diff options
Diffstat (limited to 'tools')
-rw-r--r-- | tools/lib/bpf/bpf.c | 2 | ||||
-rw-r--r-- | tools/lib/bpf/bpf.h | 1 | ||||
-rw-r--r-- | tools/lib/traceevent/event-parse.c | 2 | ||||
-rw-r--r-- | tools/objtool/Makefile | 3 | ||||
-rw-r--r-- | tools/objtool/check.c | 11 | ||||
-rw-r--r-- | tools/perf/bench/numa.c | 4 | ||||
-rw-r--r-- | tools/perf/util/intel-pt-decoder/intel-pt-decoder.c | 31 | ||||
-rw-r--r-- | tools/power/x86/turbostat/Makefile | 2 | ||||
-rw-r--r-- | tools/power/x86/turbostat/turbostat.c | 46 | ||||
-rw-r--r-- | tools/power/x86/x86_energy_perf_policy/Makefile | 2 | ||||
-rwxr-xr-x | tools/testing/selftests/net/run_netsocktests | 2 | ||||
-rw-r--r-- | tools/testing/selftests/netfilter/Makefile | 2 | ||||
-rwxr-xr-x | tools/testing/selftests/netfilter/conntrack_icmp_related.sh | 283 |
13 files changed, 351 insertions, 40 deletions
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 1d6907d379c9..976b28137d83 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -41,6 +41,8 @@ # define __NR_bpf 349 # elif defined(__s390__) # define __NR_bpf 351 +# elif defined(__arc__) +# define __NR_bpf 280 # else # error __NR_bpf not defined. libbpf does not support your arch. # endif diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index b8ea5843c39e..e9423d6af933 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -23,6 +23,7 @@ #include <linux/bpf.h> #include <stddef.h> +#include <stdint.h> int bpf_create_map_node(enum bpf_map_type map_type, int key_size, int value_size, int max_entries, __u32 map_flags, diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 3955ba9e6fcb..7989dd6289e7 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -2206,7 +2206,7 @@ eval_type_str(unsigned long long val, const char *type, int pointer) return val & 0xffffffff; if (strcmp(type, "u64") == 0 || - strcmp(type, "s64")) + strcmp(type, "s64") == 0) return val; if (strcmp(type, "s8") == 0) diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index 8ae824dbfca3..884d4f1ed0c1 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -7,11 +7,12 @@ ARCH := x86 endif # always use the host compiler +HOSTAR ?= ar HOSTCC ?= gcc HOSTLD ?= ld +AR = $(HOSTAR) CC = $(HOSTCC) LD = $(HOSTLD) -AR = ar ifeq ($(srctree),) srctree := $(patsubst %/,%,$(dir $(CURDIR))) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 3ff025b64527..95326c6a7a24 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -28,6 +28,8 @@ #include <linux/hashtable.h> #include <linux/kernel.h> +#define FAKE_JUMP_OFFSET -1 + struct alternative { struct list_head list; struct instruction *insn; @@ -498,7 +500,7 @@ static int add_jump_destinations(struct objtool_file *file) insn->type != INSN_JUMP_UNCONDITIONAL) continue; - if (insn->ignore) + if (insn->ignore || insn->offset == FAKE_JUMP_OFFSET) continue; rela = find_rela_by_dest_range(insn->sec, insn->offset, @@ -645,10 +647,10 @@ static int handle_group_alt(struct objtool_file *file, clear_insn_state(&fake_jump->state); fake_jump->sec = special_alt->new_sec; - fake_jump->offset = -1; + fake_jump->offset = FAKE_JUMP_OFFSET; fake_jump->type = INSN_JUMP_UNCONDITIONAL; fake_jump->jump_dest = list_next_entry(last_orig_insn, list); - fake_jump->ignore = true; + fake_jump->func = orig_insn->func; } if (!special_alt->new_len) { @@ -1779,7 +1781,8 @@ static int validate_branch(struct objtool_file *file, struct instruction *first, return 1; } - func = insn->func ? insn->func->pfunc : NULL; + if (insn->func) + func = insn->func->pfunc; if (func && insn->ignore) { WARN_FUNC("BUG: why am