summaryrefslogtreecommitdiff
path: root/tools
diff options
context:
space:
mode:
Diffstat (limited to 'tools')
-rw-r--r--tools/lib/subcmd/Makefile2
-rw-r--r--tools/objtool/check.c3
-rw-r--r--tools/objtool/elf.c19
-rw-r--r--tools/perf/arch/x86/util/intel-pt.c11
-rw-r--r--tools/perf/arch/x86/util/kvm-stat.c2
-rw-r--r--tools/perf/tests/evsel-tp-sched.c2
-rw-r--r--tools/perf/util/auxtrace.c4
-rw-r--r--tools/perf/util/auxtrace.h3
-rw-r--r--tools/perf/util/cpumap.c11
-rw-r--r--tools/perf/util/header.c2
-rw-r--r--tools/perf/util/intel-pt-decoder/intel-pt-decoder.c37
-rw-r--r--tools/perf/util/intel-pt.c2
-rw-r--r--tools/perf/util/parse-events.c2
-rw-r--r--tools/perf/util/pmu.c8
-rw-r--r--tools/perf/util/probe-file.c2
-rw-r--r--tools/perf/util/svghelper.c2
-rw-r--r--tools/perf/util/symbol-elf.c9
-rw-r--r--tools/perf/util/unwind-libdw.c6
-rw-r--r--tools/testing/nvdimm/test/iomap.c2
-rw-r--r--tools/testing/selftests/Makefile1
-rw-r--r--tools/testing/selftests/netfilter/Makefile6
-rw-r--r--tools/testing/selftests/netfilter/config2
-rwxr-xr-xtools/testing/selftests/netfilter/nft_nat.sh762
-rwxr-xr-xtools/testing/selftests/netfilter/nft_trans_stress.sh78
-rw-r--r--tools/testing/selftests/x86/protection_keys.c41
25 files changed, 980 insertions, 39 deletions
diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile
index ce4b7e527566..a690d230c311 100644
--- a/tools/lib/subcmd/Makefile
+++ b/tools/lib/subcmd/Makefile
@@ -29,8 +29,6 @@ endif
CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
CFLAGS += -I$(srctree)/tools/include/
-CFLAGS += -I$(srctree)/include/uapi
-CFLAGS += -I$(srctree)/include
SUBCMD_IN := $(OUTPUT)libsubcmd-in.o
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index e128d1c71c30..3ff025b64527 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -2132,9 +2132,10 @@ static void cleanup(struct objtool_file *file)
elf_close(file->elf);
}
+static struct objtool_file file;
+
int check(const char *_objname, bool orc)
{
- struct objtool_file file;
int ret, warnings = 0;
objname = _objname;
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 0d1acb704f64..dd4ed7c3c062 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -31,6 +31,8 @@
#include "elf.h"
#include "warn.h"
+#define MAX_NAME_LEN 128
+
struct section *find_section_by_name(struct elf *elf, const char *name)
{
struct section *sec;
@@ -298,6 +300,8 @@ static int read_symbols(struct elf *elf)
/* Create parent/child links for any cold subfunctions */
list_for_each_entry(sec, &elf->sections, list) {
list_for_each_entry(sym, &sec->symbol_list, list) {
+ char pname[MAX_NAME_LEN + 1];
+ size_t pnamelen;
if (sym->type != STT_FUNC)
continue;
sym->pfunc = sym->cfunc = sym;
@@ -305,14 +309,21 @@ static int read_symbols(struct elf *elf)
if (!coldstr)
continue;
- coldstr[0] = '\0';
- pfunc = find_symbol_by_name(elf, sym->name);
- coldstr[0] = '.';
+ pnamelen = coldstr - sym->name;
+ if (pnamelen > MAX_NAME_LEN) {
+ WARN("%s(): parent function name exceeds maximum length of %d characters",
+ sym->name, MAX_NAME_LEN);
+ return -1;
+ }
+
+ strncpy(pname, sym->name, pnamelen);
+ pname[pnamelen] = '\0';
+ pfunc = find_symbol_by_name(elf, pname);
if (!pfunc) {
WARN("%s(): can't find parent function",
sym->name);
- goto err;
+ return -1;
}
sym->pfunc = pfunc;
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 90fa2286edcf..c88adcbf966e 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -522,10 +522,21 @@ static int intel_pt_validate_config(struct perf_pmu *intel_pt_pmu,
struct perf_evsel *evsel)
{
int err;
+ char c;
if (!evsel)
return 0;
+ /*
+ * If supported, force pass-through config term (pt=1) even if user
+ * sets pt=0, which avoids senseless kernel errors.
