Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/samples/bpf/.gitignore b/samples/bpf/.gitignore
index 8ae4940..74d31fd 100644
--- a/samples/bpf/.gitignore
+++ b/samples/bpf/.gitignore
@@ -1,7 +1,8 @@
cpustat
fds_example
+hbm
+ibumad
lathist
-load_sock_ops
lwt_len_hist
map_perf_test
offwaketime
@@ -45,5 +46,6 @@
xdp_redirect_map
xdp_router_ipv4
xdp_rxq_info
+xdp_sample_pkts
xdp_tx_iptunnel
xdpsock
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 36f9f41..42b571c 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -26,7 +26,6 @@
hostprogs-y += test_overhead
hostprogs-y += test_cgrp2_array_pin
hostprogs-y += test_cgrp2_attach
-hostprogs-y += test_cgrp2_attach2
hostprogs-y += test_cgrp2_sock
hostprogs-y += test_cgrp2_sock2
hostprogs-y += xdp1
@@ -40,7 +39,6 @@
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 +51,8 @@
hostprogs-y += xdp_fwd
hostprogs-y += task_fd_query
hostprogs-y += xdp_sample_pkts
+hostprogs-y += ibumad
+hostprogs-y += hbm
# Libbpf dependencies
LIBBPF = $(TOOLS_PATH)/lib/bpf/libbpf.a
@@ -60,9 +60,9 @@
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 @@
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
@@ -81,24 +80,23 @@
test_overhead-objs := bpf_load.o test_overhead_user.o
test_cgrp2_array_pin-objs := test_cgrp2_array_pin.o
test_cgrp2_attach-objs := test_cgrp2_attach.o
-test_cgrp2_attach2-objs := test_cgrp2_attach2.o $(CGROUP_HELPERS)
test_cgrp2_sock-objs := test_cgrp2_sock.o
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 +107,8 @@
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)
+ibumad-objs := bpf_load.o ibumad_user.o $(TRACE_HELPERS)
+hbm-objs := bpf_load.o hbm.o $(CGROUP_HELPERS)
# Tell kbuild to always build the programs
always := $(hostprogs-y)
@@ -153,6 +153,8 @@
always += tcp_iw_kern.o
always += tcp_clamp_kern.o
always += tcp_basertt_kern.o
+always += tcp_tos_reflect_kern.o
+always += tcp_dumpstats_kern.o
always += xdp_redirect_kern.o
always += xdp_redirect_map_kern.o
always += xdp_redirect_cpu_kern.o
@@ -162,27 +164,21 @@
always += syscall_tp_kern.o
always += cpustat_kern.o
always += xdp_adjust_tail_kern.o
-always += xdpsock_kern.o
always += xdp_fwd_kern.o
always += task_fd_query_kern.o
always += xdp_sample_pkts_kern.o
+always += ibumad_kern.o
+always += hbm_out_kern.o
+always += hbm_edt_kern.o
KBUILD_HOSTCFLAGS += -I$(objtree)/usr/include
-KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/
+KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/bpf/
KBUILD_HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/ -I$(srctree)/tools/include
KBUILD_HOSTCFLAGS += -I$(srctree)/tools/perf
+KBUILD_HOSTCFLAGS += -DHAVE_ATTR_TEST=0
HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable
-HOSTCFLAGS_trace_helpers.o += -I$(srctree)/tools/lib/bpf/
-
-HOSTCFLAGS_trace_output_user.o += -I$(srctree)/tools/lib/bpf/
-HOSTCFLAGS_offwaketime_user.o += -I$(srctree)/tools/lib/bpf/
-HOSTCFLAGS_spintest_user.o += -I$(srctree)/tools/lib/bpf/
-HOSTCFLAGS_trace_event_user.o += -I$(srctree)/tools/lib/bpf/
-HOSTCFLAGS_sampleip_user.o += -I$(srctree)/tools/lib/bpf/
-HOSTCFLAGS_task_fd_query_user.o += -I$(srctree)/tools/lib/bpf/
-HOSTCFLAGS_xdp_sample_pkts_user.o += -I$(srctree)/tools/lib/bpf/
KBUILD_HOSTLDLIBS += $(LIBBPF) -lelf
HOSTLDLIBS_tracex4 += -lrt
@@ -204,15 +200,35 @@
CLANG_ARCH_ARGS = -target $(ARCH)
endif
+# Don't evaluate probes and warnings if we need to run make recursively
+ifneq ($(src),)
+HDR_PROBE := $(shell echo "\#include <linux/types.h>\n struct list_head { int a; }; int main() { return 0; }" | \
+ $(HOSTCC) $(KBUILD_HOSTCFLAGS) -x c - -o /dev/null 2>/dev/null && \
+ echo okay)
+
+ifeq ($(HDR_PROBE),)
+$(warning WARNING: Detected possible issues with include path.)
+$(warning WARNING: Please install kernel headers locally (make headers_install).)
+endif
+
BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm')
+BTF_LLVM_PROBE := $(shell echo "int main() { return 0; }" | \
+ $(CLANG) -target bpf -O2 -g -c -x c - -o ./llvm_btf_verify.o; \
+ readelf -S ./llvm_btf_verify.o | grep BTF; \
+ /bin/rm -f ./llvm_btf_verify.o)
+ifneq ($(BTF_LLVM_PROBE),)
+ EXTRA_CFLAGS += -g
+else
ifneq ($(and $(BTF_LLC_PROBE),$(BTF_PAHOLE_PROBE),$(BTF_OBJCOPY_PROBE)),)
EXTRA_CFLAGS += -g
LLC_FLAGS += -mattr=dwarfris
DWARF2BTF = y
endif
+endif
+endif
# Trick to allow make to be run from this directory
all:
@@ -226,12 +242,10 @@
# Fix up variables inherited from Kbuild that tools/ build system won't like
$(MAKE) -C $(dir $@) RM='rm -rf' LDFLAGS= srctree=$(BPF_SAMPLES_PATH)/../../ O=
-$(obj)/syscall_nrs.s: $(src)/syscall_nrs.c
- $(call if_changed_dep,cc_s_c)
-
$(obj)/syscall_nrs.h: $(obj)/syscall_nrs.s FORCE
$(call filechk,offsets,__SYSCALL_NRS_H__)
+targets += syscall_nrs.s
clean-files += syscall_nrs.h
FORCE:
@@ -259,6 +273,9 @@
$(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: $(src)/hbm.h
+$(obj)/hbm_edt_kern.o: $(src)/hbm.h $(src)/hbm_kern.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
@@ -268,10 +285,11 @@
$(Q)$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \
-I$(srctree)/tools/testing/selftests/bpf/ \
-D__KERNEL__ -D__BPF_TRACING__ -Wno-unused-value -Wno-pointer-sign \
- -D__TARGET_ARCH_$(ARCH) -Wno-compare-distinct-pointer-types \
+ -D__TARGET_ARCH_$(SRCARCH) -Wno-compare-distinct-pointer-types \
-Wno-gnu-variable-sized-type-not-at-end \
-Wno-address-of-packed-member -Wno-tautological-compare \
-Wno-unknown-warning-option $(CLANG_ARCH_ARGS) \
+ -I$(srctree)/samples/bpf/ -include asm_goto_workaround.h \
-O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf $(LLC_FLAGS) -filetype=obj -o $@
ifeq ($(DWARF2BTF),y)
$(BTF_PAHOLE) -J $@
diff --git a/samples/bpf/asm_goto_workaround.h b/samples/bpf/asm_goto_workaround.h
new file mode 100644
index 0000000..7048bb3
--- /dev/null
+++ b/samples/bpf/asm_goto_workaround.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019 Facebook */
+#ifndef __ASM_GOTO_WORKAROUND_H
+#define __ASM_GOTO_WORKAROUND_H
+
+/*
+ * This will bring in asm_volatile_goto and asm_inline macro definitions
+ * if enabled by compiler and config options.
+ */
+#include <linux/types.h>
+
+#ifdef asm_volatile_goto
+#undef asm_volatile_goto
+#define asm_volatile_goto(x...) asm volatile("invalid use of asm_volatile_goto")
+#endif
+
+/*
+ * asm_inline is defined as asm __inline in "include/linux/compiler_types.h"
+ * if supported by the kernel's CC (i.e CONFIG_CC_HAS_ASM_INLINE) which is not
+ * supported by CLANG.
+ */
+#ifdef asm_inline
+#undef asm_inline
+#define asm_inline asm
+#endif
+
+#define volatile(x...) volatile("")
+#endif
diff --git a/samples/bpf/bpf_insn.h b/samples/bpf/bpf_insn.h
index 20dc5ce..5442379 100644
--- a/samples/bpf/bpf_insn.h
+++ b/samples/bpf/bpf_insn.h
@@ -164,6 +164,16 @@
.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 @@
.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/bpf_load.c b/samples/bpf/bpf_load.c
index 904e775..4574b19 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -16,7 +16,6 @@
#include <linux/netlink.h>
#include <linux/rtnetlink.h>
#include <linux/types.h>
-#include <sys/types.h>
#include <sys/socket.h>
#include <sys/syscall.h>
#include <sys/ioctl.h>
@@ -41,7 +40,7 @@
int prog_array_fd = -1;
struct bpf_map_data map_data[MAX_MAPS];
-int map_data_count = 0;
+int map_data_count;
static int populate_prog_array(const char *event, int prog_fd)
{
@@ -55,6 +54,25 @@
return 0;
}
+static int write_kprobe_events(const char *val)
+{
+ int fd, ret, flags;
+
+ if (val == NULL)
+ return -1;
+ else if (val[0] == '\0')
+ flags = O_WRONLY | O_TRUNC;
+ else
+ flags = O_WRONLY | O_APPEND;
+
+ fd = open(DEBUGFS "kprobe_events", flags);
+
+ ret = write(fd, val, strlen(val));
+ close(fd);
+
+ return ret;
+}
+
static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
{
bool is_socket = strncmp(event, "socket", 6) == 0;
@@ -166,10 +184,9 @@
#ifdef __x86_64__
if (strncmp(event, "sys_", 4) == 0) {
- snprintf(buf, sizeof(buf),
- "echo '%c:__x64_%s __x64_%s' >> /sys/kernel/debug/tracing/kprobe_events",
- is_kprobe ? 'p' : 'r', event, event);
- err = system(buf);
+ snprintf(buf, sizeof(buf), "%c:__x64_%s __x64_%s",
+ is_kprobe ? 'p' : 'r', event, event);
+ err = write_kprobe_events(buf);
if (err >= 0) {
need_normal_check = false;
event_prefix = "__x64_";
@@ -177,10 +194,9 @@
}
#endif
if (need_normal_check) {
- snprintf(buf, sizeof(buf),
- "echo '%c:%s %s' >> /sys/kernel/debug/tracing/kprobe_events",
- is_kprobe ? 'p' : 'r', event, event);
- err = system(buf);
+ snprintf(buf, sizeof(buf), "%c:%s %s",
+ is_kprobe ? 'p' : 'r', event, event);
+ err = write_kprobe_events(buf);
if (err < 0) {
printf("failed to create kprobe '%s' error '%s'\n",
event, strerror(errno));
@@ -285,8 +301,8 @@
numa_node);
}
if (map_fd[i] < 0) {
- printf("failed to create a map: %d %s\n",
- errno, strerror(errno));
+ printf("failed to create map %d (%s): %d %s\n",
+ i, maps[i].name, errno, strerror(errno));
return 1;
}
maps[i].fd = map_fd[i];
@@ -474,8 +490,8 @@
/* Verify no newer features were requested */
if (validate_zero) {
- addr = (unsigned char*) def + map_sz_copy;
- end = (unsigned char*) def + map_sz_elf;
+ addr = (unsigned char *) def + map_sz_copy;
+ end = (unsigned char *) def + map_sz_elf;
for (; addr < end; addr++) {
if (*addr != 0) {
free(sym);
@@ -520,7 +536,7 @@
return 1;
/* clear all kprobes */
- i = system("echo \"\" > /sys/kernel/debug/tracing/kprobe_events");
+ i = write_kprobe_events("");
/* scan over all elf sections to get license and map info */
for (i = 1; i < ehdr.e_shnum; i++) {
@@ -662,7 +678,7 @@
static char buf[4096];
ssize_t sz;
- sz = read(trace_fd, buf, sizeof(buf));
+ sz = read(trace_fd, buf, sizeof(buf) - 1);
if (sz > 0) {
buf[sz] = 0;
puts(buf);
diff --git a/samples/bpf/do_hbm_test.sh b/samples/bpf/do_hbm_test.sh
new file mode 100755
index 0000000..ffe4c06
--- /dev/null
+++ b/samples/bpf/do_hbm_test.sh
@@ -0,0 +1,442 @@
+#!/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>]"
+ echo " [-D] [-d=<delay>|--delay=<delay>] [--debug] [-E] [--edt]"
+ echo " [-f=<#flows>|--flows=<#flows>] [-h] [-i=<id>|--id=<id >]"
+ echo " [-l] [-N] [--no_cn] [-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 " --edt use fq's Earliest Departure Time (requires fq)"
+ 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 " --no_cn Do not return CN notifications"
+ 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="${i#*=}"
+ ;;
+ --no_cn)
+ flags="$flags --no_cn"
+ ;;
+ --debug)
+ flags="$flags -d"
+ debug_flag=1
+ ;;
+ -d=*|--delay=*)
+ netem="${i#*=}"
+ ;;
+ -D)
+ details=1
+ ;;
+ -E)
+ ecn=1
+ ;;
+ --edt)
+ flags="$flags --edt"
+ qdisc="fq"
+ ;;
+ -f=*|--flows=*)
+ flows="${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 eth0 root > /dev/null 2>&1
+ tc qdisc add dev eth0 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
+if [ "$qdisc" != "" ] ; then
+ tc qdisc del dev eth0 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 9854854..2d4b717 100644
--- a/samples/bpf/fds_example.c
+++ b/samples/bpf/fds_example.c
@@ -14,8 +14,8 @@
#include <bpf/bpf.h>
+#include "libbpf.h"
#include "bpf_insn.h"
-#include "bpf_load.h"
#include "sock_example.h"
#define BPF_F_PIN (1 << 0)
@@ -57,10 +57,14 @@
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 0000000..e0fbab9
--- /dev/null
+++ b/samples/bpf/hbm.c
@@ -0,0 +1,498 @@
+// 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
+ * --no_cn Do not return cn notifications
+ * -r <rate> Rate limit in Mbps
+ * -s Get HBM stats (marked, dropped, etc.)
+ * -t <time> Exit after specified seconds (default 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 <getopt.h>
+
+#include "bpf_load.h"
+#include "bpf_rlimit.h"
+#include "cgroup_helpers.h"
+#include "hbm.h"
+#include "bpf_util.h"
+#include "bpf.h"
+#include "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;
+bool no_cn_flag;
+bool edt_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;
+ qstats.no_cn = no_cn_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;
+ int k;
+ static const char *returnValNames[] = {
+ "DROP_PKT",
+ "ALLOW_PKT",
+ "DROP_PKT_CWR",
+ "ALLOW_PKT_CWR"
+ };
+#define RET_VAL_COUNT 4
+
+// 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);
+
+ // ECN CE markings
+ percent_pkts = (qstats.pkts_ecn_ce * 100.0) /
+ (qstats.pkts_total + 1);
+ fprintf(fout, "pkts_ecn_ce:%6.2f (%d)\n", percent_pkts,
+ (int)qstats.pkts_ecn_ce);
+
+ // Average cwnd
+ fprintf(fout, "avg cwnd:%d\n",
+ (int)(qstats.sum_cwnd / (qstats.sum_cwnd_cnt + 1)));
+ // Average rtt
+ fprintf(fout, "avg rtt:%d\n",
+ (int)(qstats.sum_rtt / (qstats.pkts_total + 1)));
+ // Average credit
+ if (edt_flag)
+ fprintf(fout, "avg credit_ms:%.03f\n",
+ (qstats.sum_credit /
+ (qstats.pkts_total + 1.0)) / 1000000.0);
+ else
+ fprintf(fout, "avg credit:%d\n",
+ (int)(qstats.sum_credit /
+ (1500 * ((int)qstats.pkts_total ) + 1)));
+
+ // Return values stats
+ for (k = 0; k < RET_VAL_COUNT; k++) {
+ percent_pkts = (qstats.returnValCount[k] * 100.0) /
+ (qstats.pkts_total + 1);
+ fprintf(fout, "%s:%6.2f (%d)\n", returnValNames[k],
+ percent_pkts, (int)qstats.returnValCount[k]);
+ }
+ 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>] [--no_cn] [-r <rate>]\n"
+ " [-s] [-t <secs>] [-w] [-h] [prog]\n"
+ " Where:\n"
+ " -o indicates egress direction (default)\n"
+ " -d print BPF trace debug buffer\n"
+ " --edt use fq's Earliest Departure Time\n"
+ " -l also limit flows using loopback\n"
+ " -n <#> to create cgroup \"/hbm#\" and attach prog\n"
+ " Default is /hbm1\n"
+ " --no_cn disable CN notifications\n"
+ " -r <rate> Rate in Mbps\n"
+ " -s Update HBM stats\n"
+ " -t <time> Exit after specified seconds (default 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";
+ struct option loptions[] = {
+ {"no_cn", 0, NULL, 1},
+ {"edt", 0, NULL, 2},
+ {NULL, 0, NULL, 0}
+ };
+
+ while ((k = getopt_long(argc, argv, optstring, loptions, NULL)) != -1) {
+ switch (k) {
+ case 1:
+ no_cn_flag = true;
+ break;
+ case 2:
+ prog = "hbm_edt_kern.o";
+ edt_flag = true;
+ break;
+ 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 0000000..f0963ed
--- /dev/null
+++ b/samples/bpf/hbm.h
@@ -0,0 +1,38 @@
+/* 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 */
+ no_cn:1; /* do not use cn flags */
+ 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;
+ unsigned long long pkts_ecn_ce;
+ unsigned long long returnValCount[4];
+ unsigned long long sum_cwnd;
+ unsigned long long sum_rtt;
+ unsigned long long sum_cwnd_cnt;
+ long long sum_credit;
+};
diff --git a/samples/bpf/hbm_edt_kern.c b/samples/bpf/hbm_edt_kern.c
new file mode 100644
index 0000000..a65b677
--- /dev/null
+++ b/samples/bpf/hbm_edt_kern.c
@@ -0,0 +1,168 @@
+// 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
+ * a user program, such as hbm, can access.
+ */
+
+#include "hbm_kern.h"
+
+SEC("cgroup_skb/egress")
+int _hbm_out_cg(struct __sk_buff *skb)
+{
+ long long delta = 0, delta_send;
+ unsigned long long curtime, sendtime;
+ struct hbm_queue_stats *qsp = NULL;
+ unsigned int queue_index = 0;
+ bool congestion_flag = false;
+ bool ecn_ce_flag = false;
+ struct hbm_pkt_info pkti = {};
+ struct hbm_vqueue *qdp;
+ bool drop_flag = false;
+ bool cwr_flag = false;
+ int len = skb->len;
+ int rv = ALLOW_PKT;
+
+ qsp = bpf_map_lookup_elem(&queue_stats, &queue_index);
+
+ // Check if we should ignore loopback traffic
+ 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;
+ if (qdp->lasttime == 0)
+ hbm_init_edt_vqueue(qdp, 1024);
+
+ curtime = bpf_ktime_get_ns();
+
+ // Begin critical section
+ bpf_spin_lock(&qdp->lock);
+ delta = qdp->lasttime - curtime;
+ // bound bursts to 100us
+ if (delta < -BURST_SIZE_NS) {
+ // negative delta is a credit that allows bursts
+ qdp->lasttime = curtime - BURST_SIZE_NS;
+ delta = -BURST_SIZE_NS;
+ }
+ sendtime = qdp->lasttime;
+ delta_send = BYTES_TO_NS(len, qdp->rate);
+ __sync_add_and_fetch(&(qdp->lasttime), delta_send);
+ bpf_spin_unlock(&qdp->lock);
+ // End critical section
+
+ // Set EDT of packet
+ skb->tstamp = sendtime;
+
+ // Check if we should update rate
+ if (qsp != NULL && (qsp->rate * 128) != qdp->rate)
+ qdp->rate = qsp->rate * 128;
+
+ // Set flags (drop, congestion, cwr)
+ // last packet will be sent in the future, bound latency
+ if (delta > DROP_THRESH_NS || (delta > LARGE_PKT_DROP_THRESH_NS &&
+ len > LARGE_PKT_THRESH)) {
+ drop_flag = true;
+ if (pkti.is_tcp && pkti.ecn == 0)
+ cwr_flag = true;
+ } else if (delta > MARK_THRESH_NS) {
+ if (pkti.is_tcp)
+ congestion_flag = true;
+ else
+ drop_flag = true;
+ }
+
+ if (congestion_flag) {
+ if (bpf_skb_ecn_set_ce(skb)) {
+ ecn_ce_flag = true;
+ } else {
+ if (pkti.is_tcp) {
+ unsigned int rand = bpf_get_prandom_u32();
+
+ if (delta >= MARK_THRESH_NS +
+ (rand % MARK_REGION_SIZE_NS)) {
+ // Do congestion control
+ cwr_flag = true;
+ }
+ } else if (len > LARGE_PKT_THRESH) {
+ // Problem if too many small packets?
