Commit 86c392f9 authored by Stephen Hemminger's avatar Stephen Hemminger

Merge branch 'master' into net-next

parents c518d3a7 1473bda9
...@@ -263,4 +263,3 @@ int do_ipaddrlabel(int argc, char **argv) ...@@ -263,4 +263,3 @@ int do_ipaddrlabel(int argc, char **argv)
fprintf(stderr, "Command \"%s\" is unknown, try \"ip addrlabel help\".\n", *argv); fprintf(stderr, "Command \"%s\" is unknown, try \"ip addrlabel help\".\n", *argv);
exit(-1); exit(-1);
} }
...@@ -156,4 +156,3 @@ int do_ipfou(int argc, char **argv) ...@@ -156,4 +156,3 @@ int do_ipfou(int argc, char **argv)
fprintf(stderr, "Command \"%s\" is unknown, try \"ip fou help\".\n", *argv); fprintf(stderr, "Command \"%s\" is unknown, try \"ip fou help\".\n", *argv);
exit(-1); exit(-1);
} }
...@@ -113,4 +113,3 @@ struct link_util bond_slave_link_util = { ...@@ -113,4 +113,3 @@ struct link_util bond_slave_link_util = {
.parse_opt = bond_slave_parse_opt, .parse_opt = bond_slave_parse_opt,
.slave = true, .slave = true,
}; };
...@@ -107,4 +107,3 @@ int print_prefix(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg) ...@@ -107,4 +107,3 @@ int print_prefix(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
return 0; return 0;
} }
...@@ -1842,4 +1842,3 @@ int do_iproute(int argc, char **argv) ...@@ -1842,4 +1842,3 @@ int do_iproute(int argc, char **argv)
fprintf(stderr, "Command \"%s\" is unknown, try \"ip route help\".\n", *argv); fprintf(stderr, "Command \"%s\" is unknown, try \"ip route help\".\n", *argv);
exit(-1); exit(-1);
} }
...@@ -508,4 +508,3 @@ int do_tcp_metrics(int argc, char **argv) ...@@ -508,4 +508,3 @@ int do_tcp_metrics(int argc, char **argv)
"try \"ip tcp_metrics help\".\n", *argv); "try \"ip tcp_metrics help\".\n", *argv);
exit(-1); exit(-1);
} }
...@@ -12,7 +12,9 @@ MAN8PAGES = $(TARGETS) ip.8 arpd.8 lnstat.8 routel.8 rtacct.8 rtmon.8 rtpr.8 ss. ...@@ -12,7 +12,9 @@ MAN8PAGES = $(TARGETS) ip.8 arpd.8 lnstat.8 routel.8 rtacct.8 rtmon.8 rtpr.8 ss.
ip-netns.8 ip-ntable.8 ip-rule.8 ip-tunnel.8 ip-xfrm.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 \ 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.8 tipc-bearer.8 tipc-link.8 tipc-media.8 tipc-nametable.8 \
tipc-node.8 tipc-socket.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) all: $(TARGETS)
......
.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)
.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
.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)
.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)
.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)
.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)
.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)
.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/
...@@ -144,6 +144,50 @@ It is important to notice that filters reside ...@@ -144,6 +144,50 @@ It is important to notice that filters reside
.B within .B within
qdiscs - they are not masters of what happens. 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-index (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 .SH CLASSLESS QDISCS
The classless qdiscs are: The classless qdiscs are:
.TP .TP
...@@ -655,15 +699,20 @@ Shows classes as ASCII graph with stats info under each class. ...@@ -655,15 +699,20 @@ Shows classes as ASCII graph with stats info under each class.
.B tc .B tc
was written by Alexey N. Kuznetsov and added in Linux 2.2. was written by Alexey N. Kuznetsov and added in Linux 2.2.
.SH SEE ALSO .SH SEE ALSO
.BR tc-basic (8),
.BR tc-bfifo (8), .BR tc-bfifo (8),
.BR tc-bpf (8), .BR tc-bpf (8),
.BR tc-cbq (8), .BR tc-cbq (8),
.BR tc-cgroup (8),
.BR tc-choke (8), .BR tc-choke (8),
.BR tc-codel (8), .BR tc-codel (8),
.BR tc-drr (8), .BR tc-drr (8),
.BR tc-ematch (8), .BR tc-ematch (8),
.BR tc-flow (8),
.BR tc-flower (8),
.BR tc-fq (8), .BR tc-fq (8),
.BR tc-fq_codel (8), .BR tc-fq_codel (8),
.BR tc-fw (8),
.BR tc-hfsc (7), .BR tc-hfsc (7),
.BR tc-hfsc (8), .BR tc-hfsc (8),
.BR tc-htb (8), .BR tc-htb (8),
...@@ -671,10 +720,13 @@ was written by Alexey N. Kuznetsov and added in Linux 2.2. ...@@ -671,10 +720,13 @@ was written by Alexey N. Kuznetsov and added in Linux 2.2.