+ */
+ if (perf_pmu__scan_file(intel_pt_pmu, "format/pt", "%c", &c) == 1 &&
+ !(evsel->attr.config & 1)) {
+ pr_warning("pt=0 doesn't make sense, forcing pt=1\n");
+ evsel->attr.config |= 1;
+ }
+
err = intel_pt_val_config_term(intel_pt_pmu, "caps/cycle_thresholds",
"cyc_thresh", "caps/psb_cyc",
evsel->attr.config);
diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c
index b63d4be655a2..2020e12a856f 100644
--- a/tools/perf/arch/x86/util/kvm-stat.c
+++ b/tools/perf/arch/x86/util/kvm-stat.c
@@ -154,7 +154,7 @@ int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid)
if (strstr(cpuid, "Intel")) {
kvm->exit_reasons = vmx_exit_reasons;
kvm->exit_reasons_isa = "VMX";
- } else if (strstr(cpuid, "AMD")) {
+ } else if (strstr(cpuid, "AMD") || strstr(cpuid, "Hygon")) {
kvm->exit_reasons = svm_exit_reasons;
kvm->exit_reasons_isa = "SVM";
} else
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 1984b3bbfe15..66b53f10eb18 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -16,7 +16,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
return -1;
}
- is_signed = !!(field->flags | FIELD_IS_SIGNED);
+ is_signed = !!(field->flags & FIELD_IS_SIGNED);
if (should_be_signed && !is_signed) {
pr_debug("%s: \"%s\" signedness(%d) is wrong, should be %d\n",
evsel->name, name, is_signed, should_be_signed);
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 29d015e2d900..b87221efdf7e 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -1244,9 +1244,9 @@ static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
}
/* padding must be written by fn() e.g. record__process_auxtrace() */
- padding = size & 7;
+ padding = size & (PERF_AUXTRACE_RECORD_ALIGNMENT - 1);
if (padding)
- padding = 8 - padding;
+ padding = PERF_AUXTRACE_RECORD_ALIGNMENT - padding;
memset(&ev, 0, sizeof(ev));
ev.auxtrace.header.type = PERF_RECORD_AUXTRACE;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 26fb1ee5746a..1b6963e09934 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -37,6 +37,9 @@ struct record_opts;
struct auxtrace_info_event;
struct events_stats;
+/* Auxtrace records must have the same alignment as perf event records */
+#define PERF_AUXTRACE_RECORD_ALIGNMENT 8
+
enum auxtrace_type {
PERF_AUXTRACE_UNKNOWN,
PERF_AUXTRACE_INTEL_PT,
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 2c0b52264a46..a625cb1500f9 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -129,7 +129,12 @@ struct cpu_map *cpu_map__new(const char *cpu_list)
if (!cpu_list)
return cpu_map__read_all_cpu_map();
- if (!isdigit(*cpu_list))
+ /*
+ * must handle the case of empty cpumap to cover
+ * TOPOLOGY header for NUMA nodes with no CPU
+ * ( e.g., because of CPU hotplug)
+ */
+ if (!isdigit(*cpu_list) && *cpu_list != '\0')
goto out;
while (isdigit(*cpu_list)) {
@@ -176,8 +181,10 @@ struct cpu_map *cpu_map__new(const char *cpu_list)
if (nr_cpus > 0)
cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
- else
+ else if (*cpu_list != '\0')
cpus = cpu_map__default_new();
+ else
+ cpus = cpu_map__dummy_new();
invalid:
free(tmp_cpus);
out:
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index ab36aa5585b4..a11f6760cce8 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2988,7 +2988,7 @@ perf_event__synthesize_event_update_unit(struct perf_tool *tool,
if (ev == NULL)
return -ENOMEM;
- strncpy(ev->data, evsel->unit, size);
+ strlcpy(ev->data, evsel->unit, size + 1);
err = process(tool, (union perf_event *)ev, NULL, NULL);
free(ev);
return err;
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 d27715ff9a5f..94764efb0a6a 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -26,6 +26,7 @@
#include "../cache.h"
#include "../util.h"
+#include "../auxtrace.h"
#include "intel-pt-insn-decoder.h"
#include "intel-pt-pkt-decoder.h"
@@ -1311,7 +1312,6 @@ static int intel_pt_overflow(struct intel_pt_decoder *decoder)
{
intel_pt_log("ERROR: Buffer overflow\n");
intel_pt_clear_tx_flags(decoder);
- decoder->cbr = 0;
decoder->timestamp_insn_cnt = 0;
decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC;
decoder->overflow = true;
@@ -2351,6 +2351,34 @@ static int intel_pt_tsc_cmp(uint64_t tsc1, uint64_t tsc2)
}
}
+#define MAX_PADDING (PERF_AUXTRACE_RECORD_ALIGNMENT - 1)
+
+/**
+ * adj_for_padding - adjust overlap to account for padding.
+ * @buf_b: second buffer
+ * @buf_a: first buffer
+ * @len_a: size of first buffer
+ *
+ * @buf_a might have up to 7 bytes of padding appended. Adjust the overlap
+ * accordingly.
