y
+CONFIG_NET_CLS_ROUTE4=y
+CONFIG_NET_CLS_ROUTE=y
+CONFIG_NET_CLS_FW=y
+CONFIG_NET_CLS_U32=y
+CONFIG_NET_CLS_EGP=y
+CONFIG_EGP_DEBUG=y
+CONFIG_NET_CLS_EGP_SIMPLE_CMP=y
+CONFIG_NET_CLS_EGP_NBYTE=y
+CONFIG_NET_CLS_EGP_KMP=y
+CONFIG_NET_CLS_EGP_REGEXP=y
+CONFIG_NET_CLS_EGP_CMD=y
+CONFIG_EGP_CMD_BACK_TTL=4096
+CONFIG_CLS_U32_PERF=y
+CONFIG_NET_CLS_IND=y
+CONFIG_NET_CLS_RSVP=y
+CONFIG_NET_CLS_RSVP6=y
+CONFIG_NET_CLS_ACT=y
+CONFIG_NET_ACT_POLICE=y
+CONFIG_NET_ACT_GACT=y
+CONFIG_GACT_PROB=y
+CONFIG_NET_ACT_MIRRED=y
+CONFIG_NET_ACT_IPT=y
+CONFIG_NET_ACT_PEDIT=y
+
+#
+# Network testing
+#
+CONFIG_NET_PKTGEN=y
+# CONFIG_NETPOLL is not set
+# CONFIG_NET_POLL_CONTROLLER is not set
+# CONFIG_HAMRADIO is not set
+# CONFIG_IRDA is not set
+# CONFIG_BT is not set
+CONFIG_NETDEVICES=y
+CONFIG_DUMMY=y
+# CONFIG_BONDING is not set
+# CONFIG_EQUALIZER is not set
+CONFIG_TUN=y
+# CONFIG_NET_SB1000 is not set
+
+#
+# ARCnet devices
+#
+# CONFIG_ARCNET is not set
+
+#
+# Ethernet (10 or 100Mbit)
+#
+CONFIG_NET_ETHERNET=y
+CONFIG_MII=y
+# CONFIG_HAPPYMEAL is not set
+# CONFIG_SUNGEM is not set
+# CONFIG_NET_VENDOR_3COM is not set
+# CONFIG_LANCE is not set
+# CONFIG_NET_VENDOR_SMC is not set
+# CONFIG_NET_VENDOR_RACAL is not set
+
+#
+# Tulip family network device support
+#
+# CONFIG_NET_TULIP is not set
+# CONFIG_AT1700 is not set
+# CONFIG_DEPCA is not set
+# CONFIG_HP100 is not set
+# CONFIG_NET_ISA is not set
+CONFIG_NET_PCI=y
+# CONFIG_PCNET32 is not set
+# CONFIG_AMD8111_ETH is not set
+# CONFIG_ADAPTEC_STARFIRE is not set
+# CONFIG_AC3200 is not set
+# CONFIG_APRICOT is not set
+# CONFIG_B44 is not set
+# CONFIG_FORCEDETH is not set
+# CONFIG_CS89x0 is not set
+# CONFIG_DGRS is not set
+# CONFIG_EEPRO100 is not set
+# CONFIG_E100 is not set
+# CONFIG_FEALNX is not set
+# CONFIG_NATSEMI is not set
+# CONFIG_NE2K_PCI is not set
+# CONFIG_8139CP is not set
+CONFIG_8139TOO=y
+CONFIG_8139TOO_PIO=y
+# CONFIG_8139TOO_TUNE_TWISTER is not set
+# CONFIG_8139TOO_8129 is not set
+# CONFIG_8139_OLD_RX_RESET is not set
+# CONFIG_SIS900 is not set
+# CONFIG_EPIC100 is not set
+# CONFIG_SUNDANCE is not set
+# CONFIG_TLAN is not set
+# CONFIG_VIA_RHINE is not set
+# CONFIG_NET_POCKET is not set
+
+#
+# Ethernet (1000 Mbit)
+#
+# CONFIG_ACENIC is not set
+# CONFIG_DL2K is not set
+# CONFIG_E1000 is not set
+# CONFIG_NS83820 is not set
+# CONFIG_HAMACHI is not set
+# CONFIG_YELLOWFIN is not set
+# CONFIG_R8169 is not set
+# CONFIG_SK98LIN is not set
+# CONFIG_VIA_VELOCITY is not set
+# CONFIG_TIGON3 is not set
+
+#
+# Ethernet (10000 Mbit)
+#
+# CONFIG_IXGB is not set
+# CONFIG_S2IO is not set
+
+#
+# Token Ring devices
+#
+# CONFIG_TR is not set
+
+#
+# Wireless LAN (non-hamradio)
+#
+# CONFIG_NET_RADIO is not set
+
+#
+# Wan interfaces
+#
+# CONFIG_WAN is not set
+
+#
+# ATM drivers
+#
+# CONFIG_ATM_TCP is not set
+# CONFIG_ATM_LANAI is not set
+# CONFIG_ATM_ENI is not set
+# CONFIG_ATM_FIRESTREAM is not set
+# CONFIG_ATM_ZATM is not set
+# CONFIG_ATM_NICSTAR is not set
+# CONFIG_ATM_IDT77252 is not set
+# CONFIG_ATM_AMBASSADOR is not set
+# CONFIG_ATM_HORIZON is not set
+# CONFIG_ATM_IA is not set
+# CONFIG_ATM_FORE200E_MAYBE is not set
+# CONFIG_ATM_HE is not set
+# CONFIG_FDDI is not set
+# CONFIG_HIPPI is not set
+CONFIG_PPP=y
+CONFIG_PPP_MULTILINK=y
+CONFIG_PPP_FILTER=y
+# CONFIG_PPP_ASYNC is not set
+# CONFIG_PPP_SYNC_TTY is not set
+# CONFIG_PPP_DEFLATE is not set
+CONFIG_PPP_BSDCOMP=y
+# CONFIG_PPPOE is not set
+# CONFIG_PPPOATM is not set
+# CONFIG_SLIP is not set
+# CONFIG_NET_FC is not set
+CONFIG_SHAPER=y
+# CONFIG_NETCONSOLE is not set
+
+#
+# ISDN subsystem
+#
+# CONFIG_ISDN is not set
+
+#
+# Telephony Support
+#
+# CONFIG_PHONE is not set
+
+#
+# Input device support
+#
+CONFIG_INPUT=y
+
+#
+# Userland interfaces
+#
+CONFIG_INPUT_MOUSEDEV=y
+CONFIG_INPUT_MOUSEDEV_PSAUX=y
+CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
+CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
+# CONFIG_INPUT_JOYDEV is not set
+# CONFIG_INPUT_TSDEV is not set
+# CONFIG_INPUT_EVDEV is not set
+# CONFIG_INPUT_EVBUG is not set
+
+#
+# Input I/O drivers
+#
+# CONFIG_GAMEPORT is not set
+CONFIG_SOUND_GAMEPORT=y
+CONFIG_SERIO=y
+CONFIG_SERIO_I8042=y
+# CONFIG_SERIO_SERPORT is not set
+# CONFIG_SERIO_CT82C710 is not set
+# CONFIG_SERIO_PCIPS2 is not set
+# CONFIG_SERIO_RAW is not set
+
+#
+# Input Device Drivers
+#
+CONFIG_INPUT_KEYBOARD=y
+CONFIG_KEYBOARD_ATKBD=y
+# CONFIG_KEYBOARD_SUNKBD is not set
+# CONFIG_KEYBOARD_LKKBD is not set
+# CONFIG_KEYBOARD_XTKBD is not set
+# CONFIG_KEYBOARD_NEWTON is not set
+CONFIG_INPUT_MOUSE=y
+CONFIG_MOUSE_PS2=y
+# CONFIG_MOUSE_SERIAL is not set
+# CONFIG_MOUSE_INPORT is not set
+# CONFIG_MOUSE_LOGIBM is not set
+# CONFIG_MOUSE_PC110PAD is not set
+# CONFIG_MOUSE_VSXXXAA is not set
+# CONFIG_INPUT_JOYSTICK is not set
+# CONFIG_INPUT_TOUCHSCREEN is not set
+# CONFIG_INPUT_MISC is not set
+
+#
+# Character devices
+#
+CONFIG_VT=y
+CONFIG_VT_CONSOLE=y
+CONFIG_HW_CONSOLE=y
+# CONFIG_SERIAL_NONSTANDARD is not set
+
+#
+# Serial drivers
+#
+CONFIG_SERIAL_8250=y
+# CONFIG_SERIAL_8250_CONSOLE is not set
+# CONFIG_SERIAL_8250_ACPI is not set
+CONFIG_SERIAL_8250_NR_UARTS=4
+# CONFIG_SERIAL_8250_EXTENDED is not set
+
+#
+# Non-8250 serial port support
+#
+CONFIG_SERIAL_CORE=y
+CONFIG_UNIX98_PTYS=y
+CONFIG_LEGACY_PTYS=y
+CONFIG_LEGACY_PTY_COUNT=256
+
+#
+# IPMI
+#
+# CONFIG_IPMI_HANDLER is not set
+
+#
+# Watchdog Cards
+#
+# CONFIG_WATCHDOG is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_NVRAM is not set
+# CONFIG_RTC is not set
+# CONFIG_GEN_RTC is not set
+# CONFIG_DTLK is not set
+# CONFIG_R3964 is not set
+# CONFIG_APPLICOM is not set
+# CONFIG_SONYPI is not set
+
+#
+# Ftape, the floppy tape device driver
+#
+# CONFIG_AGP is not set
+# CONFIG_DRM is not set
+# CONFIG_MWAVE is not set
+# CONFIG_RAW_DRIVER is not set
+# CONFIG_HPET is not set
+# CONFIG_HANGCHECK_TIMER is not set
+
+#
+# I2C support
+#
+CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
+
+#
+# I2C Algorithms
+#
+CONFIG_I2C_ALGOBIT=y
+# CONFIG_I2C_ALGOPCF is not set
+# CONFIG_I2C_ALGOPCA is not set
+
+#
+# I2C Hardware Bus support
+#
+# CONFIG_I2C_ALI1535 is not set
+# CONFIG_I2C_ALI1563 is not set
+# CONFIG_I2C_ALI15X3 is not set
+# CONFIG_I2C_AMD756 is not set
+# CONFIG_I2C_AMD8111 is not set
+# CONFIG_I2C_I801 is not set
+# CONFIG_I2C_I810 is not set
+# CONFIG_I2C_ISA is not set
+# CONFIG_I2C_NFORCE2 is not set
+# CONFIG_I2C_PARPORT_LIGHT is not set
+# CONFIG_I2C_PIIX4 is not set
+# CONFIG_I2C_PROSAVAGE is not set
+# CONFIG_I2C_SAVAGE4 is not set
+# CONFIG_SCx200_ACB is not set
+# CONFIG_I2C_SIS5595 is not set
+# CONFIG_I2C_SIS630 is not set
+CONFIG_I2C_SIS96X=y
+# CONFIG_I2C_STUB is not set
+# CONFIG_I2C_VIA is not set
+# CONFIG_I2C_VIAPRO is not set
+# CONFIG_I2C_VOODOO3 is not set
+# CONFIG_I2C_PCA_ISA is not set
+
+#
+# Hardware Sensors Chip support
+#
+CONFIG_I2C_SENSOR=y
+# CONFIG_SENSORS_ADM1021 is not set
+# CONFIG_SENSORS_ADM1025 is not set
+# CONFIG_SENSORS_ADM1031 is not set
+# CONFIG_SENSORS_ASB100 is not set
+# CONFIG_SENSORS_DS1621 is not set
+# CONFIG_SENSORS_FSCHER is not set
+# CONFIG_SENSORS_GL518SM is not set
+# CONFIG_SENSORS_IT87 is not set
+# CONFIG_SENSORS_LM63 is not set
+# CONFIG_SENSORS_LM75 is not set
+# CONFIG_SENSORS_LM77 is not set
+# CONFIG_SENSORS_LM78 is not set
+# CONFIG_SENSORS_LM80 is not set
+# CONFIG_SENSORS_LM83 is not set
+# CONFIG_SENSORS_LM85 is not set
+# CONFIG_SENSORS_LM87 is not set
+# CONFIG_SENSORS_LM90 is not set
+# CONFIG_SENSORS_MAX1619 is not set
+# CONFIG_SENSORS_PC87360 is not set
+# CONFIG_SENSORS_SMSC47M1 is not set
+# CONFIG_SENSORS_VIA686A is not set
+# CONFIG_SENSORS_W83781D is not set
+# CONFIG_SENSORS_W83L785TS is not set
+# CONFIG_SENSORS_W83627HF is not set
+
+#
+# Other I2C Chip support
+#
+CONFIG_SENSORS_EEPROM=y
+# CONFIG_SENSORS_PCF8574 is not set
+# CONFIG_SENSORS_PCF8591 is not set
+# CONFIG_SENSORS_RTC8564 is not set
+# CONFIG_I2C_DEBUG_CORE is not set
+# CONFIG_I2C_DEBUG_ALGO is not set
+# CONFIG_I2C_DEBUG_BUS is not set
+# CONFIG_I2C_DEBUG_CHIP is not set
+
+#
+# Dallas's 1-wire bus
+#
+# CONFIG_W1 is not set
+
+#
+# Misc devices
+#
+# CONFIG_IBM_ASM is not set
+
+#
+# Multimedia devices
+#
+# CONFIG_VIDEO_DEV is not set
+
+#
+# Digital Video Broadcasting Devices
+#
+# CONFIG_DVB is not set
+
+#
+# Graphics support
+#
+# CONFIG_FB is not set
+# CONFIG_VIDEO_SELECT is not set
+
+#
+# Console display driver support
+#
+CONFIG_VGA_CONSOLE=y
+# CONFIG_MDA_CONSOLE is not set
+CONFIG_DUMMY_CONSOLE=y
+
+#
+# Sound
+#
+CONFIG_SOUND=y
+
+#
+# Advanced Linux Sound Architecture
+#
+CONFIG_SND=y
+CONFIG_SND_TIMER=y
+CONFIG_SND_PCM=y
+CONFIG_SND_HWDEP=y
+CONFIG_SND_RAWMIDI=y
+CONFIG_SND_SEQUENCER=y
+# CONFIG_SND_SEQ_DUMMY is not set
+CONFIG_SND_OSSEMUL=y
+CONFIG_SND_MIXER_OSS=y
+CONFIG_SND_PCM_OSS=y
+CONFIG_SND_SEQUENCER_OSS=y
+# CONFIG_SND_VERBOSE_PRINTK is not set
+# CONFIG_SND_DEBUG is not set
+
+#
+# Generic devices
+#
+# CONFIG_SND_DUMMY is not set
+# CONFIG_SND_VIRMIDI is not set
+# CONFIG_SND_MTPAV is not set
+# CONFIG_SND_SERIAL_U16550 is not set
+# CONFIG_SND_MPU401 is not set
+
+#
+# ISA devices
+#
+# CONFIG_SND_AD1848 is not set
+# CONFIG_SND_CS4231 is not set
+# CONFIG_SND_CS4232 is not set
+# CONFIG_SND_CS4236 is not set
+# CONFIG_SND_ES1688 is not set
+# CONFIG_SND_ES18XX is not set
+# CONFIG_SND_GUSCLASSIC is not set
+# CONFIG_SND_GUSEXTREME is not set
+# CONFIG_SND_GUSMAX is not set
+# CONFIG_SND_INTERWAVE is not set
+# CONFIG_SND_INTERWAVE_STB is not set
+# CONFIG_SND_OPTI92X_AD1848 is not set
+# CONFIG_SND_OPTI92X_CS4231 is not set
+# CONFIG_SND_OPTI93X is not set
+# CONFIG_SND_SB8 is not set
+# CONFIG_SND_SB16 is not set
+# CONFIG_SND_SBAWE is not set
+# CONFIG_SND_WAVEFRONT is not set
+# CONFIG_SND_CMI8330 is not set
+# CONFIG_SND_OPL3SA2 is not set
+# CONFIG_SND_SGALAXY is not set
+# CONFIG_SND_SSCAPE is not set
+
+#
+# PCI devices
+#
+CONFIG_SND_AC97_CODEC=y
+# CONFIG_SND_ALI5451 is not set
+# CONFIG_SND_ATIIXP is not set
+# CONFIG_SND_ATIIXP_MODEM is not set
+# CONFIG_SND_AU8810 is not set
+# CONFIG_SND_AU8820 is not set
+# CONFIG_SND_AU8830 is not set
+# CONFIG_SND_AZT3328 is not set
+# CONFIG_SND_BT87X is not set
+# CONFIG_SND_CS46XX is not set
+# CONFIG_SND_CS4281 is not set
+CONFIG_SND_EMU10K1=y
+# CONFIG_SND_KORG1212 is not set
+# CONFIG_SND_MIXART is not set
+# CONFIG_SND_NM256 is not set
+# CONFIG_SND_RME32 is not set
+# CONFIG_SND_RME96 is not set
+# CONFIG_SND_RME9652 is not set
+# CONFIG_SND_HDSP is not set
+# CONFIG_SND_TRIDENT is not set
+# CONFIG_SND_YMFPCI is not set
+# CONFIG_SND_ALS4000 is not set
+# CONFIG_SND_CMIPCI is not set
+# CONFIG_SND_ENS1370 is not set