.BR tc-pfifo (8), .BR tc-pfifo (8),
.BR tc-pfifo_fast (8), .BR tc-pfifo_fast (8),
.BR tc-red (8), .BR tc-red (8),
.BR tc-route (8),
.BR tc-sfb (8), .BR tc-sfb (8),
.BR tc-sfq (8), .BR tc-sfq (8),
.BR tc-stab (8), .BR tc-stab (8),
.BR tc-tbf (8), .BR tc-tbf (8),
.BR tc-tcindex (8),
.BR tc-u32 (8),
.br .br
.RB "User documentation at " http://lartc.org/ ", but please direct bugreports and patches to: " <netdev@vger.kernel.org> .RB "User documentation at " http://lartc.org/ ", but please direct bugreports and patches to: " <netdev@vger.kernel.org>
......
...@@ -377,4 +377,3 @@ int main(int argc, char **argv) ...@@ -377,4 +377,3 @@ int main(int argc, char **argv)
return 1; return 1;
} }
...@@ -43,5 +43,3 @@ It is available only for alpha and pentiums with correct ...@@ -43,5 +43,3 @@ It is available only for alpha and pentiums with correct
CPU timestamp. It is the fastest way, use it when it is available, CPU timestamp. It is the fastest way, use it when it is available,
but remember: not all pentiums have this facility, and but remember: not all pentiums have this facility, and
a lot of them have clock, broken by APM etc. etc. a lot of them have clock, broken by APM etc. etc.
...@@ -98,4 +98,3 @@ invert: ...@@ -98,4 +98,3 @@ invert:
{ {
ematch_err = strdup(s); ematch_err = strdup(s);
} }
...@@ -28,7 +28,7 @@ static void explain(void) ...@@ -28,7 +28,7 @@ static void explain(void)
fprintf(stderr, " [ action ACTION-SPEC ] [ classid CLASSID ]\n"); fprintf(stderr, " [ action ACTION-SPEC ] [ classid CLASSID ]\n");
fprintf(stderr, "\n"); fprintf(stderr, "\n");
fprintf(stderr, "Where: MATCH-LIST := [ MATCH-LIST ] MATCH\n"); fprintf(stderr, "Where: MATCH-LIST := [ MATCH-LIST ] MATCH\n");
fprintf(stderr, " MATCH := [ indev DEV-NAME | \n"); fprintf(stderr, " MATCH := { indev DEV-NAME | \n");
fprintf(stderr, " dst_mac MAC-ADDR | \n"); fprintf(stderr, " dst_mac MAC-ADDR | \n");
fprintf(stderr, " src_mac MAC-ADDR | \n"); fprintf(stderr, " src_mac MAC-ADDR | \n");
fprintf(stderr, " eth_type [ipv4 | ipv6 | ETH-TYPE ] | \n"); fprintf(stderr, " eth_type [ipv4 | ipv6 | ETH-TYPE ] | \n");
...@@ -36,7 +36,7 @@ static void explain(void) ...@@ -36,7 +36,7 @@ static void explain(void)
fprintf(stderr, " dst_ip [ IPV4-ADDR | IPV6-ADDR ] | \n"); fprintf(stderr, " dst_ip [ IPV4-ADDR | IPV6-ADDR ] | \n");
fprintf(stderr, " src_ip [ IPV4-ADDR | IPV6-ADDR ] | \n"); fprintf(stderr, " src_ip [ IPV4-ADDR | IPV6-ADDR ] | \n");
fprintf(stderr, " dst_port PORT-NUMBER | \n"); fprintf(stderr, " dst_port PORT-NUMBER | \n");
fprintf(stderr, " src_port PORT-NUMBER | \n"); fprintf(stderr, " src_port PORT-NUMBER }\n");
fprintf(stderr, " FILTERID := X:Y:Z\n"); fprintf(stderr, " FILTERID := X:Y:Z\n");
fprintf(stderr, " ACTION-SPEC := ... look at individual actions\n"); fprintf(stderr, " ACTION-SPEC := ... look at individual actions\n");
fprintf(stderr, "\n"); fprintf(stderr, "\n");
......