+ *
+ * Return: A pointer into @buf_b from where non-overlapped data starts
+ */
+static unsigned char *adj_for_padding(unsigned char *buf_b,
+ unsigned char *buf_a, size_t len_a)
+{
+ unsigned char *p = buf_b - MAX_PADDING;
+ unsigned char *q = buf_a + len_a - MAX_PADDING;
+ int i;
+
+ for (i = MAX_PADDING; i; i--, p++, q++) {
+ if (*p != *q)
+ break;
+ }
+
+ return p;
+}
+
/**
* intel_pt_find_overlap_tsc - determine start of non-overlapped trace data
* using TSC.
@@ -2401,8 +2429,11 @@ static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a,
/* Same TSC, so buffers are consecutive */
if (!cmp && rem_b >= rem_a) {
+ unsigned char *start;
+
*consecutive = true;
- return buf_b + len_b - (rem_b - rem_a);
+ start = buf_b + len_b - (rem_b - rem_a);
+ return adj_for_padding(start, buf_a, len_a);
}
if (cmp < 0)
return buf_b; /* tsc_a < tsc_b => no overlap */
@@ -2465,7 +2496,7 @@ unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
found = memmem(buf_a, len_a, buf_b, len_a);
if (found) {
*consecutive = true;
- return buf_b + len_a;
+ return adj_for_padding(buf_b + len_a, buf_a, len_a);
}
/* Try again at next PSB in buffer 'a' */
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index d40ab4cf8932..24c6621e2d95 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2259,6 +2259,8 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
}
pt->timeless_decoding = intel_pt_timeless_decoding(pt);
+ if (pt->timeless_decoding && !pt->tc.time_mult)
+ pt->tc.time_mult = 1;
pt->have_tsc = intel_pt_have_tsc(pt);
pt->sampling_mode = false;
pt->est_tsc = !pt->timeless_decoding;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 415a9c38d9f0..14f111a10650 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -2225,7 +2225,7 @@ restart:
if (!name_only && strlen(syms->alias))
snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias);
else
- strncpy(name, syms->symbol, MAX_NAME_LEN);
+ strlcpy(name, syms->symbol, MAX_NAME_LEN);
evt_list[evt_i] = strdup(name);
if (evt_list[evt_i] == NULL)
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 0f84371d4d6b..c86c1d5ea65c 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -103,7 +103,7 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
char path[PATH_MAX];
char *lc;
- snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
+ scnprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
fd = open(path, O_RDONLY);
if (fd == -1)
@@ -163,7 +163,7 @@ static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *n
ssize_t sret;
int fd;
- snprintf(path, PATH_MAX, "%s/%s.unit", dir, name);
+ scnprintf(path, PATH_MAX, "%s/%s.unit", dir, name);
fd = open(path, O_RDONLY);
if (fd == -1)
@@ -193,7 +193,7 @@ perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, char *dir, char *name)
char path[PATH_MAX];
int fd;
- snprintf(path, PATH_MAX, "%s/%s.per-pkg", dir, name);
+ scnprintf(path, PATH_MAX, "%s/%s.per-pkg", dir, name);
fd = open(path, O_RDONLY);
if (fd == -1)
@@ -211,7 +211,7 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
char path[PATH_MAX];
int fd;
- snprintf(path, PATH_MAX, "%s/%s.snapshot", dir, name);
+ scnprintf(path, PATH_MAX, "%s/%s.snapshot", dir, name);
fd = open(path, O_RDONLY);
if (fd == -1)
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 436b64731f65..b9507a8d0e30 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -414,7 +414,7 @@ static int probe_cache__open(struct probe_cache *pcache, const char *target)
if (target && build_id_cache__cached(target)) {
/* This is a cached buildid */
- strncpy(sbuildid, target, SBUILD_ID_SIZE);
+ strlcpy(sbuildid, target, SBUILD_ID_SIZE);
dir_name = build_id_cache__linkname(sbuildid, NULL, 0);
goto found;
}
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 1cbada2dc6be..f735ee038713 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -334,7 +334,7 @@ static char *cpu_model(void)
if (file) {
while (fgets(buf, 255, file)) {
if (strstr(buf, "model name")) {
- strncpy(cpu_m, &buf[13], 255);
+ strlcpy(cpu_m, &buf[13], 255);
break;
}
}
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index adbc6c02c3aa..20ba5a9aeae4 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -85,6 +85,11 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym)
return GELF_ST_TYPE(sym->st_info);
}
+static inline uint8_t elf_sym__visibility(const GElf_Sym *sym)
+{