I validating an ignored function?", diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 0afcc7eccc61..997875c770b1 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -38,6 +38,10 @@ #include <numa.h> #include <numaif.h> +#ifndef RUSAGE_THREAD +# define RUSAGE_THREAD 1 +#endif + /* * Regular printout to the terminal, supressed if -q is specified: */ diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 0bc3e6e93c31..4357141c7c92 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -58,6 +58,7 @@ enum intel_pt_pkt_state { INTEL_PT_STATE_NO_IP, INTEL_PT_STATE_ERR_RESYNC, INTEL_PT_STATE_IN_SYNC, + INTEL_PT_STATE_TNT_CONT, INTEL_PT_STATE_TNT, INTEL_PT_STATE_TIP, INTEL_PT_STATE_TIP_PGD, @@ -72,8 +73,9 @@ static inline bool intel_pt_sample_time(enum intel_pt_pkt_state pkt_state) case INTEL_PT_STATE_NO_IP: case INTEL_PT_STATE_ERR_RESYNC: case INTEL_PT_STATE_IN_SYNC: - case INTEL_PT_STATE_TNT: + case INTEL_PT_STATE_TNT_CONT: return true; + case INTEL_PT_STATE_TNT: case INTEL_PT_STATE_TIP: case INTEL_PT_STATE_TIP_PGD: case INTEL_PT_STATE_FUP: @@ -888,16 +890,20 @@ static uint64_t intel_pt_next_period(struct intel_pt_decoder *decoder) timestamp = decoder->timestamp + decoder->timestamp_insn_cnt; masked_timestamp = timestamp & decoder->period_mask; if (decoder->continuous_period) { - if (masked_timestamp != decoder->last_masked_timestamp) + if (masked_timestamp > decoder->last_masked_timestamp) return 1; } else { timestamp += 1; masked_timestamp = timestamp & decoder->period_mask; - if (masked_timestamp != decoder->last_masked_timestamp) { + if (masked_timestamp > decoder->last_masked_timestamp) { decoder->last_masked_timestamp = masked_timestamp; decoder->continuous_period = true; } } + + if (masked_timestamp < decoder->last_masked_timestamp) + return decoder->period_ticks; + return decoder->period_ticks - (timestamp - masked_timestamp); } @@ -926,7 +932,10 @@ static void intel_pt_sample_insn(struct intel_pt_decoder *decoder) case INTEL_PT_PERIOD_TICKS: timestamp = decoder->timestamp + decoder->timestamp_insn_cnt; masked_timestamp = timestamp & decoder->period_mask; - decoder->last_masked_timestamp = masked_timestamp; + if (masked_timestamp > decoder->last_masked_timestamp) + decoder->last_masked_timestamp = masked_timestamp; + else + decoder->last_masked_timestamp += decoder->period_ticks; break; case INTEL_PT_PERIOD_NONE: case INTEL_PT_PERIOD_MTC: @@ -1249,7 +1258,9 @@ static int intel_pt_walk_tnt(struct intel_pt_decoder *decoder) return -ENOENT; } decoder->tnt.count -= 1; - if (!decoder->tnt.count) + if (decoder->tnt.count) + decoder->pkt_state = INTEL_PT_STATE_TNT_CONT; + else decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; decoder->tnt.payload <<= 1; decoder->state.from_ip = decoder->ip; @@ -1280,7 +1291,9 @@ static int intel_pt_walk_tnt(struct intel_pt_decoder *decoder) if (intel_pt_insn.branch == INTEL_PT_BR_CONDITIONAL) { decoder->tnt.count -= 1; - if (!decoder->tnt.count) + if (decoder->tnt.count) + decoder->pkt_state = INTEL_PT_STATE_TNT_CONT; + else decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; if (decoder->tnt.payload & BIT63) { decoder->tnt.payload <<= 1; @@ -1300,8 +1313,11 @@ static int intel_pt_walk_tnt(struct intel_pt_decoder *decoder) return 0; } decoder->ip += intel_pt_insn.length; - if (!decoder->tnt.count) + if (!decoder->tnt.count) { + decoder->sample_timestamp = decoder->timestamp; + decoder->sample_insn_cnt = decoder->timestamp_insn_cnt; return -EAGAIN; + } decoder->tnt.payload <<= 1; continue; } @@ -2349,6 +2365,7 