...@@ -28,7 +28,7 @@ ...@@ -28,7 +28,7 @@
static void explain(void) static void explain(void)
{ {
fprintf(stderr, "Usage: ... route [ from REALM | fromif TAG ] [ to REALM ]\n"); fprintf(stderr, "Usage: ... route [ from REALM | fromif TAG ] [ to REALM ]\n");
fprintf(stderr, " [ flowid CLASSID ] [ action ACTION_SPEC ]]\n"); fprintf(stderr, " [ classid CLASSID ] [ action ACTION_SPEC ]\n");
fprintf(stderr, " ACTION_SPEC := ... look at individual actions\n"); fprintf(stderr, " ACTION_SPEC := ... look at individual actions\n");
fprintf(stderr, " CLASSID := X:Y\n"); fprintf(stderr, " CLASSID := X:Y\n");
fprintf(stderr, "\nNOTE: CLASSID is parsed as hexadecimal input.\n"); fprintf(stderr, "\nNOTE: CLASSID is parsed as hexadecimal input.\n");
......
...@@ -27,7 +27,7 @@ ...@@ -27,7 +27,7 @@
static void explain(void) static void explain(void)
{ {
fprintf(stderr, "Usage: ... rsvp ipproto PROTOCOL session DST[/PORT | GPI ]\n"); fprintf(stderr, "Usage: ... rsvp ipproto PROTOCOL session DST[/PORT | GPI ]\n");
fprintf(stderr, " [ sender SRC[/PORT | GPI ]\n"); fprintf(stderr, " [ sender SRC[/PORT | GPI ] ]\n");
fprintf(stderr, " [ classid CLASSID ] [ action ACTION_SPEC ]\n"); fprintf(stderr, " [ classid CLASSID ] [ action ACTION_SPEC ]\n");
fprintf(stderr, " [ tunnelid ID ] [ tunnel ID skip NUMBER ]\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, "Where: GPI := { flowlabel NUMBER | spi/ah SPI | spi/esp SPI |\n");
......
...@@ -61,14 +61,14 @@ static int get_u32_handle(__u32 *handle, const char *str) ...@@ -61,14 +61,14 @@ static int get_u32_handle(__u32 *handle, const char *str)
if (htid>=0x1000) if (htid>=0x1000)
return -1; return -1;
if (*tmp) { if (*tmp) {
str = tmp+1; str = tmp + 1;
hash = strtoul(str, &tmp, 16); hash = strtoul(str, &tmp, 16);
if (tmp == str && *str != ':' && *str != 0) if (tmp == str && *str != ':' && *str != 0)
return -1; return -1;
if (hash>=0x100) if (hash>=0x100)
return -1; return -1;
if (*tmp) { if (*tmp) {
str = tmp+1; str = tmp + 1;
nodeid = strtoul(str, &tmp, 16); nodeid = strtoul(str, &tmp, 16);
if (tmp == str && *str != 0) if (tmp == str && *str != 0)
return -1; return -1;
...@@ -124,9 +124,9 @@ static int pack_key(struct tc_u32_sel *sel, __u32 key, __u32 mask, ...@@ -124,9 +124,9 @@ static int pack_key(struct tc_u32_sel *sel, __u32 key, __u32 mask,
for (i=0; i<hwm; i++) { for (i=0; i<hwm; i++) {
if (sel->keys[i].off == off && sel->keys[i].offmask == offmask) { if (sel->keys[i].off == off && sel->keys[i].offmask == offmask) {
__u32 intersect = mask&sel->keys[i].mask; __u32 intersect = mask & sel->keys[i].mask;
if ((key^sel->keys[i].val) & intersect) if ((key ^ sel->keys[i].val) & intersect)
return -1; return -1;
sel->keys[i].val |= key; sel->keys[i].val |= key;
sel->keys[i].mask |= mask; sel->keys[i].mask |= mask;
...@@ -346,7 +346,7 @@ static int parse_ip_addr(int *argc_p, char ***argv_p, struct tc_u32_sel *sel, ...@@ -346,7 +346,7 @@ static int parse_ip_addr(int *argc_p, char ***argv_p, struct tc_u32_sel *sel,
mask = 0; mask = 0;
if (addr.bitlen) if (addr.bitlen)
mask = htonl(0xFFFFFFFF<<(32-addr.bitlen)); mask = htonl(0xFFFFFFFF << (32 - addr.bitlen));
if (pack_key(sel, addr.data[0], mask, off, offmask) < 0) if (pack_key(sel, addr.data[0], mask, off, offmask) < 0)