+# CONFIG_SND_ENS1371 is not set
+# CONFIG_SND_ES1938 is not set
+# CONFIG_SND_ES1968 is not set
+# CONFIG_SND_MAESTRO3 is not set
+# CONFIG_SND_FM801 is not set
+# CONFIG_SND_ICE1712 is not set
+# CONFIG_SND_ICE1724 is not set
+# CONFIG_SND_INTEL8X0 is not set
+# CONFIG_SND_INTEL8X0M is not set
+# CONFIG_SND_SONICVIBES is not set
+# CONFIG_SND_VIA82XX is not set
+# CONFIG_SND_VX222 is not set
+
+#
+# USB devices
+#
+# CONFIG_SND_USB_AUDIO is not set
+# CONFIG_SND_USB_USX2Y is not set
+
+#
+# Open Sound System
+#
+# CONFIG_SOUND_PRIME is not set
+
+#
+# USB support
+#
+CONFIG_USB=y
+# CONFIG_USB_DEBUG is not set
+
+#
+# Miscellaneous USB options
+#
+CONFIG_USB_DEVICEFS=y
+# CONFIG_USB_BANDWIDTH is not set
+# CONFIG_USB_DYNAMIC_MINORS is not set
+# CONFIG_USB_SUSPEND is not set
+# CONFIG_USB_OTG is not set
+CONFIG_USB_ARCH_HAS_HCD=y
+CONFIG_USB_ARCH_HAS_OHCI=y
+
+#
+# USB Host Controller Drivers
+#
+CONFIG_USB_EHCI_HCD=y
+# CONFIG_USB_EHCI_SPLIT_ISO is not set
+# CONFIG_USB_EHCI_ROOT_HUB_TT is not set
+# CONFIG_USB_OHCI_HCD is not set
+CONFIG_USB_UHCI_HCD=y
+
+#
+# USB Device Class drivers
+#
+# CONFIG_USB_AUDIO is not set
+# CONFIG_USB_BLUETOOTH_TTY is not set
+# CONFIG_USB_MIDI is not set
+# CONFIG_USB_ACM is not set
+CONFIG_USB_PRINTER=y
+CONFIG_USB_STORAGE=y
+# CONFIG_USB_STORAGE_DEBUG is not set
+# CONFIG_USB_STORAGE_RW_DETECT is not set
+# CONFIG_USB_STORAGE_DATAFAB is not set
+# CONFIG_USB_STORAGE_FREECOM is not set
+# CONFIG_USB_STORAGE_ISD200 is not set
+# CONFIG_USB_STORAGE_DPCM is not set
+# CONFIG_USB_STORAGE_HP8200e is not set
+# CONFIG_USB_STORAGE_SDDR09 is not set
+# CONFIG_USB_STORAGE_SDDR55 is not set
+# CONFIG_USB_STORAGE_JUMPSHOT is not set
+
+#
+# USB Input Devices
+#
+CONFIG_USB_HID=y
+CONFIG_USB_HIDINPUT=y
+# CONFIG_HID_FF is not set
+# CONFIG_USB_HIDDEV is not set
+# CONFIG_USB_AIPTEK is not set
+# CONFIG_USB_WACOM is not set
+# CONFIG_USB_KBTAB is not set
+# CONFIG_USB_POWERMATE is not set
+# CONFIG_USB_MTOUCH is not set
+CONFIG_USB_EGALAX=m
+# CONFIG_USB_XPAD is not set
+# CONFIG_USB_ATI_REMOTE is not set
+
+#
+# USB Imaging devices
+#
+# CONFIG_USB_MDC800 is not set
+# CONFIG_USB_MICROTEK is not set
+# CONFIG_USB_HPUSBSCSI is not set
+
+#
+# USB Multimedia devices
+#
+# CONFIG_USB_DABUSB is not set
+
+#
+# Video4Linux support is needed for USB Multimedia device support
+#
+
+#
+# USB Network Adapters
+#
+# CONFIG_USB_CATC is not set
+# CONFIG_USB_KAWETH is not set
+# CONFIG_USB_PEGASUS is not set
+# CONFIG_USB_RTL8150 is not set
+# CONFIG_USB_USBNET is not set
+
+#
+# USB port drivers
+#
+
+#
+# USB Serial Converter support
+#
+# CONFIG_USB_SERIAL is not set
+
+#
+# USB Miscellaneous drivers
+#
+# CONFIG_USB_EMI62 is not set
+# CONFIG_USB_EMI26 is not set
+# CONFIG_USB_TIGL is not set
+# CONFIG_USB_AUERSWALD is not set
+# CONFIG_USB_RIO500 is not set
+# CONFIG_USB_LEGOTOWER is not set
+# CONFIG_USB_LCD is not set
+# CONFIG_USB_LED is not set
+CONFIG_USB_CYTHERM=m
+# CONFIG_USB_PHIDGETKIT is not set
+CONFIG_USB_PHIDGETSERVO=m
+# CONFIG_USB_TEST is not set
+
+#
+# USB ATM/DSL drivers
+#
+# CONFIG_USB_ATM is not set
+# CONFIG_USB_SPEEDTOUCH is not set
+
+#
+# USB Gadget Support
+#
+# CONFIG_USB_GADGET is not set
+
+#
+# File systems
+#
+CONFIG_EXT2_FS=y
+# CONFIG_EXT2_FS_XATTR is not set
+CONFIG_EXT3_FS=y
+CONFIG_EXT3_FS_XATTR=y
+# CONFIG_EXT3_FS_POSIX_ACL is not set
+# CONFIG_EXT3_FS_SECURITY is not set
+CONFIG_JBD=y
+# CONFIG_JBD_DEBUG is not set
+CONFIG_FS_MBCACHE=y
+# CONFIG_REISERFS_FS is not set
+# CONFIG_JFS_FS is not set
+# CONFIG_XFS_FS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_ROMFS_FS is not set
+# CONFIG_QUOTA is not set
+CONFIG_DNOTIFY=y
+# CONFIG_AUTOFS_FS is not set
+CONFIG_AUTOFS4_FS=y
+
+#
+# CD-ROM/DVD Filesystems
+#
+CONFIG_ISO9660_FS=y
+CONFIG_JOLIET=y
+# CONFIG_ZISOFS is not set
+CONFIG_UDF_FS=y
+CONFIG_UDF_NLS=y
+
+#
+# DOS/FAT/NT Filesystems
+#
+CONFIG_FAT_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_FAT_DEFAULT_CODEPAGE=437
+CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
+# CONFIG_NTFS_FS is not set
+
+#
+# Pseudo filesystems
+#
+CONFIG_PROC_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_SYSFS=y
+# CONFIG_DEVFS_FS is not set
+# CONFIG_DEVPTS_FS_XATTR is not set
+CONFIG_TMPFS=y
+# CONFIG_TMPFS_XATTR is not set
+# CONFIG_HUGETLBFS is not set
+# CONFIG_HUGETLB_PAGE is not set
+CONFIG_RAMFS=y
+
+#
+# Miscellaneous filesystems
+#
+# CONFIG_ADFS_FS is not set
+# CONFIG_AFFS_FS is not set
+# CONFIG_HFS_FS is not set
+# CONFIG_HFSPLUS_FS is not set
+# CONFIG_BEFS_FS is not set
+# CONFIG_BFS_FS is not set
+# CONFIG_EFS_FS is not set
+# CONFIG_CRAMFS is not set
+# CONFIG_VXFS_FS is not set
+# CONFIG_HPFS_FS is not set
+# CONFIG_QNX4FS_FS is not set
+# CONFIG_SYSV_FS is not set
+# CONFIG_UFS_FS is not set
+
+#
+# Network File Systems
+#
+CONFIG_NFS_FS=y
+# CONFIG_NFS_V3 is not set
+# CONFIG_NFS_V4 is not set
+# CONFIG_NFS_DIRECTIO is not set
+CONFIG_NFSD=y
+# CONFIG_NFSD_V3 is not set
+CONFIG_NFSD_TCP=y
+CONFIG_LOCKD=y
+CONFIG_EXPORTFS=y
+CONFIG_SUNRPC=y
+# CONFIG_RPCSEC_GSS_KRB5 is not set
+# CONFIG_RPCSEC_GSS_SPKM3 is not set
+# CONFIG_SMB_FS is not set
+# CONFIG_CIFS is not set
+# CONFIG_NCP_FS is not set
+# CONFIG_CODA_FS is not set
+# CONFIG_AFS_FS is not set
+
+#
+# Partition Types
+#
+# CONFIG_PARTITION_ADVANCED is not set
+CONFIG_MSDOS_PARTITION=y
+
+#
+# Native Language Support
+#
+CONFIG_NLS=y
+CONFIG_NLS_DEFAULT="iso8859-1"
+CONFIG_NLS_CODEPAGE_437=y
+# CONFIG_NLS_CODEPAGE_737 is not set
+# CONFIG_NLS_CODEPAGE_775 is not set
+# CONFIG_NLS_CODEPAGE_850 is not set
+# CONFIG_NLS_CODEPAGE_852 is not set
+# CONFIG_NLS_CODEPAGE_855 is not set
+# CONFIG_NLS_CODEPAGE_857 is not set
+# CONFIG_NLS_CODEPAGE_860 is not set
+# CONFIG_NLS_CODEPAGE_861 is not set
+# CONFIG_NLS_CODEPAGE_862 is not set
+# CONFIG_NLS_CODEPAGE_863 is not set
+# CONFIG_NLS_CODEPAGE_864 is not set
+# CONFIG_NLS_CODEPAGE_865 is not set
+# CONFIG_NLS_CODEPAGE_866 is not set
+# CONFIG_NLS_CODEPAGE_869 is not set
+# CONFIG_NLS_CODEPAGE_936 is not set
+# CONFIG_NLS_CODEPAGE_950 is not set
+# CONFIG_NLS_CODEPAGE_932 is not set
+# CONFIG_NLS_CODEPAGE_949 is not set
+# CONFIG_NLS_CODEPAGE_874 is not set
+# CONFIG_NLS_ISO8859_8 is not set
+# CONFIG_NLS_CODEPAGE_1250 is not set
+# CONFIG_NLS_CODEPAGE_1251 is not set
+# CONFIG_NLS_ASCII is not set
+CONFIG_NLS_ISO8859_1=y
+# CONFIG_NLS_ISO8859_2 is not set
+# CONFIG_NLS_ISO8859_3 is not set
+# CONFIG_NLS_ISO8859_4 is not set
+# CONFIG_NLS_ISO8859_5 is not set
+# CONFIG_NLS_ISO8859_6 is not set
+# CONFIG_NLS_ISO8859_7 is not set
+# CONFIG_NLS_ISO8859_9 is not set
+# CONFIG_NLS_ISO8859_13 is not set
+# CONFIG_NLS_ISO8859_14 is not set
+# CONFIG_NLS_ISO8859_15 is not set
+# CONFIG_NLS_KOI8_R is not set
+# CONFIG_NLS_KOI8_U is not set
+# CONFIG_NLS_UTF8 is not set
+
+#
+# Profiling support
+#
+CONFIG_PROFILING=y
+CONFIG_OPROFILE=y
+
+#
+# Kernel hacking
+#
+CONFIG_DEBUG_KERNEL=y
+CONFIG_MAGIC_SYSRQ=y
+# CONFIG_SCHEDSTATS is not set
+CONFIG_DEBUG_SLAB=y
+# CONFIG_DEBUG_SPINLOCK is not set
+# CONFIG_DEBUG_SPINLOCK_SLEEP is not set
+# CONFIG_DEBUG_KOBJECT is not set
+# CONFIG_DEBUG_INFO is not set
+CONFIG_FRAME_POINTER=y
+CONFIG_EARLY_PRINTK=y
+# CONFIG_DEBUG_STACKOVERFLOW is not set
+# CONFIG_KPROBES is not set
+# CONFIG_DEBUG_STACK_USAGE is not set
+# CONFIG_DEBUG_PAGEALLOC is not set
+# CONFIG_4KSTACKS is not set
+CONFIG_X86_FIND_SMP_CONFIG=y
+CONFIG_X86_MPPARSE=y
+
+#
+# Security options
+#
+# CONFIG_KEYS is not set
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_SECURITY_CAPABILITIES=m
+CONFIG_SECURITY_ROOTPLUG=m
+# CONFIG_SECURITY_SECLVL is not set
+CONFIG_SECURITY_SELINUX=y
+# CONFIG_SECURITY_SELINUX_BOOTPARAM is not set
+CONFIG_SECURITY_SELINUX_DISABLE=y
+CONFIG_SECURITY_SELINUX_DEVELOP=y
+# CONFIG_SECURITY_SELINUX_MLS is not set
+
+#
+# Cryptographic options
+#
+CONFIG_CRYPTO=y
+CONFIG_CRYPTO_HMAC=y
+CONFIG_CRYPTO_NULL=y
+CONFIG_CRYPTO_MD4=y
+CONFIG_CRYPTO_MD5=y
+CONFIG_CRYPTO_SHA1=y
+CONFIG_CRYPTO_SHA256=y
+CONFIG_CRYPTO_SHA512=y
+CONFIG_CRYPTO_WP512=y
+CONFIG_CRYPTO_DES=y
+CONFIG_CRYPTO_BLOWFISH=y
+CONFIG_CRYPTO_TWOFISH=y
+CONFIG_CRYPTO_SERPENT=y
+CONFIG_CRYPTO_AES_586=y
+CONFIG_CRYPTO_CAST5=y
+CONFIG_CRYPTO_CAST6=y
+CONFIG_CRYPTO_TEA=y
+CONFIG_CRYPTO_ARC4=y
+CONFIG_CRYPTO_KHAZAD=y
+# CONFIG_CRYPTO_ANUBIS is not set
+CONFIG_CRYPTO_DEFLATE=y
+CONFIG_CRYPTO_MICHAEL_MIC=y
+CONFIG_CRYPTO_CRC32C=y
+CONFIG_CRYPTO_TEST=y
+
+#
+# Library routines
+#
+# CONFIG_CRC_CCITT is not set
+CONFIG_CRC32=y
+CONFIG_LIBCRC32C=y
+CONFIG_ZLIB_INFLATE=y
+CONFIG_ZLIB_DEFLATE=y
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_GENERIC_IRQ_PROBE=y
+CONFIG_X86_SMP=y
+CONFIG_X86_HT=y
+CONFIG_X86_BIOS_REBOOT=y
+CONFIG_X86_TRAMPOLINE=y
+CONFIG_PC=y
diff --git a/iproute2/testsuite/iproute2/Makefile b/iproute2/testsuite/iproute2/Makefile
new file mode 100644
index 0000000..ba128aa
--- /dev/null
+++ b/iproute2/testsuite/iproute2/Makefile
@@ -0,0 +1,33 @@
+SUBDIRS := $(filter-out Makefile,$(wildcard *))
+.PHONY: all configure clean distclean show $(SUBDIRS)
+
+all: configure
+ @for dir in $(SUBDIRS); do \
+ echo "Entering $$dir" && cd $$dir && $(MAKE) && cd ..; \
+ done
+
+link:
+ @if [ ! -L iproute2-this ]; then \
+ ln -s ../.. iproute2-this; \
+ fi
+
+configure: link
+ @for dir in $(SUBDIRS); do \
+ echo "Entering $$dir" && cd $$dir && if [ -f configure ]; then ./configure; fi && cd ..; \
+ done
+
+clean: link
+ @for dir in $(SUBDIRS); do \
+ echo "Entering $$dir" && cd $$dir && $(MAKE) clean && cd ..; \
+ done
+
+distclean: clean
+ @for dir in $(SUBDIRS); do \
+ echo "Entering $$dir" && cd $$dir && $(MAKE) distclean && cd ..; \
+ done
+
+show: link
+ @echo "$(SUBDIRS)"
+
+$(SUBDIRS):
+ cd $@ && $(MAKE)
diff --git a/iproute2/testsuite/lib/generic.sh b/iproute2/testsuite/lib/generic.sh
new file mode 100644
index 0000000..b7de704
--- /dev/null
+++ b/iproute2/testsuite/lib/generic.sh
@@ -0,0 +1,135 @@
+
+export DEST="127.0.0.1"
+
+ts_log()
+{
+ echo "$@"
+}
+
+ts_err()
+{
+ ts_log "$@" | tee >> $ERRF
+}
+
+ts_cat()
+{
+ cat "$@"
+}
+
+ts_err_cat()
+{
+ ts_cat "$@" | tee >> $ERRF
+}
+
+ts_skip()
+{
+ exit 127
+}
+
+ts_tc()
+{
+ SCRIPT=$1; shift
+ DESC=$1; shift
+
+ $TC $@ 2> $STD_ERR > $STD_OUT
+
+ if [ -s $STD_ERR ]; then
+ ts_err "${SCRIPT}: ${DESC} failed:"
+ ts_err "command: $TC $@"
+ ts_err "stderr output:"
+ ts_err_cat $STD_ERR
+ if [ -s $STD_OUT ]; then
+ ts_err "stdout output:"
+ ts_err_cat $STD_OUT
+ fi
+ elif [ -s $STD_OUT ]; then
+ echo "${SCRIPT}: ${DESC} succeeded with output:"
+ cat $STD_OUT
+ else
+ echo "${SCRIPT}: ${DESC} succeeded"
+ fi
+}
+
+ts_ip()
+{
+ SCRIPT=$1; shift
+ DESC=$1; shift
+
+ $IP $@ 2> $STD_ERR > $STD_OUT
+ RET=$?