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) err = intel_pt_walk_trace(decoder); break; case INTEL_PT_STATE_TNT: + case INTEL_PT_STATE_TNT_CONT: err = intel_pt_walk_tnt(decoder); if (err == -EAGAIN) err = intel_pt_walk_trace(decoder); diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile index a9bc914a8fe8..78e26f782f45 100644 --- a/tools/power/x86/turbostat/Makefile +++ b/tools/power/x86/turbostat/Makefile @@ -9,7 +9,7 @@ ifeq ("$(origin O)", "command line") endif turbostat : turbostat.c -CFLAGS += -Wall +CFLAGS += -Wall -I../../../include CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"' CFLAGS += -DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"' diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index d1b2348db0f9..3e5f8b3db272 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -1883,7 +1883,7 @@ int has_turbo_ratio_group_limits(int family, int model) switch (model) { case INTEL_FAM6_ATOM_GOLDMONT: case INTEL_FAM6_SKYLAKE_X: - case INTEL_FAM6_ATOM_DENVERTON: + case INTEL_FAM6_ATOM_GOLDMONT_X: return 1; } return 0; @@ -2745,9 +2745,9 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) pkg_cstate_limits = skx_pkg_cstate_limits; has_misc_feature_control = 1; break; - case INTEL_FAM6_ATOM_SILVERMONT1: /* BYT */ + case INTEL_FAM6_ATOM_SILVERMONT: /* BYT */ no_MSR_MISC_PWR_MGMT = 1; - case INTEL_FAM6_ATOM_SILVERMONT2: /* AVN */ + case INTEL_FAM6_ATOM_SILVERMONT_X: /* AVN */ pkg_cstate_limits = slv_pkg_cstate_limits; break; case INTEL_FAM6_ATOM_AIRMONT: /* AMT */ @@ -2759,8 +2759,8 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) pkg_cstate_limits = phi_pkg_cstate_limits; break; case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ - case INTEL_FAM6_ATOM_GEMINI_LAKE: - case INTEL_FAM6_ATOM_DENVERTON: /* DNV */ + case INTEL_FAM6_ATOM_GOLDMONT_PLUS: + case INTEL_FAM6_ATOM_GOLDMONT_X: /* DNV */ pkg_cstate_limits = bxt_pkg_cstate_limits; break; default: @@ -2789,9 +2789,9 @@ int has_slv_msrs(unsigned int family, unsigned int model) return 0; switch (model) { - case INTEL_FAM6_ATOM_SILVERMONT1: - case INTEL_FAM6_ATOM_MERRIFIELD: - case INTEL_FAM6_ATOM_MOOREFIELD: + case INTEL_FAM6_ATOM_SILVERMONT: + case INTEL_FAM6_ATOM_SILVERMONT_MID: + case INTEL_FAM6_ATOM_AIRMONT_MID: return 1; } return 0; @@ -2803,7 +2803,7 @@ int is_dnv(unsigned int family, unsigned int model) return 0; switch (model) { - case INTEL_FAM6_ATOM_DENVERTON: + case INTEL_FAM6_ATOM_GOLDMONT_X: return 1; } return 0; @@ -3319,8 +3319,8 @@ double get_tdp(unsigned int model) return ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units; switch (model) { - case INTEL_FAM6_ATOM_SILVERMONT1: - case INTEL_FAM6_ATOM_SILVERMONT2: + case INTEL_FAM6_ATOM_SILVERMONT: + case INTEL_FAM6_ATOM_SILVERMONT_X: return 30.0; default: return 135.0; @@ -3386,7 +3386,7 @@ void rapl_probe(unsigned int family, unsigned int model) } break; case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ - case INTEL_FAM6_ATOM_GEMINI_LAKE: + case INTEL_FAM6_ATOM_GOLDMONT_PLUS: do_rapl = RAPL_PKG | RAPL_PKG_POWER_INFO; if (rapl_joules) BIC_PRESENT(BIC_Pkg_J); @@ -3444,8 +3444,8 @@ void rapl_probe(unsigned int family, unsigned int model) BIC_PRESENT(BIC_RAMWatt); } break; - case INTEL_FAM6_ATOM_SILVERMONT1: /* BYT */ - case INTEL_FAM6_ATOM_SILVERMONT2: /* AVN */ + case INTEL_FAM6_ATOM_SILVERMONT: /* BYT */ + case INTEL_FAM6_ATOM_SILVERMONT_X: /* AVN */ do_rapl = RAPL_PKG | RAPL_CORES; if (rapl_joules) { BIC_PRESENT(BIC_Pkg_J); @@ -3455,7 +3455,7 @@ void rapl_probe(unsigned int family, unsigned int model) BIC_PRESENT(BIC_CorWatt); } break; - case