+ return GELF_ST_VISIBILITY(sym->st_other);
+}
+
#ifndef STT_GNU_IFUNC
#define STT_GNU_IFUNC 10
#endif
@@ -109,7 +114,9 @@ static inline int elf_sym__is_label(const GElf_Sym *sym)
return elf_sym__type(sym) == STT_NOTYPE &&
sym->st_name != 0 &&
sym->st_shndx != SHN_UNDEF &&
- sym->st_shndx != SHN_ABS;
+ sym->st_shndx != SHN_ABS &&
+ elf_sym__visibility(sym) != STV_HIDDEN &&
+ elf_sym__visibility(sym) != STV_INTERNAL;
}
static bool elf_sym__is_a(GElf_Sym *sym, enum map_type type)
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index b46e1cf347e5..ff32ca1d81ff 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -42,13 +42,13 @@ static int __report_module(struct addr_location *al, u64 ip,
Dwarf_Addr s;
dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL);
- if (s != al->map->start)
+ if (s != al->map->start - al->map->pgoff)
mod = 0;
}
if (!mod)
mod = dwfl_report_elf(ui->dwfl, dso->short_name,
- dso->long_name, -1, al->map->start,
+ (dso->symsrc_filename ? dso->symsrc_filename : dso->long_name), -1, al->map->start - al->map->pgoff,
false);
return mod && dwfl_addrmodule(ui->dwfl, ip) == mod ? 0 : -1;
@@ -231,7 +231,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
err = dwfl_getthread_frames(ui->dwfl, thread->tid, frame_callback, ui);
- if (err && !ui->max_stack)
+ if (err && ui->max_stack != max_stack)
err = 0;
/*
diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index 64cae1a5deff..5c7ad24cd931 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -114,7 +114,7 @@ void *__wrap_devm_memremap_pages(struct device *dev, struct resource *res,
return nfit_res->buf + offset - nfit_res->res.start;
return devm_memremap_pages(dev, res, ref, altmap);
}
-EXPORT_SYMBOL(__wrap_devm_memremap_pages);
+EXPORT_SYMBOL_GPL(__wrap_devm_memremap_pages);
pfn_t __wrap_phys_to_pfn_t(phys_addr_t addr, unsigned long flags)
{
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 76faf5bf0b32..d37dfc6608c6 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -15,6 +15,7 @@ TARGETS += memory-hotplug
TARGETS += mount
TARGETS += mqueue
TARGETS += net
+TARGETS += netfilter
TARGETS += nsfs
TARGETS += powerpc
TARGETS += pstore
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
new file mode 100644
index 000000000000..c9ff2b47bd1c
--- /dev/null
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for netfilter selftests
+
+TEST_PROGS := nft_trans_stress.sh nft_nat.sh
+
+include ../lib.mk
diff --git a/tools/testing/selftests/netfilter/config b/tools/testing/selftests/netfilter/config
new file mode 100644
index 000000000000..59caa8f71cd8
--- /dev/null
+++ b/tools/testing/selftests/netfilter/config
@@ -0,0 +1,2 @@
+CONFIG_NET_NS=y
+CONFIG_NF_TABLES_INET=y
diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh
new file mode 100755
index 000000000000..8ec76681605c
--- /dev/null
+++ b/tools/testing/selftests/netfilter/nft_nat.sh
@@ -0,0 +1,762 @@
+#!/bin/bash
+#
+# This test is for basic NAT functionality: snat, dnat, redirect, masquerade.
+#
+
+# 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 $ksft_skip
+fi
+
+ip netns add ns0
+ip netns add ns1
+ip netns add ns2
+
+ip link add veth0 netns ns0 type veth peer name eth0 netns ns1
+ip link add veth1 netns ns0 type veth peer name eth0 netns ns2
+
+ip -net ns0 link set lo up
+ip -net ns0 link set veth0 up
+ip -net ns0 addr add 10.0.1.1/24 dev veth0
+ip -net ns0 addr add dead:1::1/64 dev veth0
+
+ip -net ns0 link set veth1 up
+ip -net ns0 addr add 10.0.2.1/24 dev veth1
+ip -net ns0 addr add dead:2::1/64 dev veth1
+
+for i in 1 2; do
+ ip -net ns$i link set lo up
+ ip -net ns$i link set eth0 up
+ ip -net ns$i addr add 10.0.$i.99/24 dev eth0
+ ip -net ns$i route add default via 10.0.$i.1
+ ip -net ns$i addr add dead:$i::99/64 dev eth0
+ ip -net ns$i route add default via dead:$i::1
+done
+
+bad_counter()
+{
+ local ns=$1
+ local counter=$2
+ local expect=$3
+
+ echo "ERROR: $counter counter in $ns has unexpected value (expected $expect)" 1>&2
+ ip netns exec $ns nft list counter inet filter $counter 1>&2
+}
+
+check_counters()
+{
+ ns=$1
+ local lret=0
+
+ cnt=$(ip netns exec $ns nft list counter inet filter ns0in | grep -q "packets 1 bytes 84")
+ if [ $? -ne 0 ]; then
+ bad_counter $ns ns0in "packets 1 bytes 84"
+ lret=1
+ fi
+ cnt=$(ip netns exec $ns nft list counter inet filter ns0out | grep -q "packets 1 bytes 84")
+ if [ $? -ne 0 ]; then