return -1; return -1;
res = 0; res = 0;
...@@ -381,17 +381,17 @@ static int parse_ip6_addr(int *argc_p, char ***argv_p, ...@@ -381,17 +381,17 @@ static int parse_ip6_addr(int *argc_p, char ***argv_p,
} }
plen = addr.bitlen; plen = addr.bitlen;
for (i=0; i<plen; i+=32) { for (i = 0; i < plen; i += 32) {
// if (((i+31)&~0x1F)<=plen) { // if (((i + 31) & ~0x1F) <= plen) {
if (i + 31 <= plen) { if (i + 31 <= plen) {
res = pack_key(sel, addr.data[i/32], res = pack_key(sel, addr.data[i / 32],
0xFFFFFFFF, off+4*(i/32), offmask); 0xFFFFFFFF, off + 4 * (i / 32), offmask);
if (res < 0) if (res < 0)
return -1; return -1;
} else if (i < plen) { } else if (i < plen) {
__u32 mask = htonl(0xFFFFFFFF << (32 - (plen -i ))); __u32 mask = htonl(0xFFFFFFFF << (32 - (plen - i)));
res = pack_key(sel, addr.data[i/32], res = pack_key(sel, addr.data[i / 32],
mask, off+4*(i/32), offmask); mask, off + 4 * (i / 32), offmask);
if (res < 0) if (res < 0)
return -1; return -1;
} }
...@@ -496,7 +496,8 @@ static int parse_ip(int *argc_p, char ***argv_p, struct tc_u32_sel *sel) ...@@ -496,7 +496,8 @@ static int parse_ip(int *argc_p, char ***argv_p, struct tc_u32_sel *sel)
NEXT_ARG(); NEXT_ARG();
res = parse_ip_addr(&argc, &argv, sel, 16); res = parse_ip_addr(&argc, &argv, sel, 16);
} else if (strcmp(*argv, "tos") == 0 || } else if (strcmp(*argv, "tos") == 0 ||
matches(*argv, "dsfield") == 0) { matches(*argv, "dsfield") == 0 ||
matches(*argv, "precedence") == 0) {
NEXT_ARG(); NEXT_ARG();
res = parse_u8(&argc, &argv, sel, 1, 0); res = parse_u8(&argc, &argv, sel, 1, 0);
} else if (strcmp(*argv, "ihl") == 0) { } else if (strcmp(*argv, "ihl") == 0) {
...@@ -505,9 +506,6 @@ static int parse_ip(int *argc_p, char ***argv_p, struct tc_u32_sel *sel) ...@@ -505,9 +506,6 @@ static int parse_ip(int *argc_p, char ***argv_p, struct tc_u32_sel *sel)
} else if (strcmp(*argv, "protocol") == 0) { } else if (strcmp(*argv, "protocol") == 0) {
NEXT_ARG(); NEXT_ARG();
res = parse_u8(&argc, &argv, sel, 9, 0); res = parse_u8(&argc, &argv, sel, 9, 0);
} else if (matches(*argv, "precedence") == 0) {
NEXT_ARG();
res = parse_u8(&argc, &argv, sel, 1, 0);
} else if (strcmp(*argv, "nofrag") == 0) { } else if (strcmp(*argv, "nofrag") == 0) {
argc--; argv++; argc--; argv++;
res = pack_key16(sel, 0, 0x3FFF, 6, 0); res = pack_key16(sel, 0, 0x3FFF, 6, 0);
...@@ -1072,9 +1070,9 @@ static int u32_parse_opt(struct filter_util *qu, char *handle, ...@@ -1072,9 +1070,9 @@ static int u32_parse_opt(struct filter_util *qu, char *handle,
return -1; return -1;
} }
if (sample_ok) if (sample_ok)
htid = (htid&0xFF000)|(handle&0xFFF00000); htid = (htid & 0xFF000) | (handle & 0xFFF00000);
else else
htid = (handle&0xFFFFF000); htid = (handle & 0xFFFFF000);
} else if (strcmp(*argv, "sample") == 0) { } else if (strcmp(*argv, "sample") == 0) {
__u32 hash; __u32 hash;
unsigned divisor = 0x100; unsigned divisor = 0x100;
...@@ -1103,10 +1101,10 @@ static int u32_parse_opt(struct filter_util *qu, char *handle, ...@@ -1103,10 +1101,10 @@ static int u32_parse_opt(struct filter_util *qu, char *handle,
} }
NEXT_ARG(); NEXT_ARG();
} }