INTEL_FAM6_ATOM_DENVERTON: /* DNV */ + case INTEL_FAM6_ATOM_GOLDMONT_X: /* DNV */ do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO | RAPL_CORES_ENERGY_STATUS; BIC_PRESENT(BIC_PKG__); BIC_PRESENT(BIC_RAM__); @@ -3478,7 +3478,7 @@ void rapl_probe(unsigned int family, unsigned int model) return; rapl_power_units = 1.0 / (1 << (msr & 0xF)); - if (model == INTEL_FAM6_ATOM_SILVERMONT1) + if (model == INTEL_FAM6_ATOM_SILVERMONT) rapl_energy_units = 1.0 * (1 << (msr >> 8 & 0x1F)) / 1000000; else rapl_energy_units = 1.0 / (1 << (msr >> 8 & 0x1F)); @@ -3728,8 +3728,8 @@ int has_snb_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ case INTEL_FAM6_SKYLAKE_X: /* SKX */ case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ - case INTEL_FAM6_ATOM_GEMINI_LAKE: - case INTEL_FAM6_ATOM_DENVERTON: /* DNV */ + case INTEL_FAM6_ATOM_GOLDMONT_PLUS: + case INTEL_FAM6_ATOM_GOLDMONT_X: /* DNV */ return 1; } return 0; @@ -3760,7 +3760,7 @@ int has_hsw_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ - case INTEL_FAM6_ATOM_GEMINI_LAKE: + case INTEL_FAM6_ATOM_GOLDMONT_PLUS: return 1; } return 0; @@ -3794,8 +3794,8 @@ int is_slm(unsigned int family, unsigned int model) if (!genuine_intel) return 0; switch (model) { - case INTEL_FAM6_ATOM_SILVERMONT1: /* BYT */ - case INTEL_FAM6_ATOM_SILVERMONT2: /* AVN */ + case INTEL_FAM6_ATOM_SILVERMONT: /* BYT */ + case INTEL_FAM6_ATOM_SILVERMONT_X: /* AVN */ return 1; } return 0; @@ -4153,11 +4153,11 @@ void process_cpuid() crystal_hz = 24000000; /* 24.0 MHz */ break; case INTEL_FAM6_SKYLAKE_X: /* SKX */ - case INTEL_FAM6_ATOM_DENVERTON: /* DNV */ + case INTEL_FAM6_ATOM_GOLDMONT_X: /* DNV */ crystal_hz = 25000000; /* 25.0 MHz */ break; case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ - case INTEL_FAM6_ATOM_GEMINI_LAKE: + case INTEL_FAM6_ATOM_GOLDMONT_PLUS: crystal_hz = 19200000; /* 19.2 MHz */ break; default: diff --git a/tools/power/x86/x86_energy_perf_policy/Makefile b/tools/power/x86/x86_energy_perf_policy/Makefile index 2447b1bbaacf..f60883c574cc 100644 --- a/tools/power/x86/x86_energy_perf_policy/Makefile +++ b/tools/power/x86/x86_energy_perf_policy/Makefile @@ -9,7 +9,7 @@ ifeq ("$(origin O)", "command line") endif x86_energy_perf_policy : x86_energy_perf_policy.c -CFLAGS += -Wall +CFLAGS += -Wall -I../../../include CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"' %: %.c diff --git a/tools/testing/selftests/net/run_netsocktests b/tools/testing/selftests/net/run_netsocktests index b093f39c298c..14e41faf2c57 100755 --- a/tools/testing/selftests/net/run_netsocktests +++ b/tools/testing/selftests/net/run_netsocktests @@ -7,7 +7,7 @@ echo "--------------------" ./socket if [ $? -ne 0 ]; then echo "[FAIL]" + exit 1 else echo "[PASS]" fi - diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index c9ff2b47bd1c..a37cb1192c6a 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for netfilter selftests -TEST_PROGS := nft_trans_stress.sh nft_nat.sh +TEST_PROGS := nft_trans_stress.sh nft_nat.sh conntrack_icmp_related.sh include ../lib.mk diff --git a/tools/testing/selftests/netfilter/conntrack_icmp_related.sh b/tools/testing/selftests/netfilter/conntrack_icmp_related.sh new file mode 100755 index 000000000000..b48e1833bc89 --- /dev/null +++ b/tools/testing/selftests/netfilter/conntrack_icmp_related.sh @@ -0,0 +1,283 @@ +#!