+ drop_flag = true;
+ congestion_flag = false;
+ }
+ }
+ }
+
+ if (pkti.is_tcp && drop_flag && pkti.packets_out <= 1) {
+ drop_flag = false;
+ cwr_flag = true;
+ congestion_flag = false;
+ }
+
+ if (qsp != NULL && qsp->no_cn)
+ cwr_flag = false;
+
+ hbm_update_stats(qsp, len, curtime, congestion_flag, drop_flag,
+ cwr_flag, ecn_ce_flag, &pkti, (int) delta);
+
+ if (drop_flag) {
+ __sync_add_and_fetch(&(qdp->lasttime), -delta_send);
+ rv = DROP_PKT;
+ }
+
+ if (cwr_flag)
+ rv |= CWR;
+ return rv;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/hbm_kern.h b/samples/bpf/hbm_kern.h
new file mode 100644
index 0000000..aa207a2
--- /dev/null
+++ b/samples/bpf/hbm_kern.h
@@ -0,0 +1,220 @@
+/* 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 CWR 2
+
+#ifndef HBM_DEBUG // Define HBM_DEBUG to enable debugging
+#undef bpf_printk
+#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)
+
+// Time base accounting for fq's EDT
+#define BURST_SIZE_NS 100000 // 100us
+#define MARK_THRESH_NS 50000 // 50us
+#define DROP_THRESH_NS 500000 // 500us
+// Reserve 20us of queuing for small packets (less than 120 bytes)
+#define LARGE_PKT_DROP_THRESH_NS (DROP_THRESH_NS - 20000)
+#define MARK_REGION_SIZE_NS (LARGE_PKT_DROP_THRESH_NS - MARK_THRESH_NS)
+
+// rate in bytes per ns << 20
+#define CREDIT_PER_NS(delta, rate) ((((u64)(delta)) * (rate)) >> 20)
+#define BYTES_PER_NS(delta, rate) ((((u64)(delta)) * (rate)) >> 20)
+#define BYTES_TO_NS(bytes, rate) div64_u64(((u64)(bytes)) << 20, (u64)(rate))
+
+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 {
+ int cwnd;
+ int rtt;
+ int packets_out;
+ bool is_ip;
+ bool is_tcp;
+ short ecn;
+};
+
+static int get_tcp_info(struct __sk_buff *skb, struct hbm_pkt_info *pkti)
+{
+ struct bpf_sock *sk;
+ struct bpf_tcp_sock *tp;
+
+ sk = skb->sk;
+ if (sk) {
+ sk = bpf_sk_fullsock(sk);
+ if (sk) {
+ if (sk->protocol == IPPROTO_TCP) {
+ tp = bpf_tcp_sock(sk);
+ if (tp) {
+ pkti->cwnd = tp->snd_cwnd;
+ pkti->rtt = tp->srtt_us >> 3;
+ pkti->packets_out = tp->packets_out;
+ return 0;
+ }
+ }
+ }
+ }
+ pkti->cwnd = 0;
+ pkti->rtt = 0;
+ pkti->packets_out = 0;
+ return 1;
+}
+
+static void hbm_get_pkt_info(struct __sk_buff *skb,
+ struct hbm_pkt_info *pkti)
+{
+ struct iphdr iph;
+ struct ipv6hdr *ip6h;
+
+ pkti->cwnd = 0;
+ pkti->rtt = 0;
+ 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;
+ }
+ if (pkti->is_tcp)
+ get_tcp_info(skb, pkti);
+}
+
+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_init_edt_vqueue(struct hbm_vqueue *qdp,
+ int rate)
+{
+ unsigned long long curtime;
+
+ curtime = bpf_ktime_get_ns();
+ bpf_printk("Initializing queue_state, rate:%d\n", rate * 128);
+ qdp->lasttime = curtime - BURST_SIZE_NS; // support initial burst
+ qdp->credit = 0; // not used
+ 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,
+ bool cwr_flag,
+ bool ecn_ce_flag,
+ struct hbm_pkt_info *pkti,
+ int credit)
+{
+ int rv = ALLOW_PKT;
+
+ 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) {
+ __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);
+ }
+ if (ecn_ce_flag)
+ __sync_add_and_fetch(&(qsp->pkts_ecn_ce), 1);
+ if (pkti->cwnd) {
+ __sync_add_and_fetch(&(qsp->sum_cwnd),
+ pkti->cwnd);
+ __sync_add_and_fetch(&(qsp->sum_cwnd_cnt), 1);
+ }
+ if (pkti->rtt)
+ __sync_add_and_fetch(&(qsp->sum_rtt),
+ pkti->rtt);
+ __sync_add_and_fetch(&(qsp->sum_credit), credit);
+
+ if (drop_flag)
+ rv = DROP_PKT;
+ if (cwr_flag)
+ rv |= 2;
+ if (rv == DROP_PKT)
+ __sync_add_and_fetch(&(qsp->returnValCount[0]),
+ 1);
+ else if (rv == ALLOW_PKT)
+ __sync_add_and_fetch(&(qsp->returnValCount[1]),
+ 1);
+ else if (rv == 2)
+ __sync_add_and_fetch(&(qsp->returnValCount[2]),
+ 1);
+ else if (rv == 3)
+ __sync_add_and_fetch(&(qsp->returnValCount[3]),
+ 1);
+ }
+ }
+}
diff --git a/samples/bpf/hbm_out_kern.c b/samples/bpf/hbm_out_kern.c
new file mode 100644
index 0000000..829934b
--- /dev/null
+++ b/samples/bpf/hbm_out_kern.c
@@ -0,0 +1,179 @@
+// 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, new_credit;
+ int max_credit = MAX_CREDIT;
+ bool congestion_flag = false;
+ bool drop_flag = false;
+ bool cwr_flag = false;
+ bool ecn_ce_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;
+ new_credit = credit + CREDIT_PER_NS(delta, qdp->rate);
+ if (new_credit > MAX_CREDIT)
+ credit = MAX_CREDIT;
+ else
+ credit = new_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 packet
+ drop_flag = true;
+ if (pkti.ecn)
+ congestion_flag = true;
+ else if (pkti.is_tcp)
+ cwr_flag = true;
+ } else if (credit < 0) {
+ // Congested, set congestion flag
+ if (pkti.ecn || pkti.is_tcp) {
+ 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)) {
+ ecn_ce_flag = true;
+ } else {
+ if (pkti.is_tcp) {
+ unsigned int rand = bpf_get_prandom_u32();
+
+ if (-credit >= MARK_THRESH +
+ (rand % MARK_REGION_SIZE)) {
+ // Do congestion control
+ cwr_flag = true;
+ }
+ } else if (len > LARGE_PKT_THRESH) {
+ // Problem if too many small packets?
+ drop_flag = true;
+ }
+ }
+ }
+
+ if (qsp != NULL)
+ if (qsp->no_cn)
+ cwr_flag = false;
+
+ hbm_update_stats(qsp, len, curtime, congestion_flag, drop_flag,
+ cwr_flag, ecn_ce_flag, &pkti, credit);
+
+ if (drop_flag) {
+ __sync_add_and_fetch(&(qdp->credit), len);
+ rv = DROP_PKT;
+ }
+
+ if (cwr_flag)
+ rv |= 2;
+ return rv;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/ibumad_kern.c b/samples/bpf/ibumad_kern.c
new file mode 100644
index 0000000..f281df7
--- /dev/null
+++ b/samples/bpf/ibumad_kern.c
@@ -0,0 +1,138 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+
+/**
+ * ibumad BPF sample kernel side
+ *
+ * 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.
+ *
+ * Copyright(c) 2018 Ira Weiny, Intel Corporation
+ */
+
+#define KBUILD_MODNAME "ibumad_count_pkts_by_class"
+#include <uapi/linux/bpf.h>
+
+#include "bpf_helpers.h"
+
+
+struct bpf_map_def SEC("maps") read_count = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(u32), /* class; u32 required */
+ .value_size = sizeof(u64), /* count of mads read */
+ .max_entries = 256, /* Room for all Classes */
+};
+
+struct bpf_map_def SEC("maps") write_count = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(u32), /* class; u32 required */
+ .value_size = sizeof(u64), /* count of mads written */
+ .max_entries = 256, /* Room for all Classes */
+};
+
+#undef DEBUG
+#ifndef DEBUG
+#undef bpf_printk
+#define bpf_printk(fmt, ...)
+#endif
+
+/* Taken from the current format defined in
+ * include/trace/events/ib_umad.h
+ * and
+ * /sys/kernel/debug/tracing/events/ib_umad/ib_umad_read/format
+ * /sys/kernel/debug/tracing/events/ib_umad/ib_umad_write/format
+ */
+struct ib_umad_rw_args {
+ u64 pad;
+ u8 port_num;
+ u8 sl;
+ u8 path_bits;
+ u8 grh_present;
+ u32 id;
+ u32 status;
+ u32 timeout_ms;
+ u32 retires;
+ u32 length;
+ u32 qpn;
+ u32 qkey;
+ u8 gid_index;
+ u8 hop_limit;
+ u16 lid;
+ u16 attr_id;
+ u16 pkey_index;
+ u8 base_version;
+ u8 mgmt_class;
+ u8 class_version;
+ u8 method;
+ u32 flow_label;
+ u16 mad_status;
+ u16 class_specific;
+ u32 attr_mod;
+ u64 tid;
+ u8 gid[16];
+ u32 dev_index;
+ u8 traffic_class;
+};
+
+SEC("tracepoint/ib_umad/ib_umad_read_recv")
+int on_ib_umad_read_recv(struct ib_umad_rw_args *ctx)
+{
+ u64 zero = 0, *val;
+ u8 class = ctx->mgmt_class;
+
+ bpf_printk("ib_umad read recv : class 0x%x\n", class);
+
+ val = bpf_map_lookup_elem(&read_count, &class);
+ if (!val) {
+ bpf_map_update_elem(&read_count, &class, &zero, BPF_NOEXIST);
+ val = bpf_map_lookup_elem(&read_count, &class);
+ if (!val)
+ return 0;
+ }
+
+ (*val) += 1;
+
+ return 0;
+}
+SEC("tracepoint/ib_umad/ib_umad_read_send")
+int on_ib_umad_read_send(struct ib_umad_rw_args *ctx)
+{
+ u64 zero = 0, *val;
+ u8 class = ctx->mgmt_class;
+
+ bpf_printk("ib_umad read send : class 0x%x\n", class);
+
+ val = bpf_map_lookup_elem(&read_count, &class);
+ if (!val) {
+ bpf_map_update_elem(&read_count, &class, &zero, BPF_NOEXIST);
+ val = bpf_map_lookup_elem(&read_count, &class);
+ if (!val)
+ return 0;
+ }
+
+ (*val) += 1;
+
+ return 0;
+}
+SEC("tracepoint/ib_umad/ib_umad_write")
+int on_ib_umad_write(struct ib_umad_rw_args *ctx)
+{
+ u64 zero = 0, *val;
+ u8 class = ctx->mgmt_class;
+
+ bpf_printk("ib_umad write : class 0x%x\n", class);
+
+ val = bpf_map_lookup_elem(&write_count, &class);
+ if (!val) {
+ bpf_map_update_elem(&write_count, &class, &zero, BPF_NOEXIST);
+ val = bpf_map_lookup_elem(&write_count, &class);
+ if (!val)
+ return 0;
+ }
+
+ (*val) += 1;
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/ibumad_user.c b/samples/bpf/ibumad_user.c
new file mode 100644
index 0000000..cb5a8f9
--- /dev/null
+++ b/samples/bpf/ibumad_user.c
@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+
+/**
+ * ibumad BPF sample user side
+ *
+ * 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.
+ *
+ * Copyright(c) 2018 Ira Weiny, Intel Corporation
+ */
+
+#include <linux/bpf.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <limits.h>
+
+#include <sys/resource.h>
+#include <getopt.h>
+#include <net/if.h>
+
+#include "bpf_load.h"
+#include "bpf_util.h"
+#include "libbpf.h"
+
+static void dump_counts(int fd)
+{
+ __u32 key;
+ __u64 value;
+
+ for (key = 0; key < 256; key++) {
+ if (bpf_map_lookup_elem(fd, &key, &value)) {
+ printf("failed to read key %u\n", key);
+ continue;
+ }
+ if (value)
+ printf("0x%02x : %llu\n", key, value);
+ }
+}
+
+static void dump_all_counts(void)
+{
+ printf("Read 'Class : count'\n");
+ dump_counts(map_fd[0]);
+ printf("Write 'Class : count'\n");
+ dump_counts(map_fd[1]);
+}
+
+static void dump_exit(int sig)
+{
+ dump_all_counts();
+ exit(0);
+}
+
+static const struct option long_options[] = {
+ {"help", no_argument, NULL, 'h'},
+ {"delay", required_argument, NULL, 'd'},
+};
+
+static void usage(char *cmd)
+{
+ printf("eBPF test program to count packets from various IP addresses\n"
+ "Usage: %s <options>\n"
+ " --help, -h this menu\n"
+ " --delay, -d <delay> wait <delay> sec between prints [1 - 1000000]\n"
+ , cmd
+ );
+}
+
+int main(int argc, char **argv)
+{
+ unsigned long delay = 5;
+ int longindex = 0;
+ int opt;
+ char bpf_file[256];
+
+ /* Create the eBPF kernel code path name.
+ * This follows the pattern of all of the other bpf samples
+ */
+ snprintf(bpf_file, sizeof(bpf_file), "%s_kern.o", argv[0]);
+
+ /* Do one final dump when exiting */
+ signal(SIGINT, dump_exit);
+ signal(SIGTERM, dump_exit);
+
+ while ((opt = getopt_long(argc, argv, "hd:rSw",
+ long_options, &longindex)) != -1) {
+ switch (opt) {
+ case 'd':
+ delay = strtoul(optarg, NULL, 0);
+ if (delay == ULONG_MAX || delay < 0 ||
+ delay > 1000000) {
+ fprintf(stderr, "ERROR: invalid delay : %s\n",
+ optarg);
+ usage(argv[0]);
+ return 1;
+ }
+ break;
+ default:
+ case 'h':
+ usage(argv[0]);
+ return 1;
+ }
+ }
+
+ if (load_bpf_file(bpf_file)) {
+ fprintf(stderr, "ERROR: failed to load eBPF from file : %s\n",
+ bpf_file);
+ return 1;
+ }
+
+ while (1) {
+ sleep(delay);
+ dump_all_counts();
+ }
+
+ return 0;
+}
diff --git a/samples/bpf/lathist_user.c b/samples/bpf/lathist_user.c
index c8e88cc..2ff2839 100644
--- a/samples/bpf/lathist_user.c
+++ b/samples/bpf/lathist_user.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2013-2015 PLUMgrid, http://plumgrid.com
* Copyright (c) 2015 BMW Car IT GmbH
- *
- * 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 <unistd.h>
diff --git a/samples/bpf/load_sock_ops.c b/samples/bpf/load_sock_ops.c
deleted file mode 100644
index 8ecb41e..0000000
--- 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/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c
index 38b7b1a..fe5564b 100644
--- a/samples/bpf/map_perf_test_user.c
+++ b/samples/bpf/map_perf_test_user.c
@@ -1,8 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2016 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.
*/
#define _GNU_SOURCE
#include <sched.h>
diff --git a/samples/bpf/offwaketime_user.c b/samples/bpf/offwaketime_user.c
index f06063a..fc8767d 100644
--- a/samples/bpf/offwaketime_user.c
+++ b/samples/bpf/offwaketime_user.c
@@ -1,8 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2016 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 <unistd.h>
@@ -28,6 +25,11 @@
if (!addr)
return;
sym = ksym_search(addr);
+ if (!sym) {
+ printf("ksym not found. Is kallsyms loaded?\n");
+ return;
+ }
+
if (PRINT_RAW_ADDR)
printf("%s/%llx;", sym->name, addr);
else
diff --git a/samples/bpf/sampleip_user.c b/samples/bpf/sampleip_user.c
index 60c2b73..6b5dc26 100644
--- a/samples/bpf/sampleip_user.c
+++ b/samples/bpf/sampleip_user.c
@@ -1,15 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* sampleip: sample instruction pointer and frequency count in a BPF map.
*
* Copyright 2016 Netflix, Inc.