hash = sel2.sel.keys[0].val&sel2.sel.keys[0].mask; hash = sel2.sel.keys[0].val & sel2.sel.keys[0].mask;
hash ^= hash>>16; hash ^= hash >> 16;
hash ^= hash>>8; hash ^= hash >> 8;
htid = ((hash%divisor)<<12)|(htid&0xFFF00000); htid = ((hash % divisor) << 12) | (htid & 0xFFF00000);
sample_ok = 1; sample_ok = 1;
continue; continue;
} else if (strcmp(*argv, "indev") == 0) { } else if (strcmp(*argv, "indev") == 0) {
...@@ -1165,7 +1163,7 @@ static int u32_parse_opt(struct filter_util *qu, char *handle, ...@@ -1165,7 +1163,7 @@ static int u32_parse_opt(struct filter_util *qu, char *handle,
addattr_l(n, MAX_MSG, TCA_U32_HASH, &htid, 4); addattr_l(n, MAX_MSG, TCA_U32_HASH, &htid, 4);
if (sel_ok) if (sel_ok)
addattr_l(n, MAX_MSG, TCA_U32_SEL, &sel, addattr_l(n, MAX_MSG, TCA_U32_SEL, &sel,
sizeof(sel.sel)+sel.sel.nkeys*sizeof(struct tc_u32_key)); sizeof(sel.sel) + sel.sel.nkeys * sizeof(struct tc_u32_key));
tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail; tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
return 0; return 0;
} }
...@@ -1173,7 +1171,7 @@ static int u32_parse_opt(struct filter_util *qu, char *handle, ...@@ -1173,7 +1171,7 @@ static int u32_parse_opt(struct filter_util *qu, char *handle,
static int u32_print_opt(struct filter_util *qu, FILE *f, struct rtattr *opt, static int u32_print_opt(struct filter_util *qu, FILE *f, struct rtattr *opt,
__u32 handle) __u32 handle)
{ {
struct rtattr *tb[TCA_U32_MAX+1]; struct rtattr *tb[TCA_U32_MAX + 1];
struct tc_u32_sel *sel = NULL; struct tc_u32_sel *sel = NULL;
struct tc_u32_pcnt *pf = NULL; struct tc_u32_pcnt *pf = NULL;
...@@ -1209,9 +1207,9 @@ static int u32_print_opt(struct filter_util *qu, FILE *f, struct rtattr *opt, ...@@ -1209,9 +1207,9 @@ static int u32_print_opt(struct filter_util *qu, FILE *f, struct rtattr *opt,
if (tb[TCA_U32_CLASSID]) { if (tb[TCA_U32_CLASSID]) {
SPRINT_BUF(b1); SPRINT_BUF(b1);
fprintf(f, "%sflowid %s ", fprintf(f, "%sflowid %s ",
!sel || !(sel->flags&TC_U32_TERMINAL) ? "*" : "", !sel || !(sel->flags & TC_U32_TERMINAL) ? "*" : "",
sprint_tc_classid(rta_getattr_u32(tb[TCA_U32_CLASSID]), b1)); sprint_tc_classid(rta_getattr_u32(tb[TCA_U32_CLASSID]), b1));
} else if (sel && sel->flags&TC_U32_TERMINAL) { } else if (sel && sel->flags & TC_U32_TERMINAL) {
fprintf(f, "terminal flowid ??? "); fprintf(f, "terminal flowid ??? ");
} }
if (tb[TCA_U32_LINK]) { if (tb[TCA_U32_LINK]) {
...@@ -1254,16 +1252,16 @@ static int u32_print_opt(struct filter_util *qu, FILE *f, struct rtattr *opt, ...@@ -1254,16 +1252,16 @@ static int u32_print_opt(struct filter_util *qu, FILE *f, struct rtattr *opt,
} }
} }
if (sel->flags&(TC_U32_VAROFFSET|TC_U32_OFFSET)) { if (sel->flags & (TC_U32_VAROFFSET | TC_U32_OFFSET)) {
fprintf(f, "\n offset "); fprintf(f, "\n offset ");
if (sel->flags&TC_U32_VAROFFSET) if (sel->flags & TC_U32_VAROFFSET)
fprintf(f, "%04x>>%d at %d ", fprintf(f, "%04x>>%d at %d ",
ntohs(sel->offmask), ntohs(sel->offmask),
sel->offshift, sel->offoff); sel->offshift, sel->offoff);
if (sel->off) if (sel->off)
fprintf(f, "plus %d ", sel->off); fprintf(f, "plus %d ", sel->off);
} }
if (sel->flags&TC_U32_EAT) if (sel->flags & TC_U32_EAT)
fprintf(f, " eat "); fprintf(f, " eat ");
if (sel->hmask) { if (sel->hmask) {
......