+ bad_counter $ns ns0out "packets 1 bytes 84"
+ lret=1
+ fi
+
+ expect="packets 1 bytes 104"
+ cnt=$(ip netns exec $ns nft list counter inet filter ns0in6 | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter $ns ns0in6 "$expect"
+ lret=1
+ fi
+ cnt=$(ip netns exec $ns nft list counter inet filter ns0out6 | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter $ns ns0out6 "$expect"
+ lret=1
+ fi
+
+ return $lret
+}
+
+check_ns0_counters()
+{
+ local ns=$1
+ local lret=0
+
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns0in | grep -q "packets 0 bytes 0")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 ns0in "packets 0 bytes 0"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns0in6 | grep -q "packets 0 bytes 0")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 ns0in6 "packets 0 bytes 0"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns0out | grep -q "packets 0 bytes 0")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 ns0out "packets 0 bytes 0"
+ lret=1
+ fi
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns0out6 | grep -q "packets 0 bytes 0")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 ns0out6 "packets 0 bytes 0"
+ lret=1
+ fi
+
+ for dir in "in" "out" ; do
+ expect="packets 1 bytes 84"
+ cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 $ns$dir "$expect"
+ lret=1
+ fi
+
+ expect="packets 1 bytes 104"
+ cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir}6 | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 $ns$dir6 "$expect"
+ lret=1
+ fi
+ done
+
+ return $lret
+}
+
+reset_counters()
+{
+ for i in 0 1 2;do
+ ip netns exec ns$i nft reset counters inet > /dev/null
+ done
+}
+
+test_local_dnat6()
+{
+ local lret=0
+ip netns exec ns0 nft -f - <<EOF
+table ip6 nat {
+ chain output {
+ type nat hook output priority 0; policy accept;
+ ip6 daddr dead:1::99 dnat to dead:2::99
+ }
+}
+EOF
+ if [ $? -ne 0 ]; then
+ echo "SKIP: Could not add add ip6 dnat hook"
+ return $ksft_skip
+ fi
+
+ # ping netns1, expect rewrite to netns2
+ ip netns exec ns0 ping -q -c 1 dead:1::99 > /dev/null
+ if [ $? -ne 0 ]; then
+ lret=1
+ echo "ERROR: ping6 failed"
+ return $lret
+ fi
+
+ expect="packets 0 bytes 0"
+ for dir in "in6" "out6" ; do
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+
+ expect="packets 1 bytes 104"
+ for dir in "in6" "out6" ; do
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 ns2$dir "$expect"
+ lret=1
+ fi
+ done
+
+ # expect 0 count in ns1
+ expect="packets 0 bytes 0"
+ for dir in "in6" "out6" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns0$dir "$expect"
+ lret=1
+ fi
+ done
+
+ # expect 1 packet in ns2
+ expect="packets 1 bytes 104"
+ for dir in "in6" "out6" ; do
+ cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns0$dir "$expect"
+ lret=1
+ fi
+ done
+
+ test $lret -eq 0 && echo "PASS: ipv6 ping to ns1 was NATted to ns2"
+ ip netns exec ns0 nft flush chain ip6 nat output
+
+ return $lret
+}
+
+test_local_dnat()
+{
+ local lret=0
+ip netns exec ns0 nft -f - <<EOF
+table ip nat {
+ chain output {
+ type nat hook output priority 0; policy accept;
+ ip daddr 10.0.1.99 dnat to 10.0.2.99
+ }
+}
+EOF
+ # ping netns1, expect rewrite to netns2
+ ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null
+ if [ $? -ne 0 ]; then
+ lret=1
+ echo "ERROR: ping failed"
+ return $lret
+ fi
+
+ expect="packets 0 bytes 0"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+
+ expect="packets 1 bytes 84"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 ns2$dir "$expect"
+ lret=1
+ fi
+ done
+
+ # expect 0 count in ns1
+ expect="packets 0 bytes 0"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns0$dir "$expect"
+ lret=1
+ fi
+ done
+
+ # expect 1 packet in ns2
+ expect="packets 1 bytes 84"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns0$dir "$expect"
+ lret=1
+ fi
+ done
+
+ test $lret -eq 0 && echo "PASS: ping to ns1 was NATted to ns2"
+
+ ip netns exec ns0 nft flush chain ip nat output
+
+ reset_counters
+ ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null
+ if [ $? -ne 0 ]; then
+ lret=1
+ echo "ERROR: ping failed"
+ return $lret
+ fi
+
+ expect="packets 1 bytes 84"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+ expect="packets 0 bytes 0"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 ns2$dir "$expect"
+ lret=1
+ fi
+ done
+