+
+ if [ -s $STD_ERR ] || [ "$RET" != "0" ]; then
+ ts_err "${SCRIPT}: ${DESC} failed:"
+ ts_err "command: $IP $@"
+ ts_err "stderr output:"
+ ts_err_cat $STD_ERR
+ if [ -s $STD_OUT ]; then
+ ts_err "stdout output:"
+ ts_err_cat $STD_OUT
+ fi
+ elif [ -s $STD_OUT ]; then
+ echo "${SCRIPT}: ${DESC} succeeded with output:"
+ cat $STD_OUT
+ else
+ echo "${SCRIPT}: ${DESC} succeeded"
+ fi
+}
+
+ts_qdisc_available()
+{
+ HELPOUT=`$TC qdisc add $1 help 2>&1`
+ if [ "`echo $HELPOUT | grep \"^Unknown qdisc\"`" ]; then
+ return 0;
+ else
+ return 1;
+ fi
+}
+
+rand_dev()
+{
+ echo "dev-$(tr -dc "[:alpha:]" < /dev/urandom | head -c 6)"
+}
+
+pr_failed()
+{
+ echo " [FAILED]"
+ ts_err "matching failed"
+}
+
+pr_success()
+{
+ echo " [SUCCESS]"
+}
+
+test_on()
+{
+ echo -n "test on: \"$1\""
+ if cat "$STD_OUT" | grep -qE "$1"
+ then
+ pr_success
+ else
+ pr_failed
+ fi
+}
+
+test_on_not()
+{
+ echo -n "test on: \"$1\""
+ if cat "$STD_OUT" | grep -vqE "$1"
+ then
+ pr_success
+ else
+ pr_failed
+ fi
+}
+
+test_lines_count()
+{
+ echo -n "test on lines count ($1): "
+ if cat "$STD_OUT" | wc -l | grep -q "$1"
+ then
+ pr_success
+ else
+ pr_failed
+ fi
+}
diff --git a/iproute2/testsuite/tests/ip/link/dev_wo_vf_rate.nl b/iproute2/testsuite/tests/ip/link/dev_wo_vf_rate.nl
new file mode 100644
index 0000000..40fa87f
--- /dev/null
+++ b/iproute2/testsuite/tests/ip/link/dev_wo_vf_rate.nl
Binary files differ
diff --git a/iproute2/testsuite/tests/ip/link/new_link.t b/iproute2/testsuite/tests/ip/link/new_link.t
new file mode 100755
index 0000000..699adbc
--- /dev/null
+++ b/iproute2/testsuite/tests/ip/link/new_link.t
@@ -0,0 +1,15 @@
+#!/bin/sh
+
+source lib/generic.sh
+
+ts_log "[Testing add/del virtual links]"
+
+NEW_DEV="$(rand_dev)"
+
+ts_ip "$0" "Add $NEW_DEV dummy interface" link add dev $NEW_DEV type dummy
+
+ts_ip "$0" "Show $NEW_DEV dummy interface" link show dev $NEW_DEV
+test_on "$NEW_DEV"
+test_lines_count 2
+
+ts_ip "$0" "Del $NEW_DEV dummy interface" link del dev $NEW_DEV
diff --git a/iproute2/testsuite/tests/ip/link/show_dev_wo_vf_rate.t b/iproute2/testsuite/tests/ip/link/show_dev_wo_vf_rate.t
new file mode 100755
index 0000000..a600ba6
--- /dev/null
+++ b/iproute2/testsuite/tests/ip/link/show_dev_wo_vf_rate.t
@@ -0,0 +1,6 @@
+#!/bin/sh
+
+source lib/generic.sh
+
+NL_FILE="tests/ip/link/dev_wo_vf_rate.nl"
+ts_ip "$0" "Show VF devices w/o VF rate info" -d monitor file $NL_FILE
diff --git a/iproute2/testsuite/tests/ip/route/add_default_route.t b/iproute2/testsuite/tests/ip/route/add_default_route.t
new file mode 100755
index 0000000..e5ea647
--- /dev/null
+++ b/iproute2/testsuite/tests/ip/route/add_default_route.t
@@ -0,0 +1,33 @@
+#!/bin/sh
+
+source lib/generic.sh
+
+ts_log "[Testing add default route]"
+
+DEV=dummy0
+
+ts_ip "$0" "Add new interface $DEV" link add $DEV type dummy
+ts_ip "$0" "Set $DEV into UP state" link set up dev $DEV
+
+ts_ip "$0" "Add 1.1.1.1/24 addr on $DEV" addr add 1.1.1.1/24 dev $DEV
+ts_ip "$0" "Add default route via 1.1.1.2" route add default via 1.1.1.2
+
+ts_ip "$0" "Show IPv4 default route" -4 route show default
+test_on "default via 1.1.1.2 dev $DEV"
+test_lines_count 1
+
+ts_ip "$0" "Add another IPv4 route dst 2.2.2.0/24" -4 route add 2.2.2.0/24 dev $DEV
+ts_ip "$0" "Show IPv4 default route" -4 route show default
+test_on "default via 1.1.1.2 dev $DEV"
+test_lines_count 1
+
+ts_ip "$0" "Add dead:beef::1/64 addr on $DEV" -6 addr add dead:beef::1/64 dev $DEV
+ts_ip "$0" "Add default route via dead:beef::2" route add default via dead:beef::2
+ts_ip "$0" "Show IPv6 default route" -6 route show default
+test_on "default via dead:beef::2 dev $DEV"
+test_lines_count 1
+
+ts_ip "$0" "Add another IPv6 route dst cafe:babe::/64" -6 route add cafe:babe::/64 dev $DEV
+ts_ip "$0" "Show IPv6 default route" -6 route show default
+test_on "default via dead:beef::2 dev $DEV"
+test_lines_count 1
diff --git a/iproute2/testsuite/tests/ip/tunnel/add_tunnel.t b/iproute2/testsuite/tests/ip/tunnel/add_tunnel.t
new file mode 100755
index 0000000..18f6e37
--- /dev/null
+++ b/iproute2/testsuite/tests/ip/tunnel/add_tunnel.t
@@ -0,0 +1,14 @@
+#!/bin/sh
+
+source lib/generic.sh
+
+TUNNEL_NAME="tunnel_test_ip"
+
+ts_log "[Testing add/del tunnels]"
+
+ts_ip "$0" "Add GRE tunnel over IPv4" tunnel add name $TUNNEL_NAME mode gre local 1.1.1.1 remote 2.2.2.2
+ts_ip "$0" "Del GRE tunnel over IPv4" tunnel del $TUNNEL_NAME
+
+ts_ip "$0" "Add GRE tunnel over IPv6" tunnel add name $TUNNEL_NAME mode ip6gre local dead:beef::1 remote dead:beef::2
+ts_ip "$0" "Del GRE tunnel over IPv6" tunnel del $TUNNEL_NAME
+
diff --git a/iproute2/testsuite/tests/tc/cbq.t b/iproute2/testsuite/tests/tc/cbq.t
new file mode 100755
index 0000000..bff814b
--- /dev/null
+++ b/iproute2/testsuite/tests/tc/cbq.t
@@ -0,0 +1,10 @@
+#!/bin/sh
+$TC qdisc del dev $DEV root >/dev/null 2>&1
+$TC qdisc add dev $DEV root handle 10:0 cbq bandwidth 100Mbit avpkt 1400 mpu 64
+$TC class add dev $DEV parent 10:0 classid 10:12 cbq bandwidth 100mbit rate 100mbit allot 1514 prio 3 maxburst 1 avpkt 500 bounded
+$TC qdisc list dev $DEV
+$TC qdisc del dev $DEV root
+$TC qdisc list dev $DEV
+$TC qdisc add dev $DEV root handle 10:0 cbq bandwidth 100Mbit avpkt 1400 mpu 64
+$TC class add dev $DEV parent 10:0 classid 10:12 cbq bandwidth 100mbit rate 100mbit allot 1514 prio 3 maxburst 1 avpkt 500 bounded
+$TC qdisc del dev $DEV root
diff --git a/iproute2/testsuite/tests/tc/cls-testbed.t b/iproute2/testsuite/tests/tc/cls-testbed.t
new file mode 100755
index 0000000..2afc26f
--- /dev/null
+++ b/iproute2/testsuite/tests/tc/cls-testbed.t
@@ -0,0 +1,73 @@
+#!/bin/bash
+# vim: ft=sh
+
+source lib/generic.sh
+
+QDISCS="cbq htb dsmark"
+
+if [ ! -d tests/cls ]; then
+ ts_log "tests/cls folder does not exist"
+ ts_skip
+fi
+
+for q in ${QDISCS}; do
+ ts_log "Preparing classifier testbed with qdisc $q"
+
+ for c in tests/cls/*.c; do
+
+ case "$q" in
+ cbq)
+ ts_tc "cls-testbed" "cbq root qdisc creation" \
+ qdisc add dev $DEV root handle 10:0 \
+ cbq bandwidth 100Mbit avpkt 1400 mpu 64
+ ts_tc "cls-testbed" "cbq root class creation" \
+ class add dev $DEV parent 10:0 classid 10:12 \
+ cbq bandwidth 100mbit rate 100mbit allot 1514 prio 3 \
+ maxburst 1 avpkt 500 bounded
+ ;;
+ htb)
+ ts_qdisc_available "htb"
+ if [ $? -eq 0 ]; then
+ ts_log "cls-testbed: HTB is unsupported by $TC, skipping"
+ continue;
+ fi
+ ts_tc "cls-testbed" "htb root qdisc creation" \
+ qdisc add dev $DEV root handle 10:0 htb
+ ts_tc "cls-testbed" "htb root class creation" \
+ class add dev $DEV parent 10:0 classid 10:12 \
+ htb rate 100Mbit quantum 1514
+ ;;
+ dsmark)
+ ts_qdisc_available "dsmark"
+ if [ $? -eq 0 ]; then
+ ts_log "cls-testbed: dsmark is unsupported by $TC, skipping"
+ continue;
+ fi
+ ts_tc "cls-testbed" "dsmark root qdisc creation" \
+ qdisc add dev $DEV root handle 20:0 \
+ dsmark indices 64 default_index 1 set_tc_index
+ ts_tc "cls-testbed" "dsmark class creation" \
+ class change dev $DEV parent 20:0 classid 20:12 \
+ dsmark mask 0xff value 2
+ ts_tc "cls-testbed" "prio inner qdisc creation" \
+ qdisc add dev $DEV parent 20:0 handle 10:0 prio
+ ;;
+ *)
+ ts_err "cls-testbed: no testbed configuration found for qdisc $q"
+ continue
+ ;;
+ esac
+
+ ts_tc "cls-testbed" "tree listing" qdisc list dev eth0
+ ts_tc "cls-testbed" "tree class listing" class list dev eth0
+ ts_log "cls-testbed: starting classifier test $c"
+ $c
+
+ case "$q" in
+ *)
+ ts_tc "cls-testbed" "generic qdisc tree deletion" \
+ qdisc del dev $DEV root
+ ;;
+ esac
+ done
+done
diff --git a/iproute2/testsuite/tests/tc/dsmark.t b/iproute2/testsuite/tests/tc/dsmark.t
new file mode 100755
index 0000000..6934165
--- /dev/null
+++ b/iproute2/testsuite/tests/tc/dsmark.t
@@ -0,0 +1,31 @@
+#!/bin/bash
+# vim: ft=sh
+
+source lib/generic.sh
+
+ts_qdisc_available "dsmark"
+if [ $? -eq 0 ]; then
+ ts_log "dsmark: Unsupported by $TC, skipping"
+ exit 127
+fi
+
+ts_tc "dsmark" "dsmark root qdisc creation" \
+ qdisc add dev $DEV root handle 10:0 \
+ dsmark indices 64 default_index 1 set_tc_index
+
+ts_tc "dsmark" "dsmark class 1 creation" \
+ class change dev $DEV parent 10:0 classid 10:12 \
+ dsmark mask 0xff value 2
+
+ts_tc "dsmark" "dsmark class 2 creation" \
+ class change dev $DEV parent 10:0 classid 10:13 \
+ dsmark mask 0xfc value 4
+
+ts_tc "dsmark" "dsmark dump qdisc" \
+ qdisc list dev $DEV
+
+ts_tc "dsmark" "dsmark dump class" \
+ class list dev $DEV parent 10:0
+
+ts_tc "dsmark" "generic qdisc tree deletion" \
+ qdisc del dev $DEV root
diff --git a/iproute2/testsuite/tests/tc/policer.t b/iproute2/testsuite/tests/tc/policer.t
new file mode 100755
index 0000000..eaf16ac
--- /dev/null
+++ b/iproute2/testsuite/tests/tc/policer.t
@@ -0,0 +1,13 @@
+#!/bin/sh
+$TC qdisc del dev $DEV root >/dev/null 2>&1
+$TC qdisc add dev $DEV root handle 10:0 cbq bandwidth 100Mbit avpkt 1400 mpu 64
+$TC class add dev $DEV parent 10:0 classid 10:12 cbq bandwidth 100mbit rate 100mbit allot 1514 prio 3 maxburst 1 avpkt 500 bounded
+$TC filter add dev $DEV parent 10:0 protocol ip prio 10 u32 match ip protocol 1 0xff police rate 2kbit buffer 10k drop flowid 10:12
+$TC qdisc list dev $DEV
+$TC filter list dev $DEV parent 10:0
+$TC qdisc del dev $DEV root
+$TC qdisc list dev $DEV
+$TC qdisc add dev $DEV root handle 10:0 cbq bandwidth 100Mbit avpkt 1400 mpu 64
+$TC class add dev $DEV parent 10:0 classid 10:12 cbq bandwidth 100mbit rate 100mbit allot 1514 prio 3 maxburst 1 avpkt 500 bounded
+$TC filter add dev $DEV parent 10:0 protocol ip prio 10 u32 match ip protocol 1 0xff police rate 2kbit buffer 10k drop flowid 10:12
+$TC qdisc del dev $DEV root
diff --git a/iproute2/tipc/Makefile b/iproute2/tipc/Makefile
new file mode 100644
index 0000000..f06dcb1
--- /dev/null
+++ b/iproute2/tipc/Makefile
@@ -0,0 +1,27 @@
+include ../Config
+ifeq ($(HAVE_MNL),y)
+
+TIPCOBJ=bearer.o \
+ cmdl.o link.o \
+ media.o misc.o \
+ msg.o nametable.o \
+ node.o socket.o \
+ peer.o tipc.o
+
+include ../Config
+
+TARGETS=tipc
+CFLAGS += $(shell $(PKG_CONFIG) libmnl --cflags)
+LDLIBS += $(shell $(PKG_CONFIG) libmnl --libs)
+
+endif
+
+all: $(TARGETS) $(LIBS)
+
+tipc: $(TIPCOBJ)
+
+install: all
+ install -m 0755 $(TARGETS) $(DESTDIR)$(SBINDIR)
+
+clean:
+ rm -f $(TIPCOBJ) $(TARGETS)
diff --git a/iproute2/tipc/README b/iproute2/tipc/README
new file mode 100644
index 0000000..578a0b7
--- /dev/null
+++ b/iproute2/tipc/README
@@ -0,0 +1,63 @@
+DESIGN DECISIONS
+----------------
+
+HELP
+~~~~
+--help or -h is used for help. We do not reserve the bare word "help", which
+for example the ip command does. Reserving a bare word like help quickly
+becomes cumbersome to handle in the code. It might be simple to handle
+when it's passed early in the command chain like "ip addr help". But when
+the user tries to pass "help" further down this requires manual checks and
+special treatment. For example, at the time of writing this tool, it's
+possible to create a vlan named "help" with the ip tool, but it's impossible
+to remove it, the command just shows help. This is an effect of treating
+bare words specially.
+
+Help texts are not dynamically generated. That is, we do not pass datastructures
+like command list or option lists and print them dynamically. This is
+intentional. There is always that exception and when it comes to help texts
+these exceptions are normally neglected at the expence of usability.
+
+KEY-VALUE
+~~~~~~~~~
+All options are key-values. There are both drawbacks and benefits to this.
+The main drawback is that it becomes more to write for the user and
+information might seem redundant. The main benefits is scalability and code
+simplification. Consistency is important.
+
+Consider this.
+1. tipc link set priority PRIO link LINK
+2. tipc link set LINK priority PRIO
+
+Link might seem redundant in (1). However, if the command should live for many
+years and be able to evolve example (2) limits the set command to only work on a
+single link with no ability to extend. As an example, lets say we introduce
+grouping on the kernel side.
+
+1. tipc link set priority PRIO group GROUP
+2. tipc link set ??? priority PRIO group GROUP
+
+2. breaks, we can't extend the command to cover a group.
+
+PARSING
+~~~~~~~
+Commands are single words. As an example, all words in "tipc link list" are
+commands. Options are key-values that can be given in any order. In
+"tipc link set priority PRIO link LINK" "tipc link set" are commands while
+priority and link are options. Meaning that they can be given like
+"tipc link set link LINK priority PRIO".
+
+Abbreviation matching works for both command and options. Meaning that
+"tipc link set priority PRIO link LINK" could be given as
+"tipc l s p PRIO l LINK" and "tipc link list" as "tipc l l".
+
+MEMORY
+~~~~~~
+The tool strives to avoid allocating memory on the heap. Most (if not all)
+memory allocations are on the stack.