- *
- * 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 <stdio.h>
#include <unistd.h>
#include <errno.h>
#include <signal.h>
@@ -110,6 +106,11 @@
for (i = 0; i < max; i++) {
if (counts[i].ip > PAGE_OFFSET) {
sym = ksym_search(counts[i].ip);
+ if (!sym) {
+ printf("ksym not found. Is kallsyms loaded?\n");
+ continue;
+ }
+
printf("0x%-17llx %-32s %u\n", counts[i].ip, sym->name,
counts[i].count);
} else {
diff --git a/samples/bpf/sock_example.c b/samples/bpf/sock_example.c
index 60ec467..00aae1d 100644
--- a/samples/bpf/sock_example.c
+++ b/samples/bpf/sock_example.c
@@ -99,7 +99,7 @@
{
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 93ec01c..a219442 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 "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 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_kern.c b/samples/bpf/sockex2_kern.c
index f58acfc..f2f9dbc 100644
--- a/samples/bpf/sockex2_kern.c
+++ b/samples/bpf/sockex2_kern.c
@@ -14,7 +14,7 @@
__be16 h_vlan_encapsulated_proto;
};
-struct bpf_flow_keys {
+struct flow_key_record {
__be32 src;
__be32 dst;
union {
@@ -59,7 +59,7 @@
}
static inline __u64 parse_ip(struct __sk_buff *skb, __u64 nhoff, __u64 *ip_proto,
- struct bpf_flow_keys *flow)
+ struct flow_key_record *flow)
{
__u64 verlen;
@@ -83,7 +83,7 @@
}
static inline __u64 parse_ipv6(struct __sk_buff *skb, __u64 nhoff, __u64 *ip_proto,
- struct bpf_flow_keys *flow)
+ struct flow_key_record *flow)
{
*ip_proto = load_byte(skb,
nhoff + offsetof(struct ipv6hdr, nexthdr));
@@ -96,7 +96,8 @@
return nhoff;
}
-static inline bool flow_dissector(struct __sk_buff *skb, struct bpf_flow_keys *flow)
+static inline bool flow_dissector(struct __sk_buff *skb,
+ struct flow_key_record *flow)
{
__u64 nhoff = ETH_HLEN;
__u64 ip_proto;
@@ -198,7 +199,7 @@
SEC("socket2")
int bpf_prog2(struct __sk_buff *skb)
{
- struct bpf_flow_keys flow = {};
+ struct flow_key_record flow = {};
struct pair *value;
u32 key;
diff --git a/samples/bpf/sockex2_user.c b/samples/bpf/sockex2_user.c
index 1d5c6e9..6de383d 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 "libbpf.h"
#include "sock_example.h"
#include <unistd.h>
#include <arpa/inet.h>
@@ -17,32 +17,35 @@
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_kern.c b/samples/bpf/sockex3_kern.c
index 95907f8..c527b57 100644
--- a/samples/bpf/sockex3_kern.c
+++ b/samples/bpf/sockex3_kern.c
@@ -61,7 +61,7 @@
__be16 h_vlan_encapsulated_proto;
};
-struct bpf_flow_keys {
+struct flow_key_record {
__be32 src;
__be32 dst;
union {
@@ -88,7 +88,7 @@
}
struct globals {
- struct bpf_flow_keys flow;
+ struct flow_key_record flow;
};
struct bpf_map_def SEC("maps") percpu_map = {
@@ -114,14 +114,14 @@
struct bpf_map_def SEC("maps") hash_map = {
.type = BPF_MAP_TYPE_HASH,
- .key_size = sizeof(struct bpf_flow_keys),
+ .key_size = sizeof(struct flow_key_record),
.value_size = sizeof(struct pair),
.max_entries = 1024,
};
static void update_stats(struct __sk_buff *skb, struct globals *g)
{
- struct bpf_flow_keys key = g->flow;
+ struct flow_key_record key = g->flow;
struct pair *value;
value = bpf_map_lookup_elem(&hash_map, &key);
diff --git a/samples/bpf/sockex3_user.c b/samples/bpf/sockex3_user.c
index 5ba3ae9..bbb1cd0 100644
--- a/samples/bpf/sockex3_user.c
+++ b/samples/bpf/sockex3_user.c
@@ -13,7 +13,7 @@
#define PARSE_IP_PROG_FD (prog_fd[0])
#define PROG_ARRAY_FD (map_fd[0])
-struct bpf_flow_keys {
+struct flow_key_record {
__be32 src;
__be32 dst;
union {
@@ -58,13 +58,13 @@
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;
for (i = 0; i < 5; i++) {
- struct bpf_flow_keys key = {}, next_key;
+ struct flow_key_record key = {}, next_key;
struct pair value;
sleep(1);
diff --git a/samples/bpf/spintest_user.c b/samples/bpf/spintest_user.c
index 8d3e9cf..2556af2 100644
--- a/samples/bpf/spintest_user.c
+++ b/samples/bpf/spintest_user.c
@@ -37,8 +37,13 @@
bpf_map_lookup_elem(map_fd[0], &next_key, &value);
assert(next_key == value);
sym = ksym_search(value);
- printf(" %s", sym->name);
key = next_key;
+ if (!sym) {
+ printf("ksym not found. Is kallsyms loaded?\n");
+ continue;
+ }
+
+ printf(" %s", sym->name);
}
if (key)
printf("\n");
diff --git a/samples/bpf/syscall_nrs.c b/samples/bpf/syscall_nrs.c
index 516e255..88f9400 100644
--- a/samples/bpf/syscall_nrs.c
+++ b/samples/bpf/syscall_nrs.c
@@ -9,5 +9,11 @@
COMMENT("Linux system call numbers.");
SYSNR(__NR_write);
SYSNR(__NR_read);
+#ifdef __NR_mmap2
+ SYSNR(__NR_mmap2);
+#endif
+#ifdef __NR_mmap
SYSNR(__NR_mmap);
+#endif
+
}
diff --git a/samples/bpf/syscall_tp_kern.c b/samples/bpf/syscall_tp_kern.c
index 9149c52..1d78819 100644
--- a/samples/bpf/syscall_tp_kern.c
+++ b/samples/bpf/syscall_tp_kern.c
@@ -1,8 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* 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 <uapi/linux/bpf.h>
#include "bpf_helpers.h"
diff --git a/samples/bpf/syscall_tp_user.c b/samples/bpf/syscall_tp_user.c
index 1a1d005..57014ba 100644
--- a/samples/bpf/syscall_tp_user.c
+++ b/samples/bpf/syscall_tp_user.c
@@ -1,8 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* 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 <unistd.h>
diff --git a/samples/bpf/task_fd_query_kern.c b/samples/bpf/task_fd_query_kern.c
index f4b0a9e..fb56fc2 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 8381d79..4c31b30 100644
--- a/samples/bpf/task_fd_query_user.c
+++ b/samples/bpf/task_fd_query_user.c
@@ -13,6 +13,7 @@
#include <sys/resource.h>
#include <sys/types.h>
#include <sys/stat.h>
+#include <linux/perf_event.h>
#include "libbpf.h"
#include "bpf_load.h"
@@ -216,7 +217,7 @@
{
const char *event_type = "uprobe";
struct perf_event_attr attr = {};
- char buf[256], event_alias[256];
+ char buf[256], event_alias[sizeof("test_1234567890")];
__u64 probe_offset, probe_addr;
__u32 len, prog_id, fd_type;
int err, res, kfd, efd;
@@ -311,7 +312,7 @@
}
/* 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/tc_l2_redirect_user.c b/samples/bpf/tc_l2_redirect_user.c
index 7ec45c3..d11a6e1 100644
--- a/samples/bpf/tc_l2_redirect_user.c
+++ b/samples/bpf/tc_l2_redirect_user.c
@@ -1,8 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2016 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 <linux/unistd.h>
#include <linux/bpf.h>
diff --git a/samples/bpf/tcp_basertt_kern.c b/samples/bpf/tcp_basertt_kern.c
index 4bf4fc5..9dba48c 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>
@@ -21,13 +21,6 @@
#define DEBUG 1
-#define bpf_printk(fmt, ...) \
-({ \
- char ____fmt[] = fmt; \
- bpf_trace_printk(____fmt, sizeof(____fmt), \
- ##__VA_ARGS__); \
-})
-
SEC("sockops")
int bpf_basertt(struct bpf_sock_ops *skops)
{
diff --git a/samples/bpf/tcp_bpf.readme b/samples/bpf/tcp_bpf.readme
index 831fb60..78e247f 100644
--- a/samples/bpf/tcp_bpf.readme
+++ b/samples/bpf/tcp_bpf.readme
@@ -8,14 +8,16 @@
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 @@
To remove (unattach) a socket_ops BPF program from a cgroupv2:
- ./load_sock_ops -r /tmp/cgroupv2/foo
+ bpftool cgroup detach /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 0566b7f..af8486f 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>
@@ -22,13 +22,6 @@
#define DEBUG 1
-#define bpf_printk(fmt, ...) \
-({ \
- char ____fmt[] = fmt; \
- bpf_trace_printk(____fmt, sizeof(____fmt), \
- ##__VA_ARGS__); \
-})
-
SEC("sockops")
int bpf_bufs(struct bpf_sock_ops *skops)
{
diff --git a/samples/bpf/tcp_clamp_kern.c b/samples/bpf/tcp_clamp_kern.c
index f4225c9..26c0fd0 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>
@@ -22,13 +22,6 @@
#define DEBUG 1
-#define bpf_printk(fmt, ...) \
-({ \
- char ____fmt[] = fmt; \
- bpf_trace_printk(____fmt, sizeof(____fmt), \
- ##__VA_ARGS__); \
-})
-
SEC("sockops")
int bpf_clamp(struct bpf_sock_ops *skops)
{
diff --git a/samples/bpf/tcp_cong_kern.c b/samples/bpf/tcp_cong_kern.c
index ad0f1ba..6d4dc4c 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>
@@ -21,13 +21,6 @@
#define DEBUG 1
-#define bpf_printk(fmt, ...) \
-({ \
- char ____fmt[] = fmt; \
- bpf_trace_printk(____fmt, sizeof(____fmt), \
- ##__VA_ARGS__); \
-})
-
SEC("sockops")
int bpf_cong(struct bpf_sock_ops *skops)
{
diff --git a/samples/bpf/tcp_dumpstats_kern.c b/samples/bpf/tcp_dumpstats_kern.c
new file mode 100644
index 0000000..8557913
--- /dev/null
+++ b/samples/bpf/tcp_dumpstats_kern.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Refer to samples/bpf/tcp_bpf.readme for the instructions on
+ * how to run this sample program.
+ */
+#include <linux/bpf.h>
+
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+#define INTERVAL 1000000000ULL
+
+int _version SEC("version") = 1;
+char _license[] SEC("license") = "GPL";
+
+struct {
+ __u32 type;
+ __u32 map_flags;
+ int *key;
+ __u64 *value;
+} bpf_next_dump SEC(".maps") = {
+ .type = BPF_MAP_TYPE_SK_STORAGE,
+ .map_flags = BPF_F_NO_PREALLOC,
+};
+
+SEC("sockops")
+int _sockops(struct bpf_sock_ops *ctx)
+{
+ struct bpf_tcp_sock *tcp_sk;
+ struct bpf_sock *sk;
+ __u64 *next_dump;
+ __u64 now;
+
+ switch (ctx->op) {
+ case BPF_SOCK_OPS_TCP_CONNECT_CB:
+ bpf_sock_ops_cb_flags_set(ctx, BPF_SOCK_OPS_RTT_CB_FLAG);
+ return 1;
+ case BPF_SOCK_OPS_RTT_CB:
+ break;
+ default:
+ return 1;
+ }
+
+ sk = ctx->sk;
+ if (!sk)
+ return 1;
+
+ next_dump = bpf_sk_storage_get(&bpf_next_dump, sk, 0,
+ BPF_SK_STORAGE_GET_F_CREATE);
+ if (!next_dump)
+ return 1;
+
+ now = bpf_ktime_get_ns();
+ if (now < *next_dump)
+ return 1;
+
+ tcp_sk = bpf_tcp_sock(sk);
+ if (!tcp_sk)
+ return 1;
+
+ *next_dump = now + INTERVAL;
+
+ bpf_printk("dsack_dups=%u delivered=%u\n",
+ tcp_sk->dsack_dups, tcp_sk->delivered);
+ bpf_printk("delivered_ce=%u icsk_retransmits=%u\n",
+ tcp_sk->delivered_ce, tcp_sk->icsk_retransmits);
+
+ return 1;
+}
diff --git a/samples/bpf/tcp_iw_kern.c b/samples/bpf/tcp_iw_kern.c
index 4ca5ecc..da61d53 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>
@@ -22,13 +22,6 @@
#define DEBUG 1
-#define bpf_printk(fmt, ...) \
-({ \
- char ____fmt[] = fmt; \
- bpf_trace_printk(____fmt, sizeof(____fmt), \
- ##__VA_ARGS__); \
-})
-
SEC("sockops")
int bpf_iw(struct bpf_sock_ops *skops)
{
diff --git a/samples/bpf/tcp_rwnd_kern.c b/samples/bpf/tcp_rwnd_kern.c
index 09ff65b..d011e38 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>
@@ -21,13 +21,6 @@
#define DEBUG 1
-#define bpf_printk(fmt, ...) \
-({ \
- char ____fmt[] = fmt; \
- bpf_trace_printk(____fmt, sizeof(____fmt), \
- ##__VA_ARGS__); \
-})
-
SEC("sockops")
int bpf_rwnd(struct bpf_sock_ops *skops)
{
diff --git a/samples/bpf/tcp_synrto_kern.c b/samples/bpf/tcp_synrto_kern.c
index 232bb24..720d195 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>
@@ -21,13 +21,6 @@
#define DEBUG 1
-#define bpf_printk(fmt, ...) \
-({ \
- char ____fmt[] = fmt; \
- bpf_trace_printk(____fmt, sizeof(____fmt), \
- ##__VA_ARGS__); \
-})
-
SEC("sockops")
int bpf_synrto(struct bpf_sock_ops *skops)
{
diff --git a/samples/bpf/tcp_tos_reflect_kern.c b/samples/bpf/tcp_tos_reflect_kern.c
new file mode 100644
index 0000000..369faca
--- /dev/null
+++ b/samples/bpf/tcp_tos_reflect_kern.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 Facebook
+ *
+ * BPF program to automatically reflect TOS option from received syn packet
+ *
+ * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/tcp.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 <linux/socket.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+#define DEBUG 1
+
+SEC("sockops")
+int bpf_basertt(struct bpf_sock_ops *skops)
+{
+ char header[sizeof(struct ipv6hdr)];
+ struct ipv6hdr *hdr6;
+ struct iphdr *hdr;
+ int hdr_size = 0;
+ int save_syn = 1;
+ int tos = 0;
+ int rv = 0;
+ int op;
+
+ op = (int) skops->op;
+
+#ifdef DEBUG
+ bpf_printk("BPF command: %d\n", op);
+#endif
+ switch (op) {
+ case BPF_SOCK_OPS_TCP_LISTEN_CB:
+ rv = bpf_setsockopt(skops, SOL_TCP, TCP_SAVE_SYN,
+ &save_syn, sizeof(save_syn));
+ break;
+ case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+ if (skops->family == AF_INET)
+ hdr_size = sizeof(struct iphdr);
+ else
+ hdr_size = sizeof(struct ipv6hdr);
+ rv = bpf_getsockopt(skops, SOL_TCP, TCP_SAVED_SYN,
+ header, hdr_size);
+ if (!rv) {
+ if (skops->family == AF_INET) {
+ hdr = (struct iphdr *) header;
+ tos = hdr->tos;
+ if (tos != 0)
+ bpf_setsockopt(skops, SOL_IP, IP_TOS,
+ &tos, sizeof(tos));
+ } else {
+ hdr6 = (struct ipv6hdr *) header;
+ tos = ((hdr6->priority) << 4 |
+ (hdr6->flow_lbl[0]) >> 4);
+ if (tos)
+ bpf_setsockopt(skops, SOL_IPV6,
+ IPV6_TCLASS,
+ &tos, sizeof(tos));
+ }
+ rv = 0;
+ }
+ break;
+ default:
+ rv = -1;
+ }
+#ifdef DEBUG
+ bpf_printk("Returning %d\n", rv);
+#endif
+ skops->reply = rv;
+ return 1;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/test_cgrp2_array_pin.c b/samples/bpf/test_cgrp2_array_pin.c
index 2421842..6d564aa 100644
--- a/samples/bpf/test_cgrp2_array_pin.c
+++ b/samples/bpf/test_cgrp2_array_pin.c
@@ -1,8 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2016 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 <linux/unistd.h>
#include <linux/bpf.h>
diff --git a/samples/bpf/test_cgrp2_attach2.c b/samples/bpf/test_cgrp2_attach2.c
deleted file mode 100644
index 180f9d8..0000000
--- a/samples/bpf/test_cgrp2_attach2.c
+++ /dev/null
@@ -1,442 +0,0 @@
-/* eBPF example program:
- *
- * - Creates arraymap in kernel with 4 bytes keys and 8 byte values
- *
- * - Loads eBPF program
- *
- * The eBPF program accesses the map passed in to store two pieces of
- * information. The number of invocations of the program, which maps
- * to the number of packets received, is stored to key 0. Key 1 is
- * incremented on each iteration by the number of bytes stored in
- * the skb. The program also stores the number of received bytes
- * in the cgroup storage.
- *
- * - Attaches the new program to a cgroup using BPF_PROG_ATTACH
- *
- * - Every second, reads map[0] and map[1] to see how many bytes and
- * packets were seen on any socket of tasks in the given cgroup.
- */
-
-#define _GNU_SOURCE
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <assert.h>
-#include <sys/resource.h>
-#include <sys/time.h>
-#include <unistd.h>
-
-#include <linux/bpf.h>
-#include <bpf/bpf.h>
-
-#include "bpf_insn.h"
-#include "bpf_rlimit.h"
-#include "cgroup_helpers.h"
-
-#define FOO "/foo"
-#define BAR "/foo/bar/"
-#define PING_CMD "ping -c1 -w1 127.0.0.1 > /dev/null"
-
-char bpf_log_buf[BPF_LOG_BUF_SIZE];
-
-static int prog_load(int verdict)
-{
- int ret;
- struct bpf_insn prog[] = {
- BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */
- BPF_EXIT_INSN(),
- };
- size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
-
- ret = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB,
- prog, insns_cnt, "GPL", 0,
- bpf_log_buf, BPF_LOG_BUF_SIZE);
-
- if (ret < 0) {
- log_err("Loading program");
- printf("Output from verifier:\n%s\n-------\n", bpf_log_buf);
- return 0;
- }
- return ret;
-}
-
-static int test_foo_bar(void)
-{
- int drop_prog, allow_prog, foo = 0, bar = 0, rc = 0;
-
- allow_prog = prog_load(1);
- if (!allow_prog)
- goto err;
-
- drop_prog = prog_load(0);
- if (!drop_prog)
- goto err;
-
- if (setup_cgroup_environment())
- goto err;
-
- /* Create cgroup /foo, get fd, and join it */
- foo = create_and_get_cgroup(FOO);
- if (!foo)
- goto err;
-
- if (join_cgroup(FOO))
- goto err;
-
- if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS,
- BPF_F_ALLOW_OVERRIDE)) {
- log_err("Attaching prog to /foo");
- goto err;
- }
-
- printf("Attached DROP prog. This ping in cgroup /foo should fail...\n");
- assert(system(PING_CMD) != 0);
-
- /* Create cgroup /foo/bar, get fd, and join it */
- bar = create_and_get_cgroup(BAR);
- if (!bar)
- goto err;
-
- if (join_cgroup(BAR))
- goto err;
-
- printf("Attached DROP prog. This ping in cgroup /foo/bar should fail...\n");
- assert(system(PING_CMD) != 0);
-
- if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS,
- BPF_F_ALLOW_OVERRIDE)) {
- log_err("Attaching prog to /foo/bar");
- goto err;
- }
-
- printf("Attached PASS prog. This ping in cgroup /foo/bar should pass...\n");
- assert(system(PING_CMD) == 0);
-
- if (bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS)) {
- log_err("Detaching program from /foo/bar");
- goto err;
- }
-
- printf("Detached PASS from /foo/bar while DROP is attached to /foo.\n"
- "This ping in cgroup /foo/bar should fail...\n");
- assert(system(PING_CMD) != 0);
-
- if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS,
- BPF_F_ALLOW_OVERRIDE)) {
- log_err("Attaching prog to /foo/bar");
- goto err;
- }
-
- if (bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS)) {
- log_err("Detaching program from /foo");
- goto err;
- }
-
- printf("Attached PASS from /foo/bar and detached DROP from /foo.\n"
- "This ping in cgroup /foo/bar should pass...\n");
- assert(system(PING_CMD) == 0);
-
- if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS,
- BPF_F_ALLOW_OVERRIDE)) {
- log_err("Attaching prog to /foo/bar");
- goto err;
- }
-
- if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0)) {
- errno = 0;
- log_err("Unexpected success attaching prog to /foo/bar");
- goto err;
- }
-
- if (bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS)) {
- log_err("Detaching program from /foo/bar");
- goto err;
- }
-
- if (!bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS)) {
- errno = 0;
- log_err("Unexpected success in double detach from /foo");
- goto err;
- }
-
- if (bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, 0)) {
- log_err("Attaching non-overridable prog to /foo");
- goto err;
- }
-
- if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0)) {
- errno = 0;
- log_err("Unexpected success attaching non-overridable prog to /foo/bar");
- goto err;
- }
-
- if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS,
- BPF_F_ALLOW_OVERRIDE)) {
- errno = 0;
- log_err("Unexpected success attaching overridable prog to /foo/bar");
- goto err;
- }
-
- if (!bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS,
- BPF_F_ALLOW_OVERRIDE)) {
- errno = 0;
- log_err("Unexpected success attaching overridable prog to /foo");
- goto err;
- }
-
- if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, 0)) {
- log_err("Attaching different non-overridable prog to /foo");
- goto err;
- }
-
- goto out;
-
-err:
- rc = 1;
-
-out:
- close(foo);
- close(bar);
- cleanup_cgroup_environment();
- if (!rc)
- printf("### override:PASS\n");
- else
- printf("### override:FAIL\n");
- return rc;
-}
-
-static int map_fd = -1;
-
-static int prog_load_cnt(int verdict, int val)
-{
- int cgroup_storage_fd;
-
- if (map_fd < 0)
- map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0);
- if (map_fd < 0) {
- printf("failed to create map '%s'\n", strerror(errno));
- return -1;
- }
-
- cgroup_storage_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE,
- sizeof(struct bpf_cgroup_storage_key), 8, 0, 0);
- if (cgroup_storage_fd < 0) {
- printf("failed to create map '%s'\n", strerror(errno));
- return -1;
- }
-
- struct bpf_insn prog[] = {
- BPF_MOV32_IMM(BPF_REG_0, 0),
- BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */
- BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
- BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */
- BPF_LD_MAP_FD(BPF_REG_1, map_fd),
- BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
- BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
- BPF_MOV64_IMM(BPF_REG_1, val), /* r1 = 1 */
- BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */
- BPF_LD_MAP_FD(BPF_REG_1, cgroup_storage_fd),
- BPF_MOV64_IMM(BPF_REG_2, 0),
- BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
- BPF_MOV64_IMM(BPF_REG_1, val),
- BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_W, BPF_REG_0, BPF_REG_1, 0, 0),
- BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */
- BPF_EXIT_INSN(),
- };
- size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
- int ret;
-
- ret = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB,
- prog, insns_cnt, "GPL", 0,
- bpf_log_buf, BPF_LOG_BUF_SIZE);
-
- if (ret < 0) {
- log_err("Loading program");
- printf("Output from verifier:\n%s\n-------\n", bpf_log_buf);
- return 0;
- }
- close(cgroup_storage_fd);
- return ret;
-}
-
-
-static int test_multiprog(void)
-{
- __u32 prog_ids[4], prog_cnt = 0, attach_flags, saved_prog_id;
- int cg1 = 0, cg2 = 0, cg3 = 0, cg4 = 0, cg5 = 0, key = 0;
- int drop_prog, allow_prog[6] = {}, rc = 0;
- unsigned long long value;
- int i = 0;
-
- for (i = 0; i < 6; i++) {
- allow_prog[i] = prog_load_cnt(1, 1 << i);
- if (!allow_prog[i])
- goto err;
- }
- drop_prog = prog_load_cnt(0, 1);
- if (!drop_prog)
- goto err;
-
- if (setup_cgroup_environment())
- goto err;
-
- cg1 = create_and_get_cgroup("/cg1");
- if (!cg1)
- goto err;
- cg2 = create_and_get_cgroup("/cg1/cg2");
- if (!cg2)
- goto err;
- cg3 = create_and_get_cgroup("/cg1/cg2/cg3");
- if (!cg3)
- goto err;
- cg4 = create_and_get_cgroup("/cg1/cg2/cg3/cg4");
- if (!cg4)
- goto err;
- cg5 = create_and_get_cgroup("/cg1/cg2/cg3/cg4/cg5");
- if (!cg5)
- goto err;
-
- if (join_cgroup("/cg1/cg2/cg3/cg4/cg5"))
- goto err;
-
- if (bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS,
- BPF_F_ALLOW_MULTI)) {
- log_err("Attaching prog to cg1");
- goto err;
- }
- if (!bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS,
- BPF_F_ALLOW_MULTI)) {
- log_err("Unexpected success attaching the same prog to cg1");
- goto err;
- }
- if (bpf_prog_attach(allow_prog[1], cg1, BPF_CGROUP_INET_EGRESS,
- BPF_F_ALLOW_MULTI)) {
- log_err("Attaching prog2 to cg1");
- goto err;
- }
- if (bpf_prog_attach(allow_prog[2], cg2, BPF_CGROUP_INET_EGRESS,
- BPF_F_ALLOW_OVERRIDE)) {
- log_err("Attaching prog to cg2");
- goto err;
- }
- if (bpf_prog_attach(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS,
- BPF_F_ALLOW_MULTI)) {
- log_err("Attaching prog to cg3");
- goto err;
- }
- if (bpf_prog_attach(allow_prog[4], cg4, BPF_CGROUP_INET_EGRESS,
- BPF_F_ALLOW_OVERRIDE)) {
- log_err("Attaching prog to cg4");
- goto err;
- }
- if (bpf_prog_attach(allow_prog[5], cg5, BPF_CGROUP_INET_EGRESS, 0)) {
- log_err("Attaching prog to cg5");
- goto err;
- }
- assert(system(PING_CMD) == 0);
- assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0);
- assert(value == 1 + 2 + 8 + 32);
-
- /* query the number of effective progs in cg5 */
- assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE,
- NULL, NULL, &prog_cnt) == 0);
- assert(prog_cnt == 4);
- /* retrieve prog_ids of effective progs in cg5 */
- assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE,
- &attach_flags, prog_ids, &prog_cnt) == 0);
- assert(prog_cnt == 4);
- assert(attach_flags == 0);
- saved_prog_id = prog_ids[0];
- /* check enospc handling */
- prog_ids[0] = 0;
- prog_cnt = 2;
- assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE,
- &attach_flags, prog_ids, &prog_cnt) == -1 &&
- errno == ENOSPC);
- assert(prog_cnt == 4);
- /* check that prog_ids are returned even when buffer is too small */
- assert(prog_ids[0] == saved_prog_id);
- /* retrieve prog_id of single attached prog in cg5 */
- prog_ids[0] = 0;
- assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0,
- NULL, prog_ids, &prog_cnt) == 0);
- assert(prog_cnt == 1);
- assert(prog_ids[0] == saved_prog_id);
-
- /* detach bottom program and ping again */
- if (bpf_prog_detach2(-1, cg5, BPF_CGROUP_INET_EGRESS)) {
- log_err("Detaching prog from cg5");
- goto err;
- }
- value = 0;
- assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0);
- assert(system(PING_CMD) == 0);
- assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0);
- assert(value == 1 + 2 + 8 + 16);
-
- /* detach 3rd from bottom program and ping again */
- errno = 0;
- if (!bpf_prog_detach2(0, cg3, BPF_CGROUP_INET_EGRESS)) {
- log_err("Unexpected success on detach from cg3");
- goto err;
- }
- if (bpf_prog_detach2(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS)) {
- log_err("Detaching from cg3");
- goto err;
- }
- value = 0;
- assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0);
- assert(system(PING_CMD) == 0);
- assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0);
- assert(value == 1 + 2 + 16);
-
- /* detach 2nd from bottom program and ping again */
- if (bpf_prog_detach2(-1, cg4, BPF_CGROUP_INET_EGRESS)) {
- log_err("Detaching prog from cg4");
- goto err;
- }
- value = 0;
- assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0);
- assert(system(PING_CMD) == 0);
- assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0);
- assert(value == 1 + 2 + 4);
-
- prog_cnt = 4;
- assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE,
- &attach_flags, prog_ids, &prog_cnt) == 0);
- assert(prog_cnt == 3);
- assert(attach_flags == 0);
- assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0,
- NULL, prog_ids, &prog_cnt) == 0);
- assert(prog_cnt == 0);
- goto out;
-err:
- rc = 1;
-
-out:
- for (i = 0; i < 6; i++)
- if (allow_prog[i] > 0)
- close(allow_prog[i]);
- close(cg1);
- close(cg2);
- close(cg3);
- close(cg4);
- close(cg5);
- cleanup_cgroup_environment();
- if (!rc)
- printf("### multi:PASS\n");
- else
- printf("### multi:FAIL\n");
- return rc;
-}
-
-int main(int argc, char **argv)
-{
- int rc = 0;
-
- rc = test_foo_bar();
- if (rc)
- return rc;
-
- return test_multiprog();
-}
diff --git a/samples/bpf/test_current_task_under_cgroup_user.c b/samples/bpf/test_current_task_under_cgroup_user.c
index 4be4874..06e9f8c 100644
--- a/samples/bpf/test_current_task_under_cgroup_user.c
+++ b/samples/bpf/test_current_task_under_cgroup_user.c
@@ -1,8 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2016 Sargun Dhillon <sargun@sargun.me>
- *
- * 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.
*/
#define _GNU_SOURCE
@@ -11,7 +8,6 @@
#include <unistd.h>
#include <bpf/bpf.h>
#include "bpf_load.h"
-#include <linux/bpf.h>
#include "cgroup_helpers.h"
#define CGROUP_PATH "/my-cgroup"
@@ -33,7 +29,7 @@
cg2 = create_and_get_cgroup(CGROUP_PATH);
- if (!cg2)
+ if (cg2 < 0)
goto err;
if (bpf_map_update_elem(map_fd[0], &idx, &cg2, BPF_ANY)) {
diff --git a/samples/bpf/test_lru_dist.c b/samples/bpf/test_lru_dist.c
index eec3e25..b313dba 100644
--- a/samples/bpf/test_lru_dist.c
+++ b/samples/bpf/test_lru_dist.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2016 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.
*/
#define _GNU_SOURCE
#include <linux/types.h>
diff --git a/samples/bpf/test_map_in_map_user.c b/samples/bpf/test_map_in_map_user.c
index e308858..eb29bcb 100644
--- a/samples/bpf/test_map_in_map_user.c
+++ b/samples/bpf/test_map_in_map_user.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* 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 <sys/resource.h>
#include <sys/socket.h>
diff --git a/samples/bpf/test_overhead_user.c b/samples/bpf/test_overhead_user.c
index 9d6dcaa..94f7411 100644
--- a/samples/bpf/test_overhead_user.c
+++ b/samples/bpf/test_overhead_user.c
@@ -1,8 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2016 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.
*/
#define _GNU_SOURCE
#include <sched.h>
diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c
index d08046a..16a16ea 100644
--- a/samples/bpf/trace_event_user.c
+++ b/samples/bpf/trace_event_user.c
@@ -1,8 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2016 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 <unistd.h>
@@ -34,6 +31,11 @@
if (!addr)
return;
sym = ksym_search(addr);
+ if (!sym) {
+ printf("ksym not found. Is kallsyms loaded?\n");
+ return;
+ }
+
printf("%s;", sym->name);
if (!strcmp(sym->name, "sys_read"))
sys_read_seen = true;
diff --git a/samples/bpf/trace_output_user.c b/samples/bpf/trace_output_user.c
index 4837d73..8ee4769 100644
--- a/samples/bpf/trace_output_user.c
+++ b/samples/bpf/trace_output_user.c
@@ -1,7 +1,4 @@
-/* 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.
- */
+// SPDX-License-Identifier: GPL-2.0-only
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
@@ -21,9 +18,6 @@
#include <libbpf.h>
#include "bpf_load.h"
#include "perf-sys.h"
-#include "trace_helpers.h"
-
-static int pmu_fd;
static __u64 time_get_ns(void)
{
@@ -34,12 +28,12 @@
}
static __u64 start_time;
+static __u64 cnt;
#define MAX_CNT 100000ll
-static int print_bpf_output(void *data, int size)
+static void print_bpf_output(void *ctx, int cpu, void *data, __u32 size)
{
- static __u64 cnt;
struct {
__u64 pid;
__u64 cookie;
@@ -48,7 +42,7 @@
if (e->cookie != 0x12345678) {
printf("BUG pid %llx cookie %llx sized %d\n",
e->pid, e->cookie, size);
- return LIBBPF_PERF_EVENT_ERROR;
+ return;
}
cnt++;
@@ -56,30 +50,14 @@
if (cnt == MAX_CNT) {
printf("recv %lld events per sec\n",
MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
- return LIBBPF_PERF_EVENT_DONE;
+ return;
}
-
- return LIBBPF_PERF_EVENT_CONT;
-}
-
-static void test_bpf_perf_event(void)
-{
- struct perf_event_attr attr = {
- .sample_type = PERF_SAMPLE_RAW,
- .type = PERF_TYPE_SOFTWARE,
- .config = PERF_COUNT_SW_BPF_OUTPUT,
- };
- int key = 0;
-
- pmu_fd = sys_perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0);
-
- assert(pmu_fd >= 0);
- assert(bpf_map_update_elem(map_fd[0], &key, &pmu_fd, BPF_ANY) == 0);
- ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
}
int main(int argc, char **argv)
{
+ struct perf_buffer_opts pb_opts = {};
+ struct perf_buffer *pb;
char filename[256];
FILE *f;
int ret;
@@ -91,16 +69,20 @@
return 1;
}
- test_bpf_perf_event();
-
- if (perf_event_mmap(pmu_fd) < 0)
+ pb_opts.sample_cb = print_bpf_output;
+ pb = perf_buffer__new(map_fd[0], 8, &pb_opts);
+ ret = libbpf_get_error(pb);
+ if (ret) {
+ printf("failed to setup perf_buffer: %d\n", ret);
return 1;
+ }
f = popen("taskset 1 dd if=/dev/zero of=/dev/null", "r");
(void) f;
start_time = time_get_ns();
- ret = perf_event_poller(pmu_fd, print_bpf_output);
+ while ((ret = perf_buffer__poll(pb, 1000)) >= 0 && cnt < MAX_CNT) {
+ }
kill(0, SIGINT);
return ret;
}
diff --git a/samples/bpf/tracex2_user.c b/samples/bpf/tracex2_user.c
index 1a81e6a..c9544a4 100644
--- a/samples/bpf/tracex2_user.c
+++ b/samples/bpf/tracex2_user.c
@@ -131,7 +131,7 @@
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 9974c3d..ea1d4c1 100644
--- a/samples/bpf/tracex3_kern.c
+++ b/samples/bpf/tracex3_kern.c
@@ -20,7 +20,7 @@
/* 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/tracex3_user.c b/samples/bpf/tracex3_user.c
index 6c6b10f..cf8fedc 100644
--- a/samples/bpf/tracex3_user.c
+++ b/samples/bpf/tracex3_user.c
@@ -1,8 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2013-2015 PLUMgrid, http://plumgrid.com
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
*/
#include <stdio.h>
#include <stdlib.h>
@@ -17,8 +14,6 @@
#include "bpf_load.h"
#include "bpf_util.h"
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
-
#define SLOTS 100
static void clear_stats(int fd)
diff --git a/samples/bpf/tracex4_user.c b/samples/bpf/tracex4_user.c
index 14625c8..ec52203 100644
--- a/samples/bpf/tracex4_user.c
+++ b/samples/bpf/tracex4_user.c
@@ -1,8 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2015 PLUMgrid, http://plumgrid.com
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
*/
#include <stdio.h>
#include <stdlib.h>
diff --git a/samples/bpf/tracex5_kern.c b/samples/bpf/tracex5_kern.c
index f57f4e1..35cb0ee 100644
--- a/samples/bpf/tracex5_kern.c
+++ b/samples/bpf/tracex5_kern.c
@@ -68,12 +68,25 @@
return 0;
}
-PROG(SYS__NR_mmap)(struct pt_regs *ctx)
+#ifdef __NR_mmap2
+PROG(SYS__NR_mmap2)(struct pt_regs *ctx)
{
- char fmt[] = "mmap\n";
+ char fmt[] = "mmap2\n";
+
bpf_trace_printk(fmt, sizeof(fmt));
return 0;
}
+#endif
+
+#ifdef __NR_mmap
+PROG(SYS__NR_mmap)(struct pt_regs *ctx)
+{
+ char fmt[] = "mmap\n";
+
+ bpf_trace_printk(fmt, sizeof(fmt));
+ return 0;
+}
+#endif
char _license[] SEC("license") = "GPL";
u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c
index b02c531..a8e5fa0 100644
--- a/samples/bpf/xdp1_user.c
+++ b/samples/bpf/xdp1_user.c
@@ -1,8 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2016 PLUMgrid
- *
- * 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 <linux/bpf.h>
#include <linux/if_link.h>
@@ -15,17 +12,30 @@
#include <unistd.h>
#include <libgen.h>
#include <sys/resource.h>
+#include <net/if.h>
#include "bpf_util.h"
-#include "bpf/bpf.h"
-#include "bpf/libbpf.h"
+#include "bpf.h"
+#include "libbpf.h"
static int ifindex;
-static __u32 xdp_flags;
+static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+static __u32 prog_id;
static void int_exit(int sig)
{
- bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
+ __u32 curr_prog_id = 0;
+
+ if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) {
+ printf("bpf_get_link_xdp_id failed\n");
+ exit(1);
+ }
+ if (prog_id == curr_prog_id)
+ bpf_set_link_xdp_fd(ifindex, -1, 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(0);
}
@@ -34,26 +44,24 @@
static void poll_stats(int map_fd, int interval)
{
unsigned int nr_cpus = bpf_num_possible_cpus();
- const unsigned int nr_keys = 256;
- __u64 values[nr_cpus], prev[nr_keys][nr_cpus];
- __u32 key;
+ __u64 values[nr_cpus], prev[UINT8_MAX] = { 0 };
int i;
- memset(prev, 0, sizeof(prev));
-
while (1) {
+ __u32 key = UINT32_MAX;
+
sleep(interval);
- for (key = 0; key < nr_keys; key++) {
+ while (bpf_map_get_next_key(map_fd, &key, &key) != -1) {
__u64 sum = 0;
assert(bpf_map_lookup_elem(map_fd, &key, values) == 0);
for (i = 0; i < nr_cpus; i++)
- sum += (values[i] - prev[key][i]);
- if (sum)
+ sum += values[i];
+ if (sum > prev[key])
printf("proto %u: %10llu pkt/s\n",
- key, sum / interval);
- memcpy(prev[key], values, sizeof(values));
+ key, (sum - prev[key]) / interval);
+ prev[key] = sum;
}
}
}
@@ -61,10 +69,11 @@
static void usage(const char *prog)
{
fprintf(stderr,
- "usage: %s [OPTS] IFINDEX\n\n"
+ "usage: %s [OPTS] IFACE\n\n"
"OPTS:\n"
" -S use skb-mode\n"
- " -N enforce native mode\n",
+ " -N enforce native mode\n"
+ " -F force loading prog\n",
prog);
}
@@ -74,11 +83,14 @@
struct bpf_prog_load_attr prog_load_attr = {
.prog_type = BPF_PROG_TYPE_XDP,
};
- const char *optstr = "SN";
+ struct bpf_prog_info info = {};
+ __u32 info_len = sizeof(info);
+ const char *optstr = "FSN";
int prog_fd, map_fd, opt;
struct bpf_object *obj;
struct bpf_map *map;
char filename[256];
+ int err;
while ((opt = getopt(argc, argv, optstr)) != -1) {
switch (opt) {
@@ -88,6 +100,9 @@
case 'N':
xdp_flags |= XDP_FLAGS_DRV_MODE;
break;
+ case 'F':
+ xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+ break;
default:
usage(basename(argv[0]));
return 1;
@@ -104,7 +119,11 @@
return 1;
}
- ifindex = strtoul(argv[optind], NULL, 0);
+ ifindex = if_nametoindex(argv[optind]);
+ if (!ifindex) {
+ perror("if_nametoindex");
+ return 1;
+ }
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
prog_load_attr.file = filename;
@@ -132,6 +151,13 @@
return 1;
}
+ err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+ if (err) {
+ printf("can't get prog info - %s\n", strerror(errno));
+ return err;
+ }
+ prog_id = info.id;
+
poll_stats(map_fd, 2);
return 0;
diff --git a/samples/bpf/xdp_adjust_tail_user.c b/samples/bpf/xdp_adjust_tail_user.c
index 3042ce3..a3596b6 100644
--- a/samples/bpf/xdp_adjust_tail_user.c
+++ b/samples/bpf/xdp_adjust_tail_user.c
@@ -13,23 +13,37 @@
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
+#include <net/if.h>
#include <sys/resource.h>
#include <arpa/inet.h>
#include <netinet/ether.h>
#include <unistd.h>
#include <time.h>
-#include "bpf/bpf.h"
-#include "bpf/libbpf.h"
+#include "bpf.h"
+#include "libbpf.h"
#define STATS_INTERVAL_S 2U
static int ifindex = -1;
-static __u32 xdp_flags;
+static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+static __u32 prog_id;
static void int_exit(int sig)
{
- if (ifindex > -1)
- bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
+ __u32 curr_prog_id = 0;
+
+ if (ifindex > -1) {
+ if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) {
+ printf("bpf_get_link_xdp_id failed\n");
+ exit(1);
+ }
+ if (prog_id == curr_prog_id)
+ bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
+ else if (!curr_prog_id)
+ printf("couldn't find a prog id on a given iface\n");
+ else
+ printf("program on interface changed, not removing\n");
+ }
exit(0);
}
@@ -56,10 +70,11 @@
printf("Start a XDP prog which send ICMP \"packet too big\" \n"
"messages if ingress packet is bigger then MAX_SIZE bytes\n");
printf("Usage: %s [...]\n", cmd);
- printf(" -i <ifindex> Interface Index\n");
+ printf(" -i <ifname|ifindex> Interface\n");
printf(" -T <stop-after-X-seconds> Default: 0 (forever)\n");
printf(" -S use skb-mode\n");
printf(" -N enforce native mode\n");
+ printf(" -F force loading prog\n");
printf(" -h Display this help\n");
}
@@ -70,12 +85,15 @@
.prog_type = BPF_PROG_TYPE_XDP,
};
unsigned char opt_flags[256] = {};
+ const char *optstr = "i:T:SNFh";
+ struct bpf_prog_info info = {};
+ __u32 info_len = sizeof(info);
unsigned int kill_after_s = 0;
- const char *optstr = "i:T:SNh";
int i, prog_fd, map_fd, opt;
struct bpf_object *obj;
struct bpf_map *map;
char filename[256];
+ int err;
for (i = 0; i < strlen(optstr); i++)
if (optstr[i] != 'h' && 'a' <= optstr[i] && optstr[i] <= 'z')
@@ -85,7 +103,9 @@
switch (opt) {
case 'i':
- ifindex = atoi(optarg);
+ ifindex = if_nametoindex(optarg);
+ if (!ifindex)
+ ifindex = atoi(optarg);
break;
case 'T':
kill_after_s = atoi(optarg);
@@ -96,6 +116,9 @@
case 'N':
xdp_flags |= XDP_FLAGS_DRV_MODE;
break;
+ case 'F':
+ xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+ break;
default:
usage(argv[0]);
return 1;
@@ -116,6 +139,11 @@
return 1;
}
+ if (!ifindex) {
+ fprintf(stderr, "Invalid ifname\n");
+ return 1;
+ }
+
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
prog_load_attr.file = filename;
@@ -142,9 +170,15 @@
return 1;
}
- poll_stats(map_fd, kill_after_s);
+ err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+ if (err) {
+ printf("can't get prog info - %s\n", strerror(errno));
+ return 1;
+ }
+ prog_id = info.id;
- bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
+ poll_stats(map_fd, kill_after_s);
+ int_exit(0);
return 0;
}
diff --git a/samples/bpf/xdp_fwd_kern.c b/samples/bpf/xdp_fwd_kern.c
index a7e94e7..701a30f 100644
--- a/samples/bpf/xdp_fwd_kern.c
+++ b/samples/bpf/xdp_fwd_kern.c
@@ -23,7 +23,8 @@
#define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF)
-struct bpf_map_def SEC("maps") tx_port = {
+/* For TX-traffic redirect requires net_device ifindex to be in this devmap */
+struct bpf_map_def SEC("maps") xdp_tx_ports = {
.type = BPF_MAP_TYPE_DEVMAP,
.key_size = sizeof(int),
.value_size = sizeof(int),
@@ -102,14 +103,34 @@
fib_params.ifindex = ctx->ingress_ifindex;
rc = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags);
-
- /* verify egress index has xdp support
- * TO-DO bpf_map_lookup_elem(&tx_port, &key) fails with
- * cannot pass map_type 14 into func bpf_map_lookup_elem#1:
- * NOTE: without verification that egress index supports XDP
- * forwarding packets are dropped.