+ # expect 1 count in ns1
+ expect="packets 1 bytes 84"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 ns0$dir "$expect"
+ lret=1
+ fi
+ done
+
+ # expect 0 packet in ns2
+ expect="packets 0 bytes 0"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns2$dir "$expect"
+ lret=1
+ fi
+ done
+
+ test $lret -eq 0 && echo "PASS: ping to ns1 OK after nat output chain flush"
+
+ return $lret
+}
+
+
+test_masquerade6()
+{
+ local lret=0
+
+ ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
+
+ ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannot ping ns1 from ns2 via ipv6"
+ return 1
+ lret=1
+ fi
+
+ expect="packets 1 bytes 104"
+ for dir in "in6" "out6" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns2$dir "$expect"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+
+ reset_counters
+
+# add masquerading rule
+ip netns exec ns0 nft -f - <<EOF
+table ip6 nat {
+ chain postrouting {
+ type nat hook postrouting priority 0; policy accept;
+ meta oif veth0 masquerade
+ }
+}
+EOF
+ ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerading"
+ lret=1
+ fi
+
+ # ns1 should have seen packets from ns0, due to masquerade
+ expect="packets 1 bytes 104"
+ for dir in "in6" "out6" ; do
+
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns0$dir "$expect"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+
+ # ns1 should not have seen packets from ns2, due to masquerade
+ expect="packets 0 bytes 0"
+ for dir in "in6" "out6" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns0$dir "$expect"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+
+ ip netns exec ns0 nft flush chain ip6 nat postrouting
+ if [ $? -ne 0 ]; then
+ echo "ERROR: Could not flush ip6 nat postrouting" 1>&2
+ lret=1
+ fi
+
+ test $lret -eq 0 && echo "PASS: IPv6 masquerade for ns2"
+
+ return $lret
+}
+
+test_masquerade()
+{
+ local lret=0
+
+ ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
+ ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+
+ ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: canot ping ns1 from ns2"
+ lret=1
+ fi
+
+ expect="packets 1 bytes 84"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns2$dir "$expect"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+
+ reset_counters
+
+# add masquerading rule
+ip netns exec ns0 nft -f - <<EOF
+table ip nat {
+ chain postrouting {
+ type nat hook postrouting priority 0; policy accept;
+ meta oif veth0 masquerade
+ }
+}
+EOF
+ ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannot ping ns1 from ns2 with active ip masquerading"
+ lret=1
+ fi
+
+ # ns1 should have seen packets from ns0, due to masquerade
+ expect="packets 1 bytes 84"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns0$dir "$expect"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+
+ # ns1 should not have seen packets from ns2, due to masquerade
+ expect="packets 0 bytes 0"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns0$dir "$expect"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+
+ ip netns exec ns0 nft flush chain ip nat postrouting
+ if [ $? -ne 0 ]; then
+ echo "ERROR: Could not flush nat postrouting" 1>&2
+ lret=1
+ fi
+
+ test $lret -eq 0 && echo "PASS: IP masquerade for ns2"
+
+ return $lret
+}
+
+test_redirect6()
+{
+ local lret=0
+
+ ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
+
+ ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannnot ping ns1 from ns2 via ipv6"
+ lret=1
+ fi
+
+ expect="packets 1 bytes 104"
+ for dir in "in6" "out6" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns2$dir "$expect"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+
+ reset_counters
+
+# add redirect rule
+ip netns exec ns0 nft -f - <<EOF
+table ip6 nat {
+ chain prerouting {
+ type nat hook prerouting priority 0; policy accept;
+ meta iif veth1 meta l4proto icmpv6 ip6 saddr dead:2::99 ip6 daddr dead:1::99 redirect
+ }
+}
+EOF
+ ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannot ping ns1 from ns2 with active ip6 redirect"
+ lret=1
+ fi
+
+ # ns1 should have seen no packets from ns2, due to redirection
+ expect="packets 0 bytes 0"
+ for dir in "in6" "out6" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns0$dir "$expect"
+ lret=1
+ fi
+ done
+
+ # ns0 should have seen packets from ns2, due to masquerade
+ expect="packets 1 bytes 104"
+ for dir in "in6" "out6" ; do