+
+RETURNING
+~~~~~~~~~
+The tool could throw exit() deep down in functions but doing so always seems
+to limit the program in the long run. So we output the error and return an
+appropriate error code upon failure.
diff --git a/iproute2/tipc/bearer.c b/iproute2/tipc/bearer.c
new file mode 100644
index 0000000..30b54d9
--- /dev/null
+++ b/iproute2/tipc/bearer.c
@@ -0,0 +1,725 @@
+/*
+ * bearer.c TIPC bearer functionality.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Richard Alpe <richard.alpe@ericsson.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <netdb.h>
+#include <errno.h>
+
+#include <linux/tipc_netlink.h>
+#include <linux/tipc.h>
+#include <linux/genetlink.h>
+
+#include <libmnl/libmnl.h>
+#include <sys/socket.h>
+
+#include "cmdl.h"
+#include "msg.h"
+#include "bearer.h"
+
+static void _print_bearer_opts(void)
+{
+ fprintf(stderr,
+ "\nOPTIONS\n"
+ " priority - Bearer link priority\n"
+ " tolerance - Bearer link tolerance\n"
+ " window - Bearer link window\n");
+}
+
+static void _print_bearer_media(void)
+{
+ fprintf(stderr,
+ "\nMEDIA\n"
+ " udp - User Datagram Protocol\n"
+ " ib - Infiniband\n"
+ " eth - Ethernet\n");
+}
+
+static void cmd_bearer_enable_l2_help(struct cmdl *cmdl)
+{
+ fprintf(stderr,
+ "Usage: %s bearer enable media MEDIA device DEVICE [OPTIONS]\n"
+ "\nOPTIONS\n"
+ " domain DOMAIN - Discovery domain\n"
+ " priority PRIORITY - Bearer priority\n",
+ cmdl->argv[0]);
+}
+
+static void cmd_bearer_enable_udp_help(struct cmdl *cmdl)
+{
+ fprintf(stderr,
+ "Usage: %s bearer enable media udp name NAME localip IP [OPTIONS]\n"
+ "\nOPTIONS\n"
+ " domain DOMAIN - Discovery domain\n"
+ " priority PRIORITY - Bearer priority\n"
+ " localport PORT - Local UDP port (default 6118)\n"
+ " remoteip IP - Remote IP address\n"
+ " remoteport IP - Remote UDP port (default 6118)\n",
+ cmdl->argv[0]);
+}
+
+static int enable_l2_bearer(struct nlmsghdr *nlh, struct opt *opts,
+ struct cmdl *cmdl)
+{
+ struct opt *opt;
+ char id[TIPC_MAX_BEARER_NAME];
+
+ if (!(opt = get_opt(opts, "device"))) {
+ fprintf(stderr, "error: missing bearer device\n");
+ return -EINVAL;
+ }
+ snprintf(id, sizeof(id), "eth:%s", opt->val);
+ mnl_attr_put_strz(nlh, TIPC_NLA_BEARER_NAME, id);
+
+ return 0;
+}
+
+static int get_netid_cb(const struct nlmsghdr *nlh, void *data)
+{
+ struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+ struct nlattr *info[TIPC_NLA_MAX + 1] = {};
+ struct nlattr *attrs[TIPC_NLA_NET_MAX + 1] = {};
+ int *netid = (int*)data;
+
+ mnl_attr_parse(nlh, sizeof(*genl), parse_attrs, info);
+ if (!info[TIPC_NLA_NET])
+ return MNL_CB_ERROR;
+ mnl_attr_parse_nested(info[TIPC_NLA_NET], parse_attrs, attrs);
+ if (!attrs[TIPC_NLA_NET_ID])
+ return MNL_CB_ERROR;
+ *netid = mnl_attr_get_u32(attrs[TIPC_NLA_NET_ID]);
+
+ return MNL_CB_OK;
+}
+
+static int generate_multicast(short af, char *buf, int bufsize)
+{
+ int netid;
+ char mnl_msg[MNL_SOCKET_BUFFER_SIZE];
+ struct nlmsghdr *nlh;
+
+ if (!(nlh = msg_init(mnl_msg, TIPC_NL_NET_GET))) {
+ fprintf(stderr, "error, message initialization failed\n");
+ return -1;
+ }
+ if (msg_dumpit(nlh, get_netid_cb, &netid)) {
+ fprintf(stderr, "error, failed to fetch TIPC network id from kernel\n");
+ return -EINVAL;
+ }
+ if (af == AF_INET)
+ snprintf(buf, bufsize, "228.0.%u.%u", (netid>>8) & 0xFF, netid & 0xFF);
+ else
+ snprintf(buf, bufsize, "ff02::%u", netid);
+
+ return 0;
+}
+
+static int enable_udp_bearer(struct nlmsghdr *nlh, struct opt *opts,
+ struct cmdl *cmdl)
+{
+ int err;
+ struct opt *opt;
+ struct nlattr *nest;
+ char buf[INET6_ADDRSTRLEN];
+ char *locport = "6118";
+ char *remport = "6118";
+ char *locip = NULL;
+ char *remip = NULL;
+ char name[TIPC_MAX_BEARER_NAME];
+ struct addrinfo *loc = NULL;
+ struct addrinfo *rem = NULL;
+ struct addrinfo hints = {
+ .ai_family = AF_UNSPEC,
+ .ai_socktype = SOCK_DGRAM
+ };
+
+ if (help_flag) {
+ cmd_bearer_enable_udp_help(cmdl);
+ /* TODO find a better error code? */
+ return -EINVAL;
+ }
+
+ if (!(opt = get_opt(opts, "name"))) {
+ fprintf(stderr, "error, udp bearer name missing\n");
+ cmd_bearer_enable_udp_help(cmdl);
+ return -EINVAL;
+ }
+ snprintf(name, sizeof(name), "udp:%s", opt->val);
+
+ if (!(opt = get_opt(opts, "localip"))) {
+ fprintf(stderr, "error, udp bearer localip missing\n");
+ cmd_bearer_enable_udp_help(cmdl);
+ return -EINVAL;
+ }
+ locip = opt->val;
+
+ if ((opt = get_opt(opts, "remoteip")))
+ remip = opt->val;
+
+ if ((opt = get_opt(opts, "localport")))
+ locport = opt->val;
+
+ if ((opt = get_opt(opts, "remoteport")))
+ remport = opt->val;
+
+ if ((err = getaddrinfo(locip, locport, &hints, &loc))) {
+ fprintf(stderr, "UDP local address error: %s\n",
+ gai_strerror(err));
+ return err;
+ }
+
+ if (!remip) {
+ if (generate_multicast(loc->ai_family, buf, sizeof(buf))) {
+ fprintf(stderr, "Failed to generate multicast address\n");
+ return -EINVAL;
+ }
+ remip = buf;
+ }
+
+ if ((err = getaddrinfo(remip, remport, &hints, &rem))) {
+ fprintf(stderr, "UDP remote address error: %s\n",
+ gai_strerror(err));
+ freeaddrinfo(loc);
+ return err;
+ }
+
+ if (rem->ai_family != loc->ai_family) {
+ fprintf(stderr, "UDP local and remote AF mismatch\n");
+ return -EINVAL;
+ }
+
+ mnl_attr_put_strz(nlh, TIPC_NLA_BEARER_NAME, name);
+
+ nest = mnl_attr_nest_start(nlh, TIPC_NLA_BEARER_UDP_OPTS);
+ mnl_attr_put(nlh, TIPC_NLA_UDP_LOCAL, loc->ai_addrlen, loc->ai_addr);
+ mnl_attr_put(nlh, TIPC_NLA_UDP_REMOTE, rem->ai_addrlen, rem->ai_addr);
+ mnl_attr_nest_end(nlh, nest);
+
+ freeaddrinfo(rem);
+ freeaddrinfo(loc);
+
+ return 0;
+}
+
+static void cmd_bearer_enable_help(struct cmdl *cmdl)
+{
+ fprintf(stderr,
+ "Usage: %s bearer enable [OPTIONS] media MEDIA ARGS...\n\n"
+ "OPTIONS\n"
+ " domain DOMAIN - Discovery domain\n"
+ " priority PRIORITY - Bearer priority\n",
+ cmdl->argv[0]);
+ _print_bearer_media();
+}
+
+static int cmd_bearer_enable(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ int err;
+ struct opt *opt;
+ struct nlattr *nest;
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+ char *media;
+ struct opt opts[] = {
+ { "device", NULL },
+ { "domain", NULL },
+ { "localip", NULL },
+ { "localport", NULL },
+ { "media", NULL },
+ { "name", NULL },
+ { "priority", NULL },
+ { "remoteip", NULL },
+ { "remoteport", NULL },
+ { NULL }
+ };
+
+ if (parse_opts(opts, cmdl) < 0) {
+ if (help_flag)
+ (cmd->help)(cmdl);
+ return -EINVAL;
+ }
+
+ if (!(opt = get_opt(opts, "media"))) {
+ if (help_flag)
+ (cmd->help)(cmdl);
+ else
+ fprintf(stderr, "error, missing bearer media\n");
+ return -EINVAL;
+ }
+ media = opt->val;
+
+ if (!(nlh = msg_init(buf, TIPC_NL_BEARER_ENABLE))) {
+ fprintf(stderr, "error: message initialisation failed\n");
+ return -1;
+ }
+ nest = mnl_attr_nest_start(nlh, TIPC_NLA_BEARER);
+
+ if ((opt = get_opt(opts, "domain")))
+ mnl_attr_put_u32(nlh, TIPC_NLA_BEARER_DOMAIN, atoi(opt->val));
+
+ if ((opt = get_opt(opts, "priority"))) {
+ struct nlattr *props;
+
+ props = mnl_attr_nest_start(nlh, TIPC_NLA_BEARER_PROP);
+ mnl_attr_put_u32(nlh, TIPC_NLA_PROP_PRIO, atoi(opt->val));
+ mnl_attr_nest_end(nlh, props);
+ }
+
+ if (strcmp(media, "udp") == 0) {
+ if (help_flag) {
+ cmd_bearer_enable_udp_help(cmdl);
+ return -EINVAL;
+ }
+ if ((err = enable_udp_bearer(nlh, opts, cmdl)))
+ return err;
+ } else if ((strcmp(media, "eth") == 0) || (strcmp(media, "udp") == 0)) {
+ if (help_flag) {
+ cmd_bearer_enable_l2_help(cmdl);
+ return -EINVAL;
+ }
+ if ((err = enable_l2_bearer(nlh, opts, cmdl)))
+ return err;
+ } else {
+ fprintf(stderr, "error, invalid media type \"%s\"\n", media);
+ return -EINVAL;
+ }
+
+ mnl_attr_nest_end(nlh, nest);
+
+ return msg_doit(nlh, NULL, NULL);
+}
+
+static int add_l2_bearer(struct nlmsghdr *nlh, struct opt *opts)
+{
+ struct opt *opt;
+ char id[TIPC_MAX_BEARER_NAME];
+
+ if (!(opt = get_opt(opts, "device"))) {
+ fprintf(stderr, "error: missing bearer device\n");
+ return -EINVAL;
+ }
+ snprintf(id, sizeof(id), "eth:%s", opt->val);
+
+ mnl_attr_put_strz(nlh, TIPC_NLA_BEARER_NAME, id);
+
+ return 0;
+}
+
+static int add_udp_bearer(struct nlmsghdr *nlh, struct opt *opts)
+{
+ struct opt *opt;
+ char id[TIPC_MAX_BEARER_NAME];
+
+ if (!(opt = get_opt(opts, "name"))) {
+ fprintf(stderr, "error: missing bearer name\n");
+ return -EINVAL;
+ }
+ snprintf(id, sizeof(id), "udp:%s", opt->val);
+
+ mnl_attr_put_strz(nlh, TIPC_NLA_BEARER_NAME, id);
+
+ return 0;
+}
+
+static void cmd_bearer_disable_l2_help(struct cmdl *cmdl)
+{
+ fprintf(stderr, "Usage: %s bearer disable media udp device DEVICE\n",
+ cmdl->argv[0]);
+}
+
+static void cmd_bearer_disable_udp_help(struct cmdl *cmdl)
+{
+ fprintf(stderr, "Usage: %s bearer disable media udp name NAME\n",
+ cmdl->argv[0]);
+}
+
+static void cmd_bearer_disable_help(struct cmdl *cmdl)
+{
+ fprintf(stderr, "Usage: %s bearer disable media MEDIA ARGS...\n",
+ cmdl->argv[0]);
+ _print_bearer_media();
+}
+
+static int cmd_bearer_disable(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ int err;
+ char *media;
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+ struct nlattr *nest;
+ struct opt *opt;
+ struct opt opts[] = {
+ { "device", NULL },
+ { "name", NULL },
+ { "media", NULL },
+ { NULL }
+ };
+
+ if (parse_opts(opts, cmdl) < 0) {
+ if (help_flag)
+ (cmd->help)(cmdl);
+ return -EINVAL;
+ }
+
+ if (!(opt = get_opt(opts, "media"))) {
+ if (help_flag)
+ (cmd->help)(cmdl);
+ else
+ fprintf(stderr, "error, missing bearer media\n");
+ return -EINVAL;
+ }
+ media = opt->val;
+
+ if (!(nlh = msg_init(buf, TIPC_NL_BEARER_DISABLE))) {
+ fprintf(stderr, "error, message initialisation failed\n");
+ return -1;
+ }
+
+ nest = mnl_attr_nest_start(nlh, TIPC_NLA_BEARER);
+
+ if (strcmp(media, "udp") == 0) {
+ if (help_flag) {
+ cmd_bearer_disable_udp_help(cmdl);
+ return -EINVAL;
+ }
+ if ((err = add_udp_bearer(nlh, opts)))
+ return err;
+ } else if ((strcmp(media, "eth") == 0) || (strcmp(media, "udp") == 0)) {
+ if (help_flag) {
+ cmd_bearer_disable_l2_help(cmdl);
+ return -EINVAL;
+ }
+ if ((err = add_l2_bearer(nlh, opts)))
+ return err;
+ } else {
+ fprintf(stderr, "error, invalid media type \"%s\"\n", media);
+ return -EINVAL;
+ }
+ mnl_attr_nest_end(nlh, nest);
+
+ return msg_doit(nlh, NULL, NULL);
+
+}
+
+static void cmd_bearer_set_help(struct cmdl *cmdl)
+{
+ fprintf(stderr, "Usage: %s bearer set OPTION media MEDIA ARGS...\n",
+ cmdl->argv[0]);
+ _print_bearer_opts();
+ _print_bearer_media();
+}
+
+static void cmd_bearer_set_udp_help(struct cmdl *cmdl)
+{
+ fprintf(stderr, "Usage: %s bearer set OPTION media udp name NAME\n\n",
+ cmdl->argv[0]);
+ _print_bearer_opts();
+}
+
+static void cmd_bearer_set_l2_help(struct cmdl *cmdl, char *media)
+{
+ fprintf(stderr,
+ "Usage: %s bearer set [OPTION]... media %s device DEVICE\n",
+ cmdl->argv[0], media);
+ _print_bearer_opts();
+}
+
+static int cmd_bearer_set_prop(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ int err;
+ int val;
+ int prop;
+ char *media;
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+ struct nlattr *props;
+ struct nlattr *attrs;
+ struct opt *opt;
+ struct opt opts[] = {
+ { "device", NULL },
+ { "media", NULL },
+ { "name", NULL },
+ { NULL }
+ };
+
+ if (strcmp(cmd->cmd, "priority") == 0)
+ prop = TIPC_NLA_PROP_PRIO;
+ else if ((strcmp(cmd->cmd, "tolerance") == 0))
+ prop = TIPC_NLA_PROP_TOL;
+ else if ((strcmp(cmd->cmd, "window") == 0))
+ prop = TIPC_NLA_PROP_WIN;
+ else
+ return -EINVAL;
+
+ if (help_flag) {
+ (cmd->help)(cmdl);
+ return -EINVAL;
+ }
+
+ if (cmdl->optind >= cmdl->argc) {
+ fprintf(stderr, "error, missing value\n");
+ return -EINVAL;
+ }
+ val = atoi(shift_cmdl(cmdl));
+
+ if (parse_opts(opts, cmdl) < 0)
+ return -EINVAL;
+
+ if (!(nlh = msg_init(buf, TIPC_NL_BEARER_SET))) {
+ fprintf(stderr, "error, message initialisation failed\n");
+ return -1;
+ }
+ attrs = mnl_attr_nest_start(nlh, TIPC_NLA_BEARER);
+
+ props = mnl_attr_nest_start(nlh, TIPC_NLA_BEARER_PROP);
+ mnl_attr_put_u32(nlh, prop, val);
+ mnl_attr_nest_end(nlh, props);
+
+ if (!(opt = get_opt(opts, "media"))) {
+ fprintf(stderr, "error, missing media\n");
+ return -EINVAL;
+ }
+ media = opt->val;
+
+ if (strcmp(media, "udp") == 0) {
+ if (help_flag) {
+ cmd_bearer_set_udp_help(cmdl);
+ return -EINVAL;
+ }
+ if ((err = add_udp_bearer(nlh, opts)))
+ return err;
+ } else if ((strcmp(media, "eth") == 0) || (strcmp(media, "udp") == 0)) {
+ if (help_flag) {
+ cmd_bearer_set_l2_help(cmdl, media);
+ return -EINVAL;
+ }
+ if ((err = add_l2_bearer(nlh, opts)))
+ return err;
+ } else {
+ fprintf(stderr, "error, invalid media type \"%s\"\n", media);
+ return -EINVAL;
+ }
+ mnl_attr_nest_end(nlh, attrs);
+
+ return msg_doit(nlh, NULL, NULL);
+}
+
+static int cmd_bearer_set(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ const struct cmd cmds[] = {
+ { "priority", cmd_bearer_set_prop, cmd_bearer_set_help },
+ { "tolerance", cmd_bearer_set_prop, cmd_bearer_set_help },
+ { "window", cmd_bearer_set_prop, cmd_bearer_set_help },
+ { NULL }
+ };
+
+ return run_cmd(nlh, cmd, cmds, cmdl, NULL);
+}
+
+static void cmd_bearer_get_help(struct cmdl *cmdl)
+{
+ fprintf(stderr, "Usage: %s bearer get OPTION media MEDIA ARGS...\n",
+ cmdl->argv[0]);
+ _print_bearer_opts();
+ _print_bearer_media();
+}
+
+static void cmd_bearer_get_udp_help(struct cmdl *cmdl)
+{
+ fprintf(stderr, "Usage: %s bearer get OPTION media udp name NAME\n\n",
+ cmdl->argv[0]);
+ _print_bearer_opts();
+}
+
+static void cmd_bearer_get_l2_help(struct cmdl *cmdl, char *media)
+{
+ fprintf(stderr,
+ "Usage: %s bearer get [OPTION]... media %s device DEVICE\n",
+ cmdl->argv[0], media);
+ _print_bearer_opts();
+}
+
+static int bearer_get_cb(const struct nlmsghdr *nlh, void *data)
+{
+ int *prop = data;
+ struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+ struct nlattr *info[TIPC_NLA_MAX + 1] = {};
+ struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1] = {};
+ struct nlattr *props[TIPC_NLA_PROP_MAX + 1] = {};
+
+ mnl_attr_parse(nlh, sizeof(*genl), parse_attrs, info);
