Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Here we go, another merge window full of networking and #ebpf changes:

   1) Snoop DHCPACKS in batman-adv to learn MAC/IP pairs in the DHCP
      range without dealing with floods of ARP traffic, from Linus
      Lüssing.

   2) Throttle buffered multicast packet transmission in mt76, from
      Felix Fietkau.

   3) Support adaptive interrupt moderation in ice, from Brett Creeley.

   4) A lot of struct_size conversions, from Gustavo A. R. Silva.

   5) Add peek/push/pop commands to bpftool, as well as bash completion,
      from Stanislav Fomichev.

   6) Optimize sk_msg_clone(), from Vakul Garg.

   7) Add SO_BINDTOIFINDEX, from David Herrmann.

   8) Be more conservative with local resends due to local congestion,
      from Yuchung Cheng.

   9) Allow vetoing of unsupported VXLAN FDBs, from Petr Machata.

  10) Add health buffer support to devlink, from Eran Ben Elisha.

  11) Add TXQ scheduling API to mac80211, from Toke Høiland-Jørgensen.

  12) Add statistics to basic packet scheduler filter, from Cong Wang.

  13) Add GRE tunnel support for mlxsw Spectrum-2, from Nir Dotan.

  14) Lots of new IP tunneling forwarding tests, also from Nir Dotan.

  15) Add 3ad stats to bonding, from Nikolay Aleksandrov.

  16) Lots of probing improvements for bpftool, from Quentin Monnet.

  17) Various nfp drive #ebpf JIT improvements from Jakub Kicinski.

  18) Allow #ebpf programs to access gso_segs from skb shared info, from
      Eric Dumazet.

  19) Add sock_diag support for AF_XDP sockets, from Björn Töpel.

  20) Support 22260 iwlwifi devices, from Luca Coelho.

  21) Use rbtree for ipv6 defragmentation, from Peter Oskolkov.

  22) Add JMP32 instruction class support to #ebpf, from Jiong Wang.

  23) Add spinlock support to #ebpf, from Alexei Starovoitov.

  24) Support 256-bit keys and TLS 1.3 in ktls, from Dave Watson.

  25) Add device infomation API to devlink, from Jakub Kicinski.

  26) Add new timestamping socket options which are y2038 safe, from
      Deepa Dinamani.

  27) Add RX checksum offloading for various sh_eth chips, from Sergei
      Shtylyov.

  28) Flow offload infrastructure, from Pablo Neira Ayuso.

  29) Numerous cleanups, improvements, and bug fixes to the PHY layer
      and many drivers from Heiner Kallweit.

  30) Lots of changes to try and make packet scheduler classifiers run
      lockless as much as possible, from Vlad Buslov.

  31) Support BCM957504 chip in bnxt_en driver, from Erik Burrows.

  32) Add concurrency tests to tc-tests infrastructure, from Vlad
      Buslov.

  33) Add hwmon support to aquantia, from Heiner Kallweit.

  34) Allow 64-bit values for SO_MAX_PACING_RATE, from Eric Dumazet.

  And I would be remiss if I didn't thank the various major networking
  subsystem maintainers for integrating much of this work before I even
  saw it. Alexei Starovoitov, Daniel Borkmann, Pablo Neira Ayuso,
  Johannes Berg, Kalle Valo, and many others. Thank you!"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2207 commits)
  net/sched: avoid unused-label warning
  net: ignore sysctl_devconf_inherit_init_net without SYSCTL
  phy: mdio-mux: fix Kconfig dependencies
  net: phy: use phy_modify_mmd_changed in genphy_c45_an_config_aneg
  net: dsa: mv88e6xxx: add call to mv88e6xxx_ports_cmode_init to probe for new DSA framework
  selftest/net: Remove duplicate header
  sky2: Disable MSI on Dell Inspiron 1545 and Gateway P-79
  net/mlx5e: Update tx reporter status in case channels were successfully opened
  devlink: Add support for direct reporter health state update
  devlink: Update reporter state to error even if recover aborted
  sctp: call iov_iter_revert() after sending ABORT
  team: Free BPF filter when unregistering netdev
  ip6mr: Do not call __IP6_INC_STATS() from preemptible context
  isdn: mISDN: Fix potential NULL pointer dereference of kzalloc
  net: dsa: mv88e6xxx: support in-band signalling on SGMII ports with external PHYs
  cxgb4/chtls: Prefix adapter flags with CXGB4
  net-sysfs: Switch to bitmap_zalloc()
  mellanox: Switch to bitmap_zalloc()
  bpf: add test cases for non-pointer sanitiation logic
  mlxsw: i2c: Extend initialization by querying resources data
  ...