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns0$dir "$expect"
+ lret=1
+ fi
+ done
+
+ ip netns exec ns0 nft delete table ip6 nat
+ if [ $? -ne 0 ]; then
+ echo "ERROR: Could not delete ip6 nat table" 1>&2
+ lret=1
+ fi
+
+ test $lret -eq 0 && echo "PASS: IPv6 redirection for ns2"
+
+ return $lret
+}
+
+test_redirect()
+{
+ local lret=0
+
+ ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
+ ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+
+ ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannot ping ns1 from ns2"
+ lret=1
+ fi
+
+ expect="packets 1 bytes 84"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns2$dir "$expect"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+
+ reset_counters
+
+# add redirect rule
+ip netns exec ns0 nft -f - <<EOF
+table ip nat {
+ chain prerouting {
+ type nat hook prerouting priority 0; policy accept;
+ meta iif veth1 ip protocol icmp ip saddr 10.0.2.99 ip daddr 10.0.1.99 redirect
+ }
+}
+EOF
+ ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannot ping ns1 from ns2 with active ip redirect"
+ lret=1
+ fi
+
+ # ns1 should have seen no packets from ns2, due to redirection
+ expect="packets 0 bytes 0"
+ for dir in "in" "out" ; do
+
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns0$dir "$expect"
+ lret=1
+ fi
+ done
+
+ # ns0 should have seen packets from ns2, due to masquerade
+ expect="packets 1 bytes 84"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns0$dir "$expect"
+ lret=1
+ fi
+ done
+
+ ip netns exec ns0 nft delete table ip nat
+ if [ $? -ne 0 ]; then
+ echo "ERROR: Could not delete nat table" 1>&2
+ lret=1
+ fi
+
+ test $lret -eq 0 && echo "PASS: IP redirection for ns2"
+
+ return $lret
+}
+
+
+# ip netns exec ns0 ping -c 1 -q 10.0.$i.99
+for i in 0 1 2; do
+ip netns exec ns$i nft -f - <<EOF
+table inet filter {
+ counter ns0in {}
+ counter ns1in {}
+ counter ns2in {}
+
+ counter ns0out {}
+ counter ns1out {}
+ counter ns2out {}
+
+ counter ns0in6 {}
+ counter ns1in6 {}
+ counter ns2in6 {}
+
+ counter ns0out6 {}
+ counter ns1out6 {}
+ counter ns2out6 {}
+
+ map nsincounter {
+ type ipv4_addr : counter
+ elements = { 10.0.1.1 : "ns0in",
+ 10.0.2.1 : "ns0in",
+ 10.0.1.99 : "ns1in",
+ 10.0.2.99 : "ns2in" }
+ }
+
+ map nsincounter6 {
+ type ipv6_addr : counter
+ elements = { dead:1::1 : "ns0in6",
+ dead:2::1 : "ns0in6",
+ dead:1::99 : "ns1in6",
+ dead:2::99 : "ns2in6" }
+ }
+
+ map nsoutcounter {
+ type ipv4_addr : counter
+ elements = { 10.0.1.1 : "ns0out",
+ 10.0.2.1 : "ns0out",
+ 10.0.1.99: "ns1out",
+ 10.0.2.99: "ns2out" }
+ }
+
+ map nsoutcounter6 {
+ type ipv6_addr : counter
+ elements = { dead:1::1 : "ns0out6",
+ dead:2::1 : "ns0out6",
+ dead:1::99 : "ns1out6",
+ dead:2::99 : "ns2out6" }
+ }
+
+ chain input {
+ type filter hook input priority 0; policy accept;
+ counter name ip saddr map @nsincounter
+ icmpv6 type { "echo-request", "echo-reply" } counter name ip6 saddr map @nsincounter6
+ }
+ chain output {
+ type filter hook output priority 0; policy accept;
+ counter name ip daddr map @nsoutcounter
+ icmpv6 type { "echo-request", "echo-reply" } counter name ip6 daddr map @nsoutcounter6
+ }
+}
+EOF
+done
+
+sleep 3
+# test basic connectivity
+for i in 1 2; do
+ ip netns exec ns0 ping -c 1 -q 10.0.$i.99 > /dev/null
+ if [ $? -ne 0 ];then
+ echo "ERROR: Could not reach other namespace(s)" 1>&2
+ ret=1
+ fi
+
+ ip netns exec ns0 ping -c 1 -q dead:$i::99 > /dev/null
+ if [ $? -ne 0 ];then
+ echo "ERROR: Could not reach other namespace(s) via ipv6" 1>&2
+ ret=1
+ fi
+ check_counters ns$i
+ if [ $? -ne 0 ]; then
+ ret=1
+ fi
+
+ check_ns0_counters ns$i
+ if [ $? -ne 0 ]; then
+ ret=1
+ fi
+ reset_counters
+done
+
+if [ $ret -eq 0 ];then
+ echo "PASS: netns routing/connectivity: ns0 can reach ns1 and ns2"
+fi
+
+reset_counters
+test_local_dnat
+test_local_dnat6
+
+reset_counters
+test_masquerade
+test_masquerade6
+
+reset_counters
+test_redirect
+test_redirect6
+
+for i in 0 1 2; do ip netns del ns$i;done
+
+exit $ret
diff --git a/tools/testing/selftests/netfilter/nft_trans_stress.sh b/tools/testing/selftests/netfilter/nft_trans_stress.sh
new file mode 100755
index 000000000000..f1affd12c4b1
--- /dev/null
+++ b/tools/testing/selftests/netfilter/nft_trans_stress.sh
@@ -0,0 +1,78 @@
+#!/bin/bash
+#
+# This test is for stress-testing the nf_tables config plane path vs.