+ /*
+ * Some rc (return codes) from bpf_fib_lookup() are important,
+ * to understand how this XDP-prog interacts with network stack.
+ *
+ * BPF_FIB_LKUP_RET_NO_NEIGH:
+ * Even if route lookup was a success, then the MAC-addresses are also
+ * needed. This is obtained from arp/neighbour table, but if table is
+ * (still) empty then BPF_FIB_LKUP_RET_NO_NEIGH is returned. To avoid
+ * doing ARP lookup directly from XDP, then send packet to normal
+ * network stack via XDP_PASS and expect it will do ARP resolution.
+ *
+ * BPF_FIB_LKUP_RET_FWD_DISABLED:
+ * The bpf_fib_lookup respect sysctl net.ipv{4,6}.conf.all.forwarding
+ * setting, and will return BPF_FIB_LKUP_RET_FWD_DISABLED if not
+ * enabled this on ingress device.
*/
- if (rc == 0) {
+ if (rc == BPF_FIB_LKUP_RET_SUCCESS) {
+ /* Verify egress index has been configured as TX-port.
+ * (Note: User can still have inserted an egress ifindex that
+ * doesn't support XDP xmit, which will result in packet drops).
+ *
+ * Note: lookup in devmap supported since 0cdbb4b09a0.
+ * If not supported will fail with:
+ * cannot pass map_type 14 into func bpf_map_lookup_elem#1:
+ */
+ if (!bpf_map_lookup_elem(&xdp_tx_ports, &fib_params.ifindex))
+ return XDP_PASS;
+
if (h_proto == htons(ETH_P_IP))
ip_decrease_ttl(iph);
else if (h_proto == htons(ETH_P_IPV6))
@@ -117,7 +138,7 @@
memcpy(eth->h_dest, fib_params.dmac, ETH_ALEN);
memcpy(eth->h_source, fib_params.smac, ETH_ALEN);
- return bpf_redirect_map(&tx_port, fib_params.ifindex, 0);
+ return bpf_redirect_map(&xdp_tx_ports, fib_params.ifindex, 0);
}
return XDP_PASS;
diff --git a/samples/bpf/xdp_fwd_user.c b/samples/bpf/xdp_fwd_user.c
index f88e1d7..97ff1da 100644
--- a/samples/bpf/xdp_fwd_user.c
+++ b/samples/bpf/xdp_fwd_user.c
@@ -24,17 +24,23 @@
#include <fcntl.h>
#include <libgen.h>
-#include "bpf/libbpf.h"
+#include "libbpf.h"
#include <bpf/bpf.h>
-
-static int do_attach(int idx, int fd, const char *name)
+static int do_attach(int idx, int prog_fd, int map_fd, const char *name)
{
int err;
- err = bpf_set_link_xdp_fd(idx, fd, 0);
- if (err < 0)
+ err = bpf_set_link_xdp_fd(idx, prog_fd, 0);
+ if (err < 0) {
printf("ERROR: failed to attach program to %s\n", name);
+ return err;
+ }
+
+ /* Adding ifindex as a possible egress TX port */
+ err = bpf_map_update_elem(map_fd, &idx, &idx, 0);
+ if (err)
+ printf("ERROR: failed using device %s as TX-port\n", name);
return err;
}
@@ -47,6 +53,9 @@
if (err < 0)
printf("ERROR: failed to detach program from %s\n", name);
+ /* TODO: Remember to cleanup map, when adding use of shared map
+ * bpf_map_delete_elem((map_fd, &idx);
+ */
return err;
}
@@ -67,10 +76,10 @@
};
const char *prog_name = "xdp_fwd";
struct bpf_program *prog;
+ int prog_fd, map_fd = -1;
char filename[PATH_MAX];
struct bpf_object *obj;
int opt, i, idx, err;
- int prog_fd, map_fd;
int attach = 1;
int ret = 0;
@@ -103,8 +112,14 @@
return 1;
}
- if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
+ err = bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd);
+ if (err) {
+ printf("Does kernel support devmap lookup?\n");
+ /* If not, the error message will be:
+ * "cannot pass map_type 14 into func bpf_map_lookup_elem#1"
+ */
return 1;
+ }
prog = bpf_object__find_program_by_title(obj, prog_name);
prog_fd = bpf_program__fd(prog);
@@ -113,16 +128,12 @@
return 1;
}
map_fd = bpf_map__fd(bpf_object__find_map_by_name(obj,
- "tx_port"));
+ "xdp_tx_ports"));
if (map_fd < 0) {
printf("map not found: %s\n", strerror(map_fd));
return 1;
}
}
- if (attach) {
- for (i = 1; i < 64; ++i)
- bpf_map_update_elem(map_fd, &i, &i, 0);
- }
for (i = optind; i < argc; ++i) {
idx = if_nametoindex(argv[i]);
@@ -138,7 +149,7 @@
if (err)
ret = err;
} else {
- err = do_attach(idx, prog_fd, argv[i]);
+ err = do_attach(idx, prog_fd, map_fd, argv[i]);
if (err)
ret = err;
}
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
index 2d23054..0da6e9e 100644
--- a/samples/bpf/xdp_redirect_cpu_user.c
+++ b/samples/bpf/xdp_redirect_cpu_user.c
@@ -1,4 +1,5 @@
-/* GPLv2 Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc.
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc.
*/
static const char *__doc__ =
" XDP redirect with a CPU-map type \"BPF_MAP_TYPE_CPUMAP\"";
@@ -24,20 +25,26 @@
/* How many xdp_progs are defined in _kern.c */
#define MAX_PROG 6
-/* Wanted to get rid of bpf_load.h and fake-"libbpf.h" (and instead
- * use bpf/libbpf.h), but cannot as (currently) needed for XDP
- * attaching to a device via bpf_set_link_xdp_fd()
- */
#include <bpf/bpf.h>
-#include "bpf_load.h"
+#include "libbpf.h"
#include "bpf_util.h"
static int ifindex = -1;
static char ifname_buf[IF_NAMESIZE];
static char *ifname;
+static __u32 prog_id;
-static __u32 xdp_flags;
+static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+static int cpu_map_fd;
+static int rx_cnt_map_fd;
+static int redirect_err_cnt_map_fd;
+static int cpumap_enqueue_cnt_map_fd;
+static int cpumap_kthread_cnt_map_fd;
+static int cpus_available_map_fd;
+static int cpus_count_map_fd;
+static int cpus_iterator_map_fd;
+static int exception_cnt_map_fd;
/* Exit return codes */
#define EXIT_OK 0
@@ -51,27 +58,50 @@
{"help", no_argument, NULL, 'h' },
{"dev", required_argument, NULL, 'd' },
{"skb-mode", no_argument, NULL, 'S' },
- {"debug", no_argument, NULL, 'D' },
{"sec", required_argument, NULL, 's' },
- {"prognum", required_argument, NULL, 'p' },
+ {"progname", required_argument, NULL, 'p' },
{"qsize", required_argument, NULL, 'q' },
{"cpu", required_argument, NULL, 'c' },
{"stress-mode", no_argument, NULL, 'x' },
{"no-separators", no_argument, NULL, 'z' },
+ {"force", no_argument, NULL, 'F' },
{0, 0, NULL, 0 }
};
static void int_exit(int sig)
{
- fprintf(stderr,
- "Interrupted: Removing XDP program on ifindex:%d device:%s\n",
- ifindex, ifname);
- if (ifindex > -1)
- bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
+ __u32 curr_prog_id = 0;
+
+ if (ifindex > -1) {
+ if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) {
+ printf("bpf_get_link_xdp_id failed\n");
+ exit(EXIT_FAIL);
+ }
+ if (prog_id == curr_prog_id) {
+ fprintf(stderr,
+ "Interrupted: Removing XDP program on ifindex:%d device:%s\n",
+ ifindex, ifname);
+ bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
+ } else if (!curr_prog_id) {
+ printf("couldn't find a prog id on a given iface\n");
+ } else {
+ printf("program on interface changed, not removing\n");
+ }
+ }
exit(EXIT_OK);
}
-static void usage(char *argv[])
+static void print_avail_progs(struct bpf_object *obj)
+{
+ struct bpf_program *pos;
+
+ bpf_object__for_each_program(pos, obj) {
+ if (bpf_program__is_xdp(pos))
+ printf(" %s\n", bpf_program__title(pos, false));
+ }
+}
+
+static void usage(char *argv[], struct bpf_object *obj)
{
int i;
@@ -89,6 +119,8 @@
long_options[i].val);
printf("\n");
}
+ printf("\n Programs to be used for --progname:\n");
+ print_avail_progs(obj);
printf("\n");
}
@@ -263,7 +295,7 @@
static void stats_print(struct stats_record *stats_rec,
struct stats_record *stats_prev,
- int prog_num)
+ char *prog_name)
{
unsigned int nr_cpus = bpf_num_possible_cpus();
double pps = 0, drop = 0, err = 0;
@@ -273,7 +305,7 @@
int i;
/* Header */
- printf("Running XDP/eBPF prog_num:%d\n", prog_num);
+ printf("Running XDP/eBPF prog_name:%s\n", prog_name);
printf("%-15s %-7s %-14s %-11s %-9s\n",
"XDP-cpumap", "CPU:to", "pps", "drop-pps", "extra-info");
@@ -424,20 +456,20 @@
{
int fd, i;
- fd = map_fd[1]; /* map: rx_cnt */
+ fd = rx_cnt_map_fd;
map_collect_percpu(fd, 0, &rec->rx_cnt);
- fd = map_fd[2]; /* map: redirect_err_cnt */
+ fd = redirect_err_cnt_map_fd;
map_collect_percpu(fd, 1, &rec->redir_err);
- fd = map_fd[3]; /* map: cpumap_enqueue_cnt */
+ fd = cpumap_enqueue_cnt_map_fd;
for (i = 0; i < MAX_CPUS; i++)
map_collect_percpu(fd, i, &rec->enq[i]);
- fd = map_fd[4]; /* map: cpumap_kthread_cnt */
+ fd = cpumap_kthread_cnt_map_fd;
map_collect_percpu(fd, 0, &rec->kthread);
- fd = map_fd[8]; /* map: exception_cnt */
+ fd = exception_cnt_map_fd;
map_collect_percpu(fd, 0, &rec->exception);
}
@@ -462,7 +494,7 @@
/* Add a CPU entry to cpumap, as this allocate a cpu entry in
* the kernel for the cpu.
*/
- ret = bpf_map_update_elem(map_fd[0], &cpu, &queue_size, 0);
+ ret = bpf_map_update_elem(cpu_map_fd, &cpu, &queue_size, 0);
if (ret) {
fprintf(stderr, "Create CPU entry failed (err:%d)\n", ret);
exit(EXIT_FAIL_BPF);
@@ -471,23 +503,22 @@
/* Inform bpf_prog's that a new CPU is available to select
* from via some control maps.
*/
- /* map_fd[5] = cpus_available */
- ret = bpf_map_update_elem(map_fd[5], &avail_idx, &cpu, 0);
+ ret = bpf_map_update_elem(cpus_available_map_fd, &avail_idx, &cpu, 0);
if (ret) {
fprintf(stderr, "Add to avail CPUs failed\n");
exit(EXIT_FAIL_BPF);
}
/* When not replacing/updating existing entry, bump the count */
- /* map_fd[6] = cpus_count */
- ret = bpf_map_lookup_elem(map_fd[6], &key, &curr_cpus_count);
+ ret = bpf_map_lookup_elem(cpus_count_map_fd, &key, &curr_cpus_count);
if (ret) {
fprintf(stderr, "Failed reading curr cpus_count\n");
exit(EXIT_FAIL_BPF);
}
if (new) {
curr_cpus_count++;
- ret = bpf_map_update_elem(map_fd[6], &key, &curr_cpus_count, 0);
+ ret = bpf_map_update_elem(cpus_count_map_fd, &key,
+ &curr_cpus_count, 0);
if (ret) {
fprintf(stderr, "Failed write curr cpus_count\n");
exit(EXIT_FAIL_BPF);
@@ -510,8 +541,8 @@
int ret, i;
for (i = 0; i < MAX_CPUS; i++) {
- /* map_fd[5] = cpus_available */
- ret = bpf_map_update_elem(map_fd[5], &i, &invalid_cpu, 0);
+ ret = bpf_map_update_elem(cpus_available_map_fd, &i,
+ &invalid_cpu, 0);
if (ret) {
fprintf(stderr, "Failed marking CPU unavailable\n");
exit(EXIT_FAIL_BPF);
@@ -531,7 +562,7 @@
create_cpu_entry(1, 16000, 0, false);
}
-static void stats_poll(int interval, bool use_separators, int prog_num,
+static void stats_poll(int interval, bool use_separators, char *prog_name,
bool stress_mode)
{
struct stats_record *record, *prev;
@@ -547,7 +578,7 @@
while (1) {
swap(&prev, &record);
stats_collect(record);
- stats_print(record, prev, prog_num);
+ stats_print(record, prev, prog_name);
sleep(interval);
if (stress_mode)
stress_cpumap();
@@ -557,20 +588,55 @@
free_stats_record(prev);
}
+static int init_map_fds(struct bpf_object *obj)
+{
+ cpu_map_fd = bpf_object__find_map_fd_by_name(obj, "cpu_map");
+ rx_cnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rx_cnt");
+ redirect_err_cnt_map_fd =
+ bpf_object__find_map_fd_by_name(obj, "redirect_err_cnt");
+ cpumap_enqueue_cnt_map_fd =
+ bpf_object__find_map_fd_by_name(obj, "cpumap_enqueue_cnt");
+ cpumap_kthread_cnt_map_fd =
+ bpf_object__find_map_fd_by_name(obj, "cpumap_kthread_cnt");
+ cpus_available_map_fd =
+ bpf_object__find_map_fd_by_name(obj, "cpus_available");
+ cpus_count_map_fd = bpf_object__find_map_fd_by_name(obj, "cpus_count");
+ cpus_iterator_map_fd =
+ bpf_object__find_map_fd_by_name(obj, "cpus_iterator");
+ exception_cnt_map_fd =
+ bpf_object__find_map_fd_by_name(obj, "exception_cnt");
+
+ if (cpu_map_fd < 0 || rx_cnt_map_fd < 0 ||
+ redirect_err_cnt_map_fd < 0 || cpumap_enqueue_cnt_map_fd < 0 ||
+ cpumap_kthread_cnt_map_fd < 0 || cpus_available_map_fd < 0 ||
+ cpus_count_map_fd < 0 || cpus_iterator_map_fd < 0 ||
+ exception_cnt_map_fd < 0)
+ return -ENOENT;
+
+ return 0;
+}
+
int main(int argc, char **argv)
{
struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
+ char *prog_name = "xdp_cpu_map5_lb_hash_ip_pairs";
+ struct bpf_prog_load_attr prog_load_attr = {
+ .prog_type = BPF_PROG_TYPE_UNSPEC,
+ };
+ struct bpf_prog_info info = {};
+ __u32 info_len = sizeof(info);
bool use_separators = true;
bool stress_mode = false;
+ struct bpf_program *prog;
+ struct bpf_object *obj;
char filename[256];
- bool debug = false;
int added_cpus = 0;
int longindex = 0;
int interval = 2;
- int prog_num = 5;
int add_cpu = -1;
+ int opt, err;
+ int prog_fd;
__u32 qsize;
- int opt;
/* Notice: choosing he queue size is very important with the
* ixgbe driver, because it's driver page recycling trick is
@@ -581,26 +647,29 @@
qsize = 128+64;
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+ prog_load_attr.file = filename;
if (setrlimit(RLIMIT_MEMLOCK, &r)) {
perror("setrlimit(RLIMIT_MEMLOCK)");
return 1;
}
- if (load_bpf_file(filename)) {
- fprintf(stderr, "ERR in load_bpf_file(): %s", bpf_log_buf);
+ if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
+ return EXIT_FAIL;
+
+ if (prog_fd < 0) {
+ fprintf(stderr, "ERR: bpf_prog_load_xattr: %s\n",
+ strerror(errno));
return EXIT_FAIL;
}
-
- if (!prog_fd[0]) {
- fprintf(stderr, "ERR: load_bpf_file: %s\n", strerror(errno));
+ if (init_map_fds(obj) < 0) {
+ fprintf(stderr, "bpf_object__find_map_fd_by_name failed\n");
return EXIT_FAIL;
}
-
mark_cpus_unavailable();
/* Parse commands line args */
- while ((opt = getopt_long(argc, argv, "hSd:",
+ while ((opt = getopt_long(argc, argv, "hSd:s:p:q:c:xzF",
long_options, &longindex)) != -1) {
switch (opt) {
case 'd':
@@ -624,9 +693,6 @@
case 'S':
xdp_flags |= XDP_FLAGS_SKB_MODE;
break;
- case 'D':
- debug = true;
- break;
case 'x':
stress_mode = true;
break;
@@ -635,13 +701,7 @@
break;
case 'p':
/* Selecting eBPF prog to load */
- prog_num = atoi(optarg);
- if (prog_num < 0 || prog_num >= MAX_PROG) {
- fprintf(stderr,
- "--prognum too large err(%d):%s\n",
- errno, strerror(errno));
- goto error;
- }
+ prog_name = optarg;
break;
case 'c':
/* Add multiple CPUs */
@@ -658,24 +718,27 @@
case 'q':
qsize = atoi(optarg);
break;
+ case 'F':
+ xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+ break;
case 'h':
error:
default:
- usage(argv);
+ usage(argv, obj);
return EXIT_FAIL_OPTION;
}
}
/* Required option */
if (ifindex == -1) {
fprintf(stderr, "ERR: required option --dev missing\n");
- usage(argv);
+ usage(argv, obj);
return EXIT_FAIL_OPTION;
}
/* Required option */
if (add_cpu == -1) {
fprintf(stderr, "ERR: required option --cpu missing\n");
fprintf(stderr, " Specify multiple --cpu option to add more\n");
- usage(argv);
+ usage(argv, obj);
return EXIT_FAIL_OPTION;
}
@@ -683,16 +746,30 @@
signal(SIGINT, int_exit);
signal(SIGTERM, int_exit);
- if (bpf_set_link_xdp_fd(ifindex, prog_fd[prog_num], xdp_flags) < 0) {
+ prog = bpf_object__find_program_by_title(obj, prog_name);
+ if (!prog) {
+ fprintf(stderr, "bpf_object__find_program_by_title failed\n");
+ return EXIT_FAIL;
+ }
+
+ prog_fd = bpf_program__fd(prog);
+ if (prog_fd < 0) {
+ fprintf(stderr, "bpf_program__fd failed\n");
+ return EXIT_FAIL;
+ }
+
+ if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) {
fprintf(stderr, "link set xdp fd failed\n");
return EXIT_FAIL_XDP;
}
- if (debug) {
- printf("Debug-mode reading trace pipe (fix #define DEBUG)\n");
- read_trace_pipe();
+ err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+ if (err) {
+ printf("can't get prog info - %s\n", strerror(errno));
+ return err;
}
+ prog_id = info.id;
- stats_poll(interval, use_separators, prog_num, stress_mode);
+ stats_poll(interval, use_separators, prog_name, stress_mode);
return EXIT_OK;
}
diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c
index 4445e76..f70ee33 100644
--- a/samples/bpf/xdp_redirect_map_user.c
+++ b/samples/bpf/xdp_redirect_map_user.c
@@ -1,13 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io
- *
- * 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.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
*/
#include <linux/bpf.h>
#include <linux/if_link.h>
@@ -18,25 +10,53 @@
#include <stdlib.h>
#include <stdbool.h>
#include <string.h>
+#include <net/if.h>
#include <unistd.h>
#include <libgen.h>
#include <sys/resource.h>
-#include "bpf_load.h"
#include "bpf_util.h"
#include <bpf/bpf.h>
+#include "libbpf.h"
static int ifindex_in;
static int ifindex_out;
static bool ifindex_out_xdp_dummy_attached = true;
+static __u32 prog_id;
+static __u32 dummy_prog_id;
-static __u32 xdp_flags;
+static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+static int rxcnt_map_fd;
static void int_exit(int sig)
{
- bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags);
- if (ifindex_out_xdp_dummy_attached)
- bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags);
+ __u32 curr_prog_id = 0;
+
+ if (bpf_get_link_xdp_id(ifindex_in, &curr_prog_id, xdp_flags)) {
+ printf("bpf_get_link_xdp_id failed\n");
+ exit(1);
+ }
+ if (prog_id == curr_prog_id)
+ bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags);
+ else if (!curr_prog_id)
+ printf("couldn't find a prog id on iface IN\n");
+ else
+ printf("program on iface IN changed, not removing\n");
+
+ if (ifindex_out_xdp_dummy_attached) {
+ curr_prog_id = 0;
+ if (bpf_get_link_xdp_id(ifindex_out, &curr_prog_id,
+ xdp_flags)) {
+ printf("bpf_get_link_xdp_id failed\n");
+ exit(1);
+ }
+ 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");
+ else
+ printf("program on iface OUT changed, not removing\n");
+ }
exit(0);
}
@@ -53,7 +73,7 @@
int i;
sleep(interval);
- assert(bpf_map_lookup_elem(map_fd[1], &key, values) == 0);
+ assert(bpf_map_lookup_elem(rxcnt_map_fd, &key, values) == 0);
for (i = 0; i < nr_cpus; i++)
sum += (values[i] - prev[i]);
if (sum)
@@ -66,19 +86,29 @@
static void usage(const char *prog)
{
fprintf(stderr,
- "usage: %s [OPTS] IFINDEX_IN IFINDEX_OUT\n\n"
+ "usage: %s [OPTS] <IFNAME|IFINDEX>_IN <IFNAME|IFINDEX>_OUT\n\n"
"OPTS:\n"
" -S use skb-mode\n"
- " -N enforce native mode\n",
+ " -N enforce native mode\n"
+ " -F force loading prog\n",
prog);
}
int main(int argc, char **argv)
{
struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
- const char *optstr = "SN";
- char filename[256];
+ struct bpf_prog_load_attr prog_load_attr = {
+ .prog_type = BPF_PROG_TYPE_XDP,
+ };
+ struct bpf_program *prog, *dummy_prog;
+ struct bpf_prog_info info = {};
+ __u32 info_len = sizeof(info);
+ int prog_fd, dummy_prog_fd;
+ const char *optstr = "FSN";
+ struct bpf_object *obj;
int ret, opt, key = 0;
+ char filename[256];
+ int tx_port_map_fd;
while ((opt = getopt(argc, argv, optstr)) != -1) {
switch (opt) {
@@ -88,6 +118,9 @@
case 'N':
xdp_flags |= XDP_FLAGS_DRV_MODE;
break;
+ case 'F':
+ xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+ break;
default:
usage(basename(argv[0]));
return 1;
@@ -95,7 +128,7 @@
}
if (optind == argc) {
- printf("usage: %s IFINDEX_IN IFINDEX_OUT\n", argv[0]);
+ printf("usage: %s <IFNAME|IFINDEX>_IN <IFNAME|IFINDEX>_OUT\n", argv[0]);
return 1;
}
@@ -104,42 +137,76 @@
return 1;
}
- ifindex_in = strtoul(argv[optind], NULL, 0);
- ifindex_out = strtoul(argv[optind + 1], NULL, 0);
+ ifindex_in = if_nametoindex(argv[optind]);
+ if (!ifindex_in)
+ ifindex_in = strtoul(argv[optind], NULL, 0);
+
+ ifindex_out = if_nametoindex(argv[optind + 1]);
+ if (!ifindex_out)
+ ifindex_out = strtoul(argv[optind + 1], NULL, 0);
+
printf("input: %d output: %d\n", ifindex_in, ifindex_out);
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+ prog_load_attr.file = filename;
- if (load_bpf_file(filename)) {
- printf("%s", bpf_log_buf);
+ if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
+ return 1;
+
+ prog = bpf_program__next(NULL, obj);
+ dummy_prog = bpf_program__next(prog, obj);
+ if (!prog || !dummy_prog) {
+ printf("finding a prog in obj file failed\n");
+ return 1;
+ }
+ /* bpf_prog_load_xattr gives us the pointer to first prog's fd,
+ * so we're missing only the fd for dummy prog
+ */
+ dummy_prog_fd = bpf_program__fd(dummy_prog);
+ if (prog_fd < 0 || dummy_prog_fd < 0) {
+ printf("bpf_prog_load_xattr: %s\n", strerror(errno));
return 1;
}
- if (!prog_fd[0]) {
- printf("load_bpf_file: %s\n", strerror(errno));
+ tx_port_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_port");
+ rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt");
+ if (tx_port_map_fd < 0 || rxcnt_map_fd < 0) {
+ printf("bpf_object__find_map_fd_by_name failed\n");
return 1;
}
- if (bpf_set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) {
+ if (bpf_set_link_xdp_fd(ifindex_in, prog_fd, xdp_flags) < 0) {
printf("ERROR: link set xdp fd failed on %d\n", ifindex_in);
return 1;
}
+ 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 ret;
+ }
+ prog_id = info.id;
+
/* Loading dummy XDP prog on out-device */
- if (bpf_set_link_xdp_fd(ifindex_out, prog_fd[1],
+ if (bpf_set_link_xdp_fd(ifindex_out, dummy_prog_fd,
(xdp_flags | XDP_FLAGS_UPDATE_IF_NOEXIST)) < 0) {
printf("WARN: link set xdp fd failed on %d\n", ifindex_out);
ifindex_out_xdp_dummy_attached = false;
}
+ memset(&info, 0, sizeof(info));
+ ret = bpf_obj_get_info_by_fd(dummy_prog_fd, &info, &info_len);
+ if (ret) {
+ printf("can't get prog info - %s\n", strerror(errno));
+ return ret;
+ }
+ dummy_prog_id = info.id;
+
signal(SIGINT, int_exit);
signal(SIGTERM, int_exit);
- printf("map[0] (vports) = %i, map[1] (map) = %i, map[2] (count) = %i\n",
- map_fd[0], map_fd[1], map_fd[2]);
-
/* populate virtual to physical port map */
- ret = bpf_map_update_elem(map_fd[0], &key, &ifindex_out, 0);
+ ret = bpf_map_update_elem(tx_port_map_fd, &key, &ifindex_out, 0);
if (ret) {
perror("bpf_update_elem");
goto out;
diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c
index 81a69e3..5440cd6 100644
--- a/samples/bpf/xdp_redirect_user.c
+++ b/samples/bpf/xdp_redirect_user.c
@@ -1,13 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2016 John Fastabend <john.r.fastabend@intel.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
*/
#include <linux/bpf.h>
#include <linux/if_link.h>
@@ -18,25 +10,53 @@
#include <stdlib.h>
#include <stdbool.h>
#include <string.h>
+#include <net/if.h>
#include <unistd.h>
#include <libgen.h>
#include <sys/resource.h>
-#include "bpf_load.h"
#include "bpf_util.h"
#include <bpf/bpf.h>
+#include "libbpf.h"
static int ifindex_in;
static int ifindex_out;
static bool ifindex_out_xdp_dummy_attached = true;
+static __u32 prog_id;
+static __u32 dummy_prog_id;
-static __u32 xdp_flags;
+static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+static int rxcnt_map_fd;
static void int_exit(int sig)
{
- bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags);
- if (ifindex_out_xdp_dummy_attached)
- bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags);
+ __u32 curr_prog_id = 0;
+
+ if (bpf_get_link_xdp_id(ifindex_in, &curr_prog_id, xdp_flags)) {
+ printf("bpf_get_link_xdp_id failed\n");
+ exit(1);
+ }
+ if (prog_id == curr_prog_id)
+ bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags);
+ else if (!curr_prog_id)
+ printf("couldn't find a prog id on iface IN\n");
+ else
+ printf("program on iface IN changed, not removing\n");
+
+ if (ifindex_out_xdp_dummy_attached) {
+ curr_prog_id = 0;
+ if (bpf_get_link_xdp_id(ifindex_out, &curr_prog_id,
+ xdp_flags)) {
+ printf("bpf_get_link_xdp_id failed\n");
+ exit(1);
+ }
+ 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");
+ else
+ printf("program on iface OUT changed, not removing\n");
+ }
exit(0);
}
@@ -53,7 +73,7 @@
int i;
sleep(interval);
- assert(bpf_map_lookup_elem(map_fd[1], &key, values) == 0);
+ assert(bpf_map_lookup_elem(rxcnt_map_fd, &key, values) == 0);
for (i = 0; i < nr_cpus; i++)
sum += (values[i] - prev[i]);
if (sum)
@@ -66,10 +86,11 @@
static void usage(const char *prog)
{
fprintf(stderr,
- "usage: %s [OPTS] IFINDEX_IN IFINDEX_OUT\n\n"
+ "usage: %s [OPTS] <IFNAME|IFINDEX>_IN <IFNAME|IFINDEX>_OUT\n\n"
"OPTS:\n"
" -S use skb-mode\n"
- " -N enforce native mode\n",
+ " -N enforce native mode\n"
+ " -F force loading prog\n",
prog);
}
@@ -77,9 +98,18 @@
int main(int argc, char **argv)
{
struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
- const char *optstr = "SN";
+ struct bpf_prog_load_attr prog_load_attr = {
+ .prog_type = BPF_PROG_TYPE_XDP,
+ };
+ struct bpf_program *prog, *dummy_prog;
+ int prog_fd, tx_port_map_fd, opt;
+ struct bpf_prog_info info = {};
+ __u32 info_len = sizeof(info);
+ const char *optstr = "FSN";
+ struct bpf_object *obj;
char filename[256];
- int ret, opt, key = 0;
+ int dummy_prog_fd;
+ int ret, key = 0;
while ((opt = getopt(argc, argv, optstr)) != -1) {
switch (opt) {
@@ -89,6 +119,9 @@
case 'N':
xdp_flags |= XDP_FLAGS_DRV_MODE;
break;
+ case 'F':
+ xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+ break;
default:
usage(basename(argv[0]));
return 1;
@@ -96,7 +129,7 @@
}
if (optind == argc) {
- printf("usage: %s IFINDEX_IN IFINDEX_OUT\n", argv[0]);
+ printf("usage: %s <IFNAME|IFINDEX>_IN <IFNAME|IFINDEX>_OUT\n", argv[0]);
return 1;
}
@@ -105,39 +138,76 @@
return 1;
}
- ifindex_in = strtoul(argv[optind], NULL, 0);
- ifindex_out = strtoul(argv[optind + 1], NULL, 0);
+ ifindex_in = if_nametoindex(argv[optind]);
+ if (!ifindex_in)
+ ifindex_in = strtoul(argv[optind], NULL, 0);
+
+ ifindex_out = if_nametoindex(argv[optind + 1]);
+ if (!ifindex_out)
+ ifindex_out = strtoul(argv[optind + 1], NULL, 0);
+
printf("input: %d output: %d\n", ifindex_in, ifindex_out);
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+ prog_load_attr.file = filename;
- if (load_bpf_file(filename)) {
- printf("%s", bpf_log_buf);
+ if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
+ return 1;
+
+ prog = bpf_program__next(NULL, obj);
+ dummy_prog = bpf_program__next(prog, obj);
+ if (!prog || !dummy_prog) {
+ printf("finding a prog in obj file failed\n");
+ return 1;
+ }
+ /* bpf_prog_load_xattr gives us the pointer to first prog's fd,
+ * so we're missing only the fd for dummy prog
+ */
+ dummy_prog_fd = bpf_program__fd(dummy_prog);
+ if (prog_fd < 0 || dummy_prog_fd < 0) {
+ printf("bpf_prog_load_xattr: %s\n", strerror(errno));
return 1;
}
- if (!prog_fd[0]) {
- printf("load_bpf_file: %s\n", strerror(errno));
+ tx_port_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_port");
+ rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt");
+ if (tx_port_map_fd < 0 || rxcnt_map_fd < 0) {
+ printf("bpf_object__find_map_fd_by_name failed\n");
return 1;
}
- if (bpf_set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) {
+ if (bpf_set_link_xdp_fd(ifindex_in, prog_fd, xdp_flags) < 0) {
printf("ERROR: link set xdp fd failed on %d\n", ifindex_in);
return 1;
}
+ 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 ret;
+ }
+ prog_id = info.id;
+
/* Loading dummy XDP prog on out-device */
- if (bpf_set_link_xdp_fd(ifindex_out, prog_fd[1],
+ if (bpf_set_link_xdp_fd(ifindex_out, dummy_prog_fd,
(xdp_flags | XDP_FLAGS_UPDATE_IF_NOEXIST)) < 0) {
printf("WARN: link set xdp fd failed on %d\n", ifindex_out);
ifindex_out_xdp_dummy_attached = false;
}
+ memset(&info, 0, sizeof(info));
+ ret = bpf_obj_get_info_by_fd(dummy_prog_fd, &info, &info_len);
+ if (ret) {
+ printf("can't get prog info - %s\n", strerror(errno));
+ return ret;
+ }
+ dummy_prog_id = info.id;
+
signal(SIGINT, int_exit);
signal(SIGTERM, int_exit);
/* bpf redirect port */
- ret = bpf_map_update_elem(map_fd[0], &key, &ifindex_out, 0);
+ ret = bpf_map_update_elem(tx_port_map_fd, &key, &ifindex_out, 0);
if (ret) {
perror("bpf_update_elem");
goto out;
diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c
index b2b4dfa..1469b66 100644
--- a/samples/bpf/xdp_router_ipv4_user.c
+++ b/samples/bpf/xdp_router_ipv4_user.c
@@ -1,8 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (C) 2017 Cavium, Inc.