+ if (!info[TIPC_NLA_BEARER])
+ return MNL_CB_ERROR;
+
+ mnl_attr_parse_nested(info[TIPC_NLA_BEARER], parse_attrs, attrs);
+ if (!attrs[TIPC_NLA_BEARER_PROP])
+ return MNL_CB_ERROR;
+
+ mnl_attr_parse_nested(attrs[TIPC_NLA_BEARER_PROP], parse_attrs, props);
+ if (!props[*prop])
+ return MNL_CB_ERROR;
+
+ printf("%u\n", mnl_attr_get_u32(props[*prop]));
+
+ return MNL_CB_OK;
+}
+
+static int cmd_bearer_get_prop(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ int err;
+ int prop;
+ char *media;
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+ struct nlattr *attrs;
+ struct opt *opt;
+ struct opt opts[] = {
+ { "device", NULL },
+ { "media", NULL },
+ { "name", NULL },
+ { NULL }
+ };
+
+ if (strcmp(cmd->cmd, "priority") == 0)
+ prop = TIPC_NLA_PROP_PRIO;
+ else if ((strcmp(cmd->cmd, "tolerance") == 0))
+ prop = TIPC_NLA_PROP_TOL;
+ else if ((strcmp(cmd->cmd, "window") == 0))
+ prop = TIPC_NLA_PROP_WIN;
+ else
+ return -EINVAL;
+
+ if (help_flag) {
+ (cmd->help)(cmdl);
+ return -EINVAL;
+ }
+
+ if (parse_opts(opts, cmdl) < 0)
+ return -EINVAL;
+
+ if (!(nlh = msg_init(buf, TIPC_NL_BEARER_GET))) {
+ fprintf(stderr, "error, message initialisation failed\n");
+ return -1;
+ }
+
+ if (!(opt = get_opt(opts, "media"))) {
+ fprintf(stderr, "error, missing media\n");
+ return -EINVAL;
+ }
+ media = opt->val;
+
+ attrs = mnl_attr_nest_start(nlh, TIPC_NLA_BEARER);
+ if (strcmp(media, "udp") == 0) {
+ if (help_flag) {
+ cmd_bearer_get_udp_help(cmdl);
+ return -EINVAL;
+ }
+ if ((err = add_udp_bearer(nlh, opts)))
+ return err;
+ } else if ((strcmp(media, "eth") == 0) || (strcmp(media, "udp") == 0)) {
+ if (help_flag) {
+ cmd_bearer_get_l2_help(cmdl, media);
+ return -EINVAL;
+ }
+ if ((err = add_l2_bearer(nlh, opts)))
+ return err;
+ } else {
+ fprintf(stderr, "error, invalid media type \"%s\"\n", media);
+ return -EINVAL;
+ }
+ mnl_attr_nest_end(nlh, attrs);
+
+ return msg_doit(nlh, bearer_get_cb, &prop);
+}
+
+static int cmd_bearer_get(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ const struct cmd cmds[] = {
+ { "priority", cmd_bearer_get_prop, cmd_bearer_get_help },
+ { "tolerance", cmd_bearer_get_prop, cmd_bearer_get_help },
+ { "window", cmd_bearer_get_prop, cmd_bearer_get_help },
+ { NULL }
+ };
+
+ return run_cmd(nlh, cmd, cmds, cmdl, NULL);
+}
+
+static int bearer_list_cb(const struct nlmsghdr *nlh, void *data)
+{
+ struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+ struct nlattr *info[TIPC_NLA_MAX + 1] = {};
+ struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1] = {};
+
+ mnl_attr_parse(nlh, sizeof(*genl), parse_attrs, info);
+ if (!info[TIPC_NLA_BEARER]) {
+ fprintf(stderr, "No bearer in netlink response\n");
+ return MNL_CB_ERROR;
+ }
+
+ mnl_attr_parse_nested(info[TIPC_NLA_BEARER], parse_attrs, attrs);
+ if (!attrs[TIPC_NLA_BEARER_NAME]) {
+ fprintf(stderr, "Bearer name missing in netlink response\n");
+ return MNL_CB_ERROR;
+ }
+
+ printf("%s\n", mnl_attr_get_str(attrs[TIPC_NLA_BEARER_NAME]));
+
+ return MNL_CB_OK;
+}
+
+static int cmd_bearer_list(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+
+ if (help_flag) {
+ fprintf(stderr, "Usage: %s bearer list\n", cmdl->argv[0]);
+ return -EINVAL;
+ }
+
+ if (!(nlh = msg_init(buf, TIPC_NL_BEARER_GET))) {
+ fprintf(stderr, "error, message initialisation failed\n");
+ return -1;
+ }
+
+ return msg_dumpit(nlh, bearer_list_cb, NULL);
+}
+
+void cmd_bearer_help(struct cmdl *cmdl)
+{
+ fprintf(stderr,
+ "Usage: %s bearer COMMAND [ARGS] ...\n"
+ "\n"
+ "COMMANDS\n"
+ " enable - Enable a bearer\n"
+ " disable - Disable a bearer\n"
+ " set - Set various bearer properties\n"
+ " get - Get various bearer properties\n"
+ " list - List bearers\n", cmdl->argv[0]);
+}
+
+int cmd_bearer(struct nlmsghdr *nlh, const struct cmd *cmd, struct cmdl *cmdl,
+ void *data)
+{
+ const struct cmd cmds[] = {
+ { "disable", cmd_bearer_disable, cmd_bearer_disable_help },
+ { "enable", cmd_bearer_enable, cmd_bearer_enable_help },
+ { "get", cmd_bearer_get, cmd_bearer_get_help },
+ { "list", cmd_bearer_list, NULL },
+ { "set", cmd_bearer_set, cmd_bearer_set_help },
+ { NULL }
+ };
+
+ return run_cmd(nlh, cmd, cmds, cmdl, NULL);
+}
diff --git a/iproute2/tipc/bearer.h b/iproute2/tipc/bearer.h
new file mode 100644
index 0000000..9459d65
--- /dev/null
+++ b/iproute2/tipc/bearer.h
@@ -0,0 +1,22 @@
+/*
+ * bearer.h TIPC bearer functionality.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Richard Alpe <richard.alpe@ericsson.com>
+ */
+
+#ifndef _TIPC_BEARER_H
+#define _TIPC_BEARER_H
+
+#include "cmdl.h"
+
+extern int help_flag;
+
+int cmd_bearer(struct nlmsghdr *nlh, const struct cmd *cmd, struct cmdl *cmdl, void *data);
+void cmd_bearer_help(struct cmdl *cmdl);
+
+#endif
diff --git a/iproute2/tipc/cmdl.c b/iproute2/tipc/cmdl.c
new file mode 100644
index 0000000..b816f7d
--- /dev/null
+++ b/iproute2/tipc/cmdl.c
@@ -0,0 +1,127 @@
+/*
+ * cmdl.c Framework for handling command line options.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Richard Alpe <richard.alpe@ericsson.com>
+ */
+
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+
+#include <libmnl/libmnl.h>
+
+#include "cmdl.h"
+
+const struct cmd *find_cmd(const struct cmd *cmds, char *str)
+{
+ const struct cmd *c;
+ const struct cmd *match = NULL;
+
+ for (c = cmds; c->cmd; c++) {
+ if (strstr(c->cmd, str) != c->cmd)
+ continue;
+ if (match)
+ return NULL;
+ match = c;
+ }
+
+ return match;
+}
+
+static struct opt *find_opt(struct opt *opts, char *str)
+{
+ struct opt *o;
+ struct opt *match = NULL;
+
+ for (o = opts; o->key; o++) {
+ if (strstr(o->key, str) != o->key)
+ continue;
+ if (match)
+ return NULL;
+
+ match = o;
+ }
+
+ return match;
+}
+
+struct opt *get_opt(struct opt *opts, char *key)
+{
+ struct opt *o;
+
+ for (o = opts; o->key; o++) {
+ if (strcmp(o->key, key) == 0 && o->val)
+ return o;
+ }
+
+ return NULL;
+}
+
+char *shift_cmdl(struct cmdl *cmdl)
+{
+ int next;
+
+ if (cmdl->optind < cmdl->argc)
+ next = (cmdl->optind)++;
+ else
+ next = cmdl->argc;
+
+ return cmdl->argv[next];
+}
+
+/* Returns the number of options parsed or a negative error code upon failure */
+int parse_opts(struct opt *opts, struct cmdl *cmdl)
+{
+ int i;
+ int cnt = 0;
+
+ for (i = cmdl->optind; i < cmdl->argc; i += 2) {
+ struct opt *o;
+
+ o = find_opt(opts, cmdl->argv[i]);
+ if (!o) {
+ fprintf(stderr, "error, invalid option \"%s\"\n",
+ cmdl->argv[i]);
+ return -EINVAL;
+ }
+ cnt++;
+ o->val = cmdl->argv[i + 1];
+ cmdl->optind += 2;
+ }
+
+ return cnt;
+}
+
+int run_cmd(struct nlmsghdr *nlh, const struct cmd *caller,
+ const struct cmd *cmds, struct cmdl *cmdl, void *data)
+{
+ char *name;
+ const struct cmd *cmd;
+
+ if ((cmdl->optind) >= cmdl->argc) {
+ if (caller->help)
+ (caller->help)(cmdl);
+ return -EINVAL;
+ }
+ name = cmdl->argv[cmdl->optind];
+ (cmdl->optind)++;
+
+ cmd = find_cmd(cmds, name);
+ if (!cmd) {
+ /* Show help about last command if we don't find this one */
+ if (help_flag && caller->help) {
+ (caller->help)(cmdl);
+ } else {
+ fprintf(stderr, "error, invalid command \"%s\"\n", name);
+ fprintf(stderr, "use --help for command help\n");
+ }
+ return -EINVAL;
+ }
+
+ return (cmd->func)(nlh, cmd, cmdl, data);
+}
diff --git a/iproute2/tipc/cmdl.h b/iproute2/tipc/cmdl.h
new file mode 100644
index 0000000..9f2666f
--- /dev/null
+++ b/iproute2/tipc/cmdl.h
@@ -0,0 +1,46 @@
+/*
+ * cmdl.h Framework for handling command line options.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Richard Alpe <richard.alpe@ericsson.com>
+ */
+
+#ifndef _TIPC_CMDL_H
+#define _TIPC_CMDL_H
+
+#include <libmnl/libmnl.h>
+
+extern int help_flag;
+
+struct cmdl {
+ int optind;
+ int argc;
+ char **argv;
+};
+
+struct cmd {
+ const char *cmd;
+ int (*func)(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data);
+ void (*help)(struct cmdl *cmdl);
+};
+
+struct opt {
+ const char *key;
+ char *val;
+};
+
+struct opt *get_opt(struct opt *opts, char *key);
+int parse_opts(struct opt *opts, struct cmdl *cmdl);
+char *shift_cmdl(struct cmdl *cmdl);
+
+int run_cmd(struct nlmsghdr *nlh, const struct cmd *caller,
+ const struct cmd *cmds, struct cmdl *cmdl, void *data);
+
+const struct cmd *find_cmd(const struct cmd *cmds, char *str);
+
+#endif
diff --git a/iproute2/tipc/link.c b/iproute2/tipc/link.c
new file mode 100644
index 0000000..89fb4ff
--- /dev/null
+++ b/iproute2/tipc/link.c
@@ -0,0 +1,520 @@
+/*
+ * link.c TIPC link functionality.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Richard Alpe <richard.alpe@ericsson.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+
+#include <linux/tipc_netlink.h>
+#include <linux/tipc.h>
+#include <linux/genetlink.h>
+#include <libmnl/libmnl.h>
+
+#include "cmdl.h"
+#include "msg.h"
+#include "link.h"
+
+static int link_list_cb(const struct nlmsghdr *nlh, void *data)
+{
+ struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+ struct nlattr *info[TIPC_NLA_MAX + 1] = {};
+ struct nlattr *attrs[TIPC_NLA_LINK_MAX + 1] = {};
+
+ mnl_attr_parse(nlh, sizeof(*genl), parse_attrs, info);
+ if (!info[TIPC_NLA_LINK])
+ return MNL_CB_ERROR;
+
+ mnl_attr_parse_nested(info[TIPC_NLA_LINK], parse_attrs, attrs);
+ if (!attrs[TIPC_NLA_LINK_NAME])
+ return MNL_CB_ERROR;
+
+ printf("%s: ", mnl_attr_get_str(attrs[TIPC_NLA_LINK_NAME]));
+
+ if (attrs[TIPC_NLA_LINK_UP])
+ printf("up\n");
+ else
+ printf("down\n");
+
+ return MNL_CB_OK;
+}
+
+static int cmd_link_list(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+
+ if (help_flag) {
+ fprintf(stderr, "Usage: %s link list\n", cmdl->argv[0]);
+ return -EINVAL;
+ }
+
+ if (!(nlh = msg_init(buf, TIPC_NL_LINK_GET))) {
+ fprintf(stderr, "error, message initialisation failed\n");
+ return -1;
+ }
+
+ return msg_dumpit(nlh, link_list_cb, NULL);
+}
+
+static int link_get_cb(const struct nlmsghdr *nlh, void *data)
+{
+ int *prop = data;
+ struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+ struct nlattr *info[TIPC_NLA_MAX + 1] = {};
+ struct nlattr *attrs[TIPC_NLA_LINK_MAX + 1] = {};
+ struct nlattr *props[TIPC_NLA_PROP_MAX + 1] = {};
+
+ mnl_attr_parse(nlh, sizeof(*genl), parse_attrs, info);
+ if (!info[TIPC_NLA_LINK])
+ return MNL_CB_ERROR;
+
+ mnl_attr_parse_nested(info[TIPC_NLA_LINK], parse_attrs, attrs);
+ if (!attrs[TIPC_NLA_LINK_PROP])
+ return MNL_CB_ERROR;
+
+ mnl_attr_parse_nested(attrs[TIPC_NLA_LINK_PROP], parse_attrs, props);
+ if (!props[*prop])
+ return MNL_CB_ERROR;
+
+ printf("%u\n", mnl_attr_get_u32(props[*prop]));
+
+ return MNL_CB_OK;
+}
+
+
+static int cmd_link_get_prop(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ int prop;
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+ struct opt *opt;
+ struct opt opts[] = {
+ { "link", NULL },
+ { NULL }
+ };
+
+ if (strcmp(cmd->cmd, "priority") == 0)
+ prop = TIPC_NLA_PROP_PRIO;
+ else if ((strcmp(cmd->cmd, "tolerance") == 0))
+ prop = TIPC_NLA_PROP_TOL;
+ else if ((strcmp(cmd->cmd, "window") == 0))
+ prop = TIPC_NLA_PROP_WIN;
+ else
+ return -EINVAL;
+
+ if (help_flag) {
+ (cmd->help)(cmdl);
+ return -EINVAL;
+ }
+
+ if (parse_opts(opts, cmdl) < 0)
+ return -EINVAL;
+
+ if (!(nlh = msg_init(buf, TIPC_NL_LINK_GET))) {
+ fprintf(stderr, "error, message initialisation failed\n");
+ return -1;
+ }
+
+ if (!(opt = get_opt(opts, "link"))) {
+ fprintf(stderr, "error, missing link\n");
+ return -EINVAL;
+ }
+ mnl_attr_put_strz(nlh, TIPC_NLA_LINK_NAME, opt->val);
+
+ return msg_doit(nlh, link_get_cb, &prop);
+}
+
+static void cmd_link_get_help(struct cmdl *cmdl)
+{
+ fprintf(stderr, "Usage: %s link get PPROPERTY link LINK\n\n"
+ "PROPERTIES\n"
+ " tolerance - Get link tolerance\n"
+ " priority - Get link priority\n"
+ " window - Get link window\n",
+ cmdl->argv[0]);
+}
+
+static int cmd_link_get(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ const struct cmd cmds[] = {
+ { "priority", cmd_link_get_prop, cmd_link_get_help },
+ { "tolerance", cmd_link_get_prop, cmd_link_get_help },
+ { "window", cmd_link_get_prop, cmd_link_get_help },
+ { NULL }
+ };
+
+ return run_cmd(nlh, cmd, cmds, cmdl, NULL);
+}
+
+static void cmd_link_stat_reset_help(struct cmdl *cmdl)
+{
+ fprintf(stderr, "Usage: %s link stat reset link LINK\n\n", cmdl->argv[0]);
+}
+
+static int cmd_link_stat_reset(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ char *link;
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+ struct opt *opt;
+ struct nlattr *nest;
+ struct opt opts[] = {
+ { "link", NULL },
+ { NULL }
+ };
+
+ if (help_flag) {
+ (cmd->help)(cmdl);
+ return -EINVAL;
+ }
+
+ if (parse_opts(opts, cmdl) != 1) {
+ (cmd->help)(cmdl);
+ return -EINVAL;
+ }
+
+ if (!(nlh = msg_init(buf, TIPC_NL_LINK_RESET_STATS))) {
+ fprintf(stderr, "error, message initialisation failed\n");
+ return -1;
+ }
+
+ if (!(opt = get_opt(opts, "link"))) {
+ fprintf(stderr, "error, missing link\n");
+ return -EINVAL;
+ }
+ link = opt->val;
+
+ nest = mnl_attr_nest_start(nlh, TIPC_NLA_LINK);
+ mnl_attr_put_strz(nlh, TIPC_NLA_LINK_NAME, link);
+ mnl_attr_nest_end(nlh, nest);
+
+ return msg_doit(nlh, NULL, NULL);
+}
+
+static uint32_t perc(uint32_t count, uint32_t total)
+{
+ return (count * 100 + (total / 2)) / total;
+}
+
+static int _show_link_stat(struct nlattr *attrs[], struct nlattr *prop[],
+ struct nlattr *stats[])
+{
+ uint32_t proft;
+
+ if (attrs[TIPC_NLA_LINK_ACTIVE])
+ printf(" ACTIVE");
+ else if (attrs[TIPC_NLA_LINK_UP])
+ printf(" STANDBY");
+ else
+ printf(" DEFUNCT");
+
+ printf(" MTU:%u Priority:%u Tolerance:%u ms Window:%u packets\n",
+ mnl_attr_get_u32(attrs[TIPC_NLA_LINK_MTU]),
+ mnl_attr_get_u32(prop[TIPC_NLA_PROP_PRIO]),
+ mnl_attr_get_u32(prop[TIPC_NLA_PROP_TOL]),
+ mnl_attr_get_u32(prop[TIPC_NLA_PROP_WIN]));
+
+ printf(" RX packets:%u fragments:%u/%u bundles:%u/%u\n",
+ mnl_attr_get_u32(attrs[TIPC_NLA_LINK_RX]) -
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_RX_INFO]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_RX_FRAGMENTS]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_RX_FRAGMENTED]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_RX_BUNDLES]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_RX_BUNDLED]));
