kernel_optimize_test/samples/bpf/test_cls_bpf.sh
Alexei Starovoitov 65d472fb00 samples/bpf: add 'pointer to packet' tests
parse_simple.c - packet parser exapmle with single length check that
filters out udp packets for port 9

parse_varlen.c - variable length parser that understand multiple vlan headers,
ipip, ipip6 and ip options to filter out udp or tcp packets on port 9.
The packet is parsed layer by layer with multitple length checks.

parse_ldabs.c - classic style of packet parsing using LD_ABS instruction.
Same functionality as parse_simple.

simple = 24.1Mpps per core
varlen = 22.7Mpps
ldabs  = 21.4Mpps

Parser with LD_ABS instructions is slower than full direct access parser
which does more packet accesses and checks.

These examples demonstrate the choice bpf program authors can make between
flexibility of the parser vs speed.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-05-06 16:01:54 -04:00

38 lines
880 B
Bash
Executable File

#!/bin/bash
function pktgen {
../pktgen/pktgen_bench_xmit_mode_netif_receive.sh -i $IFC -s 64 \
-m 90:e2:ba:ff:ff:ff -d 192.168.0.1 -t 4
local dropped=`tc -s qdisc show dev $IFC | tail -3 | awk '/drop/{print $7}'`
if [ "$dropped" == "0," ]; then
echo "FAIL"
else
echo "Successfully filtered " $dropped " packets"
fi
}
function test {
echo -n "Loading bpf program '$2'... "
tc qdisc add dev $IFC clsact
tc filter add dev $IFC ingress bpf da obj $1 sec $2
local status=$?
if [ $status -ne 0 ]; then
echo "FAIL"
else
echo "ok"
pktgen
fi
tc qdisc del dev $IFC clsact
}
IFC=test_veth
ip link add name $IFC type veth peer name pair_$IFC
ip link set $IFC up
ip link set pair_$IFC up
test ./parse_simple.o simple
test ./parse_varlen.o varlen
test ./parse_ldabs.o ldabs
ip link del dev $IFC