39 files changed, 2216 insertions, 971 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 db1a91dfa702..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
@@ -87,18 +86,18 @@ test_cgrp2_sock2-objs := bpf_load.o test_cgrp2_sock2.o
 xdp1-objs := xdp1_user.o
 # reuse xdp1 source intentionally
 xdp2-objs := xdp1_user.o
-xdp_router_ipv4-objs := bpf_load.o xdp_router_ipv4_user.o
+xdp_router_ipv4-objs := xdp_router_ipv4_user.o
 test_current_task_under_cgroup-objs := bpf_load.o $(CGROUP_HELPERS) \
 				       test_current_task_under_cgroup_user.o
 trace_event-objs := bpf_load.o trace_event_user.o $(TRACE_HELPERS)
 sampleip-objs := bpf_load.o sampleip_user.o $(TRACE_HELPERS)
 tc_l2_redirect-objs := bpf_load.o tc_l2_redirect_user.o
 lwt_len_hist-objs := bpf_load.o lwt_len_hist_user.o
-xdp_tx_iptunnel-objs := bpf_load.o xdp_tx_iptunnel_user.o
+xdp_tx_iptunnel-objs := xdp_tx_iptunnel_user.o
 test_map_in_map-objs := bpf_load.o test_map_in_map_user.o
 per_socket_stats_example-objs := cookie_uid_helper_example.o
-xdp_redirect-objs := bpf_load.o xdp_redirect_user.o
-xdp_redirect_map-objs := bpf_load.o xdp_redirect_map_user.o
+xdp_redirect-objs := xdp_redirect_user.o
+xdp_redirect_map-objs := xdp_redirect_map_user.o
 xdp_redirect_cpu-objs := bpf_load.o xdp_redirect_cpu_user.o
 xdp_monitor-objs := bpf_load.o xdp_monitor_user.o
 xdp_rxq_info-objs := xdp_rxq_info_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/bpf_insn.h b/samples/bpf/bpf_insn.h
index 20dc5cefec84..544237980582 100644
--- a/samples/bpf/bpf_insn.h
+++ b/samples/bpf/bpf_insn.h
@@ -164,6 +164,16 @@ struct bpf_insn;
 		.off   = OFF,					\
 		.imm   = 0 })
 
+/* Like BPF_JMP_REG, but with 32-bit wide operands for comparison. */
+
+#define BPF_JMP32_REG(OP, DST, SRC, OFF)			\
+	((struct bpf_insn) {					\
+		.code  = BPF_JMP32 | BPF_OP(OP) | BPF_X,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
 /* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */
 
 #define BPF_JMP_IMM(OP, DST, IMM, OFF)				\
@@ -174,6 +184,16 @@ struct bpf_insn;
 		.off   = OFF,					\
 		.imm   = IMM })
 
+/* Like BPF_JMP_IMM, but with 32-bit wide operands for comparison. */
+
+#define BPF_JMP32_IMM(OP, DST, IMM, OFF)			\
+	((struct bpf_insn) {					\
+		.code  = BPF_JMP32 | BPF_OP(OP) | BPF_K,	\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = OFF,					\
+		.imm   = IMM })
+
 /* Raw code statement block */
 
 #define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM)			\
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)