+
+ printf(" TX packets:%u fragments:%u/%u bundles:%u/%u\n",
+ mnl_attr_get_u32(attrs[TIPC_NLA_LINK_TX]) -
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_TX_INFO]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_TX_FRAGMENTS]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_TX_FRAGMENTED]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_TX_BUNDLES]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_TX_BUNDLED]));
+
+ proft = mnl_attr_get_u32(stats[TIPC_NLA_STATS_MSG_PROF_TOT]);
+ printf(" TX profile sample:%u packets average:%u octets\n",
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_CNT]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_TOT]) / proft);
+
+ printf(" 0-64:%u%% -256:%u%% -1024:%u%% -4096:%u%% "
+ "-16384:%u%% -32768:%u%% -66000:%u%%\n",
+ perc(mnl_attr_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_P0]), proft),
+ perc(mnl_attr_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_P1]), proft),
+ perc(mnl_attr_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_P2]), proft),
+ perc(mnl_attr_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_P3]), proft),
+ perc(mnl_attr_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_P4]), proft),
+ perc(mnl_attr_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_P5]), proft),
+ perc(mnl_attr_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_P6]), proft));
+
+ printf(" RX states:%u probes:%u naks:%u defs:%u dups:%u\n",
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_RX_STATES]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_RX_PROBES]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_RX_NACKS]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_RX_DEFERRED]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_DUPLICATES]));
+
+ printf(" TX states:%u probes:%u naks:%u acks:%u dups:%u\n",
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_TX_STATES]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_TX_PROBES]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_TX_NACKS]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_TX_ACKS]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_RETRANSMITTED]));
+
+ printf(" Congestion link:%u Send queue max:%u avg:%u\n",
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_LINK_CONGS]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_MAX_QUEUE]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_AVG_QUEUE]));
+
+ return MNL_CB_OK;
+}
+
+static int _show_bc_link_stat(struct nlattr *prop[], struct nlattr *stats[])
+{
+ printf(" Window:%u packets\n",
+ mnl_attr_get_u32(prop[TIPC_NLA_PROP_WIN]));
+
+ printf(" RX packets:%u fragments:%u/%u bundles:%u/%u\n",
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_RX_INFO]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_RX_FRAGMENTS]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_RX_FRAGMENTED]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_RX_BUNDLES]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_RX_BUNDLED]));
+
+ printf(" TX packets:%u fragments:%u/%u bundles:%u/%u\n",
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_TX_INFO]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_TX_FRAGMENTS]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_TX_FRAGMENTED]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_TX_BUNDLES]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_TX_BUNDLED]));
+
+ printf(" RX naks:%u defs:%u dups:%u\n",
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_RX_NACKS]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_RX_DEFERRED]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_DUPLICATES]));
+
+ printf(" TX naks:%u acks:%u dups:%u\n",
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_TX_NACKS]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_TX_ACKS]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_RETRANSMITTED]));
+
+ printf(" Congestion link:%u Send queue max:%u avg:%u\n",
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_LINK_CONGS]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_MAX_QUEUE]),
+ mnl_attr_get_u32(stats[TIPC_NLA_STATS_AVG_QUEUE]));
+
+ return MNL_CB_OK;
+}
+
+static int link_stat_show_cb(const struct nlmsghdr *nlh, void *data)
+{
+ const char *name;
+ const char *link = data;
+ struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+ struct nlattr *info[TIPC_NLA_MAX + 1] = {};
+ struct nlattr *attrs[TIPC_NLA_LINK_MAX + 1] = {};
+ struct nlattr *prop[TIPC_NLA_PROP_MAX + 1] = {};
+ struct nlattr *stats[TIPC_NLA_STATS_MAX + 1] = {};
+
+ mnl_attr_parse(nlh, sizeof(*genl), parse_attrs, info);
+ if (!info[TIPC_NLA_LINK])
+ return MNL_CB_ERROR;
+
+ mnl_attr_parse_nested(info[TIPC_NLA_LINK], parse_attrs, attrs);
+ if (!attrs[TIPC_NLA_LINK_NAME] || !attrs[TIPC_NLA_LINK_PROP] ||
+ !attrs[TIPC_NLA_LINK_STATS])
+ return MNL_CB_ERROR;
+
+ mnl_attr_parse_nested(attrs[TIPC_NLA_LINK_PROP], parse_attrs, prop);
+ mnl_attr_parse_nested(attrs[TIPC_NLA_LINK_STATS], parse_attrs, stats);
+
+ name = mnl_attr_get_str(attrs[TIPC_NLA_LINK_NAME]);
+
+ /* If a link is passed, skip all but that link */
+ if (link && (strcmp(name, link) != 0))
+ return MNL_CB_OK;
+
+ if (attrs[TIPC_NLA_LINK_BROADCAST]) {
+ printf("Link <%s>\n", name);
+ return _show_bc_link_stat(prop, stats);
+ }
+
+ printf("\nLink <%s>\n", name);
+
+ return _show_link_stat(attrs, prop, stats);
+}
+
+static void cmd_link_stat_show_help(struct cmdl *cmdl)
+{
+ fprintf(stderr, "Usage: %s link stat show [ link LINK ]\n",
+ cmdl->argv[0]);
+}
+
+static int cmd_link_stat_show(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ char *link = NULL;
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+ struct opt *opt;
+ struct opt opts[] = {
+ { "link", NULL },
+ { NULL }
+ };
+
+ if (help_flag) {
+ (cmd->help)(cmdl);
+ return -EINVAL;
+ }
+
+ if (!(nlh = msg_init(buf, TIPC_NL_LINK_GET))) {
+ fprintf(stderr, "error, message initialisation failed\n");
+ return -1;
+ }
+
+ if (parse_opts(opts, cmdl) < 0)
+ return -EINVAL;
+
+ if ((opt = get_opt(opts, "link")))
+ link = opt->val;
+
+ return msg_dumpit(nlh, link_stat_show_cb, link);
+}
+
+static void cmd_link_stat_help(struct cmdl *cmdl)
+{
+ fprintf(stderr, "Usage: %s link stat COMMAND [ARGS]\n\n"
+ "COMMANDS:\n"
+ " reset - Reset link statistics for link\n"
+ " show - Get link priority\n",
+ cmdl->argv[0]);
+}
+
+static int cmd_link_stat(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ const struct cmd cmds[] = {
+ { "reset", cmd_link_stat_reset, cmd_link_stat_reset_help },
+ { "show", cmd_link_stat_show, cmd_link_stat_show_help },
+ { NULL }
+ };
+
+ return run_cmd(nlh, cmd, cmds, cmdl, NULL);
+}
+
+static void cmd_link_set_help(struct cmdl *cmdl)
+{
+ fprintf(stderr, "Usage: %s link set PPROPERTY link LINK\n\n"
+ "PROPERTIES\n"
+ " tolerance TOLERANCE - Set link tolerance\n"
+ " priority PRIORITY - Set link priority\n"
+ " window WINDOW - Set link window\n",
+ cmdl->argv[0]);
+}
+
+static int cmd_link_set_prop(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ int val;
+ int prop;
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+ struct nlattr *props;
+ struct nlattr *attrs;
+ struct opt *opt;
+ struct opt opts[] = {
+ { "link", NULL },
+ { NULL }
+ };
+
+ if (strcmp(cmd->cmd, "priority") == 0)
+ prop = TIPC_NLA_PROP_PRIO;
+ else if ((strcmp(cmd->cmd, "tolerance") == 0))
+ prop = TIPC_NLA_PROP_TOL;
+ else if ((strcmp(cmd->cmd, "window") == 0))
+ prop = TIPC_NLA_PROP_WIN;
+ else
+ return -EINVAL;
+
+ if (help_flag) {
+ (cmd->help)(cmdl);
+ return -EINVAL;
+ }
+
+ if (cmdl->optind >= cmdl->argc) {
+ fprintf(stderr, "error, missing value\n");
+ return -EINVAL;
+ }
+ val = atoi(shift_cmdl(cmdl));
+
+ if (parse_opts(opts, cmdl) < 0)
+ return -EINVAL;
+
+ if (!(nlh = msg_init(buf, TIPC_NL_LINK_SET))) {
+ fprintf(stderr, "error, message initialisation failed\n");
+ return -1;
+ }
+ attrs = mnl_attr_nest_start(nlh, TIPC_NLA_LINK);
+
+ if (!(opt = get_opt(opts, "link"))) {
+ fprintf(stderr, "error, missing link\n");
+ return -EINVAL;
+ }
+ mnl_attr_put_strz(nlh, TIPC_NLA_LINK_NAME, opt->val);
+
+ props = mnl_attr_nest_start(nlh, TIPC_NLA_LINK_PROP);
+ mnl_attr_put_u32(nlh, prop, val);
+ mnl_attr_nest_end(nlh, props);
+
+ mnl_attr_nest_end(nlh, attrs);
+
+ return msg_doit(nlh, link_get_cb, &prop);
+
+ return 0;
+}
+
+static int cmd_link_set(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ const struct cmd cmds[] = {
+ { "priority", cmd_link_set_prop, cmd_link_set_help },
+ { "tolerance", cmd_link_set_prop, cmd_link_set_help },
+ { "window", cmd_link_set_prop, cmd_link_set_help },
+ { NULL }
+ };
+
+ return run_cmd(nlh, cmd, cmds, cmdl, NULL);
+}
+
+void cmd_link_help(struct cmdl *cmdl)
+{
+ fprintf(stderr,
+ "Usage: %s link COMMAND [ARGS] ...\n"
+ "\n"
+ "COMMANDS\n"
+ " list - List links\n"
+ " get - Get various link properties\n"
+ " set - Set various link properties\n"
+ " statistics - Show or reset statistics\n",
+ cmdl->argv[0]);
+}
+
+int cmd_link(struct nlmsghdr *nlh, const struct cmd *cmd, struct cmdl *cmdl,
+ void *data)
+{
+ const struct cmd cmds[] = {
+ { "get", cmd_link_get, cmd_link_get_help },
+ { "list", cmd_link_list, NULL },
+ { "set", cmd_link_set, cmd_link_set_help },
+ { "statistics", cmd_link_stat, cmd_link_stat_help },
+ { NULL }
+ };
+
+ return run_cmd(nlh, cmd, cmds, cmdl, NULL);
+}
diff --git a/iproute2/tipc/link.h b/iproute2/tipc/link.h
new file mode 100644
index 0000000..6dc95e5
--- /dev/null
+++ b/iproute2/tipc/link.h
@@ -0,0 +1,21 @@
+/*
+ * link.c TIPC link functionality.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Richard Alpe <richard.alpe@ericsson.com>
+ */
+
+#ifndef _TIPC_LINK_H
+#define _TIPC_LINK_H
+
+extern int help_flag;
+
+int cmd_link(struct nlmsghdr *nlh, const struct cmd *cmd, struct cmdl *cmdl,
+ void *data);
+void cmd_link_help(struct cmdl *cmdl);
+
+#endif
diff --git a/iproute2/tipc/media.c b/iproute2/tipc/media.c
new file mode 100644
index 0000000..a902ab7
--- /dev/null
+++ b/iproute2/tipc/media.c
@@ -0,0 +1,260 @@
+/*
+ * media.c TIPC link functionality.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Richard Alpe <richard.alpe@ericsson.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+
+#include <linux/tipc_netlink.h>
+#include <linux/tipc.h>
+#include <linux/genetlink.h>
+#include <libmnl/libmnl.h>
+
+#include "cmdl.h"
+#include "msg.h"
+#include "media.h"
+
+static int media_list_cb(const struct nlmsghdr *nlh, void *data)
+{
+ struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+ struct nlattr *info[TIPC_NLA_MAX + 1] = {};
+ struct nlattr *attrs[TIPC_NLA_MEDIA_MAX + 1] = {};
+
+ mnl_attr_parse(nlh, sizeof(*genl), parse_attrs, info);
+ if (!info[TIPC_NLA_MEDIA])
+ return MNL_CB_ERROR;
+
+ mnl_attr_parse_nested(info[TIPC_NLA_MEDIA], parse_attrs, attrs);
+ if (!attrs[TIPC_NLA_MEDIA_NAME])
+ return MNL_CB_ERROR;
+
+ printf("%s\n", mnl_attr_get_str(attrs[TIPC_NLA_MEDIA_NAME]));
+
+ return MNL_CB_OK;
+}
+
+static int cmd_media_list(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+
+ if (help_flag) {
+ fprintf(stderr, "Usage: %s media list\n", cmdl->argv[0]);
+ return -EINVAL;
+ }
+
+ if (!(nlh = msg_init(buf, TIPC_NL_MEDIA_GET))) {
+ fprintf(stderr, "error, message initialisation failed\n");
+ return -1;
+ }
+
+ return msg_dumpit(nlh, media_list_cb, NULL);
+}
+
+static int media_get_cb(const struct nlmsghdr *nlh, void *data)
+{
+ int *prop = data;
+ struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+ struct nlattr *info[TIPC_NLA_MAX + 1] = {};
+ struct nlattr *attrs[TIPC_NLA_MEDIA_MAX + 1] = {};
+ struct nlattr *props[TIPC_NLA_PROP_MAX + 1] = {};
+
+ mnl_attr_parse(nlh, sizeof(*genl), parse_attrs, info);
+ if (!info[TIPC_NLA_MEDIA])
+ return MNL_CB_ERROR;
+
+ mnl_attr_parse_nested(info[TIPC_NLA_MEDIA], parse_attrs, attrs);
+ if (!attrs[TIPC_NLA_MEDIA_PROP])
+ return MNL_CB_ERROR;
+
+ mnl_attr_parse_nested(attrs[TIPC_NLA_MEDIA_PROP], parse_attrs, props);
+ if (!props[*prop])
+ return MNL_CB_ERROR;
+
+ printf("%u\n", mnl_attr_get_u32(props[*prop]));
+
+ return MNL_CB_OK;
+}
+
+static int cmd_media_get_prop(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ int prop;
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+ struct nlattr *nest;
+ struct opt *opt;
+ struct opt opts[] = {
+ { "media", NULL },
+ { NULL }
+ };
+
+ if (strcmp(cmd->cmd, "priority") == 0)
+ prop = TIPC_NLA_PROP_PRIO;
+ else if ((strcmp(cmd->cmd, "tolerance") == 0))
+ prop = TIPC_NLA_PROP_TOL;
+ else if ((strcmp(cmd->cmd, "window") == 0))
+ prop = TIPC_NLA_PROP_WIN;
+ else
+ return -EINVAL;
+
+ if (help_flag) {
+ (cmd->help)(cmdl);
+ return -EINVAL;
+ }
+
+ if (parse_opts(opts, cmdl) < 0)
+ return -EINVAL;
+
+ if (!(nlh = msg_init(buf, TIPC_NL_MEDIA_GET))) {
+ fprintf(stderr, "error, message initialisation failed\n");
+ return -1;
+ }
+
+ if (!(opt = get_opt(opts, "media"))) {
+ fprintf(stderr, "error, missing media\n");
+ return -EINVAL;
+ }
+ nest = mnl_attr_nest_start(nlh, TIPC_NLA_MEDIA);
+ mnl_attr_put_strz(nlh, TIPC_NLA_MEDIA_NAME, opt->val);
+ mnl_attr_nest_end(nlh, nest);
+
+ return msg_doit(nlh, media_get_cb, &prop);
+}
+
+static void cmd_media_get_help(struct cmdl *cmdl)
+{
+ fprintf(stderr, "Usage: %s media get PPROPERTY media MEDIA\n\n"
+ "PROPERTIES\n"
+ " tolerance - Get media tolerance\n"
+ " priority - Get media priority\n"
+ " window - Get media window\n",
+ cmdl->argv[0]);
+}
+
+static int cmd_media_get(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ const struct cmd cmds[] = {
+ { "priority", cmd_media_get_prop, cmd_media_get_help },
+ { "tolerance", cmd_media_get_prop, cmd_media_get_help },
+ { "window", cmd_media_get_prop, cmd_media_get_help },
+ { NULL }
+ };
+
+ return run_cmd(nlh, cmd, cmds, cmdl, NULL);
+}
+
+static void cmd_media_set_help(struct cmdl *cmdl)
+{
+ fprintf(stderr, "Usage: %s media set PPROPERTY media MEDIA\n\n"
+ "PROPERTIES\n"