- *
- * 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 <linux/bpf.h>
#include <linux/netlink.h>
@@ -15,7 +12,6 @@
#include <string.h>
#include <sys/socket.h>
#include <unistd.h>
-#include "bpf_load.h"
#include <bpf/bpf.h>
#include <arpa/inet.h>
#include <fcntl.h>
@@ -25,32 +21,52 @@
#include <sys/ioctl.h>
#include <sys/syscall.h>
#include "bpf_util.h"
+#include "libbpf.h"
+#include <sys/resource.h>
+#include <libgen.h>
-int sock, sock_arp, flags = 0;
+int sock, sock_arp, flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
static int total_ifindex;
-int *ifindex_list;
+static int *ifindex_list;
+static __u32 *prog_id_list;
char buf[8192];
+static int lpm_map_fd;
+static int rxcnt_map_fd;
+static int arp_table_map_fd;
+static int exact_match_map_fd;
+static int tx_port_map_fd;
static int get_route_table(int rtm_family);
static void int_exit(int sig)
{
+ __u32 prog_id = 0;
int i = 0;
- for (i = 0; i < total_ifindex; i++)
- bpf_set_link_xdp_fd(ifindex_list[i], -1, flags);
+ for (i = 0; i < total_ifindex; i++) {
+ if (bpf_get_link_xdp_id(ifindex_list[i], &prog_id, flags)) {
+ printf("bpf_get_link_xdp_id on iface %d failed\n",
+ ifindex_list[i]);
+ exit(1);
+ }
+ if (prog_id_list[i] == prog_id)
+ bpf_set_link_xdp_fd(ifindex_list[i], -1, flags);
+ else if (!prog_id)
+ printf("couldn't find a prog id on iface %d\n",
+ ifindex_list[i]);
+ else
+ printf("program on iface %d changed, not removing\n",
+ ifindex_list[i]);
+ prog_id = 0;
+ }
exit(0);
}
static void close_and_exit(int sig)
{
- int i = 0;
-
close(sock);
close(sock_arp);
- for (i = 0; i < total_ifindex; i++)
- bpf_set_link_xdp_fd(ifindex_list[i], -1, flags);
- exit(0);
+ int_exit(0);
}
/* Get the mac address of the interface given interface name */
@@ -179,14 +195,10 @@
route.iface_name = alloca(sizeof(char *) * IFNAMSIZ);
route.iface_name = if_indextoname(route.iface, route.iface_name);
route.mac = getmac(route.iface_name);
- if (route.mac == -1) {
- int i = 0;
-
- for (i = 0; i < total_ifindex; i++)
- bpf_set_link_xdp_fd(ifindex_list[i], -1, flags);
- exit(0);
- }
- assert(bpf_map_update_elem(map_fd[4], &route.iface, &route.iface, 0) == 0);
+ if (route.mac == -1)
+ int_exit(0);
+ assert(bpf_map_update_elem(tx_port_map_fd,
+ &route.iface, &route.iface, 0) == 0);
if (rtm_family == AF_INET) {
struct trie_value {
__u8 prefix[4];
@@ -207,11 +219,16 @@
direct_entry.arp.dst = 0;
if (route.dst_len == 32) {
if (nh->nlmsg_type == RTM_DELROUTE) {
- assert(bpf_map_delete_elem(map_fd[3], &route.dst) == 0);
+ assert(bpf_map_delete_elem(exact_match_map_fd,
+ &route.dst) == 0);
} else {
- if (bpf_map_lookup_elem(map_fd[2], &route.dst, &direct_entry.arp.mac) == 0)
+ if (bpf_map_lookup_elem(arp_table_map_fd,
+ &route.dst,
+ &direct_entry.arp.mac) == 0)
direct_entry.arp.dst = route.dst;
- assert(bpf_map_update_elem(map_fd[3], &route.dst, &direct_entry, 0) == 0);
+ assert(bpf_map_update_elem(exact_match_map_fd,
+ &route.dst,
+ &direct_entry, 0) == 0);
}
}
for (i = 0; i < 4; i++)
@@ -225,7 +242,7 @@
route.gw, route.dst_len,
route.metric,
route.iface_name);
- if (bpf_map_lookup_elem(map_fd[0], prefix_key,
+ if (bpf_map_lookup_elem(lpm_map_fd, prefix_key,
prefix_value) < 0) {
for (i = 0; i < 4; i++)
prefix_value->prefix[i] = prefix_key->data[i];
@@ -234,7 +251,7 @@
prefix_value->gw = route.gw;
prefix_value->metric = route.metric;
- assert(bpf_map_update_elem(map_fd[0],
+ assert(bpf_map_update_elem(lpm_map_fd,
prefix_key,
prefix_value, 0
) == 0);
@@ -247,7 +264,7 @@
prefix_key->data[2],
prefix_key->data[3],
prefix_key->prefixlen);
- assert(bpf_map_delete_elem(map_fd[0],
+ assert(bpf_map_delete_elem(lpm_map_fd,
prefix_key
) == 0);
/* Rereading the route table to check if
@@ -275,8 +292,7 @@
prefix_value->ifindex = route.iface;
prefix_value->gw = route.gw;
prefix_value->metric = route.metric;
- assert(bpf_map_update_elem(
- map_fd[0],
+ assert(bpf_map_update_elem(lpm_map_fd,
prefix_key,
prefix_value,
0) == 0);
@@ -401,7 +417,8 @@
arp_entry.mac = atol(mac);
printf("%x\t\t%llx\n", arp_entry.dst, arp_entry.mac);
if (ndm_family == AF_INET) {
- if (bpf_map_lookup_elem(map_fd[3], &arp_entry.dst,
+ if (bpf_map_lookup_elem(exact_match_map_fd,
+ &arp_entry.dst,
&direct_entry) == 0) {
if (nh->nlmsg_type == RTM_DELNEIGH) {
direct_entry.arp.dst = 0;
@@ -410,16 +427,17 @@
direct_entry.arp.dst = arp_entry.dst;
direct_entry.arp.mac = arp_entry.mac;
}
- assert(bpf_map_update_elem(map_fd[3],
+ assert(bpf_map_update_elem(exact_match_map_fd,
&arp_entry.dst,
&direct_entry, 0
) == 0);
memset(&direct_entry, 0, sizeof(direct_entry));
}
if (nh->nlmsg_type == RTM_DELNEIGH) {
- assert(bpf_map_delete_elem(map_fd[2], &arp_entry.dst) == 0);
+ assert(bpf_map_delete_elem(arp_table_map_fd,
+ &arp_entry.dst) == 0);
} else if (nh->nlmsg_type == RTM_NEWNEIGH) {
- assert(bpf_map_update_elem(map_fd[2],
+ assert(bpf_map_update_elem(arp_table_map_fd,
&arp_entry.dst,
&arp_entry.mac, 0
) == 0);
@@ -553,7 +571,8 @@
for (key = 0; key < nr_keys; key++) {
__u64 sum = 0;
- assert(bpf_map_lookup_elem(map_fd[1], &key, values) == 0);
+ assert(bpf_map_lookup_elem(rxcnt_map_fd,
+ &key, values) == 0);
for (i = 0; i < nr_cpus; i++)
sum += (values[i] - prev[key][i]);
if (sum)
@@ -594,36 +613,87 @@
return ret;
}
+static void usage(const char *prog)
+{
+ fprintf(stderr,
+ "%s: %s [OPTS] interface name list\n\n"
+ "OPTS:\n"
+ " -S use skb-mode\n"
+ " -F force loading prog\n",
+ __func__, prog);
+}
+
int main(int ac, char **argv)
{
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+ struct bpf_prog_load_attr prog_load_attr = {
+ .prog_type = BPF_PROG_TYPE_XDP,
+ };
+ struct bpf_prog_info info = {};
+ __u32 info_len = sizeof(info);
+ const char *optstr = "SF";
+ struct bpf_object *obj;
char filename[256];
char **ifname_list;
- int i = 1;
+ int prog_fd, opt;
+ int err, i = 1;
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
- if (ac < 2) {
- printf("usage: %s [-S] Interface name list\n", argv[0]);
+ prog_load_attr.file = filename;
+
+ total_ifindex = ac - 1;
+ ifname_list = (argv + 1);
+
+ while ((opt = getopt(ac, argv, optstr)) != -1) {
+ switch (opt) {
+ case 'S':
+ flags |= XDP_FLAGS_SKB_MODE;
+ total_ifindex--;
+ ifname_list++;
+ break;
+ case 'F':
+ flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+ total_ifindex--;
+ ifname_list++;
+ break;
+ default:
+ usage(basename(argv[0]));
+ return 1;
+ }
+ }
+
+ if (optind == ac) {
+ usage(basename(argv[0]));
return 1;
}
- if (!strcmp(argv[1], "-S")) {
- flags = XDP_FLAGS_SKB_MODE;
- total_ifindex = ac - 2;
- ifname_list = (argv + 2);
- } else {
- flags = 0;
- total_ifindex = ac - 1;
- ifname_list = (argv + 1);
- }
- if (load_bpf_file(filename)) {
- printf("%s", bpf_log_buf);
+
+ if (setrlimit(RLIMIT_MEMLOCK, &r)) {
+ perror("setrlimit(RLIMIT_MEMLOCK)");
return 1;
}
+
+ if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
+ return 1;
+
printf("\n**************loading bpf file*********************\n\n\n");
- if (!prog_fd[0]) {
- printf("load_bpf_file: %s\n", strerror(errno));
+ if (!prog_fd) {
+ printf("bpf_prog_load_xattr: %s\n", strerror(errno));
return 1;
}
- ifindex_list = (int *)malloc(total_ifindex * sizeof(int *));
+
+ lpm_map_fd = bpf_object__find_map_fd_by_name(obj, "lpm_map");
+ rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt");
+ arp_table_map_fd = bpf_object__find_map_fd_by_name(obj, "arp_table");
+ exact_match_map_fd = bpf_object__find_map_fd_by_name(obj,
+ "exact_match");
+ tx_port_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_port");
+ if (lpm_map_fd < 0 || rxcnt_map_fd < 0 || arp_table_map_fd < 0 ||
+ exact_match_map_fd < 0 || tx_port_map_fd < 0) {
+ printf("bpf_object__find_map_fd_by_name failed\n");
+ return 1;
+ }
+
+ ifindex_list = (int *)calloc(total_ifindex, sizeof(int *));
for (i = 0; i < total_ifindex; i++) {
ifindex_list[i] = if_nametoindex(ifname_list[i]);
if (!ifindex_list[i]) {
@@ -632,8 +702,9 @@
return 1;
}
}
+ prog_id_list = (__u32 *)calloc(total_ifindex, sizeof(__u32 *));
for (i = 0; i < total_ifindex; i++) {
- if (bpf_set_link_xdp_fd(ifindex_list[i], prog_fd[0], flags) < 0) {
+ if (bpf_set_link_xdp_fd(ifindex_list[i], prog_fd, flags) < 0) {
printf("link set xdp fd failed\n");
int recovery_index = i;
@@ -642,6 +713,13 @@
return 1;
}
+ err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+ if (err) {
+ printf("can't get prog info - %s\n", strerror(errno));
+ return err;
+ }
+ prog_id_list[i] = info.id;
+ memset(&info, 0, sizeof(info));
printf("Attached to %d\n", ifindex_list[i]);
}
signal(SIGINT, int_exit);
diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c
index ef26f88..c7e4e45 100644
--- a/samples/bpf/xdp_rxq_info_user.c
+++ b/samples/bpf/xdp_rxq_info_user.c
@@ -22,15 +22,16 @@
#include <arpa/inet.h>
#include <linux/if_link.h>
-#include "bpf/bpf.h"
-#include "bpf/libbpf.h"
+#include "bpf.h"
+#include "libbpf.h"
#include "bpf_util.h"
static int ifindex = -1;
static char ifname_buf[IF_NAMESIZE];
static char *ifname;
+static __u32 prog_id;
-static __u32 xdp_flags;
+static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
static struct bpf_map *stats_global_map;
static struct bpf_map *rx_queue_index_map;
@@ -52,16 +53,30 @@
{"action", required_argument, NULL, 'a' },
{"readmem", no_argument, NULL, 'r' },
{"swapmac", no_argument, NULL, 'm' },
+ {"force", no_argument, NULL, 'F' },
{0, 0, NULL, 0 }
};
static void int_exit(int sig)
{
- fprintf(stderr,
- "Interrupted: Removing XDP program on ifindex:%d device:%s\n",
- ifindex, ifname);
- if (ifindex > -1)
- bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
+ __u32 curr_prog_id = 0;
+
+ if (ifindex > -1) {
+ if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) {
+ printf("bpf_get_link_xdp_id failed\n");
+ exit(EXIT_FAIL);
+ }
+ if (prog_id == curr_prog_id) {
+ fprintf(stderr,
+ "Interrupted: Removing XDP program on ifindex:%d device:%s\n",
+ ifindex, ifname);
+ bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
+ } else if (!curr_prog_id) {
+ printf("couldn't find a prog id on a given iface\n");
+ } else {
+ printf("program on interface changed, not removing\n");
+ }
+ }
exit(EXIT_OK);
}
@@ -446,6 +461,8 @@
struct bpf_prog_load_attr prog_load_attr = {
.prog_type = BPF_PROG_TYPE_XDP,
};
+ struct bpf_prog_info info = {};
+ __u32 info_len = sizeof(info);
int prog_fd, map_fd, opt, err;
bool use_separators = true;
struct config cfg = { 0 };
@@ -487,7 +504,7 @@
}
/* Parse commands line args */
- while ((opt = getopt_long(argc, argv, "hSd:",
+ while ((opt = getopt_long(argc, argv, "FhSrmzd:s:a:",
long_options, &longindex)) != -1) {
switch (opt) {
case 'd':
@@ -524,6 +541,9 @@
case 'm':
cfg_options |= SWAP_MAC;
break;
+ case 'F':
+ xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+ break;
case 'h':
error:
default:
@@ -576,6 +596,13 @@
return EXIT_FAIL_XDP;
}
+ err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+ if (err) {
+ printf("can't get prog info - %s\n", strerror(errno));
+ return err;
+ }
+ prog_id = info.id;
+
stats_poll(interval, action, cfg_options);
return EXIT_OK;
}
diff --git a/samples/bpf/xdp_sample_pkts_kern.c b/samples/bpf/xdp_sample_pkts_kern.c
index f7ca8b8..6c7c7e0 100644
--- a/samples/bpf/xdp_sample_pkts_kern.c
+++ b/samples/bpf/xdp_sample_pkts_kern.c
@@ -7,13 +7,6 @@
#define SAMPLE_SIZE 64ul
#define MAX_CPUS 128
-#define bpf_printk(fmt, ...) \
-({ \
- char ____fmt[] = fmt; \
- bpf_trace_printk(____fmt, sizeof(____fmt), \
- ##__VA_ARGS__); \
-})
-
struct bpf_map_def SEC("maps") my_map = {
.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
.key_size = sizeof(int),
diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c
index 8dd87c1..3002714 100644
--- a/samples/bpf/xdp_sample_pkts_user.c
+++ b/samples/bpf/xdp_sample_pkts_user.c
@@ -12,40 +12,67 @@
#include <signal.h>
#include <libbpf.h>
#include <bpf/bpf.h>
+#include <sys/resource.h>
+#include <libgen.h>
+#include <linux/if_link.h>
#include "perf-sys.h"
-#include "trace_helpers.h"
#define MAX_CPUS 128
-static int pmu_fds[MAX_CPUS], if_idx;
-static struct perf_event_mmap_page *headers[MAX_CPUS];
+static int if_idx;
static char *if_name;
+static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+static __u32 prog_id;
+static struct perf_buffer *pb = NULL;
static int do_attach(int idx, int fd, const char *name)
{
+ struct bpf_prog_info info = {};
+ __u32 info_len = sizeof(info);
int err;
- err = bpf_set_link_xdp_fd(idx, fd, 0);
- if (err < 0)
+ err = bpf_set_link_xdp_fd(idx, fd, xdp_flags);
+ if (err < 0) {
printf("ERROR: failed to attach program to %s\n", name);
+ return err;
+ }
+
+ err = bpf_obj_get_info_by_fd(fd, &info, &info_len);
+ if (err) {
+ printf("can't get prog info - %s\n", strerror(errno));
+ return err;
+ }
+ prog_id = info.id;
return err;
}
static int do_detach(int idx, const char *name)
{
- int err;
+ __u32 curr_prog_id = 0;
+ int err = 0;
- err = bpf_set_link_xdp_fd(idx, -1, 0);
- if (err < 0)
- printf("ERROR: failed to detach program from %s\n", name);
+ err = bpf_get_link_xdp_id(idx, &curr_prog_id, 0);
+ if (err) {
+ printf("bpf_get_link_xdp_id failed\n");
+ return err;
+ }
+ if (prog_id == curr_prog_id) {
+ err = bpf_set_link_xdp_fd(idx, -1, 0);
+ if (err < 0)
+ printf("ERROR: failed to detach prog from %s\n", name);
+ } else if (!curr_prog_id) {
+ printf("couldn't find a prog id on a %s\n", name);
+ } else {
+ printf("program on interface changed, not removing\n");
+ }
return err;
}
#define SAMPLE_SIZE 64
-static int print_bpf_output(void *data, int size)
+static void print_bpf_output(void *ctx, int cpu, void *data, __u32 size)
{
struct {
__u16 cookie;
@@ -55,68 +82,66 @@
int i;
if (e->cookie != 0xdead) {
- printf("BUG cookie %x sized %d\n",
- e->cookie, size);
- return LIBBPF_PERF_EVENT_ERROR;
+ printf("BUG cookie %x sized %d\n", e->cookie, size);
+ return;
}
printf("Pkt len: %-5d bytes. Ethernet hdr: ", e->pkt_len);
for (i = 0; i < 14 && i < e->pkt_len; i++)
printf("%02x ", e->pkt_data[i]);
printf("\n");
-
- return LIBBPF_PERF_EVENT_CONT;
-}
-
-static void test_bpf_perf_event(int map_fd, int num)
-{
- struct perf_event_attr attr = {
- .sample_type = PERF_SAMPLE_RAW,
- .type = PERF_TYPE_SOFTWARE,
- .config = PERF_COUNT_SW_BPF_OUTPUT,
- .wakeup_events = 1, /* get an fd notification for every event */
- };
- int i;
-
- for (i = 0; i < num; i++) {
- int key = i;
-
- pmu_fds[i] = sys_perf_event_open(&attr, -1/*pid*/, i/*cpu*/,
- -1/*group_fd*/, 0);
-
- assert(pmu_fds[i] >= 0);
- assert(bpf_map_update_elem(map_fd, &key,
- &pmu_fds[i], BPF_ANY) == 0);
- ioctl(pmu_fds[i], PERF_EVENT_IOC_ENABLE, 0);
- }
}
static void sig_handler(int signo)
{
do_detach(if_idx, if_name);
+ perf_buffer__free(pb);
exit(0);
}
+static void usage(const char *prog)
+{
+ fprintf(stderr,
+ "%s: %s [OPTS] <ifname|ifindex>\n\n"
+ "OPTS:\n"
+ " -F force loading prog\n",
+ __func__, prog);
+}
+
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,
};
+ struct perf_buffer_opts pb_opts = {};
+ const char *optstr = "F";
+ int prog_fd, map_fd, opt;
struct bpf_object *obj;
struct bpf_map *map;
- int prog_fd, map_fd;
char filename[256];
- int ret, err, i;
- int numcpus;
+ int ret, err;
- if (argc < 2) {
- printf("Usage: %s <ifname>\n", argv[0]);
+ while ((opt = getopt(argc, argv, optstr)) != -1) {
+ switch (opt) {
+ case 'F':
+ xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+ break;
+ default:
+ usage(basename(argv[0]));
+ return 1;
+ }
+ }
+
+ if (optind == argc) {
+ usage(basename(argv[0]));
return 1;
}
- numcpus = get_nprocs();
- if (numcpus > MAX_CPUS)
- numcpus = MAX_CPUS;
+ if (setrlimit(RLIMIT_MEMLOCK, &r)) {
+ perror("setrlimit(RLIMIT_MEMLOCK)");
+ return 1;
+ }
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
prog_load_attr.file = filename;
@@ -136,16 +161,16 @@
}
map_fd = bpf_map__fd(map);
- if_idx = if_nametoindex(argv[1]);
+ if_idx = if_nametoindex(argv[optind]);
if (!if_idx)
- if_idx = strtoul(argv[1], NULL, 0);
+ if_idx = strtoul(argv[optind], NULL, 0);
if (!if_idx) {
fprintf(stderr, "Invalid ifname\n");
return 1;
}
- if_name = argv[1];
- err = do_attach(if_idx, prog_fd, argv[1]);
+ if_name = argv[optind];
+ err = do_attach(if_idx, prog_fd, if_name);
if (err)
return err;
@@ -156,14 +181,17 @@
return 1;
}
- test_bpf_perf_event(map_fd, numcpus);
+ pb_opts.sample_cb = print_bpf_output;
+ pb = perf_buffer__new(map_fd, 8, &pb_opts);
+ err = libbpf_get_error(pb);
+ if (err) {
+ perror("perf_buffer setup failed");
+ return 1;
+ }
- for (i = 0; i < numcpus; i++)
- if (perf_event_mmap_header(pmu_fds[i], &headers[i]) < 0)
- return 1;
+ while ((ret = perf_buffer__poll(pb, 1000)) >= 0) {
+ }
- ret = perf_event_poller_multi(pmu_fds, headers, numcpus,
- print_bpf_output);
kill(0, SIGINT);
return ret;
}
diff --git a/samples/bpf/xdp_tx_iptunnel_common.h b/samples/bpf/xdp_tx_iptunnel_common.h
index dd12cc3..be83989 100644
--- a/samples/bpf/xdp_tx_iptunnel_common.h
+++ b/samples/bpf/xdp_tx_iptunnel_common.h
@@ -1,8 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
/* Copyright (c) 2016 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.