+# packet path processing: Make sure we never release rules that are
+# still visible to other cpus.
+#
+# set -e
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+testns=testns1
+tables="foo bar baz quux"
+
+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 $ksft_skip
+fi
+
+tmp=$(mktemp)
+
+for table in $tables; do
+ echo add table inet "$table" >> "$tmp"
+ echo flush table inet "$table" >> "$tmp"
+
+ echo "add chain inet $table INPUT { type filter hook input priority 0; }" >> "$tmp"
+ echo "add chain inet $table OUTPUT { type filter hook output priority 0; }" >> "$tmp"
+ for c in $(seq 1 400); do
+ chain=$(printf "chain%03u" "$c")
+ echo "add chain inet $table $chain" >> "$tmp"
+ done
+
+ for c in $(seq 1 400); do
+ chain=$(printf "chain%03u" "$c")
+ for BASE in INPUT OUTPUT; do
+ echo "add rule inet $table $BASE counter jump $chain" >> "$tmp"
+ done
+ echo "add rule inet $table $chain counter return" >> "$tmp"
+ done
+done
+
+ip netns add "$testns"
+ip -netns "$testns" link set lo up
+
+lscpu | grep ^CPU\(s\): | ( read cpu cpunum ;
+cpunum=$((cpunum-1))
+for i in $(seq 0 $cpunum);do
+ mask=$(printf 0x%x $((1<<$i)))
+ ip netns exec "$testns" taskset $mask ping -4 127.0.0.1 -fq > /dev/null &
+ ip netns exec "$testns" taskset $mask ping -6 ::1 -fq > /dev/null &
+done)
+
+sleep 1
+
+for i in $(seq 1 10) ; do ip netns exec "$testns" nft -f "$tmp" & done
+
+for table in $tables;do
+ randsleep=$((RANDOM%10))
+ sleep $randsleep
+ ip netns exec "$testns" nft delete table inet $table 2>/dev/null
+done
+
+randsleep=$((RANDOM%10))
+sleep $randsleep
+
+pkill -9 ping
+
+wait
+
+rm -f "$tmp"
+ip netns del "$testns"
diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c
index 85a78eba0a93..874972ccfc95 100644
--- a/tools/testing/selftests/x86/protection_keys.c
+++ b/tools/testing/selftests/x86/protection_keys.c
@@ -1129,6 +1129,21 @@ void test_pkey_syscalls_bad_args(int *ptr, u16 pkey)
pkey_assert(err);
}
+void become_child(void)
+{
+ pid_t forkret;
+
+ forkret = fork();
+ pkey_assert(forkret >= 0);
+ dprintf3("[%d] fork() ret: %d\n", getpid(), forkret);
+
+ if (!forkret) {
+ /* in the child */
+ return;
+ }
+ exit(0);
+}
+
/* Assumes that all pkeys other than 'pkey' are unallocated */
void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
{
@@ -1139,7 +1154,7 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
int nr_allocated_pkeys = 0;
int i;
- for (i = 0; i < NR_PKEYS*2; i++) {
+ for (i = 0; i < NR_PKEYS*3; i++) {
int new_pkey;
dprintf1("%s() alloc loop: %d\n", __func__, i);
new_pkey = alloc_pkey();
@@ -1150,21 +1165,27 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
if ((new_pkey == -1) && (errno == ENOSPC)) {
dprintf2("%s() failed to allocate pkey after %d tries\n",
__func__, nr_allocated_pkeys);
- break;
+ } else {
+ /*
+ * Ensure the number of successes never
+ * exceeds the number of keys supported
+ * in the hardware.
+ */
+ pkey_assert(nr_allocated_pkeys < NR_PKEYS);
+ allocated_pkeys[nr_allocated_pkeys++] = new_pkey;
}
- pkey_assert(nr_allocated_pkeys < NR_PKEYS);
- allocated_pkeys[nr_allocated_pkeys++] = new_pkey;
+
+ /*
+ * Make sure that allocation state is properly
+ * preserved across fork().
+ */
+ if (i == NR_PKEYS*2)
+ become_child();
}
dprintf3("%s()::%d\n", __func__, __LINE__);
/*
- * ensure it did not reach the end of the loop without
- * failure:
- */
- pkey_assert(i < NR_PKEYS*2);
-
- /*
* There are 16 pkeys supported in hardware. One is taken
* up for the default (0) and another can be taken up by
* an execute-only mapping. Ensure that we can allocate