+ " tolerance TOLERANCE - Set media tolerance\n"
+ " priority PRIORITY - Set media priority\n"
+ " window WINDOW - Set media window\n",
+ cmdl->argv[0]);
+}
+
+static int cmd_media_set_prop(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ int val;
+ int prop;
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+ struct nlattr *props;
+ struct nlattr *attrs;
+ struct opt *opt;
+ struct opt opts[] = {
+ { "media", NULL },
+ { NULL }
+ };
+
+ if (strcmp(cmd->cmd, "priority") == 0)
+ prop = TIPC_NLA_PROP_PRIO;
+ else if ((strcmp(cmd->cmd, "tolerance") == 0))
+ prop = TIPC_NLA_PROP_TOL;
+ else if ((strcmp(cmd->cmd, "window") == 0))
+ prop = TIPC_NLA_PROP_WIN;
+ else
+ return -EINVAL;
+
+ if (help_flag) {
+ (cmd->help)(cmdl);
+ return -EINVAL;
+ }
+
+ if (cmdl->optind >= cmdl->argc) {
+ fprintf(stderr, "error, missing value\n");
+ return -EINVAL;
+ }
+ val = atoi(shift_cmdl(cmdl));
+
+ if (parse_opts(opts, cmdl) < 0)
+ return -EINVAL;
+
+ if (!(nlh = msg_init(buf, TIPC_NL_MEDIA_SET))) {
+ fprintf(stderr, "error, message initialisation failed\n");
+ return -1;
+ }
+ attrs = mnl_attr_nest_start(nlh, TIPC_NLA_MEDIA);
+
+ if (!(opt = get_opt(opts, "media"))) {
+ fprintf(stderr, "error, missing media\n");
+ return -EINVAL;
+ }
+ mnl_attr_put_strz(nlh, TIPC_NLA_MEDIA_NAME, opt->val);
+
+ props = mnl_attr_nest_start(nlh, TIPC_NLA_MEDIA_PROP);
+ mnl_attr_put_u32(nlh, prop, val);
+ mnl_attr_nest_end(nlh, props);
+
+ mnl_attr_nest_end(nlh, attrs);
+
+ return msg_doit(nlh, NULL, NULL);
+}
+
+static int cmd_media_set(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ const struct cmd cmds[] = {
+ { "priority", cmd_media_set_prop, cmd_media_set_help },
+ { "tolerance", cmd_media_set_prop, cmd_media_set_help },
+ { "window", cmd_media_set_prop, cmd_media_set_help },
+ { NULL }
+ };
+
+ return run_cmd(nlh, cmd, cmds, cmdl, NULL);
+}
+
+void cmd_media_help(struct cmdl *cmdl)
+{
+ fprintf(stderr,
+ "Usage: %s media COMMAND [ARGS] ...\n"
+ "\n"
+ "Commands:\n"
+ " list - List active media types\n"
+ " get - Get various media properties\n"
+ " set - Set various media properties\n",
+ cmdl->argv[0]);
+}
+
+int cmd_media(struct nlmsghdr *nlh, const struct cmd *cmd, struct cmdl *cmdl,
+ void *data)
+{
+ const struct cmd cmds[] = {
+ { "get", cmd_media_get, cmd_media_get_help },
+ { "list", cmd_media_list, NULL },
+ { "set", cmd_media_set, cmd_media_set_help },
+ { NULL }
+ };
+
+ return run_cmd(nlh, cmd, cmds, cmdl, NULL);
+}
diff --git a/iproute2/tipc/media.h b/iproute2/tipc/media.h
new file mode 100644
index 0000000..8584af7
--- /dev/null
+++ b/iproute2/tipc/media.h
@@ -0,0 +1,21 @@
+/*
+ * media.h TIPC link functionality.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Richard Alpe <richard.alpe@ericsson.com>
+ */
+
+#ifndef _TIPC_MEDIA_H
+#define _TIPC_MEDIA_H
+
+extern int help_flag;
+
+int cmd_media(struct nlmsghdr *nlh, const struct cmd *cmd, struct cmdl *cmdl,
+ void *data);
+void cmd_media_help(struct cmdl *cmdl);
+
+#endif
diff --git a/iproute2/tipc/misc.c b/iproute2/tipc/misc.c
new file mode 100644
index 0000000..8091222
--- /dev/null
+++ b/iproute2/tipc/misc.c
@@ -0,0 +1,35 @@
+/*
+ * misc.c Miscellaneous TIPC helper functions.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Richard Alpe <richard.alpe@ericsson.com>
+ */
+
+#include <stdio.h>
+#include <stdint.h>
+#include <linux/tipc.h>
+
+#include "misc.h"
+
+#define IN_RANGE(val, low, high) ((val) <= (high) && (val) >= (low))
+
+uint32_t str2addr(char *str)
+{
+ unsigned int z, c, n;
+ char dummy;
+
+ if (sscanf(str, "%u.%u.%u%c", &z, &c, &n, &dummy) != 3) {
+ fprintf(stderr, "invalid network address, syntax: Z.C.N\n");
+ return 0;
+ }
+
+ if (IN_RANGE(z, 0, 255) && IN_RANGE(c, 0, 4095) && IN_RANGE(n, 0, 4095))
+ return tipc_addr(z, c, n);
+
+ fprintf(stderr, "invalid network address \"%s\"\n", str);
+ return 0;
+}
diff --git a/iproute2/tipc/misc.h b/iproute2/tipc/misc.h
new file mode 100644
index 0000000..585df74
--- /dev/null
+++ b/iproute2/tipc/misc.h
@@ -0,0 +1,19 @@
+/*
+ * misc.h Miscellaneous TIPC helper functions.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Richard Alpe <richard.alpe@ericsson.com>
+ */
+
+#ifndef _TIPC_MISC_H
+#define _TIPC_MISC_H
+
+#include <stdint.h>
+
+uint32_t str2addr(char *str);
+
+#endif
diff --git a/iproute2/tipc/msg.c b/iproute2/tipc/msg.c
new file mode 100644
index 0000000..22c2222
--- /dev/null
+++ b/iproute2/tipc/msg.c
@@ -0,0 +1,170 @@
+/*
+ * msg.c Messaging (netlink) helper functions.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Richard Alpe <richard.alpe@ericsson.com>
+ */
+
+#include <stdio.h>
+#include <time.h>
+#include <errno.h>
+
+#include <linux/tipc_netlink.h>
+#include <linux/tipc.h>
+#include <linux/genetlink.h>
+#include <libmnl/libmnl.h>
+
+#include "msg.h"
+
+int parse_attrs(const struct nlattr *attr, void *data)
+{
+ const struct nlattr **tb = data;
+ int type = mnl_attr_get_type(attr);
+
+ tb[type] = attr;
+
+ return MNL_CB_OK;
+}
+
+static int family_id_cb(const struct nlmsghdr *nlh, void *data)
+{
+ struct nlattr *tb[CTRL_ATTR_MAX + 1] = {};
+ struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+ int *id = data;
+
+ mnl_attr_parse(nlh, sizeof(*genl), parse_attrs, tb);
+ if (!tb[CTRL_ATTR_FAMILY_ID])
+ return MNL_CB_ERROR;
+
+ *id = mnl_attr_get_u16(tb[CTRL_ATTR_FAMILY_ID]);
+
+ return MNL_CB_OK;
+}
+
+static struct mnl_socket *msg_send(struct nlmsghdr *nlh)
+{
+ int ret;
+ struct mnl_socket *nl;
+
+ nl = mnl_socket_open(NETLINK_GENERIC);
+ if (nl == NULL) {
+ perror("mnl_socket_open");
+ return NULL;
+ }
+
+ ret = mnl_socket_bind(nl, 0, MNL_SOCKET_AUTOPID);
+ if (ret < 0) {
+ perror("mnl_socket_bind");
+ return NULL;
+ }
+
+ ret = mnl_socket_sendto(nl, nlh, nlh->nlmsg_len);
+ if (ret < 0) {
+ perror("mnl_socket_send");
+ return NULL;
+ }
+
+ return nl;
+}
+
+static int msg_recv(struct mnl_socket *nl, mnl_cb_t callback, void *data, int seq)
+{
+ int ret;
+ unsigned int portid;
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+
+ portid = mnl_socket_get_portid(nl);
+
+ ret = mnl_socket_recvfrom(nl, buf, sizeof(buf));
+ while (ret > 0) {
+ ret = mnl_cb_run(buf, ret, seq, portid, callback, data);
+ if (ret <= 0)
+ break;
+ ret = mnl_socket_recvfrom(nl, buf, sizeof(buf));
+ }
+ if (ret == -1)
+ perror("error");
+
+ mnl_socket_close(nl);
+
+ return ret;
+}
+
+static int msg_query(struct nlmsghdr *nlh, mnl_cb_t callback, void *data)
+{
+ unsigned int seq;
+ struct mnl_socket *nl;
+
+ seq = time(NULL);
+ nlh->nlmsg_seq = seq;
+
+ nl = msg_send(nlh);
+ if (!nl)
+ return -ENOTSUP;
+
+ return msg_recv(nl, callback, data, seq);
+}
+
+static int get_family(void)
+{
+ int err;
+ int nl_family;
+ struct nlmsghdr *nlh;
+ struct genlmsghdr *genl;
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+
+ nlh = mnl_nlmsg_put_header(buf);
+ nlh->nlmsg_type = GENL_ID_CTRL;
+ nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+
+ genl = mnl_nlmsg_put_extra_header(nlh, sizeof(struct genlmsghdr));
+ genl->cmd = CTRL_CMD_GETFAMILY;
+ genl->version = 1;
+
+ mnl_attr_put_u32(nlh, CTRL_ATTR_FAMILY_ID, GENL_ID_CTRL);
+ mnl_attr_put_strz(nlh, CTRL_ATTR_FAMILY_NAME, TIPC_GENL_V2_NAME);
+
+ if ((err = msg_query(nlh, family_id_cb, &nl_family)))
+ return err;
+
+ return nl_family;
+}
+
+int msg_doit(struct nlmsghdr *nlh, mnl_cb_t callback, void *data)
+{
+ nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+ return msg_query(nlh, callback, data);
+}
+
+int msg_dumpit(struct nlmsghdr *nlh, mnl_cb_t callback, void *data)
+{
+ nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP;
+ return msg_query(nlh, callback, data);
+}
+
+struct nlmsghdr *msg_init(char *buf, int cmd)
+{
+ int family;
+ struct nlmsghdr *nlh;
+ struct genlmsghdr *genl;
+
+ family = get_family();
+ if (family <= 0) {
+ fprintf(stderr,
+ "Unable to get TIPC nl family id (module loaded?)\n");
+ return NULL;
+ }
+
+ nlh = mnl_nlmsg_put_header(buf);
+ nlh->nlmsg_type = family;
+
+ genl = mnl_nlmsg_put_extra_header(nlh, sizeof(struct genlmsghdr));
+ genl->cmd = cmd;
+ genl->version = 1;
+
+ return nlh;
+}
diff --git a/iproute2/tipc/msg.h b/iproute2/tipc/msg.h
new file mode 100644
index 0000000..41fd1ad
--- /dev/null
+++ b/iproute2/tipc/msg.h
@@ -0,0 +1,20 @@
+/*
+ * msg.h Messaging (netlink) helper functions.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Richard Alpe <richard.alpe@ericsson.com>
+ */
+
+#ifndef _TIPC_MSG_H
+#define _TIPC_MSG_H
+
+struct nlmsghdr *msg_init(char *buf, int cmd);
+int msg_doit(struct nlmsghdr *nlh, mnl_cb_t callback, void *data);
+int msg_dumpit(struct nlmsghdr *nlh, mnl_cb_t callback, void *data);
+int parse_attrs(const struct nlattr *attr, void *data);
+
+#endif
diff --git a/iproute2/tipc/nametable.c b/iproute2/tipc/nametable.c
new file mode 100644
index 0000000..770a644
--- /dev/null
+++ b/iproute2/tipc/nametable.c
@@ -0,0 +1,109 @@
+/*
+ * nametable.c TIPC nametable functionality.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Richard Alpe <richard.alpe@ericsson.com>
+ */
+
+#include <stdio.h>
+#include <errno.h>
+
+#include <linux/tipc_netlink.h>
+#include <linux/tipc.h>
+#include <linux/genetlink.h>
+#include <libmnl/libmnl.h>
+
+#include "cmdl.h"
+#include "msg.h"
+#include "nametable.h"
+
+#define PORTID_STR_LEN 45 /* Four u32 and five delimiter chars */
+
+static int nametable_show_cb(const struct nlmsghdr *nlh, void *data)
+{
+ int *iteration = data;
+ char port_id[PORTID_STR_LEN];
+ struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+ struct nlattr *info[TIPC_NLA_MAX + 1] = {};
+ struct nlattr *attrs[TIPC_NLA_NAME_TABLE_MAX + 1] = {};
+ struct nlattr *publ[TIPC_NLA_PUBL_MAX + 1] = {};
+ const char *scope[] = { "", "zone", "cluster", "node" };
+
+ mnl_attr_parse(nlh, sizeof(*genl), parse_attrs, info);
+ if (!info[TIPC_NLA_NAME_TABLE])
+ return MNL_CB_ERROR;
+
+ mnl_attr_parse_nested(info[TIPC_NLA_NAME_TABLE], parse_attrs, attrs);
+ if (!attrs[TIPC_NLA_NAME_TABLE_PUBL])
+ return MNL_CB_ERROR;
+
+ mnl_attr_parse_nested(attrs[TIPC_NLA_NAME_TABLE_PUBL], parse_attrs, publ);
+ if (!publ[TIPC_NLA_NAME_TABLE_PUBL])
+ return MNL_CB_ERROR;
+
+ if (!*iteration)
+ printf("%-10s %-10s %-10s %-26s %-10s\n",
+ "Type", "Lower", "Upper", "Port Identity",
+ "Publication Scope");
+ (*iteration)++;
+
+ snprintf(port_id, sizeof(port_id), "<%u.%u.%u:%u>",
+ tipc_zone(mnl_attr_get_u32(publ[TIPC_NLA_PUBL_NODE])),
+ tipc_cluster(mnl_attr_get_u32(publ[TIPC_NLA_PUBL_NODE])),
+ tipc_node(mnl_attr_get_u32(publ[TIPC_NLA_PUBL_NODE])),
+ mnl_attr_get_u32(publ[TIPC_NLA_PUBL_REF]));
+
+ printf("%-10u %-10u %-10u %-26s %-12u",
+ mnl_attr_get_u32(publ[TIPC_NLA_PUBL_TYPE]),
+ mnl_attr_get_u32(publ[TIPC_NLA_PUBL_LOWER]),
+ mnl_attr_get_u32(publ[TIPC_NLA_PUBL_UPPER]),
+ port_id,
+ mnl_attr_get_u32(publ[TIPC_NLA_PUBL_KEY]));
+
+ printf("%s\n", scope[mnl_attr_get_u32(publ[TIPC_NLA_PUBL_SCOPE])]);
+
+ return MNL_CB_OK;
+}
+
+static int cmd_nametable_show(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ int iteration = 0;
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+
+ if (help_flag) {
+ fprintf(stderr, "Usage: %s nametable show\n", cmdl->argv[0]);
+ return -EINVAL;
+ }
+
+ if (!(nlh = msg_init(buf, TIPC_NL_NAME_TABLE_GET))) {
+ fprintf(stderr, "error, message initialisation failed\n");
+ return -1;
+ }
+
+ return msg_dumpit(nlh, nametable_show_cb, &iteration);
+}
+
+void cmd_nametable_help(struct cmdl *cmdl)
+{
+ fprintf(stderr,
+ "Usage: %s nametable COMMAND\n\n"
+ "COMMANDS\n"
+ " show - Show nametable\n",
+ cmdl->argv[0]);
+}
+
+int cmd_nametable(struct nlmsghdr *nlh, const struct cmd *cmd, struct cmdl *cmdl,
+ void *data)
+{
+ const struct cmd cmds[] = {
+ { "show", cmd_nametable_show, NULL },
+ { NULL }
+ };
+
+ return run_cmd(nlh, cmd, cmds, cmdl, NULL);
+}
diff --git a/iproute2/tipc/nametable.h b/iproute2/tipc/nametable.h
new file mode 100644
index 0000000..e0473e1
--- /dev/null
+++ b/iproute2/tipc/nametable.h
@@ -0,0 +1,21 @@
+/*
+ * nametable.h TIPC nametable functionality.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Richard Alpe <richard.alpe@ericsson.com>
+ */
+
+#ifndef _TIPC_NAMETABLE_H
+#define _TIPC_NAMETABLE_H
+
+extern int help_flag;
+
+void cmd_nametable_help(struct cmdl *cmdl);
+int cmd_nametable(struct nlmsghdr *nlh, const struct cmd *cmd, struct cmdl *cmdl,
+ void *data);
+
+#endif
diff --git a/iproute2/tipc/node.c b/iproute2/tipc/node.c
new file mode 100644
index 0000000..201fe1a
--- /dev/null
+++ b/iproute2/tipc/node.c
@@ -0,0 +1,267 @@
+/*
+ * node.c TIPC node functionality.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Richard Alpe <richard.alpe@ericsson.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+
+#include <linux/tipc_netlink.h>
+#include <linux/tipc.h>
+#include <linux/genetlink.h>
+#include <libmnl/libmnl.h>
+
+#include "cmdl.h"
+#include "msg.h"
+#include "misc.h"
+#include "node.h"
+
+static int node_list_cb(const struct nlmsghdr *nlh, void *data)
+{
+ uint32_t addr;
+ struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+ struct nlattr *info[TIPC_NLA_MAX + 1] = {};
+ struct nlattr *attrs[TIPC_NLA_NODE_MAX + 1] = {};
+
+ mnl_attr_parse(nlh, sizeof(*genl), parse_attrs, info);
+ if (!info[TIPC_NLA_NODE])
+ return MNL_CB_ERROR;
+
+ mnl_attr_parse_nested(info[TIPC_NLA_NODE], parse_attrs, attrs);
+ if (!attrs[TIPC_NLA_NODE_ADDR])
+ return MNL_CB_ERROR;
+
+ addr = mnl_attr_get_u32(attrs[TIPC_NLA_NODE_ADDR]);
+ printf("<%u.%u.%u>: ",
+ tipc_zone(addr),
+ tipc_cluster(addr),
+ tipc_node(addr));
+
+ if (attrs[TIPC_NLA_NODE_UP])
+ printf("up\n");
+ else
+ printf("down\n");
+
+ return MNL_CB_OK;
+}
+
+static int cmd_node_list(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+
+ if (help_flag) {
+ fprintf(stderr, "Usage: %s node list\n", cmdl->argv[0]);
+ return -EINVAL;
+ }
+
+ if (!(nlh = msg_init(buf, TIPC_NL_NODE_GET))) {
+ fprintf(stderr, "error, message initialisation failed\n");
+ return -1;
+ }
+
+ return msg_dumpit(nlh, node_list_cb, NULL);
+}
+
+static int cmd_node_set_addr(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ char *str;