/bin/bash +# +# check that ICMP df-needed/pkttoobig icmp are set are set as related +# state +# +# Setup is: +# +# nsclient1 -> nsrouter1 -> nsrouter2 -> nsclient2 +# MTU 1500, except for nsrouter2 <-> nsclient2 link (1280). +# ping nsclient2 from nsclient1, checking that conntrack did set RELATED +# 'fragmentation needed' icmp packet. +# +# In addition, nsrouter1 will perform IP masquerading, i.e. also +# check the icmp errors are propagated to the correct host as per +# nat of "established" icmp-echo "connection". + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +ret=0 + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +cleanup() { + for i in 1 2;do ip netns del nsclient$i;done + for i in 1 2;do ip netns del nsrouter$i;done +} + +ipv4() { + echo -n 192.168.$1.2 +} + +ipv6 () { + echo -n dead:$1::2 +} + +check_counter() +{ + ns=$1 + name=$2 + expect=$3 + local lret=0 + + cnt=$(ip netns exec $ns nft list counter inet filter "$name" | grep -q "$expect") + if [ $? -ne 0 ]; then + echo "ERROR: counter $name in $ns has unexpected value (expected $expect)" 1>&2 + ip netns exec $ns nft list counter inet filter "$name" 1>&2 + lret=1 + fi + + return $lret +} + +check_unknown() +{ + expect="packets 0 bytes 0" + for n in nsclient1 nsclient2 nsrouter1 nsrouter2; do + check_counter $n "unknown" "$expect" + if [ $? -ne 0 ] ;then + return 1 + fi + done + + return 0 +} + +for n in nsclient1 nsclient2 nsrouter1 nsrouter2; do + ip netns add $n + ip -net $n link set lo up +done + +DEV=veth0 +ip link add $DEV netns nsclient1 type veth peer name eth1 netns nsrouter1 +DEV=veth0 +ip link add $DEV netns nsclient2 type veth peer name eth1 netns nsrouter2 + +DEV=veth0 +ip link add $DEV netns nsrouter1 type veth peer name eth2 netns nsrouter2 + +DEV=veth0 +for i in 1 2; do + ip -net nsclient$i link set $DEV up + ip -net nsclient$i addr add $(ipv4 $i)/24 dev $DEV + ip -net nsclient$i addr add $(ipv6 $i)/64 dev $DEV +done + +ip -net nsrouter1 link set eth1 up +ip -net nsrouter1 link set veth0 up + +ip -net nsrouter2 link set eth1 up +ip -net nsrouter2 link set eth2 up + +ip -net nsclient1 route add default via 192.168.1.1 +ip -net nsclient1 -6 route add default via dead:1::1 + +ip -net nsclient2 route add default via 192.168.2.1 +ip -net nsclient2 route add default via dead:2::1 + +i=3 +ip -net nsrouter1 addr add 192.168.1.1/24 dev eth1 +ip -net nsrouter1 addr add 192.168.3.1/24 dev veth0 +ip -net nsrouter1 addr add dead:1::1/64 dev eth1 +ip -net nsrouter1 addr add dead:3::1/64 dev veth0 +ip -net nsrouter1 route add default via 192.168.3.10 +ip -net nsrouter1 -6 route add default via dead:3::10 + +ip -net nsrouter2 addr add 192.168.2.1/24 dev eth1 +ip -net nsrouter2 addr add 192.168.3.10/24 dev eth2 +ip -net nsrouter2 addr add dead:2::1/64 dev eth1 +ip -net nsrouter2 addr add dead:3::10/64 dev eth2 +ip -net nsrouter2 route add default via 192.168.3.1 +ip -net nsrouter2 route add default via dead:3::1 + +sleep 2 +for i in 4 6; do + ip netns exec nsrouter1 sysctl -q net.ipv$i.conf.all.forwarding=1 + ip netns exec nsrouter2 sysctl -q net.ipv$i.conf.all.forwarding=1 +done + +for netns in nsrouter1 nsrouter2; do +ip netns exec $netns nft -f - <<EOF +table inet filter { + counter unknown { } + counter related { } + chain forward { + type filter hook forward priority 0; policy accept; + meta l4proto icmpv6 icmpv6 type "packet-too-big" ct state "related" counter name "related" accept + meta l4proto icmp icmp type "destination-unreachable" ct state "related" counter name "related" accept + meta l4proto { icmp, icmpv6 } ct state new,established accept + counter name "unknown" drop + } +} +EOF +done + +ip netns exec nsclient1 nft -f - <<EOF +table inet filter { + counter unknown { } + counter related { } + chain input { + type filter hook input priority 0; policy accept; + meta l4proto { icmp, icmpv6 } ct state established,untracked accept + + meta l4proto { icmp, icmpv6 } ct state "related" counter name "related" accept + counter name "unknown" drop + } +} +EOF + +ip netns exec nsclient2 nft -f - <<EOF +table inet filter { + counter unknown { } + counter new { } + counter established { } + + chain input { + type filter hook input priority 0; policy accept; + meta l4proto { icmp, icmpv6 } ct state established,untracked accept + + meta l4proto { icmp, icmpv6 } ct state "new" counter name "new" accept + meta l4proto { icmp, icmpv6 } ct state "established" counter name "established" accept + counter name "unknown" drop + } + chain output { + type filter hook output priority 0; policy accept; + meta l4proto { icmp, icmpv6 } ct state established,untracked accept + + meta l4proto { icmp, icmpv6 } ct state "new" counter name "new" + meta l4proto { icmp, icmpv6 } ct state "established" counter name "established" + counter name "unknown" drop + } +} +EOF + + +# make sure NAT core rewrites adress of icmp error if nat is used according to +# conntrack nat information (icmp error will be directed at nsrouter1 address, +# but it needs to be routed to nsclient1 address). +ip netns exec nsrouter1 nft -f - <<EOF +table ip nat { + chain postrouting { + type nat hook postrouting priority 0; policy accept; + ip protocol icmp oifname "veth0" counter masquerade + } +} +table ip6 nat { + chain postrouting { + type nat hook postrouting priority 0; policy accept; + ip6 nexthdr icmpv6 oifname "veth0" counter masquerade + } +} +EOF + +ip netns exec nsrouter2 ip link set eth1 mtu 1280 +ip netns exec nsclient2 ip link set veth0 mtu 1280 +sleep 1 + +ip netns exec nsclient1 ping -c 1 -s 1000 -q -M do 192.168.2.2 >/dev/null +if [ $? -ne 0 ]; then + echo "ERROR: netns ip routing/connectivity broken" 1>&2 + cleanup + exit 1 +fi +ip netns exec nsclient1 ping6 -q -c 1 -s 1000 dead:2::2 >/dev/null +if [ $? -ne 0 ]; then + echo "ERROR: netns ipv6 routing/connectivity broken" 1>&2 + cleanup + exit 1 +fi + +check_unknown +if [ $? -ne 0 ]; then + ret=1 +fi + +expect="packets 0 bytes 0" +for netns in nsrouter1 nsrouter2 nsclient1;do + check_counter "$netns" "related" "$expect" + if [ $? -ne 0 ]; then + ret=1 + fi +done + +expect="packets 2 bytes 2076" +check_counter nsclient2 "new" "$expect" +if [ $? -ne 0 ]; then + ret=1 +fi + +ip netns exec nsclient1 ping -q -c 1 -s 1300 -M do 192.168.2.2 > /dev/null +if [ $? -eq 0 ]; then + echo "ERROR: ping should have failed with PMTU too big error" 1>&2 + ret=1 +fi + +# nsrouter2 should have generated the icmp error, so +# related counter should be 0 (its in forward). +expect="packets 0 bytes 0" +check_counter "nsrouter2" "related" "$expect" +if [ $? -ne 0 ]; then + ret=1 +fi + +# but nsrouter1 should have seen it, same for nsclient1. +expect="packets 1 bytes 576" +for netns in nsrouter1 nsclient1;do + check_counter "$netns" "related" "$expect" + if [ $? -ne 0 ]; then + ret=1 + fi +done + +ip netns exec nsclient1 ping6 -c 1 -s 1300 dead:2::2 > /dev/null +if [ $? -eq 0 ]; then + echo "ERROR: ping6 should have failed with PMTU too big error" 1>&2 + ret=1 +fi + +expect="packets 2 bytes 1856" +for netns in nsrouter1 nsclient1;do + check_counter "$netns" "related" "$expect" + if [ $? -ne 0 ]; then + ret=1 + fi +done + +if [ $ret -eq 0 ];then + echo "PASS: icmp mtu error had RELATED state" +else + echo "ERROR: icmp error RELATED state test has failed" +fi + +cleanup +exit $ret |