...@@ -648,4 +648,3 @@ int do_action(int argc, char **argv) ...@@ -648,4 +648,3 @@ int do_action(int argc, char **argv)
return 0; return 0;
} }
...@@ -618,4 +618,3 @@ struct action_util ipt_action_util = { ...@@ -618,4 +618,3 @@ struct action_util ipt_action_util = {
.parse_aopt = parse_ipt, .parse_aopt = parse_ipt,
.print_aopt = print_ipt, .print_aopt = print_ipt,
}; };
...@@ -433,4 +433,3 @@ struct action_util ipt_action_util = { ...@@ -433,4 +433,3 @@ struct action_util ipt_action_util = {
.parse_aopt = parse_ipt, .parse_aopt = parse_ipt,
.print_aopt = print_ipt, .print_aopt = print_ipt,
}; };
...@@ -34,5 +34,3 @@ struct m_pedit_util p_pedit_tcp = { ...@@ -34,5 +34,3 @@ struct m_pedit_util p_pedit_tcp = {
"tcp", "tcp",
parse_tcp, parse_tcp,
}; };
...@@ -35,4 +35,3 @@ struct m_pedit_util p_pedit_udp = { ...@@ -35,4 +35,3 @@ struct m_pedit_util p_pedit_udp = {
"udp", "udp",
parse_udp, parse_udp,
}; };
...@@ -582,4 +582,3 @@ struct qdisc_util cbq_qdisc_util = { ...@@ -582,4 +582,3 @@ struct qdisc_util cbq_qdisc_util = {
.parse_copt = cbq_parse_class_opt, .parse_copt = cbq_parse_class_opt,
.print_copt = cbq_print_opt, .print_copt = cbq_print_opt,
}; };
...@@ -688,4 +688,3 @@ struct qdisc_util netem_qdisc_util = { ...@@ -688,4 +688,3 @@ struct qdisc_util netem_qdisc_util = {
.parse_qopt = netem_parse_opt, .parse_qopt = netem_parse_opt,
.print_qopt = netem_print_opt, .print_qopt = netem_print_opt,
}; };
...@@ -122,4 +122,3 @@ struct qdisc_util prio_qdisc_util = { ...@@ -122,4 +122,3 @@ struct qdisc_util prio_qdisc_util = {
.parse_qopt = prio_parse_opt, .parse_qopt = prio_parse_opt,
.print_qopt = prio_print_opt, .print_qopt = prio_print_opt,
}; };
...@@ -328,4 +328,3 @@ struct qdisc_util tbf_qdisc_util = { ...@@ -328,4 +328,3 @@ struct qdisc_util tbf_qdisc_util = {
.parse_qopt = tbf_parse_opt, .parse_qopt = tbf_parse_opt,
.print_qopt = tbf_print_opt, .print_qopt = tbf_print_opt,
}; };
...@@ -375,4 +375,3 @@ int do_filter(int argc, char **argv) ...@@ -375,4 +375,3 @@ int do_filter(int argc, char **argv)
fprintf(stderr, "Command \"%s\" is unknown, try \"tc filter help\".\n", *argv); fprintf(stderr, "Command \"%s\" is unknown, try \"tc filter help\".\n", *argv);
return -1; return -1;
} }
...@@ -148,4 +148,3 @@ void print_size_table(FILE *fp, const char *prefix, struct rtattr *rta) ...@@ -148,4 +148,3 @@ void print_size_table(FILE *fp, const char *prefix, struct rtattr *rta)
} }
#endif #endif
} }
...@@ -608,4 +608,3 @@ compat_xstats: ...@@ -608,4 +608,3 @@ compat_xstats:
if (tb[TCA_XSTATS] && xstats) if (tb[TCA_XSTATS] && xstats)
*xstats = tb[TCA_XSTATS]; *xstats = tb[TCA_XSTATS];
} }
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment