diff options
| author | David S. Miller <davem@davemloft.net> | 2019-03-04 10:14:31 -0800 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2019-03-04 10:14:31 -0800 |
| commit | f7fb7c1a1c8f86005d34f28278524213c521f761 (patch) | |
| tree | 05a3b21c5e0b1667b106153fc0f0eb88cd980ab2 /samples/bpf | |
| parent | 8c4238df4d0cc3420c5ee14b54d200d74267cfe5 (diff) | |
| parent | 87dab7c3d54ce0f1ff6b54840bf7279d0944bc6a (diff) | |
| download | linux-f7fb7c1a1c8f86005d34f28278524213c521f761.tar.bz2 | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Daniel Borkmann says:
====================
pull-request: bpf-next 2019-03-04
The following pull-request contains BPF updates for your *net-next* tree.
The main changes are:
1) Add AF_XDP support to libbpf. Rationale is to facilitate writing
AF_XDP applications by offering higher-level APIs that hide many
of the details of the AF_XDP uapi. Sample programs are converted
over to this new interface as well, from Magnus.
2) Introduce a new cant_sleep() macro for annotation of functions
that cannot sleep and use it in BPF_PROG_RUN() to assert that
BPF programs run under preemption disabled context, from Peter.
3) Introduce per BPF prog stats in order to monitor the usage
of BPF; this is controlled by kernel.bpf_stats_enabled sysctl
knob where monitoring tools can make use of this to efficiently
determine the average cost of programs, from Alexei.
4) Split up BPF selftest's test_progs similarly as we already
did with test_verifier. This allows to further reduce merge
conflicts in future and to get more structure into our
quickly growing BPF selftest suite, from Stanislav.
5) Fix a bug in BTF's dedup algorithm which can cause an infinite
loop in some circumstances; also various BPF doc fixes and
improvements, from Andrii.
6) Various BPF sample cleanups and migration to libbpf in order
to further isolate the old sample loader code (so we can get
rid of it at some point), from Jakub.
7) Add a new BPF helper for BPF cgroup skb progs that allows
to set ECN CE code point and a Host Bandwidth Manager (HBM)
sample program for limiting the bandwidth used by v2 cgroups,
from Lawrence.
8) Enable write access to skb->queue_mapping from tc BPF egress
programs in order to let BPF pick TX queue, from Jesper.
9) Fix a bug in BPF spinlock handling for map-in-map which did
not propagate spin_lock_off to the meta map, from Yonghong.
10) Fix a bug in the new per-CPU BPF prog counters to properly
initialize stats for each CPU, from Eric.
11) Add various BPF helper prototypes to selftest's bpf_helpers.h,
from Willem.
12) Fix various BPF samples bugs in XDP and tracing progs,
from Toke, Daniel and Yonghong.
13) Silence preemption splat in test_bpf after BPF_PROG_RUN()
enforces it now everywhere, from Anders.
14) Fix a signedness bug in libbpf's btf_dedup_ref_type() to
get error handling working, from Dan.
15) Fix bpftool documentation and auto-completion with regards
to stream_{verdict,parser} attach types, from Alban.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'samples/bpf')
31 files changed, 1529 insertions, 797 deletions
diff --git a/samples/bpf/.gitignore b/samples/bpf/.gitignore index 8ae4940025f8..dbb817dbacfc 100644 --- a/samples/bpf/.gitignore +++ b/samples/bpf/.gitignore @@ -1,7 +1,6 @@ cpustat fds_example lathist -load_sock_ops lwt_len_hist map_perf_test offwaketime diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index a0ef7eddd0b3..65e667bdf979 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -40,7 +40,6 @@ hostprogs-y += lwt_len_hist hostprogs-y += xdp_tx_iptunnel hostprogs-y += test_map_in_map hostprogs-y += per_socket_stats_example -hostprogs-y += load_sock_ops hostprogs-y += xdp_redirect hostprogs-y += xdp_redirect_map hostprogs-y += xdp_redirect_cpu @@ -53,6 +52,7 @@ hostprogs-y += xdpsock hostprogs-y += xdp_fwd hostprogs-y += task_fd_query hostprogs-y += xdp_sample_pkts +hostprogs-y += hbm # Libbpf dependencies LIBBPF = $(TOOLS_PATH)/lib/bpf/libbpf.a @@ -60,9 +60,9 @@ LIBBPF = $(TOOLS_PATH)/lib/bpf/libbpf.a CGROUP_HELPERS := ../../tools/testing/selftests/bpf/cgroup_helpers.o TRACE_HELPERS := ../../tools/testing/selftests/bpf/trace_helpers.o -fds_example-objs := bpf_load.o fds_example.o -sockex1-objs := bpf_load.o sockex1_user.o -sockex2-objs := bpf_load.o sockex2_user.o +fds_example-objs := fds_example.o +sockex1-objs := sockex1_user.o +sockex2-objs := sockex2_user.o sockex3-objs := bpf_load.o sockex3_user.o tracex1-objs := bpf_load.o tracex1_user.o tracex2-objs := bpf_load.o tracex2_user.o @@ -71,7 +71,6 @@ tracex4-objs := bpf_load.o tracex4_user.o tracex5-objs := bpf_load.o tracex5_user.o tracex6-objs := bpf_load.o tracex6_user.o tracex7-objs := bpf_load.o tracex7_user.o -load_sock_ops-objs := bpf_load.o load_sock_ops.o test_probe_write_user-objs := bpf_load.o test_probe_write_user_user.o trace_output-objs := bpf_load.o trace_output_user.o $(TRACE_HELPERS) lathist-objs := bpf_load.o lathist_user.o @@ -109,6 +108,7 @@ xdpsock-objs := xdpsock_user.o xdp_fwd-objs := xdp_fwd_user.o task_fd_query-objs := bpf_load.o task_fd_query_user.o $(TRACE_HELPERS) xdp_sample_pkts-objs := xdp_sample_pkts_user.o $(TRACE_HELPERS) +hbm-objs := bpf_load.o hbm.o $(CGROUP_HELPERS) # Tell kbuild to always build the programs always := $(hostprogs-y) @@ -163,10 +163,10 @@ always += xdp2skb_meta_kern.o always += syscall_tp_kern.o always += cpustat_kern.o always += xdp_adjust_tail_kern.o -always += xdpsock_kern.o always += xdp_fwd_kern.o always += task_fd_query_kern.o always += xdp_sample_pkts_kern.o +always += hbm_out_kern.o KBUILD_HOSTCFLAGS += -I$(objtree)/usr/include KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/ @@ -266,6 +266,8 @@ $(BPF_SAMPLES_PATH)/*.c: verify_target_bpf $(LIBBPF) $(src)/*.c: verify_target_bpf $(LIBBPF) $(obj)/tracex5_kern.o: $(obj)/syscall_nrs.h +$(obj)/hbm_out_kern.o: $(src)/hbm.h $(src)/hbm_kern.h +$(obj)/hbm.o: $(src)/hbm.h # asm/sysreg.h - inline assembly used by it is incompatible with llvm. # But, there is no easy way to fix it, so just exclude it since it is diff --git a/samples/bpf/do_hbm_test.sh b/samples/bpf/do_hbm_test.sh new file mode 100755 index 000000000000..56c8b4115c95 --- /dev/null +++ b/samples/bpf/do_hbm_test.sh @@ -0,0 +1,436 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2019 Facebook +# +# 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. + +Usage() { + echo "Script for testing HBM (Host Bandwidth Manager) framework." + echo "It creates a cgroup to use for testing and load a BPF program to limit" + echo "egress or ingress bandwidht. It then uses iperf3 or netperf to create" + echo "loads. The output is the goodput in Mbps (unless -D was used)." + echo "" + echo "USAGE: $name [out] [-b=<prog>|--bpf=<prog>] [-c=<cc>|--cc=<cc>] [-D]" + echo " [-d=<delay>|--delay=<delay>] [--debug] [-E]" + echo " [-f=<#flows>|--flows=<#flows>] [-h] [-i=<id>|--id=<id >]" + echo " [-l] [-N] [-p=<port>|--port=<port>] [-P]" + echo " [-q=<qdisc>] [-R] [-s=<server>|--server=<server]" + echo " [-S|--stats] -t=<time>|--time=<time>] [-w] [cubic|dctcp]" + echo " Where:" + echo " out egress (default)" + echo " -b or --bpf BPF program filename to load and attach." + echo " Default is hbm_out_kern.o for egress," + echo " -c or -cc TCP congestion control (cubic or dctcp)" + echo " --debug print BPF trace buffer" + echo " -d or --delay add a delay in ms using netem" + echo " -D In addition to the goodput in Mbps, it also outputs" + echo " other detailed information. This information is" + echo " test dependent (i.e. iperf3 or netperf)." + echo " -E enable ECN (not required for dctcp)" + echo " -f or --flows number of concurrent flows (default=1)" + echo " -i or --id cgroup id (an integer, default is 1)" + echo " -N use netperf instead of iperf3" + echo " -l do not limit flows using loopback" + echo " -h Help" + echo " -p or --port iperf3 port (default is 5201)" + echo " -P use an iperf3 instance for each flow" + echo " -q use the specified qdisc" + echo " -r or --rate rate in Mbps (default 1s 1Gbps)" + echo " -R Use TCP_RR for netperf. 1st flow has req" + echo " size of 10KB, rest of 1MB. Reply in all" + echo " cases is 1 byte." + echo " More detailed output for each flow can be found" + echo " in the files netperf.<cg>.<flow>, where <cg> is the" + echo " cgroup id as specified with the -i flag, and <flow>" + echo " is the flow id starting at 1 and increasing by 1 for" + echo " flow (as specified by -f)." + echo " -s or --server hostname of netperf server. Used to create netperf" + echo " test traffic between to hosts (default is within host)" + echo " netserver must be running on the host." + echo " -S or --stats whether to update hbm stats (default is yes)." + echo " -t or --time duration of iperf3 in seconds (default=5)" + echo " -w Work conserving flag. cgroup can increase its" + echo " bandwidth beyond the rate limit specified" + echo " while there is available bandwidth. Current" + echo " implementation assumes there is only one NIC" + echo " (eth0), but can be extended to support multiple" + echo " NICs." + echo " cubic or dctcp specify which TCP CC to use" + echo " " + exit +} + +#set -x + +debug_flag=0 +args="$@" +name="$0" +netem=0 +cc=x +dir="-o" +dir_name="out" +dur=5 +flows=1 +id=1 +prog="" +port=5201 +rate=1000 +multi_iperf=0 +flow_cnt=1 +use_netperf=0 +rr=0 +ecn=0 +details=0 +server="" +qdisc="" +flags="" +do_stats=0 + +function start_hbm () { + rm -f hbm.out + echo "./hbm $dir -n $id -r $rate -t $dur $flags $dbg $prog" > hbm.out + echo " " >> hbm.out + ./hbm $dir -n $id -r $rate -t $dur $flags $dbg $prog >> hbm.out 2>&1 & + echo $! +} + +processArgs () { + for i in $args ; do + case $i in + # Support for upcomming ingress rate limiting + #in) # support for upcoming ingress rate limiting + # dir="-i" + # dir_name="in" + # ;; + out) + dir="-o" + dir_name="out" + ;; + -b=*|--bpf=*) + prog="${i#*=}" + ;; + -c=*|--cc=*) + cc="${i#*=}" + ;; + --debug) + flags="$flags -d" + debug_flag=1 + ;; + -d=*|--delay=*) + netem="${i#*=}" + ;; + -D) + details=1 + ;; + -E) + ecn=1 + ;; + # Support for upcomming fq Early Departure Time egress rate limiting + #--edt) + # prog="hbm_out_edt_kern.o" + # qdisc="fq" + # ;; + -f=*|--flows=*) + flows="${i#*=}" + ;; + -i=*|--id=*) + id="${i#*=}" + ;; + -l) + flags="$flags -l" + ;; + -N) + use_netperf=1 + ;; + -p=*|--port=*) + port="${i#*=}" + ;; + -P) + multi_iperf=1 + ;; + -q=*) + qdisc="${i#*=}" + ;; + -r=*|--rate=*) + rate="${i#*=}" + ;; + -R) + rr=1 + ;; + -s=*|--server=*) + server="${i#*=}" + ;; + -S|--stats) + flags="$flags -s" + do_stats=1 + ;; + -t=*|--time=*) + dur="${i#*=}" + ;; + -w) + flags="$flags -w" + ;; + cubic) + cc=cubic + ;; + dctcp) + cc=dctcp + ;; + *) + echo "Unknown arg:$i" + Usage + ;; + esac + done +} + +processArgs + +if [ $debug_flag -eq 1 ] ; then + rm -f hbm_out.log +fi + +hbm_pid=$(start_hbm) +usleep 100000 + +host=`hostname` +cg_base_dir=/sys/fs/cgroup +cg_dir="$cg_base_dir/cgroup-test-work-dir/hbm$id" + +echo $$ >> $cg_dir/cgroup.procs + +ulimit -l unlimited + +rm -f ss.out +rm -f hbm.[0-9]*.$dir_name +if [ $ecn -ne 0 ] ; then + sysctl -w -q -n net.ipv4.tcp_ecn=1 +fi + +if [ $use_netperf -eq 0 ] ; then + cur_cc=`sysctl -n net.ipv4.tcp_congestion_control` + if [ "$cc" != "x" ] ; then + sysctl -w -q -n net.ipv4.tcp_congestion_control=$cc + fi +fi + +if [ "$netem" -ne "0" ] ; then + if [ "$qdisc" != "" ] ; then + echo "WARNING: Ignoring -q options because -d option used" + fi + tc qdisc del dev lo root > /dev/null 2>&1 + tc qdisc add dev lo root netem delay $netem\ms > /dev/null 2>&1 +elif [ "$qdisc" != "" ] ; then + tc qdisc del dev lo root > /dev/null 2>&1 + tc qdisc add dev lo root $qdisc > /dev/null 2>&1 +fi + +n=0 +m=$[$dur * 5] +hn="::1" +if [ $use_netperf -ne 0 ] ; then + if [ "$server" != "" ] ; then + hn=$server + fi +fi + +( ping6 -i 0.2 -c $m $hn > ping.out 2>&1 ) & + +if [ $use_netperf -ne 0 ] ; then + begNetserverPid=`ps ax | grep netserver | grep --invert-match "grep" | \ + awk '{ print $1 }'` + if [ "$begNetserverPid" == "" ] ; then + if [ "$server" == "" ] ; then + ( ./netserver > /dev/null 2>&1) & + usleep 100000 + fi + fi + flow_cnt=1 + if [ "$server" == "" ] ; then + np_server=$host + else + np_server=$server + fi + if [ "$cc" == "x" ] ; then + np_cc="" + else + np_cc="-K $cc,$cc" + fi + replySize=1 + while [ $flow_cnt -le $flows ] ; do + if [ $rr -ne 0 ] ; then + reqSize=1M + if [ $flow_cnt -eq 1 ] ; then + reqSize=10K + fi + if [ "$dir" == "-i" ] ; then + replySize=$reqSize + reqSize=1 + fi + ( ./netperf -H $np_server -l $dur -f m -j -t TCP_RR -- -r $reqSize,$replySize $np_cc -k P50_lATENCY,P90_LATENCY,LOCAL_TRANSPORT_RETRANS,REMOTE_TRANSPORT_RETRANS,LOCAL_SEND_THROUGHPUT,LOCAL_RECV_THROUGHPUT,REQUEST_SIZE,RESPONSE_SIZE > netperf.$id.$flow_cnt ) & + else + if [ "$dir" == "-i" ] ; then + ( ./netperf -H $np_server -l $dur -f m -j -t TCP_RR -- -r 1,10M $np_cc -k P50_LATENCY,P90_LATENCY,LOCAL_TRANSPORT_RETRANS,LOCAL_SEND_THROUGHPUT,REMOTE_TRANSPORT_RETRANS,REMOTE_SEND_THROUGHPUT,REQUEST_SIZE,RESPONSE_SIZE > netperf.$id.$flow_cnt ) & + else + ( ./netperf -H $np_server -l $dur -f m -j -t TCP_STREAM -- $np_cc -k P50_lATENCY,P90_LATENCY,LOCAL_TRANSPORT_RETRANS,LOCAL_SEND_THROUGHPUT,REQUEST_SIZE,RESPONSE_SIZE > netperf.$id.$flow_cnt ) & + fi + fi + flow_cnt=$[flow_cnt+1] + done + +# sleep for duration of test (plus some buffer) + n=$[dur+2] + sleep $n + +# force graceful termination of netperf + pids=`pgrep netperf` + for p in $pids ; do + kill -SIGALRM $p + done + + flow_cnt=1 + rate=0 + if [ $details -ne 0 ] ; then + echo "" + echo "Details for HBM in cgroup $id" + if [ $do_stats -eq 1 ] ; then + if [ -e hbm.$id.$dir_name ] ; then + cat hbm.$id.$dir_name + fi + fi + fi + while [ $flow_cnt -le $flows ] ; do + if [ "$dir" == "-i" ] ; then + r=`cat netperf.$id.$flow_cnt | grep -o "REMOTE_SEND_THROUGHPUT=[0-9]*" | grep -o "[0-9]*"` + else + r=`cat netperf.$id.$flow_cnt | grep -o "LOCAL_SEND_THROUGHPUT=[0-9]*" | grep -o "[0-9]*"` + fi + echo "rate for flow $flow_cnt: $r" + rate=$[rate+r] + if [ $details -ne 0 ] ; then + echo "-----" + echo "Details for cgroup $id, flow $flow_cnt" + cat netperf.$id.$flow_cnt + fi + flow_cnt=$[flow_cnt+1] + done + if [ $details -ne 0 ] ; then + echo "" + delay=`grep "avg" ping.out | grep -o "= [0-9.]*/[0-9.]*" | grep -o "[0-9.]*$"` + echo "PING AVG DELAY:$delay" + echo "AGGREGATE_GOODPUT:$rate" + else + echo $rate + fi +elif [ $multi_iperf -eq 0 ] ; then + (iperf3 -s -p $port -1 > /dev/null 2>&1) & + usleep 100000 + iperf3 -c $host -p $port -i 0 -P $flows -f m -t $dur > iperf.$id + rates=`grep receiver iperf.$id | grep -o "[0-9.]* Mbits" | grep -o "^[0-9]*"` + rate=`echo $rates | grep -o "[0-9]*$"` + + if [ $details -ne 0 ] ; then + echo "" + echo "Details for HBM in cgroup $id" + if [ $do_stats -eq 1 ] ; then + if [ -e hbm.$id.$dir_name ] ; then + cat hbm.$id.$dir_name + fi + fi + delay=`grep "avg" ping.out | grep -o "= [0-9.]*/[0-9.]*" | grep -o "[0-9.]*$"` + echo "PING AVG DELAY:$delay" + echo "AGGREGATE_GOODPUT:$rate" + else + echo $rate + fi +else + flow_cnt=1 + while [ $flow_cnt -le $flows ] ; do + (iperf3 -s -p $port -1 > /dev/null 2>&1) & + ( iperf3 -c $host -p $port -i 0 -P 1 -f m -t $dur | grep receiver | grep -o "[0-9.]* Mbits" | grep -o "^[0-9]*" | grep -o "[0-9]*$" > iperf3.$id.$flow_cnt ) & + port=$[port+1] + flow_cnt=$[flow_cnt+1] + done + n=$[dur+1] + sleep $n + flow_cnt=1 + rate=0 + if [ $details -ne 0 ] ; then + echo "" + echo "Details for HBM in cgroup $id" + if [ $do_stats -eq 1 ] ; then + if [ -e hbm.$id.$dir_name ] ; then + cat hbm.$id.$dir_name + fi + fi + fi + + while [ $flow_cnt -le $flows ] ; do + r=`cat iperf3.$id.$flow_cnt` +# echo "rate for flow $flow_cnt: $r" + if [ $details -ne 0 ] ; then + echo "Rate for cgroup $id, flow $flow_cnt LOCAL_SEND_THROUGHPUT=$r" + fi + rate=$[rate+r] + flow_cnt=$[flow_cnt+1] + done + if [ $details -ne 0 ] ; then + delay=`grep "avg" ping.out | grep -o "= [0-9.]*/[0-9.]*" | grep -o "[0-9.]*$"` + echo "PING AVG DELAY:$delay" + echo "AGGREGATE_GOODPUT:$rate" + else + echo $rate + fi +fi + +if [ $use_netperf -eq 0 ] ; then + sysctl -w -q -n net.ipv4.tcp_congestion_control=$cur_cc +fi +if [ $ecn -ne 0 ] ; then + sysctl -w -q -n net.ipv4.tcp_ecn=0 +fi +if [ "$netem" -ne "0" ] ; then + tc qdisc del dev lo root > /dev/null 2>&1 +fi + +sleep 2 + +hbmPid=`ps ax | grep "hbm " | grep --invert-match "grep" | awk '{ print $1 }'` +if [ "$hbmPid" == "$hbm_pid" ] ; then + kill $hbm_pid +fi + +sleep 1 + +# Detach any BPF programs that may have lingered +ttx=`bpftool cgroup tree | grep hbm` +v=2 +for x in $ttx ; do + if [ "${x:0:36}" == "/sys/fs/cgroup/cgroup-test-work-dir/" ] ; then + cg=$x ; v=0 + else + if [ $v -eq 0 ] ; then + id=$x ; v=1 + else + if [ $v -eq 1 ] ; then + type=$x ; bpftool cgroup detach $cg $type id $id + v=0 + fi + fi + fi +done + +if [ $use_netperf -ne 0 ] ; then + if [ "$server" == "" ] ; then + if [ "$begNetserverPid" == "" ] ; then + netserverPid=`ps ax | grep netserver | grep --invert-match "grep" | awk '{ print $1 }'` + if [ "$netserverPid" != "" ] ; then + kill $netserverPid + fi + fi + fi +fi +exit diff --git a/samples/bpf/fds_example.c b/samples/bpf/fds_example.c index 9854854f05d1..e51eb060244e 100644 --- a/samples/bpf/fds_example.c +++ b/samples/bpf/fds_example.c @@ -14,8 +14,8 @@ #include <bpf/bpf.h> +#include "bpf/libbpf.h" #include "bpf_insn.h" -#include "bpf_load.h" #include "sock_example.h" #define BPF_F_PIN (1 << 0) @@ -57,10 +57,14 @@ static int bpf_prog_create(const char *object) BPF_EXIT_INSN(), }; size_t insns_cnt = sizeof(insns) / sizeof(struct bpf_insn); + char bpf_log_buf[BPF_LOG_BUF_SIZE]; + struct bpf_object *obj; + int prog_fd; if (object) { - assert(!load_bpf_file((char *)object)); - return prog_fd[0]; + assert(!bpf_prog_load(object, BPF_PROG_TYPE_UNSPEC, + &obj, &prog_fd)); + return prog_fd; } else { return bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, insns, insns_cnt, "GPL", 0, diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c new file mode 100644 index 000000000000..8408ccb7409f --- /dev/null +++ b/samples/bpf/hbm.c @@ -0,0 +1,441 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook + * + * 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. + * + * Example program for Host Bandwidth Managment + * + * This program loads a cgroup skb BPF program to enforce cgroup output + * (egress) or input (ingress) bandwidth limits. + * + * USAGE: hbm [-d] [-l] [-n <id>] [-r <rate>] [-s] [-t <secs>] [-w] [-h] [prog] + * Where: + * -d Print BPF trace debug buffer + * -l Also limit flows doing loopback + * -n <#> To create cgroup \"/hbm#\" and attach prog + * Default is /hbm1 + * -r <rate> Rate limit in Mbps + * -s Get HBM stats (marked, dropped, etc.) + * -t <time> Exit after specified seconds (deault is 0) + * -w Work conserving flag. cgroup can increase its bandwidth + * beyond the rate limit specified while there is available + * bandwidth. Current implementation assumes there is only + * NIC (eth0), but can be extended to support multiple NICs. + * Currrently only supported for egress. + * -h Print this info + * prog BPF program file name. Name defaults to hbm_out_kern.o + */ + +#define _GNU_SOURCE + +#include <stdio.h> +#include <stdlib.h> +#include <assert.h> +#include <sys/resource.h> +#include <sys/time.h> +#include <unistd.h> +#include <errno.h> +#include <fcntl.h> +#include <linux/unistd.h> + +#include <linux/bpf.h> +#include <bpf/bpf.h> + +#include "bpf_load.h" +#include "bpf_rlimit.h" +#include "cgroup_helpers.h" +#include "hbm.h" +#include "bpf_util.h" +#include "bpf/bpf.h" +#include "bpf/libbpf.h" + +bool outFlag = true; +int minRate = 1000; /* cgroup rate limit in Mbps */ +int rate = 1000; /* can grow if rate conserving is enabled */ +int dur = 1; +bool stats_flag; +bool loopback_flag; +bool debugFlag; +bool work_conserving_flag; + +static void Usage(void); +static void read_trace_pipe2(void); +static void do_error(char *msg, bool errno_flag); + +#define DEBUGFS "/sys/kernel/debug/tracing/" + +struct bpf_object *obj; +int bpfprog_fd; +int cgroup_storage_fd; + +static void read_trace_pipe2(void) +{ + int trace_fd; + FILE *outf; + char *outFname = "hbm_out.log"; + + trace_fd = open(DEBUGFS "trace_pipe", O_RDONLY, 0); + if (trace_fd < 0) { + printf("Error opening trace_pipe\n"); + return; + } + +// Future support of ingress +// if (!outFlag) +// outFname = "hbm_in.log"; + outf = fopen(outFname, "w"); + + if (outf == NULL) + printf("Error creating %s\n", outFname); + + while (1) { + static char buf[4097]; + ssize_t sz; + + sz = read(trace_fd, buf, sizeof(buf) - 1); + if (sz > 0) { + buf[sz] = 0; + puts(buf); + if (outf != NULL) { + fprintf(outf, "%s\n", buf); + fflush(outf); + } + } + } +} + +static void do_error(char *msg, bool errno_flag) +{ + if (errno_flag) + printf("ERROR: %s, errno: %d\n", msg, errno); + else + printf("ERROR: %s\n", msg); + exit(1); +} + +static int prog_load(char *prog) +{ + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .file = prog, + .expected_attach_type = BPF_CGROUP_INET_EGRESS, + }; + int map_fd; + struct bpf_map *map; + + int ret = 0; + + if (access(prog, O_RDONLY) < 0) { + printf("Error accessing file %s: %s\n", prog, strerror(errno)); + return 1; + } + if (bpf_prog_load_xattr(&prog_load_attr, &obj, &bpfprog_fd)) + ret = 1; + if (!ret) { + map = bpf_object__find_map_by_name(obj, "queue_stats"); + map_fd = bpf_map__fd(map); + if (map_fd < 0) { + printf("Map not found: %s\n", strerror(map_fd)); + ret = 1; + } + } + + if (ret) { + printf("ERROR: load_bpf_file failed for: %s\n", prog); + printf(" Output from verifier:\n%s\n------\n", bpf_log_buf); + ret = -1; + } else { + ret = map_fd; + } + + return ret; +} + +static int run_bpf_prog(char *prog, int cg_id) +{ + int map_fd; + int rc = 0; + int key = 0; + int cg1 = 0; + int type = BPF_CGROUP_INET_EGRESS; + char cg_dir[100]; + struct hbm_queue_stats qstats = {0}; + + sprintf(cg_dir, "/hbm%d", cg_id); + map_fd = prog_load(prog); + if (map_fd == -1) + return 1; + + if (setup_cgroup_environment()) { + printf("ERROR: setting cgroup environment\n"); + goto err; + } + cg1 = create_and_get_cgroup(cg_dir); + if (!cg1) { + printf("ERROR: create_and_get_cgroup\n"); + goto err; + } + if (join_cgroup(cg_dir)) { + printf("ERROR: join_cgroup\n"); + goto err; + } + + qstats.rate = rate; + qstats.stats = stats_flag ? 1 : 0; + qstats.loopback = loopback_flag ? 1 : 0; + if (bpf_map_update_elem(map_fd, &key, &qstats, BPF_ANY)) { + printf("ERROR: Could not update map element\n"); + goto err; + } + + if (!outFlag) + type = BPF_CGROUP_INET_INGRESS; + if (bpf_prog_attach(bpfprog_fd, cg1, type, 0)) { + printf("ERROR: bpf_prog_attach fails!\n"); + log_err("Attaching prog"); + goto err; + } + + if (work_conserving_flag) { + struct timeval t0, t_last, t_new; + FILE *fin; + unsigned long long last_eth_tx_bytes, new_eth_tx_bytes; + signed long long last_cg_tx_bytes, new_cg_tx_bytes; + signed long long delta_time, delta_bytes, delta_rate; + int delta_ms; +#define DELTA_RATE_CHECK 10000 /* in us */ +#define RATE_THRESHOLD 9500000000 /* 9.5 Gbps */ + + bpf_map_lookup_elem(map_fd, &key, &qstats); + if (gettimeofday(&t0, NULL) < 0) + do_error("gettimeofday failed", true); + t_last = t0; + fin = fopen("/sys/class/net/eth0/statistics/tx_bytes", "r"); + if (fscanf(fin, "%llu", &last_eth_tx_bytes) != 1) + do_error("fscanf fails", false); + fclose(fin); + last_cg_tx_bytes = qstats.bytes_total; + while (true) { + usleep(DELTA_RATE_CHECK); + if (gettimeofday(&t_new, NULL) < 0) + do_error("gettimeofday failed", true); + delta_ms = (t_new.tv_sec - t0.tv_sec) * 1000 + + (t_new.tv_usec - t0.tv_usec)/1000; + if (delta_ms > dur * 1000) + break; + delta_time = (t_new.tv_sec - t_last.tv_sec) * 1000000 + + (t_new.tv_usec - t_last.tv_usec); + if (delta_time == 0) + continue; + t_last = t_new; + fin = fopen("/sys/class/net/eth0/statistics/tx_bytes", + "r"); + if (fscanf(fin, "%llu", &new_eth_tx_bytes) != 1) + do_error("fscanf fails", false); + fclose(fin); + printf(" new_eth_tx_bytes:%llu\n", + new_eth_tx_bytes); + bpf_map_lookup_elem(map_fd, &key, &qstats); + new_cg_tx_bytes = qstats.bytes_total; + delta_bytes = new_eth_tx_bytes - last_eth_tx_bytes; + last_eth_tx_bytes = new_eth_tx_bytes; + delta_rate = (delta_bytes * 8000000) / delta_time; + printf("%5d - eth_rate:%.1fGbps cg_rate:%.3fGbps", + delta_ms, delta_rate/1000000000.0, + rate/1000.0); + if (delta_rate < RATE_THRESHOLD) { + /* can increase cgroup rate limit, but first + * check if we are using the current limit. + * Currently increasing by 6.25%, unknown + * if that is the optimal rate. + */ + int rate_diff100; + + delta_bytes = new_cg_tx_bytes - + last_cg_tx_bytes; + last_cg_tx_bytes = new_cg_tx_bytes; + delta_rate = (delta_bytes * 8000000) / + delta_time; + printf(" rate:%.3fGbps", + delta_rate/1000000000.0); + rate_diff100 = (((long long)rate)*1000000 - + delta_rate) * 100 / + (((long long) rate) * 1000000); + printf(" rdiff:%d", rate_diff100); + if (rate_diff100 <= 3) { + rate += (rate >> 4); + if (rate > RATE_THRESHOLD / 1000000) + rate = RATE_THRESHOLD / 1000000; + qstats.rate = rate; + printf(" INC\n"); + } else { + printf("\n"); + } + } else { + /* Need to decrease cgroup rate limit. + * Currently decreasing by 12.5%, unknown + * if that is optimal + */ + printf(" DEC\n"); + rate -= (rate >> 3); + if (rate < minRate) + rate = minRate; + qstats.rate = rate; + } + if (bpf_map_update_elem(map_fd, &key, &qstats, BPF_ANY)) + do_error("update map element fails", false); + } + } else { + sleep(dur); + } + // Get stats! + if (stats_flag && bpf_map_lookup_elem(map_fd, &key, &qstats)) { + char fname[100]; + FILE *fout; + + if (!outFlag) + sprintf(fname, "hbm.%d.in", cg_id); + else + sprintf(fname, "hbm.%d.out", cg_id); + fout = fopen(fname, "w"); + fprintf(fout, "id:%d\n", cg_id); + fprintf(fout, "ERROR: Could not lookup queue_stats\n"); + } else if (stats_flag && qstats.lastPacketTime > + qstats.firstPacketTime) { + long long delta_us = (qstats.lastPacketTime - + qstats.firstPacketTime)/1000; + unsigned int rate_mbps = ((qstats.bytes_total - + qstats.bytes_dropped) * 8 / + delta_us); + double percent_pkts, percent_bytes; + char fname[100]; + FILE *fout; + +// Future support of ingress +// if (!outFlag) +// sprintf(fname, "hbm.%d.in", cg_id); +// else + sprintf(fname, "hbm.%d.out", cg_id); + fout = fopen(fname, "w"); + fprintf(fout, "id:%d\n", cg_id); + fprintf(fout, "rate_mbps:%d\n", rate_mbps); + fprintf(fout, "duration:%.1f secs\n", + (qstats.lastPacketTime - qstats.firstPacketTime) / + 1000000000.0); + fprintf(fout, "packets:%d\n", (int)qstats.pkts_total); + fprintf(fout, "bytes_MB:%d\n", (int)(qstats.bytes_total / + 1000000)); + fprintf(fout, "pkts_dropped:%d\n", (int)qstats.pkts_dropped); + fprintf(fout, "bytes_dropped_MB:%d\n", + (int)(qstats.bytes_dropped / + 1000000)); + // Marked Pkts and Bytes + percent_pkts = (qstats.pkts_marked * 100.0) / + (qstats.pkts_total + 1); + percent_bytes = (qstats.bytes_marked * 100.0) / + (qstats.bytes_total + 1); + fprintf(fout, "pkts_marked_percent:%6.2f\n", percent_pkts); + fprintf(fout, "bytes_marked_percent:%6.2f\n", percent_bytes); + + // Dropped Pkts and Bytes + percent_pkts = (qstats.pkts_dropped * 100.0) / + (qstats.pkts_total + 1); + percent_bytes = (qstats.bytes_dropped * 100.0) / + (qstats.bytes_total + 1); + fprintf(fout, "pkts_dropped_percent:%6.2f\n", percent_pkts); + fprintf(fout, "bytes_dropped_percent:%6.2f\n", percent_bytes); + fclose(fout); + } + + if (debugFlag) + read_trace_pipe2(); + return rc; +err: + rc = 1; + + if (cg1) + close(cg1); + cleanup_cgroup_environment(); + + return rc; +} + +static void Usage(void) +{ + printf("This program loads a cgroup skb BPF program to enforce\n" + "cgroup output (egress) bandwidth limits.\n\n" + "USAGE: hbm [-o] [-d] [-l] [-n <id>] [-r <rate>] [-s]\n" + " [-t <secs>] [-w] [-h] [prog]\n" + " Where:\n" + " -o indicates egress direction (default)\n" + " -d print BPF trace debug buffer\n" + " -l also limit flows using loopback\n" + " -n <#> to create cgroup \"/hbm#\" and attach prog\n" + " Default is /hbm1\n" + " -r <rate> Rate in Mbps\n" + " -s Update HBM stats\n" + " -t <time> Exit after specified seconds (deault is 0)\n" + " -w Work conserving flag. cgroup can increase\n" + " bandwidth beyond the rate limit specified\n" + " while there is available bandwidth. Current\n" + " implementation assumes there is only eth0\n" + " but can be extended to support multiple NICs\n" + " -h print this info\n" + " prog BPF program file name. Name defaults to\n" + " hbm_out_kern.o\n"); +} + +int main(int argc, char **argv) +{ + char *prog = "hbm_out_kern.o"; + int k; + int cg_id = 1; + char *optstring = "iodln:r:st:wh"; + + while ((k = getopt(argc, argv, optstring)) != -1) { + switch (k) { + case'o': + break; + case 'd': + debugFlag = true; + break; + case 'l': + loopback_flag = true; + break; + case 'n': + cg_id = atoi(optarg); + break; + case 'r': + minRate = atoi(optarg) * 1.024; + rate = minRate; + break; + case 's': + stats_flag = true; + break; + case 't': + dur = atoi(optarg); + break; + case 'w': + work_conserving_flag = true; + break; + case '?': + if (optopt == 'n' || optopt == 'r' || optopt == 't') + fprintf(stderr, + "Option -%c requires an argument.\n\n", + optopt); + case 'h': + // fallthrough + default: + Usage(); + return 0; + } + } + + if (optind < argc) + prog = argv[optind]; + printf("HBM prog: %s\n", prog != NULL ? prog : "NULL"); + + return run_bpf_prog(prog, cg_id); +} diff --git a/samples/bpf/hbm.h b/samples/bpf/hbm.h new file mode 100644 index 000000000000..518e8147d084 --- /dev/null +++ b/samples/bpf/hbm.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright (c) 2019 Facebook + * + * 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. + * + * Include file for Host Bandwidth Management (HBM) programs + */ +struct hbm_vqueue { + struct bpf_spin_lock lock; + /* 4 byte hole */ + unsigned long long lasttime; /* In ns */ + int credit; /* In bytes */ + unsigned int rate; /* In bytes per NS << 20 */ +}; + +struct hbm_queue_stats { + unsigned long rate; /* in Mbps*/ + unsigned long stats:1, /* get HBM stats (marked, dropped,..) */ + loopback:1; /* also limit flows using loopback */ + unsigned long long pkts_marked; + unsigned long long bytes_marked; + unsigned long long pkts_dropped; + unsigned long long bytes_dropped; + unsigned long long pkts_total; + unsigned long long bytes_total; + unsigned long long firstPacketTime; + unsigned long long lastPacketTime; +}; diff --git a/samples/bpf/hbm_kern.h b/samples/bpf/hbm_kern.h new file mode 100644 index 000000000000..c5635d924193 --- /dev/null +++ b/samples/bpf/hbm_kern.h @@ -0,0 +1,137 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright (c) 2019 Facebook + * + * 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. + * + * Include file for sample Host Bandwidth Manager (HBM) BPF programs + */ +#define KBUILD_MODNAME "foo" +#include <stddef.h> +#include <stdbool.h> +#include <uapi/linux/bpf.h> +#include <uapi/linux/if_ether.h> +#include <uapi/linux/if_packet.h> +#include <uapi/linux/ip.h> +#include <uapi/linux/ipv6.h> +#include <uapi/linux/in.h> +#include <uapi/linux/tcp.h> +#include <uapi/linux/filter.h> +#include <uapi/linux/pkt_cls.h> +#include <net/ipv6.h> +#include <net/inet_ecn.h> +#include "bpf_endian.h" +#include "bpf_helpers.h" +#include "hbm.h" + +#define DROP_PKT 0 +#define ALLOW_PKT 1 +#define TCP_ECN_OK 1 + +#define HBM_DEBUG 0 // Set to 1 to enable debugging +#if HBM_DEBUG +#define bpf_printk(fmt, ...) \ +({ \ + char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) +#else +#define bpf_printk(fmt, ...) +#endif + +#define INITIAL_CREDIT_PACKETS 100 +#define MAX_BYTES_PER_PACKET 1500 +#define MARK_THRESH (40 * MAX_BYTES_PER_PACKET) +#define DROP_THRESH (80 * 5 * MAX_BYTES_PER_PACKET) +#define LARGE_PKT_DROP_THRESH (DROP_THRESH - (15 * MAX_BYTES_PER_PACKET)) +#define MARK_REGION_SIZE (LARGE_PKT_DROP_THRESH - MARK_THRESH) +#define LARGE_PKT_THRESH 120 +#define MAX_CREDIT (100 * MAX_BYTES_PER_PACKET) +#define INIT_CREDIT (INITIAL_CREDIT_PACKETS * MAX_BYTES_PER_PACKET) + +// rate in bytes per ns << 20 +#define CREDIT_PER_NS(delta, rate) ((((u64)(delta)) * (rate)) >> 20) + +struct bpf_map_def SEC("maps") queue_state = { + .type = BPF_MAP_TYPE_CGROUP_STORAGE, + .key_size = sizeof(struct bpf_cgroup_storage_key), + .value_size = sizeof(struct hbm_vqueue), +}; +BPF_ANNOTATE_KV_PAIR(queue_state, struct bpf_cgroup_storage_key, + struct hbm_vqueue); + +struct bpf_map_def SEC("maps") queue_stats = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(struct hbm_queue_stats), + .max_entries = 1, +}; +BPF_ANNOTATE_KV_PAIR(queue_stats, int, struct hbm_queue_stats); + +struct hbm_pkt_info { + bool is_ip; + bool is_tcp; + short ecn; +}; + +static __always_inline void hbm_get_pkt_info(struct __sk_buff *skb, + struct hbm_pkt_info *pkti) +{ + struct iphdr iph; + struct ipv6hdr *ip6h; + + bpf_skb_load_bytes(skb, 0, &iph, 12); + if (iph.version == 6) { + ip6h = (struct ipv6hdr *)&iph; + pkti->is_ip = true; + pkti->is_tcp = (ip6h->nexthdr == 6); + pkti->ecn = (ip6h->flow_lbl[0] >> 4) & INET_ECN_MASK; + } else if (iph.version == 4) { + pkti->is_ip = true; + pkti->is_tcp = (iph.protocol == 6); + pkti->ecn = iph.tos & INET_ECN_MASK; + } else { + pkti->is_ip = false; + pkti->is_tcp = false; + pkti->ecn = 0; + } +} + +static __always_inline void hbm_init_vqueue(struct hbm_vqueue *qdp, int rate) +{ + bpf_printk("Initializing queue_state, rate:%d\n", rate * 128); + qdp->lasttime = bpf_ktime_get_ns(); + qdp->credit = INIT_CREDIT; + qdp->rate = rate * 128; +} + +static __always_inline void hbm_update_stats(struct hbm_queue_stats *qsp, + int len, + unsigned long long curtime, + bool congestion_flag, + bool drop_flag) +{ + if (qsp != NULL) { + // Following is needed for work conserving + __sync_add_and_fetch(&(qsp->bytes_total), len); + if (qsp->stats) { + // Optionally update statistics + if (qsp->firstPacketTime == 0) + qsp->firstPacketTime = curtime; + qsp->lastPacketTime = curtime; + __sync_add_and_fetch(&(qsp->pkts_total), 1); + if (congestion_flag || drop_flag) { + __sync_add_and_fetch(&(qsp->pkts_marked), 1); + __sync_add_and_fetch(&(qsp->bytes_marked), len); + } + if (drop_flag) { + __sync_add_and_fetch(&(qsp->pkts_dropped), 1); + __sync_add_and_fetch(&(qsp->bytes_dropped), + len); + } + } + } +} diff --git a/samples/bpf/hbm_out_kern.c b/samples/bpf/hbm_out_kern.c new file mode 100644 index 000000000000..f806863d0b79 --- /dev/null +++ b/samples/bpf/hbm_out_kern.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook + * + * 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. + * + * Sample Host Bandwidth Manager (HBM) BPF program. + * + * A cgroup skb BPF egress program to limit cgroup output bandwidth. + * It uses a modified virtual token bucket queue to limit average + * egress bandwidth. The implementation uses credits instead of tokens. + * Negative credits imply that queueing would have happened (this is + * a virtual queue, so no queueing is done by it. However, queueing may + * occur at the actual qdisc (which is not used for rate limiting). + * + * This implementation uses 3 thresholds, one to start marking packets and + * the other two to drop packets: + * CREDIT + * - <--------------------------|------------------------> + + * | | | 0 + * | Large pkt | + * | drop thresh | + * Small pkt drop Mark threshold + * thresh + * + * The effect of marking depends on the type of packet: + * a) If the packet is ECN enabled and it is a TCP packet, then the packet + * is ECN marked. + * b) If the packet is a TCP packet, then we probabilistically call tcp_cwr + * to reduce the congestion window. The current implementation uses a linear + * distribution (0% probability at marking threshold, 100% probability + * at drop threshold). + * c) If the packet is not a TCP packet, then it is dropped. + * + * If the credit is below the drop threshold, the packet is dropped. If it + * is a TCP packet, then it also calls tcp_cwr since packets dropped by + * by a cgroup skb BPF program do not automatically trigger a call to + * tcp_cwr in the current kernel code. + * + * This BPF program actually uses 2 drop thresholds, one threshold + * for larger packets (>= 120 bytes) and another for smaller packets. This + * protects smaller packets such as SYNs, ACKs, etc. + * + * The default bandwidth limit is set at 1Gbps but this can be changed by + * a user program through a shared BPF map. In addition, by default this BPF + * program does not limit connections using loopback. This behavior can be + * overwritten by the user program. There is also an option to calculate + * some statistics, such as percent of packets marked or dropped, which + * the user program can access. + * + * A latter patch provides such a program (hbm.c) + */ + +#include "hbm_kern.h" + +SEC("cgroup_skb/egress") +int _hbm_out_cg(struct __sk_buff *skb) +{ + struct hbm_pkt_info pkti; + int len = skb->len; + unsigned int queue_index = 0; + unsigned long long curtime; + int credit; + signed long long delta = 0, zero = 0; + int max_credit = MAX_CREDIT; + bool congestion_flag = false; + bool drop_flag = false; + bool cwr_flag = false; + struct hbm_vqueue *qdp; + struct hbm_queue_stats *qsp = NULL; + int rv = ALLOW_PKT; + + qsp = bpf_map_lookup_elem(&queue_stats, &queue_index); + if (qsp != NULL && !qsp->loopback && (skb->ifindex == 1)) + return ALLOW_PKT; + + hbm_get_pkt_info(skb, &pkti); + + // We may want to account for the length of headers in len + // calculation, like ETH header + overhead, specially if it + // is a gso packet. But I am not doing it right now. + + qdp = bpf_get_local_storage(&queue_state, 0); + if (!qdp) + return ALLOW_PKT; + else if (qdp->lasttime == 0) + hbm_init_vqueue(qdp, 1024); + + curtime = bpf_ktime_get_ns(); + + // Begin critical section + bpf_spin_lock(&qdp->lock); + credit = qdp->credit; + delta = curtime - qdp->lasttime; + /* delta < 0 implies that another process with a curtime greater + * than ours beat us to the critical section and already added + * the new credit, so we should not add it ourselves + */ + if (delta > 0) { + qdp->lasttime = curtime; + credit += CREDIT_PER_NS(delta, qdp->rate); + if (credit > MAX_CREDIT) + credit = MAX_CREDIT; + } + credit -= len; + qdp->credit = credit; + bpf_spin_unlock(&qdp->lock); + // End critical section + + // Check if we should update rate + if (qsp != NULL && (qsp->rate * 128) != qdp->rate) { + qdp->rate = qsp->rate * 128; + bpf_printk("Updating rate: %d (1sec:%llu bits)\n", + (int)qdp->rate, + CREDIT_PER_NS(1000000000, qdp->rate) * 8); + } + + // Set flags (drop, congestion, cwr) + // Dropping => we are congested, so ignore congestion flag + if (credit < -DROP_THRESH || + (len > LARGE_PKT_THRESH && + credit < -LARGE_PKT_DROP_THRESH)) { + // Very congested, set drop flag + drop_flag = true; + } else if (credit < 0) { + // Congested, set congestion flag + if (pkti.ecn) { + if (credit < -MARK_THRESH) + congestion_flag = true; + else + congestion_flag = false; + } else { + congestion_flag = true; + } + } + + if (congestion_flag) { + if (!bpf_skb_ecn_set_ce(skb)) { + if (len > LARGE_PKT_THRESH) { + // Problem if too many small packets? + drop_flag = true; + } + } + } + + if (drop_flag) + rv = DROP_PKT; + + hbm_update_stats(qsp, len, curtime, congestion_flag, drop_flag); + + if (rv == DROP_PKT) + __sync_add_and_fetch(&(qdp->credit), len); + + return rv; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/load_sock_ops.c b/samples/bpf/load_sock_ops.c deleted file mode 100644 index 8ecb41ea0c03..000000000000 --- a/samples/bpf/load_sock_ops.c +++ /dev/null @@ -1,97 +0,0 @@ -/* Copyright (c) 2017 Facebook - * - * 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. - */ -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <linux/bpf.h> -#include <bpf/bpf.h> -#include "bpf_load.h" -#include <unistd.h> -#include <errno.h> -#include <fcntl.h> -#include <linux/unistd.h> - -static void usage(char *pname) -{ - printf("USAGE:\n %s [-l] <cg-path> <prog filename>\n", pname); - printf("\tLoad and attach a sock_ops program to the specified " - "cgroup\n"); - printf("\tIf \"-l\" is used, the program will continue to run\n"); - printf("\tprinting the BPF log buffer\n"); - printf("\tIf the specified filename does not end in \".o\", it\n"); - printf("\tappends \"_kern.o\" to the name\n"); - printf("\n"); - printf(" %s -r <cg-path>\n", pname); - printf("\tDetaches the currently attached sock_ops program\n"); - printf("\tfrom the specified cgroup\n"); - printf("\n"); - exit(1); -} - -int main(int argc, char **argv) -{ - int logFlag = 0; - int error = 0; - char *cg_path; - char fn[500]; - char *prog; - int cg_fd; - - if (argc < 3) - usage(argv[0]); - - if (!strcmp(argv[1], "-r")) { - cg_path = argv[2]; - cg_fd = open(cg_path, O_DIRECTORY, O_RDONLY); - error = bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS); - if (error) { - printf("ERROR: bpf_prog_detach: %d (%s)\n", - error, strerror(errno)); - return 2; - } - return 0; - } else if (!strcmp(argv[1], "-h")) { - usage(argv[0]); - } else if (!strcmp(argv[1], "-l")) { - logFlag = 1; - if (argc < 4) - usage(argv[0]); - } - - prog = argv[argc - 1]; - cg_path = argv[argc - 2]; - if (strlen(prog) > 480) { - fprintf(stderr, "ERROR: program name too long (> 480 chars)\n"); - return 3; - } - cg_fd = open(cg_path, O_DIRECTORY, O_RDONLY); - - if (!strcmp(prog + strlen(prog)-2, ".o")) - strcpy(fn, prog); - else - sprintf(fn, "%s_kern.o", prog); - if (logFlag) - printf("loading bpf file:%s\n", fn); - if (load_bpf_file(fn)) { - printf("ERROR: load_bpf_file failed for: %s\n", fn); - printf("%s", bpf_log_buf); - return 4; - } - if (logFlag) - printf("TCP BPF Loaded %s\n", fn); - - error = bpf_prog_attach(prog_fd[0], cg_fd, BPF_CGROUP_SOCK_OPS, 0); - if (error) { - printf("ERROR: bpf_prog_attach: %d (%s)\n", - error, strerror(errno)); - return 5; - } else if (logFlag) { - read_trace_pipe(); - } - - return error; -} diff --git a/samples/bpf/sock_example.c b/samples/bpf/sock_example.c index 60ec467c78ab..00aae1d33fca 100644 --- a/samples/bpf/sock_example.c +++ b/samples/bpf/sock_example.c @@ -99,7 +99,7 @@ int main(void) { FILE *f; - f = popen("ping -c5 localhost", "r"); + f = popen("ping -4 -c5 localhost", "r"); (void)f; return test_sock(); diff --git a/samples/bpf/sockex1_user.c b/samples/bpf/sockex1_user.c index 93ec01c56104..7f90796ae15a 100644 --- a/samples/bpf/sockex1_user.c +++ b/samples/bpf/sockex1_user.c @@ -3,30 +3,33 @@ #include <assert.h> #include <linux/bpf.h> #include <bpf/bpf.h> -#include "bpf_load.h" +#include "bpf/libbpf.h" #include "sock_example.h" #include <unistd.h> #include <arpa/inet.h> int main(int ac, char **argv) { + struct bpf_object *obj; + int map_fd, prog_fd; char filename[256]; - FILE *f; int i, sock; + FILE *f; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); + if (bpf_prog_load(filename, BPF_PROG_TYPE_SOCKET_FILTER, + &obj, &prog_fd)) return 1; - } + + map_fd = bpf_object__find_map_fd_by_name(obj, "my_map"); sock = open_raw_sock("lo"); - assert(setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, prog_fd, - sizeof(prog_fd[0])) == 0); + assert(setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &prog_fd, + sizeof(prog_fd)) == 0); - f = popen("ping -c5 localhost", "r"); + f = popen("ping -4 -c5 localhost", "r"); (void) f; for (i = 0; i < 5; i++) { @@ -34,13 +37,13 @@ int main(int ac, char **argv) int key; key = IPPROTO_TCP; - assert(bpf_map_lookup_elem(map_fd[0], &key, &tcp_cnt) == 0); + assert(bpf_map_lookup_elem(map_fd, &key, &tcp_cnt) == 0); key = IPPROTO_UDP; - assert(bpf_map_lookup_elem(map_fd[0], &key, &udp_cnt) == 0); + assert(bpf_map_lookup_elem(map_fd, &key, &udp_cnt) == 0); key = IPPROTO_ICMP; - assert(bpf_map_lookup_elem(map_fd[0], &key, &icmp_cnt) == 0); + assert(bpf_map_lookup_elem(map_fd, &key, &icmp_cnt) == 0); printf("TCP %lld UDP %lld ICMP %lld bytes\n", tcp_cnt, udp_cnt, icmp_cnt); diff --git a/samples/bpf/sockex2_user.c b/samples/bpf/sockex2_user.c index 1d5c6e9a6d27..bc257333ad92 100644 --- a/samples/bpf/sockex2_user.c +++ b/samples/bpf/sockex2_user.c @@ -3,7 +3,7 @@ #include <assert.h> #include <linux/bpf.h> #include <bpf/bpf.h> -#include "bpf_load.h" +#include "bpf/libbpf.h" #include "sock_example.h" #include <unistd.h> #include <arpa/inet.h> @@ -17,32 +17,35 @@ struct pair { int main(int ac, char **argv) { struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_object *obj; + int map_fd, prog_fd; char filename[256]; - FILE *f; int i, sock; + FILE *f; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); setrlimit(RLIMIT_MEMLOCK, &r); - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); + if (bpf_prog_load(filename, BPF_PROG_TYPE_SOCKET_FILTER, + &obj, &prog_fd)) return 1; - } + + map_fd = bpf_object__find_map_fd_by_name(obj, "hash_map"); sock = open_raw_sock("lo"); - assert(setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, prog_fd, - sizeof(prog_fd[0])) == 0); + assert(setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &prog_fd, + sizeof(prog_fd)) == 0); - f = popen("ping -c5 localhost", "r"); + f = popen("ping -4 -c5 localhost", "r"); (void) f; for (i = 0; i < 5; i++) { int key = 0, next_key; struct pair value; - while (bpf_map_get_next_key(map_fd[0], &key, &next_key) == 0) { - bpf_map_lookup_elem(map_fd[0], &next_key, &value); + while (bpf_map_get_next_key(map_fd, &key, &next_key) == 0) { + bpf_map_lookup_elem(map_fd, &next_key, &value); printf("ip %s bytes %lld packets %lld\n", inet_ntoa((struct in_addr){htonl(next_key)}), value.bytes, value.packets); diff --git a/samples/bpf/sockex3_user.c b/samples/bpf/sockex3_user.c index 9d02e0404719..bbb1cd0666a9 100644 --- a/samples/bpf/sockex3_user.c +++ b/samples/bpf/sockex3_user.c @@ -58,7 +58,7 @@ int main(int argc, char **argv) sizeof(__u32)) == 0); if (argc > 1) - f = popen("ping -c5 localhost", "r"); + f = popen("ping -4 -c5 localhost", "r"); else f = popen("netperf -l 4 localhost", "r"); (void) f; diff --git a/samples/bpf/task_fd_query_kern.c b/samples/bpf/task_fd_query_kern.c index f4b0a9ea674d..fb56fc2a3e5d 100644 --- a/samples/bpf/task_fd_query_kern.c +++ b/samples/bpf/task_fd_query_kern.c @@ -4,7 +4,7 @@ #include <uapi/linux/bpf.h> #include "bpf_helpers.h" -SEC("kprobe/blk_start_request") +SEC("kprobe/blk_mq_start_request") int bpf_prog1(struct pt_regs *ctx) { return 0; diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c index 8381d792f138..aff2b4ae914e 100644 --- a/samples/bpf/task_fd_query_user.c +++ b/samples/bpf/task_fd_query_user.c @@ -311,7 +311,7 @@ int main(int argc, char **argv) } /* test two functions in the corresponding *_kern.c file */ - CHECK_AND_RET(test_debug_fs_kprobe(0, "blk_start_request", + CHECK_AND_RET(test_debug_fs_kprobe(0, "blk_mq_start_request", BPF_FD_TYPE_KPROBE)); CHECK_AND_RET(test_debug_fs_kprobe(1, "blk_account_io_completion", BPF_FD_TYPE_KRETPROBE)); diff --git a/samples/bpf/tcp_basertt_kern.c b/samples/bpf/tcp_basertt_kern.c index 4bf4fc597db9..6ef1625e8b2c 100644 --- a/samples/bpf/tcp_basertt_kern.c +++ b/samples/bpf/tcp_basertt_kern.c @@ -7,7 +7,7 @@ * BPF program to set base_rtt to 80us when host is running TCP-NV and * both hosts are in the same datacenter (as determined by IPv6 prefix). * - * Use load_sock_ops to load this BPF program. + * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program. */ #include <uapi/linux/bpf.h> diff --git a/samples/bpf/tcp_bpf.readme b/samples/bpf/tcp_bpf.readme index 831fb601e3c9..fee746621aec 100644 --- a/samples/bpf/tcp_bpf.readme +++ b/samples/bpf/tcp_bpf.readme @@ -8,14 +8,16 @@ a cgroupv2 and attach a bash shell to the group. bash echo $$ >> /tmp/cgroupv2/foo/cgroup.procs -Anything that runs under this shell belongs to the foo cgroupv2 To load +Anything that runs under this shell belongs to the foo cgroupv2. To load (attach) one of the tcp_*_kern.o programs: - ./load_sock_ops -l /tmp/cgroupv2/foo tcp_basertt_kern.o + bpftool prog load tcp_basertt_kern.o /sys/fs/bpf/tcp_prog + bpftool cgroup attach /tmp/cgroupv2/foo sock_ops pinned /sys/fs/bpf/tcp_prog + bpftool prog tracelog -If the "-l" flag is used, the load_sock_ops program will continue to run -printing the BPF log buffer. The tcp_*_kern.o programs use special print -functions to print logging information (if enabled by the ifdef). +"bpftool prog tracelog" will continue to run printing the BPF log buffer. +The tcp_*_kern.o programs use special print functions to print logging +information (if enabled by the ifdef). If using netperf/netserver to create traffic, you need to run them under the cgroupv2 to which the BPF programs are attached (i.e. under bash shell @@ -23,4 +25,4 @@ attached to the cgroupv2). To remove (unattach) a socket_ops BPF program from a cgroupv2: - ./load_sock_ops -r /tmp/cgroupv2/foo + bpftool cgroup attach /tmp/cgroupv2/foo sock_ops pinned /sys/fs/bpf/tcp_prog diff --git a/samples/bpf/tcp_bufs_kern.c b/samples/bpf/tcp_bufs_kern.c index 0566b7fa38a1..e03e204739fa 100644 --- a/samples/bpf/tcp_bufs_kern.c +++ b/samples/bpf/tcp_bufs_kern.c @@ -9,7 +9,7 @@ * doing appropriate checks that indicate the hosts are far enough * away (i.e. large RTT). * - * Use load_sock_ops to load this BPF program. + * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program. */ #include <uapi/linux/bpf.h> diff --git a/samples/bpf/tcp_clamp_kern.c b/samples/bpf/tcp_clamp_kern.c index f4225c9d2c0c..a0dc2d254aca 100644 --- a/samples/bpf/tcp_clamp_kern.c +++ b/samples/bpf/tcp_clamp_kern.c @@ -9,7 +9,7 @@ * the same datacenter. For his example, we assume they are within the same * datacenter when the first 5.5 bytes of their IPv6 addresses are the same. * - * Use load_sock_ops to load this BPF program. + * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program. */ #include <uapi/linux/bpf.h> diff --git a/samples/bpf/tcp_cong_kern.c b/samples/bpf/tcp_cong_kern.c index ad0f1ba8206a..4fd3ca979a06 100644 --- a/samples/bpf/tcp_cong_kern.c +++ b/samples/bpf/tcp_cong_kern.c @@ -7,7 +7,7 @@ * BPF program to set congestion control to dctcp when both hosts are * in the same datacenter (as deteremined by IPv6 prefix). * - * Use load_sock_ops to load this BPF program. + * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program. */ #include <uapi/linux/bpf.h> diff --git a/samples/bpf/tcp_iw_kern.c b/samples/bpf/tcp_iw_kern.c index 4ca5ecc9f580..9b139ec69560 100644 --- a/samples/bpf/tcp_iw_kern.c +++ b/samples/bpf/tcp_iw_kern.c @@ -9,7 +9,7 @@ * would usually be done after doing appropriate checks that indicate * the hosts are far enough away (i.e. large RTT). * - * Use load_sock_ops to load this BPF program. + * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program. */ #include <uapi/linux/bpf.h> diff --git a/samples/bpf/tcp_rwnd_kern.c b/samples/bpf/tcp_rwnd_kern.c index 09ff65b40b31..cc71ee96e044 100644 --- a/samples/bpf/tcp_rwnd_kern.c +++ b/samples/bpf/tcp_rwnd_kern.c @@ -8,7 +8,7 @@ * and the first 5.5 bytes of the IPv6 addresses are not the same (in this * example that means both hosts are not the same datacenter). * - * Use load_sock_ops to load this BPF program. + * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program. */ #include <uapi/linux/bpf.h> diff --git a/samples/bpf/tcp_synrto_kern.c b/samples/bpf/tcp_synrto_kern.c index 232bb242823e..ca87ed34f896 100644 --- a/samples/bpf/tcp_synrto_kern.c +++ b/samples/bpf/tcp_synrto_kern.c @@ -8,7 +8,7 @@ * and the first 5.5 bytes of the IPv6 addresses are the same (in this example * that means both hosts are in the same datacenter). * - * Use load_sock_ops to load this BPF program. + * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program. */ #include <uapi/linux/bpf.h> diff --git a/samples/bpf/tcp_tos_reflect_kern.c b/samples/bpf/tcp_tos_reflect_kern.c index d51dab19eca6..de788be6f862 100644 --- a/samples/bpf/tcp_tos_reflect_kern.c +++ b/samples/bpf/tcp_tos_reflect_kern.c @@ -4,7 +4,7 @@ * * BPF program to automatically reflect TOS option from received syn packet * - * Use load_sock_ops to load this BPF program. + * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program. */ #include <uapi/linux/bpf.h> diff --git a/samples/bpf/tracex2_user.c b/samples/bpf/tracex2_user.c index 1a81e6a5c2ea..c9544a4ce61a 100644 --- a/samples/bpf/tracex2_user.c +++ b/samples/bpf/tracex2_user.c @@ -131,7 +131,7 @@ int main(int ac, char **argv) signal(SIGTERM, int_exit); /* start 'ping' in the background to have some kfree_skb events */ - f = popen("ping -c5 localhost", "r"); + f = popen("ping -4 -c5 localhost", "r"); (void) f; /* start 'dd' in the background to have plenty of 'write' syscalls */ diff --git a/samples/bpf/tracex3_kern.c b/samples/bpf/tracex3_kern.c index 9974c3d7c18b..ea1d4c19c132 100644 --- a/samples/bpf/tracex3_kern.c +++ b/samples/bpf/tracex3_kern.c @@ -20,7 +20,7 @@ struct bpf_map_def SEC("maps") my_map = { /* kprobe is NOT a stable ABI. If kernel internals change this bpf+kprobe * example will no longer be meaningful */ -SEC("kprobe/blk_start_request") +SEC("kprobe/blk_mq_start_request") int bpf_prog1(struct pt_regs *ctx) { long rq = PT_REGS_PARM1(ctx); diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c index 327226be5a06..1dbe7fd3a1a8 100644 --- a/samples/bpf/xdp_redirect_map_user.c +++ b/samples/bpf/xdp_redirect_map_user.c @@ -57,7 +57,7 @@ static void int_exit(int sig) printf("bpf_get_link_xdp_id failed\n"); exit(1); } - if (prog_id == curr_prog_id) + if (dummy_prog_id == curr_prog_id) bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags); else if (!curr_prog_id) printf("couldn't find a prog id on iface OUT\n"); diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c index a5d8ad3129ed..e9054c0269ff 100644 --- a/samples/bpf/xdp_redirect_user.c +++ b/samples/bpf/xdp_redirect_user.c @@ -57,7 +57,7 @@ static void int_exit(int sig) printf("bpf_get_link_xdp_id failed\n"); exit(1); } - if (prog_id == curr_prog_id) + if (dummy_prog_id == curr_prog_id) bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags); else if (!curr_prog_id) printf("couldn't find a prog id on iface OUT\n"); diff --git a/samples/bpf/xdpsock.h b/samples/bpf/xdpsock.h deleted file mode 100644 index 533ab81adfa1..000000000000 --- a/samples/bpf/xdpsock.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef XDPSOCK_H_ -#define XDPSOCK_H_ - -/* Power-of-2 number of sockets */ -#define MAX_SOCKS 4 - -/* Round-robin receive */ -#define RR_LB 0 - -#endif /* XDPSOCK_H_ */ diff --git a/samples/bpf/xdpsock_kern.c b/samples/bpf/xdpsock_kern.c deleted file mode 100644 index b8ccd0802b3f..000000000000 --- a/samples/bpf/xdpsock_kern.c +++ /dev/null @@ -1,56 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#define KBUILD_MODNAME "foo" -#include <uapi/linux/bpf.h> -#include "bpf_helpers.h" - -#include "xdpsock.h" - -struct bpf_map_def SEC("maps") qidconf_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 1, -}; - -struct bpf_map_def SEC("maps") xsks_map = { - .type = BPF_MAP_TYPE_XSKMAP, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = MAX_SOCKS, -}; - -struct bpf_map_def SEC("maps") rr_map = { - .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(unsigned int), - .max_entries = 1, -}; - -SEC("xdp_sock") -int xdp_sock_prog(struct xdp_md *ctx) -{ - int *qidconf, key = 0, idx; - unsigned int *rr; - - qidconf = bpf_map_lookup_elem(&qidconf_map, &key); - if (!qidconf) - return XDP_ABORTED; - - if (*qidconf != ctx->rx_queue_index) - return XDP_PASS; - -#if RR_LB /* NB! RR_LB is configured in xdpsock.h */ - rr = bpf_map_lookup_elem(&rr_map, &key); - if (!rr) - return XDP_ABORTED; - - *rr = (*rr + 1) & (MAX_SOCKS - 1); - idx = *rr; -#else - idx = 0; -#endif - - return bpf_redirect_map(&xsks_map, idx, 0); -} - -char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index f73055e0191f..d08ee1ab7bb4 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -1,37 +1,36 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2017 - 2018 Intel Corporation. */ -#include <assert.h> +#include <asm/barrier.h> #include <errno.h> #include <getopt.h> #include <libgen.h> #include <linux/bpf.h> +#include <linux/compiler.h> #include <linux/if_link.h> #include <linux/if_xdp.h> #include <linux/if_ether.h> +#include <locale.h> +#include <net/ethernet.h> #include <net/if.h> +#include <poll.h> +#include <pthread.h> #include <signal.h> #include <stdbool.h> #include <stdio.h> #include <stdlib.h> #include <string.h> -#include <net/ethernet.h> +#include <sys/mman.h> #include <sys/resource.h> #include <sys/socket.h> -#include <sys/mman.h> +#include <sys/types.h> #include <time.h> #include <unistd.h> -#include <pthread.h> -#include <locale.h> -#include <sys/types.h> -#include <poll.h> #include "bpf/libbpf.h" -#include "bpf_util.h" +#include "bpf/xsk.h" #include <bpf/bpf.h> -#include "xdpsock.h" - #ifndef SOL_XDP #define SOL_XDP 283 #endif @@ -44,17 +43,11 @@ #define PF_XDP AF_XDP #endif -#define NUM_FRAMES 131072 -#define FRAME_HEADROOM 0 -#define FRAME_SHIFT 11 -#define FRAME_SIZE 2048 -#define NUM_DESCS 1024 -#define BATCH_SIZE 16 - -#define FQ_NUM_DESCS 1024 -#define CQ_NUM_DESCS 1024 +#define NUM_FRAMES (4 * 1024) +#define BATCH_SIZE 64 #define DEBUG_HEXDUMP 0 +#define MAX_SOCKS 8 typedef __u64 u64; typedef __u32 u32; @@ -73,54 +66,31 @@ static const char *opt_if = ""; static int opt_ifindex; static int opt_queue; static int opt_poll; -static int opt_shared_packet_buffer; static int opt_interval = 1; static u32 opt_xdp_bind_flags; static __u32 prog_id; -struct xdp_umem_uqueue { - u32 cached_prod; - u32 cached_cons; - u32 mask; - u32 size; - u32 *producer; - u32 *consumer; - u64 *ring; - void *map; +struct xsk_umem_info { + struct xsk_ring_prod fq; + struct xsk_ring_cons cq; + struct xsk_umem *umem; + void *buffer; }; -struct xdp_umem { - char *frames; - struct xdp_umem_uqueue fq; - struct xdp_umem_uqueue cq; - int fd; -}; - -struct xdp_uqueue { - u32 cached_prod; - u32 cached_cons; - u32 mask; - u32 size; - u32 *producer; - u32 *consumer; - struct xdp_desc *ring; - void *map; -}; - -struct xdpsock { - struct xdp_uqueue rx; - struct xdp_uqueue tx; - int sfd; - struct xdp_umem *umem; - u32 outstanding_tx; +struct xsk_socket_info { + struct xsk_ring_cons rx; + struct xsk_ring_prod tx; + struct xsk_umem_info *umem; + struct xsk_socket *xsk; unsigned long rx_npkts; unsigned long tx_npkts; unsigned long prev_rx_npkts; unsigned long prev_tx_npkts; + u32 outstanding_tx; }; static int num_socks; -struct xdpsock *xsks[MAX_SOCKS]; +struct xsk_socket_info *xsks[MAX_SOCKS]; static unsigned long get_nsecs(void) { @@ -130,225 +100,124 @@ static unsigned long get_nsecs(void) return ts.tv_sec * 1000000000UL + ts.tv_nsec; } -static void dump_stats(void); - -#define lassert(expr) \ - do { \ - if (!(expr)) { \ - fprintf(stderr, "%s:%s:%i: Assertion failed: " \ - #expr ": errno: %d/\"%s\"\n", \ - __FILE__, __func__, __LINE__, \ - errno, strerror(errno)); \ - dump_stats(); \ - exit(EXIT_FAILURE); \ - } \ - } while (0) - -#define barrier() __asm__ __volatile__("": : :"memory") -#ifdef __aarch64__ -#define u_smp_rmb() __asm__ __volatile__("dmb ishld": : :"memory") -#define u_smp_wmb() __asm__ __volatile__("dmb ishst": : :"memory") -#else -#define u_smp_rmb() barrier() -#define u_smp_wmb() barrier() -#endif -#define likely(x) __builtin_expect(!!(x), 1) -#define unlikely(x) __builtin_expect(!!(x), 0) - -static const char pkt_data[] = - "\x3c\xfd\xfe\x9e\x7f\x71\xec\xb1\xd7\x98\x3a\xc0\x08\x00\x45\x00" - "\x00\x2e\x00\x00\x00\x00\x40\x11\x88\x97\x05\x08\x07\x08\xc8\x14" - "\x1e\x04\x10\x92\x10\x92\x00\x1a\x6d\xa3\x34\x33\x1f\x69\x40\x6b" - "\x54\x59\xb6\x14\x2d\x11\x44\xbf\xaf\xd9\xbe\xaa"; - -static inline u32 umem_nb_free(struct xdp_umem_uqueue *q, u32 nb) -{ - u32 free_entries = q->cached_cons - q->cached_prod; - - if (free_entries >= nb) - return free_entries; - - /* Refresh the local tail pointer */ - q->cached_cons = *q->consumer + q->size; - - return q->cached_cons - q->cached_prod; -} - -static inline u32 xq_nb_free(struct xdp_uqueue *q, u32 ndescs) +static void print_benchmark(bool running) { - u32 free_entries = q->cached_cons - q->cached_prod; + const char *bench_str = "INVALID"; - if (free_entries >= ndescs) - return free_entries; + if (opt_bench == BENCH_RXDROP) + bench_str = "rxdrop"; + else if (opt_bench == BENCH_TXONLY) + bench_str = "txonly"; + else if (opt_bench == BENCH_L2FWD) + bench_str = "l2fwd"; - /* Refresh the local tail pointer */ - q->cached_cons = *q->consumer + q->size; - return q->cached_cons - q->cached_prod; -} + printf("%s:%d %s ", opt_if, opt_queue, bench_str); + if (opt_xdp_flags & XDP_FLAGS_SKB_MODE) + printf("xdp-skb "); + else if (opt_xdp_flags & XDP_FLAGS_DRV_MODE) + printf("xdp-drv "); + else + printf(" "); -static inline u32 umem_nb_avail(struct xdp_umem_uqueue *q, u32 nb) -{ - u32 entries = q->cached_prod - q->cached_cons; + if (opt_poll) + printf("poll() "); - if (entries == 0) { - q->cached_prod = *q->producer; - entries = q->cached_prod - q->cached_cons; + if (running) { + printf("running..."); + fflush(stdout); } - - return (entries > nb) ? nb : entries; } -static inline u32 xq_nb_avail(struct xdp_uqueue *q, u32 ndescs) +static void dump_stats(void) { - u32 entries = q->cached_prod - q->cached_cons; + unsigned long now = get_nsecs(); + long dt = now - prev_time; + int i; - if (entries == 0) { - q->cached_prod = *q->producer; - entries = q->cached_prod - q->cached_cons; - } + prev_time = now; - return (entries > ndescs) ? ndescs : entries; -} + for (i = 0; i < num_socks && xsks[i]; i++) { + char *fmt = "%-15s %'-11.0f %'-11lu\n"; + double rx_pps, tx_pps; -static inline int umem_fill_to_kernel_ex(struct xdp_umem_uqueue *fq, - struct xdp_desc *d, - size_t nb) -{ - u32 i; + rx_pps = (xsks[i]->rx_npkts - xsks[i]->prev_rx_npkts) * + 1000000000. / dt; + tx_pps = (xsks[i]->tx_npkts - xsks[i]->prev_tx_npkts) * + 1000000000. / dt; - if (umem_nb_free(fq, nb) < nb) - return -ENOSPC; + printf("\n sock%d@", i); + print_benchmark(false); + printf("\n"); - for (i = 0; i < nb; i++) { - u32 idx = fq->cached_prod++ & fq->mask; + printf("%-15s %-11s %-11s %-11.2f\n", "", "pps", "pkts", + dt / 1000000000.); + printf(fmt, "rx", rx_pps, xsks[i]->rx_npkts); + printf(fmt, "tx", tx_pps, xsks[i]->tx_npkts); - fq->ring[idx] = d[i].addr; + xsks[i]->prev_rx_npkts = xsks[i]->rx_npkts; + xsks[i]->prev_tx_npkts = xsks[i]->tx_npkts; } - - u_smp_wmb(); - - *fq->producer = fq->cached_prod; - - return 0; } -static inline int umem_fill_to_kernel(struct xdp_umem_uqueue *fq, u64 *d, - size_t nb) +static void *poller(void *arg) { - u32 i; - - if (umem_nb_free(fq, nb) < nb) - return -ENOSPC; - - for (i = 0; i < nb; i++) { - u32 idx = fq->cached_prod++ & fq->mask; - - fq->ring[idx] = d[i]; + (void)arg; + for (;;) { + sleep(opt_interval); + dump_stats(); } - u_smp_wmb(); - - *fq->producer = fq->cached_prod; - - return 0; + return NULL; } -static inline size_t umem_complete_from_kernel(struct xdp_umem_uqueue *cq, - u64 *d, size_t nb) +static void remove_xdp_program(void) { - u32 idx, i, entries = umem_nb_avail(cq, nb); - - u_smp_rmb(); - - for (i = 0; i < entries; i++) { - idx = cq->cached_cons++ & cq->mask; - d[i] = cq->ring[idx]; - } - - if (entries > 0) { - u_smp_wmb(); + __u32 curr_prog_id = 0; - *cq->consumer = cq->cached_cons; + if (bpf_get_link_xdp_id(opt_ifindex, &curr_prog_id, opt_xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(EXIT_FAILURE); } - - return entries; -} - -static inline void *xq_get_data(struct xdpsock *xsk, u64 addr) -{ - return &xsk->umem->frames[addr]; + if (prog_id == curr_prog_id) + bpf_set_link_xdp_fd(opt_ifindex, -1, opt_xdp_flags); + else if (!curr_prog_id) + printf("couldn't find a prog id on a given interface\n"); + else + printf("program on interface changed, not removing\n"); } -static inline int xq_enq(struct xdp_uqueue *uq, - const struct xdp_desc *descs, - unsigned int ndescs) +static void int_exit(int sig) { - struct xdp_desc *r = uq->ring; - unsigned int i; + struct xsk_umem *umem = xsks[0]->umem->umem; - if (xq_nb_free(uq, ndescs) < ndescs) - return -ENOSPC; - - for (i = 0; i < ndescs; i++) { - u32 idx = uq->cached_prod++ & uq->mask; - - r[idx].addr = descs[i].addr; - r[idx].len = descs[i].len; - } + (void)sig; - u_smp_wmb(); + dump_stats(); + xsk_socket__delete(xsks[0]->xsk); + (void)xsk_umem__delete(umem); + remove_xdp_program(); - *uq->producer = uq->cached_prod; - return 0; + exit(EXIT_SUCCESS); } -static inline int xq_enq_tx_only(struct xdp_uqueue *uq, - unsigned int id, unsigned int ndescs) +static void __exit_with_error(int error, const char *file, const char *func, + int line) { - struct xdp_desc *r = uq->ring; - unsigned int i; - - if (xq_nb_free(uq, ndescs) < ndescs) - return -ENOSPC; - - for (i = 0; i < ndescs; i++) { - u32 idx = uq->cached_prod++ & uq->mask; - - r[idx].addr = (id + i) << FRAME_SHIFT; - r[idx].len = sizeof(pkt_data) - 1; - } - - u_smp_wmb(); - - *uq->producer = uq->cached_prod; - return 0; + fprintf(stderr, "%s:%s:%i: errno: %d/\"%s\"\n", file, func, + line, error, strerror(error)); + dump_stats(); + remove_xdp_program(); + exit(EXIT_FAILURE); } -static inline int xq_deq(struct xdp_uqueue *uq, - struct xdp_desc *descs, - int ndescs) -{ - struct xdp_desc *r = uq->ring; - unsigned int idx; - int i, entries; - - entries = xq_nb_avail(uq, ndescs); - - u_smp_rmb(); - - for (i = 0; i < entries; i++) { - idx = uq->cached_cons++ & uq->mask; - descs[i] = r[idx]; - } - - if (entries > 0) { - u_smp_wmb(); +#define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, \ + __LINE__) - *uq->consumer = uq->cached_cons; - } - - return entries; -} +static const char pkt_data[] = + "\x3c\xfd\xfe\x9e\x7f\x71\xec\xb1\xd7\x98\x3a\xc0\x08\x00\x45\x00" + "\x00\x2e\x00\x00\x00\x00\x40\x11\x88\x97\x05\x08\x07\x08\xc8\x14" + "\x1e\x04\x10\x92\x10\x92\x00\x1a\x6d\xa3\x34\x33\x1f\x69\x40\x6b" + "\x54\x59\xb6\x14\x2d\x11\x44\xbf\xaf\xd9\xbe\xaa"; static void swap_mac_addresses(void *data) { @@ -397,258 +266,74 @@ static void hex_dump(void *pkt, size_t length, u64 addr) printf("\n"); } -static size_t gen_eth_frame(char *frame) +static size_t gen_eth_frame(struct xsk_umem_info *umem, u64 addr) { - memcpy(frame, pkt_data, sizeof(pkt_data) - 1); + memcpy(xsk_umem__get_data(umem->buffer, addr), pkt_data, + sizeof(pkt_data) - 1); return sizeof(pkt_data) - 1; } -static struct xdp_umem *xdp_umem_configure(int sfd) +static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size) { - int fq_size = FQ_NUM_DESCS, cq_size = CQ_NUM_DESCS; - struct xdp_mmap_offsets off; - struct xdp_umem_reg mr; - struct xdp_umem *umem; - socklen_t optlen; - void *bufs; + struct xsk_umem_info *umem; + int ret; umem = calloc(1, sizeof(*umem)); - lassert(umem); - - lassert(posix_memalign(&bufs, getpagesize(), /* PAGE_SIZE aligned */ - NUM_FRAMES * FRAME_SIZE) == 0); - - mr.addr = (__u64)bufs; - mr.len = NUM_FRAMES * FRAME_SIZE; - mr.chunk_size = FRAME_SIZE; - mr.headroom = FRAME_HEADROOM; - - lassert(setsockopt(sfd, SOL_XDP, XDP_UMEM_REG, &mr, sizeof(mr)) == 0); - lassert(setsockopt(sfd, SOL_XDP, XDP_UMEM_FILL_RING, &fq_size, - sizeof(int)) == 0); - lassert(setsockopt(sfd, SOL_XDP, XDP_UMEM_COMPLETION_RING, &cq_size, - sizeof(int)) == 0); - - optlen = sizeof(off); - lassert(getsockopt(sfd, SOL_XDP, XDP_MMAP_OFFSETS, &off, - &optlen) == 0); - - umem->fq.map = mmap(0, off.fr.desc + - FQ_NUM_DESCS * sizeof(u64), - PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, sfd, - XDP_UMEM_PGOFF_FILL_RING); - lassert(umem->fq.map != MAP_FAILED); - - umem->fq.mask = FQ_NUM_DESCS - 1; - umem->fq.size = FQ_NUM_DESCS; - umem->fq.producer = umem->fq.map + off.fr.producer; - umem->fq.consumer = umem->fq.map + off.fr.consumer; - umem->fq.ring = umem->fq.map + off.fr.desc; - umem->fq.cached_cons = FQ_NUM_DESCS; - - umem->cq.map = mmap(0, off.cr.desc + - CQ_NUM_DESCS * sizeof(u64), - PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, sfd, - XDP_UMEM_PGOFF_COMPLETION_RING); - lassert(umem->cq.map != MAP_FAILED); - - umem->cq.mask = CQ_NUM_DESCS - 1; - umem->cq.size = CQ_NUM_DESCS; - umem->cq.producer = umem->cq.map + off.cr.producer; - umem->cq.consumer = umem->cq.map + off.cr.consumer; - umem->cq.ring = umem->cq.map + off.cr.desc; - - umem->frames = bufs; - umem->fd = sfd; + if (!umem) + exit_with_error(errno); - if (opt_bench == BENCH_TXONLY) { - int i; - - for (i = 0; i < NUM_FRAMES * FRAME_SIZE; i += FRAME_SIZE) - (void)gen_eth_frame(&umem->frames[i]); - } + ret = xsk_umem__create(&umem->umem, buffer, size, &umem->fq, &umem->cq, + NULL); + if (ret) + exit_with_error(-ret); + umem->buffer = buffer; return umem; } -static struct xdpsock *xsk_configure(struct xdp_umem *umem) +static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem) { - struct sockaddr_xdp sxdp = {}; - struct xdp_mmap_offsets off; - int sfd, ndescs = NUM_DESCS; - struct xdpsock *xsk; - bool shared = true; - socklen_t optlen; - u64 i; - - sfd = socket(PF_XDP, SOCK_RAW, 0); - lassert(sfd >= 0); + struct xsk_socket_config cfg; + struct xsk_socket_info *xsk; + int ret; + u32 idx; + int i; xsk = calloc(1, sizeof(*xsk)); - lassert(xsk); - - xsk->sfd = sfd; - xsk->outstanding_tx = 0; - - if (!umem) { - shared = false; - xsk->umem = xdp_umem_configure(sfd); - } else { - xsk->umem = umem; - } - - lassert(setsockopt(sfd, SOL_XDP, XDP_RX_RING, - &ndescs, sizeof(int)) == 0); - lassert(setsockopt(sfd, SOL_XDP, XDP_TX_RING, - &ndescs, sizeof(int)) == 0); - optlen = sizeof(off); - lassert(getsockopt(sfd, SOL_XDP, XDP_MMAP_OFFSETS, &off, - &optlen) == 0); - - /* Rx */ - xsk->rx.map = mmap(NULL, - off.rx.desc + - NUM_DESCS * sizeof(struct xdp_desc), - PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, sfd, - XDP_PGOFF_RX_RING); - lassert(xsk->rx.map != MAP_FAILED); - - if (!shared) { - for (i = 0; i < NUM_DESCS * FRAME_SIZE; i += FRAME_SIZE) - lassert(umem_fill_to_kernel(&xsk->umem->fq, &i, 1) - == 0); - } - - /* Tx */ - xsk->tx.map = mmap(NULL, - off.tx.desc + - NUM_DESCS * sizeof(struct xdp_desc), - PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, sfd, - XDP_PGOFF_TX_RING); - lassert(xsk->tx.map != MAP_FAILED); - - xsk->rx.mask = NUM_DESCS - 1; - xsk->rx.size = NUM_DESCS; - xsk->rx.producer = xsk->rx.map + off.rx.producer; - xsk->rx.consumer = xsk->rx.map + off.rx.consumer; - xsk->rx.ring = xsk->rx.map + off.rx.desc; - - xsk->tx.mask = NUM_DESCS - 1; - xsk->tx.size = NUM_DESCS; - xsk->tx.producer = xsk->tx.map + off.tx.producer; - xsk->tx.consumer = xsk->tx.map + off.tx.consumer; - xsk->tx.ring = xsk->tx.map + off.tx.desc; - xsk->tx.cached_cons = NUM_DESCS; - - sxdp.sxdp_family = PF_XDP; - sxdp.sxdp_ifindex = opt_ifindex; - sxdp.sxdp_queue_id = opt_queue; - - if (shared) { - sxdp.sxdp_flags = XDP_SHARED_UMEM; - sxdp.sxdp_shared_umem_fd = umem->fd; - } else { - sxdp.sxdp_flags = opt_xdp_bind_flags; - } - - lassert(bind(sfd, (struct sockaddr *)&sxdp, sizeof(sxdp)) == 0); + if (!xsk) + exit_with_error(errno); + + xsk->umem = umem; + cfg.rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS; + cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; + cfg.libbpf_flags = 0; + cfg.xdp_flags = opt_xdp_flags; + cfg.bind_flags = opt_xdp_bind_flags; + ret = xsk_socket__create(&xsk->xsk, opt_if, opt_queue, umem->umem, + &xsk->rx, &xsk->tx, &cfg); + if (ret) + exit_with_error(-ret); + + ret = bpf_get_link_xdp_id(opt_ifindex, &prog_id, opt_xdp_flags); + if (ret) + exit_with_error(-ret); + + ret = xsk_ring_prod__reserve(&xsk->umem->fq, + XSK_RING_PROD__DEFAULT_NUM_DESCS, + &idx); + if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS) + exit_with_error(-ret); + for (i = 0; + i < XSK_RING_PROD__DEFAULT_NUM_DESCS * + XSK_UMEM__DEFAULT_FRAME_SIZE; + i += XSK_UMEM__DEFAULT_FRAME_SIZE) + *xsk_ring_prod__fill_addr(&xsk->umem->fq, idx++) = i; + xsk_ring_prod__submit(&xsk->umem->fq, + XSK_RING_PROD__DEFAULT_NUM_DESCS); return xsk; } -static void print_benchmark(bool running) -{ - const char *bench_str = "INVALID"; - - if (opt_bench == BENCH_RXDROP) - bench_str = "rxdrop"; - else if (opt_bench == BENCH_TXONLY) - bench_str = "txonly"; - else if (opt_bench == BENCH_L2FWD) - bench_str = "l2fwd"; - - printf("%s:%d %s ", opt_if, opt_queue, bench_str); - if (opt_xdp_flags & XDP_FLAGS_SKB_MODE) - printf("xdp-skb "); - else if (opt_xdp_flags & XDP_FLAGS_DRV_MODE) - printf("xdp-drv "); - else - printf(" "); - - if (opt_poll) - printf("poll() "); - - if (running) { - printf("running..."); - fflush(stdout); - } -} - -static void dump_stats(void) -{ - unsigned long now = get_nsecs(); - long dt = now - prev_time; - int i; - - prev_time = now; - - for (i = 0; i < num_socks && xsks[i]; i++) { - char *fmt = "%-15s %'-11.0f %'-11lu\n"; - double rx_pps, tx_pps; - - rx_pps = (xsks[i]->rx_npkts - xsks[i]->prev_rx_npkts) * - 1000000000. / dt; - tx_pps = (xsks[i]->tx_npkts - xsks[i]->prev_tx_npkts) * - 1000000000. / dt; - - printf("\n sock%d@", i); - print_benchmark(false); - printf("\n"); - - printf("%-15s %-11s %-11s %-11.2f\n", "", "pps", "pkts", - dt / 1000000000.); - printf(fmt, "rx", rx_pps, xsks[i]->rx_npkts); - printf(fmt, "tx", tx_pps, xsks[i]->tx_npkts); - - xsks[i]->prev_rx_npkts = xsks[i]->rx_npkts; - xsks[i]->prev_tx_npkts = xsks[i]->tx_npkts; - } -} - -static void *poller(void *arg) -{ - (void)arg; - for (;;) { - sleep(opt_interval); - dump_stats(); - } - - return NULL; -} - -static void int_exit(int sig) -{ - __u32 curr_prog_id = 0; - - (void)sig; - dump_stats(); - if (bpf_get_link_xdp_id(opt_ifindex, &curr_prog_id, opt_xdp_flags)) { - printf("bpf_get_link_xdp_id failed\n"); - exit(EXIT_FAILURE); - } - if (prog_id == curr_prog_id) - bpf_set_link_xdp_fd(opt_ifindex, -1, opt_xdp_flags); - else if (!curr_prog_id) - printf("couldn't find a prog id on a given interface\n"); - else - printf("program on interface changed, not removing\n"); - exit(EXIT_SUCCESS); -} - static struct option long_options[] = { {"rxdrop", no_argument, 0, 'r'}, {"txonly", no_argument, 0, 't'}, @@ -656,7 +341,6 @@ static struct option long_options[] = { {"interface", required_argument, 0, 'i'}, {"queue", required_argument, 0, 'q'}, {"poll", no_argument, 0, 'p'}, - {"shared-buffer", no_argument, 0, 's'}, {"xdp-skb", no_argument, 0, 'S'}, {"xdp-native", no_argument, 0, 'N'}, {"interval", required_argument, 0, 'n'}, @@ -676,7 +360,6 @@ static void usage(const char *prog) " -i, --interface=n Run on interface n\n" " -q, --queue=n Use queue n (default 0)\n" " -p, --poll Use poll syscall\n" - " -s, --shared-buffer Use shared packet buffer\n" " -S, --xdp-skb=n Use XDP skb-mod\n" " -N, --xdp-native=n Enfore XDP native mode\n" " -n, --interval=n Specify statistics update interval (default 1 sec).