+ uint32_t addr;
+ struct nlattr *nest;
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+
+ if (cmdl->argc != cmdl->optind + 1) {
+ fprintf(stderr, "Usage: %s node set address ADDRESS\n",
+ cmdl->argv[0]);
+ return -EINVAL;
+ }
+
+ str = shift_cmdl(cmdl);
+ addr = str2addr(str);
+ if (!addr)
+ return -1;
+
+ if (!(nlh = msg_init(buf, TIPC_NL_NET_SET))) {
+ fprintf(stderr, "error, message initialisation failed\n");
+ return -1;
+ }
+
+ nest = mnl_attr_nest_start(nlh, TIPC_NLA_NET);
+ mnl_attr_put_u32(nlh, TIPC_NLA_NET_ADDR, addr);
+ mnl_attr_nest_end(nlh, nest);
+
+ return msg_doit(nlh, NULL, NULL);
+}
+
+static int cmd_node_get_addr(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ int sk;
+ socklen_t sz = sizeof(struct sockaddr_tipc);
+ struct sockaddr_tipc addr;
+
+ if (!(sk = socket(AF_TIPC, SOCK_RDM, 0))) {
+ fprintf(stderr, "opening TIPC socket: %s\n", strerror(errno));
+ return -1;
+ }
+
+ if (getsockname(sk, (struct sockaddr *)&addr, &sz) < 0) {
+ fprintf(stderr, "getting TIPC socket address: %s\n",
+ strerror(errno));
+ close(sk);
+ return -1;
+ }
+ close(sk);
+
+ printf("<%u.%u.%u>\n",
+ tipc_zone(addr.addr.id.node),
+ tipc_cluster(addr.addr.id.node),
+ tipc_node(addr.addr.id.node));
+
+ return 0;
+}
+
+static int netid_get_cb(const struct nlmsghdr *nlh, void *data)
+{
+ struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+ struct nlattr *info[TIPC_NLA_MAX + 1] = {};
+ struct nlattr *attrs[TIPC_NLA_NET_MAX + 1] = {};
+
+ mnl_attr_parse(nlh, sizeof(*genl), parse_attrs, info);
+ if (!info[TIPC_NLA_NET])
+ return MNL_CB_ERROR;
+
+ mnl_attr_parse_nested(info[TIPC_NLA_NET], parse_attrs, attrs);
+ if (!attrs[TIPC_NLA_NET_ID])
+ return MNL_CB_ERROR;
+
+ printf("%u\n", mnl_attr_get_u32(attrs[TIPC_NLA_NET_ID]));
+
+ return MNL_CB_OK;
+}
+
+static int cmd_node_get_netid(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+
+ if (help_flag) {
+ (cmd->help)(cmdl);
+ return -EINVAL;
+ }
+
+ if (!(nlh = msg_init(buf, TIPC_NL_NET_GET))) {
+ fprintf(stderr, "error, message initialisation failed\n");
+ return -1;
+ }
+
+ return msg_dumpit(nlh, netid_get_cb, NULL);
+}
+
+static int cmd_node_set_netid(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ int netid;
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+ struct nlattr *nest;
+
+ if (help_flag) {
+ (cmd->help)(cmdl);
+ return -EINVAL;
+ }
+
+ if (!(nlh = msg_init(buf, TIPC_NL_NET_SET))) {
+ fprintf(stderr, "error, message initialisation failed\n");
+ return -1;
+ }
+
+ if (cmdl->argc != cmdl->optind + 1) {
+ fprintf(stderr, "Usage: %s node set netid NETID\n",
+ cmdl->argv[0]);
+ return -EINVAL;
+ }
+ netid = atoi(shift_cmdl(cmdl));
+
+ nest = mnl_attr_nest_start(nlh, TIPC_NLA_NET);
+ mnl_attr_put_u32(nlh, TIPC_NLA_NET_ID, netid);
+ mnl_attr_nest_end(nlh, nest);
+
+ return msg_doit(nlh, NULL, NULL);
+}
+
+static void cmd_node_set_help(struct cmdl *cmdl)
+{
+ fprintf(stderr,
+ "Usage: %s node set PROPERTY\n\n"
+ "PROPERTIES\n"
+ " address ADDRESS - Set local address\n"
+ " netid NETID - Set local netid\n",
+ cmdl->argv[0]);
+}
+
+static int cmd_node_set(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ const struct cmd cmds[] = {
+ { "address", cmd_node_set_addr, NULL },
+ { "netid", cmd_node_set_netid, NULL },
+ { NULL }
+ };
+
+ return run_cmd(nlh, cmd, cmds, cmdl, NULL);
+}
+
+static void cmd_node_get_help(struct cmdl *cmdl)
+{
+ fprintf(stderr,
+ "Usage: %s node get PROPERTY\n\n"
+ "PROPERTIES\n"
+ " address - Get local address\n"
+ " netid - Get local netid\n",
+ cmdl->argv[0]);
+}
+
+static int cmd_node_get(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ const struct cmd cmds[] = {
+ { "address", cmd_node_get_addr, NULL },
+ { "netid", cmd_node_get_netid, NULL },
+ { NULL }
+ };
+
+ return run_cmd(nlh, cmd, cmds, cmdl, NULL);
+}
+
+void cmd_node_help(struct cmdl *cmdl)
+{
+ fprintf(stderr,
+ "Usage: %s node COMMAND [ARGS] ...\n\n"
+ "COMMANDS\n"
+ " list - List remote nodes\n"
+ " get - Get local node parameters\n"
+ " set - Set local node parameters\n",
+ cmdl->argv[0]);
+}
+
+int cmd_node(struct nlmsghdr *nlh, const struct cmd *cmd, struct cmdl *cmdl,
+ void *data)
+{
+ const struct cmd cmds[] = {
+ { "list", cmd_node_list, NULL },
+ { "get", cmd_node_get, cmd_node_get_help },
+ { "set", cmd_node_set, cmd_node_set_help },
+ { NULL }
+ };
+
+ return run_cmd(nlh, cmd, cmds, cmdl, NULL);
+}
diff --git a/iproute2/tipc/node.h b/iproute2/tipc/node.h
new file mode 100644
index 0000000..afee1fd
--- /dev/null
+++ b/iproute2/tipc/node.h
@@ -0,0 +1,21 @@
+/*
+ * node.h TIPC node functionality.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Richard Alpe <richard.alpe@ericsson.com>
+ */
+
+#ifndef _TIPC_NODE_H
+#define _TIPC_NODE_H
+
+extern int help_flag;
+
+int cmd_node(struct nlmsghdr *nlh, const struct cmd *cmd, struct cmdl *cmdl,
+ void *data);
+void cmd_node_help(struct cmdl *cmdl);
+
+#endif
diff --git a/iproute2/tipc/peer.c b/iproute2/tipc/peer.c
new file mode 100644
index 0000000..de0c73c
--- /dev/null
+++ b/iproute2/tipc/peer.c
@@ -0,0 +1,93 @@
+/*
+ * peer.c TIPC peer functionality.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Richard Alpe <richard.alpe@ericsson.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+
+#include <linux/tipc_netlink.h>
+#include <linux/tipc.h>
+#include <linux/genetlink.h>
+#include <libmnl/libmnl.h>
+
+#include "cmdl.h"
+#include "msg.h"
+#include "misc.h"
+#include "peer.h"
+
+static int cmd_peer_rm_addr(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ char *str;
+ uint32_t addr;
+ struct nlattr *nest;
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+
+ if ((cmdl->argc != cmdl->optind + 1) || help_flag) {
+ fprintf(stderr, "Usage: %s peer remove address ADDRESS\n",
+ cmdl->argv[0]);
+ return -EINVAL;
+ }
+
+ str = shift_cmdl(cmdl);
+ addr = str2addr(str);
+ if (!addr)
+ return -1;
+
+ if (!(nlh = msg_init(buf, TIPC_NL_PEER_REMOVE))) {
+ fprintf(stderr, "error, message initialisation failed\n");
+ return -1;
+ }
+
+ nest = mnl_attr_nest_start(nlh, TIPC_NLA_NET);
+ mnl_attr_put_u32(nlh, TIPC_NLA_NET_ADDR, addr);
+ mnl_attr_nest_end(nlh, nest);
+
+ return msg_doit(nlh, NULL, NULL);
+}
+
+static void cmd_peer_rm_help(struct cmdl *cmdl)
+{
+ fprintf(stderr, "Usage: %s peer remove address ADDRESS\n",
+ cmdl->argv[0]);
+}
+
+static int cmd_peer_rm(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ const struct cmd cmds[] = {
+ { "address", cmd_peer_rm_addr, cmd_peer_rm_help },
+ { NULL }
+ };
+
+ return run_cmd(nlh, cmd, cmds, cmdl, NULL);
+}
+
+void cmd_peer_help(struct cmdl *cmdl)
+{
+ fprintf(stderr,
+ "Usage: %s peer COMMAND [ARGS] ...\n\n"
+ "COMMANDS\n"
+ " remove - Remove an offline peer node\n",
+ cmdl->argv[0]);
+}
+
+int cmd_peer(struct nlmsghdr *nlh, const struct cmd *cmd, struct cmdl *cmdl,
+ void *data)
+{
+ const struct cmd cmds[] = {
+ { "remove", cmd_peer_rm, cmd_peer_rm_help },
+ { NULL }
+ };
+
+ return run_cmd(nlh, cmd, cmds, cmdl, NULL);
+}
diff --git a/iproute2/tipc/peer.h b/iproute2/tipc/peer.h
new file mode 100644
index 0000000..8972261
--- /dev/null
+++ b/iproute2/tipc/peer.h
@@ -0,0 +1,21 @@
+/*
+ * peer.h TIPC peer functionality.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Richard Alpe <richard.alpe@ericsson.com>
+ */
+
+#ifndef _TIPC_PEER_H
+#define _TIPC_PEER_H
+
+extern int help_flag;
+
+int cmd_peer(struct nlmsghdr *nlh, const struct cmd *cmd, struct cmdl *cmdl,
+ void *data);
+void cmd_peer_help(struct cmdl *cmdl);
+
+#endif
diff --git a/iproute2/tipc/socket.c b/iproute2/tipc/socket.c
new file mode 100644
index 0000000..48ba821
--- /dev/null
+++ b/iproute2/tipc/socket.c
@@ -0,0 +1,140 @@
+/*
+ * socket.c TIPC socket functionality.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Richard Alpe <richard.alpe@ericsson.com>
+ */
+
+#include <stdio.h>
+#include <errno.h>
+
+#include <linux/tipc.h>
+#include <linux/tipc_netlink.h>
+#include <linux/genetlink.h>
+#include <libmnl/libmnl.h>
+
+#include "cmdl.h"
+#include "msg.h"
+#include "socket.h"
+
+#define PORTID_STR_LEN 45 /* Four u32 and five delimiter chars */
+
+static int publ_list_cb(const struct nlmsghdr *nlh, void *data)
+{
+ struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+ struct nlattr *info[TIPC_NLA_MAX + 1] = {};
+ struct nlattr *attrs[TIPC_NLA_SOCK_MAX + 1] = {};
+
+ mnl_attr_parse(nlh, sizeof(*genl), parse_attrs, info);
+ if (!info[TIPC_NLA_PUBL])
+ return MNL_CB_ERROR;
+
+ mnl_attr_parse_nested(info[TIPC_NLA_PUBL], parse_attrs, attrs);
+
+ printf(" bound to {%u,%u,%u}\n",
+ mnl_attr_get_u32(attrs[TIPC_NLA_PUBL_TYPE]),
+ mnl_attr_get_u32(attrs[TIPC_NLA_PUBL_LOWER]),
+ mnl_attr_get_u32(attrs[TIPC_NLA_PUBL_UPPER]));
+
+ return MNL_CB_OK;
+}
+
+static int publ_list(uint32_t sock)
+{
+ struct nlmsghdr *nlh;
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+ struct nlattr *nest;
+
+ if (!(nlh = msg_init(buf, TIPC_NL_PUBL_GET))) {
+ fprintf(stderr, "error, message initialisation failed\n");
+ return -1;
+ }
+
+ nest = mnl_attr_nest_start(nlh, TIPC_NLA_SOCK);
+ mnl_attr_put_u32(nlh, TIPC_NLA_SOCK_REF, sock);
+ mnl_attr_nest_end(nlh, nest);
+
+ return msg_dumpit(nlh, publ_list_cb, NULL);
+}
+
+static int sock_list_cb(const struct nlmsghdr *nlh, void *data)
+{
+ struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+ struct nlattr *info[TIPC_NLA_MAX + 1] = {};
+ struct nlattr *attrs[TIPC_NLA_SOCK_MAX + 1] = {};
+
+ mnl_attr_parse(nlh, sizeof(*genl), parse_attrs, info);
+ if (!info[TIPC_NLA_SOCK])
+ return MNL_CB_ERROR;
+
+ mnl_attr_parse_nested(info[TIPC_NLA_SOCK], parse_attrs, attrs);
+ if (!attrs[TIPC_NLA_SOCK_REF])
+ return MNL_CB_ERROR;
+
+ printf("socket %u\n", mnl_attr_get_u32(attrs[TIPC_NLA_SOCK_REF]));
+
+ if (attrs[TIPC_NLA_SOCK_CON]) {
+ uint32_t node;
+ struct nlattr *con[TIPC_NLA_CON_MAX + 1] = {};
+
+ mnl_attr_parse_nested(attrs[TIPC_NLA_SOCK_CON], parse_attrs, con);
+ node = mnl_attr_get_u32(con[TIPC_NLA_CON_NODE]);
+
+ printf(" connected to <%u.%u.%u:%u>", tipc_zone(node),
+ tipc_cluster(node), tipc_node(node),
+ mnl_attr_get_u32(con[TIPC_NLA_CON_SOCK]));
+
+ if (con[TIPC_NLA_CON_FLAG])
+ printf(" via {%u,%u}\n",
+ mnl_attr_get_u32(con[TIPC_NLA_CON_TYPE]),
+ mnl_attr_get_u32(con[TIPC_NLA_CON_INST]));
+ else
+ printf("\n");
+ } else if (attrs[TIPC_NLA_SOCK_HAS_PUBL]) {
+ publ_list(mnl_attr_get_u32(attrs[TIPC_NLA_SOCK_REF]));
+ }
+
+ return MNL_CB_OK;
+}
+
+static int cmd_socket_list(struct nlmsghdr *nlh, const struct cmd *cmd,
+ struct cmdl *cmdl, void *data)
+{
+ char buf[MNL_SOCKET_BUFFER_SIZE];
+
+ if (help_flag) {
+ fprintf(stderr, "Usage: %s socket list\n", cmdl->argv[0]);
+ return -EINVAL;
+ }
+
+ if (!(nlh = msg_init(buf, TIPC_NL_SOCK_GET))) {
+ fprintf(stderr, "error, message initialisation failed\n");
+ return -1;
+ }
+
+ return msg_dumpit(nlh, sock_list_cb, NULL);
+}
+
+void cmd_socket_help(struct cmdl *cmdl)
+{
+ fprintf(stderr,
+ "Usage: %s socket COMMAND\n\n"
+ "Commands:\n"
+ " list - List sockets (ports)\n",
+ cmdl->argv[0]);
+}
+
+int cmd_socket(struct nlmsghdr *nlh, const struct cmd *cmd, struct cmdl *cmdl,
+ void *data)
+{
+ const struct cmd cmds[] = {
+ { "list", cmd_socket_list, NULL },
+ { NULL }
+ };
+
+ return run_cmd(nlh, cmd, cmds, cmdl, NULL);
+}
diff --git a/iproute2/tipc/socket.h b/iproute2/tipc/socket.h
new file mode 100644
index 0000000..9d1b648
--- /dev/null
+++ b/iproute2/tipc/socket.h
@@ -0,0 +1,21 @@
+/*
+ * socket.h TIPC socket functionality.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Richard Alpe <richard.alpe@ericsson.com>
+ */
+
+#ifndef _TIPC_SOCKET_H
+#define _TIPC_SOCKET_H
+
+extern int help_flag;
+
+void cmd_socket_help(struct cmdl *cmdl);
+int cmd_socket(struct nlmsghdr *nlh, const struct cmd *cmd, struct cmdl *cmdl,
+ void *data);
+
+#endif
diff --git a/iproute2/tipc/tipc.c b/iproute2/tipc/tipc.c
new file mode 100644
index 0000000..600d5e2
--- /dev/null
+++ b/iproute2/tipc/tipc.c
@@ -0,0 +1,99 @@
+/*
+ * tipc. TIPC utility frontend.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Richard Alpe <richard.alpe@ericsson.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <getopt.h>
+#include <unistd.h>
+
+#include "bearer.h"
+#include "link.h"
+#include "nametable.h"
+#include "socket.h"
+#include "media.h"
+#include "node.h"
+#include "peer.h"
+#include "cmdl.h"
+
+int help_flag;
+
+static void about(struct cmdl *cmdl)
+{
+ fprintf(stderr,
+ "Transparent Inter-Process Communication Protocol\n"
+ "Usage: %s [OPTIONS] COMMAND [ARGS] ...\n"
+ "\n"
+ "Options:\n"
+ " -h, --help \t\tPrint help for last given command\n"
+ "\n"
+ "Commands:\n"
+ " bearer - Show or modify bearers\n"
+ " link - Show or modify links\n"
+ " media - Show or modify media\n"
+ " nametable - Show nametable\n"
+ " node - Show or modify node related parameters\n"
+ " peer - Peer related operations\n"
+ " socket - Show sockets\n",
+ cmdl->argv[0]);
+}
+
+int main(int argc, char *argv[])
+{
+ int i;
+ int res;
+ struct cmdl cmdl;
+ const struct cmd cmd = {"tipc", NULL, about};
+ struct option long_options[] = {
+ {"help", no_argument, 0, 'h'},
+ {0, 0, 0, 0}
+ };
+ const struct cmd cmds[] = {
+ { "bearer", cmd_bearer, cmd_bearer_help},
+ { "link", cmd_link, cmd_link_help},
+ { "media", cmd_media, cmd_media_help},
+ { "nametable", cmd_nametable, cmd_nametable_help},
+ { "node", cmd_node, cmd_node_help},
+ { "peer", cmd_peer, cmd_peer_help},
+ { "socket", cmd_socket, cmd_socket_help},
+ { NULL }
+ };
+
+ do {
+ int option_index = 0;
+
+ i = getopt_long(argc, argv, "h", long_options, &option_index);
+
+ switch (i) {
+ case 'h':
+ /*
+ * We want the help for the last command, so we flag
+ * here in order to print later.
+ */
+ help_flag = 1;
+ break;
+ case -1:
+ /* End of options */
+ break;
+ default:
+ /* Invalid option, error msg is printed by getopts */
+ return 1;
+ }
+ } while (i != -1);
+
+ cmdl.optind = optind;
+ cmdl.argc = argc;
+ cmdl.argv = argv;
+
+ if ((res = run_cmd(NULL, &cmd, cmds, &cmdl, NULL)) != 0)
+ return 1;
+
+ return 0;
+}