*/
#ifndef _SAMPLES_BPF_XDP_TX_IPTNL_COMMON_H
#define _SAMPLES_BPF_XDP_TX_IPTNL_COMMON_H
diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c
index a4ccc33..dfb6858 100644
--- a/samples/bpf/xdp_tx_iptunnel_user.c
+++ b/samples/bpf/xdp_tx_iptunnel_user.c
@@ -1,8 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2016 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 <linux/bpf.h>
#include <linux/if_link.h>
@@ -12,12 +9,13 @@
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
+#include <net/if.h>
#include <sys/resource.h>
#include <arpa/inet.h>
#include <netinet/ether.h>
#include <unistd.h>
#include <time.h>
-#include "bpf_load.h"
+#include "libbpf.h"
#include <bpf/bpf.h>
#include "bpf_util.h"
#include "xdp_tx_iptunnel_common.h"
@@ -25,12 +23,26 @@
#define STATS_INTERVAL_S 2U
static int ifindex = -1;
-static __u32 xdp_flags = 0;
+static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+static int rxcnt_map_fd;
+static __u32 prog_id;
static void int_exit(int sig)
{
- if (ifindex > -1)
- bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
+ __u32 curr_prog_id = 0;
+
+ if (ifindex > -1) {
+ if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) {
+ printf("bpf_get_link_xdp_id failed\n");
+ exit(1);
+ }
+ if (prog_id == curr_prog_id)
+ bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
+ else if (!curr_prog_id)
+ printf("couldn't find a prog id on a given iface\n");
+ else
+ printf("program on interface changed, not removing\n");
+ }
exit(0);
}
@@ -53,7 +65,8 @@
for (proto = 0; proto < nr_protos; proto++) {
__u64 sum = 0;
- assert(bpf_map_lookup_elem(map_fd[0], &proto, values) == 0);
+ assert(bpf_map_lookup_elem(rxcnt_map_fd, &proto,
+ values) == 0);
for (i = 0; i < nr_cpus; i++)
sum += (values[i] - prev[proto][i]);
@@ -71,7 +84,7 @@
"in an IPv4/v6 header and XDP_TX it out. The dst <VIP:PORT>\n"
"is used to select packets to encapsulate\n\n");
printf("Usage: %s [...]\n", cmd);
- printf(" -i <ifindex> Interface Index\n");
+ printf(" -i <ifname|ifindex> Interface\n");
printf(" -a <vip-service-address> IPv4 or IPv6\n");
printf(" -p <vip-service-port> A port range (e.g. 433-444) is also allowed\n");
printf(" -s <source-ip> Used in the IPTunnel header\n");
@@ -81,6 +94,7 @@
printf(" -P <IP-Protocol> Default is TCP\n");
printf(" -S use skb-mode\n");
printf(" -N enforce native mode\n");
+ printf(" -F Force loading the XDP prog\n");
printf(" -h Display this help\n");
}
@@ -138,16 +152,22 @@
int main(int argc, char **argv)
{
- unsigned char opt_flags[256] = {};
- unsigned int kill_after_s = 0;
- const char *optstr = "i:a:p:s:d:m:T:P:SNh";
- int min_port = 0, max_port = 0;
- struct iptnl_info tnl = {};
+ struct bpf_prog_load_attr prog_load_attr = {
+ .prog_type = BPF_PROG_TYPE_XDP,
+ };
struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+ int min_port = 0, max_port = 0, vip2tnl_map_fd;
+ const char *optstr = "i:a:p:s:d:m:T:P:FSNh";
+ unsigned char opt_flags[256] = {};
+ struct bpf_prog_info info = {};
+ __u32 info_len = sizeof(info);
+ unsigned int kill_after_s = 0;
+ struct iptnl_info tnl = {};
+ struct bpf_object *obj;
struct vip vip = {};
char filename[256];
- int opt;
- int i;
+ int opt, prog_fd;
+ int i, err;
tnl.family = AF_UNSPEC;
vip.protocol = IPPROTO_TCP;
@@ -162,7 +182,9 @@
switch (opt) {
case 'i':
- ifindex = atoi(optarg);
+ ifindex = if_nametoindex(optarg);
+ if (!ifindex)
+ ifindex = atoi(optarg);
break;
case 'a':
vip.family = parse_ipstr(optarg, vip.daddr.v6);
@@ -211,6 +233,9 @@
case 'N':
xdp_flags |= XDP_FLAGS_DRV_MODE;
break;
+ case 'F':
+ xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+ break;
default:
usage(argv[0]);
return 1;
@@ -231,34 +256,53 @@
return 1;
}
- snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
-
- if (load_bpf_file(filename)) {
- printf("%s", bpf_log_buf);
+ if (!ifindex) {
+ fprintf(stderr, "Invalid ifname\n");
return 1;
}
- if (!prog_fd[0]) {
+ snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+ prog_load_attr.file = filename;
+
+ if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
+ return 1;
+
+ if (!prog_fd) {
printf("load_bpf_file: %s\n", strerror(errno));
return 1;
}
+ rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt");
+ vip2tnl_map_fd = bpf_object__find_map_fd_by_name(obj, "vip2tnl");
+ if (vip2tnl_map_fd < 0 || rxcnt_map_fd < 0) {
+ printf("bpf_object__find_map_fd_by_name failed\n");
+ return 1;
+ }
+
signal(SIGINT, int_exit);
signal(SIGTERM, int_exit);
while (min_port <= max_port) {
vip.dport = htons(min_port++);
- if (bpf_map_update_elem(map_fd[1], &vip, &tnl, BPF_NOEXIST)) {
+ if (bpf_map_update_elem(vip2tnl_map_fd, &vip, &tnl,
+ BPF_NOEXIST)) {
perror("bpf_map_update_elem(&vip2tnl)");
return 1;
}
}
- if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
+ if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) {
printf("link set xdp fd failed\n");
return 1;
}
+ err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+ if (err) {
+ printf("can't get prog info - %s\n", strerror(errno));
+ return err;
+ }
+ prog_id = info.id;
+
poll_stats(kill_after_s);
bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
diff --git a/samples/bpf/xdpsock.h b/samples/bpf/xdpsock.h
deleted file mode 100644
index 533ab81..0000000
--- 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 d8806c4..0000000
--- 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 = 4,
-};
-
-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 4914788..df011ac 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 "libbpf.h"
+#include "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;
@@ -68,59 +61,43 @@
};
static enum benchmark_type opt_bench = BENCH_RXDROP;
-static u32 opt_xdp_flags;
+static u32 opt_xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
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 = XDP_USE_NEED_WAKEUP;
+static u32 opt_umem_flags;
+static int opt_unaligned_chunks;
+static int opt_mmap_flags;
static u32 opt_xdp_bind_flags;
+static int opt_xsk_frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
+static int opt_timeout = 1000;
+static bool opt_need_wakeup = true;
+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;
};
-#define MAX_SOCKS 4
static int num_socks;
-struct xdpsock *xsks[MAX_SOCKS];
+struct xsk_socket_info *xsks[MAX_SOCKS];
static unsigned long get_nsecs(void)
{
@@ -130,30 +107,118 @@
return ts.tv_sec * 1000000000UL + ts.tv_nsec;
}
-static void dump_stats(void);
+static void print_benchmark(bool running)
+{
+ const char *bench_str = "INVALID";
-#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)
+ 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";
-#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)
+ 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 remove_xdp_program(void)
+{
+ __u32 curr_prog_id = 0;
+
+ 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");
+}
+
+static void int_exit(int sig)
+{
+ struct xsk_umem *umem = xsks[0]->umem->umem;
+
+ (void)sig;
+
+ dump_stats();
+ xsk_socket__delete(xsks[0]->xsk);
+ (void)xsk_umem__delete(umem);
+ remove_xdp_program();
+
+ exit(EXIT_SUCCESS);
+}
+
+static void __exit_with_error(int error, const char *file, const char *func,
+ int line)
+{
+ fprintf(stderr, "%s:%s:%i: errno: %d/\"%s\"\n", file, func,
+ line, error, strerror(error));
+ dump_stats();
+ remove_xdp_program();
+ exit(EXIT_FAILURE);
+}
+
+#define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, \
+ __LINE__)
static const char pkt_data[] =
"\x3c\xfd\xfe\x9e\x7f\x71\xec\xb1\xd7\x98\x3a\xc0\x08\x00\x45\x00"
@@ -161,195 +226,6 @@
"\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)
-{
- u32 free_entries = q->cached_cons - q->cached_prod;
-
- if (free_entries >= ndescs)
- 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 umem_nb_avail(struct xdp_umem_uqueue *q, u32 nb)
-{
- u32 entries = q->cached_prod - q->cached_cons;
-
- if (entries == 0) {
- q->cached_prod = *q->producer;
- entries = q->cached_prod - q->cached_cons;
- }
-
- return (entries > nb) ? nb : entries;
-}
-
-static inline u32 xq_nb_avail(struct xdp_uqueue *q, u32 ndescs)
-{
- u32 entries = q->cached_prod - q->cached_cons;
-
- if (entries == 0) {
- q->cached_prod = *q->producer;
- entries = q->cached_prod - q->cached_cons;
- }
-
- return (entries > ndescs) ? ndescs : entries;
-}
-
-static inline int umem_fill_to_kernel_ex(struct xdp_umem_uqueue *fq,
- struct xdp_desc *d,
- size_t nb)
-{
- 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].addr;
- }
-
- 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)
-{
- 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];
- }
-
- u_smp_wmb();
-
- *fq->producer = fq->cached_prod;
-
- return 0;
-}
-
-static inline size_t umem_complete_from_kernel(struct xdp_umem_uqueue *cq,
- u64 *d, size_t nb)
-{
- 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();
-
- *cq->consumer = cq->cached_cons;
- }
-
- return entries;
-}
-
-static inline void *xq_get_data(struct xdpsock *xsk, u64 addr)
-{
- return &xsk->umem->frames[addr];
-}
-
-static inline int xq_enq(struct xdp_uqueue *uq,
- const struct xdp_desc *descs,
- unsigned int ndescs)
-{
- 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 = descs[i].addr;
- r[idx].len = descs[i].len;
- }
-
- u_smp_wmb();
-
- *uq->producer = uq->cached_prod;
- return 0;
-}
-
-static inline int xq_enq_tx_only(struct xdp_uqueue *uq,
- unsigned int id, unsigned int ndescs)
-{
- 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;
-}
-
-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();
-
- *uq->consumer = uq->cached_cons;
- }
-
- return entries;
-}
-
static void swap_mac_addresses(void *data)
{
struct ether_header *eth = (struct ether_header *)data;
@@ -397,245 +273,79 @@
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;
+ struct xsk_umem_config cfg = {
+ .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
+ .comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
+ .frame_size = opt_xsk_frame_size,
+ .frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM,
+ .flags = opt_umem_flags
+ };
+
+ int ret;
umem = calloc(1, sizeof(*umem));
- lassert(umem);
+ if (!umem)
+ exit_with_error(errno);
- lassert(posix_memalign(&bufs, getpagesize(), /* PAGE_SIZE aligned */
- NUM_FRAMES * FRAME_SIZE) == 0);
+ ret = xsk_umem__create(&umem->umem, buffer, size, &umem->fq, &umem->cq,
+ &cfg);
- mr.addr = (__u64)bufs;
- mr.len = NUM_FRAMES * FRAME_SIZE;
- mr.chunk_size = FRAME_SIZE;
- mr.headroom = FRAME_HEADROOM;
+ if (ret)
+ exit_with_error(-ret);
- 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 (opt_bench == BENCH_TXONLY) {
- int i;
-
- for (i = 0; i < NUM_FRAMES * FRAME_SIZE; i += FRAME_SIZE)
- (void)gen_eth_frame(&umem->frames[i]);
- }
-
+ 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);
-
- 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);
-
- 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;
+ struct xsk_socket_config cfg;
+ struct xsk_socket_info *xsk;
+ int ret;
+ u32 idx;
int i;
- prev_time = now;
+ xsk = calloc(1, sizeof(*xsk));
+ if (!xsk)
+ exit_with_error(errno);
- for (i = 0; i < num_socks; i++) {
- char *fmt = "%-15s %'-11.0f %'-11lu\n";
- double rx_pps, tx_pps;
+ 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);
- 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;
+ ret = bpf_get_link_xdp_id(opt_ifindex, &prog_id, opt_xdp_flags);
+ if (ret)
+ exit_with_error(-ret);
- printf("\n sock%d@", i);
- print_benchmark(false);
- printf("\n");
+ 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; i++)
+ *xsk_ring_prod__fill_addr(&xsk->umem->fq, idx++) =
+ i * opt_xsk_frame_size;
+ xsk_ring_prod__submit(&xsk->umem->fq,
+ XSK_RING_PROD__DEFAULT_NUM_DESCS);
- 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)
-{
- (void)sig;
- dump_stats();
- bpf_set_link_xdp_fd(opt_ifindex, -1, opt_xdp_flags);
- exit(EXIT_SUCCESS);
+ return xsk;
}
static struct option long_options[] = {
@@ -645,10 +355,14 @@
{"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'},
+ {"zero-copy", no_argument, 0, 'z'},
+ {"copy", no_argument, 0, 'c'},
+ {"frame-size", required_argument, 0, 'f'},
+ {"no-need-wakeup", no_argument, 0, 'm'},
+ {"unaligned", no_argument, 0, 'u'},
{0, 0, 0, 0}
};
@@ -663,12 +377,17 @@
" -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"
+ " -z, --zero-copy Force zero-copy mode.\n"
+ " -c, --copy Force copy mode.\n"
+ " -f, --frame-size=n Set the frame size (must be a power of two, default is %d).\n"
+ " -m, --no-need-wakeup Turn off use of driver need wakeup flag.\n"
+ " -f, --frame-size=n Set the frame size (must be a power of two in aligned mode, default is %d).\n"
+ " -u, --unaligned Enable unaligned chunk placement\n"
"\n";
- fprintf(stderr, str, prog);
+ fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE);
exit(EXIT_FAILURE);
}
@@ -679,8 +398,8 @@
opterr = 0;
for (;;) {
- c = getopt_long(argc, argv, "rtli:q:psSNn:", long_options,
- &option_index);
+ c = getopt_long(argc, argv, "Frtli:q:psSNn:czf:mu",
+ long_options, &option_index);
if (c == -1)
break;
@@ -700,9 +419,6 @@
case 'q':
opt_queue = atoi(optarg);
break;
- case 's':
- opt_shared_packet_buffer = 1;
- break;
case 'p':
opt_poll = 1;
break;
@@ -716,6 +432,27 @@
case 'n':
opt_interval = atoi(optarg);
break;
+ case 'z':
+ opt_xdp_bind_flags |= XDP_ZEROCOPY;
+ break;
+ case 'c':
+ opt_xdp_bind_flags |= XDP_COPY;
+ break;
+ case 'u':
+ opt_umem_flags |= XDP_UMEM_UNALIGNED_CHUNK_FLAG;
+ opt_unaligned_chunks = 1;
+ opt_mmap_flags = MAP_HUGETLB;
+ break;
+ case 'F':
+ opt_xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+ break;
+ case 'f':
+ opt_xsk_frame_size = atoi(optarg);
+ case 'm':
+ opt_need_wakeup = false;
+ opt_xdp_bind_flags &= ~XDP_USE_NEED_WAKEUP;
+ break;
+
default:
usage(basename(argv[0]));
}
@@ -727,179 +464,277 @@
opt_if);
usage(basename(argv[0]));
}
+
+ if ((opt_xsk_frame_size & (opt_xsk_frame_size - 1)) &&
+ !opt_unaligned_chunks) {
+ fprintf(stderr, "--frame-size=%d is not a power of two\n",
+ opt_xsk_frame_size);
+ 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,
+ struct pollfd *fds)
{
- u64 descs[BATCH_SIZE];
+ struct xsk_umem_info *umem = xsk->umem;
+ u32 idx_cq = 0, idx_fq = 0;
unsigned int rcvd;
size_t ndescs;
if (!xsk->outstanding_tx)
return;
- kick_tx(xsk->sfd);
+ if (!opt_need_wakeup || xsk_ring_prod__needs_wakeup(&xsk->tx))
+ 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(&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(&umem->fq, rcvd, &idx_fq);
+ while (ret != rcvd) {
+ if (ret < 0)
+ exit_with_error(-ret);
+ if (xsk_ring_prod__needs_wakeup(&umem->fq))
+ ret = poll(fds, num_socks, opt_timeout);
+ ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
+ }
+
+ for (i = 0; i < rcvd; i++)
+ *xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) =
+ *xsk_ring_cons__comp_addr(&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);
+ if (!opt_need_wakeup || xsk_ring_prod__needs_wakeup(&xsk->tx))
+ 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 pollfd *fds)
{
- 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);
- if (!rcvd)
+ rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx);
+ if (!rcvd) {
+ if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq))
+ ret = poll(fds, num_socks, opt_timeout);
return;
-
- for (i = 0; i < rcvd; i++) {
- char *pkt = xq_get_data(xsk, descs[i].addr);
-
- hex_dump(pkt, descs[i].len, descs[i].addr);
}
- xsk->rx_npkts += rcvd;
+ ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq);
+ while (ret != rcvd) {
+ if (ret < 0)
+ exit_with_error(-ret);
+ if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq))
+ ret = poll(fds, num_socks, opt_timeout);
+ ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq);
+ }
- umem_fill_to_kernel_ex(&xsk->umem->fq, descs, rcvd);
+ for (i = 0; i < rcvd; i++) {
+ u64 addr = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx)->addr;
+ u32 len = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++)->len;
+ u64 orig = xsk_umem__extract_addr(addr);
+
+ addr = xsk_umem__add_offset_to_addr(addr);
+ char *pkt = xsk_umem__get_data(xsk->umem->buffer, addr);
+
+ hex_dump(pkt, len, addr);
+ *xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = orig;
+ }
+
+ xsk_ring_prod__submit(&xsk->umem->fq, rcvd);
+ xsk_ring_cons__release(&xsk->rx, rcvd);
+ xsk->rx_npkts += rcvd;
}
static void rx_drop_all(void)
{
struct pollfd fds[MAX_SOCKS + 1];
- int i, ret, timeout, nfds = 1;
+ int i, ret;
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 */
}
for (;;) {
if (opt_poll) {
- ret = poll(fds, nfds, timeout);
+ ret = poll(fds, num_socks, opt_timeout);
if (ret <= 0)
continue;
}
for (i = 0; i < num_socks; i++)
- rx_drop(xsks[i]);
+ rx_drop(xsks[i], fds);
}
}
-static void tx_only(struct xdpsock *xsk)
+static void tx_only(struct xsk_socket_info *xsk, u32 frame_nb)
{
- int timeout, ret, nfds = 1;
- struct pollfd fds[nfds + 1];
- unsigned int idx = 0;
+ u32 idx;
+
+ 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;
+ frame_nb += BATCH_SIZE;
+ frame_nb %= NUM_FRAMES;
+ }
+
+ complete_tx_only(xsk);
+}
+
+static void tx_only_all(void)
+{
+ struct pollfd fds[MAX_SOCKS];
+ u32 frame_nb[MAX_SOCKS] = {};
+ int i, ret;
memset(fds, 0, sizeof(fds));
- fds[0].fd = xsk->sfd;
- fds[0].events = POLLOUT;
- timeout = 1000; /* 1sn */
+ for (i = 0; i < num_socks; i++) {
+ fds[0].fd = xsk_socket__fd(xsks[i]->xsk);
+ fds[0].events = POLLOUT;
+ }
for (;;) {
if (opt_poll) {
- ret = poll(fds, nfds, timeout);
+ ret = poll(fds, num_socks, opt_timeout);
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);
-
- xsk->outstanding_tx += BATCH_SIZE;
- idx += BATCH_SIZE;
- idx %= NUM_FRAMES;
- }
-
- complete_tx_only(xsk);
+ for (i = 0; i < num_socks; i++)
+ tx_only(xsks[i], frame_nb[i]);
}
}
-static void l2fwd(struct xdpsock *xsk)
+static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds)
{
+ unsigned int rcvd, i;
+ u32 idx_rx = 0, idx_tx = 0;
+ int ret;
+
+ complete_tx_l2fwd(xsk, fds);
+
+ rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx);
+ if (!rcvd) {
+ if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq))
+ ret = poll(fds, num_socks, opt_timeout);
+ return;
+ }
+
+ ret = xsk_ring_prod__reserve(&xsk->tx, rcvd, &idx_tx);
+ while (ret != rcvd) {
+ if (ret < 0)
+ exit_with_error(-ret);
+ if (xsk_ring_prod__needs_wakeup(&xsk->tx))
+ kick_tx(xsk);
+ ret = xsk_ring_prod__reserve(&xsk->tx, rcvd, &idx_tx);
+ }
+
+ for (i = 0; i < rcvd; i++) {
+ u64 addr = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx)->addr;
+ u32 len = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++)->len;
+ u64 orig = addr;
+
+ addr = xsk_umem__add_offset_to_addr(addr);
+ char *pkt = xsk_umem__get_data(xsk->umem->buffer, addr);
+
+ swap_mac_addresses(pkt);
+
+ hex_dump(pkt, len, addr);
+ xsk_ring_prod__tx_desc(&xsk->tx, idx_tx)->addr = orig;
+ xsk_ring_prod__tx_desc(&xsk->tx, idx_tx++)->len = len;
+ }
+
+ xsk_ring_prod__submit(&xsk->tx, rcvd);
+ xsk_ring_cons__release(&xsk->rx, rcvd);
+
+ xsk->rx_npkts += rcvd;
+ xsk->outstanding_tx += rcvd;
+}
+
+static void l2fwd_all(void)
+{
+ struct pollfd fds[MAX_SOCKS];
+ int i, ret;
+
+ memset(fds, 0, sizeof(fds));
+
+ for (i = 0; i < num_socks; i++) {
+ fds[i].fd = xsk_socket__fd(xsks[i]->xsk);
+ fds[i].events = POLLOUT | POLLIN;
+ }
+
for (;;) {
- struct xdp_desc descs[BATCH_SIZE];
- unsigned int rcvd, i;
- int ret;
-
- for (;;) {
- complete_tx_l2fwd(xsk);
-
- rcvd = xq_deq(&xsk->rx, descs, BATCH_SIZE);
- if (rcvd > 0)
- break;
+ if (opt_poll) {
+ ret = poll(fds, num_socks, opt_timeout);
+ if (ret <= 0)
+ continue;
}
- for (i = 0; i < rcvd; i++) {
- char *pkt = xq_get_data(xsk, descs[i].addr);
-
- swap_mac_addresses(pkt);
-
- hex_dump(pkt, descs[i].len, descs[i].addr);
- }
-
- xsk->rx_npkts += rcvd;
-
- ret = xq_enq(&xsk->tx, descs, rcvd);
- lassert(ret == 0);
- xsk->outstanding_tx += rcvd;
+ for (i = 0; i < num_socks; i++)
+ l2fwd(xsks[i], fds);
}
}
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_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);
@@ -909,60 +744,23 @@
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));
+ /* Reserve memory for the umem. Use hugepages if unaligned chunk mode */
+ bufs = mmap(NULL, NUM_FRAMES * opt_xsk_frame_size,
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS | opt_mmap_flags, -1, 0);
+ if (bufs == MAP_FAILED) {
+ printf("ERROR: mmap failed\n");
exit(EXIT_FAILURE);
}
+ /* Create sockets... */
+ umem = xsk_configure_umem(bufs, NUM_FRAMES * opt_xsk_frame_size);
+ xsks[num_socks++] = xsk_configure_socket(umem);
- 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);
- }
+ if (opt_bench == BENCH_TXONLY) {
+ int i;
- 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_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... */
- 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
-
- /* ...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; i++)
+ (void)gen_eth_frame(umem, i * opt_xsk_frame_size);
}
signal(SIGINT, int_exit);
@@ -972,16 +770,17 @@
setlocale(LC_ALL, "");
ret = pthread_create(&pt, NULL, poller, NULL);
- lassert(ret == 0);
+ if (ret)
+ exit_with_error(ret);
prev_time = get_nsecs();
if (opt_bench == BENCH_RXDROP)
rx_drop_all();
else if (opt_bench == BENCH_TXONLY)
- tx_only(xsks[0]);
+ tx_only_all();
else
- l2fwd(xsks[0]);
+ l2fwd_all();
return 0;
}