\n" @@ -715,9 +398,6 @@ static void parse_command_line(int argc, char **argv) case 'q': opt_queue = atoi(optarg); break; - case 's': - opt_shared_packet_buffer = 1; - break; case 'p': opt_poll = 1; break; @@ -751,75 +431,104 @@ static void parse_command_line(int argc, char **argv) opt_if); usage(basename(argv[0])); } + } -static void kick_tx(int fd) +static void kick_tx(struct xsk_socket_info *xsk) { int ret; - ret = sendto(fd, NULL, 0, MSG_DONTWAIT, NULL, 0); + ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN || errno == EBUSY) return; - lassert(0); + exit_with_error(errno); } -static inline void complete_tx_l2fwd(struct xdpsock *xsk) +static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk) { - u64 descs[BATCH_SIZE]; + u32 idx_cq = 0, idx_fq = 0; unsigned int rcvd; size_t ndescs; if (!xsk->outstanding_tx) return; - kick_tx(xsk->sfd); + kick_tx(xsk); ndescs = (xsk->outstanding_tx > BATCH_SIZE) ? BATCH_SIZE : - xsk->outstanding_tx; + xsk->outstanding_tx; /* re-add completed Tx buffers */ - rcvd = umem_complete_from_kernel(&xsk->umem->cq, descs, ndescs); + rcvd = xsk_ring_cons__peek(&xsk->umem->cq, ndescs, &idx_cq); if (rcvd > 0) { - umem_fill_to_kernel(&xsk->umem->fq, descs, rcvd); + unsigned int i; + int ret; + + ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); + while (ret != rcvd) { + if (ret < 0) + exit_with_error(-ret); + ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, + &idx_fq); + } + for (i = 0; i < rcvd; i++) + *xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = + *xsk_ring_cons__comp_addr(&xsk->umem->cq, + idx_cq++); + + xsk_ring_prod__submit(&xsk->umem->fq, rcvd); + xsk_ring_cons__release(&xsk->umem->cq, rcvd); xsk->outstanding_tx -= rcvd; xsk->tx_npkts += rcvd; } } -static inline void complete_tx_only(struct xdpsock *xsk) +static inline void complete_tx_only(struct xsk_socket_info *xsk) { - u64 descs[BATCH_SIZE]; unsigned int rcvd; + u32 idx; if (!xsk->outstanding_tx) return; - kick_tx(xsk->sfd); + kick_tx(xsk); - rcvd = umem_complete_from_kernel(&xsk->umem->cq, descs, BATCH_SIZE); + rcvd = xsk_ring_cons__peek(&xsk->umem->cq, BATCH_SIZE, &idx); if (rcvd > 0) { + xsk_ring_cons__release(&xsk->umem->cq, rcvd); xsk->outstanding_tx -= rcvd; xsk->tx_npkts += rcvd; } } -static void rx_drop(struct xdpsock *xsk) +static void rx_drop(struct xsk_socket_info *xsk) { - struct xdp_desc descs[BATCH_SIZE]; unsigned int rcvd, i; + u32 idx_rx = 0, idx_fq = 0; + int ret; - rcvd = xq_deq(&xsk->rx, descs, BATCH_SIZE); + rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx); if (!rcvd) return; + ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); + while (ret != rcvd) { + if (ret < 0) + exit_with_error(-ret); + ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); + } + for (i = 0; i < rcvd; i++) { - char *pkt = xq_get_data(xsk, descs[i].addr); + u64 addr = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx)->addr; + u32 len = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++)->len; + char *pkt = xsk_umem__get_data(xsk->umem->buffer, addr); - hex_dump(pkt, descs[i].len, descs[i].addr); + hex_dump(pkt, len, addr); + *xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = addr; } + xsk_ring_prod__submit(&xsk->umem->fq, rcvd); + xsk_ring_cons__release(&xsk->rx, rcvd); xsk->rx_npkts += rcvd; - - umem_fill_to_kernel_ex(&xsk->umem->fq, descs, rcvd); } static void rx_drop_all(void) @@ -830,7 +539,7 @@ static void rx_drop_all(void) memset(fds, 0, sizeof(fds)); for (i = 0; i < num_socks; i++) { - fds[i].fd = xsks[i]->sfd; + fds[i].fd = xsk_socket__fd(xsks[i]->xsk); fds[i].events = POLLIN; timeout = 1000; /* 1sn */ } @@ -847,14 +556,14 @@ static void rx_drop_all(void) } } -static void tx_only(struct xdpsock *xsk) +static void tx_only(struct xsk_socket_info *xsk) { int timeout, ret, nfds = 1; struct pollfd fds[nfds + 1]; - unsigned int idx = 0; + u32 idx, frame_nb = 0; memset(fds, 0, sizeof(fds)); - fds[0].fd = xsk->sfd; + fds[0].fd = xsk_socket__fd(xsk->xsk); fds[0].events = POLLOUT; timeout = 1000; /* 1sn */ @@ -864,50 +573,73 @@ static void tx_only(struct xdpsock *xsk) if (ret <= 0) continue; - if (fds[0].fd != xsk->sfd || - !(fds[0].revents & POLLOUT)) + if (!(fds[0].revents & POLLOUT)) continue; } - if (xq_nb_free(&xsk->tx, BATCH_SIZE) >= BATCH_SIZE) { - lassert(xq_enq_tx_only(&xsk->tx, idx, BATCH_SIZE) == 0); + if (xsk_ring_prod__reserve(&xsk->tx, BATCH_SIZE, &idx) == + BATCH_SIZE) { + unsigned int i; + for (i = 0; i < BATCH_SIZE; i++) { + xsk_ring_prod__tx_desc(&xsk->tx, idx + i)->addr + = (frame_nb + i) << + XSK_UMEM__DEFAULT_FRAME_SHIFT; + xsk_ring_prod__tx_desc(&xsk->tx, idx + i)->len = + sizeof(pkt_data) - 1; + } + + xsk_ring_prod__submit(&xsk->tx, BATCH_SIZE); xsk->outstanding_tx += BATCH_SIZE; - idx += BATCH_SIZE; - idx %= NUM_FRAMES; + frame_nb += BATCH_SIZE; + frame_nb %= NUM_FRAMES; } complete_tx_only(xsk); } } -static void l2fwd(struct xdpsock *xsk) +static void l2fwd(struct xsk_socket_info *xsk) { for (;;) { - struct xdp_desc descs[BATCH_SIZE]; unsigned int rcvd, i; + u32 idx_rx = 0, idx_tx = 0; int ret; for (;;) { complete_tx_l2fwd(xsk); - rcvd = xq_deq(&xsk->rx, descs, BATCH_SIZE); + rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, + &idx_rx); if (rcvd > 0) break; } + ret = xsk_ring_prod__reserve(&xsk->tx, rcvd, &idx_tx); + while (ret != rcvd) { + if (ret < 0) + exit_with_error(-ret); + ret = xsk_ring_prod__reserve(&xsk->tx, rcvd, &idx_tx); + } + for (i = 0; i < rcvd; i++) { - char *pkt = xq_get_data(xsk, descs[i].addr); + u64 addr = xsk_ring_cons__rx_desc(&xsk->rx, + idx_rx)->addr; + u32 len = xsk_ring_cons__rx_desc(&xsk->rx, + idx_rx++)->len; + char *pkt = xsk_umem__get_data(xsk->umem->buffer, addr); swap_mac_addresses(pkt); - hex_dump(pkt, descs[i].len, descs[i].addr); + hex_dump(pkt, len, addr); + xsk_ring_prod__tx_desc(&xsk->tx, idx_tx)->addr = addr; + xsk_ring_prod__tx_desc(&xsk->tx, idx_tx++)->len = len; } - xsk->rx_npkts += rcvd; + xsk_ring_prod__submit(&xsk->tx, rcvd); + xsk_ring_cons__release(&xsk->rx, rcvd); - ret = xq_enq(&xsk->tx, descs, rcvd); - lassert(ret == 0); + xsk->rx_npkts += rcvd; xsk->outstanding_tx += rcvd; } } @@ -915,17 +647,10 @@ static void l2fwd(struct xdpsock *xsk) int main(int argc, char **argv) { struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; - struct bpf_prog_load_attr prog_load_attr = { - .prog_type = BPF_PROG_TYPE_XDP, - }; - int prog_fd, qidconf_map, xsks_map; - struct bpf_prog_info info = {}; - __u32 info_len = sizeof(info); - struct bpf_object *obj; - char xdp_filename[256]; - struct bpf_map *map; - int i, ret, key = 0; + struct xsk_umem_info *umem; pthread_t pt; + void *bufs; + int ret; parse_command_line(argc, argv); @@ -935,67 +660,22 @@ int main(int argc, char **argv) exit(EXIT_FAILURE); } - snprintf(xdp_filename, sizeof(xdp_filename), "%s_kern.o", argv[0]); - prog_load_attr.file = xdp_filename; - - if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) - exit(EXIT_FAILURE); - if (prog_fd < 0) { - fprintf(stderr, "ERROR: no program found: %s\n", - strerror(prog_fd)); - exit(EXIT_FAILURE); - } - - map = bpf_object__find_map_by_name(obj, "qidconf_map"); - qidconf_map = bpf_map__fd(map); - if (qidconf_map < 0) { - fprintf(stderr, "ERROR: no qidconf map found: %s\n", - strerror(qidconf_map)); - exit(EXIT_FAILURE); - } - - map = bpf_object__find_map_by_name(obj, "xsks_map"); - xsks_map = bpf_map__fd(map); - if (xsks_map < 0) { - fprintf(stderr, "ERROR: no xsks map found: %s\n", - strerror(xsks_map)); - exit(EXIT_FAILURE); - } - - if (bpf_set_link_xdp_fd(opt_ifindex, prog_fd, opt_xdp_flags) < 0) { - fprintf(stderr, "ERROR: link set xdp fd failed\n"); - exit(EXIT_FAILURE); - } - - ret = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); - if (ret) { - printf("can't get prog info - %s\n", strerror(errno)); - return 1; - } - prog_id = info.id; + ret = posix_memalign(&bufs, getpagesize(), /* PAGE_SIZE aligned */ + NUM_FRAMES * XSK_UMEM__DEFAULT_FRAME_SIZE); + if (ret) + exit_with_error(ret); - ret = bpf_map_update_elem(qidconf_map, &key, &opt_queue, 0); - if (ret) { - fprintf(stderr, "ERROR: bpf_map_update_elem qidconf\n"); - exit(EXIT_FAILURE); - } + /* Create sockets... */ + umem = xsk_configure_umem(bufs, + NUM_FRAMES * XSK_UMEM__DEFAULT_FRAME_SIZE); + xsks[num_socks++] = xsk_configure_socket(umem); - /* Create sockets... */ - xsks[num_socks++] = xsk_configure(NULL); - -#if RR_LB - for (i = 0; i < MAX_SOCKS - 1; i++) - xsks[num_socks++] = xsk_configure(xsks[0]->umem); -#endif + if (opt_bench == BENCH_TXONLY) { + int i; - /* ...and insert them into the map. */ - for (i = 0; i < num_socks; i++) { - key = i; - ret = bpf_map_update_elem(xsks_map, &key, &xsks[i]->sfd, 0); - if (ret) { - fprintf(stderr, "ERROR: bpf_map_update_elem %d\n", i); - exit(EXIT_FAILURE); - } + for (i = 0; i < NUM_FRAMES * XSK_UMEM__DEFAULT_FRAME_SIZE; + i += XSK_UMEM__DEFAULT_FRAME_SIZE) + (void)gen_eth_frame(umem, i); } signal(SIGINT, int_exit); @@ -1005,7 +685,8 @@ int main(int argc, char **argv) setlocale(LC_ALL, ""); ret = pthread_create(&pt, NULL, poller, NULL); - lassert(ret == 0); + if (ret) + exit_with_error(ret); prev_time = get_nsecs(); |